Bump rollup from 4.54.0 to 4.55.1 in /web/frontend

Bumps [rollup](https://github.com/rollup/rollup) from 4.54.0 to 4.55.1.
- [Release notes](https://github.com/rollup/rollup/releases)
- [Changelog](https://github.com/rollup/rollup/blob/master/CHANGELOG.md)
- [Commits](https://github.com/rollup/rollup/compare/v4.54.0...v4.55.1)

---
updated-dependencies:
- dependency-name: rollup
  dependency-version: 4.55.1
  dependency-type: direct:development
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>

.github/dependabot.yml

@@ -0,0 +1,15 @@
+# To get started with Dependabot version updates, you'll need to specify which
+# package ecosystems to update and where the package manifests are located.
+# Please see the documentation for all configuration options:
+# https://docs.github.com/code-security/dependabot/dependabot-version-updates/configuration-options-for-the-dependabot.yml-file
+
+version: 2
+updates:
+  - package-ecosystem: "gomod"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+  - package-ecosystem: "npm"
+    directory: "/web/frontend"
+    schedule:
+      interval: "weekly"

.github/workflows/Release.yml

@@ -1,331 +0,0 @@
-# See: https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions
-
-# Workflow name
-name: Release
-
-# Run on tag push
-on:
- push:
-  tags:
-  - '**'
-
-jobs:
-
-  #
-  # Build on AlmaLinux 8.5 using golang-1.18.2
-  #
-  AlmaLinux-RPM-build:
-    runs-on: ubuntu-latest
-    # See: https://hub.docker.com/_/almalinux
-    container: almalinux:8.5
-    # The job outputs link to the outputs of the 'rpmrename' step
-    # Only job outputs can be used in child jobs
-    outputs:
-      rpm : ${{steps.rpmrename.outputs.RPM}}
-      srpm : ${{steps.rpmrename.outputs.SRPM}}
-    steps:
-
-    # Use dnf to install development packages
-    - name: Install development packages
-      run: |
-          dnf --assumeyes group install "Development Tools" "RPM Development Tools"
-          dnf --assumeyes install wget openssl-devel diffutils delve which npm
-          dnf --assumeyes install 'dnf-command(builddep)'
-
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: |
-          wget -q http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm \
-                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm \
-                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.18.2-1.module_el8.7.0+1173+5d37c0fd.noarch.rpm \
-                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm
-          rpm -i go*.rpm
-          npm install --global yarn rollup svelte rollup-plugin-svelte
-          #dnf --assumeyes builddep build/package/cc-backend.spec
-
-    - name: RPM build ClusterCockpit
-      id: rpmbuild
-      run: make RPM
-
-    # AlmaLinux 8.5 is a derivate of RedHat Enterprise Linux 8 (UBI8),
-    # so the created RPM both contain the substring 'el8' in the RPM file names
-    # This step replaces the substring 'el8' to 'alma85'. It uses the move operation
-    # because it is unclear whether the default AlmaLinux 8.5 container contains the 
-    # 'rename' command. This way we also get the new names for output.
-    - name: Rename RPMs (s/el8/alma85/)
-      id: rpmrename
-      run: |
-        OLD_RPM="${{steps.rpmbuild.outputs.RPM}}"
-        OLD_SRPM="${{steps.rpmbuild.outputs.SRPM}}"
-        NEW_RPM="${OLD_RPM/el8/alma85}"
-        NEW_SRPM=${OLD_SRPM/el8/alma85}
-        mv "${OLD_RPM}" "${NEW_RPM}"
-        mv "${OLD_SRPM}" "${NEW_SRPM}"
-        echo "::set-output name=SRPM::${NEW_SRPM}"
-        echo "::set-output name=RPM::${NEW_RPM}"
-
-    # See: https://github.com/actions/upload-artifact
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-backend RPM for AlmaLinux 8.5
-        path: ${{ steps.rpmrename.outputs.RPM }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-backend SRPM for AlmaLinux 8.5
-        path: ${{ steps.rpmrename.outputs.SRPM }}
-
-  #
-  # Build on UBI 8 using golang-1.18.2
-  #
-  UBI-8-RPM-build:
-    runs-on: ubuntu-latest
-    # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
-    container: registry.access.redhat.com/ubi8/ubi:8.5-226.1645809065
-    # The job outputs link to the outputs of the 'rpmbuild' step
-    outputs:
-      rpm : ${{steps.rpmbuild.outputs.RPM}}
-      srpm : ${{steps.rpmbuild.outputs.SRPM}}
-    steps:
-
-    # Use dnf to install development packages
-    - name: Install development packages
-      run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros rpm-build-libs rpm-libs gcc make python38 git wget openssl-devel diffutils delve which
-
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: |
-          wget -q http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm \
-                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm \
-                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.18.2-1.module_el8.7.0+1173+5d37c0fd.noarch.rpm \
-                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm
-          rpm -i go*.rpm
-          dnf --assumeyes --disableplugin=subscription-manager install npm
-          npm install --global yarn rollup svelte rollup-plugin-svelte
-          #dnf --assumeyes builddep build/package/cc-backend.spec
-
-    - name: RPM build ClusterCockpit
-      id: rpmbuild
-      run: make RPM
-
-    # See: https://github.com/actions/upload-artifact
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-backend RPM for UBI 8
-        path: ${{ steps.rpmbuild.outputs.RPM }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-backend SRPM for UBI 8
-        path: ${{ steps.rpmbuild.outputs.SRPM }}
-
-  #
-  # Build on Ubuntu 20.04 using official go 1.19.1 package
-  #
-  Ubuntu-focal-build:
-    runs-on: ubuntu-latest
-    container: ubuntu:20.04
-    # The job outputs link to the outputs of the 'debrename' step
-    # Only job outputs can be used in child jobs
-    outputs:
-      deb : ${{steps.debrename.outputs.DEB}}
-    steps:
-    # Use apt to install development packages
-    - name: Install development packages
-      run: |
-          apt update && apt --assume-yes upgrade
-          apt --assume-yes install build-essential sed git wget bash
-          apt --assume-yes install npm
-          npm install --global yarn rollup svelte rollup-plugin-svelte
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-    # Use official golang package
-    - name: Install Golang
-      run: |
-          wget -q https://go.dev/dl/go1.19.1.linux-amd64.tar.gz
-          tar -C /usr/local -xzf go1.19.1.linux-amd64.tar.gz
-          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
-          go version
-    - name: DEB build ClusterCockpit
-      id: dpkg-build
-      run: |
-          ls -la
-          pwd
-          env
-          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
-          git config --global --add safe.directory $(pwd)
-          make DEB
-    - name: Rename DEB (add '_ubuntu20.04')
-      id: debrename
-      run: |
-        OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev)
-        NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu20.04.deb"
-        mv "${{steps.dpkg-build.outputs.DEB}}" "${NEW_DEB_FILE}"
-        echo "::set-output name=DEB::${NEW_DEB_FILE}"
-    # See: https://github.com/actions/upload-artifact
-    - name: Save DEB as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-backend DEB for Ubuntu 20.04
-        path: ${{ steps.debrename.outputs.DEB }}
-
-  #
-  # Build on Ubuntu 20.04 using official go 1.19.1 package
-  #
-  Ubuntu-jammy-build:
-    runs-on: ubuntu-latest
-    container: ubuntu:22.04
-    # The job outputs link to the outputs of the 'debrename' step
-    # Only job outputs can be used in child jobs
-    outputs:
-      deb : ${{steps.debrename.outputs.DEB}}
-    steps:
-    # Use apt to install development packages
-    - name: Install development packages
-      run: |
-          apt update && apt --assume-yes upgrade
-          apt --assume-yes install build-essential sed git wget bash npm
-          npm install --global yarn rollup svelte rollup-plugin-svelte
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-    # Use official golang package
-    - name: Install Golang
-      run: |
-          wget -q https://go.dev/dl/go1.19.1.linux-amd64.tar.gz
-          tar -C /usr/local -xzf go1.19.1.linux-amd64.tar.gz
-          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
-          go version
-    - name: DEB build ClusterCockpit
-      id: dpkg-build
-      run: |
-          ls -la
-          pwd
-          env
-          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
-          git config --global --add safe.directory $(pwd)
-          make DEB
-    - name: Rename DEB (add '_ubuntu22.04')
-      id: debrename
-      run: |
-        OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev)
-        NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu22.04.deb"
-        mv "${{steps.dpkg-build.outputs.DEB}}" "${NEW_DEB_FILE}"
-        echo "::set-output name=DEB::${NEW_DEB_FILE}"
-    # See: https://github.com/actions/upload-artifact
-    - name: Save DEB as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-backend DEB for Ubuntu 22.04
-        path: ${{ steps.debrename.outputs.DEB }}
-
-  #
-  # Create release with fresh RPMs
-  #
-  Release:
-    runs-on: ubuntu-latest
-    # We need the RPMs, so add dependency
-    needs: [AlmaLinux-RPM-build, UBI-8-RPM-build, Ubuntu-focal-build, Ubuntu-jammy-build]
-
-    steps:
-    # See: https://github.com/actions/download-artifact
-    - name: Download AlmaLinux 8.5 RPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-backend RPM for AlmaLinux 8.5
-    - name: Download AlmaLinux 8.5 SRPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-backend SRPM for AlmaLinux 8.5
-    
-    - name: Download UBI 8 RPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-backend RPM for UBI 8
-    - name: Download UBI 8 SRPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-backend SRPM for UBI 8
-
-    - name: Download Ubuntu 20.04 DEB
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-backend DEB for Ubuntu 20.04
-
-    - name: Download Ubuntu 22.04 DEB
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-backend DEB for Ubuntu 22.04
-
-    # The download actions do not publish the name of the downloaded file,
-    # so we re-use the job outputs of the parent jobs. The files are all
-    # downloaded to the current folder.
-    # The gh-release action afterwards does not accept file lists but all
-    # files have to be listed at 'files'. The step creates one output per
-    # RPM package (2 per distro)
-    - name: Set RPM variables
-      id: files
-      run: |
-        ALMA_85_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
-        ALMA_85_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
-        UBI_8_RPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.rpm}}")
-        UBI_8_SRPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.srpm}}")
-        U_2004_DEB=$(basename "${{ needs.Ubuntu-focal-build.outputs.deb}}")
-        U_2204_DEB=$(basename "${{ needs.Ubuntu-jammy-build.outputs.deb}}")
-        echo "ALMA_85_RPM::${ALMA_85_RPM}"
-        echo "ALMA_85_SRPM::${ALMA_85_SRPM}"
-        echo "UBI_8_RPM::${UBI_8_RPM}"
-        echo "UBI_8_SRPM::${UBI_8_SRPM}"
-        echo "U_2004_DEB::${U_2004_DEB}"
-        echo "U_2204_DEB::${U_2204_DEB}"
-        echo "::set-output name=ALMA_85_RPM::${ALMA_85_RPM}"
-        echo "::set-output name=ALMA_85_SRPM::${ALMA_85_SRPM}"
-        echo "::set-output name=UBI_8_RPM::${UBI_8_RPM}"
-        echo "::set-output name=UBI_8_SRPM::${UBI_8_SRPM}"
-        echo "::set-output name=U_2004_DEB::${U_2004_DEB}"
-        echo "::set-output name=U_2204_DEB::${U_2204_DEB}"
-
-    # See: https://github.com/softprops/action-gh-release
-    - name: Release
-      uses: softprops/action-gh-release@v1
-      if: startsWith(github.ref, 'refs/tags/')
-      with:
-        name: cc-backend-${{github.ref_name}}
-        files: |
-         ${{ steps.files.outputs.ALMA_85_RPM }}
-         ${{ steps.files.outputs.ALMA_85_SRPM }}
-         ${{ steps.files.outputs.UBI_8_RPM }}
-         ${{ steps.files.outputs.UBI_8_SRPM }}
-         ${{ steps.files.outputs.U_2004_DEB }}
-         ${{ steps.files.outputs.U_2204_DEB }}

.github/workflows/test.yml

@@ -7,7 +7,7 @@ jobs:
       - name: Install Go
         uses: actions/setup-go@v4
         with:
-          go-version: 1.22.x
+          go-version: 1.25.x
       - name: Checkout code
         uses: actions/checkout@v3
       - name: Build, Vet & Test

.gitignore

@@ -1,14 +1,20 @@
 /cc-backend
 /.env
 /config.json
+/uiConfig.json
 
 /var/job-archive
 /var/machine-state
-/var/job.db-shm
-/var/job.db-wal
+/var/*.db-shm
+/var/*.db-wal
 /var/*.db
 /var/*.txt
 
+/var/checkpoints*
+
+migrateTimestamps.pl
+test_ccms_write_api*
+
 /web/frontend/public/build
 /web/frontend/node_modules
 
@@ -21,3 +27,6 @@
 /.vscode/*
 dist/
 *.db
+.idea
+tools/archive-migration/archive-migration
+tools/archive-manager/archive-manager

AGENTS.md

@@ -0,0 +1,26 @@
+# ClusterCockpit Backend - Agent Guidelines
+
+## Build/Test Commands
+
+- Build: `make` or `go build ./cmd/cc-backend`
+- Run all tests: `make test` (runs: `go clean -testcache && go build ./... && go vet ./... && go test ./...`)
+- Run single test: `go test -run TestName ./path/to/package`
+- Run single test file: `go test ./path/to/package -run TestName`
+- Frontend build: `cd web/frontend && npm install && npm run build`
+- Generate GraphQL: `make graphql` (uses gqlgen)
+- Generate Swagger: `make swagger` (uses swaggo/swag)
+
+## Code Style
+
+- **Formatting**: Use `gofumpt` for all Go files (strict requirement)
+- **Copyright header**: All files must include copyright header (see existing files)
+- **Package docs**: Document packages with comprehensive package-level comments explaining purpose, usage, configuration
+- **Imports**: Standard library first, then external packages, then internal packages (grouped with blank lines)
+- **Naming**: Use camelCase for private, PascalCase for exported; descriptive names (e.g., `JobRepository`, `handleError`)
+- **Error handling**: Return errors, don't panic; use custom error types where appropriate; log with cclog package
+- **Logging**: Use `cclog` package (e.g., `cclog.Errorf()`, `cclog.Warnf()`, `cclog.Debugf()`)
+- **Testing**: Use standard `testing` package; use `testify/assert` for assertions; name tests `TestFunctionName`
+- **Comments**: Document all exported functions/types with godoc-style comments
+- **Structs**: Document fields with inline comments, especially for complex configurations
+- **HTTP handlers**: Return proper status codes; use `handleError()` helper for consistent error responses
+- **JSON**: Use struct tags for JSON marshaling; `DisallowUnknownFields()` for strict decoding

Makefile

@@ -1,8 +1,6 @@
 TARGET = ./cc-backend
-VAR = ./var
-CFG = config.json .env
 FRONTEND = ./web/frontend
-VERSION = 1.4.3
+VERSION = 1.4.4
 GIT_HASH := $(shell git rev-parse --short HEAD || echo 'development')
 CURRENT_TIME = $(shell date +"%Y-%m-%d:T%H:%M:%S")
 LD_FLAGS = '-s -X main.date=${CURRENT_TIME} -X main.version=${VERSION} -X main.commit=${GIT_HASH}'
@@ -42,7 +40,7 @@ SVELTE_SRC = $(wildcard $(FRONTEND)/src/*.svelte)                 \
 
 .NOTPARALLEL:
 
-$(TARGET): $(VAR) $(CFG) $(SVELTE_TARGETS)
+$(TARGET): $(SVELTE_TARGETS)
 	$(info ===>  BUILD cc-backend)
 	@go build -ldflags=${LD_FLAGS} ./cmd/cc-backend
 
@@ -52,12 +50,12 @@ frontend:
 
 swagger:
 	$(info ===>  GENERATE swagger)
-	@go run github.com/swaggo/swag/cmd/swag init -d ./internal/api,./pkg/schema -g rest.go -o ./api
+	@go tool github.com/swaggo/swag/cmd/swag init  --parseDependency -d ./internal/api -g rest.go -o ./api
 	@mv ./api/docs.go ./internal/api/docs.go
 
 graphql:
 	$(info ===>  GENERATE graphql)
-	@go run github.com/99designs/gqlgen
+	@go tool github.com/99designs/gqlgen
 
 clean:
 	$(info ===>  CLEAN)
@@ -68,7 +66,7 @@ distclean:
 	@$(MAKE) clean
 	$(info ===>  DISTCLEAN)
 	@rm -rf $(FRONTEND)/node_modules
-	@rm -rf $(VAR)
+	@rm -rf ./var
 
 test:
 	$(info ===>  TESTING)
@@ -84,14 +82,6 @@ tags:
 $(VAR):
 	@mkdir -p $(VAR)
 
-config.json:
-	$(info ===>  Initialize config.json file)
-	@cp configs/config.json config.json
-
-.env:
-	$(info ===>  Initialize .env file)
-	@cp configs/env-template.txt .env
-
 $(SVELTE_TARGETS): $(SVELTE_SRC)
 	$(info ===>  BUILD frontend)
 	cd web/frontend && npm install && npm run build

README.md

@@ -1,5 +1,8 @@
 # NOTE
 
+While we do our best to keep the master branch in a usable state, there is no guarantee the master branch works.
+Please do not use it for production!
+
 Please have a look at the [Release
 Notes](https://github.com/ClusterCockpit/cc-backend/blob/master/ReleaseNotes.md)
 for breaking changes!
@@ -28,7 +31,7 @@ Layout and styling are based on [Bootstrap 5](https://getbootstrap.com/) using
 
 The backend uses [SQLite 3](https://sqlite.org/) as a relational SQL database by
 default. Optionally it can use a MySQL/MariaDB database server. While there are
-metric data  backends for the InfluxDB and Prometheus time series databases, the
+metric data backends for the InfluxDB and Prometheus time series databases, the
 only tested and supported setup is to use cc-metric-store as the metric data
 backend. Documentation on how to integrate ClusterCockpit with other time series
 databases will be added in the future.
@@ -69,7 +72,7 @@ You can also try the demo using the latest release binary.
 Create a folder and put the release binary `cc-backend` into this folder.
 Execute the following steps:
 
-``` shell
+```shell
 ./cc-backend -init
 vim config.json (Add a second cluster entry and name the clusters alex and fritz)
 wget https://hpc-mover.rrze.uni-erlangen.de/HPC-Data/0x7b58aefb/eig7ahyo6fo2bais0ephuf2aitohv1ai/job-archive-demo.tar
@@ -88,11 +91,11 @@ Analysis, Systems and Status views).
 There is a Makefile to automate the build of cc-backend. The Makefile supports
 the following targets:
 
-* `make`: Initialize `var` directory and build svelte frontend and backend
-binary. Note that there is no proper prerequisite handling. Any change of
-frontend source files will result in a complete rebuild.
-* `make clean`: Clean go build cache and remove binary.
-* `make test`: Run the tests that are also run in the GitHub workflow setup.
+- `make`: Initialize `var` directory and build svelte frontend and backend
+  binary. Note that there is no proper prerequisite handling. Any change of
+  frontend source files will result in a complete rebuild.
+- `make clean`: Clean go build cache and remove binary.
+- `make test`: Run the tests that are also run in the GitHub workflow setup.
 
 A common workflow for setting up cc-backend from scratch is:
 
@@ -128,41 +131,41 @@ ln -s <your-existing-job-archive> ./var/job-archive
 
 ## Project file structure
 
-* [`api/`](https://github.com/ClusterCockpit/cc-backend/tree/master/api)
-contains the API schema files for the REST and GraphQL APIs. The REST API is
-documented in the OpenAPI 3.0 format in
-[./api/openapi.yaml](./api/openapi.yaml).
-* [`cmd/cc-backend`](https://github.com/ClusterCockpit/cc-backend/tree/master/cmd/cc-backend)
-contains `main.go` for the main application.
-* [`configs/`](https://github.com/ClusterCockpit/cc-backend/tree/master/configs)
-contains documentation about configuration and command line options and required
-environment variables. A sample configuration file is provided.
-* [`docs/`](https://github.com/ClusterCockpit/cc-backend/tree/master/docs)
-contains more in-depth documentation.
-* [`init/`](https://github.com/ClusterCockpit/cc-backend/tree/master/init)
-contains an example of setting up systemd for production use.
-* [`internal/`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal)
-contains library source code that is not intended for use by others.
-* [`pkg/`](https://github.com/ClusterCockpit/cc-backend/tree/master/pkg)
-contains Go packages that can be used by other projects.
-* [`tools/`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools)
-Additional command line helper tools.
-  * [`archive-manager`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/archive-manager)
-  Commands for getting infos about and existing job archive.
-  * [`convert-pem-pubkey`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/convert-pem-pubkey)
-  Tool to convert external pubkey for use in `cc-backend`.
-  * [`gen-keypair`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/gen-keypair)
-  contains a small application to generate a compatible JWT keypair. You find
-  documentation on how to use it
-  [here](https://github.com/ClusterCockpit/cc-backend/blob/master/docs/JWT-Handling.md).
-* [`web/`](https://github.com/ClusterCockpit/cc-backend/tree/master/web)
-Server-side templates and frontend-related files:
-  * [`frontend`](https://github.com/ClusterCockpit/cc-backend/tree/master/web/frontend)
-  Svelte components and static assets for the frontend UI
-  * [`templates`](https://github.com/ClusterCockpit/cc-backend/tree/master/web/templates)
-  Server-side Go templates
-* [`gqlgen.yml`](https://github.com/ClusterCockpit/cc-backend/blob/master/gqlgen.yml)
-Configures the behaviour and generation of
-[gqlgen](https://github.com/99designs/gqlgen).
-* [`startDemo.sh`](https://github.com/ClusterCockpit/cc-backend/blob/master/startDemo.sh)
-is a shell script that sets up demo data, and builds and starts `cc-backend`.
+- [`api/`](https://github.com/ClusterCockpit/cc-backend/tree/master/api)
+  contains the API schema files for the REST and GraphQL APIs. The REST API is
+  documented in the OpenAPI 3.0 format in
+  [./api/openapi.yaml](./api/openapi.yaml).
+- [`cmd/cc-backend`](https://github.com/ClusterCockpit/cc-backend/tree/master/cmd/cc-backend)
+  contains `main.go` for the main application.
+- [`configs/`](https://github.com/ClusterCockpit/cc-backend/tree/master/configs)
+  contains documentation about configuration and command line options and required
+  environment variables. A sample configuration file is provided.
+- [`docs/`](https://github.com/ClusterCockpit/cc-backend/tree/master/docs)
+  contains more in-depth documentation.
+- [`init/`](https://github.com/ClusterCockpit/cc-backend/tree/master/init)
+  contains an example of setting up systemd for production use.
+- [`internal/`](https://github.com/ClusterCockpit/cc-backend/tree/master/internal)
+  contains library source code that is not intended for use by others.
+- [`pkg/`](https://github.com/ClusterCockpit/cc-backend/tree/master/pkg)
+  contains Go packages that can be used by other projects.
+- [`tools/`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools)
+  Additional command line helper tools.
+  - [`archive-manager`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/archive-manager)
+    Commands for getting infos about and existing job archive.
+  - [`convert-pem-pubkey`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/convert-pem-pubkey)
+    Tool to convert external pubkey for use in `cc-backend`.
+  - [`gen-keypair`](https://github.com/ClusterCockpit/cc-backend/tree/master/tools/gen-keypair)
+    contains a small application to generate a compatible JWT keypair. You find
+    documentation on how to use it
+    [here](https://github.com/ClusterCockpit/cc-backend/blob/master/docs/JWT-Handling.md).
+- [`web/`](https://github.com/ClusterCockpit/cc-backend/tree/master/web)
+  Server-side templates and frontend-related files:
+  - [`frontend`](https://github.com/ClusterCockpit/cc-backend/tree/master/web/frontend)
+    Svelte components and static assets for the frontend UI
+  - [`templates`](https://github.com/ClusterCockpit/cc-backend/tree/master/web/templates)
+    Server-side Go templates
+- [`gqlgen.yml`](https://github.com/ClusterCockpit/cc-backend/blob/master/gqlgen.yml)
+  Configures the behaviour and generation of
+  [gqlgen](https://github.com/99designs/gqlgen).
+- [`startDemo.sh`](https://github.com/ClusterCockpit/cc-backend/blob/master/startDemo.sh)
+  is a shell script that sets up demo data, and builds and starts `cc-backend`.

ReleaseNotes.md

@@ -1,4 +1,4 @@
-# `cc-backend` version 1.4.3
+# `cc-backend` version 1.4.4
 
 Supports job archive version 2 and database version 8.
 
@@ -6,6 +6,20 @@ This is a bug fix release of `cc-backend`, the API backend and frontend
 implementation of ClusterCockpit.
 For release specific notes visit the [ClusterCockpit Documentation](https://clusterockpit.org/docs/release/).
 
+## Breaking changes
+
+The option `apiAllowedIPs` is now a required configuration attribute in
+`config.json`. This option restricts access to the admin API.
+
+To retain the previous behavior that the API is per default accessible from
+everywhere set:
+
+```json
+  "apiAllowedIPs": [
+    "*"
+  ]
+```
+
 ## Breaking changes for minor release 1.4.x
 
 - You need to perform a database migration. Depending on your database size the
@@ -22,21 +36,7 @@ For release specific notes visit the [ClusterCockpit Documentation](https://clus
 
 ## New features
 
-- Detailed Node List
-  - Adds new routes `/systems/list/$cluster` and `/systems/list/$cluster/$subcluster`
-  - Displays live, scoped metric data requested from the nodes indepenent of jobs
-- Color Blind Mode
-  - Set on a per-user basis in options
-  - Applies to plot data, plot background color, statsseries colors, roofline timescale
-- Job-View metric selection is now persisted based on the jobs subcluster.
-Helpful for heterogeneous subcluster configurations.
-- Histogram Bin Select in User-View
-  - Metric-Histograms: `10 Bins` now default, selectable options `20, 50, 100`
-  - Job-Duration-Histogram: `48h in 1h Bins` now default, selectable options:
-    - `60 minutes in 1 minute Bins`
-    - `12 hours in 10 minute Bins`
-    - `3 days in 6 hour Bins`
-    - `7 days in 12 hour Bins`
+- Enable to delete tags from the web interface
 
 ## Known issues
 

api/schema.graphqls

@@ -4,61 +4,88 @@ scalar Any
 scalar NullableFloat
 scalar MetricScope
 scalar JobState
+scalar SchedulerState
+scalar MonitoringState
+
+type Node {
+  id: ID!
+  hostname: String!
+  cluster: String!
+  subCluster: String!
+  jobsRunning: Int!
+  cpusAllocated: Int
+  memoryAllocated: Int
+  gpusAllocated: Int
+  schedulerState: SchedulerState!
+  healthState: MonitoringState!
+  metaData: Any
+}
+
+type NodeStates {
+  state: String!
+  count: Int!
+}
+
+type NodeStatesTimed {
+  state: String!
+  counts: [Int!]!
+  times: [Int!]!
+}
 
 type Job {
-  id:               ID!
-  jobId:            Int!
-  user:             String!
-  project:          String!
-  cluster:          String!
-  subCluster:       String!
-  startTime:        Time!
-  duration:         Int!
-  walltime:         Int!
-  numNodes:         Int!
-  numHWThreads:     Int!
-  numAcc:           Int!
-  energy:           Float!
-  SMT:              Int!
-  exclusive:        Int!
-  partition:        String!
-  arrayJobId:       Int!
+  id: ID!
+  jobId: Int!
+  user: String!
+  project: String!
+  cluster: String!
+  subCluster: String!
+  startTime: Time!
+  duration: Int!
+  walltime: Int!
+  numNodes: Int!
+  numHWThreads: Int!
+  numAcc: Int!
+  energy: Float!
+  SMT: Int!
+  shared: String!
+  partition: String!
+  arrayJobId: Int!
   monitoringStatus: Int!
-  state:            JobState!
-  tags:             [Tag!]!
-  resources:        [Resource!]!
-  concurrentJobs:   JobLinkResultList
-  footprint:        [FootprintValue]
-  energyFootprint:  [EnergyFootprintValue]
-  metaData:         Any
-  userData:         User
+  state: JobState!
+  tags: [Tag!]!
+  resources: [Resource!]!
+  concurrentJobs: JobLinkResultList
+  footprint: [FootprintValue]
+  energyFootprint: [EnergyFootprintValue]
+  metaData: Any
+  userData: User
 }
 
 type JobLink {
-  id:               ID!
-  jobId:            Int!
+  id: ID!
+  jobId: Int!
 }
 
 type Cluster {
-  name:         String!
-  partitions:   [String!]!        # Slurm partitions
-  subClusters:  [SubCluster!]!    # Hardware partitions/subclusters
+  name: String!
+  partitions: [String!]! # Slurm partitions
+  subClusters: [SubCluster!]! # Hardware partitions/subclusters
 }
 
 type SubCluster {
-  name:            String!
-  nodes:           String!
-  numberOfNodes:   Int!
-  processorType:   String!
-  socketsPerNode:  Int!
-  coresPerSocket:  Int!
-  threadsPerCore:  Int!
-  flopRateScalar:  MetricValue!
-  flopRateSimd:    MetricValue!
+  name: String!
+  nodes: String!
+  numberOfNodes: Int!
+  processorType: String!
+  socketsPerNode: Int!
+  coresPerSocket: Int!
+  threadsPerCore: Int!
+  flopRateScalar: MetricValue!
+  flopRateSimd: MetricValue!
   memoryBandwidth: MetricValue!
-  topology:        Topology!
-  metricConfig:    [MetricConfig!]!
-  footprint:       [String!]!
+  topology: Topology!
+  metricConfig: [MetricConfig!]!
+  footprint: [String!]!
 }
 
 type FootprintValue {
@@ -80,80 +107,119 @@ type MetricValue {
 }
 
 type Topology {
-  node:         [Int!]
-  socket:       [[Int!]!]
+  node: [Int!]
+  socket: [[Int!]!]
   memoryDomain: [[Int!]!]
-  die:          [[Int!]!]
-  core:         [[Int!]!]
+  die: [[Int!]!]
+  core: [[Int!]!]
   accelerators: [Accelerator!]
 }
 
 type Accelerator {
-  id:    String!
-  type:  String!
+  id: String!
+  type: String!
   model: String!
 }
 
 type SubClusterConfig {
-  name:    String!
-  peak:    Float
-  normal:  Float
+  name: String!
+  peak: Float
+  normal: Float
   caution: Float
-  alert:   Float
-  remove:  Boolean
+  alert: Float
+  remove: Boolean
 }
 
 type MetricConfig {
-  name:        String!
-  unit:        Unit!
-  scope:       MetricScope!
+  name: String!
+  unit: Unit!
+  scope: MetricScope!
   aggregation: String!
-  timestep:    Int!
-  peak:    Float!
-  normal:  Float
+  timestep: Int!
+  peak: Float!
+  normal: Float
   caution: Float!
-  alert:   Float!
+  alert: Float!
   lowerIsBetter: Boolean
   subClusters: [SubClusterConfig!]!
 }
 
 type Tag {
-  id:   ID!
+  id: ID!
   type: String!
   name: String!
   scope: String!
 }
 
 type Resource {
-  hostname:      String!
-  hwthreads:     [Int!]
-  accelerators:  [String!]
+  hostname: String!
+  hwthreads: [Int!]
+  accelerators: [String!]
   configuration: String
 }
 
 type JobMetricWithName {
-  name:   String!
-  scope:  MetricScope!
+  name: String!
+  scope: MetricScope!
   metric: JobMetric!
 }
 
-type JobMetricStatWithName {
-  name:   String!
-  stats:  MetricStatistics!
+type ClusterMetricWithName {
+  name: String!
+  unit: Unit
+  timestep: Int!
+  data: [NullableFloat!]!
 }
 
 type JobMetric {
-  unit:             Unit
-  timestep:         Int!
-  series:           [Series!]
+  unit: Unit
+  timestep: Int!
+  series: [Series!]
   statisticsSeries: StatsSeries
 }
 
 type Series {
-  hostname:   String!
-  id:         String
+  hostname: String!
+  id: String
   statistics: MetricStatistics
-  data:       [NullableFloat!]!
+  data: [NullableFloat!]!
+}
+
+type StatsSeries {
+  mean: [NullableFloat!]!
+  median: [NullableFloat!]!
+  min: [NullableFloat!]!
+  max: [NullableFloat!]!
+}
+
+type NamedStatsWithScope {
+  name: String!
+  scope: MetricScope!
+  stats: [ScopedStats!]!
+}
+
+type ScopedStats {
+  hostname: String!
+  id: String
+  data: MetricStatistics!
+}
+
+type JobStats {
+  id: Int!
+  jobId: String!
+  startTime: Int!
+  duration: Int!
+  cluster: String!
+  subCluster: String!
+  numNodes: Int!
+  numHWThreads: Int
+  numAccelerators: Int
+  stats: [NamedStats!]!
+}
+
+type NamedStats {
+  name: String!
+  data: MetricStatistics!
 }
 
 type Unit {
@@ -167,21 +233,14 @@ type MetricStatistics {
   max: Float!
 }
 
-type StatsSeries {
-  mean:   [NullableFloat!]!
-  median: [NullableFloat!]!
-  min:    [NullableFloat!]!
-  max:    [NullableFloat!]!
-}
-
 type MetricFootprints {
   metric: String!
-  data:   [NullableFloat!]!
+  data: [NullableFloat!]!
 }
 
 type Footprints {
   timeWeights: TimeWeights!
-  metrics:   [MetricFootprints!]!
+  metrics: [MetricFootprints!]!
 }
 
 type TimeWeights {
@@ -190,20 +249,41 @@ type TimeWeights {
   coreHours: [NullableFloat!]!
 }
 
-enum Aggregate { USER, PROJECT, CLUSTER }
-enum SortByAggregate { TOTALWALLTIME, TOTALJOBS, TOTALNODES, TOTALNODEHOURS, TOTALCORES, TOTALCOREHOURS, TOTALACCS, TOTALACCHOURS }
+enum Aggregate {
+  USER
+  PROJECT
+  CLUSTER
+  SUBCLUSTER
+}
+enum SortByAggregate {
+  TOTALWALLTIME
+  TOTALJOBS
+  TOTALUSERS
+  TOTALNODES
+  TOTALNODEHOURS
+  TOTALCORES
+  TOTALCOREHOURS
+  TOTALACCS
+  TOTALACCHOURS
+}
 
 type NodeMetrics {
-  host:       String!
+  host: String!
+  state: String!
   subCluster: String!
-  metrics:    [JobMetricWithName!]!
+  metrics: [JobMetricWithName!]!
+}
+
+type ClusterMetrics {
+  nodeCount: Int!
+  metrics: [ClusterMetricWithName!]!
 }
 
 type NodesResultList {
-  items:  [NodeMetrics!]!
+  items: [NodeMetrics!]!
   offset: Int
-  limit:  Int
-  count:  Int
+  limit: Int
+  count: Int
   totalNodes: Int
   hasNextPage: Boolean
 }
@@ -222,14 +302,14 @@ type GlobalMetricListItem {
 }
 
 type Count {
-  name:  String!
+  name: String!
   count: Int!
 }
 
 type User {
   username: String!
-  name:     String!
-  email:    String!
+  name: String!
+  email: String!
 }
 
 input MetricStatItem {
@@ -238,25 +318,92 @@ input MetricStatItem {
 }
 
 type Query {
-  clusters:     [Cluster!]!   # List of all clusters
-  tags:         [Tag!]!       # List of all tags
-  globalMetrics:   [GlobalMetricListItem!]!
+  clusters: [Cluster!]! # List of all clusters
+  tags: [Tag!]! # List of all tags
+  globalMetrics: [GlobalMetricListItem!]!
 
   user(username: String!): User
   allocatedNodes(cluster: String!): [Count!]!
 
+  ## Node Queries New
+  node(id: ID!): Node
+  nodes(filter: [NodeFilter!], order: OrderByInput): NodeStateResultList!
+  nodeStates(filter: [NodeFilter!]): [NodeStates!]!
+  nodeStatesTimed(filter: [NodeFilter!], type: String!): [NodeStatesTimed!]!
+
   job(id: ID!): Job
-  jobMetrics(id: ID!, metrics: [String!], scopes: [MetricScope!], resolution: Int): [JobMetricWithName!]!
-  jobMetricStats(id: ID!, metrics: [String!]): [JobMetricStatWithName!]!
+  jobMetrics(
+    id: ID!
+    metrics: [String!]
+    scopes: [MetricScope!]
+    resolution: Int
+  ): [JobMetricWithName!]!
+
+  jobStats(id: ID!, metrics: [String!]): [NamedStats!]!
+
+  scopedJobStats(
+    id: ID!
+    metrics: [String!]
+    scopes: [MetricScope!]
+  ): [NamedStatsWithScope!]!
+
+  jobs(
+    filter: [JobFilter!]
+    page: PageRequest
+    order: OrderByInput
+  ): JobResultList!
+
+  jobsStatistics(
+    filter: [JobFilter!]
+    metrics: [String!]
+    page: PageRequest
+    sortBy: SortByAggregate
+    groupBy: Aggregate
+    numDurationBins: String
+    numMetricBins: Int
+  ): [JobsStatistics!]!
+
+  jobsMetricStats(filter: [JobFilter!], metrics: [String!]): [JobStats!]!
   jobsFootprints(filter: [JobFilter!], metrics: [String!]!): Footprints
 
-  jobs(filter: [JobFilter!], page: PageRequest, order: OrderByInput): JobResultList!
-  jobsStatistics(filter: [JobFilter!], metrics: [String!], page: PageRequest, sortBy: SortByAggregate, groupBy: Aggregate, numDurationBins: String, numMetricBins: Int): [JobsStatistics!]!
+  rooflineHeatmap(
+    filter: [JobFilter!]!
+    rows: Int!
+    cols: Int!
+    minX: Float!
+    minY: Float!
+    maxX: Float!
+    maxY: Float!
+  ): [[Float!]!]!
 
-  rooflineHeatmap(filter: [JobFilter!]!, rows: Int!, cols: Int!, minX: Float!, minY: Float!, maxX: Float!, maxY: Float!): [[Float!]!]!
+  nodeMetrics(
+    cluster: String!
+    nodes: [String!]
+    scopes: [MetricScope!]
+    metrics: [String!]
+    from: Time!
+    to: Time!
+  ): [NodeMetrics!]!
 
-  nodeMetrics(cluster: String!, nodes: [String!], scopes: [MetricScope!], metrics: [String!], from: Time!, to: Time!): [NodeMetrics!]!
-  nodeMetricsList(cluster: String!, subCluster: String!, nodeFilter: String!, scopes: [MetricScope!], metrics: [String!], from: Time!, to: Time!, page: PageRequest, resolution: Int): NodesResultList!
+  nodeMetricsList(
+    cluster: String!
+    subCluster: String!
+    stateFilter: String!
+    nodeFilter: String!
+    scopes: [MetricScope!]
+    metrics: [String!]
+    from: Time!
+    to: Time!
+    page: PageRequest
+    resolution: Int
+  ): NodesResultList!
+
+  clusterMetrics(
+    cluster: String!
+    metrics: [String!]
+    from: Time!
+    to: Time!
+  ): ClusterMetrics!
 }
 
 type Mutation {
@@ -264,41 +411,59 @@ type Mutation {
   deleteTag(id: ID!): ID!
   addTagsToJob(job: ID!, tagIds: [ID!]!): [Tag!]!
   removeTagsFromJob(job: ID!, tagIds: [ID!]!): [Tag!]!
+  removeTagFromList(tagIds: [ID!]!): [Int!]!
 
   updateConfiguration(name: String!, value: String!): String
 }
 
-type IntRangeOutput { from: Int!, to: Int! }
-type TimeRangeOutput { range: String, from: Time!, to: Time! }
+type IntRangeOutput {
+  from: Int!
+  to: Int!
+}
+type TimeRangeOutput {
+  range: String
+  from: Time!
+  to: Time!
+}
+
+input NodeFilter {
+  hostname: StringInput
+  cluster: StringInput
+  subcluster: StringInput
+  schedulerState: SchedulerState
+  healthState: MonitoringState
+  timeStart: Int
+}
 
 input JobFilter {
-  tags:        [ID!]
-  jobId:       StringInput
-  arrayJobId:  Int
-  user:        StringInput
-  project:     StringInput
-  jobName:     StringInput
-  cluster:     StringInput
-  partition:   StringInput
-  duration:    IntRange
-  energy:      FloatRange
+  tags: [ID!]
+  dbId: [ID!]
+  jobId: StringInput
+  arrayJobId: Int
+  user: StringInput
+  project: StringInput
+  jobName: StringInput
+  cluster: StringInput
+  partition: StringInput
+  duration: IntRange
+  energy: FloatRange
 
   minRunningFor: Int
 
-  numNodes:        IntRange
+  numNodes: IntRange
   numAccelerators: IntRange
-  numHWThreads:    IntRange
+  numHWThreads: IntRange
 
-  startTime:   TimeRange
-  state:       [JobState!]
+  startTime: TimeRange
+  state: [JobState!]
   metricStats: [MetricStatItem!]
-  exclusive:     Int
-  node:    StringInput
+  shared: String
+  node: StringInput
 }
 
 input OrderByInput {
   field: String!
-  type: String!,
+  type: String!
   order: SortDirectionEnum! = ASC
 }
 
@@ -308,34 +473,46 @@ enum SortDirectionEnum {
 }
 
 input StringInput {
-  eq:         String
-  neq:        String
-  contains:   String
+  eq: String
+  neq: String
+  contains: String
   startsWith: String
-  endsWith:   String
-  in:         [String!]
+  endsWith: String
+  in: [String!]
 }
 
-input IntRange   { from: Int!, to: Int! }
-input TimeRange  { range: String, from: Time, to: Time }
+input IntRange {
+  from: Int!
+  to: Int!
+}
+input TimeRange {
+  range: String
+  from: Time
+  to: Time
+}
 
 input FloatRange {
   from: Float!
   to: Float!
 }
 
+type NodeStateResultList {
+  items: [Node!]!
+  count: Int
+}
+
 type JobResultList {
-  items:  [Job!]!
+  items: [Job!]!
   offset: Int
-  limit:  Int
-  count:  Int
+  limit: Int
+  count: Int
   hasNextPage: Boolean
 }
 
 type JobLinkResultList {
   listQuery: String
-  items:  [JobLink!]!
-  count:  Int
+  items: [JobLink!]!
+  count: Int
 }
 
 type HistoPoint {
@@ -357,27 +534,28 @@ type MetricHistoPoint {
   max: Int
 }
 
-type JobsStatistics  {
-  id:             ID!            # If `groupBy` was used, ID of the user/project/cluster
-  name:           String!        # if User-Statistics: Given Name of Account (ID) Owner
-  totalJobs:      Int!           # Number of jobs
-  runningJobs:    Int!           # Number of running jobs
-  shortJobs:      Int!           # Number of jobs with a duration of less than duration
-  totalWalltime:  Int!           # Sum of the duration of all matched jobs in hours
-  totalNodes:     Int!           # Sum of the nodes of all matched jobs
-  totalNodeHours: Int!           # Sum of the node hours of all matched jobs
-  totalCores:     Int!           # Sum of the cores of all matched jobs
-  totalCoreHours: Int!           # Sum of the core hours of all matched jobs
-  totalAccs:      Int!         # Sum of the accs of all matched jobs
-  totalAccHours:  Int!           # Sum of the gpu hours of all matched jobs
-  histDuration:   [HistoPoint!]! # value: hour, count: number of jobs with a rounded duration of value
-  histNumNodes:   [HistoPoint!]! # value: number of nodes, count: number of jobs with that number of nodes
-  histNumCores:   [HistoPoint!]! # value: number of cores, count: number of jobs with that number of cores
-  histNumAccs:    [HistoPoint!]! # value: number of accs, count: number of jobs with that number of accs
-  histMetrics:    [MetricHistoPoints!]! # metric: metricname, data array of histopoints: value: metric average bin, count: number of jobs with that metric average
+type JobsStatistics {
+  id: ID! # If `groupBy` was used, ID of the user/project/cluster/subcluster
+  name: String! # if User-Statistics: Given Name of Account (ID) Owner
+  totalUsers: Int! # if *not* User-Statistics: Number of active users (based on running jobs)
+  totalJobs: Int! # Number of jobs
+  runningJobs: Int! # Number of running jobs
+  shortJobs: Int! # Number of jobs with a duration of less than config'd ShortRunningJobsDuration
+  totalWalltime: Int! # Sum of the duration of all matched jobs in hours
+  totalNodes: Int! # Sum of the nodes of all matched jobs
+  totalNodeHours: Int! # Sum of the node hours of all matched jobs
+  totalCores: Int! # Sum of the cores of all matched jobs
+  totalCoreHours: Int! # Sum of the core hours of all matched jobs
+  totalAccs: Int! # Sum of the accs of all matched jobs
+  totalAccHours: Int! # Sum of the gpu hours of all matched jobs
+  histDuration: [HistoPoint!]! # value: hour, count: number of jobs with a rounded duration of value
+  histNumNodes: [HistoPoint!]! # value: number of nodes, count: number of jobs with that number of nodes
+  histNumCores: [HistoPoint!]! # value: number of cores, count: number of jobs with that number of cores
+  histNumAccs: [HistoPoint!]! # value: number of accs, count: number of jobs with that number of accs
+  histMetrics: [MetricHistoPoints!]! # metric: metricname, data array of histopoints: value: metric average bin, count: number of jobs with that metric average
 }
 
 input PageRequest {
   itemsPerPage: Int!
-  page:         Int!
+  page: Int!
 }

api/swagger.yaml

@@ -1,4 +1,3 @@
-basePath: /api
 definitions:
   api.ApiReturnedUser:
     properties:
@@ -32,7 +31,7 @@ definitions:
         example: Debug
         type: string
     type: object
-  api.DefaultJobApiResponse:
+  api.DefaultApiResponse:
     properties:
       msg:
         type: string
@@ -97,7 +96,7 @@ definitions:
       jobs:
         description: Array of jobs
         items:
-          $ref: '#/definitions/schema.JobMeta'
+          $ref: '#/definitions/schema.Job'
         type: array
       page:
         description: Page id returned
@@ -112,6 +111,27 @@ definitions:
       scope:
         $ref: '#/definitions/schema.MetricScope'
     type: object
+  api.Node:
+    properties:
+      cpusAllocated:
+        type: integer
+      cpusTotal:
+        type: integer
+      gpusAllocated:
+        type: integer
+      gpusTotal:
+        type: integer
+      hostname:
+        type: string
+      memoryAllocated:
+        type: integer
+      memoryTotal:
+        type: integer
+      states:
+        items:
+          type: string
+        type: array
+    type: object
   api.StopJobApiRequest:
     properties:
       cluster:
@@ -134,6 +154,16 @@ definitions:
     - jobState
     - stopTime
     type: object
+  api.UpdateNodeStatesRequest:
+    properties:
+      cluster:
+        example: fritz
+        type: string
+      nodes:
+        items:
+          $ref: '#/definitions/api.Node'
+        type: array
+    type: object
   schema.Accelerator:
     properties:
       id:
@@ -157,7 +187,6 @@ definitions:
         type: array
     type: object
   schema.Job:
-    description: Information of a HPC job.
     properties:
       arrayJobId:
         example: 123000
@@ -175,15 +204,12 @@ definitions:
         type: number
       energyFootprint:
         additionalProperties:
+          format: float64
           type: number
         type: object
-      exclusive:
-        example: 1
-        maximum: 2
-        minimum: 0
-        type: integer
       footprint:
         additionalProperties:
+          format: float64
           type: number
         type: object
       id:
@@ -195,12 +221,18 @@ definitions:
         allOf:
         - $ref: '#/definitions/schema.JobState'
         enum:
-        - completed
-        - failed
+        - boot_fail
         - cancelled
-        - stopped
-        - timeout
+        - completed
+        - deadline
+        - failed
+        - node_fail
         - out_of_memory
+        - pending
+        - preempted
+        - running
+        - suspended
+        - timeout
         example: completed
       metaData:
         additionalProperties:
@@ -229,18 +261,37 @@ definitions:
       project:
         example: abcd200
         type: string
+      requestedMemory:
+        description: in MB
+        example: 128000
+        minimum: 1
+        type: integer
       resources:
         items:
           $ref: '#/definitions/schema.Resource'
         type: array
+      shared:
+        enum:
+        - none
+        - single_user
+        - multi_user
+        type: string
       smt:
         example: 4
         type: integer
       startTime:
-        type: string
+        example: 1649723812
+        type: integer
+      statistics:
+        additionalProperties:
+          $ref: '#/definitions/schema.JobStatistics'
+        type: object
       subCluster:
         example: main
         type: string
+      submitTime:
+        example: 1649723812
+        type: integer
       tags:
         items:
           $ref: '#/definitions/schema.Tag'
@@ -269,109 +320,6 @@ definitions:
           $ref: '#/definitions/schema.JobLink'
         type: array
     type: object
-  schema.JobMeta:
-    description: Meta data information of a HPC job.
-    properties:
-      arrayJobId:
-        example: 123000
-        type: integer
-      cluster:
-        example: fritz
-        type: string
-      concurrentJobs:
-        $ref: '#/definitions/schema.JobLinkResultList'
-      duration:
-        example: 43200
-        minimum: 1
-        type: integer
-      energy:
-        type: number
-      energyFootprint:
-        additionalProperties:
-          type: number
-        type: object
-      exclusive:
-        example: 1
-        maximum: 2
-        minimum: 0
-        type: integer
-      footprint:
-        additionalProperties:
-          type: number
-        type: object
-      id:
-        type: integer
-      jobId:
-        example: 123000
-        type: integer
-      jobState:
-        allOf:
-        - $ref: '#/definitions/schema.JobState'
-        enum:
-        - completed
-        - failed
-        - cancelled
-        - stopped
-        - timeout
-        - out_of_memory
-        example: completed
-      metaData:
-        additionalProperties:
-          type: string
-        type: object
-      monitoringStatus:
-        example: 1
-        maximum: 3
-        minimum: 0
-        type: integer
-      numAcc:
-        example: 2
-        minimum: 1
-        type: integer
-      numHwthreads:
-        example: 20
-        minimum: 1
-        type: integer
-      numNodes:
-        example: 2
-        minimum: 1
-        type: integer
-      partition:
-        example: main
-        type: string
-      project:
-        example: abcd200
-        type: string
-      resources:
-        items:
-          $ref: '#/definitions/schema.Resource'
-        type: array
-      smt:
-        example: 4
-        type: integer
-      startTime:
-        example: 1649723812
-        minimum: 1
-        type: integer
-      statistics:
-        additionalProperties:
-          $ref: '#/definitions/schema.JobStatistics'
-        type: object
-      subCluster:
-        example: main
-        type: string
-      tags:
-        items:
-          $ref: '#/definitions/schema.Tag'
-        type: array
-      user:
-        example: abcd100h
-        type: string
-      walltime:
-        example: 86400
-        minimum: 1
-        type: integer
-    type: object
   schema.JobMetric:
     properties:
       series:
@@ -387,24 +335,32 @@ definitions:
     type: object
   schema.JobState:
     enum:
-    - running
-    - completed
-    - failed
+    - boot_fail
     - cancelled
-    - stopped
-    - timeout
-    - preempted
+    - completed
+    - deadline
+    - failed
+    - node_fail
     - out_of_memory
+    - pending
+    - preempted
+    - running
+    - suspended
+    - timeout
     type: string
     x-enum-varnames:
-    - JobStateRunning
-    - JobStateCompleted
-    - JobStateFailed
+    - JobStateBootFail
     - JobStateCancelled
-    - JobStateStopped
-    - JobStateTimeout
-    - JobStatePreempted
+    - JobStateCompleted
+    - JobStateDeadline
+    - JobStateFailed
+    - JobStateNodeFail
     - JobStateOutOfMemory
+    - JobStatePending
+    - JobStatePreempted
+    - JobStateRunning
+    - JobStateSuspended
+    - JobStateTimeout
   schema.JobStatistics:
     description: Specification for job metric statistics.
     properties:
@@ -541,6 +497,7 @@ definitions:
       percentiles:
         additionalProperties:
           items:
+            format: float64
             type: number
           type: array
         type: object
@@ -600,6 +557,8 @@ definitions:
         type: number
       remove:
         type: boolean
+      unit:
+        $ref: '#/definitions/schema.Unit'
     type: object
   schema.Tag:
     description: Defines a tag using name and type.
@@ -671,7 +630,7 @@ info:
   title: ClusterCockpit REST API
   version: 1.0.0
 paths:
-  /clusters/:
+  /api/clusters/:
     get:
       description: Get a list of all cluster configs. Specific cluster can be requested
         using query parameter.
@@ -708,7 +667,7 @@ paths:
       summary: Lists all cluster configs
       tags:
       - Cluster query
-  /jobs/:
+  /api/jobs/:
     get:
       description: |-
         Get a list of all jobs. Filters can be applied using query parameters.
@@ -773,11 +732,11 @@ paths:
       summary: Lists all jobs
       tags:
       - Job query
-  /jobs/{id}:
+  /api/jobs/{id}:
     get:
       description: |-
         Job to get is specified by database ID
-        Returns full job resource information according to 'JobMeta' scheme and all metrics according to 'JobData'.
+        Returns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.
       parameters:
       - description: Database ID of Job
         in: path
@@ -830,7 +789,7 @@ paths:
       - application/json
       description: |-
         Job to get is specified by database ID
-        Returns full job resource information according to 'JobMeta' scheme and all metrics according to 'JobData'.
+        Returns full job resource information according to 'Job' scheme and all metrics according to 'JobData'.
       parameters:
       - description: Database ID of Job
         in: path
@@ -882,7 +841,7 @@ paths:
       summary: Get job meta and configurable metric data
       tags:
       - Job query
-  /jobs/delete_job/:
+  /api/jobs/delete_job/:
     delete:
       consumes:
       - application/json
@@ -901,7 +860,7 @@ paths:
         "200":
           description: Success message
           schema:
-            $ref: '#/definitions/api.DefaultJobApiResponse'
+            $ref: '#/definitions/api.DefaultApiResponse'
         "400":
           description: Bad Request
           schema:
@@ -932,7 +891,7 @@ paths:
       summary: Remove a job from the sql database
       tags:
       - Job remove
-  /jobs/delete_job/{id}:
+  /api/jobs/delete_job/{id}:
     delete:
       description: Job to remove is specified by database ID. This will not remove
         the job from the job archive.
@@ -948,7 +907,7 @@ paths:
         "200":
           description: Success message
           schema:
-            $ref: '#/definitions/api.DefaultJobApiResponse'
+            $ref: '#/definitions/api.DefaultApiResponse'
         "400":
           description: Bad Request
           schema:
@@ -979,7 +938,7 @@ paths:
       summary: Remove a job from the sql database
       tags:
       - Job remove
-  /jobs/delete_job_before/{ts}:
+  /api/jobs/delete_job_before/{ts}:
     delete:
       description: Remove all jobs with start time before timestamp. The jobs will
         not be removed from the job archive.
@@ -995,7 +954,7 @@ paths:
         "200":
           description: Success message
           schema:
-            $ref: '#/definitions/api.DefaultJobApiResponse'
+            $ref: '#/definitions/api.DefaultApiResponse'
         "400":
           description: Bad Request
           schema:
@@ -1026,7 +985,7 @@ paths:
       summary: Remove a job from the sql database
       tags:
       - Job remove
-  /jobs/edit_meta/{id}:
+  /api/jobs/edit_meta/{id}:
     post:
       consumes:
       - application/json
@@ -1073,27 +1032,27 @@ paths:
       summary: Edit meta-data json
       tags:
       - Job add and modify
-  /jobs/start_job/:
+  /api/jobs/start_job/:
     post:
       consumes:
       - application/json
       description: |-
         Job specified in request body will be saved to database as "running" with new DB ID.
-        Job specifications follow the 'JobMeta' scheme, API will fail to execute if requirements are not met.
+        Job specifications follow the 'Job' scheme, API will fail to execute if requirements are not met.
       parameters:
       - description: Job to add
         in: body
         name: request
         required: true
         schema:
-          $ref: '#/definitions/schema.JobMeta'
+          $ref: '#/definitions/schema.Job'
       produces:
       - application/json
       responses:
         "201":
           description: Job added successfully
           schema:
-            $ref: '#/definitions/api.DefaultJobApiResponse'
+            $ref: '#/definitions/api.DefaultApiResponse'
         "400":
           description: Bad Request
           schema:
@@ -1120,11 +1079,11 @@ paths:
       summary: Adds a new job as "running"
       tags:
       - Job add and modify
-  /jobs/stop_job/:
+  /api/jobs/stop_job/:
     post:
       description: |-
         Job to stop is specified by request body. All fields are required in this case.
-        Returns full job resource information according to 'JobMeta' scheme.
+        Returns full job resource information according to 'Job' scheme.
       parameters:
       - description: All fields required
         in: body
@@ -1138,7 +1097,7 @@ paths:
         "200":
           description: Success message
           schema:
-            $ref: '#/definitions/schema.JobMeta'
+            $ref: '#/definitions/schema.Job'
         "400":
           description: Bad Request
           schema:
@@ -1168,7 +1127,7 @@ paths:
       summary: Marks job as completed and triggers archiving
       tags:
       - Job add and modify
-  /jobs/tag_job/{id}:
+  /api/jobs/tag_job/{id}:
     post:
       consumes:
       - application/json
@@ -1218,173 +1177,51 @@ paths:
       summary: Adds one or more tags to a job
       tags:
       - Job add and modify
-  /notice/:
+  /api/nodestats/:
     post:
-      consumes:
-      - multipart/form-data
       description: |-
-        Modifies the content of notice.txt, shown as notice box on the homepage.
-        If more than one formValue is set then only the highest priority field is used.
-        Only accessible from IPs registered with apiAllowedIPs configuration option.
+        Returns a JSON-encoded list of users.
+        Required query-parameter defines if all users or only users with additional special roles are returned.
       parameters:
-      - description: 'Priority 1: New content to display'
-        in: formData
-        name: new-content
-        type: string
-      produces:
-      - text/plain
-      responses:
-        "200":
-          description: Success Response Message
-          schema:
-            type: string
-        "400":
-          description: Bad Request
-          schema:
-            type: string
-        "401":
-          description: Unauthorized
-          schema:
-            type: string
-        "403":
-          description: Forbidden
-          schema:
-            type: string
-        "422":
-          description: 'Unprocessable Entity: The user could not be updated'
-          schema:
-            type: string
-        "500":
-          description: Internal Server Error
-          schema:
-            type: string
-      security:
-      - ApiKeyAuth: []
-      summary: Updates or empties the notice box content
-      tags:
-      - User
-  /user/{id}:
-    post:
-      consumes:
-      - multipart/form-data
-      description: |-
-        Modifies user defined by username (id) in one of four possible ways.
-        If more than one formValue is set then only the highest priority field is used.
-        Only accessible from IPs registered with apiAllowedIPs configuration option.
-      parameters:
-      - description: Database ID of User
-        in: path
-        name: id
+      - description: Request body containing nodes and their states
+        in: body
+        name: request
         required: true
-        type: string
-      - description: 'Priority 1: Role to add'
-        enum:
-        - admin
-        - support
-        - manager
-        - user
-        - api
-        in: formData
-        name: add-role
-        type: string
-      - description: 'Priority 2: Role to remove'
-        enum:
-        - admin
-        - support
-        - manager
-        - user
-        - api
-        in: formData
-        name: remove-role
-        type: string
-      - description: 'Priority 3: Project to add'
-        in: formData
-        name: add-project
-        type: string
-      - description: 'Priority 4: Project to remove'
-        in: formData
-        name: remove-project
-        type: string
+        schema:
+          $ref: '#/definitions/api.UpdateNodeStatesRequest'
       produces:
-      - text/plain
+      - application/json
       responses:
         "200":
-          description: Success Response Message
+          description: Success message
           schema:
-            type: string
+            $ref: '#/definitions/api.DefaultApiResponse'
         "400":
           description: Bad Request
           schema:
-            type: string
+            $ref: '#/definitions/api.ErrorResponse'
         "401":
           description: Unauthorized
           schema:
-            type: string
+            $ref: '#/definitions/api.ErrorResponse'
         "403":
           description: Forbidden
           schema:
-            type: string
-        "422":
-          description: 'Unprocessable Entity: The user could not be updated'
-          schema:
-            type: string
+            $ref: '#/definitions/api.ErrorResponse'
         "500":
           description: Internal Server Error
           schema:
-            type: string
+            $ref: '#/definitions/api.ErrorResponse'
       security:
       - ApiKeyAuth: []
-      summary: Updates an existing user
+      summary: Deliver updated Slurm node states
       tags:
-      - User
-  /users/:
-    delete:
-      consumes:
-      - multipart/form-data
-      description: |-
-        User defined by username in form data will be deleted from database.
-        Only accessible from IPs registered with apiAllowedIPs configuration option.
-      parameters:
-      - description: User ID to delete
-        in: formData
-        name: username
-        required: true
-        type: string
-      produces:
-      - text/plain
-      responses:
-        "200":
-          description: User deleted successfully
-        "400":
-          description: Bad Request
-          schema:
-            type: string
-        "401":
-          description: Unauthorized
-          schema:
-            type: string
-        "403":
-          description: Forbidden
-          schema:
-            type: string
-        "422":
-          description: 'Unprocessable Entity: deleting user failed'
-          schema:
-            type: string
-        "500":
-          description: Internal Server Error
-          schema:
-            type: string
-      security:
-      - ApiKeyAuth: []
-      summary: Deletes a user
-      tags:
-      - User
+      - Nodestates
+  /api/users/:
     get:
       description: |-
         Returns a JSON-encoded list of users.
         Required query-parameter defines if all users or only users with additional special roles are returned.
-        Only accessible from IPs registered with apiAllowedIPs configuration option.
       parameters:
       - description: If returned list should contain all users or only users with
           additional special roles
@@ -1422,46 +1259,73 @@ paths:
       summary: Returns a list of users
       tags:
       - User
-    post:
+  /jobs/tag_job/{id}:
+    delete:
       consumes:
-      - multipart/form-data
+      - application/json
       description: |-
-        User specified in form data will be saved to database.
-        Only accessible from IPs registered with apiAllowedIPs configuration option.
+        Removes tag(s) from a job specified by DB ID. Name and Type of Tag(s) must match.
+        Tag Scope is required for matching, options: "global", "admin". Private tags can not be deleted via API.
+        If tagged job is already finished: Tag will be removed from respective archive files.
       parameters:
-      - description: Unique user ID
-        in: formData
-        name: username
+      - description: Job Database ID
+        in: path
+        name: id
         required: true
-        type: string
-      - description: User password
-        in: formData
-        name: password
+        type: integer
+      - description: Array of tag-objects to remove
+        in: body
+        name: request
         required: true
-        type: string
-      - description: User role
-        enum:
-        - admin
-        - support
-        - manager
-        - user
-        - api
-        in: formData
-        name: role
+        schema:
+          items:
+            $ref: '#/definitions/api.ApiTag'
+          type: array
+      produces:
+      - application/json
+      responses:
+        "200":
+          description: Updated job resource
+          schema:
+            $ref: '#/definitions/schema.Job'
+        "400":
+          description: Bad Request
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "401":
+          description: Unauthorized
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "404":
+          description: Job or tag does not exist
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+        "500":
+          description: Internal Server Error
+          schema:
+            $ref: '#/definitions/api.ErrorResponse'
+      security:
+      - ApiKeyAuth: []
+      summary: Removes one or more tags from a job
+      tags:
+      - Job add and modify
+  /tags/:
+    delete:
+      consumes:
+      - application/json
+      description: |-
+        Removes tags by type and name. Name and Type of Tag(s) must match.
+        Tag Scope is required for matching, options: "global", "admin". Private tags can not be deleted via API.
+        Tag wills be removed from respective archive files.
+      parameters:
+      - description: Array of tag-objects to remove
+        in: body
+        name: request
         required: true
-        type: string
-      - description: Managed project, required for new manager role user
-        in: formData
-        name: project
-        type: string
-      - description: Users name
-        in: formData
-        name: name
-        type: string
-      - description: Users email
-        in: formData
-        name: email
-        type: string
+        schema:
+          items:
+            $ref: '#/definitions/api.ApiTag'
+          type: array
       produces:
       - text/plain
       responses:
@@ -1472,28 +1336,24 @@ paths:
         "400":
           description: Bad Request
           schema:
-            type: string
+            $ref: '#/definitions/api.ErrorResponse'
         "401":
           description: Unauthorized
           schema:
-            type: string
-        "403":
-          description: Forbidden
+            $ref: '#/definitions/api.ErrorResponse'
+        "404":
+          description: Job or tag does not exist
           schema:
-            type: string
-        "422":
-          description: 'Unprocessable Entity: creating user failed'
-          schema:
-            type: string
+            $ref: '#/definitions/api.ErrorResponse'
         "500":
           description: Internal Server Error
           schema:
-            type: string
+            $ref: '#/definitions/api.ErrorResponse'
       security:
       - ApiKeyAuth: []
-      summary: Adds a new user
+      summary: Removes all tags and job-relations for type:name tuple
       tags:
-      - User
+      - Tag remove
 securityDefinitions:
   ApiKeyAuth:
     in: header

cmd/cc-backend/cli.go

@@ -1,18 +1,22 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// Package main provides the entry point for the ClusterCockpit backend server.
+// This file defines all command-line flags and their default values.
 package main
 
 import "flag"
 
 var (
-	flagReinitDB, flagInit, flagServer, flagSyncLDAP, flagGops, flagMigrateDB, flagRevertDB, flagForceDB, flagDev, flagVersion, flagLogDateTime bool
-	flagNewUser, flagDelUser, flagGenJWT, flagConfigFile, flagImportJob, flagLogLevel                                                           string
+	flagReinitDB, flagInit, flagServer, flagSyncLDAP, flagGops, flagMigrateDB, flagRevertDB,
+	flagForceDB, flagDev, flagVersion, flagLogDateTime, flagApplyTags bool
+	flagNewUser, flagDelUser, flagGenJWT, flagConfigFile, flagImportJob, flagLogLevel string
 )
 
 func cliInit() {
-	flag.BoolVar(&flagInit, "init", false, "Setup var directory, initialize swlite database file, config.json and .env")
+	flag.BoolVar(&flagInit, "init", false, "Setup var directory, initialize sqlite database file, config.json and .env")
 	flag.BoolVar(&flagReinitDB, "init-db", false, "Go through job-archive and re-initialize the 'job', 'tag', and 'jobtag' tables (all running jobs will be lost!)")
 	flag.BoolVar(&flagSyncLDAP, "sync-ldap", false, "Sync the 'hpc_user' table with ldap")
 	flag.BoolVar(&flagServer, "server", false, "Start a server, continues listening on port after initialization and argument handling")
@@ -21,13 +25,14 @@ func cliInit() {
 	flag.BoolVar(&flagVersion, "version", false, "Show version information and exit")
 	flag.BoolVar(&flagMigrateDB, "migrate-db", false, "Migrate database to supported version and exit")
 	flag.BoolVar(&flagRevertDB, "revert-db", false, "Migrate database to previous version and exit")
+	flag.BoolVar(&flagApplyTags, "apply-tags", false, "Run taggers on all completed jobs and exit")
 	flag.BoolVar(&flagForceDB, "force-db", false, "Force database version, clear dirty flag and exit")
 	flag.BoolVar(&flagLogDateTime, "logdate", false, "Set this flag to add date and time to log messages")
 	flag.StringVar(&flagConfigFile, "config", "./config.json", "Specify alternative path to `config.json`")
-	flag.StringVar(&flagNewUser, "add-user", "", "Add a new user. Argument format: `<username>:[admin,support,manager,api,user]:<password>`")
-	flag.StringVar(&flagDelUser, "del-user", "", "Remove user by `username`")
+	flag.StringVar(&flagNewUser, "add-user", "", "Add a new user. Argument format: <username>:[admin,support,manager,api,user]:<password>")
+	flag.StringVar(&flagDelUser, "del-user", "", "Remove a existing user. Argument format: <username>")
 	flag.StringVar(&flagGenJWT, "jwt", "", "Generate and print a JWT for the user specified by its `username`")
 	flag.StringVar(&flagImportJob, "import-job", "", "Import a job. Argument format: `<path-to-meta.json>:<path-to-data.json>,...`")
-	flag.StringVar(&flagLogLevel, "loglevel", "warn", "Sets the logging level: `[debug,info,warn (default),err,fatal,crit]`")
+	flag.StringVar(&flagLogLevel, "loglevel", "warn", "Sets the logging level: `[debug, info , warn (default), err, crit]`")
 	flag.Parse()
 }

cmd/cc-backend/init.go

@@ -1,16 +1,22 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// Package main provides the entry point for the ClusterCockpit backend server.
+// This file contains bootstrap logic for initializing the environment,
+// creating default configuration files, and setting up the database.
 package main
 
 import (
-	"fmt"
+	"encoding/json"
 	"os"
 
+	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/internal/util"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
+	"github.com/ClusterCockpit/cc-backend/pkg/archive"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/util"
 )
 
 const envString = `
@@ -25,61 +31,89 @@ SESSION_KEY="67d829bf61dc5f87a73fd814e2c9f629"
 
 const configString = `
 {
+  "main": {
     "addr": "127.0.0.1:8080",
-    "archive": {
-        "kind": "file",
-        "path": "./var/job-archive"
+    "short-running-jobs-duration": 300,
+    "resampling": {
+      "minimumPoints": 600,
+      "trigger": 180,
+      "resolutions": [
+        240,
+        60
+      ]
     },
+    "apiAllowedIPs": [
+      "*"
+    ],
+    "emission-constant": 317
+  },
+  "cron": {
+    "commit-job-worker": "2m",
+    "duration-worker": "5m",
+    "footprint-worker": "10m"
+  },
+  "archive": {
+    "kind": "file",
+    "path": "./var/job-archive"
+  },
+  "auth": {
     "jwts": {
-        "max-age": "2000h"
-    },
-    "clusters": [
-        {
-            "name": "name",
-            "metricDataRepository": {
-                "kind": "cc-metric-store",
-                "url": "http://localhost:8082",
-                "token": ""
-            },
-            "filterRanges": {
-                "numNodes": {
-                    "from": 1,
-                    "to": 64
-                },
-                "duration": {
-                    "from": 0,
-                    "to": 86400
-                },
-                "startTime": {
-                    "from": "2023-01-01T00:00:00Z",
-                    "to": null
-                }
-            }
-        }
-    ]
+      "max-age": "2000h"
+    }
+  },
+ "clusters": [
+     {
+         "name": "name",
+         "metricDataRepository": {
+             "kind": "cc-metric-store",
+             "url": "http://localhost:8082",
+             "token": ""
+         },
+         "filterRanges": {
+             "numNodes": {
+                 "from": 1,
+                 "to": 64
+             },
+             "duration": {
+                 "from": 0,
+                 "to": 86400
+             },
+             "startTime": {
+                 "from": "2023-01-01T00:00:00Z",
+                 "to": null
+             }
+         }
+     }
+ ]
 }
 `
 
 func initEnv() {
 	if util.CheckFileExists("var") {
-		fmt.Print("Directory ./var already exists. Exiting!\n")
-		os.Exit(0)
+		cclog.Exit("Directory ./var already exists. Cautiously exiting application initialization.")
 	}
 
 	if err := os.WriteFile("config.json", []byte(configString), 0o666); err != nil {
-		log.Fatalf("Writing config.json failed: %s", err.Error())
+		cclog.Abortf("Could not write default ./config.json with permissions '0o666'. Application initialization failed, exited.\nError: %s\n", err.Error())
 	}
 
 	if err := os.WriteFile(".env", []byte(envString), 0o666); err != nil {
-		log.Fatalf("Writing .env failed: %s", err.Error())
+		cclog.Abortf("Could not write default ./.env file with permissions '0o666'. Application initialization failed, exited.\nError: %s\n", err.Error())
 	}
 
 	if err := os.Mkdir("var", 0o777); err != nil {
-		log.Fatalf("Mkdir var failed: %s", err.Error())
+		cclog.Abortf("Could not create default ./var folder with permissions '0o777'. Application initialization failed, exited.\nError: %s\n", err.Error())
 	}
 
 	err := repository.MigrateDB("sqlite3", "./var/job.db")
 	if err != nil {
-		log.Fatalf("Initialize job.db failed: %s", err.Error())
+		cclog.Abortf("Could not initialize default sqlite3 database as './var/job.db'. Application initialization failed, exited.\nError: %s\n", err.Error())
+	}
+	if err := os.Mkdir("var/job-archive", 0o777); err != nil {
+		cclog.Abortf("Could not create default ./var/job-archive folder with permissions '0o777'. Application initialization failed, exited.\nError: %s\n", err.Error())
+	}
+	archiveCfg := "{\"kind\": \"file\",\"path\": \"./var/job-archive\"}"
+	if err := archive.Init(json.RawMessage(archiveCfg), config.Keys.DisableArchive); err != nil {
+		cclog.Abortf("Could not initialize job-archive, exited.\nError: %s\n", err.Error())
 	}
 }

cmd/cc-backend/main.go

@@ -1,10 +1,16 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// Package main provides the entry point for the ClusterCockpit backend server.
+// It orchestrates initialization of all subsystems including configuration,
+// database, authentication, and the HTTP server.
 package main
 
 import (
+	"context"
+	"encoding/json"
 	"fmt"
 	"os"
 	"os/signal"
@@ -12,19 +18,27 @@ import (
 	"strings"
 	"sync"
 	"syscall"
+	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/archiver"
 	"github.com/ClusterCockpit/cc-backend/internal/auth"
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/importer"
+	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
 	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/internal/taskManager"
+	"github.com/ClusterCockpit/cc-backend/internal/tagger"
+	"github.com/ClusterCockpit/cc-backend/internal/taskmanager"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/runtimeEnv"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	"github.com/ClusterCockpit/cc-backend/pkg/nats"
+	"github.com/ClusterCockpit/cc-backend/web"
+	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/runtimeEnv"
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/util"
 	"github.com/google/gops/agent"
+	"github.com/joho/godotenv"
 
 	_ "github.com/go-sql-driver/mysql"
 	_ "github.com/mattn/go-sqlite3"
@@ -39,198 +53,436 @@ const logoString = `
                                                     |_|
 `
 
+// Environment variable names
+const (
+	envGOGC = "GOGC"
+)
+
+// Default configurations
+const (
+	defaultArchiveConfig = `{"kind":"file","path":"./var/job-archive"}`
+)
+
 var (
 	date    string
 	commit  string
 	version string
 )
 
-func main() {
-	cliInit()
+func printVersion() {
+	fmt.Print(logoString)
+	fmt.Printf("Version:\t%s\n", version)
+	fmt.Printf("Git hash:\t%s\n", commit)
+	fmt.Printf("Build time:\t%s\n", date)
+	fmt.Printf("SQL db version:\t%d\n", repository.Version)
+	fmt.Printf("Job archive version:\t%d\n", archive.Version)
+}
 
-	if flagVersion {
-		fmt.Print(logoString)
-		fmt.Printf("Version:\t%s\n", version)
-		fmt.Printf("Git hash:\t%s\n", commit)
-		fmt.Printf("Build time:\t%s\n", date)
-		fmt.Printf("SQL db version:\t%d\n", repository.Version)
-		fmt.Printf("Job archive version:\t%d\n", archive.Version)
-		os.Exit(0)
+func initGops() error {
+	if !flagGops {
+		return nil
 	}
 
-	// Apply config flags for pkg/log
-	log.Init(flagLogLevel, flagLogDateTime)
+	if err := agent.Listen(agent.Options{}); err != nil {
+		return fmt.Errorf("starting gops agent: %w", err)
+	}
+	return nil
+}
 
-	// See https://github.com/google/gops (Runtime overhead is almost zero)
-	if flagGops {
-		if err := agent.Listen(agent.Options{}); err != nil {
-			log.Fatalf("gops/agent.Listen failed: %s", err.Error())
-		}
+func loadEnvironment() error {
+	if err := godotenv.Load(); err != nil {
+		return fmt.Errorf("loading .env file: %w", err)
+	}
+	return nil
+}
+
+func initConfiguration() error {
+	ccconf.Init(flagConfigFile)
+
+	cfg := ccconf.GetPackageConfig("main")
+	if cfg == nil {
+		return fmt.Errorf("main configuration must be present")
 	}
 
-	if err := runtimeEnv.LoadEnv("./.env"); err != nil && !os.IsNotExist(err) {
-		log.Fatalf("parsing './.env' file failed: %s", err.Error())
+	clustercfg := ccconf.GetPackageConfig("clusters")
+	if clustercfg == nil {
+		return fmt.Errorf("cluster configuration must be present")
 	}
 
-	// Initialize sub-modules and handle command line flags.
-	// The order here is important!
-	config.Init(flagConfigFile)
+	config.Init(cfg, clustercfg)
+	return nil
+}
 
-	// As a special case for `db`, allow using an environment variable instead of the value
-	// stored in the config. This can be done for people having security concerns about storing
-	// the password for their mysql database in config.json.
-	if strings.HasPrefix(config.Keys.DB, "env:") {
-		envvar := strings.TrimPrefix(config.Keys.DB, "env:")
-		config.Keys.DB = os.Getenv(envvar)
-	}
+func initDatabase() error {
+	repository.Connect(config.Keys.DBDriver, config.Keys.DB)
+	return nil
+}
 
+func handleDatabaseCommands() error {
 	if flagMigrateDB {
 		err := repository.MigrateDB(config.Keys.DBDriver, config.Keys.DB)
 		if err != nil {
-			log.Fatal(err)
+			return fmt.Errorf("migrating database to version %d: %w", repository.Version, err)
 		}
-		os.Exit(0)
+		cclog.Exitf("MigrateDB Success: Migrated '%s' database at location '%s' to version %d.\n",
+			config.Keys.DBDriver, config.Keys.DB, repository.Version)
 	}
 
 	if flagRevertDB {
 		err := repository.RevertDB(config.Keys.DBDriver, config.Keys.DB)
 		if err != nil {
-			log.Fatal(err)
+			return fmt.Errorf("reverting database to version %d: %w", repository.Version-1, err)
 		}
-		os.Exit(0)
+		cclog.Exitf("RevertDB Success: Reverted '%s' database at location '%s' to version %d.\n",
+			config.Keys.DBDriver, config.Keys.DB, repository.Version-1)
 	}
 
 	if flagForceDB {
 		err := repository.ForceDB(config.Keys.DBDriver, config.Keys.DB)
 		if err != nil {
-			log.Fatal(err)
+			return fmt.Errorf("forcing database to version %d: %w", repository.Version, err)
 		}
-		os.Exit(0)
+		cclog.Exitf("ForceDB Success: Forced '%s' database at location '%s' to version %d.\n",
+			config.Keys.DBDriver, config.Keys.DB, repository.Version)
 	}
 
-	repository.Connect(config.Keys.DBDriver, config.Keys.DB)
+	return nil
+}
 
-	if flagInit {
-		initEnv()
-		fmt.Print("Successfully setup environment!\n")
-		fmt.Print("Please review config.json and .env and adjust it to your needs.\n")
-		fmt.Print("Add your job-archive at ./var/job-archive.\n")
-		os.Exit(0)
+func handleUserCommands() error {
+	if config.Keys.DisableAuthentication && (flagNewUser != "" || flagDelUser != "") {
+		return fmt.Errorf("--add-user and --del-user can only be used if authentication is enabled")
 	}
 
 	if !config.Keys.DisableAuthentication {
+		if cfg := ccconf.GetPackageConfig("auth"); cfg != nil {
+			auth.Init(&cfg)
+		} else {
+			cclog.Warn("Authentication disabled due to missing configuration")
+			auth.Init(nil)
+		}
 
-		auth.Init()
+		// Check for default security keys
+		checkDefaultSecurityKeys()
 
 		if flagNewUser != "" {
-			parts := strings.SplitN(flagNewUser, ":", 3)
-			if len(parts) != 3 || len(parts[0]) == 0 {
-				log.Fatal("invalid argument format for user creation")
-			}
-
-			ur := repository.GetUserRepository()
-			if err := ur.AddUser(&schema.User{
-				Username: parts[0], Projects: make([]string, 0), Password: parts[2], Roles: strings.Split(parts[1], ","),
-			}); err != nil {
-				log.Fatalf("adding '%s' user authentication failed: %v", parts[0], err)
+			if err := addUser(flagNewUser); err != nil {
+				return err
 			}
 		}
+
 		if flagDelUser != "" {
-			ur := repository.GetUserRepository()
-			if err := ur.DelUser(flagDelUser); err != nil {
-				log.Fatalf("deleting user failed: %v", err)
+			if err := delUser(flagDelUser); err != nil {
+				return err
 			}
 		}
 
 		authHandle := auth.GetAuthInstance()
 
 		if flagSyncLDAP {
-			if authHandle.LdapAuth == nil {
-				log.Fatal("cannot sync: LDAP authentication is not configured")
+			if err := syncLDAP(authHandle); err != nil {
+				return err
 			}
-
-			if err := authHandle.LdapAuth.Sync(); err != nil {
-				log.Fatalf("LDAP sync failed: %v", err)
-			}
-			log.Info("LDAP sync successfull")
 		}
 
 		if flagGenJWT != "" {
-			ur := repository.GetUserRepository()
-			user, err := ur.GetUser(flagGenJWT)
-			if err != nil {
-				log.Fatalf("could not get user from JWT: %v", err)
+			if err := generateJWT(authHandle, flagGenJWT); err != nil {
+				return err
 			}
-
-			if !user.HasRole(schema.RoleApi) {
-				log.Warnf("user '%s' does not have the API role", user.Username)
-			}
-
-			jwt, err := authHandle.JwtAuth.ProvideJWT(user)
-			if err != nil {
-				log.Fatalf("failed to provide JWT to user '%s': %v", user.Username, err)
-			}
-
-			fmt.Printf("MAIN > JWT for '%s': %s\n", user.Username, jwt)
 		}
-
-	} else if flagNewUser != "" || flagDelUser != "" {
-		log.Fatal("arguments --add-user and --del-user can only be used if authentication is enabled")
 	}
 
-	if err := archive.Init(config.Keys.Archive, config.Keys.DisableArchive); err != nil {
-		log.Fatalf("failed to initialize archive: %s", err.Error())
+	return nil
+}
+
+// checkDefaultSecurityKeys warns if default JWT keys are detected
+func checkDefaultSecurityKeys() {
+	// Default JWT public key from init.go
+	defaultJWTPublic := "kzfYrYy+TzpanWZHJ5qSdMj5uKUWgq74BWhQG6copP0="
+
+	if os.Getenv("JWT_PUBLIC_KEY") == defaultJWTPublic {
+		cclog.Warn("Using default JWT keys - not recommended for production environments")
+	}
+}
+
+func addUser(userSpec string) error {
+	parts := strings.SplitN(userSpec, ":", 3)
+	if len(parts) != 3 || len(parts[0]) == 0 {
+		return fmt.Errorf("invalid user format, want: <username>:[admin,support,manager,api,user]:<password>, have: %s", userSpec)
 	}
 
+	ur := repository.GetUserRepository()
+	if err := ur.AddUser(&schema.User{
+		Username: parts[0],
+		Projects: make([]string, 0),
+		Password: parts[2],
+		Roles:    strings.Split(parts[1], ","),
+	}); err != nil {
+		return fmt.Errorf("adding user '%s' with roles '%s': %w", parts[0], parts[1], err)
+	}
+
+	cclog.Infof("Add User: Added new user '%s' with roles '%s'", parts[0], parts[1])
+	return nil
+}
+
+func delUser(username string) error {
+	ur := repository.GetUserRepository()
+	if err := ur.DelUser(username); err != nil {
+		return fmt.Errorf("deleting user '%s': %w", username, err)
+	}
+	cclog.Infof("Delete User: Deleted user '%s' from DB", username)
+	return nil
+}
+
+func syncLDAP(authHandle *auth.Authentication) error {
+	if authHandle.LdapAuth == nil {
+		return fmt.Errorf("LDAP authentication is not configured")
+	}
+
+	if err := authHandle.LdapAuth.Sync(); err != nil {
+		return fmt.Errorf("synchronizing LDAP: %w", err)
+	}
+
+	cclog.Print("Sync LDAP: LDAP synchronization successfull.")
+	return nil
+}
+
+func generateJWT(authHandle *auth.Authentication, username string) error {
+	ur := repository.GetUserRepository()
+	user, err := ur.GetUser(username)
+	if err != nil {
+		return fmt.Errorf("getting user '%s': %w", username, err)
+	}
+
+	if !user.HasRole(schema.RoleApi) {
+		cclog.Warnf("JWT: User '%s' does not have the role 'api'. REST API endpoints will return error!\n", user.Username)
+	}
+
+	jwt, err := authHandle.JwtAuth.ProvideJWT(user)
+	if err != nil {
+		return fmt.Errorf("generating JWT for user '%s': %w", user.Username, err)
+	}
+
+	cclog.Printf("JWT: Successfully generated JWT for user '%s': %s\n", user.Username, jwt)
+	return nil
+}
+
+func initSubsystems() error {
+	// Initialize nats client
+	natsConfig := ccconf.GetPackageConfig("nats")
+	if err := nats.Init(natsConfig); err != nil {
+		cclog.Warnf("initializing (optional) nats client: %s", err.Error())
+	}
+	nats.Connect()
+
+	// Initialize job archive
+	archiveCfg := ccconf.GetPackageConfig("archive")
+	if archiveCfg == nil {
+		archiveCfg = json.RawMessage(defaultArchiveConfig)
+	}
+	if err := archive.Init(archiveCfg, config.Keys.DisableArchive); err != nil {
+		return fmt.Errorf("initializing archive: %w", err)
+	}
+
+	// Initialize metricdata
 	if err := metricdata.Init(); err != nil {
-		log.Fatalf("failed to initialize metricdata repository: %s", err.Error())
+		return fmt.Errorf("initializing metricdata repository: %w", err)
 	}
 
+	// Handle database re-initialization
 	if flagReinitDB {
 		if err := importer.InitDB(); err != nil {
-			log.Fatalf("failed to re-initialize repository DB: %s", err.Error())
+			return fmt.Errorf("re-initializing repository DB: %w", err)
 		}
+		cclog.Print("Init DB: Successfully re-initialized repository DB.")
 	}
 
+	// Handle job import
 	if flagImportJob != "" {
 		if err := importer.HandleImportFlag(flagImportJob); err != nil {
-			log.Fatalf("job import failed: %s", err.Error())
+			return fmt.Errorf("importing job: %w", err)
+		}
+		cclog.Infof("Import Job: Imported Job '%s' into DB", flagImportJob)
+	}
+
+	// Initialize taggers
+	if config.Keys.EnableJobTaggers {
+		tagger.Init()
+	}
+
+	// Apply tags if requested
+	if flagApplyTags {
+		if err := tagger.RunTaggers(); err != nil {
+			return fmt.Errorf("running job taggers: %w", err)
 		}
 	}
 
-	if !flagServer {
-		return
-	}
-
-	archiver.Start(repository.GetJobRepository())
-	taskManager.Start()
-	serverInit()
+	return nil
+}
 
+func runServer(ctx context.Context) error {
 	var wg sync.WaitGroup
 
+	// Start metric store if enabled
+	if memorystore.InternalCCMSFlag {
+		mscfg := ccconf.GetPackageConfig("metric-store")
+		if mscfg == nil {
+			return fmt.Errorf("metric store configuration must be present")
+		}
+		memorystore.Init(mscfg, &wg)
+	}
+
+	// Start archiver and task manager
+	archiver.Start(repository.GetJobRepository(), ctx)
+	taskmanager.Start(ccconf.GetPackageConfig("cron"), ccconf.GetPackageConfig("archive"))
+
+	// Initialize web UI
+	cfg := ccconf.GetPackageConfig("ui")
+	if err := web.Init(cfg); err != nil {
+		return fmt.Errorf("initializing web UI: %w", err)
+	}
+
+	// Initialize HTTP server
+	srv, err := NewServer(version, commit, date)
+	if err != nil {
+		return fmt.Errorf("creating server: %w", err)
+	}
+
+	// Channel to collect errors from server
+	errChan := make(chan error, 1)
+
+	// Start HTTP server
 	wg.Add(1)
 	go func() {
 		defer wg.Done()
-		serverStart()
+		if err := srv.Start(ctx); err != nil {
+			errChan <- err
+		}
 	}()
 
+	// Handle shutdown signals
 	wg.Add(1)
 	sigs := make(chan os.Signal, 1)
 	signal.Notify(sigs, syscall.SIGINT, syscall.SIGTERM)
 	go func() {
 		defer wg.Done()
-		<-sigs
+		select {
+		case <-sigs:
+			cclog.Info("Shutdown signal received")
+		case <-ctx.Done():
+		}
+
 		runtimeEnv.SystemdNotifiy(false, "Shutting down ...")
-
-		serverShutdown()
-
-		taskManager.Shutdown()
+		srv.Shutdown(ctx)
+		util.FsWatcherShutdown()
+		taskmanager.Shutdown()
 	}()
 
-	if os.Getenv("GOGC") == "" {
+	// Set GC percent if not configured
+	if os.Getenv(envGOGC) == "" {
 		debug.SetGCPercent(25)
 	}
 	runtimeEnv.SystemdNotifiy(true, "running")
-	wg.Wait()
-	log.Print("Graceful shutdown completed!")
+
+	// Wait for completion or error
+	go func() {
+		wg.Wait()
+		close(errChan)
+	}()
+
+	// Check for server startup errors
+	select {
+	case err := <-errChan:
+		if err != nil {
+			return err
+		}
+	case <-time.After(100 * time.Millisecond):
+		// Server started successfully, wait for completion
+		if err := <-errChan; err != nil {
+			return err
+		}
+	}
+
+	cclog.Print("Graceful shutdown completed!")
+	return nil
+}
+
+func run() error {
+	cliInit()
+
+	if flagVersion {
+		printVersion()
+		return nil
+	}
+
+	// Initialize logger
+	cclog.Init(flagLogLevel, flagLogDateTime)
+
+	// Handle init flag
+	if flagInit {
+		initEnv()
+		cclog.Exit("Successfully setup environment!\n" +
+			"Please review config.json and .env and adjust it to your needs.\n" +
+			"Add your job-archive at ./var/job-archive.")
+	}
+
+	// Initialize gops agent
+	if err := initGops(); err != nil {
+		return err
+	}
+
+	// Initialize subsystems in dependency order:
+	// 1. Load environment variables from .env file (contains sensitive configuration)
+	// 2. Load configuration from config.json (may reference environment variables)
+	// 3. Handle database migration commands if requested
+	// 4. Initialize database connection (requires config for connection string)
+	// 5. Handle user commands if requested (requires database and authentication config)
+	// 6. Initialize subsystems like archive and metrics (require config and database)
+
+	// Load environment and configuration
+	if err := loadEnvironment(); err != nil {
+		return err
+	}
+
+	if err := initConfiguration(); err != nil {
+		return err
+	}
+
+	// Handle database migration (migrate, revert, force)
+	if err := handleDatabaseCommands(); err != nil {
+		return err
+	}
+
+	// Initialize database
+	if err := initDatabase(); err != nil {
+		return err
+	}
+
+	// Handle user commands (add, delete, sync, JWT)
+	if err := handleUserCommands(); err != nil {
+		return err
+	}
+
+	// Initialize subsystems (archive, metrics, taggers)
+	if err := initSubsystems(); err != nil {
+		return err
+	}
+
+	// Exit if start server is not requested
+	if !flagServer {
+		cclog.Exit("No errors, server flag not set. Exiting cc-backend.")
+	}
+
+	// Run server with context
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	return runServer(ctx)
+}
+
+func main() {
+	if err := run(); err != nil {
+		cclog.Error(err.Error())
+		os.Exit(1)
+	}
 }

cmd/cc-backend/server.go

@@ -1,7 +1,10 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+// Package main provides the entry point for the ClusterCockpit backend server.
+// This file contains HTTP server setup, routing configuration, and
+// authentication middleware integration.
 package main
 
 import (
@@ -18,6 +21,7 @@ import (
 	"time"
 
 	"github.com/99designs/gqlgen/graphql/handler"
+	"github.com/99designs/gqlgen/graphql/handler/transport"
 	"github.com/99designs/gqlgen/graphql/playground"
 	"github.com/ClusterCockpit/cc-backend/internal/api"
 	"github.com/ClusterCockpit/cc-backend/internal/archiver"
@@ -25,20 +29,30 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/generated"
+	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
 	"github.com/ClusterCockpit/cc-backend/internal/routerConfig"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/runtimeEnv"
+	"github.com/ClusterCockpit/cc-backend/pkg/nats"
 	"github.com/ClusterCockpit/cc-backend/web"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/runtimeEnv"
 	"github.com/gorilla/handlers"
 	"github.com/gorilla/mux"
 	httpSwagger "github.com/swaggo/http-swagger"
 )
 
-var (
+var buildInfo web.Build
+
+// Environment variable names
+const (
+	envDebug = "DEBUG"
+)
+
+// Server encapsulates the HTTP server state and dependencies
+type Server struct {
 	router    *mux.Router
 	server    *http.Server
-	apiHandle *api.RestApi
-)
+	apiHandle *api.RestAPI
+}
 
 func onFailureResponse(rw http.ResponseWriter, r *http.Request, err error) {
 	rw.Header().Add("Content-Type", "application/json")
@@ -49,22 +63,39 @@ func onFailureResponse(rw http.ResponseWriter, r *http.Request, err error) {
 	})
 }
 
-func serverInit() {
+// NewServer creates and initializes a new Server instance
+func NewServer(version, commit, buildDate string) (*Server, error) {
+	buildInfo = web.Build{Version: version, Hash: commit, Buildtime: buildDate}
+
+	s := &Server{
+		router: mux.NewRouter(),
+	}
+
+	if err := s.init(); err != nil {
+		return nil, err
+	}
+
+	return s, nil
+}
+
+func (s *Server) init() error {
 	// Setup the http.Handler/Router used by the server
 	graph.Init()
 	resolver := graph.GetResolverInstance()
-	graphQLEndpoint := handler.NewDefaultServer(
+	graphQLServer := handler.New(
 		generated.NewExecutableSchema(generated.Config{Resolvers: resolver}))
 
-	if os.Getenv("DEBUG") != "1" {
+	graphQLServer.AddTransport(transport.POST{})
+
+	if os.Getenv(envDebug) != "1" {
 		// Having this handler means that a error message is returned via GraphQL instead of the connection simply beeing closed.
 		// The problem with this is that then, no more stacktrace is printed to stderr.
-		graphQLEndpoint.SetRecoverFunc(func(ctx context.Context, err interface{}) error {
+		graphQLServer.SetRecoverFunc(func(ctx context.Context, err any) error {
 			switch e := err.(type) {
 			case string:
 				return fmt.Errorf("MAIN > Panic: %s", e)
 			case error:
-				return fmt.Errorf("MAIN > Panic caused by: %w", e)
+				return fmt.Errorf("MAIN > Panic caused by: %s", e.Error())
 			}
 
 			return errors.New("MAIN > Internal server error (panic)")
@@ -73,72 +104,56 @@ func serverInit() {
 
 	authHandle := auth.GetAuthInstance()
 
-	apiHandle = api.New()
+	s.apiHandle = api.New()
 
-	router = mux.NewRouter()
-	buildInfo := web.Build{Version: version, Hash: commit, Buildtime: date}
-
-	info := map[string]interface{}{}
+	info := map[string]any{}
 	info["hasOpenIDConnect"] = false
 
-	if config.Keys.OpenIDConfig != nil {
+	if auth.Keys.OpenIDConfig != nil {
 		openIDConnect := auth.NewOIDC(authHandle)
-		openIDConnect.RegisterEndpoints(router)
+		openIDConnect.RegisterEndpoints(s.router)
 		info["hasOpenIDConnect"] = true
 	}
 
-	router.HandleFunc("/login", func(rw http.ResponseWriter, r *http.Request) {
+	s.router.HandleFunc("/login", func(rw http.ResponseWriter, r *http.Request) {
 		rw.Header().Add("Content-Type", "text/html; charset=utf-8")
-		log.Debugf("##%v##", info)
+		cclog.Debugf("##%v##", info)
 		web.RenderTemplate(rw, "login.tmpl", &web.Page{Title: "Login", Build: buildInfo, Infos: info})
 	}).Methods(http.MethodGet)
-	router.HandleFunc("/imprint", func(rw http.ResponseWriter, r *http.Request) {
+	s.router.HandleFunc("/imprint", func(rw http.ResponseWriter, r *http.Request) {
 		rw.Header().Add("Content-Type", "text/html; charset=utf-8")
 		web.RenderTemplate(rw, "imprint.tmpl", &web.Page{Title: "Imprint", Build: buildInfo})
 	})
-	router.HandleFunc("/privacy", func(rw http.ResponseWriter, r *http.Request) {
+	s.router.HandleFunc("/privacy", func(rw http.ResponseWriter, r *http.Request) {
 		rw.Header().Add("Content-Type", "text/html; charset=utf-8")
 		web.RenderTemplate(rw, "privacy.tmpl", &web.Page{Title: "Privacy", Build: buildInfo})
 	})
 
-	secured := router.PathPrefix("/").Subrouter()
-	securedapi := router.PathPrefix("/api").Subrouter()
-	userapi := router.PathPrefix("/userapi").Subrouter()
-	configapi := router.PathPrefix("/config").Subrouter()
-	frontendapi := router.PathPrefix("/frontend").Subrouter()
+	secured := s.router.PathPrefix("/").Subrouter()
+	securedapi := s.router.PathPrefix("/api").Subrouter()
+	userapi := s.router.PathPrefix("/userapi").Subrouter()
+	configapi := s.router.PathPrefix("/config").Subrouter()
+	frontendapi := s.router.PathPrefix("/frontend").Subrouter()
+	metricstoreapi := s.router.PathPrefix("/metricstore").Subrouter()
 
 	if !config.Keys.DisableAuthentication {
-		router.Handle("/login", authHandle.Login(
-			// On success: Handled within Login()
-			// On failure:
-			func(rw http.ResponseWriter, r *http.Request, err error) {
-				rw.Header().Add("Content-Type", "text/html; charset=utf-8")
-				rw.WriteHeader(http.StatusUnauthorized)
-				web.RenderTemplate(rw, "login.tmpl", &web.Page{
-					Title:   "Login failed - ClusterCockpit",
-					MsgType: "alert-warning",
-					Message: err.Error(),
-					Build:   buildInfo,
-					Infos:   info,
-				})
-			})).Methods(http.MethodPost)
+		// Create login failure handler (used by both /login and /jwt-login)
+		loginFailureHandler := func(rw http.ResponseWriter, r *http.Request, err error) {
+			rw.Header().Add("Content-Type", "text/html; charset=utf-8")
+			rw.WriteHeader(http.StatusUnauthorized)
+			web.RenderTemplate(rw, "login.tmpl", &web.Page{
+				Title:   "Login failed - ClusterCockpit",
+				MsgType: "alert-warning",
+				Message: err.Error(),
+				Build:   buildInfo,
+				Infos:   info,
+			})
+		}
 
-		router.Handle("/jwt-login", authHandle.Login(
-			// On success: Handled within Login()
-			// On failure:
-			func(rw http.ResponseWriter, r *http.Request, err error) {
-				rw.Header().Add("Content-Type", "text/html; charset=utf-8")
-				rw.WriteHeader(http.StatusUnauthorized)
-				web.RenderTemplate(rw, "login.tmpl", &web.Page{
-					Title:   "Login failed - ClusterCockpit",
-					MsgType: "alert-warning",
-					Message: err.Error(),
-					Build:   buildInfo,
-					Infos:   info,
-				})
-			}))
+		s.router.Handle("/login", authHandle.Login(loginFailureHandler)).Methods(http.MethodPost)
+		s.router.Handle("/jwt-login", authHandle.Login(loginFailureHandler))
 
-		router.Handle("/logout", authHandle.Logout(
+		s.router.Handle("/logout", authHandle.Logout(
 			http.HandlerFunc(func(rw http.ResponseWriter, r *http.Request) {
 				rw.Header().Add("Content-Type", "text/html; charset=utf-8")
 				rw.WriteHeader(http.StatusOK)
@@ -171,7 +186,7 @@ func serverInit() {
 		})
 
 		securedapi.Use(func(next http.Handler) http.Handler {
-			return authHandle.AuthApi(
+			return authHandle.AuthAPI(
 				// On success;
 				next,
 				// On failure: JSON Response
@@ -179,7 +194,15 @@ func serverInit() {
 		})
 
 		userapi.Use(func(next http.Handler) http.Handler {
-			return authHandle.AuthUserApi(
+			return authHandle.AuthUserAPI(
+				// On success;
+				next,
+				// On failure: JSON Response
+				onFailureResponse)
+		})
+
+		metricstoreapi.Use(func(next http.Handler) http.Handler {
+			return authHandle.AuthMetricStoreAPI(
 				// On success;
 				next,
 				// On failure: JSON Response
@@ -187,7 +210,7 @@ func serverInit() {
 		})
 
 		configapi.Use(func(next http.Handler) http.Handler {
-			return authHandle.AuthConfigApi(
+			return authHandle.AuthConfigAPI(
 				// On success;
 				next,
 				// On failure: JSON Response
@@ -195,7 +218,7 @@ func serverInit() {
 		})
 
 		frontendapi.Use(func(next http.Handler) http.Handler {
-			return authHandle.AuthFrontendApi(
+			return authHandle.AuthFrontendAPI(
 				// On success;
 				next,
 				// On failure: JSON Response
@@ -204,11 +227,11 @@ func serverInit() {
 	}
 
 	if flagDev {
-		router.Handle("/playground", playground.Handler("GraphQL playground", "/query"))
-		router.PathPrefix("/swagger/").Handler(httpSwagger.Handler(
+		s.router.Handle("/playground", playground.Handler("GraphQL playground", "/query"))
+		s.router.PathPrefix("/swagger/").Handler(httpSwagger.Handler(
 			httpSwagger.URL("http://" + config.Keys.Addr + "/swagger/doc.json"))).Methods(http.MethodGet)
 	}
-	secured.Handle("/query", graphQLEndpoint)
+	secured.Handle("/query", graphQLServer)
 
 	// Send a searchId and then reply with a redirect to a user, or directly send query to job table for jobid and project.
 	secured.HandleFunc("/search", func(rw http.ResponseWriter, r *http.Request) {
@@ -217,50 +240,66 @@ func serverInit() {
 
 	// Mount all /monitoring/... and /api/... routes.
 	routerConfig.SetupRoutes(secured, buildInfo)
-	apiHandle.MountApiRoutes(securedapi)
-	apiHandle.MountUserApiRoutes(userapi)
-	apiHandle.MountConfigApiRoutes(configapi)
-	apiHandle.MountFrontendApiRoutes(frontendapi)
+	s.apiHandle.MountAPIRoutes(securedapi)
+	s.apiHandle.MountUserAPIRoutes(userapi)
+	s.apiHandle.MountConfigAPIRoutes(configapi)
+	s.apiHandle.MountFrontendAPIRoutes(frontendapi)
+
+	if memorystore.InternalCCMSFlag {
+		s.apiHandle.MountMetricStoreAPIRoutes(metricstoreapi)
+	}
 
 	if config.Keys.EmbedStaticFiles {
 		if i, err := os.Stat("./var/img"); err == nil {
 			if i.IsDir() {
-				log.Info("Use local directory for static images")
-				router.PathPrefix("/img/").Handler(http.StripPrefix("/img/", http.FileServer(http.Dir("./var/img"))))
+				cclog.Info("Use local directory for static images")
+				s.router.PathPrefix("/img/").Handler(http.StripPrefix("/img/", http.FileServer(http.Dir("./var/img"))))
 			}
 		}
-		router.PathPrefix("/").Handler(web.ServeFiles())
+		s.router.PathPrefix("/").Handler(http.StripPrefix("/", web.ServeFiles()))
 	} else {
-		router.PathPrefix("/").Handler(http.FileServer(http.Dir(config.Keys.StaticFiles)))
+		s.router.PathPrefix("/").Handler(http.FileServer(http.Dir(config.Keys.StaticFiles)))
 	}
 
-	router.Use(handlers.CompressHandler)
-	router.Use(handlers.RecoveryHandler(handlers.PrintRecoveryStack(true)))
-	router.Use(handlers.CORS(
+	s.router.Use(handlers.CompressHandler)
+	s.router.Use(handlers.RecoveryHandler(handlers.PrintRecoveryStack(true)))
+	s.router.Use(handlers.CORS(
 		handlers.AllowCredentials(),
 		handlers.AllowedHeaders([]string{"X-Requested-With", "Content-Type", "Authorization", "Origin"}),
 		handlers.AllowedMethods([]string{"GET", "POST", "HEAD", "OPTIONS"}),
 		handlers.AllowedOrigins([]string{"*"})))
+
+	return nil
 }
 
-func serverStart() {
-	handler := handlers.CustomLoggingHandler(io.Discard, router, func(_ io.Writer, params handlers.LogFormatterParams) {
+// Server timeout defaults (in seconds)
+const (
+	defaultReadTimeout  = 20
+	defaultWriteTimeout = 20
+)
+
+func (s *Server) Start(ctx context.Context) error {
+	handler := handlers.CustomLoggingHandler(io.Discard, s.router, func(_ io.Writer, params handlers.LogFormatterParams) {
 		if strings.HasPrefix(params.Request.RequestURI, "/api/") {
-			log.Debugf("%s %s (%d, %.02fkb, %dms)",
+			cclog.Debugf("%s %s (%d, %.02fkb, %dms)",
 				params.Request.Method, params.URL.RequestURI(),
 				params.StatusCode, float32(params.Size)/1024,
 				time.Since(params.TimeStamp).Milliseconds())
 		} else {
-			log.Debugf("%s %s (%d, %.02fkb, %dms)",
+			cclog.Debugf("%s %s (%d, %.02fkb, %dms)",
 				params.Request.Method, params.URL.RequestURI(),
 				params.StatusCode, float32(params.Size)/1024,
 				time.Since(params.TimeStamp).Milliseconds())
 		}
 	})
 
-	server = &http.Server{
-		ReadTimeout:  20 * time.Second,
-		WriteTimeout: 20 * time.Second,
+	// Use configurable timeouts with defaults
+	readTimeout := time.Duration(defaultReadTimeout) * time.Second
+	writeTimeout := time.Duration(defaultWriteTimeout) * time.Second
+
+	s.server = &http.Server{
+		ReadTimeout:  readTimeout,
+		WriteTimeout: writeTimeout,
 		Handler:      handler,
 		Addr:         config.Keys.Addr,
 	}
@@ -268,20 +307,20 @@ func serverStart() {
 	// Start http or https server
 	listener, err := net.Listen("tcp", config.Keys.Addr)
 	if err != nil {
-		log.Fatalf("starting http listener failed: %v", err)
+		return fmt.Errorf("starting listener on '%s': %w", config.Keys.Addr, err)
 	}
 
-	if !strings.HasSuffix(config.Keys.Addr, ":80") && config.Keys.RedirectHttpTo != "" {
+	if !strings.HasSuffix(config.Keys.Addr, ":80") && config.Keys.RedirectHTTPTo != "" {
 		go func() {
-			http.ListenAndServe(":80", http.RedirectHandler(config.Keys.RedirectHttpTo, http.StatusMovedPermanently))
+			http.ListenAndServe(":80", http.RedirectHandler(config.Keys.RedirectHTTPTo, http.StatusMovedPermanently))
 		}()
 	}
 
-	if config.Keys.HttpsCertFile != "" && config.Keys.HttpsKeyFile != "" {
+	if config.Keys.HTTPSCertFile != "" && config.Keys.HTTPSKeyFile != "" {
 		cert, err := tls.LoadX509KeyPair(
-			config.Keys.HttpsCertFile, config.Keys.HttpsKeyFile)
+			config.Keys.HTTPSCertFile, config.Keys.HTTPSKeyFile)
 		if err != nil {
-			log.Fatalf("loading X509 keypair failed: %v", err)
+			return fmt.Errorf("loading X509 keypair (check 'https-cert-file' and 'https-key-file' in config.json): %w", err)
 		}
 		listener = tls.NewListener(listener, &tls.Config{
 			Certificates: []tls.Certificate{cert},
@@ -292,27 +331,56 @@ func serverStart() {
 			MinVersion:               tls.VersionTLS12,
 			PreferServerCipherSuites: true,
 		})
-		fmt.Printf("HTTPS server listening at %s...", config.Keys.Addr)
+		cclog.Infof("HTTPS server listening at %s...", config.Keys.Addr)
 	} else {
-		fmt.Printf("HTTP server listening at %s...", config.Keys.Addr)
+		cclog.Infof("HTTP server listening at %s...", config.Keys.Addr)
 	}
 	//
 	// Because this program will want to bind to a privileged port (like 80), the listener must
 	// be established first, then the user can be changed, and after that,
 	// the actual http server can be started.
 	if err := runtimeEnv.DropPrivileges(config.Keys.Group, config.Keys.User); err != nil {
-		log.Fatalf("error while preparing server start: %s", err.Error())
+		return fmt.Errorf("dropping privileges: %w", err)
 	}
 
-	if err = server.Serve(listener); err != nil && err != http.ErrServerClosed {
-		log.Fatalf("starting server failed: %v", err)
+	// Handle context cancellation for graceful shutdown
+	go func() {
+		<-ctx.Done()
+		shutdownCtx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+		defer cancel()
+		if err := s.server.Shutdown(shutdownCtx); err != nil {
+			cclog.Errorf("Server shutdown error: %v", err)
+		}
+	}()
+
+	if err = s.server.Serve(listener); err != nil && err != http.ErrServerClosed {
+		return fmt.Errorf("server failed: %w", err)
 	}
+	return nil
 }
 
-func serverShutdown() {
+func (s *Server) Shutdown(ctx context.Context) {
+	// Create a shutdown context with timeout
+	shutdownCtx, cancel := context.WithTimeout(ctx, 30*time.Second)
+	defer cancel()
+
+	nc := nats.GetClient()
+	if nc != nil {
+		nc.Close()
+	}
+
 	// First shut down the server gracefully (waiting for all ongoing requests)
-	server.Shutdown(context.Background())
+	if err := s.server.Shutdown(shutdownCtx); err != nil {
+		cclog.Errorf("Server shutdown error: %v", err)
+	}
 
-	// Then, wait for any async archivings still pending...
-	archiver.WaitForArchiving()
+	// Archive all the metric store data
+	if memorystore.InternalCCMSFlag {
+		memorystore.Shutdown()
+	}
+
+	// Shutdown archiver with 10 second timeout for fast shutdown
+	if err := archiver.Shutdown(10 * time.Second); err != nil {
+		cclog.Warnf("Archiver shutdown: %v", err)
+	}
 }

configs/config-demo.json

@@ -1,30 +1,46 @@
 {
-  "addr": "127.0.0.1:8080",
-  "short-running-jobs-duration": 300,
+  "main": {
+    "addr": "127.0.0.1:8080",
+    "short-running-jobs-duration": 300,
+    "resampling": {
+      "minimumPoints": 600,
+      "trigger": 180,
+      "resolutions": [
+        240,
+        60
+      ]
+    },
+    "apiAllowedIPs": [
+      "*"
+    ],
+    "emission-constant": 317
+  },
+  "cron": {
+    "commit-job-worker": "2m",
+    "duration-worker": "5m",
+    "footprint-worker": "10m"
+  },
   "archive": {
     "kind": "file",
     "path": "./var/job-archive"
   },
-  "jwts": {
-    "max-age": "2000h"
+  "auth": {
+    "jwts": {
+      "max-age": "2000h"
+    }
   },
-  "enable-resampling": {
-    "trigger": 30,
-    "resolutions": [
-      600,
-      300,
-      120,
-      60
-    ]
+  "nats": {
+    "address": "nats://0.0.0.0:4222",
+    "username": "root",
+    "password": "root"
   },
-  "emission-constant": 317,
   "clusters": [
     {
       "name": "fritz",
       "metricDataRepository": {
-        "kind": "cc-metric-store",
+        "kind": "cc-metric-store-internal",
         "url": "http://localhost:8082",
-        "token": ""
+        "token": "eyJ0eXAiOiJKV1QiLCJhbGciOiJFZERTQSJ9.eyJ1c2VyIjoiYWRtaW4iLCJyb2xlcyI6WyJST0xFX0FETUlOIiwiUk9MRV9BTkFMWVNUIiwiUk9MRV9VU0VSIl19.d-3_3FZTsadPjDEdsWrrQ7nS0edMAR4zjl-eK7rJU3HziNBfI9PDHDIpJVHTNN5E5SlLGLFXctWyKAkwhXL-Dw"
       },
       "filterRanges": {
         "numNodes": {
@@ -44,9 +60,9 @@
     {
       "name": "alex",
       "metricDataRepository": {
-        "kind": "cc-metric-store",
+        "kind": "cc-metric-store-internal",
         "url": "http://localhost:8082",
-        "token": ""
+        "token": "eyJ0eXAiOiJKV1QiLCJhbGciOiJFZERTQSJ9.eyJ1c2VyIjoiYWRtaW4iLCJyb2xlcyI6WyJST0xFX0FETUlOIiwiUk9MRV9BTkFMWVNUIiwiUk9MRV9VU0VSIl19.d-3_3FZTsadPjDEdsWrrQ7nS0edMAR4zjl-eK7rJU3HziNBfI9PDHDIpJVHTNN5E5SlLGLFXctWyKAkwhXL-Dw"
       },
       "filterRanges": {
         "numNodes": {
@@ -63,5 +79,28 @@
         }
       }
     }
-  ]
-}
+  ],
+  "metric-store": {
+    "checkpoints": {
+      "file-format": "avro",
+      "interval": "1h",
+      "directory": "./var/checkpoints",
+      "restore": "48h"
+    },
+    "archive": {
+      "interval": "1h",
+      "directory": "./var/archive"
+    },
+    "retention-in-memory": "48h",
+    "subscriptions": [
+      {
+        "subscribe-to": "hpc-nats",
+        "cluster-tag": "fritz"
+      },
+      {
+        "subscribe-to": "hpc-nats",
+        "cluster-tag": "alex"
+      }
+    ]
+  }
+}

configs/config-mariadb.json

@@ -12,12 +12,7 @@
   "db": "clustercockpit:demo@tcp(127.0.0.1:3306)/clustercockpit",
   "enable-resampling": {
     "trigger": 30,
-    "resolutions": [
-      600,
-      300,
-      120,
-      60
-    ]
+    "resolutions": [600, 300, 120, 60]
   },
   "emission-constant": 317,
   "clusters": [

configs/config.json

@@ -1,50 +1,54 @@
 {
+  "main": {
     "addr": "0.0.0.0:443",
-    "ldap": {
-        "url": "ldaps://test",
-        "user_base": "ou=people,ou=hpc,dc=test,dc=de",
-        "search_dn": "cn=hpcmonitoring,ou=roadm,ou=profile,ou=hpc,dc=test,dc=de",
-        "user_bind": "uid={username},ou=people,ou=hpc,dc=test,dc=de",
-        "user_filter": "(&(objectclass=posixAccount))"
-    },
     "https-cert-file": "/etc/letsencrypt/live/url/fullchain.pem",
     "https-key-file": "/etc/letsencrypt/live/url/privkey.pem",
     "user": "clustercockpit",
     "group": "clustercockpit",
-    "archive": {
-        "kind": "file",
-        "path": "./var/job-archive"
-    },
-    "validate": true,
-    "clusters": [
-        {
-            "name": "test",
-            "metricDataRepository": {
-                "kind": "cc-metric-store",
-                "url": "http://localhost:8082",
-                "token": "eyJhbGciOiJF-E-pQBQ"
-            },
-            "filterRanges": {
-                "numNodes": {
-                    "from": 1,
-                    "to": 64
-                },
-                "duration": {
-                    "from": 0,
-                    "to": 86400
-                },
-                "startTime": {
-                    "from": "2022-01-01T00:00:00Z",
-                    "to": null
-                }
-            }
+    "validate": false,
+    "apiAllowedIPs": ["*"],
+    "short-running-jobs-duration": 300,
+    "resampling": {
+      "minimumPoints": 600,
+      "trigger": 180,
+      "resolutions": [
+        240,
+        60
+      ]
+    }
+  },
+  "cron": {
+    "commit-job-worker": "2m",
+    "duration-worker": "5m",
+    "footprint-worker": "10m"
+  },
+  "archive": {
+    "kind": "file",
+    "path": "./var/job-archive"
+  },
+  "clusters": [
+    {
+      "name": "test",
+      "metricDataRepository": {
+        "kind": "cc-metric-store",
+        "url": "http://localhost:8082",
+        "token": "eyJhbGciOiJF-E-pQBQ"
+      },
+      "filterRanges": {
+        "numNodes": {
+          "from": 1,
+          "to": 64
+        },
+        "duration": {
+          "from": 0,
+          "to": 86400
+        },
+        "startTime": {
+          "from": "2022-01-01T00:00:00Z",
+          "to": null
         }
-    ],
-    "jwts": {
-        "cookieName": "",
-        "validateUser": false,
-        "max-age": "2000h",
-        "trustedIssuer": ""
-    },
-    "short-running-jobs-duration": 300
+      }
+    }
+  ]
 }
+

configs/default_metrics.json

@@ -1,12 +0,0 @@
-{
-  "clusters": [
-    {
-      "name": "fritz",
-      "default_metrics": "cpu_load, flops_any, core_power, lustre_open, mem_used, mem_bw, net_bytes_in"
-    },
-    {
-      "name": "alex",
-      "default_metrics": "flops_any, mem_bw, mem_used, vectorization_ratio"
-    }
-  ]
-}

configs/uiConfig.json

@@ -0,0 +1,45 @@
+{
+  "jobList": {
+    "usePaging": false,
+    "showFootprint":false
+  },
+  "jobView": {
+    "showPolarPlot": true,
+    "showFootprint": true,
+    "showRoofline": true,
+    "showStatTable": true
+  },
+  "metricConfig": {
+    "jobListMetrics": ["mem_bw", "flops_dp"],
+    "jobViewPlotMetrics": ["mem_bw", "flops_dp"],
+    "jobViewTableMetrics": ["mem_bw", "flops_dp"],
+    "clusters": [
+      {
+        "name": "test",
+        "subClusters": [
+          {
+            "name": "one",
+            "jobListMetrics": ["mem_used", "flops_sp"]
+          }
+        ]
+      }
+    ]
+  },
+  "nodeList": {
+    "usePaging": true
+  },
+  "plotConfiguration": {
+    "plotsPerRow": 3,
+    "colorBackground": true,
+    "lineWidth": 3,
+    "colorScheme": [
+	"#00bfff",
+	"#0000ff",
+	"#ff00ff",
+	"#ff0000",
+	"#ff8000",
+	"#ffff00",
+	"#80ff00"
+    ]
+  }
+}

go.mod

@@ -1,35 +1,50 @@
 module github.com/ClusterCockpit/cc-backend
 
-go 1.23.5
+go 1.24.0
+
+toolchain go1.24.1
+
+tool (
+	github.com/99designs/gqlgen
+	github.com/swaggo/swag/cmd/swag
+)
 
 require (
-	github.com/99designs/gqlgen v0.17.66
-	github.com/ClusterCockpit/cc-units v0.4.0
+	github.com/99designs/gqlgen v0.17.85
+	github.com/ClusterCockpit/cc-lib v1.0.2
 	github.com/Masterminds/squirrel v1.5.4
-	github.com/coreos/go-oidc/v3 v3.12.0
-	github.com/go-co-op/gocron/v2 v2.16.0
-	github.com/go-ldap/ldap/v3 v3.4.10
-	github.com/go-sql-driver/mysql v1.9.0
-	github.com/golang-jwt/jwt/v5 v5.2.1
-	github.com/golang-migrate/migrate/v4 v4.18.2
+	github.com/aws/aws-sdk-go-v2 v1.41.0
+	github.com/aws/aws-sdk-go-v2/config v1.32.6
+	github.com/aws/aws-sdk-go-v2/credentials v1.19.6
+	github.com/aws/aws-sdk-go-v2/service/s3 v1.95.0
+	github.com/coreos/go-oidc/v3 v3.17.0
+	github.com/expr-lang/expr v1.17.7
+	github.com/go-co-op/gocron/v2 v2.19.0
+	github.com/go-ldap/ldap/v3 v3.4.12
+	github.com/go-sql-driver/mysql v1.9.3
+	github.com/golang-jwt/jwt/v5 v5.3.0
+	github.com/golang-migrate/migrate/v4 v4.19.1
 	github.com/google/gops v0.3.28
 	github.com/gorilla/handlers v1.5.2
 	github.com/gorilla/mux v1.8.1
 	github.com/gorilla/sessions v1.4.0
-	github.com/influxdata/influxdb-client-go/v2 v2.14.0
+	github.com/influxdata/line-protocol/v2 v2.2.1
 	github.com/jmoiron/sqlx v1.4.0
-	github.com/mattn/go-sqlite3 v1.14.24
-	github.com/prometheus/client_golang v1.21.0
-	github.com/prometheus/common v0.62.0
+	github.com/joho/godotenv v1.5.1
+	github.com/linkedin/goavro/v2 v2.14.1
+	github.com/mattn/go-sqlite3 v1.14.32
+	github.com/nats-io/nats.go v1.47.0
+	github.com/prometheus/client_golang v1.23.2
+	github.com/prometheus/common v0.67.4
 	github.com/qustavo/sqlhooks/v2 v2.1.0
 	github.com/santhosh-tekuri/jsonschema/v5 v5.3.1
+	github.com/stretchr/testify v1.11.1
 	github.com/swaggo/http-swagger v1.3.4
-	github.com/swaggo/swag v1.16.4
-	github.com/vektah/gqlparser/v2 v2.5.22
-	golang.org/x/crypto v0.35.0
-	golang.org/x/exp v0.0.0-20250218142911-aa4b98e5adaa
-	golang.org/x/oauth2 v0.27.0
-	golang.org/x/time v0.5.0
+	github.com/swaggo/swag v1.16.6
+	github.com/vektah/gqlparser/v2 v2.5.31
+	golang.org/x/crypto v0.46.0
+	golang.org/x/oauth2 v0.34.0
+	golang.org/x/time v0.14.0
 )
 
 require (
@@ -37,54 +52,78 @@ require (
 	github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358 // indirect
 	github.com/KyleBanks/depth v1.2.1 // indirect
 	github.com/agnivade/levenshtein v1.2.1 // indirect
-	github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
+	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4 // indirect
+	github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.16 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.16 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.16 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4 // indirect
+	github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.16 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.4 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.7 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.16 // indirect
+	github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.16 // indirect
+	github.com/aws/aws-sdk-go-v2/service/signin v1.0.4 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sso v1.30.8 // indirect
+	github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.12 // indirect
+	github.com/aws/aws-sdk-go-v2/service/sts v1.41.5 // indirect
+	github.com/aws/smithy-go v1.24.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/cespare/xxhash/v2 v2.3.0 // indirect
-	github.com/cpuguy83/go-md2man/v2 v2.0.6 // indirect
+	github.com/cpuguy83/go-md2man/v2 v2.0.7 // indirect
+	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
-	github.com/go-asn1-ber/asn1-ber v1.5.7 // indirect
-	github.com/go-jose/go-jose/v4 v4.0.5 // indirect
-	github.com/go-openapi/jsonpointer v0.21.0 // indirect
-	github.com/go-openapi/jsonreference v0.21.0 // indirect
-	github.com/go-openapi/spec v0.21.0 // indirect
-	github.com/go-openapi/swag v0.23.0 // indirect
-	github.com/go-viper/mapstructure/v2 v2.2.1 // indirect
+	github.com/fsnotify/fsnotify v1.9.0 // indirect
+	github.com/go-asn1-ber/asn1-ber v1.5.8-0.20250403174932-29230038a667 // indirect
+	github.com/go-jose/go-jose/v4 v4.1.3 // indirect
+	github.com/go-openapi/jsonpointer v0.22.3 // indirect
+	github.com/go-openapi/jsonreference v0.21.3 // indirect
+	github.com/go-openapi/spec v0.22.1 // indirect
+	github.com/go-openapi/swag/conv v0.25.4 // indirect
+	github.com/go-openapi/swag/jsonname v0.25.4 // indirect
+	github.com/go-openapi/swag/jsonutils v0.25.4 // indirect
+	github.com/go-openapi/swag/loading v0.25.4 // indirect
+	github.com/go-openapi/swag/stringutils v0.25.4 // indirect
+	github.com/go-openapi/swag/typeutils v0.25.4 // indirect
+	github.com/go-openapi/swag/yamlutils v0.25.4 // indirect
+	github.com/go-viper/mapstructure/v2 v2.4.0 // indirect
+	github.com/goccy/go-yaml v1.19.0 // indirect
+	github.com/golang/snappy v0.0.4 // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/gorilla/securecookie v1.1.2 // indirect
 	github.com/gorilla/websocket v1.5.3 // indirect
-	github.com/hashicorp/errwrap v1.1.0 // indirect
-	github.com/hashicorp/go-multierror v1.1.1 // indirect
 	github.com/hashicorp/golang-lru/v2 v2.0.7 // indirect
-	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf // indirect
 	github.com/jonboulle/clockwork v0.5.0 // indirect
-	github.com/josharian/intern v1.0.0 // indirect
 	github.com/jpillora/backoff v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
+	github.com/klauspost/compress v1.18.1 // indirect
 	github.com/lann/builder v0.0.0-20180802200727-47ae307949d0 // indirect
 	github.com/lann/ps v0.0.0-20150810152359-62de8c46ede0 // indirect
-	github.com/mailru/easyjson v0.9.0 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f // indirect
-	github.com/oapi-codegen/runtime v1.1.1 // indirect
-	github.com/prometheus/client_model v0.6.1 // indirect
-	github.com/prometheus/procfs v0.15.1 // indirect
+	github.com/nats-io/nkeys v0.4.11 // indirect
+	github.com/nats-io/nuid v1.0.1 // indirect
+	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
+	github.com/prometheus/client_model v0.6.2 // indirect
+	github.com/prometheus/procfs v0.16.1 // indirect
 	github.com/robfig/cron/v3 v3.0.1 // indirect
 	github.com/russross/blackfriday/v2 v2.1.0 // indirect
 	github.com/sosodev/duration v1.3.1 // indirect
+	github.com/stretchr/objx v0.5.2 // indirect
 	github.com/swaggo/files v1.0.1 // indirect
-	github.com/urfave/cli/v2 v2.27.5 // indirect
-	github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1 // indirect
-	go.uber.org/atomic v1.11.0 // indirect
-	golang.org/x/mod v0.23.0 // indirect
-	golang.org/x/net v0.35.0 // indirect
-	golang.org/x/sync v0.11.0 // indirect
-	golang.org/x/sys v0.30.0 // indirect
-	golang.org/x/text v0.22.0 // indirect
-	golang.org/x/tools v0.30.0 // indirect
-	google.golang.org/protobuf v1.36.5 // indirect
-	gopkg.in/yaml.v2 v2.4.0 // indirect
+	github.com/urfave/cli/v2 v2.27.7 // indirect
+	github.com/urfave/cli/v3 v3.6.1 // indirect
+	github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 // indirect
+	go.yaml.in/yaml/v2 v2.4.3 // indirect
+	go.yaml.in/yaml/v3 v3.0.4 // indirect
+	golang.org/x/mod v0.31.0 // indirect
+	golang.org/x/net v0.48.0 // indirect
+	golang.org/x/sync v0.19.0 // indirect
+	golang.org/x/sys v0.39.0 // indirect
+	golang.org/x/text v0.32.0 // indirect
+	golang.org/x/tools v0.40.0 // indirect
+	google.golang.org/protobuf v1.36.11 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
-	sigs.k8s.io/yaml v1.4.0 // indirect
+	sigs.k8s.io/yaml v1.6.0 // indirect
 )

go.sum

@@ -1,95 +1,172 @@
 filippo.io/edwards25519 v1.1.0 h1:FNf4tywRC1HmFuKW5xopWpigGjJKiJSV0Cqo0cJWDaA=
 filippo.io/edwards25519 v1.1.0/go.mod h1:BxyFTGdWcka3PhytdK4V28tE5sGfRvvvRV7EaN4VDT4=
-github.com/99designs/gqlgen v0.17.66 h1:2/SRc+h3115fCOZeTtsqrB5R5gTGm+8qCAwcrZa+CXA=
-github.com/99designs/gqlgen v0.17.66/go.mod h1:gucrb5jK5pgCKzAGuOMMVU9C8PnReecHEHd2UxLQwCg=
+github.com/99designs/gqlgen v0.17.85 h1:EkGx3U2FDcxQm8YDLQSpXIAVmpDyZ3IcBMOJi2nH1S0=
+github.com/99designs/gqlgen v0.17.85/go.mod h1:yvs8s0bkQlRfqg03YXr3eR4OQUowVhODT/tHzCXnbOU=
 github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161 h1:L/gRVlceqvL25UVaW/CKtUDjefjrs0SPonmDGUVOYP0=
 github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161/go.mod h1:xomTg63KZ2rFqZQzSB4Vz2SUXa1BpHTVz9L5PTmPC4E=
 github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358 h1:mFRzDkZVAjdal+s7s0MwaRv9igoPqLRdzOLzw/8Xvq8=
 github.com/Azure/go-ntlmssp v0.0.0-20221128193559-754e69321358/go.mod h1:chxPXzSsl7ZWRAuOIE23GDNzjWuZquvFlgA8xmpunjU=
-github.com/ClusterCockpit/cc-units v0.4.0 h1:zP5DOu99GmErW0tCDf0gcLrlWt42RQ9dpoONEOh4cI0=
-github.com/ClusterCockpit/cc-units v0.4.0/go.mod h1:3S3PAhAayS3pbgcT4q9Vn9VJw22Op51X0YimtG77zBw=
+github.com/ClusterCockpit/cc-lib v1.0.2 h1:ZWn3oZkXgxrr3zSigBdlOOfayZ4Om4xL20DhmritPPg=
+github.com/ClusterCockpit/cc-lib v1.0.2/go.mod h1:UGdOvXEnjFqlnPSxtvtFwO6BtXYW6NnXFoud9FtN93k=
 github.com/KyleBanks/depth v1.2.1 h1:5h8fQADFrWtarTdtDudMmGsC7GPbOAu6RVB3ffsVFHc=
 github.com/KyleBanks/depth v1.2.1/go.mod h1:jzSb9d0L43HxTQfT+oSA1EEp2q+ne2uh6XgeJcm8brE=
 github.com/Masterminds/squirrel v1.5.4 h1:uUcX/aBc8O7Fg9kaISIUsHXdKuqehiXAMQTYX8afzqM=
 github.com/Masterminds/squirrel v1.5.4/go.mod h1:NNaOrjSoIDfDA40n7sr2tPNZRfjzjA400rg+riTZj10=
 github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
 github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
-github.com/PuerkitoBio/goquery v1.9.3 h1:mpJr/ikUA9/GNJB/DBZcGeFDXUtosHRyRrwh7KGdTG0=
-github.com/PuerkitoBio/goquery v1.9.3/go.mod h1:1ndLHPdTz+DyQPICCWYlYQMPl0oXZj0G6D4LCYA6u4U=
-github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk=
+github.com/NVIDIA/go-nvml v0.13.0-1 h1:OLX8Jq3dONuPOQPC7rndB6+iDmDakw0XTYgzMxObkEw=
+github.com/NVIDIA/go-nvml v0.13.0-1/go.mod h1:+KNA7c7gIBH7SKSJ1ntlwkfN80zdx8ovl4hrK3LmPt4=
+github.com/PuerkitoBio/goquery v1.11.0 h1:jZ7pwMQXIITcUXNH83LLk+txlaEy6NVOfTuP43xxfqw=
+github.com/PuerkitoBio/goquery v1.11.0/go.mod h1:wQHgxUOU3JGuj3oD/QFfxUdlzW6xPHfqyHre6VMY4DQ=
 github.com/agnivade/levenshtein v1.2.1 h1:EHBY3UOn1gwdy/VbFwgo4cxecRznFk7fKWN1KOX7eoM=
 github.com/agnivade/levenshtein v1.2.1/go.mod h1:QVVI16kDrtSuwcpd0p1+xMC6Z/VfhtCyDIjcwga4/DU=
-github.com/alexbrainman/sspi v0.0.0-20231016080023-1a75b4708caa h1:LHTHcTQiSGT7VVbI0o4wBRNQIgn917usHWOd6VAffYI=
-github.com/alexbrainman/sspi v0.0.0-20231016080023-1a75b4708caa/go.mod h1:cEWa1LVoE5KvSD9ONXsZrj0z6KqySlCCNKHlLzbqAt4=
+github.com/alexbrainman/sspi v0.0.0-20250919150558-7d374ff0d59e h1:4dAU9FXIyQktpoUAgOJK3OTFc/xug0PCXYCqU0FgDKI=
+github.com/alexbrainman/sspi v0.0.0-20250919150558-7d374ff0d59e/go.mod h1:cEWa1LVoE5KvSD9ONXsZrj0z6KqySlCCNKHlLzbqAt4=
 github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883 h1:bvNMNQO63//z+xNgfBlViaCIJKLlCJ6/fmUseuG0wVQ=
 github.com/andreyvit/diff v0.0.0-20170406064948-c7f18ee00883/go.mod h1:rCTlJbsFo29Kk6CurOXKm700vrz8f0KW0JNfpkRJY/8=
-github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss=
-github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
+github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=
+github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=
 github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ=
 github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP2+08jFMw88y4klk=
 github.com/arbovm/levenshtein v0.0.0-20160628152529-48b4e1c0c4d0 h1:jfIu9sQUG6Ig+0+Ap1h4unLjW6YQJpKZVmUzxsD4E/Q=
 github.com/arbovm/levenshtein v0.0.0-20160628152529-48b4e1c0c4d0/go.mod h1:t2tdKJDJF9BV14lnkjHmOQgcvEKgtqs5a1N3LNdJhGE=
+github.com/aws/aws-sdk-go-v2 v1.41.0 h1:tNvqh1s+v0vFYdA1xq0aOJH+Y5cRyZ5upu6roPgPKd4=
+github.com/aws/aws-sdk-go-v2 v1.41.0/go.mod h1:MayyLB8y+buD9hZqkCW3kX1AKq07Y5pXxtgB+rRFhz0=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4 h1:489krEF9xIGkOaaX3CE/Be2uWjiXrkCH6gUX+bZA/BU=
+github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.4/go.mod h1:IOAPF6oT9KCsceNTvvYMNHy0+kMF8akOjeDvPENWxp4=
+github.com/aws/aws-sdk-go-v2/config v1.32.6 h1:hFLBGUKjmLAekvi1evLi5hVvFQtSo3GYwi+Bx4lpJf8=
+github.com/aws/aws-sdk-go-v2/config v1.32.6/go.mod h1:lcUL/gcd8WyjCrMnxez5OXkO3/rwcNmvfno62tnXNcI=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.6 h1:F9vWao2TwjV2MyiyVS+duza0NIRtAslgLUM0vTA1ZaE=
+github.com/aws/aws-sdk-go-v2/credentials v1.19.6/go.mod h1:SgHzKjEVsdQr6Opor0ihgWtkWdfRAIwxYzSJ8O85VHY=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.16 h1:80+uETIWS1BqjnN9uJ0dBUaETh+P1XwFy5vwHwK5r9k=
+github.com/aws/aws-sdk-go-v2/feature/ec2/imds v1.18.16/go.mod h1:wOOsYuxYuB/7FlnVtzeBYRcjSRtQpAW0hCP7tIULMwo=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.16 h1:rgGwPzb82iBYSvHMHXc8h9mRoOUBZIGFgKb9qniaZZc=
+github.com/aws/aws-sdk-go-v2/internal/configsources v1.4.16/go.mod h1:L/UxsGeKpGoIj6DxfhOWHWQ/kGKcd4I1VncE4++IyKA=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.16 h1:1jtGzuV7c82xnqOVfx2F0xmJcOw5374L7N6juGW6x6U=
+github.com/aws/aws-sdk-go-v2/internal/endpoints/v2 v2.7.16/go.mod h1:M2E5OQf+XLe+SZGmmpaI2yy+J326aFf6/+54PoxSANc=
+github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4 h1:WKuaxf++XKWlHWu9ECbMlha8WOEGm0OUEZqm4K/Gcfk=
+github.com/aws/aws-sdk-go-v2/internal/ini v1.8.4/go.mod h1:ZWy7j6v1vWGmPReu0iSGvRiise4YI5SkR3OHKTZ6Wuc=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.16 h1:CjMzUs78RDDv4ROu3JnJn/Ig1r6ZD7/T2DXLLRpejic=
+github.com/aws/aws-sdk-go-v2/internal/v4a v1.4.16/go.mod h1:uVW4OLBqbJXSHJYA9svT9BluSvvwbzLQ2Crf6UPzR3c=
+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.4 h1:0ryTNEdJbzUCEWkVXEXoqlXV72J5keC1GvILMOuD00E=
+github.com/aws/aws-sdk-go-v2/service/internal/accept-encoding v1.13.4/go.mod h1:HQ4qwNZh32C3CBeO6iJLQlgtMzqeG17ziAA/3KDJFow=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.7 h1:DIBqIrJ7hv+e4CmIk2z3pyKT+3B6qVMgRsawHiR3qso=
+github.com/aws/aws-sdk-go-v2/service/internal/checksum v1.9.7/go.mod h1:vLm00xmBke75UmpNvOcZQ/Q30ZFjbczeLFqGx5urmGo=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.16 h1:oHjJHeUy0ImIV0bsrX0X91GkV5nJAyv1l1CC9lnO0TI=
+github.com/aws/aws-sdk-go-v2/service/internal/presigned-url v1.13.16/go.mod h1:iRSNGgOYmiYwSCXxXaKb9HfOEj40+oTKn8pTxMlYkRM=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.16 h1:NSbvS17MlI2lurYgXnCOLvCFX38sBW4eiVER7+kkgsU=
+github.com/aws/aws-sdk-go-v2/service/internal/s3shared v1.19.16/go.mod h1:SwT8Tmqd4sA6G1qaGdzWCJN99bUmPGHfRwwq3G5Qb+A=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.95.0 h1:MIWra+MSq53CFaXXAywB2qg9YvVZifkk6vEGl/1Qor0=
+github.com/aws/aws-sdk-go-v2/service/s3 v1.95.0/go.mod h1:79S2BdqCJpScXZA2y+cpZuocWsjGjJINyXnOsf5DTz8=
+github.com/aws/aws-sdk-go-v2/service/signin v1.0.4 h1:HpI7aMmJ+mm1wkSHIA2t5EaFFv5EFYXePW30p1EIrbQ=
+github.com/aws/aws-sdk-go-v2/service/signin v1.0.4/go.mod h1:C5RdGMYGlfM0gYq/tifqgn4EbyX99V15P2V3R+VHbQU=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.8 h1:aM/Q24rIlS3bRAhTyFurowU8A0SMyGDtEOY/l/s/1Uw=
+github.com/aws/aws-sdk-go-v2/service/sso v1.30.8/go.mod h1:+fWt2UHSb4kS7Pu8y+BMBvJF0EWx+4H0hzNwtDNRTrg=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.12 h1:AHDr0DaHIAo8c9t1emrzAlVDFp+iMMKnPdYy6XO4MCE=
+github.com/aws/aws-sdk-go-v2/service/ssooidc v1.35.12/go.mod h1:GQ73XawFFiWxyWXMHWfhiomvP3tXtdNar/fi8z18sx0=
+github.com/aws/aws-sdk-go-v2/service/sts v1.41.5 h1:SciGFVNZ4mHdm7gpD1dgZYnCuVdX1s+lFTg4+4DOy70=
+github.com/aws/aws-sdk-go-v2/service/sts v1.41.5/go.mod h1:iW40X4QBmUxdP+fZNOpfmkdMZqsovezbAeO+Ubiv2pk=
+github.com/aws/smithy-go v1.24.0 h1:LpilSUItNPFr1eY85RYgTIg5eIEPtvFbskaFcmmIUnk=
+github.com/aws/smithy-go v1.24.0/go.mod h1:LEj2LM3rBRQJxPZTB4KuzZkaZYnZPnvgIhb4pu07mx0=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
-github.com/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/coreos/go-oidc/v3 v3.12.0 h1:sJk+8G2qq94rDI6ehZ71Bol3oUHy63qNYmkiSjrc/Jo=
-github.com/coreos/go-oidc/v3 v3.12.0/go.mod h1:gE3LgjOgFoHi9a4ce4/tJczr0Ai2/BoDhf0r5lltWI0=
-github.com/cpuguy83/go-md2man/v2 v2.0.6 h1:XJtiaUW6dEEqVuZiMTn1ldk455QWwEIsMIJlo5vtkx0=
-github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
+github.com/containerd/errdefs v1.0.0 h1:tg5yIfIlQIrxYtu9ajqY42W3lpS19XqdxRQeEwYG8PI=
+github.com/containerd/errdefs v1.0.0/go.mod h1:+YBYIdtsnF4Iw6nWZhJcqGSg/dwvV7tyJ/kCkyJ2k+M=
+github.com/containerd/errdefs/pkg v0.3.0 h1:9IKJ06FvyNlexW690DXuQNx2KA2cUJXx151Xdx3ZPPE=
+github.com/containerd/errdefs/pkg v0.3.0/go.mod h1:NJw6s9HwNuRhnjJhM7pylWwMyAkmCQvQ4GpJHEqRLVk=
+github.com/coreos/go-oidc/v3 v3.17.0 h1:hWBGaQfbi0iVviX4ibC7bk8OKT5qNr4klBaCHVNvehc=
+github.com/coreos/go-oidc/v3 v3.17.0/go.mod h1:wqPbKFrVnE90vty060SB40FCJ8fTHTxSwyXJqZH+sI8=
+github.com/cpuguy83/go-md2man/v2 v2.0.7 h1:zbFlGlXEAKlwXpmvle3d8Oe3YnkKIK4xSRTd3sHPnBo=
+github.com/cpuguy83/go-md2man/v2 v2.0.7/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
+github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
+github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/dgryski/trifles v0.0.0-20230903005119-f50d829f2e54 h1:SG7nF6SRlWhcT7cNTs5R6Hk4V2lcmLz2NsG2VnInyNo=
 github.com/dgryski/trifles v0.0.0-20230903005119-f50d829f2e54/go.mod h1:if7Fbed8SFyPtHLHbg49SI7NAdJiC5WIA09pe59rfAA=
-github.com/dhui/dktest v0.4.4 h1:+I4s6JRE1yGuqflzwqG+aIaMdgXIorCf5P98JnaAWa8=
-github.com/dhui/dktest v0.4.4/go.mod h1:4+22R4lgsdAXrDyaH4Nqx2JEz2hLp49MqQmm9HLCQhM=
+github.com/dhui/dktest v0.4.6 h1:+DPKyScKSEp3VLtbMDHcUq6V5Lm5zfZZVb0Sk7Ahom4=
+github.com/dhui/dktest v0.4.6/go.mod h1:JHTSYDtKkvFNFHJKqCzVzqXecyv+tKt8EzceOmQOgbU=
 github.com/distribution/reference v0.6.0 h1:0IXCQ5g4/QMHHkarYzh5l+u8T3t73zM5QvfrDyIgxBk=
 github.com/distribution/reference v0.6.0/go.mod h1:BbU0aIcezP1/5jX/8MP0YiH4SdvB5Y4f/wlDRiLyi3E=
-github.com/docker/docker v27.2.0+incompatible h1:Rk9nIVdfH3+Vz4cyI/uhbINhEZ/oLmc+CBXmH6fbNk4=
-github.com/docker/docker v27.2.0+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
+github.com/docker/docker v28.3.3+incompatible h1:Dypm25kh4rmk49v1eiVbsAtpAsYURjYkaKubwuBdxEI=
+github.com/docker/docker v28.3.3+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
 github.com/docker/go-connections v0.5.0 h1:USnMq7hx7gwdVZq1L49hLXaFtUdTADjXGp+uj1Br63c=
 github.com/docker/go-connections v0.5.0/go.mod h1:ov60Kzw0kKElRwhNs9UlUHAE/F9Fe6GLaXnqyDdmEXc=
 github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4=
 github.com/docker/go-units v0.5.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
+github.com/expr-lang/expr v1.17.7 h1:Q0xY/e/2aCIp8g9s/LGvMDCC5PxYlvHgDZRQ4y16JX8=
+github.com/expr-lang/expr v1.17.7/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
 github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
-github.com/go-asn1-ber/asn1-ber v1.5.7 h1:DTX+lbVTWaTw1hQ+PbZPlnDZPEIs0SS/GCZAl535dDk=
-github.com/go-asn1-ber/asn1-ber v1.5.7/go.mod h1:hEBeB/ic+5LoWskz+yKT7vGhhPYkProFKoKdwZRWMe0=
-github.com/go-co-op/gocron/v2 v2.16.0 h1:uqUF6WFZ4enRU45pWFNcn1xpDLc+jBOTKhPQI16Z1xs=
-github.com/go-co-op/gocron/v2 v2.16.0/go.mod h1:opexeOFy5BplhsKdA7bzY9zeYih8I8/WNJ4arTIFPVc=
-github.com/go-jose/go-jose/v4 v4.0.5 h1:M6T8+mKZl/+fNNuFHvGIzDz7BTLQPIounk/b9dw3AaE=
-github.com/go-jose/go-jose/v4 v4.0.5/go.mod h1:s3P1lRrkT8igV8D9OjyL4WRyHvjB6a4JSllnOrmmBOA=
-github.com/go-ldap/ldap/v3 v3.4.10 h1:ot/iwPOhfpNVgB1o+AVXljizWZ9JTp7YF5oeyONmcJU=
-github.com/go-ldap/ldap/v3 v3.4.10/go.mod h1:JXh4Uxgi40P6E9rdsYqpUtbW46D9UTjJ9QSwGRznplY=
-github.com/go-logr/logr v1.4.2 h1:6pFjapn8bFcIbiKo3XT4j/BhANplGihG6tvd+8rYgrY=
-github.com/go-logr/logr v1.4.2/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
+github.com/frankban/quicktest v1.11.0/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
+github.com/frankban/quicktest v1.11.2/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
+github.com/frankban/quicktest v1.13.0 h1:yNZif1OkDfNoDfb9zZa9aXIpejNR4F23Wely0c+Qdqk=
+github.com/frankban/quicktest v1.13.0/go.mod h1:qLE0fzW0VuyUAJgPU19zByoIr0HtCHN/r/VLSOOIySU=
+github.com/fsnotify/fsnotify v1.9.0 h1:2Ml+OJNzbYCTzsxtv8vKSFD9PbJjmhYF14k/jKC7S9k=
+github.com/fsnotify/fsnotify v1.9.0/go.mod h1:8jBTzvmWwFyi3Pb8djgCCO5IBqzKJ/Jwo8TRcHyHii0=
+github.com/go-asn1-ber/asn1-ber v1.5.8-0.20250403174932-29230038a667 h1:BP4M0CvQ4S3TGls2FvczZtj5Re/2ZzkV9VwqPHH/3Bo=
+github.com/go-asn1-ber/asn1-ber v1.5.8-0.20250403174932-29230038a667/go.mod h1:hEBeB/ic+5LoWskz+yKT7vGhhPYkProFKoKdwZRWMe0=
+github.com/go-co-op/gocron/v2 v2.19.0 h1:OKf2y6LXPs/BgBI2fl8PxUpNAI1DA9Mg+hSeGOS38OU=
+github.com/go-co-op/gocron/v2 v2.19.0/go.mod h1:5lEiCKk1oVJV39Zg7/YG10OnaVrDAV5GGR6O0663k6U=
+github.com/go-jose/go-jose/v4 v4.1.3 h1:CVLmWDhDVRa6Mi/IgCgaopNosCaHz7zrMeF9MlZRkrs=
+github.com/go-jose/go-jose/v4 v4.1.3/go.mod h1:x4oUasVrzR7071A4TnHLGSPpNOm2a21K9Kf04k1rs08=
+github.com/go-ldap/ldap/v3 v3.4.12 h1:1b81mv7MagXZ7+1r7cLTWmyuTqVqdwbtJSjC0DAp9s4=
+github.com/go-ldap/ldap/v3 v3.4.12/go.mod h1:+SPAGcTtOfmGsCb3h1RFiq4xpp4N636G75OEace8lNo=
+github.com/go-logr/logr v1.4.3 h1:CjnDlHq8ikf6E492q6eKboGOC0T8CDaOvkHCIg8idEI=
+github.com/go-logr/logr v1.4.3/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
 github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
 github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
-github.com/go-openapi/jsonpointer v0.21.0 h1:YgdVicSA9vH5RiHs9TZW5oyafXZFc6+2Vc1rr/O9oNQ=
-github.com/go-openapi/jsonpointer v0.21.0/go.mod h1:IUyH9l/+uyhIYQ/PXVA41Rexl+kOkAPDdXEYns6fzUY=
-github.com/go-openapi/jsonreference v0.21.0 h1:Rs+Y7hSXT83Jacb7kFyjn4ijOuVGSvOdF2+tg1TRrwQ=
-github.com/go-openapi/jsonreference v0.21.0/go.mod h1:LmZmgsrTkVg9LG4EaHeY8cBDslNPMo06cago5JNLkm4=
-github.com/go-openapi/spec v0.21.0 h1:LTVzPc3p/RzRnkQqLRndbAzjY0d0BCL72A6j3CdL9ZY=
-github.com/go-openapi/spec v0.21.0/go.mod h1:78u6VdPw81XU44qEWGhtr982gJ5BWg2c0I5XwVMotYk=
-github.com/go-openapi/swag v0.23.0 h1:vsEVJDUo2hPJ2tu0/Xc+4noaxyEffXNIs3cOULZ+GrE=
-github.com/go-openapi/swag v0.23.0/go.mod h1:esZ8ITTYEsH1V2trKHjAN8Ai7xHb8RV+YSZ577vPjgQ=
+github.com/go-openapi/jsonpointer v0.22.3 h1:dKMwfV4fmt6Ah90zloTbUKWMD+0he+12XYAsPotrkn8=
+github.com/go-openapi/jsonpointer v0.22.3/go.mod h1:0lBbqeRsQ5lIanv3LHZBrmRGHLHcQoOXQnf88fHlGWo=
+github.com/go-openapi/jsonreference v0.21.3 h1:96Dn+MRPa0nYAR8DR1E03SblB5FJvh7W6krPI0Z7qMc=
+github.com/go-openapi/jsonreference v0.21.3/go.mod h1:RqkUP0MrLf37HqxZxrIAtTWW4ZJIK1VzduhXYBEeGc4=
+github.com/go-openapi/spec v0.22.1 h1:beZMa5AVQzRspNjvhe5aG1/XyBSMeX1eEOs7dMoXh/k=
+github.com/go-openapi/spec v0.22.1/go.mod h1:c7aeIQT175dVowfp7FeCvXXnjN/MrpaONStibD2WtDA=
+github.com/go-openapi/swag v0.19.15 h1:D2NRCBzS9/pEY3gP9Nl8aDqGUcPFrwG2p+CNFrLyrCM=
+github.com/go-openapi/swag/conv v0.25.4 h1:/Dd7p0LZXczgUcC/Ikm1+YqVzkEeCc9LnOWjfkpkfe4=
+github.com/go-openapi/swag/conv v0.25.4/go.mod h1:3LXfie/lwoAv0NHoEuY1hjoFAYkvlqI/Bn5EQDD3PPU=
+github.com/go-openapi/swag/jsonname v0.25.4 h1:bZH0+MsS03MbnwBXYhuTttMOqk+5KcQ9869Vye1bNHI=
+github.com/go-openapi/swag/jsonname v0.25.4/go.mod h1:GPVEk9CWVhNvWhZgrnvRA6utbAltopbKwDu8mXNUMag=
+github.com/go-openapi/swag/jsonutils v0.25.4 h1:VSchfbGhD4UTf4vCdR2F4TLBdLwHyUDTd1/q4i+jGZA=
+github.com/go-openapi/swag/jsonutils v0.25.4/go.mod h1:7OYGXpvVFPn4PpaSdPHJBtF0iGnbEaTk8AvBkoWnaAY=
+github.com/go-openapi/swag/jsonutils/fixtures_test v0.25.4 h1:IACsSvBhiNJwlDix7wq39SS2Fh7lUOCJRmx/4SN4sVo=
+github.com/go-openapi/swag/jsonutils/fixtures_test v0.25.4/go.mod h1:Mt0Ost9l3cUzVv4OEZG+WSeoHwjWLnarzMePNDAOBiM=
+github.com/go-openapi/swag/loading v0.25.4 h1:jN4MvLj0X6yhCDduRsxDDw1aHe+ZWoLjW+9ZQWIKn2s=
+github.com/go-openapi/swag/loading v0.25.4/go.mod h1:rpUM1ZiyEP9+mNLIQUdMiD7dCETXvkkC30z53i+ftTE=
+github.com/go-openapi/swag/stringutils v0.25.4 h1:O6dU1Rd8bej4HPA3/CLPciNBBDwZj9HiEpdVsb8B5A8=
+github.com/go-openapi/swag/stringutils v0.25.4/go.mod h1:GTsRvhJW5xM5gkgiFe0fV3PUlFm0dr8vki6/VSRaZK0=
+github.com/go-openapi/swag/typeutils v0.25.4 h1:1/fbZOUN472NTc39zpa+YGHn3jzHWhv42wAJSN91wRw=
+github.com/go-openapi/swag/typeutils v0.25.4/go.mod h1:Ou7g//Wx8tTLS9vG0UmzfCsjZjKhpjxayRKTHXf2pTE=
+github.com/go-openapi/swag/yamlutils v0.25.4 h1:6jdaeSItEUb7ioS9lFoCZ65Cne1/RZtPBZ9A56h92Sw=
+github.com/go-openapi/swag/yamlutils v0.25.4/go.mod h1:MNzq1ulQu+yd8Kl7wPOut/YHAAU/H6hL91fF+E2RFwc=
+github.com/go-openapi/testify/enable/yaml/v2 v2.0.2 h1:0+Y41Pz1NkbTHz8NngxTuAXxEodtNSI1WG1c/m5Akw4=
+github.com/go-openapi/testify/enable/yaml/v2 v2.0.2/go.mod h1:kme83333GCtJQHXQ8UKX3IBZu6z8T5Dvy5+CW3NLUUg=
+github.com/go-openapi/testify/v2 v2.0.2 h1:X999g3jeLcoY8qctY/c/Z8iBHTbwLz7R2WXd6Ub6wls=
+github.com/go-openapi/testify/v2 v2.0.2/go.mod h1:HCPmvFFnheKK2BuwSA0TbbdxJ3I16pjwMkYkP4Ywn54=
 github.com/go-sql-driver/mysql v1.4.1/go.mod h1:zAC/RDZ24gD3HViQzih4MyKcchzm+sOG5ZlKdlhCg5w=
 github.com/go-sql-driver/mysql v1.8.1/go.mod h1:wEBSXgmK//2ZFJyE+qWnIsVGmvmEKlqwuVSjsCm7DZg=
-github.com/go-sql-driver/mysql v1.9.0 h1:Y0zIbQXhQKmQgTp44Y1dp3wTXcn804QoTptLZT1vtvo=
-github.com/go-sql-driver/mysql v1.9.0/go.mod h1:pDetrLJeA3oMujJuvXc8RJoasr589B6A9fwzD3QMrqw=
-github.com/go-viper/mapstructure/v2 v2.2.1 h1:ZAaOCxANMuZx5RCeg0mBdEZk7DZasvvZIxtHqx8aGss=
-github.com/go-viper/mapstructure/v2 v2.2.1/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
+github.com/go-sql-driver/mysql v1.9.3 h1:U/N249h2WzJ3Ukj8SowVFjdtZKfu9vlLZxjPXV1aweo=
+github.com/go-sql-driver/mysql v1.9.3/go.mod h1:qn46aNg1333BRMNU69Lq93t8du/dwxI64Gl8i5p1WMU=
+github.com/go-viper/mapstructure/v2 v2.4.0 h1:EBsztssimR/CONLSZZ04E8qAkxNYq4Qp9LvH92wZUgs=
+github.com/go-viper/mapstructure/v2 v2.4.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
+github.com/goccy/go-yaml v1.19.0 h1:EmkZ9RIsX+Uq4DYFowegAuJo8+xdX3T/2dwNPXbxEYE=
+github.com/goccy/go-yaml v1.19.0/go.mod h1:XBurs7gK8ATbW4ZPGKgcbrY1Br56PdM69F7LkFRi1kA=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
-github.com/golang-jwt/jwt/v5 v5.2.1 h1:OuVbFODueb089Lh128TAcimifWaLhJwVflnrgM17wHk=
-github.com/golang-jwt/jwt/v5 v5.2.1/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=
-github.com/golang-migrate/migrate/v4 v4.18.2 h1:2VSCMz7x7mjyTXx3m2zPokOY82LTRgxK1yQYKo6wWQ8=
-github.com/golang-migrate/migrate/v4 v4.18.2/go.mod h1:2CM6tJvn2kqPXwnXO/d3rAQYiyoIm180VsO8PRX6Rpk=
-github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
-github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
-github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/golang-jwt/jwt/v5 v5.3.0 h1:pv4AsKCKKZuqlgs5sUmn4x8UlGa0kEVt/puTpKx9vvo=
+github.com/golang-jwt/jwt/v5 v5.3.0/go.mod h1:fxCRLWMO43lRc8nhHWY6LGqRcf+1gQWArsqaEUEa5bE=
+github.com/golang-migrate/migrate/v4 v4.19.1 h1:OCyb44lFuQfYXYLx1SCxPZQGU7mcaZ7gH9yH4jSFbBA=
+github.com/golang-migrate/migrate/v4 v4.19.1/go.mod h1:CTcgfjxhaUtsLipnLoQRWCrjYXycRz/g5+RWDuYgPrE=
+github.com/golang/snappy v0.0.1/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
+github.com/golang/snappy v0.0.4 h1:yAGX7huGHXlcLOEtBnF4w7FQwA26wojNCwOYAEhLjQM=
+github.com/golang/snappy v0.0.4/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
+github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
+github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/gofuzz v1.2.0 h1:xRy4A+RhZaiKjJ1bPfwQ8sedCA+YS2YcCHW6ec7JMi0=
 github.com/google/gofuzz v1.2.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
@@ -101,20 +178,12 @@ github.com/gorilla/handlers v1.5.2 h1:cLTUSsNkgcwhgRqvCNmdbRWG0A3N4F+M2nWKdScwyE
 github.com/gorilla/handlers v1.5.2/go.mod h1:dX+xVpaxdSw+q0Qek8SSsl3dfMk3jNddUkMzo0GtH0w=
 github.com/gorilla/mux v1.8.1 h1:TuBL49tXwgrFYWhqrNgrUNEY92u81SPhu7sTdzQEiWY=
 github.com/gorilla/mux v1.8.1/go.mod h1:AKf9I4AEqPTmMytcMc0KkNouC66V3BtZ4qD5fmWSiMQ=
-github.com/gorilla/securecookie v1.1.1/go.mod h1:ra0sb63/xPlUeL+yeDciTfxMRAA+MP+HVt/4epWDjd4=
 github.com/gorilla/securecookie v1.1.2 h1:YCIWL56dvtr73r6715mJs5ZvhtnY73hBvEF8kXD8ePA=
 github.com/gorilla/securecookie v1.1.2/go.mod h1:NfCASbcHqRSY+3a8tlWJwsQap2VX5pwzwo4h3eOamfo=
-github.com/gorilla/sessions v1.2.1/go.mod h1:dk2InVEVJ0sfLlnXv9EAgkf6ecYs/i80K/zI+bUmuGM=
 github.com/gorilla/sessions v1.4.0 h1:kpIYOp/oi6MG/p5PgxApU8srsSw9tuFbt46Lt7auzqQ=
 github.com/gorilla/sessions v1.4.0/go.mod h1:FLWm50oby91+hl7p/wRxDth9bWSuk0qVL2emc7lT5ik=
 github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg=
 github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
-github.com/hashicorp/errwrap v1.0.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
-github.com/hashicorp/errwrap v1.1.0 h1:OxrOeh75EUXMY8TBjag2fzXGZ40LB6IKw45YeGUDY2I=
-github.com/hashicorp/errwrap v1.1.0/go.mod h1:YH+1FKiLXxHSkmPseP+kNlulaMuP3n2brvKWEqk/Jc4=
-github.com/hashicorp/go-multierror v1.1.1 h1:H5DkEtf6CXdFp0N0Em5UCwQpXMWke8IA0+lD48awMYo=
-github.com/hashicorp/go-multierror v1.1.1/go.mod h1:iw975J/qwKPdAO1clOe2L8331t/9/fmwbPZ6JB6eMoM=
-github.com/hashicorp/go-uuid v1.0.2/go.mod h1:6SBZvOh/SIDV7/2o3Jml5SYk/TvGqwFJ/bN7x4byOro=
 github.com/hashicorp/go-uuid v1.0.3 h1:2gKiV6YVmrJ1i2CKKa9obLvRieoRGviZFL26PcT/Co8=
 github.com/hashicorp/go-uuid v1.0.3/go.mod h1:6SBZvOh/SIDV7/2o3Jml5SYk/TvGqwFJ/bN7x4byOro=
 github.com/hashicorp/golang-lru/v2 v2.0.7 h1:a+bsQ5rvGLjzHuww6tVxozPZFVghXaHOwFs4luLUK2k=
@@ -123,6 +192,13 @@ github.com/influxdata/influxdb-client-go/v2 v2.14.0 h1:AjbBfJuq+QoaXNcrova8smSjw
 github.com/influxdata/influxdb-client-go/v2 v2.14.0/go.mod h1:Ahpm3QXKMJslpXl3IftVLVezreAUtBOTZssDrjZEFHI=
 github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf h1:7JTmneyiNEwVBOHSjoMxiWAqB992atOeepeFYegn5RU=
 github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
+github.com/influxdata/line-protocol-corpus v0.0.0-20210519164801-ca6fa5da0184/go.mod h1:03nmhxzZ7Xk2pdG+lmMd7mHDfeVOYFyhOgwO61qWU98=
+github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937 h1:MHJNQ+p99hFATQm6ORoLmpUCF7ovjwEFshs/NHzAbig=
+github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937/go.mod h1:BKR9c0uHSmRgM/se9JhFHtTT7JTO67X23MtKMHtZcpo=
+github.com/influxdata/line-protocol/v2 v2.0.0-20210312151457-c52fdecb625a/go.mod h1:6+9Xt5Sq1rWx+glMgxhcg2c0DUaehK+5TDcPZ76GypY=
+github.com/influxdata/line-protocol/v2 v2.1.0/go.mod h1:QKw43hdUBg3GTk2iC3iyCxksNj7PX9aUSeYOYE/ceHY=
+github.com/influxdata/line-protocol/v2 v2.2.1 h1:EAPkqJ9Km4uAxtMRgUubJyqAr6zgWM0dznKMLRauQRE=
+github.com/influxdata/line-protocol/v2 v2.2.1/go.mod h1:DmB3Cnh+3oxmG6LOBIxce4oaL4CPj3OmMPgvauXh+tM=
 github.com/jcmturner/aescts/v2 v2.0.0 h1:9YKLH6ey7H4eDBXW8khjYslgyqG2xZikXP0EQFKrle8=
 github.com/jcmturner/aescts/v2 v2.0.0/go.mod h1:AiaICIRyfYg35RUkr8yESTqvSy7csK90qZ5xfvvsoNs=
 github.com/jcmturner/dnsutils/v2 v2.0.0 h1:lltnkeZGL0wILNvrNiVCR6Ro5PGU/SeBvVO/8c/iPbo=
@@ -137,19 +213,21 @@ github.com/jcmturner/rpc/v2 v2.0.3 h1:7FXXj8Ti1IaVFpSAziCZWNzbNuZmnvw/i6CqLNdWfZ
 github.com/jcmturner/rpc/v2 v2.0.3/go.mod h1:VUJYCIDm3PVOEHw8sgt091/20OJjskO/YJki3ELg/Hc=
 github.com/jmoiron/sqlx v1.4.0 h1:1PLqN7S1UYp5t4SrVVnt4nUVNemrDAtxlulVe+Qgm3o=
 github.com/jmoiron/sqlx v1.4.0/go.mod h1:ZrZ7UsYB/weZdl2Bxg6jCRO9c3YHl8r3ahlKmRT4JLY=
+github.com/joho/godotenv v1.5.1 h1:7eLL/+HRGLY0ldzfGMeQkb7vMd0as4CfYvUVzLqw0N0=
+github.com/joho/godotenv v1.5.1/go.mod h1:f4LDr5Voq0i2e/R5DDNOoa2zzDfwtkZa6DnEwAbqwq4=
 github.com/jonboulle/clockwork v0.5.0 h1:Hyh9A8u51kptdkR+cqRpT1EebBwTn1oK9YfGYbdFz6I=
 github.com/jonboulle/clockwork v0.5.0/go.mod h1:3mZlmanh0g2NDKO5TWZVJAfofYk64M7XN3SzBPjZF60=
-github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY=
-github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
 github.com/jpillora/backoff v1.0.0 h1:uvFg412JmmHBHw7iwprIxkPMI+sGQ4kzOWsMeHnm2EA=
 github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX5e0EB2j4=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
-github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
-github.com/klauspost/compress v1.17.11 h1:In6xLpyWOi1+C7tXUUWv2ot1QvBjxevKAaI6IXrJmUc=
-github.com/klauspost/compress v1.17.11/go.mod h1:pMDklpSncoRMuLFrf1W9Ss9KT+0rH90U12bZKk7uwG0=
+github.com/klauspost/compress v1.18.1 h1:bcSGx7UbpBqMChDtsF28Lw6v/G94LPrrbMbdC3JH2co=
+github.com/klauspost/compress v1.18.1/go.mod h1:ZQFFVG+MdnR0P+l6wpXgIL4NTtwiKIdBnrBd8Nrxr+0=
+github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
 github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
+github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
+github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/lann/builder v0.0.0-20180802200727-47ae307949d0 h1:SOEGU9fKiNWd/HOJuq6+3iTQz8KNCLtVX6idSoTLdUw=
@@ -159,12 +237,12 @@ github.com/lann/ps v0.0.0-20150810152359-62de8c46ede0/go.mod h1:vmVJ0l/dxyfGW6Fm
 github.com/lib/pq v1.2.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
 github.com/lib/pq v1.10.9 h1:YXG7RB+JIjhP29X+OtkiDnYaXQwpS4JEWq7dtCCRUEw=
 github.com/lib/pq v1.10.9/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o=
-github.com/mailru/easyjson v0.9.0 h1:PrnmzHw7262yW8sTBwxi1PdJA3Iw/EKBa8psRf7d9a4=
-github.com/mailru/easyjson v0.9.0/go.mod h1:1+xMtQp2MRNVL/V1bOzuP3aP8VNwRW55fQUto+XFtTU=
+github.com/linkedin/goavro/v2 v2.14.1 h1:/8VjDpd38PRsy02JS0jflAu7JZPfJcGTwqWgMkFS2iI=
+github.com/linkedin/goavro/v2 v2.14.1/go.mod h1:KXx+erlq+RPlGSPmLF7xGo6SAbh8sCQ53x064+ioxhk=
 github.com/mattn/go-sqlite3 v1.10.0/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsOqkbpncsNc=
 github.com/mattn/go-sqlite3 v1.14.22/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
-github.com/mattn/go-sqlite3 v1.14.24 h1:tpSp2G2KyMnnQu99ngJ47EIkWVmliIizyZBfPrBWDRM=
-github.com/mattn/go-sqlite3 v1.14.24/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
+github.com/mattn/go-sqlite3 v1.14.32 h1:JD12Ag3oLy1zQA+BNn74xRgaBbdhbNIDYvQUEuuErjs=
+github.com/mattn/go-sqlite3 v1.14.32/go.mod h1:Uh1q+B4BYcTPb+yiD3kU8Ct7aC0hY9fxUwlHK0RXw+Y=
 github.com/moby/docker-image-spec v1.3.1 h1:jMKff3w6PgbfSa69GfNg+zN/XLhfXJGnEx3Nl2EsFP0=
 github.com/moby/docker-image-spec v1.3.1/go.mod h1:eKmb5VW8vQEh/BAr2yvVNvuiJuY6UIocYsFu/DxxRpo=
 github.com/moby/term v0.5.0 h1:xt8Q1nalod/v7BqbG21f8mQPqH+xAaC9C3N3wfWbVP0=
@@ -180,6 +258,13 @@ github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
 github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+SVif2QVs3tOP0zanoHgBEVAwHxUSIzRqU=
 github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
+github.com/nats-io/nats.go v1.47.0 h1:YQdADw6J/UfGUd2Oy6tn4Hq6YHxCaJrVKayxxFqYrgM=
+github.com/nats-io/nats.go v1.47.0/go.mod h1:iRWIPokVIFbVijxuMQq4y9ttaBTMe0SFdlZfMDd+33g=
+github.com/nats-io/nkeys v0.4.11 h1:q44qGV008kYd9W1b1nEBkNzvnWxtRSQ7A8BoqRrcfa0=
+github.com/nats-io/nkeys v0.4.11/go.mod h1:szDimtgmfOi9n25JpfIdGw12tZFYXqhGxjhVxsatHVE=
+github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw=
+github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OSON2c=
+github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
 github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmtpMYro=
 github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg=
 github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
@@ -189,22 +274,23 @@ github.com/opencontainers/image-spec v1.1.0/go.mod h1:W4s4sFTMaBeK1BQLXbG4AdM2sz
 github.com/opentracing/opentracing-go v1.1.0/go.mod h1:UkNAQd3GIcIGf0SeVgPpRdFStlNbqXla1AfSYxPUl2o=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
-github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
-github.com/prometheus/client_golang v1.21.0 h1:DIsaGmiaBkSangBgMtWdNfxbMNdku5IK6iNhrEqWvdA=
-github.com/prometheus/client_golang v1.21.0/go.mod h1:U9NM32ykUErtVBxdvD3zfi+EuFkkaBvMb09mIfe0Zgg=
-github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E=
-github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
-github.com/prometheus/common v0.62.0 h1:xasJaQlnWAeyHdUBeGjXmutelfJHWMRr+Fg4QszZ2Io=
-github.com/prometheus/common v0.62.0/go.mod h1:vyBcEuLSvWos9B1+CyL7JZ2up+uFzXhkqml0W5zIY1I=
-github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
-github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
+github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/prometheus/client_golang v1.23.2 h1:Je96obch5RDVy3FDMndoUsjAhG5Edi49h0RJWRi/o0o=
+github.com/prometheus/client_golang v1.23.2/go.mod h1:Tb1a6LWHB3/SPIzCoaDXI4I8UHKeFTEQ1YCr+0Gyqmg=
+github.com/prometheus/client_model v0.6.2 h1:oBsgwpGs7iVziMvrGhE53c/GrLUsZdHnqNwqPLxwZyk=
+github.com/prometheus/client_model v0.6.2/go.mod h1:y3m2F6Gdpfy6Ut/GBsUqTWZqCUvMVzSfMLjcu6wAwpE=
+github.com/prometheus/common v0.67.4 h1:yR3NqWO1/UyO1w2PhUvXlGQs/PtFmoveVO0KZ4+Lvsc=
+github.com/prometheus/common v0.67.4/go.mod h1:gP0fq6YjjNCLssJCQp0yk4M8W6ikLURwkdd/YKtTbyI=
+github.com/prometheus/procfs v0.16.1 h1:hZ15bTNuirocR6u0JZ6BAHHmwS1p8B4P6MRqxtzMyRg=
+github.com/prometheus/procfs v0.16.1/go.mod h1:teAbpZRB1iIAJYREa1LsoWUXykVXA1KlTmWl8x/U+Is=
 github.com/qustavo/sqlhooks/v2 v2.1.0 h1:54yBemHnGHp/7xgT+pxwmIlMSDNYKx5JW5dfRAiCZi0=
 github.com/qustavo/sqlhooks/v2 v2.1.0/go.mod h1:aMREyKo7fOKTwiLuWPsaHRXEmtqG4yREztO0idF83AU=
 github.com/robfig/cron/v3 v3.0.1 h1:WdRxkvbJztn8LMz/QEvLN5sBU+xKpSqwwUO1Pjr4qDs=
 github.com/robfig/cron/v3 v3.0.1/go.mod h1:eQICP3HwyT7UooqI/z+Ov+PtYAWygg1TEWWzGIFLtro=
-github.com/rogpeppe/go-internal v1.12.0 h1:exVL4IDcn6na9z1rAb56Vxr+CgyK3nn3O+epU5NdKM8=
-github.com/rogpeppe/go-internal v1.12.0/go.mod h1:E+RYuTGaKKdloAfM02xzb0FW3Paa99yedzYV+kq4uf4=
+github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=
+github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=
 github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 h1:lZUw3E0/J3roVtGQ+SCrUrg3ON6NgVqpn3+iol9aGu4=
@@ -213,139 +299,105 @@ github.com/sergi/go-diff v1.3.1 h1:xkr+Oxo4BOQKmkn/B9eMK0g5Kg/983T9DqqPHwYqD+8=
 github.com/sergi/go-diff v1.3.1/go.mod h1:aMJSSKb2lpPvRNec0+w3fl7LP9IOFzdc9Pa4NFbPK1I=
 github.com/sosodev/duration v1.3.1 h1:qtHBDMQ6lvMQsL15g4aopM4HEfOaYuhWBw3NPTtlqq4=
 github.com/sosodev/duration v1.3.1/go.mod h1:RQIBBX0+fMLc/D9+Jb/fwvVmo0eZvDDEERAikUR6SDg=
-github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
-github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
+github.com/stretchr/objx v0.5.2 h1:xuMeJ0Sdp5ZMRXx/aWO6RZxdr3beISkG5/G/aIRr3pY=
+github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
 github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
-github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
-github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
-github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
-github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/stretchr/testify v1.7.5/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
+github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
+github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
 github.com/swaggo/files v1.0.1 h1:J1bVJ4XHZNq0I46UU90611i9/YzdrF7x92oX1ig5IdE=
 github.com/swaggo/files v1.0.1/go.mod h1:0qXmMNH6sXNf+73t65aKeB+ApmgxdnkQzVTAj2uaMUg=
 github.com/swaggo/http-swagger v1.3.4 h1:q7t/XLx0n15H1Q9/tk3Y9L4n210XzJF5WtnDX64a5ww=
 github.com/swaggo/http-swagger v1.3.4/go.mod h1:9dAh0unqMBAlbp1uE2Uc2mQTxNMU/ha4UbucIg1MFkQ=
-github.com/swaggo/swag v1.16.4 h1:clWJtd9LStiG3VeijiCfOVODP6VpHtKdQy9ELFG3s1A=
-github.com/swaggo/swag v1.16.4/go.mod h1:VBsHJRsDvfYvqoiMKnsdwhNV9LEMHgEDZcyVYX0sxPg=
-github.com/urfave/cli/v2 v2.27.5 h1:WoHEJLdsXr6dDWoJgMq/CboDmyY/8HMMH1fTECbih+w=
-github.com/urfave/cli/v2 v2.27.5/go.mod h1:3Sevf16NykTbInEnD0yKkjDAeZDS0A6bzhBH5hrMvTQ=
-github.com/vektah/gqlparser/v2 v2.5.22 h1:yaaeJ0fu+nv1vUMW0Hl+aS1eiv1vMfapBNjpffAda1I=
-github.com/vektah/gqlparser/v2 v2.5.22/go.mod h1:xMl+ta8a5M1Yo1A1Iwt/k7gSpscwSnHZdw7tfhEGfTM=
-github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1 h1:gEOO8jv9F4OT7lGCjxCBTO/36wtF6j2nSip77qHd4x4=
-github.com/xrash/smetrics v0.0.0-20240521201337-686a1a2994c1/go.mod h1:Ohn+xnUBiLI6FVj/9LpzZWtj1/D6lUovWYBkxHVV3aM=
+github.com/swaggo/swag v1.16.6 h1:qBNcx53ZaX+M5dxVyTrgQ0PJ/ACK+NzhwcbieTt+9yI=
+github.com/swaggo/swag v1.16.6/go.mod h1:ngP2etMK5a0P3QBizic5MEwpRmluJZPHjXcMoj4Xesg=
+github.com/urfave/cli/v2 v2.27.7 h1:bH59vdhbjLv3LAvIu6gd0usJHgoTTPhCFib8qqOwXYU=
+github.com/urfave/cli/v2 v2.27.7/go.mod h1:CyNAG/xg+iAOg0N4MPGZqVmv2rCoP267496AOXUZjA4=
+github.com/urfave/cli/v3 v3.6.1 h1:j8Qq8NyUawj/7rTYdBGrxcH7A/j7/G8Q5LhWEW4G3Mo=
+github.com/urfave/cli/v3 v3.6.1/go.mod h1:ysVLtOEmg2tOy6PknnYVhDoouyC/6N42TMeoMzskhso=
+github.com/vektah/gqlparser/v2 v2.5.31 h1:YhWGA1mfTjID7qJhd1+Vxhpk5HTgydrGU9IgkWBTJ7k=
+github.com/vektah/gqlparser/v2 v2.5.31/go.mod h1:c1I28gSOVNzlfc4WuDlqU7voQnsqI6OG2amkBAFmgts=
+github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342 h1:FnBeRrxr7OU4VvAzt5X7s6266i6cSVkkFPS0TuXWbIg=
+github.com/xrash/smetrics v0.0.0-20250705151800-55b8f293f342/go.mod h1:Ohn+xnUBiLI6FVj/9LpzZWtj1/D6lUovWYBkxHVV3aM=
 github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
-go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0 h1:TT4fX+nBOA/+LUkobKGW1ydGcn+G3vRw9+g5HwCphpk=
-go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.54.0/go.mod h1:L7UH0GbB0p47T4Rri3uHjbpCFYrVrwc1I25QhNPiGK8=
-go.opentelemetry.io/otel v1.29.0 h1:PdomN/Al4q/lN6iBJEN3AwPvUiHPMlt93c8bqTG5Llw=
-go.opentelemetry.io/otel v1.29.0/go.mod h1:N/WtXPs1CNCUEx+Agz5uouwCba+i+bJGFicT8SR4NP8=
-go.opentelemetry.io/otel/metric v1.29.0 h1:vPf/HFWTNkPu1aYeIsc98l4ktOQaL6LeSoeV2g+8YLc=
-go.opentelemetry.io/otel/metric v1.29.0/go.mod h1:auu/QWieFVWx+DmQOUMgj0F8LHWdgalxXqvp7BII/W8=
-go.opentelemetry.io/otel/trace v1.29.0 h1:J/8ZNK4XgR7a21DZUAsbF8pZ5Jcw1VhACmnYt39JTi4=
-go.opentelemetry.io/otel/trace v1.29.0/go.mod h1:eHl3w0sp3paPkYstJOmAimxhiFXPg+MMTlEh3nsQgWQ=
-go.uber.org/atomic v1.11.0 h1:ZvwS0R+56ePWxUNi+Atn9dWONBPp/AUETXlHW0DxSjE=
-go.uber.org/atomic v1.11.0/go.mod h1:LUxbIzbOniOlMKjJjyPfpl4v+PKK2cNJn91OQbhoJI0=
+go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
+go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0 h1:F7Jx+6hwnZ41NSFTO5q4LYDtJRXBf2PD0rNBkeB/lus=
+go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.61.0/go.mod h1:UHB22Z8QsdRDrnAtX4PntOl36ajSxcdUMt1sF7Y6E7Q=
+go.opentelemetry.io/otel v1.37.0 h1:9zhNfelUvx0KBfu/gb+ZgeAfAgtWrfHJZcAqFC228wQ=
+go.opentelemetry.io/otel v1.37.0/go.mod h1:ehE/umFRLnuLa/vSccNq9oS1ErUlkkK71gMcN34UG8I=
+go.opentelemetry.io/otel/metric v1.37.0 h1:mvwbQS5m0tbmqML4NqK+e3aDiO02vsf/WgbsdpcPoZE=
+go.opentelemetry.io/otel/metric v1.37.0/go.mod h1:04wGrZurHYKOc+RKeye86GwKiTb9FKm1WHtO+4EVr2E=
+go.opentelemetry.io/otel/trace v1.37.0 h1:HLdcFNbRQBE2imdSEgm/kwqmQj1Or1l/7bW6mxVK7z4=
+go.opentelemetry.io/otel/trace v1.37.0/go.mod h1:TlgrlQ+PtQO5XFerSPUYG0JSgGyryXewPGyayAWSBS0=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
+go.yaml.in/yaml/v2 v2.4.3 h1:6gvOSjQoTB3vt1l+CU+tSyi/HOjfOjRLJ4YwYZGwRO0=
+go.yaml.in/yaml/v2 v2.4.3/go.mod h1:zSxWcmIDjOzPXpjlTTbAsKokqkDNAVtZO0WOMiT90s8=
+go.yaml.in/yaml/v3 v3.0.4 h1:tfq32ie2Jv2UxXFdLJdh3jXuOzWiL1fo0bu/FbuKpbc=
+go.yaml.in/yaml/v3 v3.0.4/go.mod h1:DhzuOOF2ATzADvBadXxruRBLzYTpT36CKvDb3+aBEFg=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
-golang.org/x/crypto v0.6.0/go.mod h1:OFC/31mSvZgRz0V1QTNCzfAI1aIRzbiufJtkMIlEp58=
-golang.org/x/crypto v0.13.0/go.mod h1:y6Z2r+Rw4iayiXXAIxJIDAJ1zMW4yaTpebo8fPOliYc=
-golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
-golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
-golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
-golang.org/x/crypto v0.35.0 h1:b15kiHdrGCHrP6LvwaQ3c03kgNhhiMgvlhxHQhmg2Xs=
-golang.org/x/crypto v0.35.0/go.mod h1:dy7dXNW32cAb/6/PRuTNsix8T+vJAqvuIy5Bli/x0YQ=
-golang.org/x/exp v0.0.0-20250218142911-aa4b98e5adaa h1:t2QcU6V556bFjYgu4L6C+6VrCPyJZ+eyRsABUPs1mz4=
-golang.org/x/exp v0.0.0-20250218142911-aa4b98e5adaa/go.mod h1:BHOTPb3L19zxehTsLoJXVaTktb06DFgmdW6Wb9s8jqk=
+golang.org/x/crypto v0.46.0 h1:cKRW/pmt1pKAfetfu+RCEvjvZkA9RimPbh7bhFjGVBU=
+golang.org/x/crypto v0.46.0/go.mod h1:Evb/oLKmMraqjZ2iQTwDwvCtJkczlDuTmdJXoZVzqU0=
+golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b h1:M2rDM6z3Fhozi9O7NWsxAkg/yqS/lQJ6PmkyIV3YP+o=
+golang.org/x/exp v0.0.0-20250620022241-b7579e27df2b/go.mod h1:3//PLf8L/X+8b4vuAfHzxeRUl04Adcb341+IGKfnqS8=
 golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
-golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
-golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
-golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
-golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
-golang.org/x/mod v0.23.0 h1:Zb7khfcRGKk+kqfxFaP5tZqCnDZMjC5VtUBs87Hr6QM=
-golang.org/x/mod v0.23.0/go.mod h1:6SkKJ3Xj0I0BrPOZoBy3bdMptDDU9oJrpohJ3eWZ1fY=
+golang.org/x/mod v0.31.0 h1:HaW9xtz0+kOcWKwli0ZXy79Ix+UW/vOfmWI5QVd2tgI=
+golang.org/x/mod v0.31.0/go.mod h1:43JraMp9cGx1Rx3AqioxrbrhNsLl2l/iNAvuBkrezpg=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
-golang.org/x/net v0.0.0-20200114155413-6afb5195e5aa/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
-golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
 golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
-golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
-golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk=
-golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
-golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
-golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
-golang.org/x/net v0.35.0 h1:T5GQRQb2y08kTAByq9L4/bz8cipCdA8FbRTXewonqY8=
-golang.org/x/net v0.35.0/go.mod h1:EglIi67kWsHKlRzzVMUD93VMSWGFOMSZgxFjparz1Qk=
-golang.org/x/oauth2 v0.27.0 h1:da9Vo7/tDv5RH/7nZDz1eMGS/q1Vv1N/7FCrBhI9I3M=
-golang.org/x/oauth2 v0.27.0/go.mod h1:onh5ek6nERTohokkhCD/y2cV4Do3fxFHFuAejCkRWT8=
+golang.org/x/net v0.48.0 h1:zyQRTTrjc33Lhh0fBgT/H3oZq9WuvRR5gPC70xpDiQU=
+golang.org/x/net v0.48.0/go.mod h1:+ndRgGjkh8FGtu1w1FGbEC31if4VrNVMuKTgcAAnQRY=
+golang.org/x/oauth2 v0.34.0 h1:hqK/t4AKgbqWkdkcAeI8XLmbK+4m4G5YeQRrmiotGlw=
+golang.org/x/oauth2 v0.34.0/go.mod h1:lzm5WQJQwKZ3nwavOZ3IS5Aulzxi68dUSgRHujetwEA=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=
-golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
-golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
-golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
-golang.org/x/sync v0.11.0 h1:GGz8+XQP4FvTTrjZPzNKTMFtSXH80RAzG+5ghFPgK9w=
-golang.org/x/sync v0.11.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.19.0 h1:vV+1eWNmZ5geRlYjzm2adRgW2/mcpevXNg50YZtPCE4=
+golang.org/x/sync v0.19.0/go.mod h1:9KTHXmSnoGruLpwFjVSX0lNNA75CykiMECbovNTZqGI=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.30.0 h1:QjkSwP/36a20jFYWkSue1YwXzLmsV5Gfq7Eiy72C1uc=
-golang.org/x/sys v0.30.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=
+golang.org/x/sys v0.39.0 h1:CvCKL8MeisomCi6qNZ+wbb0DN9E5AATixKsvNtMoMFk=
+golang.org/x/sys v0.39.0/go.mod h1:OgkHotnGiDImocRcuBABYBEXf8A9a87e/uXjp9XT3ks=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
-golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
-golang.org/x/term v0.12.0/go.mod h1:owVbMEjm3cBLCHdkQu9b1opXd4ETQWc3BhuQGKgXgvU=
-golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
-golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
-golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
 golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
-golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
-golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
-golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
-golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
-golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
-golang.org/x/text v0.22.0 h1:bofq7m3/HAFvbF51jz3Q9wLg3jkvSPuiZu/pD1XwgtM=
-golang.org/x/text v0.22.0/go.mod h1:YRoo4H8PVmsu+E3Ou7cqLVH8oXWIHVoX0jqUWALQhfY=
-golang.org/x/time v0.5.0 h1:o7cqy6amK/52YcAKIPlM3a+Fpj35zvRj2TP+e1xFSfk=
-golang.org/x/time v0.5.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
+golang.org/x/text v0.32.0 h1:ZD01bjUt1FQ9WJ0ClOL5vxgxOI/sVCNgX1YtKwcY0mU=
+golang.org/x/text v0.32.0/go.mod h1:o/rUWzghvpD5TXrTIBuJU77MTaN0ljMWE47kxGJQ7jY=
+golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
+golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
-golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
-golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=
-golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
-golang.org/x/tools v0.30.0 h1:BgcpHewrV5AUp2G9MebG4XPFI1E2W41zU1SaqVA9vJY=
-golang.org/x/tools v0.30.0/go.mod h1:c347cR/OJfw5TI+GfX7RUPNMdDRRbjvYTS0jPyvsVtY=
+golang.org/x/tools v0.40.0 h1:yLkxfA+Qnul4cs9QA3KnlFu0lVmd8JJfoq+E41uSutA=
+golang.org/x/tools v0.40.0/go.mod h1:Ik/tzLRlbscWpqqMRjyWYDisX8bG13FrdXp3o4Sr9lc=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-google.golang.org/protobuf v1.36.5 h1:tPhr+woSbjfYvY6/GPufUoYizxw1cF/yFoxJ2fmpwlM=
-google.golang.org/protobuf v1.36.5/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
+golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/protobuf v1.36.11 h1:fV6ZwhNocDyBLK0dj+fg8ektcVegBBuEolpbTQyBNVE=
+google.golang.org/protobuf v1.36.11/go.mod h1:HTf+CrKn2C3g5S8VImy6tdcUvCska2kB7j23XfzDpco=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
-gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
-gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
-sigs.k8s.io/yaml v1.4.0 h1:Mk1wCc2gy/F0THH0TAp1QYyJNzRm2KCLy3o5ASXVI5E=
-sigs.k8s.io/yaml v1.4.0/go.mod h1:Ejl7/uTz7PSA4eKMyQCUTnhZYNmLIl+5c2lQPGR2BPY=
+sigs.k8s.io/yaml v1.6.0 h1:G8fkbMSAFqgEFgh4b1wmtzDnioxFCUgTZhlbj5P9QYs=
+sigs.k8s.io/yaml v1.6.0/go.mod h1:796bPqUfzR/0jLAl6XjHl3Ck7MiyVv8dbTdyT3/pMf4=

gqlgen.yml

@@ -32,6 +32,7 @@ resolver:
 autobind:
   - "github.com/99designs/gqlgen/graphql/introspection"
   - "github.com/ClusterCockpit/cc-backend/internal/graph/model"
+  - "github.com/ClusterCockpit/cc-backend/internal/config"
 
 # This section declares type mapping between the GraphQL and go type systems
 #
@@ -51,61 +52,51 @@ models:
       - github.com/99designs/gqlgen/graphql.Int64
       - github.com/99designs/gqlgen/graphql.Int32
   Job:
-    model: "github.com/ClusterCockpit/cc-backend/pkg/schema.Job"
+    model: "github.com/ClusterCockpit/cc-lib/schema.Job"
     fields:
       tags:
         resolver: true
       metaData:
         resolver: true
   Cluster:
-    model: "github.com/ClusterCockpit/cc-backend/pkg/schema.Cluster"
+    model: "github.com/ClusterCockpit/cc-lib/schema.Cluster"
     fields:
       partitions:
         resolver: true
-  NullableFloat:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.Float" }
-  MetricScope:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.MetricScope" }
-  MetricValue:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.MetricValue" }
+  # Node:
+  #   model: "github.com/ClusterCockpit/cc-lib/schema.Node"
+  #   fields:
+  #     metaData:
+  #       resolver: true
+  NullableFloat: { model: "github.com/ClusterCockpit/cc-lib/schema.Float" }
+  MetricScope: { model: "github.com/ClusterCockpit/cc-lib/schema.MetricScope" }
+  MetricValue: { model: "github.com/ClusterCockpit/cc-lib/schema.MetricValue" }
   JobStatistics:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.JobStatistics" }
+    { model: "github.com/ClusterCockpit/cc-lib/schema.JobStatistics" }
   GlobalMetricListItem:
-    {
-      model: "github.com/ClusterCockpit/cc-backend/pkg/schema.GlobalMetricListItem",
-    }
+    { model: "github.com/ClusterCockpit/cc-lib/schema.GlobalMetricListItem" }
   ClusterSupport:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.ClusterSupport" }
-  Tag: { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.Tag" }
-  Resource:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.Resource" }
-  JobState:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.JobState" }
-  TimeRange:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.TimeRange" }
-  IntRange:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.IntRange" }
-  JobMetric:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.JobMetric" }
-  Series: { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.Series" }
+    { model: "github.com/ClusterCockpit/cc-lib/schema.ClusterSupport" }
+  Tag: { model: "github.com/ClusterCockpit/cc-lib/schema.Tag" }
+  Resource: { model: "github.com/ClusterCockpit/cc-lib/schema.Resource" }
+  JobState: { model: "github.com/ClusterCockpit/cc-lib/schema.JobState" }
+  Node: { model: "github.com/ClusterCockpit/cc-lib/schema.Node" }
+  SchedulerState:
+    { model: "github.com/ClusterCockpit/cc-lib/schema.SchedulerState" }
+  HealthState:
+    { model: "github.com/ClusterCockpit/cc-lib/schema.MonitoringState" }
+  JobMetric: { model: "github.com/ClusterCockpit/cc-lib/schema.JobMetric" }
+  Series: { model: "github.com/ClusterCockpit/cc-lib/schema.Series" }
   MetricStatistics:
-    {
-      model: "github.com/ClusterCockpit/cc-backend/pkg/schema.MetricStatistics",
-    }
+    { model: "github.com/ClusterCockpit/cc-lib/schema.MetricStatistics" }
   MetricConfig:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.MetricConfig" }
+    { model: "github.com/ClusterCockpit/cc-lib/schema.MetricConfig" }
   SubClusterConfig:
-    {
-      model: "github.com/ClusterCockpit/cc-backend/pkg/schema.SubClusterConfig",
-    }
-  Accelerator:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.Accelerator" }
-  Topology:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.Topology" }
+    { model: "github.com/ClusterCockpit/cc-lib/schema.SubClusterConfig" }
+  Accelerator: { model: "github.com/ClusterCockpit/cc-lib/schema.Accelerator" }
+  Topology: { model: "github.com/ClusterCockpit/cc-lib/schema.Topology" }
   FilterRanges:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.FilterRanges" }
-  SubCluster:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.SubCluster" }
-  StatsSeries:
-    { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.StatsSeries" }
-  Unit: { model: "github.com/ClusterCockpit/cc-backend/pkg/schema.Unit" }
+    { model: "github.com/ClusterCockpit/cc-lib/schema.FilterRanges" }
+  SubCluster: { model: "github.com/ClusterCockpit/cc-lib/schema.SubCluster" }
+  StatsSeries: { model: "github.com/ClusterCockpit/cc-lib/schema.StatsSeries" }
+  Unit: { model: "github.com/ClusterCockpit/cc-lib/schema.Unit" }

internal/api/api_test.go

@@ -1,5 +1,5 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package api_test
@@ -27,24 +27,32 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	"github.com/gorilla/mux"
 
 	_ "github.com/mattn/go-sqlite3"
 )
 
-func setup(t *testing.T) *api.RestApi {
+func setup(t *testing.T) *api.RestAPI {
 	const testconfig = `{
+		"main": {
 	"addr":            "0.0.0.0:8080",
 	"validate": false,
+  "apiAllowedIPs": [
+    "*"
+  ]
+	},
 	"archive": {
 		"kind": "file",
 		"path": "./var/job-archive"
 	},
-    "jwts": {
-        "max-age": "2m"
-    },
+	"auth": {
+  "jwts": {
+      "max-age": "2m"
+  }
+	},
 	"clusters": [
 	{
 	   "name": "testcluster",
@@ -57,7 +65,7 @@ func setup(t *testing.T) *api.RestApi {
 	}
 	]
 }`
-	const testclusterJson = `{
+	const testclusterJSON = `{
         "name": "testcluster",
 		"subClusters": [
 			{
@@ -113,22 +121,22 @@ func setup(t *testing.T) *api.RestApi {
 		]
 	}`
 
-	log.Init("info", true)
+	cclog.Init("info", true)
 	tmpdir := t.TempDir()
 	jobarchive := filepath.Join(tmpdir, "job-archive")
-	if err := os.Mkdir(jobarchive, 0777); err != nil {
+	if err := os.Mkdir(jobarchive, 0o777); err != nil {
 		t.Fatal(err)
 	}
 
-	if err := os.WriteFile(filepath.Join(jobarchive, "version.txt"), []byte(fmt.Sprintf("%d", 2)), 0666); err != nil {
+	if err := os.WriteFile(filepath.Join(jobarchive, "version.txt"), fmt.Appendf(nil, "%d", 3), 0o666); err != nil {
 		t.Fatal(err)
 	}
 
-	if err := os.Mkdir(filepath.Join(jobarchive, "testcluster"), 0777); err != nil {
+	if err := os.Mkdir(filepath.Join(jobarchive, "testcluster"), 0o777); err != nil {
 		t.Fatal(err)
 	}
 
-	if err := os.WriteFile(filepath.Join(jobarchive, "testcluster", "cluster.json"), []byte(testclusterJson), 0666); err != nil {
+	if err := os.WriteFile(filepath.Join(jobarchive, "testcluster", "cluster.json"), []byte(testclusterJSON), 0o666); err != nil {
 		t.Fatal(err)
 	}
 
@@ -139,11 +147,22 @@ func setup(t *testing.T) *api.RestApi {
 	}
 
 	cfgFilePath := filepath.Join(tmpdir, "config.json")
-	if err := os.WriteFile(cfgFilePath, []byte(testconfig), 0666); err != nil {
+	if err := os.WriteFile(cfgFilePath, []byte(testconfig), 0o666); err != nil {
 		t.Fatal(err)
 	}
 
-	config.Init(cfgFilePath)
+	ccconf.Init(cfgFilePath)
+
+	// Load and check main configuration
+	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
+		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
+			config.Init(cfg, clustercfg)
+		} else {
+			cclog.Abort("Cluster configuration must be present")
+		}
+	} else {
+		cclog.Abort("Main configuration must be present")
+	}
 	archiveCfg := fmt.Sprintf("{\"kind\": \"file\",\"path\": \"%s\"}", jobarchive)
 
 	repository.Connect("sqlite3", dbfilepath)
@@ -156,14 +175,25 @@ func setup(t *testing.T) *api.RestApi {
 		t.Fatal(err)
 	}
 
-	archiver.Start(repository.GetJobRepository())
-	auth.Init()
+	archiver.Start(repository.GetJobRepository(), context.Background())
+
+	if cfg := ccconf.GetPackageConfig("auth"); cfg != nil {
+		auth.Init(&cfg)
+	} else {
+		cclog.Warn("Authentication disabled due to missing configuration")
+		auth.Init(nil)
+	}
+
 	graph.Init()
 
 	return api.New()
 }
 
 func cleanup() {
+	// Gracefully shutdown archiver with timeout
+	if err := archiver.Shutdown(5 * time.Second); err != nil {
+		cclog.Warnf("Archiver shutdown timeout in tests: %v", err)
+	}
 	// TODO: Clear all caches, reset all modules, etc...
 }
 
@@ -198,14 +228,14 @@ func TestRestApi(t *testing.T) {
 	r := mux.NewRouter()
 	r.PathPrefix("/api").Subrouter()
 	r.StrictSlash(true)
-	restapi.MountApiRoutes(r)
+	restapi.MountAPIRoutes(r)
 
 	var TestJobId int64 = 123
-	var TestClusterName string = "testcluster"
+	TestClusterName := "testcluster"
 	var TestStartTime int64 = 123456789
 
 	const startJobBody string = `{
-        "jobId":            123,
+    "jobId":            123,
 		"user":             "testuser",
 		"project":          "testproj",
 		"cluster":          "testcluster",
@@ -215,10 +245,9 @@ func TestRestApi(t *testing.T) {
 		"numNodes":         1,
 		"numHwthreads":     8,
 		"numAcc":           0,
-		"exclusive":        1,
+		"shared":           "none",
 		"monitoringStatus": 1,
 		"smt":              1,
-		"tags":             [{ "type": "testTagType", "name": "testTagName", "scope": "testuser" }],
 		"resources": [
 			{
 				"hostname": "host123",
@@ -249,16 +278,17 @@ func TestRestApi(t *testing.T) {
 		if response.StatusCode != http.StatusCreated {
 			t.Fatal(response.Status, recorder.Body.String())
 		}
-		resolver := graph.GetResolverInstance()
+		// resolver := graph.GetResolverInstance()
+		restapi.JobRepository.SyncJobs()
 		job, err := restapi.JobRepository.Find(&TestJobId, &TestClusterName, &TestStartTime)
 		if err != nil {
 			t.Fatal(err)
 		}
 
-		job.Tags, err = resolver.Job().Tags(ctx, job)
-		if err != nil {
-			t.Fatal(err)
-		}
+		// job.Tags, err = resolver.Job().Tags(ctx, job)
+		// if err != nil {
+		// 	t.Fatal(err)
+		// }
 
 		if job.JobID != 123 ||
 			job.User != "testuser" ||
@@ -267,21 +297,20 @@ func TestRestApi(t *testing.T) {
 			job.SubCluster != "sc1" ||
 			job.Partition != "default" ||
 			job.Walltime != 3600 ||
-			job.ArrayJobId != 0 ||
+			job.ArrayJobID != 0 ||
 			job.NumNodes != 1 ||
 			job.NumHWThreads != 8 ||
 			job.NumAcc != 0 ||
-			job.Exclusive != 1 ||
 			job.MonitoringStatus != 1 ||
 			job.SMT != 1 ||
 			!reflect.DeepEqual(job.Resources, []*schema.Resource{{Hostname: "host123", HWThreads: []int{0, 1, 2, 3, 4, 5, 6, 7}}}) ||
-			job.StartTime.Unix() != 123456789 {
+			job.StartTime != 123456789 {
 			t.Fatalf("unexpected job properties: %#v", job)
 		}
 
-		if len(job.Tags) != 1 || job.Tags[0].Type != "testTagType" || job.Tags[0].Name != "testTagName" || job.Tags[0].Scope != "testuser" {
-			t.Fatalf("unexpected tags: %#v", job.Tags)
-		}
+		// if len(job.Tags) != 1 || job.Tags[0].Type != "testTagType" || job.Tags[0].Name != "testTagName" || job.Tags[0].Scope != "testuser" {
+		// 	t.Fatalf("unexpected tags: %#v", job.Tags)
+		// }
 	}); !ok {
 		return
 	}
@@ -308,7 +337,7 @@ func TestRestApi(t *testing.T) {
 			t.Fatal(response.Status, recorder.Body.String())
 		}
 
-		archiver.WaitForArchiving()
+		// Archiving happens asynchronously, will be completed in cleanup
 		job, err := restapi.JobRepository.Find(&TestJobId, &TestClusterName, &TestStartTime)
 		if err != nil {
 			t.Fatal(err)
@@ -349,7 +378,7 @@ func TestRestApi(t *testing.T) {
 
 	t.Run("CheckDoubleStart", func(t *testing.T) {
 		// Starting a job with the same jobId and cluster should only be allowed if the startTime is far appart!
-		body := strings.Replace(startJobBody, `"startTime": 123456789`, `"startTime": 123456790`, -1)
+		body := strings.ReplaceAll(startJobBody, `"startTime": 123456789`, `"startTime": 123456790`)
 
 		req := httptest.NewRequest(http.MethodPost, "/jobs/start_job/", bytes.NewBuffer([]byte(body)))
 		recorder := httptest.NewRecorder()
@@ -371,7 +400,7 @@ func TestRestApi(t *testing.T) {
 		"partition":        "default",
 		"walltime":         3600,
 		"numNodes":         1,
-		"exclusive":        1,
+		"shared":        	"none",
 		"monitoringStatus": 1,
 		"smt":              1,
 		"resources": [
@@ -399,6 +428,7 @@ func TestRestApi(t *testing.T) {
 	}
 
 	time.Sleep(1 * time.Second)
+	restapi.JobRepository.SyncJobs()
 
 	const stopJobBodyFailed string = `{
     "jobId":     12345,
@@ -420,7 +450,7 @@ func TestRestApi(t *testing.T) {
 			t.Fatal(response.Status, recorder.Body.String())
 		}
 
-		archiver.WaitForArchiving()
+		// Archiving happens asynchronously, will be completed in cleanup
 		jobid, cluster := int64(12345), "testcluster"
 		job, err := restapi.JobRepository.Find(&jobid, &cluster, nil)
 		if err != nil {

internal/api/cluster.go

@@ -0,0 +1,71 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package api
+
+import (
+	"bufio"
+	"encoding/json"
+	"fmt"
+	"net/http"
+
+	"github.com/ClusterCockpit/cc-backend/internal/repository"
+	"github.com/ClusterCockpit/cc-backend/pkg/archive"
+	"github.com/ClusterCockpit/cc-lib/schema"
+)
+
+// GetClustersAPIResponse model
+type GetClustersAPIResponse struct {
+	Clusters []*schema.Cluster `json:"clusters"` // Array of clusters
+}
+
+// getClusters godoc
+// @summary     Lists all cluster configs
+// @tags Cluster query
+// @description Get a list of all cluster configs. Specific cluster can be requested using query parameter.
+// @produce     json
+// @param       cluster        query    string            false "Job Cluster"
+// @success     200            {object} api.GetClustersApiResponse  "Array of clusters"
+// @failure     400            {object} api.ErrorResponse       "Bad Request"
+// @failure     401            {object} api.ErrorResponse       "Unauthorized"
+// @failure     403            {object} api.ErrorResponse       "Forbidden"
+// @failure     500            {object} api.ErrorResponse       "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /api/clusters/ [get]
+func (api *RestAPI) getClusters(rw http.ResponseWriter, r *http.Request) {
+	if user := repository.GetUserFromContext(r.Context()); user != nil &&
+		!user.HasRole(schema.RoleApi) {
+
+		handleError(fmt.Errorf("missing role: %v", schema.GetRoleString(schema.RoleApi)), http.StatusForbidden, rw)
+		return
+	}
+
+	rw.Header().Add("Content-Type", "application/json")
+	bw := bufio.NewWriter(rw)
+	defer bw.Flush()
+
+	var clusters []*schema.Cluster
+
+	if r.URL.Query().Has("cluster") {
+		name := r.URL.Query().Get("cluster")
+		cluster := archive.GetCluster(name)
+		if cluster == nil {
+			handleError(fmt.Errorf("unknown cluster: %s", name), http.StatusBadRequest, rw)
+			return
+		}
+		clusters = append(clusters, cluster)
+	} else {
+		clusters = archive.Clusters
+	}
+
+	payload := GetClustersAPIResponse{
+		Clusters: clusters,
+	}
+
+	if err := json.NewEncoder(bw).Encode(payload); err != nil {
+		handleError(err, http.StatusInternalServerError, rw)
+		return
+	}
+}

internal/api/memorystore.go

@@ -0,0 +1,170 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package api
+
+import (
+	"bufio"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+
+	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+
+	"github.com/influxdata/line-protocol/v2/lineprotocol"
+)
+
+// handleFree godoc
+// @summary
+// @tags free
+// @description This endpoint allows the users to free the Buffers from the
+// metric store. This endpoint offers the users to remove then systematically
+// and also allows then to prune the data under node, if they do not want to
+// remove the whole node.
+// @produce     json
+// @param       to        query    string        false  "up to timestamp"
+// @success     200            {string} string  "ok"
+// @failure     400            {object} api.ErrorResponse       "Bad Request"
+// @failure     401            {object} api.ErrorResponse       "Unauthorized"
+// @failure     403            {object} api.ErrorResponse       "Forbidden"
+// @failure     500            {object} api.ErrorResponse       "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /free/ [post]
+func freeMetrics(rw http.ResponseWriter, r *http.Request) {
+	rawTo := r.URL.Query().Get("to")
+	if rawTo == "" {
+		handleError(errors.New("'to' is a required query parameter"), http.StatusBadRequest, rw)
+		return
+	}
+
+	to, err := strconv.ParseInt(rawTo, 10, 64)
+	if err != nil {
+		handleError(err, http.StatusInternalServerError, rw)
+		return
+	}
+
+	bodyDec := json.NewDecoder(r.Body)
+	var selectors [][]string
+	err = bodyDec.Decode(&selectors)
+	if err != nil {
+		http.Error(rw, err.Error(), http.StatusBadRequest)
+		return
+	}
+
+	ms := memorystore.GetMemoryStore()
+	n := 0
+	for _, sel := range selectors {
+		bn, err := ms.Free(sel, to)
+		if err != nil {
+			handleError(err, http.StatusInternalServerError, rw)
+			return
+		}
+
+		n += bn
+	}
+
+	rw.WriteHeader(http.StatusOK)
+	fmt.Fprintf(rw, "buffers freed: %d\n", n)
+}
+
+// handleWrite godoc
+// @summary Receive metrics in InfluxDB line-protocol
+// @tags write
+// @description Write data to the in-memory store in the InfluxDB line-protocol using [this format](https://github.com/ClusterCockpit/cc-specifications/blob/master/metrics/lineprotocol_alternative.md)
+
+// @accept      plain
+// @produce     json
+// @param       cluster        query string false "If the lines in the body do not have a cluster tag, use this value instead."
+// @success     200            {string} string  "ok"
+// @failure     400            {object} api.ErrorResponse       "Bad Request"
+// @failure     401            {object} api.ErrorResponse       "Unauthorized"
+// @failure     403            {object} api.ErrorResponse       "Forbidden"
+// @failure     500            {object} api.ErrorResponse       "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /write/ [post]
+func writeMetrics(rw http.ResponseWriter, r *http.Request) {
+	bytes, err := io.ReadAll(r.Body)
+	rw.Header().Add("Content-Type", "application/json")
+	if err != nil {
+		handleError(err, http.StatusInternalServerError, rw)
+		return
+	}
+
+	ms := memorystore.GetMemoryStore()
+	dec := lineprotocol.NewDecoderWithBytes(bytes)
+	if err := memorystore.DecodeLine(dec, ms, r.URL.Query().Get("cluster")); err != nil {
+		cclog.Errorf("/api/write error: %s", err.Error())
+		handleError(err, http.StatusBadRequest, rw)
+		return
+	}
+	rw.WriteHeader(http.StatusOK)
+}
+
+// handleDebug godoc
+// @summary Debug endpoint
+// @tags debug
+// @description This endpoint allows the users to print the content of
+// nodes/clusters/metrics to review the state of the data.
+// @produce     json
+// @param       selector        query    string            false "Selector"
+// @success     200            {string} string  "Debug dump"
+// @failure     400            {object} api.ErrorResponse       "Bad Request"
+// @failure     401            {object} api.ErrorResponse       "Unauthorized"
+// @failure     403            {object} api.ErrorResponse       "Forbidden"
+// @failure     500            {object} api.ErrorResponse       "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /debug/ [post]
+func debugMetrics(rw http.ResponseWriter, r *http.Request) {
+	raw := r.URL.Query().Get("selector")
+	rw.Header().Add("Content-Type", "application/json")
+	selector := []string{}
+	if len(raw) != 0 {
+		selector = strings.Split(raw, ":")
+	}
+
+	ms := memorystore.GetMemoryStore()
+	if err := ms.DebugDump(bufio.NewWriter(rw), selector); err != nil {
+		handleError(err, http.StatusBadRequest, rw)
+		return
+	}
+}
+
+// handleHealthCheck godoc
+// @summary HealthCheck endpoint
+// @tags healthcheck
+// @description This endpoint allows the users to check if a node is healthy
+// @produce     json
+// @param       selector        query    string            false "Selector"
+// @success     200            {string} string  "Debug dump"
+// @failure     400            {object} api.ErrorResponse       "Bad Request"
+// @failure     401            {object} api.ErrorResponse       "Unauthorized"
+// @failure     403            {object} api.ErrorResponse       "Forbidden"
+// @failure     500            {object} api.ErrorResponse       "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /healthcheck/ [get]
+func metricsHealth(rw http.ResponseWriter, r *http.Request) {
+	rawCluster := r.URL.Query().Get("cluster")
+	rawNode := r.URL.Query().Get("node")
+
+	if rawCluster == "" || rawNode == "" {
+		handleError(errors.New("'cluster' and 'node' are required query parameter"), http.StatusBadRequest, rw)
+		return
+	}
+
+	rw.Header().Add("Content-Type", "application/json")
+
+	selector := []string{rawCluster, rawNode}
+
+	ms := memorystore.GetMemoryStore()
+	if err := ms.HealthCheck(bufio.NewWriter(rw), selector); err != nil {
+		handleError(err, http.StatusBadRequest, rw)
+		return
+	}
+}

internal/api/nats.go

@@ -0,0 +1,231 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package api
+
+import (
+	"bytes"
+	"database/sql"
+	"encoding/json"
+	"sync"
+	"time"
+
+	"github.com/ClusterCockpit/cc-backend/internal/archiver"
+	"github.com/ClusterCockpit/cc-backend/internal/config"
+	"github.com/ClusterCockpit/cc-backend/internal/importer"
+	"github.com/ClusterCockpit/cc-backend/internal/repository"
+	"github.com/ClusterCockpit/cc-backend/pkg/nats"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
+)
+
+// NatsAPI provides NATS subscription-based handlers for Job and Node operations.
+// It mirrors the functionality of the REST API but uses NATS messaging.
+type NatsAPI struct {
+	JobRepository *repository.JobRepository
+	// RepositoryMutex protects job creation operations from race conditions
+	// when checking for duplicate jobs during startJob calls.
+	RepositoryMutex sync.Mutex
+}
+
+// NewNatsAPI creates a new NatsAPI instance with default dependencies.
+func NewNatsAPI() *NatsAPI {
+	return &NatsAPI{
+		JobRepository: repository.GetJobRepository(),
+	}
+}
+
+// StartSubscriptions registers all NATS subscriptions for Job and Node APIs.
+// Returns an error if the NATS client is not available or subscription fails.
+func (api *NatsAPI) StartSubscriptions() error {
+	client := nats.GetClient()
+	if client == nil {
+		cclog.Warn("NATS client not available, skipping API subscriptions")
+		return nil
+	}
+
+	if config.Keys.APISubjects != nil {
+
+		s := config.Keys.APISubjects
+
+		if err := client.Subscribe(s.SubjectJobStart, api.handleStartJob); err != nil {
+			return err
+		}
+
+		if err := client.Subscribe(s.SubjectJobStop, api.handleStopJob); err != nil {
+			return err
+		}
+
+		if err := client.Subscribe(s.SubjectNodeState, api.handleNodeState); err != nil {
+			return err
+		}
+
+		cclog.Info("NATS API subscriptions started")
+	}
+	return nil
+}
+
+// handleStartJob processes job start messages received via NATS.
+// Expected JSON payload follows the schema.Job structure.
+func (api *NatsAPI) handleStartJob(subject string, data []byte) {
+	req := schema.Job{
+		Shared:           "none",
+		MonitoringStatus: schema.MonitoringStatusRunningOrArchiving,
+	}
+
+	dec := json.NewDecoder(bytes.NewReader(data))
+	dec.DisallowUnknownFields()
+	if err := dec.Decode(&req); err != nil {
+		cclog.Errorf("NATS %s: parsing request failed: %v", subject, err)
+		return
+	}
+
+	cclog.Debugf("NATS %s: %s", subject, req.GoString())
+	req.State = schema.JobStateRunning
+
+	if err := importer.SanityChecks(&req); err != nil {
+		cclog.Errorf("NATS %s: sanity check failed: %v", subject, err)
+		return
+	}
+
+	var unlockOnce sync.Once
+	api.RepositoryMutex.Lock()
+	defer unlockOnce.Do(api.RepositoryMutex.Unlock)
+
+	jobs, err := api.JobRepository.FindAll(&req.JobID, &req.Cluster, nil)
+	if err != nil && err != sql.ErrNoRows {
+		cclog.Errorf("NATS %s: checking for duplicate failed: %v", subject, err)
+		return
+	}
+	if err == nil {
+		for _, job := range jobs {
+			if (req.StartTime - job.StartTime) < secondsPerDay {
+				cclog.Errorf("NATS %s: job with jobId %d, cluster %s already exists (dbid: %d)",
+					subject, req.JobID, req.Cluster, job.ID)
+				return
+			}
+		}
+	}
+
+	id, err := api.JobRepository.Start(&req)
+	if err != nil {
+		cclog.Errorf("NATS %s: insert into database failed: %v", subject, err)
+		return
+	}
+	unlockOnce.Do(api.RepositoryMutex.Unlock)
+
+	for _, tag := range req.Tags {
+		if _, err := api.JobRepository.AddTagOrCreate(nil, id, tag.Type, tag.Name, tag.Scope); err != nil {
+			cclog.Errorf("NATS %s: adding tag to new job %d failed: %v", subject, id, err)
+			return
+		}
+	}
+
+	cclog.Infof("NATS: new job (id: %d): cluster=%s, jobId=%d, user=%s, startTime=%d",
+		id, req.Cluster, req.JobID, req.User, req.StartTime)
+}
+
+// handleStopJob processes job stop messages received via NATS.
+// Expected JSON payload follows the StopJobAPIRequest structure.
+func (api *NatsAPI) handleStopJob(subject string, data []byte) {
+	var req StopJobAPIRequest
+
+	dec := json.NewDecoder(bytes.NewReader(data))
+	dec.DisallowUnknownFields()
+	if err := dec.Decode(&req); err != nil {
+		cclog.Errorf("NATS %s: parsing request failed: %v", subject, err)
+		return
+	}
+
+	if req.JobID == nil {
+		cclog.Errorf("NATS %s: the field 'jobId' is required", subject)
+		return
+	}
+
+	job, err := api.JobRepository.Find(req.JobID, req.Cluster, req.StartTime)
+	if err != nil {
+		cachedJob, cachedErr := api.JobRepository.FindCached(req.JobID, req.Cluster, req.StartTime)
+		if cachedErr != nil {
+			cclog.Errorf("NATS %s: finding job failed: %v (cached lookup also failed: %v)",
+				subject, err, cachedErr)
+			return
+		}
+		job = cachedJob
+	}
+
+	if job.State != schema.JobStateRunning {
+		cclog.Errorf("NATS %s: jobId %d (id %d) on %s: job has already been stopped (state is: %s)",
+			subject, job.JobID, job.ID, job.Cluster, job.State)
+		return
+	}
+
+	if job.StartTime > req.StopTime {
+		cclog.Errorf("NATS %s: jobId %d (id %d) on %s: stopTime %d must be >= startTime %d",
+			subject, job.JobID, job.ID, job.Cluster, req.StopTime, job.StartTime)
+		return
+	}
+
+	if req.State != "" && !req.State.Valid() {
+		cclog.Errorf("NATS %s: jobId %d (id %d) on %s: invalid job state: %#v",
+			subject, job.JobID, job.ID, job.Cluster, req.State)
+		return
+	} else if req.State == "" {
+		req.State = schema.JobStateCompleted
+	}
+
+	job.Duration = int32(req.StopTime - job.StartTime)
+	job.State = req.State
+	api.JobRepository.Mutex.Lock()
+	defer api.JobRepository.Mutex.Unlock()
+
+	if err := api.JobRepository.Stop(*job.ID, job.Duration, job.State, job.MonitoringStatus); err != nil {
+		if err := api.JobRepository.StopCached(*job.ID, job.Duration, job.State, job.MonitoringStatus); err != nil {
+			cclog.Errorf("NATS %s: jobId %d (id %d) on %s: marking job as '%s' failed: %v",
+				subject, job.JobID, job.ID, job.Cluster, job.State, err)
+			return
+		}
+	}
+
+	cclog.Infof("NATS: archiving job (dbid: %d): cluster=%s, jobId=%d, user=%s, startTime=%d, duration=%d, state=%s",
+		job.ID, job.Cluster, job.JobID, job.User, job.StartTime, job.Duration, job.State)
+
+	if job.MonitoringStatus == schema.MonitoringStatusDisabled {
+		return
+	}
+
+	archiver.TriggerArchiving(job)
+}
+
+// handleNodeState processes node state update messages received via NATS.
+// Expected JSON payload follows the UpdateNodeStatesRequest structure.
+func (api *NatsAPI) handleNodeState(subject string, data []byte) {
+	var req UpdateNodeStatesRequest
+
+	dec := json.NewDecoder(bytes.NewReader(data))
+	dec.DisallowUnknownFields()
+	if err := dec.Decode(&req); err != nil {
+		cclog.Errorf("NATS %s: parsing request failed: %v", subject, err)
+		return
+	}
+
+	repo := repository.GetNodeRepository()
+
+	for _, node := range req.Nodes {
+		state := determineState(node.States)
+		nodeState := schema.NodeStateDB{
+			TimeStamp:       time.Now().Unix(),
+			NodeState:       state,
+			CpusAllocated:   node.CpusAllocated,
+			MemoryAllocated: node.MemoryAllocated,
+			GpusAllocated:   node.GpusAllocated,
+			HealthState:     schema.MonitoringStateFull,
+			JobsRunning:     node.JobsRunning,
+		}
+
+		repo.UpdateNodeState(node.Hostname, req.Cluster, &nodeState)
+	}
+
+	cclog.Debugf("NATS %s: updated %d node states for cluster %s", subject, len(req.Nodes), req.Cluster)
+}

internal/api/node.go

@@ -0,0 +1,80 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package api
+
+import (
+	"fmt"
+	"net/http"
+	"strings"
+	"time"
+
+	"github.com/ClusterCockpit/cc-backend/internal/repository"
+	"github.com/ClusterCockpit/cc-lib/schema"
+)
+
+type UpdateNodeStatesRequest struct {
+	Nodes   []schema.NodePayload `json:"nodes"`
+	Cluster string               `json:"cluster" example:"fritz"`
+}
+
+// this routine assumes that only one of them exists per node
+func determineState(states []string) schema.SchedulerState {
+	for _, state := range states {
+		switch strings.ToLower(state) {
+		case "allocated":
+			return schema.NodeStateAllocated
+		case "reserved":
+			return schema.NodeStateReserved
+		case "idle":
+			return schema.NodeStateIdle
+		case "down":
+			return schema.NodeStateDown
+		case "mixed":
+			return schema.NodeStateMixed
+		}
+	}
+
+	return schema.NodeStateUnknown
+}
+
+// updateNodeStates godoc
+// @summary     Deliver updated Slurm node states
+// @tags Nodestates
+// @description Returns a JSON-encoded list of users.
+// @description Required query-parameter defines if all users or only users with additional special roles are returned.
+// @produce     json
+// @param       request body UpdateNodeStatesRequest true "Request body containing nodes and their states"
+// @success     200     {object} api.DefaultApiResponse "Success message"
+// @failure     400     {object} api.ErrorResponse      "Bad Request"
+// @failure     401     {object} api.ErrorResponse      "Unauthorized"
+// @failure     403     {object} api.ErrorResponse      "Forbidden"
+// @failure     500     {object} api.ErrorResponse      "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /api/nodestats/ [post]
+func (api *RestAPI) updateNodeStates(rw http.ResponseWriter, r *http.Request) {
+	// Parse request body
+	req := UpdateNodeStatesRequest{}
+	if err := decode(r.Body, &req); err != nil {
+		handleError(fmt.Errorf("parsing request body failed: %w", err),
+			http.StatusBadRequest, rw)
+		return
+	}
+	repo := repository.GetNodeRepository()
+
+	for _, node := range req.Nodes {
+		state := determineState(node.States)
+		nodeState := schema.NodeStateDB{
+			TimeStamp: time.Now().Unix(), NodeState: state,
+			CpusAllocated:   node.CpusAllocated,
+			MemoryAllocated: node.MemoryAllocated,
+			GpusAllocated:   node.GpusAllocated,
+			HealthState:     schema.MonitoringStateFull,
+			JobsRunning:     node.JobsRunning,
+		}
+
+		repo.UpdateNodeState(node.Hostname, req.Cluster, &nodeState)
+	}
+}

internal/api/user.go

@@ -0,0 +1,221 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package api
+
+import (
+	"encoding/json"
+	"fmt"
+	"net/http"
+
+	"github.com/ClusterCockpit/cc-backend/internal/repository"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/gorilla/mux"
+)
+
+type APIReturnedUser struct {
+	Username string   `json:"username"`
+	Name     string   `json:"name"`
+	Roles    []string `json:"roles"`
+	Email    string   `json:"email"`
+	Projects []string `json:"projects"`
+}
+
+// getUsers godoc
+// @summary     Returns a list of users
+// @tags User
+// @description Returns a JSON-encoded list of users.
+// @description Required query-parameter defines if all users or only users with additional special roles are returned.
+// @produce     json
+// @param       not-just-user query bool true "If returned list should contain all users or only users with additional special roles"
+// @success     200     {array} api.ApiReturnedUser "List of users returned successfully"
+// @failure     400     {string} string             "Bad Request"
+// @failure     401     {string} string             "Unauthorized"
+// @failure     403     {string} string             "Forbidden"
+// @failure     500     {string} string             "Internal Server Error"
+// @security    ApiKeyAuth
+// @router      /api/users/ [get]
+func (api *RestAPI) getUsers(rw http.ResponseWriter, r *http.Request) {
+	// SecuredCheck() only worked with TokenAuth: Removed
+
+	if user := repository.GetUserFromContext(r.Context()); !user.HasRole(schema.RoleAdmin) {
+		handleError(fmt.Errorf("only admins are allowed to fetch a list of users"), http.StatusForbidden, rw)
+		return
+	}
+
+	users, err := repository.GetUserRepository().ListUsers(r.URL.Query().Get("not-just-user") == "true")
+	if err != nil {
+		handleError(fmt.Errorf("listing users failed: %w", err), http.StatusInternalServerError, rw)
+		return
+	}
+
+	rw.Header().Set("Content-Type", "application/json")
+	if err := json.NewEncoder(rw).Encode(users); err != nil {
+		cclog.Errorf("Failed to encode users response: %v", err)
+	}
+}
+
+// updateUser godoc
+// @summary     Update user roles and projects
+// @tags User
+// @description Allows admins to add/remove roles and projects for a user
+// @produce     plain
+// @param       id          path   string  true  "Username"
+// @param       add-role    formData string false "Role to add"
+// @param       remove-role formData string false "Role to remove"
+// @param       add-project formData string false "Project to add"
+// @param       remove-project formData string false "Project to remove"
+// @success     200     {string} string "Success message"
+// @failure     403     {object} api.ErrorResponse "Forbidden"
+// @failure     422     {object} api.ErrorResponse "Unprocessable Entity"
+// @security    ApiKeyAuth
+// @router      /api/user/{id} [post]
+func (api *RestAPI) updateUser(rw http.ResponseWriter, r *http.Request) {
+	// SecuredCheck() only worked with TokenAuth: Removed
+
+	if user := repository.GetUserFromContext(r.Context()); !user.HasRole(schema.RoleAdmin) {
+		handleError(fmt.Errorf("only admins are allowed to update a user"), http.StatusForbidden, rw)
+		return
+	}
+
+	// Get Values
+	newrole := r.FormValue("add-role")
+	delrole := r.FormValue("remove-role")
+	newproj := r.FormValue("add-project")
+	delproj := r.FormValue("remove-project")
+
+	rw.Header().Set("Content-Type", "application/json")
+
+	// Handle role updates
+	if newrole != "" {
+		if err := repository.GetUserRepository().AddRole(r.Context(), mux.Vars(r)["id"], newrole); err != nil {
+			handleError(fmt.Errorf("adding role failed: %w", err), http.StatusUnprocessableEntity, rw)
+			return
+		}
+		if err := json.NewEncoder(rw).Encode(DefaultAPIResponse{Message: "Add Role Success"}); err != nil {
+			cclog.Errorf("Failed to encode response: %v", err)
+		}
+	} else if delrole != "" {
+		if err := repository.GetUserRepository().RemoveRole(r.Context(), mux.Vars(r)["id"], delrole); err != nil {
+			handleError(fmt.Errorf("removing role failed: %w", err), http.StatusUnprocessableEntity, rw)
+			return
+		}
+		if err := json.NewEncoder(rw).Encode(DefaultAPIResponse{Message: "Remove Role Success"}); err != nil {
+			cclog.Errorf("Failed to encode response: %v", err)
+		}
+	} else if newproj != "" {
+		if err := repository.GetUserRepository().AddProject(r.Context(), mux.Vars(r)["id"], newproj); err != nil {
+			handleError(fmt.Errorf("adding project failed: %w", err), http.StatusUnprocessableEntity, rw)
+			return
+		}
+		if err := json.NewEncoder(rw).Encode(DefaultAPIResponse{Message: "Add Project Success"}); err != nil {
+			cclog.Errorf("Failed to encode response: %v", err)
+		}
+	} else if delproj != "" {
+		if err := repository.GetUserRepository().RemoveProject(r.Context(), mux.Vars(r)["id"], delproj); err != nil {
+			handleError(fmt.Errorf("removing project failed: %w", err), http.StatusUnprocessableEntity, rw)
+			return
+		}
+		if err := json.NewEncoder(rw).Encode(DefaultAPIResponse{Message: "Remove Project Success"}); err != nil {
+			cclog.Errorf("Failed to encode response: %v", err)
+		}
+	} else {
+		handleError(fmt.Errorf("no operation specified: must provide add-role, remove-role, add-project, or remove-project"), http.StatusBadRequest, rw)
+	}
+}
+
+// createUser godoc
+// @summary     Create a new user
+// @tags User
+// @description Creates a new user with specified credentials and role
+// @produce     plain
+// @param       username formData string true  "Username"
+// @param       password formData string false "Password (not required for API users)"
+// @param       role     formData string true  "User role"
+// @param       name     formData string false "Full name"
+// @param       email    formData string false "Email address"
+// @param       project  formData string false "Project (required for managers)"
+// @success     200     {string} string "Success message"
+// @failure     400     {object} api.ErrorResponse "Bad Request"
+// @failure     403     {object} api.ErrorResponse "Forbidden"
+// @failure     422     {object} api.ErrorResponse "Unprocessable Entity"
+// @security    ApiKeyAuth
+// @router      /api/users/ [post]
+func (api *RestAPI) createUser(rw http.ResponseWriter, r *http.Request) {
+	// SecuredCheck() only worked with TokenAuth: Removed
+
+	rw.Header().Set("Content-Type", "text/plain")
+	me := repository.GetUserFromContext(r.Context())
+	if !me.HasRole(schema.RoleAdmin) {
+		handleError(fmt.Errorf("only admins are allowed to create new users"), http.StatusForbidden, rw)
+		return
+	}
+
+	username, password, role, name, email, project := r.FormValue("username"),
+		r.FormValue("password"), r.FormValue("role"), r.FormValue("name"),
+		r.FormValue("email"), r.FormValue("project")
+
+	// Validate username length
+	if len(username) == 0 || len(username) > 100 {
+		handleError(fmt.Errorf("username must be between 1 and 100 characters"), http.StatusBadRequest, rw)
+		return
+	}
+
+	if len(password) == 0 && role != schema.GetRoleString(schema.RoleApi) {
+		handleError(fmt.Errorf("only API users are allowed to have a blank password (login will be impossible)"), http.StatusBadRequest, rw)
+		return
+	}
+
+	if len(project) != 0 && role != schema.GetRoleString(schema.RoleManager) {
+		handleError(fmt.Errorf("only managers require a project (can be changed later)"), http.StatusBadRequest, rw)
+		return
+	} else if len(project) == 0 && role == schema.GetRoleString(schema.RoleManager) {
+		handleError(fmt.Errorf("managers require a project to manage (can be changed later)"), http.StatusBadRequest, rw)
+		return
+	}
+
+	if err := repository.GetUserRepository().AddUser(&schema.User{
+		Username: username,
+		Name:     name,
+		Password: password,
+		Email:    email,
+		Projects: []string{project},
+		Roles:    []string{role},
+	}); err != nil {
+		handleError(fmt.Errorf("adding user failed: %w", err), http.StatusUnprocessableEntity, rw)
+		return
+	}
+
+	fmt.Fprintf(rw, "User %v successfully created!\n", username)
+}
+
+// deleteUser godoc
+// @summary     Delete a user
+// @tags User
+// @description Deletes a user from the system
+// @produce     plain
+// @param       username formData string true "Username to delete"
+// @success     200     {string} string "Success"
+// @failure     403     {object} api.ErrorResponse "Forbidden"
+// @failure     422     {object} api.ErrorResponse "Unprocessable Entity"
+// @security    ApiKeyAuth
+// @router      /api/users/ [delete]
+func (api *RestAPI) deleteUser(rw http.ResponseWriter, r *http.Request) {
+	// SecuredCheck() only worked with TokenAuth: Removed
+
+	if user := repository.GetUserFromContext(r.Context()); !user.HasRole(schema.RoleAdmin) {
+		handleError(fmt.Errorf("only admins are allowed to delete a user"), http.StatusForbidden, rw)
+		return
+	}
+
+	username := r.FormValue("username")
+	if err := repository.GetUserRepository().DelUser(username); err != nil {
+		handleError(fmt.Errorf("deleting user failed: %w", err), http.StatusUnprocessableEntity, rw)
+		return
+	}
+
+	rw.WriteHeader(http.StatusOK)
+}

internal/archiver/README.md

@@ -0,0 +1,190 @@
+# Archiver Package
+
+The `archiver` package provides asynchronous job archiving functionality for ClusterCockpit. When jobs complete, their metric data is archived from the metric store to a persistent archive backend (filesystem, S3, SQLite, etc.).
+
+## Architecture
+
+### Producer-Consumer Pattern
+
+```
+┌──────────────┐     TriggerArchiving()      ┌───────────────┐
+│  API Handler │  ───────────────────────▶   │ archiveChannel│
+│ (Job Stop)   │                             │  (buffer: 128)│
+└──────────────┘                             └───────┬───────┘
+                                                     │
+                   ┌─────────────────────────────────┘
+                   │
+                   ▼
+         ┌──────────────────────┐
+         │  archivingWorker()   │
+         │   (goroutine)        │
+         └──────────┬───────────┘
+                    │
+                    ▼
+         1. Fetch job metadata
+         2. Load metric data
+         3. Calculate statistics
+         4. Archive to backend
+         5. Update database
+         6. Call hooks
+```
+
+### Components
+
+- **archiveChannel**: Buffered channel (128 jobs) for async communication
+- **archivePending**: WaitGroup tracking in-flight archiving operations
+- **archivingWorker**: Background goroutine processing archiving requests
+- **shutdownCtx**: Context for graceful cancellation during shutdown
+
+## Usage
+
+### Initialization
+
+```go
+// Start archiver with context for shutdown control
+ctx, cancel := context.WithCancel(context.Background())
+defer cancel()
+
+archiver.Start(jobRepository, ctx)
+```
+
+### Archiving a Job
+
+```go
+// Called automatically when a job completes
+archiver.TriggerArchiving(job)
+```
+
+The function returns immediately. Actual archiving happens in the background.
+
+### Graceful Shutdown
+
+```go
+// Shutdown with 10 second timeout
+if err := archiver.Shutdown(10 * time.Second); err != nil {
+    log.Printf("Archiver shutdown timeout: %v", err)
+}
+```
+
+**Shutdown process:**
+1. Closes channel (rejects new jobs)
+2. Waits for pending jobs (up to timeout)
+3. Cancels context if timeout exceeded
+4. Waits for worker to exit cleanly
+
+## Configuration
+
+### Channel Buffer Size
+
+The archiving channel has a buffer of 128 jobs. If more than 128 jobs are queued simultaneously, `TriggerArchiving()` will block until space is available.
+
+To adjust:
+```go
+// In archiveWorker.go Start() function
+archiveChannel = make(chan *schema.Job, 256) // Increase buffer
+```
+
+### Scope Selection
+
+Archive data scopes are automatically selected based on job size:
+
+- **Node scope**: Always included
+- **Core scope**: Included for jobs with ≤8 nodes (reduces data volume for large jobs)
+- **Accelerator scope**: Included if job used accelerators (`NumAcc > 0`)
+
+To adjust the node threshold:
+```go
+// In archiver.go ArchiveJob() function
+if job.NumNodes <= 16 { // Change from 8 to 16
+    scopes = append(scopes, schema.MetricScopeCore)
+}
+```
+
+### Resolution
+
+Data is archived at the highest available resolution (typically 60s intervals). To change:
+
+```go
+// In archiver.go ArchiveJob() function
+jobData, err := metricDataDispatcher.LoadData(job, allMetrics, scopes, ctx, 300)
+// 0 = highest resolution
+// 300 = 5-minute resolution
+```
+
+## Error Handling
+
+### Automatic Retry
+
+The archiver does **not** automatically retry failed archiving operations. If archiving fails:
+
+1. Error is logged
+2. Job is marked as `MonitoringStatusArchivingFailed` in database
+3. Worker continues processing other jobs
+
+### Manual Retry
+
+To re-archive failed jobs, query for jobs with `MonitoringStatusArchivingFailed` and call `TriggerArchiving()` again.
+
+## Performance Considerations
+
+### Single Worker Thread
+
+The archiver uses a single worker goroutine. For high-throughput systems:
+
+- Large channel buffer (128) prevents blocking
+- Archiving is typically I/O bound (writing to storage)
+- Single worker prevents overwhelming storage backend
+
+### Shutdown Timeout
+
+Recommended timeout values:
+- **Development**: 5-10 seconds
+- **Production**: 10-30 seconds
+- **High-load**: 30-60 seconds
+
+Choose based on:
+- Average archiving time per job
+- Storage backend latency
+- Acceptable shutdown delay
+
+## Monitoring
+
+### Logging
+
+The archiver logs:
+- **Info**: Startup, shutdown, successful completions
+- **Debug**: Individual job archiving times
+- **Error**: Archiving failures with job ID and reason
+- **Warn**: Shutdown timeout exceeded
+
+### Metrics
+
+Monitor these signals for archiver health:
+- Jobs with `MonitoringStatusArchivingFailed`
+- Time from job stop to successful archive
+- Shutdown timeout occurrences
+
+## Thread Safety
+
+All exported functions are safe for concurrent use:
+- `Start()` - Safe to call once
+- `TriggerArchiving()` - Safe from multiple goroutines
+- `Shutdown()` - Safe to call once
+- `WaitForArchiving()` - Deprecated, but safe
+
+Internal state is protected by:
+- Channel synchronization (`archiveChannel`)
+- WaitGroup for pending count (`archivePending`)
+- Context for cancellation (`shutdownCtx`)
+
+## Files
+
+- **archiveWorker.go**: Worker lifecycle, channel management, shutdown logic
+- **archiver.go**: Core archiving logic, metric loading, statistics calculation
+
+## Dependencies
+
+- `internal/repository`: Database operations for job metadata
+- `internal/metricDataDispatcher`: Loading metric data from various backends
+- `pkg/archive`: Archive backend abstraction (filesystem, S3, SQLite)
+- `cc-lib/schema`: Job and metric data structures

internal/archiver/archiveWorker.go

@@ -1,17 +1,61 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// Package archiver provides asynchronous job archiving functionality for ClusterCockpit.
+//
+// The archiver runs a background worker goroutine that processes job archiving requests
+// from a buffered channel. When jobs complete, their metric data is archived from the
+// metric store to the configured archive backend (filesystem, S3, etc.).
+//
+// # Architecture
+//
+// The archiver uses a producer-consumer pattern:
+//   - Producer: TriggerArchiving() sends jobs to archiveChannel
+//   - Consumer: archivingWorker() processes jobs from the channel
+//   - Coordination: sync.WaitGroup tracks pending archive operations
+//
+// # Lifecycle
+//
+//  1. Start(repo, ctx) - Initialize worker with context for cancellation
+//  2. TriggerArchiving(job) - Queue job for archiving (called when job stops)
+//  3. archivingWorker() - Background goroutine processes jobs
+//  4. Shutdown(timeout) - Graceful shutdown with timeout
+//
+// # Graceful Shutdown
+//
+// The archiver supports graceful shutdown with configurable timeout:
+//   - Closes channel to reject new jobs
+//   - Waits for pending jobs to complete (up to timeout)
+//   - Cancels context if timeout exceeded
+//   - Ensures worker goroutine exits cleanly
+//
+// # Example Usage
+//
+//	// Initialize archiver
+//	ctx, cancel := context.WithCancel(context.Background())
+//	defer cancel()
+//	archiver.Start(jobRepository, ctx)
+//
+//	// Trigger archiving when job completes
+//	archiver.TriggerArchiving(job)
+//
+//	// Graceful shutdown with 10 second timeout
+//	if err := archiver.Shutdown(10 * time.Second); err != nil {
+//	    log.Printf("Archiver shutdown timeout: %v", err)
+//	}
 package archiver
 
 import (
 	"context"
+	"fmt"
 	"sync"
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
@@ -19,76 +63,188 @@ var (
 	archivePending sync.WaitGroup
 	archiveChannel chan *schema.Job
 	jobRepo        *repository.JobRepository
+	shutdownCtx    context.Context
+	shutdownCancel context.CancelFunc
+	workerDone     chan struct{}
 )
 
-func Start(r *repository.JobRepository) {
+// Start initializes the archiver and starts the background worker goroutine.
+//
+// The archiver processes job archiving requests asynchronously via a buffered channel.
+// Jobs are sent to the channel using TriggerArchiving() and processed by the worker.
+//
+// Parameters:
+//   - r: JobRepository instance for database operations
+//   - ctx: Context for cancellation (shutdown signal propagation)
+//
+// The worker goroutine will run until:
+//   - ctx is cancelled (via parent shutdown)
+//   - archiveChannel is closed (via Shutdown())
+//
+// Must be called before TriggerArchiving(). Safe to call only once.
+func Start(r *repository.JobRepository, ctx context.Context) {
+	shutdownCtx, shutdownCancel = context.WithCancel(ctx)
 	archiveChannel = make(chan *schema.Job, 128)
+	workerDone = make(chan struct{})
 	jobRepo = r
 
 	go archivingWorker()
 }
 
-// Archiving worker thread
+// archivingWorker is the background goroutine that processes job archiving requests.
+//
+// The worker loop:
+//  1. Blocks waiting for jobs on archiveChannel or shutdown signal
+//  2. Fetches job metadata from repository
+//  3. Archives job data to configured backend (calls ArchiveJob)
+//  4. Updates job footprint and energy metrics in database
+//  5. Marks job as successfully archived
+//  6. Calls job stop hooks
+//
+// The worker exits when:
+//   - shutdownCtx is cancelled (timeout during shutdown)
+//   - archiveChannel is closed (normal shutdown)
+//
+// Errors during archiving are logged and the job is marked as failed,
+// but the worker continues processing other jobs.
 func archivingWorker() {
+	defer close(workerDone)
+
 	for {
 		select {
+		case <-shutdownCtx.Done():
+			cclog.Info("Archive worker received shutdown signal")
+			return
+
 		case job, ok := <-archiveChannel:
 			if !ok {
-				break
+				cclog.Info("Archive channel closed, worker exiting")
+				return
 			}
+
 			start := time.Now()
 			// not using meta data, called to load JobMeta into Cache?
 			// will fail if job meta not in repository
 			if _, err := jobRepo.FetchMetadata(job); err != nil {
-				log.Errorf("archiving job (dbid: %d) failed at check metadata step: %s", job.ID, err.Error())
-				jobRepo.UpdateMonitoringStatus(job.ID, schema.MonitoringStatusArchivingFailed)
+				cclog.Errorf("archiving job (dbid: %d) failed at check metadata step: %s", job.ID, err.Error())
+				jobRepo.UpdateMonitoringStatus(*job.ID, schema.MonitoringStatusArchivingFailed)
+				archivePending.Done()
 				continue
 			}
 
 			// ArchiveJob will fetch all the data from a MetricDataRepository and push into configured archive backend
-			// TODO: Maybe use context with cancel/timeout here
-			jobMeta, err := ArchiveJob(job, context.Background())
+			// Use shutdown context to allow cancellation
+			jobMeta, err := ArchiveJob(job, shutdownCtx)
 			if err != nil {
-				log.Errorf("archiving job (dbid: %d) failed at archiving job step: %s", job.ID, err.Error())
-				jobRepo.UpdateMonitoringStatus(job.ID, schema.MonitoringStatusArchivingFailed)
+				cclog.Errorf("archiving job (dbid: %d) failed at archiving job step: %s", job.ID, err.Error())
+				jobRepo.UpdateMonitoringStatus(*job.ID, schema.MonitoringStatusArchivingFailed)
+				archivePending.Done()
 				continue
 			}
 
 			stmt := sq.Update("job").Where("job.id = ?", job.ID)
 
 			if stmt, err = jobRepo.UpdateFootprint(stmt, jobMeta); err != nil {
-				log.Errorf("archiving job (dbid: %d) failed at update Footprint step: %s", job.ID, err.Error())
+				cclog.Errorf("archiving job (dbid: %d) failed at update Footprint step: %s", job.ID, err.Error())
+				archivePending.Done()
 				continue
 			}
 			if stmt, err = jobRepo.UpdateEnergy(stmt, jobMeta); err != nil {
-				log.Errorf("archiving job (dbid: %d) failed at update Energy step: %s", job.ID, err.Error())
+				cclog.Errorf("archiving job (dbid: %d) failed at update Energy step: %s", job.ID, err.Error())
+				archivePending.Done()
 				continue
 			}
 			// Update the jobs database entry one last time:
 			stmt = jobRepo.MarkArchived(stmt, schema.MonitoringStatusArchivingSuccessful)
 			if err := jobRepo.Execute(stmt); err != nil {
-				log.Errorf("archiving job (dbid: %d) failed at db execute: %s", job.ID, err.Error())
+				cclog.Errorf("archiving job (dbid: %d) failed at db execute: %s", job.ID, err.Error())
+				archivePending.Done()
 				continue
 			}
-			log.Debugf("archiving job %d took %s", job.JobID, time.Since(start))
-			log.Printf("archiving job (dbid: %d) successful", job.ID)
+			cclog.Debugf("archiving job %d took %s", job.JobID, time.Since(start))
+			cclog.Infof("archiving job (dbid: %d) successful", job.ID)
+
+			repository.CallJobStopHooks(job)
 			archivePending.Done()
 		}
 	}
 }
 
-// Trigger async archiving
+// TriggerArchiving queues a job for asynchronous archiving.
+//
+// This function should be called when a job completes (stops) to archive its
+// metric data from the metric store to the configured archive backend.
+//
+// The function:
+//  1. Increments the pending job counter (WaitGroup)
+//  2. Sends the job to the archiving channel (buffered, capacity 128)
+//  3. Returns immediately (non-blocking unless channel is full)
+//
+// The actual archiving is performed asynchronously by the worker goroutine.
+// Upon completion, the worker will decrement the pending counter.
+//
+// Panics if Start() has not been called first.
 func TriggerArchiving(job *schema.Job) {
 	if archiveChannel == nil {
-		log.Fatal("Cannot archive without archiving channel. Did you Start the archiver?")
+		cclog.Fatal("Cannot archive without archiving channel. Did you Start the archiver?")
 	}
 
 	archivePending.Add(1)
 	archiveChannel <- job
 }
 
-// Wait for background thread to finish pending archiving operations
-func WaitForArchiving() {
-	// close channel and wait for worker to process remaining jobs
-	archivePending.Wait()
+// Shutdown performs a graceful shutdown of the archiver with a configurable timeout.
+//
+// The shutdown process:
+//  1. Closes archiveChannel - no new jobs will be accepted
+//  2. Waits for pending jobs to complete (up to timeout duration)
+//  3. If timeout is exceeded:
+//     - Cancels shutdownCtx to interrupt ongoing ArchiveJob operations
+//     - Returns error indicating timeout
+//  4. Waits for worker goroutine to exit cleanly
+//
+// Parameters:
+//   - timeout: Maximum duration to wait for pending jobs to complete
+//     (recommended: 10-30 seconds for production)
+//
+// Returns:
+//   - nil if all jobs completed within timeout
+//   - error if timeout was exceeded (some jobs may not have been archived)
+//
+// Jobs that don't complete within the timeout will be marked as failed.
+// The function always ensures the worker goroutine exits before returning.
+//
+// Example:
+//
+//	if err := archiver.Shutdown(10 * time.Second); err != nil {
+//	    log.Printf("Some jobs did not complete: %v", err)
+//	}
+func Shutdown(timeout time.Duration) error {
+	cclog.Info("Initiating archiver shutdown...")
+
+	// Close channel to signal no more jobs will be accepted
+	close(archiveChannel)
+
+	// Create a channel to signal when all jobs are done
+	done := make(chan struct{})
+	go func() {
+		archivePending.Wait()
+		close(done)
+	}()
+
+	// Wait for jobs to complete or timeout
+	select {
+	case <-done:
+		cclog.Info("All archive jobs completed successfully")
+		// Wait for worker to exit
+		<-workerDone
+		return nil
+	case <-time.After(timeout):
+		cclog.Warn("Archiver shutdown timeout exceeded, cancelling remaining operations")
+		// Cancel any ongoing operations
+		shutdownCancel()
+		// Wait for worker to exit
+		<-workerDone
+		return fmt.Errorf("archiver shutdown timeout after %v", timeout)
+	}
 }

internal/archiver/archiver.go

@@ -1,7 +1,8 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package archiver
 
 import (
@@ -11,12 +12,37 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
-// Writes a running job to the job-archive
-func ArchiveJob(job *schema.Job, ctx context.Context) (*schema.JobMeta, error) {
+// ArchiveJob archives a completed job's metric data to the configured archive backend.
+//
+// This function performs the following operations:
+//  1. Loads all metric data for the job from the metric data repository
+//  2. Calculates job-level statistics (avg, min, max) for each metric
+//  3. Stores the job metadata and metric data to the archive backend
+//
+// Metric data is retrieved at the highest available resolution (typically 60s)
+// for the following scopes:
+//   - Node scope (always)
+//   - Core scope (for jobs with ≤8 nodes, to reduce data volume)
+//   - Accelerator scope (if job used accelerators)
+//
+// The function respects context cancellation. If ctx is cancelled (e.g., during
+// shutdown timeout), the operation will be interrupted and return an error.
+//
+// Parameters:
+//   - job: The job to archive (must be a completed job)
+//   - ctx: Context for cancellation and timeout control
+//
+// Returns:
+//   - *schema.Job with populated Statistics field
+//   - error if data loading or archiving fails
+//
+// If config.Keys.DisableArchive is true, only job statistics are calculated
+// and returned (no data is written to archive backend).
+func ArchiveJob(job *schema.Job, ctx context.Context) (*schema.Job, error) {
 	allMetrics := make([]string, 0)
 	metricConfigs := archive.GetCluster(job.Cluster).MetricConfig
 	for _, mc := range metricConfigs {
@@ -36,15 +62,11 @@ func ArchiveJob(job *schema.Job, ctx context.Context) (*schema.JobMeta, error) {
 
 	jobData, err := metricDataDispatcher.LoadData(job, allMetrics, scopes, ctx, 0) // 0 Resulotion-Value retrieves highest res (60s)
 	if err != nil {
-		log.Error("Error wile loading job data for archiving")
+		cclog.Error("Error wile loading job data for archiving")
 		return nil, err
 	}
 
-	jobMeta := &schema.JobMeta{
-		BaseJob:    job.BaseJob,
-		StartTime:  job.StartTime.Unix(),
-		Statistics: make(map[string]schema.JobStatistics),
-	}
+	job.Statistics = make(map[string]schema.JobStatistics)
 
 	for metric, data := range jobData {
 		avg, min, max := 0.0, math.MaxFloat32, -math.MaxFloat32
@@ -61,7 +83,7 @@ func ArchiveJob(job *schema.Job, ctx context.Context) (*schema.JobMeta, error) {
 		}
 
 		// Round AVG Result to 2 Digits
-		jobMeta.Statistics[metric] = schema.JobStatistics{
+		job.Statistics[metric] = schema.JobStatistics{
 			Unit: schema.Unit{
 				Prefix: archive.GetMetricConfig(job.Cluster, metric).Unit.Prefix,
 				Base:   archive.GetMetricConfig(job.Cluster, metric).Unit.Base,
@@ -76,8 +98,8 @@ func ArchiveJob(job *schema.Job, ctx context.Context) (*schema.JobMeta, error) {
 	// only return the JobMeta structure as the
 	// statistics in there are needed.
 	if config.Keys.DisableArchive {
-		return jobMeta, nil
+		return job, nil
 	}
 
-	return jobMeta, archive.GetHandle().ImportJob(jobMeta, &jobData)
+	return job, archive.GetHandle().ImportJob(job, &jobData)
 }

internal/auth/auth.go

@@ -1,15 +1,20 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// Package auth implements various authentication methods
 package auth
 
 import (
+	"bytes"
 	"context"
 	"crypto/rand"
 	"database/sql"
 	"encoding/base64"
+	"encoding/json"
 	"errors"
+	"fmt"
 	"net"
 	"net/http"
 	"os"
@@ -20,13 +25,25 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/util"
 	"github.com/gorilla/sessions"
 )
 
+// Authenticator is the interface for all authentication methods.
+// Each authenticator determines if it can handle a login request (CanLogin)
+// and performs the actual authentication (Login).
 type Authenticator interface {
+	// CanLogin determines if this authenticator can handle the login request.
+	// It returns the user object if available and a boolean indicating if this
+	// authenticator should attempt the login. This method should not perform
+	// expensive operations or actual authentication.
 	CanLogin(user *schema.User, username string, rw http.ResponseWriter, r *http.Request) (*schema.User, bool)
+	
+	// Login performs the actually authentication for the user.
+	// It returns the authenticated user or an error if authentication fails.
+	// The user parameter may be nil if the user doesn't exist in the database yet.
 	Login(user *schema.User, rw http.ResponseWriter, r *http.Request) (*schema.User, error)
 }
 
@@ -35,19 +52,70 @@ var (
 	authInstance *Authentication
 )
 
-var ipUserLimiters sync.Map
-
-func getIPUserLimiter(ip, username string) *rate.Limiter {
-	key := ip + ":" + username
-	limiter, ok := ipUserLimiters.Load(key)
-	if !ok {
-		newLimiter := rate.NewLimiter(rate.Every(time.Hour/10), 10)
-		ipUserLimiters.Store(key, newLimiter)
-		return newLimiter
-	}
-	return limiter.(*rate.Limiter)
+// rateLimiterEntry tracks a rate limiter and its last use time for cleanup
+type rateLimiterEntry struct {
+	limiter  *rate.Limiter
+	lastUsed time.Time
 }
 
+var ipUserLimiters sync.Map
+
+// getIPUserLimiter returns a rate limiter for the given IP and username combination.
+// Rate limiters are created on demand and track 5 attempts per 15 minutes.
+func getIPUserLimiter(ip, username string) *rate.Limiter {
+	key := ip + ":" + username
+	now := time.Now()
+	
+	if entry, ok := ipUserLimiters.Load(key); ok {
+		rle := entry.(*rateLimiterEntry)
+		rle.lastUsed = now
+		return rle.limiter
+	}
+	
+	// More aggressive rate limiting: 5 attempts per 15 minutes
+	newLimiter := rate.NewLimiter(rate.Every(15*time.Minute/5), 5)
+	ipUserLimiters.Store(key, &rateLimiterEntry{
+		limiter:  newLimiter,
+		lastUsed: now,
+	})
+	return newLimiter
+}
+
+// cleanupOldRateLimiters removes rate limiters that haven't been used recently
+func cleanupOldRateLimiters(olderThan time.Time) {
+	ipUserLimiters.Range(func(key, value any) bool {
+		entry := value.(*rateLimiterEntry)
+		if entry.lastUsed.Before(olderThan) {
+			ipUserLimiters.Delete(key)
+			cclog.Debugf("Cleaned up rate limiter for %v", key)
+		}
+		return true
+	})
+}
+
+// startRateLimiterCleanup starts a background goroutine to clean up old rate limiters
+func startRateLimiterCleanup() {
+	go func() {
+		ticker := time.NewTicker(1 * time.Hour)
+		defer ticker.Stop()
+		for range ticker.C {
+			// Clean up limiters not used in the last 24 hours
+			cleanupOldRateLimiters(time.Now().Add(-24 * time.Hour))
+		}
+	}()
+}
+
+// AuthConfig contains configuration for all authentication methods
+type AuthConfig struct {
+	LdapConfig   *LdapConfig    `json:"ldap"`
+	JwtConfig    *JWTAuthConfig `json:"jwts"`
+	OpenIDConfig *OpenIDConfig  `json:"oidc"`
+}
+
+// Keys holds the global authentication configuration
+var Keys AuthConfig
+
+// Authentication manages all authentication methods and session handling
 type Authentication struct {
 	sessionStore   *sessions.CookieStore
 	LdapAuth       *LdapAuthenticator
@@ -63,7 +131,7 @@ func (auth *Authentication) AuthViaSession(
 ) (*schema.User, error) {
 	session, err := auth.sessionStore.Get(r, "session")
 	if err != nil {
-		log.Error("Error while getting session store")
+		cclog.Error("Error while getting session store")
 		return nil, err
 	}
 
@@ -71,10 +139,31 @@ func (auth *Authentication) AuthViaSession(
 		return nil, nil
 	}
 
-	// TODO: Check if session keys exist
-	username, _ := session.Values["username"].(string)
-	projects, _ := session.Values["projects"].([]string)
-	roles, _ := session.Values["roles"].([]string)
+	// Validate session data with proper type checking
+	username, ok := session.Values["username"].(string)
+	if !ok || username == "" {
+		cclog.Warn("Invalid session: missing or invalid username")
+		// Invalidate the corrupted session
+		session.Options.MaxAge = -1
+		_ = auth.sessionStore.Save(r, rw, session)
+		return nil, errors.New("invalid session data")
+	}
+
+	projects, ok := session.Values["projects"].([]string)
+	if !ok {
+		cclog.Warn("Invalid session: projects not found or invalid type, using empty list")
+		projects = []string{}
+	}
+
+	roles, ok := session.Values["roles"].([]string)
+	if !ok || len(roles) == 0 {
+		cclog.Warn("Invalid session: missing or invalid roles")
+		// Invalidate the corrupted session
+		session.Options.MaxAge = -1
+		_ = auth.sessionStore.Save(r, rw, session)
+		return nil, errors.New("invalid session data")
+	}
+
 	return &schema.User{
 		Username:   username,
 		Projects:   projects,
@@ -84,22 +173,25 @@ func (auth *Authentication) AuthViaSession(
 	}, nil
 }
 
-func Init() {
+func Init(authCfg *json.RawMessage) {
 	initOnce.Do(func() {
 		authInstance = &Authentication{}
+		
+		// Start background cleanup of rate limiters
+		startRateLimiterCleanup()
 
 		sessKey := os.Getenv("SESSION_KEY")
 		if sessKey == "" {
-			log.Warn("environment variable 'SESSION_KEY' not set (will use non-persistent random key)")
+			cclog.Warn("environment variable 'SESSION_KEY' not set (will use non-persistent random key)")
 			bytes := make([]byte, 32)
 			if _, err := rand.Read(bytes); err != nil {
-				log.Fatal("Error while initializing authentication -> failed to generate random bytes for session key")
+				cclog.Fatal("Error while initializing authentication -> failed to generate random bytes for session key")
 			}
 			authInstance.sessionStore = sessions.NewCookieStore(bytes)
 		} else {
 			bytes, err := base64.StdEncoding.DecodeString(sessKey)
 			if err != nil {
-				log.Fatal("Error while initializing authentication -> decoding session key failed")
+				cclog.Fatal("Error while initializing authentication -> decoding session key failed")
 			}
 			authInstance.sessionStore = sessions.NewCookieStore(bytes)
 		}
@@ -108,44 +200,55 @@ func Init() {
 			authInstance.SessionMaxAge = d
 		}
 
-		if config.Keys.LdapConfig != nil {
+		if authCfg == nil {
+			return
+		}
+
+		config.Validate(configSchema, *authCfg)
+		dec := json.NewDecoder(bytes.NewReader(*authCfg))
+		dec.DisallowUnknownFields()
+		if err := dec.Decode(&Keys); err != nil {
+			cclog.Errorf("error while decoding ldap config: %v", err)
+		}
+
+		if Keys.LdapConfig != nil {
 			ldapAuth := &LdapAuthenticator{}
 			if err := ldapAuth.Init(); err != nil {
-				log.Warn("Error while initializing authentication -> ldapAuth init failed")
+				cclog.Warn("Error while initializing authentication -> ldapAuth init failed")
 			} else {
 				authInstance.LdapAuth = ldapAuth
 				authInstance.authenticators = append(authInstance.authenticators, authInstance.LdapAuth)
 			}
 		} else {
-			log.Info("Missing LDAP configuration: No LDAP support!")
+			cclog.Info("Missing LDAP configuration: No LDAP support!")
 		}
 
-		if config.Keys.JwtConfig != nil {
+		if Keys.JwtConfig != nil {
 			authInstance.JwtAuth = &JWTAuthenticator{}
 			if err := authInstance.JwtAuth.Init(); err != nil {
-				log.Fatal("Error while initializing authentication -> jwtAuth init failed")
+				cclog.Fatal("Error while initializing authentication -> jwtAuth init failed")
 			}
 
 			jwtSessionAuth := &JWTSessionAuthenticator{}
 			if err := jwtSessionAuth.Init(); err != nil {
-				log.Info("jwtSessionAuth init failed: No JWT login support!")
+				cclog.Info("jwtSessionAuth init failed: No JWT login support!")
 			} else {
 				authInstance.authenticators = append(authInstance.authenticators, jwtSessionAuth)
 			}
 
 			jwtCookieSessionAuth := &JWTCookieSessionAuthenticator{}
 			if err := jwtCookieSessionAuth.Init(); err != nil {
-				log.Info("jwtCookieSessionAuth init failed: No JWT cookie login support!")
+				cclog.Info("jwtCookieSessionAuth init failed: No JWT cookie login support!")
 			} else {
 				authInstance.authenticators = append(authInstance.authenticators, jwtCookieSessionAuth)
 			}
 		} else {
-			log.Info("Missing JWT configuration: No JWT token support!")
+			cclog.Info("Missing JWT configuration: No JWT token support!")
 		}
 
 		authInstance.LocalAuth = &LocalAuthenticator{}
 		if err := authInstance.LocalAuth.Init(); err != nil {
-			log.Fatal("Error while initializing authentication -> localAuth init failed")
+			cclog.Fatal("Error while initializing authentication -> localAuth init failed")
 		}
 		authInstance.authenticators = append(authInstance.authenticators, authInstance.LocalAuth)
 	})
@@ -153,50 +256,48 @@ func Init() {
 
 func GetAuthInstance() *Authentication {
 	if authInstance == nil {
-		log.Fatal("Authentication module not initialized!")
+		cclog.Fatal("Authentication module not initialized!")
 	}
 
 	return authInstance
 }
 
-func handleTokenUser(tokenUser *schema.User) {
+// handleUserSync syncs or updates a user in the database based on configuration.
+// This is used for both JWT and OIDC authentication when syncUserOnLogin or updateUserOnLogin is enabled.
+func handleUserSync(user *schema.User, syncUserOnLogin, updateUserOnLogin bool) {
 	r := repository.GetUserRepository()
-	dbUser, err := r.GetUser(tokenUser.Username)
+	dbUser, err := r.GetUser(user.Username)
 
 	if err != nil && err != sql.ErrNoRows {
-		log.Errorf("Error while loading user '%s': %v", tokenUser.Username, err)
-	} else if err == sql.ErrNoRows && config.Keys.JwtConfig.SyncUserOnLogin { // Adds New User
-		if err := r.AddUser(tokenUser); err != nil {
-			log.Errorf("Error while adding user '%s' to DB: %v", tokenUser.Username, err)
+		cclog.Errorf("Error while loading user '%s': %v", user.Username, err)
+		return
+	}
+	
+	if err == sql.ErrNoRows && syncUserOnLogin { // Add new user
+		if err := r.AddUser(user); err != nil {
+			cclog.Errorf("Error while adding user '%s' to DB: %v", user.Username, err)
 		}
-	} else if err == nil && config.Keys.JwtConfig.UpdateUserOnLogin { // Update Existing User
-		if err := r.UpdateUser(dbUser, tokenUser); err != nil {
-			log.Errorf("Error while updating user '%s' to DB: %v", dbUser.Username, err)
+	} else if err == nil && updateUserOnLogin { // Update existing user
+		if err := r.UpdateUser(dbUser, user); err != nil {
+			cclog.Errorf("Error while updating user '%s' in DB: %v", dbUser.Username, err)
 		}
 	}
 }
 
-func handleOIDCUser(OIDCUser *schema.User) {
-	r := repository.GetUserRepository()
-	dbUser, err := r.GetUser(OIDCUser.Username)
+// handleTokenUser syncs JWT token user with database
+func handleTokenUser(tokenUser *schema.User) {
+	handleUserSync(tokenUser, Keys.JwtConfig.SyncUserOnLogin, Keys.JwtConfig.UpdateUserOnLogin)
+}
 
-	if err != nil && err != sql.ErrNoRows {
-		log.Errorf("Error while loading user '%s': %v", OIDCUser.Username, err)
-	} else if err == sql.ErrNoRows && config.Keys.OpenIDConfig.SyncUserOnLogin { // Adds New User
-		if err := r.AddUser(OIDCUser); err != nil {
-			log.Errorf("Error while adding user '%s' to DB: %v", OIDCUser.Username, err)
-		}
-	} else if err == nil && config.Keys.OpenIDConfig.UpdateUserOnLogin { // Update Existing User
-		if err := r.UpdateUser(dbUser, OIDCUser); err != nil {
-			log.Errorf("Error while updating user '%s' to DB: %v", dbUser.Username, err)
-		}
-	}
+// handleOIDCUser syncs OIDC user with database
+func handleOIDCUser(OIDCUser *schema.User) {
+	handleUserSync(OIDCUser, Keys.OpenIDConfig.SyncUserOnLogin, Keys.OpenIDConfig.UpdateUserOnLogin)
 }
 
 func (auth *Authentication) SaveSession(rw http.ResponseWriter, r *http.Request, user *schema.User) error {
 	session, err := auth.sessionStore.New(r, "session")
 	if err != nil {
-		log.Errorf("session creation failed: %s", err.Error())
+		cclog.Errorf("session creation failed: %s", err.Error())
 		http.Error(rw, err.Error(), http.StatusInternalServerError)
 		return err
 	}
@@ -204,7 +305,8 @@ func (auth *Authentication) SaveSession(rw http.ResponseWriter, r *http.Request,
 	if auth.SessionMaxAge != 0 {
 		session.Options.MaxAge = int(auth.SessionMaxAge.Seconds())
 	}
-	if config.Keys.HttpsCertFile == "" && config.Keys.HttpsKeyFile == "" {
+	if config.Keys.HTTPSCertFile == "" && config.Keys.HTTPSKeyFile == "" {
+		cclog.Warn("HTTPS not configured - session cookies will not have Secure flag set (insecure for production)")
 		session.Options.Secure = false
 	}
 	session.Options.SameSite = http.SameSiteStrictMode
@@ -212,7 +314,7 @@ func (auth *Authentication) SaveSession(rw http.ResponseWriter, r *http.Request,
 	session.Values["projects"] = user.Projects
 	session.Values["roles"] = user.Roles
 	if err := auth.sessionStore.Save(r, rw, session); err != nil {
-		log.Warnf("session save failed: %s", err.Error())
+		cclog.Warnf("session save failed: %s", err.Error())
 		http.Error(rw, err.Error(), http.StatusInternalServerError)
 		return err
 	}
@@ -233,9 +335,9 @@ func (auth *Authentication) Login(
 
 		limiter := getIPUserLimiter(ip, username)
 		if !limiter.Allow() {
-				log.Warnf("AUTH/RATE > Too many login attempts for combination IP: %s, Username: %s", ip, username)
-				onfailure(rw, r, errors.New("Too many login attempts, try again in a few minutes."))
-				return
+			cclog.Warnf("AUTH/RATE > Too many login attempts for combination IP: %s, Username: %s", ip, username)
+			onfailure(rw, r, errors.New("too many login attempts, try again in a few minutes"))
+			return
 		}
 
 		var dbUser *schema.User
@@ -243,7 +345,7 @@ func (auth *Authentication) Login(
 			var err error
 			dbUser, err = repository.GetUserRepository().GetUser(username)
 			if err != nil && err != sql.ErrNoRows {
-				log.Errorf("Error while loading user '%v'", username)
+				cclog.Errorf("Error while loading user '%v'", username)
 			}
 		}
 
@@ -253,12 +355,12 @@ func (auth *Authentication) Login(
 			if user, ok = authenticator.CanLogin(dbUser, username, rw, r); !ok {
 				continue
 			} else {
-				log.Debugf("Can login with user %v", user)
+				cclog.Debugf("Can login with user %v", user)
 			}
 
 			user, err := authenticator.Login(user, rw, r)
 			if err != nil {
-				log.Warnf("user login failed: %s", err.Error())
+				cclog.Warnf("user login failed: %s", err.Error())
 				onfailure(rw, r, err)
 				return
 			}
@@ -267,7 +369,7 @@ func (auth *Authentication) Login(
 				return
 			}
 
-			log.Infof("login successfull: user: %#v (roles: %v, projects: %v)", user.Username, user.Roles, user.Projects)
+			cclog.Infof("login successfull: user: %#v (roles: %v, projects: %v)", user.Username, user.Roles, user.Projects)
 			ctx := context.WithValue(r.Context(), repository.ContextUserKey, user)
 
 			if r.FormValue("redirect") != "" {
@@ -279,7 +381,7 @@ func (auth *Authentication) Login(
 			return
 		}
 
-		log.Debugf("login failed: no authenticator applied")
+		cclog.Debugf("login failed: no authenticator applied")
 		onfailure(rw, r, errors.New("no authenticator applied"))
 	})
 }
@@ -291,14 +393,14 @@ func (auth *Authentication) Auth(
 	return http.HandlerFunc(func(rw http.ResponseWriter, r *http.Request) {
 		user, err := auth.JwtAuth.AuthViaJWT(rw, r)
 		if err != nil {
-			log.Infof("auth -> authentication failed: %s", err.Error())
+			cclog.Infof("auth -> authentication failed: %s", err.Error())
 			http.Error(rw, err.Error(), http.StatusUnauthorized)
 			return
 		}
 		if user == nil {
 			user, err = auth.AuthViaSession(rw, r)
 			if err != nil {
-				log.Infof("auth -> authentication failed: %s", err.Error())
+				cclog.Infof("auth -> authentication failed: %s", err.Error())
 				http.Error(rw, err.Error(), http.StatusUnauthorized)
 				return
 			}
@@ -309,22 +411,30 @@ func (auth *Authentication) Auth(
 			return
 		}
 
-		log.Info("auth -> authentication failed")
+		cclog.Info("auth -> authentication failed")
 		onfailure(rw, r, errors.New("unauthorized (please login first)"))
 	})
 }
 
-func (auth *Authentication) AuthApi(
+func (auth *Authentication) AuthAPI(
 	onsuccess http.Handler,
 	onfailure func(rw http.ResponseWriter, r *http.Request, authErr error),
 ) http.Handler {
 	return http.HandlerFunc(func(rw http.ResponseWriter, r *http.Request) {
 		user, err := auth.JwtAuth.AuthViaJWT(rw, r)
 		if err != nil {
-			log.Infof("auth api -> authentication failed: %s", err.Error())
+			cclog.Infof("auth api -> authentication failed: %s", err.Error())
 			onfailure(rw, r, err)
 			return
 		}
+
+		ipErr := securedCheck(user, r)
+		if ipErr != nil {
+			cclog.Infof("auth api -> secured check failed: %s", ipErr.Error())
+			onfailure(rw, r, ipErr)
+			return
+		}
+
 		if user != nil {
 			switch {
 			case len(user.Roles) == 1:
@@ -340,26 +450,63 @@ func (auth *Authentication) AuthApi(
 					return
 				}
 			default:
-				log.Info("auth api -> authentication failed: missing role")
+				cclog.Info("auth api -> authentication failed: missing role")
 				onfailure(rw, r, errors.New("unauthorized"))
 			}
 		}
-		log.Info("auth api -> authentication failed: no auth")
+		cclog.Info("auth api -> authentication failed: no auth")
 		onfailure(rw, r, errors.New("unauthorized"))
 	})
 }
 
-func (auth *Authentication) AuthUserApi(
+func (auth *Authentication) AuthUserAPI(
 	onsuccess http.Handler,
 	onfailure func(rw http.ResponseWriter, r *http.Request, authErr error),
 ) http.Handler {
 	return http.HandlerFunc(func(rw http.ResponseWriter, r *http.Request) {
 		user, err := auth.JwtAuth.AuthViaJWT(rw, r)
 		if err != nil {
-			log.Infof("auth user api -> authentication failed: %s", err.Error())
+			cclog.Infof("auth user api -> authentication failed: %s", err.Error())
 			onfailure(rw, r, err)
 			return
 		}
+
+		if user != nil {
+			switch {
+			case len(user.Roles) == 1:
+				if user.HasRole(schema.RoleApi) {
+					ctx := context.WithValue(r.Context(), repository.ContextUserKey, user)
+					onsuccess.ServeHTTP(rw, r.WithContext(ctx))
+					return
+				}
+			case len(user.Roles) >= 2:
+				if user.HasRole(schema.RoleApi) && user.HasAnyRole([]schema.Role{schema.RoleUser, schema.RoleManager, schema.RoleSupport, schema.RoleAdmin}) {
+					ctx := context.WithValue(r.Context(), repository.ContextUserKey, user)
+					onsuccess.ServeHTTP(rw, r.WithContext(ctx))
+					return
+				}
+			default:
+				cclog.Info("auth user api -> authentication failed: missing role")
+				onfailure(rw, r, errors.New("unauthorized"))
+			}
+		}
+		cclog.Info("auth user api -> authentication failed: no auth")
+		onfailure(rw, r, errors.New("unauthorized"))
+	})
+}
+
+func (auth *Authentication) AuthMetricStoreAPI(
+	onsuccess http.Handler,
+	onfailure func(rw http.ResponseWriter, r *http.Request, authErr error),
+) http.Handler {
+	return http.HandlerFunc(func(rw http.ResponseWriter, r *http.Request) {
+		user, err := auth.JwtAuth.AuthViaJWT(rw, r)
+		if err != nil {
+			cclog.Infof("auth metricstore api -> authentication failed: %s", err.Error())
+			onfailure(rw, r, err)
+			return
+		}
+
 		if user != nil {
 			switch {
 			case len(user.Roles) == 1:
@@ -375,23 +522,23 @@ func (auth *Authentication) AuthUserApi(
 					return
 				}
 			default:
-				log.Info("auth user api -> authentication failed: missing role")
+				cclog.Info("auth metricstore api -> authentication failed: missing role")
 				onfailure(rw, r, errors.New("unauthorized"))
 			}
 		}
-		log.Info("auth user api -> authentication failed: no auth")
+		cclog.Info("auth metricstore api -> authentication failed: no auth")
 		onfailure(rw, r, errors.New("unauthorized"))
 	})
 }
 
-func (auth *Authentication) AuthConfigApi(
+func (auth *Authentication) AuthConfigAPI(
 	onsuccess http.Handler,
 	onfailure func(rw http.ResponseWriter, r *http.Request, authErr error),
 ) http.Handler {
 	return http.HandlerFunc(func(rw http.ResponseWriter, r *http.Request) {
 		user, err := auth.AuthViaSession(rw, r)
 		if err != nil {
-			log.Infof("auth config api -> authentication failed: %s", err.Error())
+			cclog.Infof("auth config api -> authentication failed: %s", err.Error())
 			onfailure(rw, r, err)
 			return
 		}
@@ -400,19 +547,19 @@ func (auth *Authentication) AuthConfigApi(
 			onsuccess.ServeHTTP(rw, r.WithContext(ctx))
 			return
 		}
-		log.Info("auth config api -> authentication failed: no auth")
+		cclog.Info("auth config api -> authentication failed: no auth")
 		onfailure(rw, r, errors.New("unauthorized"))
 	})
 }
 
-func (auth *Authentication) AuthFrontendApi(
+func (auth *Authentication) AuthFrontendAPI(
 	onsuccess http.Handler,
 	onfailure func(rw http.ResponseWriter, r *http.Request, authErr error),
 ) http.Handler {
 	return http.HandlerFunc(func(rw http.ResponseWriter, r *http.Request) {
 		user, err := auth.AuthViaSession(rw, r)
 		if err != nil {
-			log.Infof("auth frontend api -> authentication failed: %s", err.Error())
+			cclog.Infof("auth frontend api -> authentication failed: %s", err.Error())
 			onfailure(rw, r, err)
 			return
 		}
@@ -421,7 +568,7 @@ func (auth *Authentication) AuthFrontendApi(
 			onsuccess.ServeHTTP(rw, r.WithContext(ctx))
 			return
 		}
-		log.Info("auth frontend api -> authentication failed: no auth")
+		cclog.Info("auth frontend api -> authentication failed: no auth")
 		onfailure(rw, r, errors.New("unauthorized"))
 	})
 }
@@ -445,3 +592,42 @@ func (auth *Authentication) Logout(onsuccess http.Handler) http.Handler {
 		onsuccess.ServeHTTP(rw, r)
 	})
 }
+
+// Helper Moved To MiddleWare Auth Handlers
+func securedCheck(user *schema.User, r *http.Request) error {
+	if user == nil {
+		return fmt.Errorf("no user for secured check")
+	}
+
+	// extract IP address for checking
+	IPAddress := r.Header.Get("X-Real-Ip")
+	if IPAddress == "" {
+		IPAddress = r.Header.Get("X-Forwarded-For")
+	}
+	if IPAddress == "" {
+		IPAddress = r.RemoteAddr
+	}
+
+	// Handle both IPv4 and IPv6 addresses properly
+	// For IPv6, this will strip the port and brackets
+	// For IPv4, this will strip the port
+	if host, _, err := net.SplitHostPort(IPAddress); err == nil {
+		IPAddress = host
+	}
+	// If SplitHostPort fails, IPAddress is already just a host (no port)
+
+	// If nothing declared in config: deny all request to this api endpoint
+	if len(config.Keys.APIAllowedIPs) == 0 {
+		return fmt.Errorf("missing configuration key ApiAllowedIPs")
+	}
+	// If wildcard declared in config: Continue
+	if config.Keys.APIAllowedIPs[0] == "*" {
+		return nil
+	}
+	// check if IP is allowed
+	if !util.Contains(config.Keys.APIAllowedIPs, IPAddress) {
+		return fmt.Errorf("unknown ip: %v", IPAddress)
+	}
+
+	return nil
+}

internal/auth/auth_test.go

@@ -0,0 +1,176 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package auth
+
+import (
+	"net"
+	"testing"
+	"time"
+)
+
+// TestGetIPUserLimiter tests the rate limiter creation and retrieval
+func TestGetIPUserLimiter(t *testing.T) {
+	ip := "192.168.1.1"
+	username := "testuser"
+	
+	// Get limiter for the first time
+	limiter1 := getIPUserLimiter(ip, username)
+	if limiter1 == nil {
+		t.Fatal("Expected limiter to be created")
+	}
+	
+	// Get the same limiter again
+	limiter2 := getIPUserLimiter(ip, username)
+	if limiter1 != limiter2 {
+		t.Error("Expected to get the same limiter instance")
+	}
+	
+	// Get a different limiter for different user
+	limiter3 := getIPUserLimiter(ip, "otheruser")
+	if limiter1 == limiter3 {
+		t.Error("Expected different limiter for different user")
+	}
+	
+	// Get a different limiter for different IP
+	limiter4 := getIPUserLimiter("192.168.1.2", username)
+	if limiter1 == limiter4 {
+		t.Error("Expected different limiter for different IP")
+	}
+}
+
+// TestRateLimiterBehavior tests that rate limiting works correctly
+func TestRateLimiterBehavior(t *testing.T) {
+	ip := "10.0.0.1"
+	username := "ratelimituser"
+	
+	limiter := getIPUserLimiter(ip, username)
+	
+	// Should allow first 5 attempts
+	for i := 0; i < 5; i++ {
+		if !limiter.Allow() {
+			t.Errorf("Request %d should be allowed within rate limit", i+1)
+		}
+	}
+	
+	// 6th attempt should be blocked
+	if limiter.Allow() {
+		t.Error("Request 6 should be blocked by rate limiter")
+	}
+}
+
+// TestCleanupOldRateLimiters tests the cleanup function
+func TestCleanupOldRateLimiters(t *testing.T) {
+	// Clear all existing limiters first to avoid interference from other tests
+	cleanupOldRateLimiters(time.Now().Add(24 * time.Hour))
+	
+	// Create some new rate limiters
+	limiter1 := getIPUserLimiter("1.1.1.1", "user1")
+	limiter2 := getIPUserLimiter("2.2.2.2", "user2")
+	
+	if limiter1 == nil || limiter2 == nil {
+		t.Fatal("Failed to create test limiters")
+	}
+	
+	// Cleanup limiters older than 1 second from now (should keep both)
+	time.Sleep(10 * time.Millisecond) // Small delay to ensure timestamp difference
+	cleanupOldRateLimiters(time.Now().Add(-1 * time.Second))
+	
+	// Verify they still exist (should get same instance)
+	if getIPUserLimiter("1.1.1.1", "user1") != limiter1 {
+		t.Error("Limiter 1 was incorrectly cleaned up")
+	}
+	if getIPUserLimiter("2.2.2.2", "user2") != limiter2 {
+		t.Error("Limiter 2 was incorrectly cleaned up")
+	}
+	
+	// Cleanup limiters older than 1 hour from now (should remove both)
+	cleanupOldRateLimiters(time.Now().Add(2 * time.Hour))
+	
+	// Getting them again should create new instances
+	newLimiter1 := getIPUserLimiter("1.1.1.1", "user1")
+	if newLimiter1 == limiter1 {
+		t.Error("Old limiter should have been cleaned up")
+	}
+}
+
+// TestIPv4Extraction tests extracting IPv4 addresses
+func TestIPv4Extraction(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    string
+		expected string
+	}{
+		{"IPv4 with port", "192.168.1.1:8080", "192.168.1.1"},
+		{"IPv4 without port", "192.168.1.1", "192.168.1.1"},
+		{"Localhost with port", "127.0.0.1:3000", "127.0.0.1"},
+	}
+	
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := tt.input
+			if host, _, err := net.SplitHostPort(result); err == nil {
+				result = host
+			}
+			
+			if result != tt.expected {
+				t.Errorf("Expected %s, got %s", tt.expected, result)
+			}
+		})
+	}
+}
+
+// TestIPv6Extraction tests extracting IPv6 addresses  
+func TestIPv6Extraction(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    string
+		expected string
+	}{
+		{"IPv6 with port", "[2001:db8::1]:8080", "2001:db8::1"},
+		{"IPv6 localhost with port", "[::1]:3000", "::1"},
+		{"IPv6 without port", "2001:db8::1", "2001:db8::1"},
+		{"IPv6 localhost", "::1", "::1"},
+	}
+	
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := tt.input
+			if host, _, err := net.SplitHostPort(result); err == nil {
+				result = host
+			}
+			
+			if result != tt.expected {
+				t.Errorf("Expected %s, got %s", tt.expected, result)
+			}
+		})
+	}
+}
+
+// TestIPExtractionEdgeCases tests edge cases for IP extraction
+func TestIPExtractionEdgeCases(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    string
+		expected string
+	}{
+		{"Hostname without port", "example.com", "example.com"},
+		{"Empty string", "", ""},
+		{"Just port", ":8080", ""},
+	}
+	
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := tt.input
+			if host, _, err := net.SplitHostPort(result); err == nil {
+				result = host
+			}
+			
+			if result != tt.expected {
+				t.Errorf("Expected %s, got %s", tt.expected, result)
+			}
+		})
+	}
+}

internal/auth/jwt.go

@@ -1,7 +1,8 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package auth
 
 import (
@@ -13,13 +14,33 @@ import (
 	"strings"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/internal/config"
-	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	"github.com/golang-jwt/jwt/v5"
 )
 
+type JWTAuthConfig struct {
+	// Specifies for how long a JWT token shall be valid
+	// as a string parsable by time.ParseDuration().
+	MaxAge string `json:"max-age"`
+
+	// Specifies which cookie should be checked for a JWT token (if no authorization header is present)
+	CookieName string `json:"cookieName"`
+
+	// Deny login for users not in database (but defined in JWT).
+	// Ignore user roles defined in JWTs ('roles' claim), get them from db.
+	ValidateUser bool `json:"validateUser"`
+
+	// Specifies which issuer should be accepted when validating external JWTs ('iss' claim)
+	TrustedIssuer string `json:"trustedIssuer"`
+
+	// Should an non-existent user be added to the DB based on the information in the token
+	SyncUserOnLogin bool `json:"syncUserOnLogin"`
+
+	// Should an existent user be updated in the DB based on the information in the token
+	UpdateUserOnLogin bool `json:"updateUserOnLogin"`
+}
+
 type JWTAuthenticator struct {
 	publicKey  ed25519.PublicKey
 	privateKey ed25519.PrivateKey
@@ -28,17 +49,17 @@ type JWTAuthenticator struct {
 func (ja *JWTAuthenticator) Init() error {
 	pubKey, privKey := os.Getenv("JWT_PUBLIC_KEY"), os.Getenv("JWT_PRIVATE_KEY")
 	if pubKey == "" || privKey == "" {
-		log.Warn("environment variables 'JWT_PUBLIC_KEY' or 'JWT_PRIVATE_KEY' not set (token based authentication will not work)")
+		cclog.Warn("environment variables 'JWT_PUBLIC_KEY' or 'JWT_PRIVATE_KEY' not set (token based authentication will not work)")
 	} else {
 		bytes, err := base64.StdEncoding.DecodeString(pubKey)
 		if err != nil {
-			log.Warn("Could not decode JWT public key")
+			cclog.Warn("Could not decode JWT public key")
 			return err
 		}
 		ja.publicKey = ed25519.PublicKey(bytes)
 		bytes, err = base64.StdEncoding.DecodeString(privKey)
 		if err != nil {
-			log.Warn("Could not decode JWT private key")
+			cclog.Warn("Could not decode JWT private key")
 			return err
 		}
 		ja.privateKey = ed25519.PrivateKey(bytes)
@@ -62,7 +83,7 @@ func (ja *JWTAuthenticator) AuthViaJWT(
 		return nil, nil
 	}
 
-	token, err := jwt.Parse(rawtoken, func(t *jwt.Token) (interface{}, error) {
+	token, err := jwt.Parse(rawtoken, func(t *jwt.Token) (any, error) {
 		if t.Method != jwt.SigningMethodEdDSA {
 			return nil, errors.New("only Ed25519/EdDSA supported")
 		}
@@ -70,51 +91,34 @@ func (ja *JWTAuthenticator) AuthViaJWT(
 		return ja.publicKey, nil
 	})
 	if err != nil {
-		log.Warn("Error while parsing JWT token")
+		cclog.Warn("Error while parsing JWT token")
 		return nil, err
 	}
 	if !token.Valid {
-		log.Warn("jwt token claims are not valid")
+		cclog.Warn("jwt token claims are not valid")
 		return nil, errors.New("jwt token claims are not valid")
 	}
 
 	// Token is valid, extract payload
 	claims := token.Claims.(jwt.MapClaims)
-	sub, _ := claims["sub"].(string)
-
-	var roles []string
-
-	// Validate user + roles from JWT against database?
-	if config.Keys.JwtConfig.ValidateUser {
-		ur := repository.GetUserRepository()
-		user, err := ur.GetUser(sub)
-		// Deny any logins for unknown usernames
-		if err != nil {
-			log.Warn("Could not find user from JWT in internal database.")
-			return nil, errors.New("unknown user")
-		}
-		// Take user roles from database instead of trusting the JWT
-		roles = user.Roles
-	} else {
-		// Extract roles from JWT (if present)
-		if rawroles, ok := claims["roles"].([]interface{}); ok {
-			for _, rr := range rawroles {
-				if r, ok := rr.(string); ok {
-					roles = append(roles, r)
-				}
-			}
-		}
+	
+	// Use shared helper to get user from JWT claims
+	var user *schema.User
+	user, err = getUserFromJWT(claims, Keys.JwtConfig.ValidateUser, schema.AuthToken, -1)
+	if err != nil {
+		return nil, err
 	}
-
-	return &schema.User{
-		Username:   sub,
-		Roles:      roles,
-		AuthType:   schema.AuthToken,
-		AuthSource: -1,
-	}, nil
+	
+	// If not validating user, we only get roles from JWT (no projects for this auth method)
+	if !Keys.JwtConfig.ValidateUser {
+		user.Roles = extractRolesFromClaims(claims, false)
+		user.Projects = nil // Standard JWT auth doesn't include projects
+	}
+	
+	return user, nil
 }
 
-// Generate a new JWT that can be used for authentication
+// ProvideJWT generates a new JWT that can be used for authentication
 func (ja *JWTAuthenticator) ProvideJWT(user *schema.User) (string, error) {
 	if ja.privateKey == nil {
 		return "", errors.New("environment variable 'JWT_PRIVATE_KEY' not set")
@@ -126,8 +130,8 @@ func (ja *JWTAuthenticator) ProvideJWT(user *schema.User) (string, error) {
 		"roles": user.Roles,
 		"iat":   now.Unix(),
 	}
-	if config.Keys.JwtConfig.MaxAge != "" {
-		d, err := time.ParseDuration(config.Keys.JwtConfig.MaxAge)
+	if Keys.JwtConfig.MaxAge != "" {
+		d, err := time.ParseDuration(Keys.JwtConfig.MaxAge)
 		if err != nil {
 			return "", errors.New("cannot parse max-age config key")
 		}

internal/auth/jwtCookieSession.go

@@ -1,22 +1,19 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package auth
 
 import (
 	"crypto/ed25519"
-	"database/sql"
 	"encoding/base64"
 	"errors"
-	"fmt"
 	"net/http"
 	"os"
 
-	"github.com/ClusterCockpit/cc-backend/internal/config"
-	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	"github.com/golang-jwt/jwt/v5"
 )
 
@@ -31,18 +28,18 @@ var _ Authenticator = (*JWTCookieSessionAuthenticator)(nil)
 func (ja *JWTCookieSessionAuthenticator) Init() error {
 	pubKey, privKey := os.Getenv("JWT_PUBLIC_KEY"), os.Getenv("JWT_PRIVATE_KEY")
 	if pubKey == "" || privKey == "" {
-		log.Warn("environment variables 'JWT_PUBLIC_KEY' or 'JWT_PRIVATE_KEY' not set (token based authentication will not work)")
+		cclog.Warn("environment variables 'JWT_PUBLIC_KEY' or 'JWT_PRIVATE_KEY' not set (token based authentication will not work)")
 		return errors.New("environment variables 'JWT_PUBLIC_KEY' or 'JWT_PRIVATE_KEY' not set (token based authentication will not work)")
 	} else {
 		bytes, err := base64.StdEncoding.DecodeString(pubKey)
 		if err != nil {
-			log.Warn("Could not decode JWT public key")
+			cclog.Warn("Could not decode JWT public key")
 			return err
 		}
 		ja.publicKey = ed25519.PublicKey(bytes)
 		bytes, err = base64.StdEncoding.DecodeString(privKey)
 		if err != nil {
-			log.Warn("Could not decode JWT private key")
+			cclog.Warn("Could not decode JWT private key")
 			return err
 		}
 		ja.privateKey = ed25519.PrivateKey(bytes)
@@ -53,36 +50,35 @@ func (ja *JWTCookieSessionAuthenticator) Init() error {
 	if keyFound && pubKeyCrossLogin != "" {
 		bytes, err := base64.StdEncoding.DecodeString(pubKeyCrossLogin)
 		if err != nil {
-			log.Warn("Could not decode cross login JWT public key")
+			cclog.Warn("Could not decode cross login JWT public key")
 			return err
 		}
 		ja.publicKeyCrossLogin = ed25519.PublicKey(bytes)
 	} else {
 		ja.publicKeyCrossLogin = nil
-		log.Debug("environment variable 'CROSS_LOGIN_JWT_PUBLIC_KEY' not set (cross login token based authentication will not work)")
+		cclog.Debug("environment variable 'CROSS_LOGIN_JWT_PUBLIC_KEY' not set (cross login token based authentication will not work)")
 		return errors.New("environment variable 'CROSS_LOGIN_JWT_PUBLIC_KEY' not set (cross login token based authentication will not work)")
 	}
 
-	jc := config.Keys.JwtConfig
 	// Warn if other necessary settings are not configured
-	if jc != nil {
-		if jc.CookieName == "" {
-			log.Info("cookieName for JWTs not configured (cross login via JWT cookie will fail)")
+	if Keys.JwtConfig != nil {
+		if Keys.JwtConfig.CookieName == "" {
+			cclog.Info("cookieName for JWTs not configured (cross login via JWT cookie will fail)")
 			return errors.New("cookieName for JWTs not configured (cross login via JWT cookie will fail)")
 		}
-		if !jc.ValidateUser {
-			log.Info("forceJWTValidationViaDatabase not set to true: CC will accept users and roles defined in JWTs regardless of its own database!")
+		if !Keys.JwtConfig.ValidateUser {
+			cclog.Info("forceJWTValidationViaDatabase not set to true: CC will accept users and roles defined in JWTs regardless of its own database!")
 		}
-		if jc.TrustedIssuer == "" {
-			log.Info("trustedExternalIssuer for JWTs not configured (cross login via JWT cookie will fail)")
+		if Keys.JwtConfig.TrustedIssuer == "" {
+			cclog.Info("trustedExternalIssuer for JWTs not configured (cross login via JWT cookie will fail)")
 			return errors.New("trustedExternalIssuer for JWTs not configured (cross login via JWT cookie will fail)")
 		}
 	} else {
-		log.Warn("config for JWTs not configured (cross login via JWT cookie will fail)")
+		cclog.Warn("config for JWTs not configured (cross login via JWT cookie will fail)")
 		return errors.New("config for JWTs not configured (cross login via JWT cookie will fail)")
 	}
 
-	log.Info("JWT Cookie Session authenticator successfully registered")
+	cclog.Info("JWT Cookie Session authenticator successfully registered")
 	return nil
 }
 
@@ -92,7 +88,7 @@ func (ja *JWTCookieSessionAuthenticator) CanLogin(
 	rw http.ResponseWriter,
 	r *http.Request,
 ) (*schema.User, bool) {
-	jc := config.Keys.JwtConfig
+	jc := Keys.JwtConfig
 	cookieName := ""
 	if jc.CookieName != "" {
 		cookieName = jc.CookieName
@@ -115,7 +111,7 @@ func (ja *JWTCookieSessionAuthenticator) Login(
 	rw http.ResponseWriter,
 	r *http.Request,
 ) (*schema.User, error) {
-	jc := config.Keys.JwtConfig
+	jc := Keys.JwtConfig
 	jwtCookie, err := r.Cookie(jc.CookieName)
 	var rawtoken string
 
@@ -123,7 +119,7 @@ func (ja *JWTCookieSessionAuthenticator) Login(
 		rawtoken = jwtCookie.Value
 	}
 
-	token, err := jwt.Parse(rawtoken, func(t *jwt.Token) (interface{}, error) {
+	token, err := jwt.Parse(rawtoken, func(t *jwt.Token) (any, error) {
 		if t.Method != jwt.SigningMethodEdDSA {
 			return nil, errors.New("only Ed25519/EdDSA supported")
 		}
@@ -140,67 +136,26 @@ func (ja *JWTCookieSessionAuthenticator) Login(
 		return ja.publicKey, nil
 	})
 	if err != nil {
-		log.Warn("JWT cookie session: error while parsing token")
+		cclog.Warn("JWT cookie session: error while parsing token")
 		return nil, err
 	}
 
 	if !token.Valid {
-		log.Warn("jwt token claims are not valid")
+		cclog.Warn("jwt token claims are not valid")
 		return nil, errors.New("jwt token claims are not valid")
 	}
 
 	claims := token.Claims.(jwt.MapClaims)
-	sub, _ := claims["sub"].(string)
-
-	var roles []string
-	projects := make([]string, 0)
-
-	if jc.ValidateUser {
-		var err error
-		user, err = repository.GetUserRepository().GetUser(sub)
-		if err != nil && err != sql.ErrNoRows {
-			log.Errorf("Error while loading user '%v'", sub)
-		}
-
-		// Deny any logins for unknown usernames
-		if user == nil {
-			log.Warn("Could not find user from JWT in internal database.")
-			return nil, errors.New("unknown user")
-		}
-	} else {
-		var name string
-		if wrap, ok := claims["name"].(map[string]interface{}); ok {
-			if vals, ok := wrap["values"].([]interface{}); ok {
-				if len(vals) != 0 {
-					name = fmt.Sprintf("%v", vals[0])
-
-					for i := 1; i < len(vals); i++ {
-						name += fmt.Sprintf(" %v", vals[i])
-					}
-				}
-			}
-		}
-
-		// Extract roles from JWT (if present)
-		if rawroles, ok := claims["roles"].([]interface{}); ok {
-			for _, rr := range rawroles {
-				if r, ok := rr.(string); ok {
-					roles = append(roles, r)
-				}
-			}
-		}
-		user = &schema.User{
-			Username:   sub,
-			Name:       name,
-			Roles:      roles,
-			Projects:   projects,
-			AuthType:   schema.AuthSession,
-			AuthSource: schema.AuthViaToken,
-		}
-
-		if jc.SyncUserOnLogin || jc.UpdateUserOnLogin {
-			handleTokenUser(user)
-		}
+	
+	// Use shared helper to get user from JWT claims
+	user, err = getUserFromJWT(claims, jc.ValidateUser, schema.AuthSession, schema.AuthViaToken)
+	if err != nil {
+		return nil, err
+	}
+	
+	// Sync or update user if configured
+	if !jc.ValidateUser && (jc.SyncUserOnLogin || jc.UpdateUserOnLogin) {
+		handleTokenUser(user)
 	}
 
 	// (Ask browser to) Delete JWT cookie

internal/auth/jwtHelpers.go

@@ -0,0 +1,136 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package auth
+
+import (
+	"database/sql"
+	"errors"
+	"fmt"
+
+	"github.com/ClusterCockpit/cc-backend/internal/repository"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/golang-jwt/jwt/v5"
+)
+
+// extractStringFromClaims extracts a string value from JWT claims
+func extractStringFromClaims(claims jwt.MapClaims, key string) string {
+	if val, ok := claims[key].(string); ok {
+		return val
+	}
+	return ""
+}
+
+// extractRolesFromClaims extracts roles from JWT claims
+// If validateRoles is true, only valid roles are returned
+func extractRolesFromClaims(claims jwt.MapClaims, validateRoles bool) []string {
+	var roles []string
+	
+	if rawroles, ok := claims["roles"].([]any); ok {
+		for _, rr := range rawroles {
+			if r, ok := rr.(string); ok {
+				if validateRoles {
+					if schema.IsValidRole(r) {
+						roles = append(roles, r)
+					}
+				} else {
+					roles = append(roles, r)
+				}
+			}
+		}
+	}
+	
+	return roles
+}
+
+// extractProjectsFromClaims extracts projects from JWT claims
+func extractProjectsFromClaims(claims jwt.MapClaims) []string {
+	projects := make([]string, 0)
+	
+	if rawprojs, ok := claims["projects"].([]any); ok {
+		for _, pp := range rawprojs {
+			if p, ok := pp.(string); ok {
+				projects = append(projects, p)
+			}
+		}
+	} else if rawprojs, ok := claims["projects"]; ok {
+		if projSlice, ok := rawprojs.([]string); ok {
+			projects = append(projects, projSlice...)
+		}
+	}
+	
+	return projects
+}
+
+// extractNameFromClaims extracts name from JWT claims
+// Handles both simple string and complex nested structure
+func extractNameFromClaims(claims jwt.MapClaims) string {
+	// Try simple string first
+	if name, ok := claims["name"].(string); ok {
+		return name
+	}
+	
+	// Try nested structure: {name: {values: [...]}}
+	if wrap, ok := claims["name"].(map[string]any); ok {
+		if vals, ok := wrap["values"].([]any); ok {
+			if len(vals) == 0 {
+				return ""
+			}
+			
+			name := fmt.Sprintf("%v", vals[0])
+			for i := 1; i < len(vals); i++ {
+				name += fmt.Sprintf(" %v", vals[i])
+			}
+			return name
+		}
+	}
+	
+	return ""
+}
+
+// getUserFromJWT creates or retrieves a user based on JWT claims
+// If validateUser is true, the user must exist in the database
+// Otherwise, a new user object is created from claims
+// authSource should be a schema.AuthSource constant (like schema.AuthViaToken)
+func getUserFromJWT(claims jwt.MapClaims, validateUser bool, authType schema.AuthType, authSource schema.AuthSource) (*schema.User, error) {
+	sub := extractStringFromClaims(claims, "sub")
+	if sub == "" {
+		return nil, errors.New("missing 'sub' claim in JWT")
+	}
+	
+	if validateUser {
+		// Validate user against database
+		ur := repository.GetUserRepository()
+		user, err := ur.GetUser(sub)
+		if err != nil && err != sql.ErrNoRows {
+			cclog.Errorf("Error while loading user '%v': %v", sub, err)
+			return nil, fmt.Errorf("database error: %w", err)
+		}
+		
+		// Deny any logins for unknown usernames
+		if user == nil || err == sql.ErrNoRows {
+			cclog.Warn("Could not find user from JWT in internal database.")
+			return nil, errors.New("unknown user")
+		}
+		
+		// Return database user (with database roles)
+		return user, nil
+	}
+	
+	// Create user from JWT claims
+	name := extractNameFromClaims(claims)
+	roles := extractRolesFromClaims(claims, true) // Validate roles
+	projects := extractProjectsFromClaims(claims)
+	
+	return &schema.User{
+		Username:   sub,
+		Name:       name,
+		Roles:      roles,
+		Projects:   projects,
+		AuthType:   authType,
+		AuthSource: authSource,
+	}, nil
+}

internal/auth/jwtHelpers_test.go

@@ -0,0 +1,281 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package auth
+
+import (
+	"testing"
+
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/golang-jwt/jwt/v5"
+)
+
+// TestExtractStringFromClaims tests extracting string values from JWT claims
+func TestExtractStringFromClaims(t *testing.T) {
+	claims := jwt.MapClaims{
+		"sub":   "testuser",
+		"email": "test@example.com",
+		"age":   25, // not a string
+	}
+	
+	tests := []struct {
+		name     string
+		key      string
+		expected string
+	}{
+		{"Existing string", "sub", "testuser"},
+		{"Another string", "email", "test@example.com"},
+		{"Non-existent key", "missing", ""},
+		{"Non-string value", "age", ""},
+	}
+	
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := extractStringFromClaims(claims, tt.key)
+			if result != tt.expected {
+				t.Errorf("Expected %s, got %s", tt.expected, result)
+			}
+		})
+	}
+}
+
+// TestExtractRolesFromClaims tests role extraction and validation
+func TestExtractRolesFromClaims(t *testing.T) {
+	tests := []struct {
+		name          string
+		claims        jwt.MapClaims
+		validateRoles bool
+		expected      []string
+	}{
+		{
+			name: "Valid roles without validation",
+			claims: jwt.MapClaims{
+				"roles": []any{"admin", "user", "invalid_role"},
+			},
+			validateRoles: false,
+			expected:      []string{"admin", "user", "invalid_role"},
+		},
+		{
+			name: "Valid roles with validation",
+			claims: jwt.MapClaims{
+				"roles": []any{"admin", "user", "api"},
+			},
+			validateRoles: true,
+			expected:      []string{"admin", "user", "api"},
+		},
+		{
+			name: "Invalid roles with validation",
+			claims: jwt.MapClaims{
+				"roles": []any{"invalid_role", "fake_role"},
+			},
+			validateRoles: true,
+			expected:      []string{}, // Should filter out invalid roles
+		},
+		{
+			name:          "No roles claim",
+			claims:        jwt.MapClaims{},
+			validateRoles: false,
+			expected:      []string{},
+		},
+		{
+			name: "Non-array roles",
+			claims: jwt.MapClaims{
+				"roles": "admin",
+			},
+			validateRoles: false,
+			expected:      []string{},
+		},
+	}
+	
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := extractRolesFromClaims(tt.claims, tt.validateRoles)
+			
+			if len(result) != len(tt.expected) {
+				t.Errorf("Expected %d roles, got %d", len(tt.expected), len(result))
+				return
+			}
+			
+			for i, role := range result {
+				if i >= len(tt.expected) || role != tt.expected[i] {
+					t.Errorf("Expected role %s at position %d, got %s", tt.expected[i], i, role)
+				}
+			}
+		})
+	}
+}
+
+// TestExtractProjectsFromClaims tests project extraction from claims
+func TestExtractProjectsFromClaims(t *testing.T) {
+	tests := []struct {
+		name     string
+		claims   jwt.MapClaims
+		expected []string
+	}{
+		{
+			name: "Projects as array of interfaces",
+			claims: jwt.MapClaims{
+				"projects": []any{"project1", "project2", "project3"},
+			},
+			expected: []string{"project1", "project2", "project3"},
+		},
+		{
+			name: "Projects as string array",
+			claims: jwt.MapClaims{
+				"projects": []string{"projectA", "projectB"},
+			},
+			expected: []string{"projectA", "projectB"},
+		},
+		{
+			name:     "No projects claim",
+			claims:   jwt.MapClaims{},
+			expected: []string{},
+		},
+		{
+			name: "Mixed types in projects array",
+			claims: jwt.MapClaims{
+				"projects": []any{"project1", 123, "project2"},
+			},
+			expected: []string{"project1", "project2"}, // Should skip non-strings
+		},
+	}
+	
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := extractProjectsFromClaims(tt.claims)
+			
+			if len(result) != len(tt.expected) {
+				t.Errorf("Expected %d projects, got %d", len(tt.expected), len(result))
+				return
+			}
+			
+			for i, project := range result {
+				if i >= len(tt.expected) || project != tt.expected[i] {
+					t.Errorf("Expected project %s at position %d, got %s", tt.expected[i], i, project)
+				}
+			}
+		})
+	}
+}
+
+// TestExtractNameFromClaims tests name extraction from various formats
+func TestExtractNameFromClaims(t *testing.T) {
+	tests := []struct {
+		name     string
+		claims   jwt.MapClaims
+		expected string
+	}{
+		{
+			name: "Simple string name",
+			claims: jwt.MapClaims{
+				"name": "John Doe",
+			},
+			expected: "John Doe",
+		},
+		{
+			name: "Nested name structure",
+			claims: jwt.MapClaims{
+				"name": map[string]any{
+					"values": []any{"John", "Doe"},
+				},
+			},
+			expected: "John Doe",
+		},
+		{
+			name: "Nested name with single value",
+			claims: jwt.MapClaims{
+				"name": map[string]any{
+					"values": []any{"Alice"},
+				},
+			},
+			expected: "Alice",
+		},
+		{
+			name:     "No name claim",
+			claims:   jwt.MapClaims{},
+			expected: "",
+		},
+		{
+			name: "Empty nested values",
+			claims: jwt.MapClaims{
+				"name": map[string]any{
+					"values": []any{},
+				},
+			},
+			expected: "",
+		},
+		{
+			name: "Nested with non-string values",
+			claims: jwt.MapClaims{
+				"name": map[string]any{
+					"values": []any{123, "Smith"},
+				},
+			},
+			expected: "123 Smith", // Should convert to string
+		},
+	}
+	
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := extractNameFromClaims(tt.claims)
+			if result != tt.expected {
+				t.Errorf("Expected '%s', got '%s'", tt.expected, result)
+			}
+		})
+	}
+}
+
+// TestGetUserFromJWT_NoValidation tests getUserFromJWT without database validation
+func TestGetUserFromJWT_NoValidation(t *testing.T) {
+	claims := jwt.MapClaims{
+		"sub":      "testuser",
+		"name":     "Test User",
+		"roles":    []any{"user", "admin"},
+		"projects": []any{"project1", "project2"},
+	}
+	
+	user, err := getUserFromJWT(claims, false, schema.AuthToken, -1)
+	
+	if err != nil {
+		t.Fatalf("Unexpected error: %v", err)
+	}
+	
+	if user.Username != "testuser" {
+		t.Errorf("Expected username 'testuser', got '%s'", user.Username)
+	}
+	
+	if user.Name != "Test User" {
+		t.Errorf("Expected name 'Test User', got '%s'", user.Name)
+	}
+	
+	if len(user.Roles) != 2 {
+		t.Errorf("Expected 2 roles, got %d", len(user.Roles))
+	}
+	
+	if len(user.Projects) != 2 {
+		t.Errorf("Expected 2 projects, got %d", len(user.Projects))
+	}
+	
+	if user.AuthType != schema.AuthToken {
+		t.Errorf("Expected AuthType %v, got %v", schema.AuthToken, user.AuthType)
+	}
+}
+
+// TestGetUserFromJWT_MissingSub tests error when sub claim is missing
+func TestGetUserFromJWT_MissingSub(t *testing.T) {
+	claims := jwt.MapClaims{
+		"name": "Test User",
+	}
+	
+	_, err := getUserFromJWT(claims, false, schema.AuthToken, -1)
+	
+	if err == nil {
+		t.Error("Expected error for missing sub claim")
+	}
+	
+	if err.Error() != "missing 'sub' claim in JWT" {
+		t.Errorf("Expected specific error message, got: %v", err)
+	}
+}

internal/auth/jwtSession.go

@@ -1,11 +1,11 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package auth
 
 import (
-	"database/sql"
 	"encoding/base64"
 	"errors"
 	"fmt"
@@ -13,10 +13,8 @@ import (
 	"os"
 	"strings"
 
-	"github.com/ClusterCockpit/cc-backend/internal/config"
-	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	"github.com/golang-jwt/jwt/v5"
 )
 
@@ -30,13 +28,13 @@ func (ja *JWTSessionAuthenticator) Init() error {
 	if pubKey := os.Getenv("CROSS_LOGIN_JWT_HS512_KEY"); pubKey != "" {
 		bytes, err := base64.StdEncoding.DecodeString(pubKey)
 		if err != nil {
-			log.Warn("Could not decode cross login JWT HS512 key")
+			cclog.Warn("Could not decode cross login JWT HS512 key")
 			return err
 		}
 		ja.loginTokenKey = bytes
 	}
 
-	log.Info("JWT Session authenticator successfully registered")
+	cclog.Info("JWT Session authenticator successfully registered")
 	return nil
 }
 
@@ -60,87 +58,33 @@ func (ja *JWTSessionAuthenticator) Login(
 		rawtoken = r.URL.Query().Get("login-token")
 	}
 
-	token, err := jwt.Parse(rawtoken, func(t *jwt.Token) (interface{}, error) {
+	token, err := jwt.Parse(rawtoken, func(t *jwt.Token) (any, error) {
 		if t.Method == jwt.SigningMethodHS256 || t.Method == jwt.SigningMethodHS512 {
 			return ja.loginTokenKey, nil
 		}
 		return nil, fmt.Errorf("unkown signing method for login token: %s (known: HS256, HS512, EdDSA)", t.Method.Alg())
 	})
 	if err != nil {
-		log.Warn("Error while parsing jwt token")
+		cclog.Warn("Error while parsing jwt token")
 		return nil, err
 	}
 
 	if !token.Valid {
-		log.Warn("jwt token claims are not valid")
+		cclog.Warn("jwt token claims are not valid")
 		return nil, errors.New("jwt token claims are not valid")
 	}
 
 	claims := token.Claims.(jwt.MapClaims)
-	sub, _ := claims["sub"].(string)
-
-	var roles []string
-	projects := make([]string, 0)
-
-	if config.Keys.JwtConfig.ValidateUser {
-		var err error
-		user, err = repository.GetUserRepository().GetUser(sub)
-		if err != nil && err != sql.ErrNoRows {
-			log.Errorf("Error while loading user '%v'", sub)
-		}
-
-		// Deny any logins for unknown usernames
-		if user == nil {
-			log.Warn("Could not find user from JWT in internal database.")
-			return nil, errors.New("unknown user")
-		}
-	} else {
-		var name string
-		if wrap, ok := claims["name"].(map[string]interface{}); ok {
-			if vals, ok := wrap["values"].([]interface{}); ok {
-				if len(vals) != 0 {
-					name = fmt.Sprintf("%v", vals[0])
-
-					for i := 1; i < len(vals); i++ {
-						name += fmt.Sprintf(" %v", vals[i])
-					}
-				}
-			}
-		}
-
-		// Extract roles from JWT (if present)
-		if rawroles, ok := claims["roles"].([]interface{}); ok {
-			for _, rr := range rawroles {
-				if r, ok := rr.(string); ok {
-					if schema.IsValidRole(r) {
-						roles = append(roles, r)
-					}
-				}
-			}
-		}
-
-		if rawprojs, ok := claims["projects"].([]interface{}); ok {
-			for _, pp := range rawprojs {
-				if p, ok := pp.(string); ok {
-					projects = append(projects, p)
-				}
-			}
-		} else if rawprojs, ok := claims["projects"]; ok {
-			projects = append(projects, rawprojs.([]string)...)
-		}
-
-		user = &schema.User{
-			Username:   sub,
-			Name:       name,
-			Roles:      roles,
-			Projects:   projects,
-			AuthType:   schema.AuthSession,
-			AuthSource: schema.AuthViaToken,
-		}
-
-		if config.Keys.JwtConfig.SyncUserOnLogin || config.Keys.JwtConfig.UpdateUserOnLogin {
-			handleTokenUser(user)
-		}
+	
+	// Use shared helper to get user from JWT claims
+	user, err = getUserFromJWT(claims, Keys.JwtConfig.ValidateUser, schema.AuthSession, schema.AuthViaToken)
+	if err != nil {
+		return nil, err
+	}
+	
+	// Sync or update user if configured
+	if !Keys.JwtConfig.ValidateUser && (Keys.JwtConfig.SyncUserOnLogin || Keys.JwtConfig.UpdateUserOnLogin) {
+		handleTokenUser(user)
 	}
 
 	return user, nil

internal/auth/ldap.go

@@ -1,7 +1,8 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package auth
 
 import (
@@ -11,13 +12,26 @@ import (
 	"os"
 	"strings"
 
-	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	"github.com/go-ldap/ldap/v3"
 )
 
+type LdapConfig struct {
+	URL             string `json:"url"`
+	UserBase        string `json:"user_base"`
+	SearchDN        string `json:"search_dn"`
+	UserBind        string `json:"user_bind"`
+	UserFilter      string `json:"user_filter"`
+	UserAttr        string `json:"username_attr"`
+	SyncInterval    string `json:"sync_interval"` // Parsed using time.ParseDuration.
+	SyncDelOldUsers bool   `json:"sync_del_old_users"`
+
+	// Should an non-existent user be added to the DB if user exists in ldap directory
+	SyncUserOnLogin bool `json:"syncUserOnLogin"`
+}
+
 type LdapAuthenticator struct {
 	syncPassword string
 	UserAttr     string
@@ -28,13 +42,11 @@ var _ Authenticator = (*LdapAuthenticator)(nil)
 func (la *LdapAuthenticator) Init() error {
 	la.syncPassword = os.Getenv("LDAP_ADMIN_PASSWORD")
 	if la.syncPassword == "" {
-		log.Warn("environment variable 'LDAP_ADMIN_PASSWORD' not set (ldap sync will not work)")
+		cclog.Warn("environment variable 'LDAP_ADMIN_PASSWORD' not set (ldap sync will not work)")
 	}
 
-	lc := config.Keys.LdapConfig
-
-	if lc.UserAttr != "" {
-		la.UserAttr = lc.UserAttr
+	if Keys.LdapConfig.UserAttr != "" {
+		la.UserAttr = Keys.LdapConfig.UserAttr
 	} else {
 		la.UserAttr = "gecos"
 	}
@@ -48,7 +60,7 @@ func (la *LdapAuthenticator) CanLogin(
 	rw http.ResponseWriter,
 	r *http.Request,
 ) (*schema.User, bool) {
-	lc := config.Keys.LdapConfig
+	lc := Keys.LdapConfig
 
 	if user != nil {
 		if user.AuthSource == schema.AuthViaLDAP {
@@ -58,7 +70,8 @@ func (la *LdapAuthenticator) CanLogin(
 		if lc.SyncUserOnLogin {
 			l, err := la.getLdapConnection(true)
 			if err != nil {
-				log.Error("LDAP connection error")
+				cclog.Error("LDAP connection error")
+				return nil, false
 			}
 			defer l.Close()
 
@@ -71,12 +84,12 @@ func (la *LdapAuthenticator) CanLogin(
 
 			sr, err := l.Search(searchRequest)
 			if err != nil {
-				log.Warn(err)
+				cclog.Warn(err)
 				return nil, false
 			}
 
 			if len(sr.Entries) != 1 {
-				log.Warn("LDAP: User does not exist or too many entries returned")
+				cclog.Warn("LDAP: User does not exist or too many entries returned")
 				return nil, false
 			}
 
@@ -96,7 +109,7 @@ func (la *LdapAuthenticator) CanLogin(
 			}
 
 			if err := repository.GetUserRepository().AddUser(user); err != nil {
-				log.Errorf("User '%s' LDAP: Insert into DB failed", username)
+				cclog.Errorf("User '%s' LDAP: Insert into DB failed", username)
 				return nil, false
 			}
 
@@ -114,14 +127,14 @@ func (la *LdapAuthenticator) Login(
 ) (*schema.User, error) {
 	l, err := la.getLdapConnection(false)
 	if err != nil {
-		log.Warn("Error while getting ldap connection")
+		cclog.Warn("Error while getting ldap connection")
 		return nil, err
 	}
 	defer l.Close()
 
-	userDn := strings.Replace(config.Keys.LdapConfig.UserBind, "{username}", user.Username, -1)
+	userDn := strings.ReplaceAll(Keys.LdapConfig.UserBind, "{username}", user.Username)
 	if err := l.Bind(userDn, r.FormValue("password")); err != nil {
-		log.Errorf("AUTH/LDAP > Authentication for user %s failed: %v",
+		cclog.Errorf("AUTH/LDAP > Authentication for user %s failed: %v",
 			user.Username, err)
 		return nil, fmt.Errorf("Authentication failed")
 	}
@@ -130,11 +143,11 @@ func (la *LdapAuthenticator) Login(
 }
 
 func (la *LdapAuthenticator) Sync() error {
-	const IN_DB int = 1
-	const IN_LDAP int = 2
-	const IN_BOTH int = 3
+	const InDB int = 1
+	const InLdap int = 2
+	const InBoth int = 3
 	ur := repository.GetUserRepository()
-	lc := config.Keys.LdapConfig
+	lc := Keys.LdapConfig
 
 	users := map[string]int{}
 	usernames, err := ur.GetLdapUsernames()
@@ -143,12 +156,12 @@ func (la *LdapAuthenticator) Sync() error {
 	}
 
 	for _, username := range usernames {
-		users[username] = IN_DB
+		users[username] = InDB
 	}
 
 	l, err := la.getLdapConnection(true)
 	if err != nil {
-		log.Error("LDAP connection error")
+		cclog.Error("LDAP connection error")
 		return err
 	}
 	defer l.Close()
@@ -159,7 +172,7 @@ func (la *LdapAuthenticator) Sync() error {
 		lc.UserFilter,
 		[]string{"dn", "uid", la.UserAttr}, nil))
 	if err != nil {
-		log.Warn("LDAP search error")
+		cclog.Warn("LDAP search error")
 		return err
 	}
 
@@ -172,18 +185,18 @@ func (la *LdapAuthenticator) Sync() error {
 
 		_, ok := users[username]
 		if !ok {
-			users[username] = IN_LDAP
+			users[username] = InLdap
 			newnames[username] = entry.GetAttributeValue(la.UserAttr)
 		} else {
-			users[username] = IN_BOTH
+			users[username] = InBoth
 		}
 	}
 
 	for username, where := range users {
-		if where == IN_DB && lc.SyncDelOldUsers {
+		if where == InDB && lc.SyncDelOldUsers {
 			ur.DelUser(username)
-			log.Debugf("sync: remove %v (does not show up in LDAP anymore)", username)
-		} else if where == IN_LDAP {
+			cclog.Debugf("sync: remove %v (does not show up in LDAP anymore)", username)
+		} else if where == InLdap {
 			name := newnames[username]
 
 			var roles []string
@@ -198,9 +211,9 @@ func (la *LdapAuthenticator) Sync() error {
 				AuthSource: schema.AuthViaLDAP,
 			}
 
-			log.Debugf("sync: add %v (name: %v, roles: [user], ldap: true)", username, name)
+			cclog.Debugf("sync: add %v (name: %v, roles: [user], ldap: true)", username, name)
 			if err := ur.AddUser(user); err != nil {
-				log.Errorf("User '%s' LDAP: Insert into DB failed", username)
+				cclog.Errorf("User '%s' LDAP: Insert into DB failed", username)
 				return err
 			}
 		}
@@ -210,17 +223,17 @@ func (la *LdapAuthenticator) Sync() error {
 }
 
 func (la *LdapAuthenticator) getLdapConnection(admin bool) (*ldap.Conn, error) {
-	lc := config.Keys.LdapConfig
-	conn, err := ldap.DialURL(lc.Url)
+	lc := Keys.LdapConfig
+	conn, err := ldap.DialURL(lc.URL)
 	if err != nil {
-		log.Warn("LDAP URL dial failed")
+		cclog.Warn("LDAP URL dial failed")
 		return nil, err
 	}
 
 	if admin {
 		if err := conn.Bind(lc.SearchDN, la.syncPassword); err != nil {
 			conn.Close()
-			log.Warn("LDAP connection bind failed")
+			cclog.Warn("LDAP connection bind failed")
 			return nil, err
 		}
 	}

internal/auth/local.go

@@ -1,15 +1,16 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package auth
 
 import (
 	"fmt"
 	"net/http"
 
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	"golang.org/x/crypto/bcrypt"
 )
 
@@ -27,19 +28,19 @@ func (la *LocalAuthenticator) CanLogin(
 	user *schema.User,
 	username string,
 	rw http.ResponseWriter,
-	r *http.Request) (*schema.User, bool) {
-
+	r *http.Request,
+) (*schema.User, bool) {
 	return user, user != nil && user.AuthSource == schema.AuthViaLocalPassword
 }
 
 func (la *LocalAuthenticator) Login(
 	user *schema.User,
 	rw http.ResponseWriter,
-	r *http.Request) (*schema.User, error) {
-
+	r *http.Request,
+) (*schema.User, error) {
 	if e := bcrypt.CompareHashAndPassword([]byte(user.Password),
 		[]byte(r.FormValue("password"))); e != nil {
-		log.Errorf("AUTH/LOCAL > Authentication for user %s failed!", user.Username)
+		cclog.Errorf("AUTH/LOCAL > Authentication for user %s failed!", user.Username)
 		return nil, fmt.Errorf("Authentication failed")
 	}
 

internal/auth/oidc.go

@@ -1,7 +1,8 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package auth
 
 import (
@@ -13,15 +14,20 @@ import (
 	"os"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	"github.com/coreos/go-oidc/v3/oidc"
 	"github.com/gorilla/mux"
 	"golang.org/x/oauth2"
 )
 
+type OpenIDConfig struct {
+	Provider          string `json:"provider"`
+	SyncUserOnLogin   bool   `json:"syncUserOnLogin"`
+	UpdateUserOnLogin bool   `json:"updateUserOnLogin"`
+}
+
 type OIDC struct {
 	client         *oauth2.Config
 	provider       *oidc.Provider
@@ -48,18 +54,23 @@ func setCallbackCookie(w http.ResponseWriter, r *http.Request, name, value strin
 	http.SetCookie(w, c)
 }
 
+// NewOIDC creates a new OIDC authenticator with the configured provider
 func NewOIDC(a *Authentication) *OIDC {
-	provider, err := oidc.NewProvider(context.Background(), config.Keys.OpenIDConfig.Provider)
+	// Use context with timeout for provider initialization
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+	
+	provider, err := oidc.NewProvider(ctx, Keys.OpenIDConfig.Provider)
 	if err != nil {
-		log.Fatal(err)
+		cclog.Fatal(err)
 	}
 	clientID := os.Getenv("OID_CLIENT_ID")
 	if clientID == "" {
-		log.Warn("environment variable 'OID_CLIENT_ID' not set (Open ID connect auth will not work)")
+		cclog.Warn("environment variable 'OID_CLIENT_ID' not set (Open ID connect auth will not work)")
 	}
 	clientSecret := os.Getenv("OID_CLIENT_SECRET")
 	if clientSecret == "" {
-		log.Warn("environment variable 'OID_CLIENT_SECRET' not set (Open ID connect auth will not work)")
+		cclog.Warn("environment variable 'OID_CLIENT_SECRET' not set (Open ID connect auth will not work)")
 	}
 
 	client := &oauth2.Config{
@@ -105,13 +116,18 @@ func (oa *OIDC) OAuth2Callback(rw http.ResponseWriter, r *http.Request) {
 		http.Error(rw, "Code not found", http.StatusBadRequest)
 		return
 	}
-	token, err := oa.client.Exchange(context.Background(), code, oauth2.VerifierOption(codeVerifier))
+	// Exchange authorization code for token with timeout
+	ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
+	defer cancel()
+	
+	token, err := oa.client.Exchange(ctx, code, oauth2.VerifierOption(codeVerifier))
 	if err != nil {
 		http.Error(rw, "Failed to exchange token: "+err.Error(), http.StatusInternalServerError)
 		return
 	}
 
-	userInfo, err := oa.provider.UserInfo(context.Background(), oauth2.StaticTokenSource(token))
+	// Get user info from OIDC provider with same timeout
+	userInfo, err := oa.provider.UserInfo(ctx, oauth2.StaticTokenSource(token))
 	if err != nil {
 		http.Error(rw, "Failed to get userinfo: "+err.Error(), http.StatusInternalServerError)
 		return
@@ -168,14 +184,14 @@ func (oa *OIDC) OAuth2Callback(rw http.ResponseWriter, r *http.Request) {
 		AuthSource: schema.AuthViaOIDC,
 	}
 
-	if config.Keys.OpenIDConfig.SyncUserOnLogin || config.Keys.OpenIDConfig.UpdateUserOnLogin {
+	if Keys.OpenIDConfig.SyncUserOnLogin || Keys.OpenIDConfig.UpdateUserOnLogin {
 		handleOIDCUser(user)
 	}
 
 	oa.authentication.SaveSession(rw, r, user)
-	log.Infof("login successfull: user: %#v (roles: %v, projects: %v)", user.Username, user.Roles, user.Projects)
-	ctx := context.WithValue(r.Context(), repository.ContextUserKey, user)
-	http.RedirectHandler("/", http.StatusTemporaryRedirect).ServeHTTP(rw, r.WithContext(ctx))
+	cclog.Infof("login successfull: user: %#v (roles: %v, projects: %v)", user.Username, user.Roles, user.Projects)
+	userCtx := context.WithValue(r.Context(), repository.ContextUserKey, user)
+	http.RedirectHandler("/", http.StatusTemporaryRedirect).ServeHTTP(rw, r.WithContext(userCtx))
 }
 
 func (oa *OIDC) OAuth2Login(rw http.ResponseWriter, r *http.Request) {

internal/auth/schema.go

@@ -0,0 +1,96 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package auth
+
+var configSchema = `
+	{
+    "jwts": {
+      "description": "For JWT token authentication.",
+      "type": "object",
+      "properties": {
+        "max-age": {
+          "description": "Configure how long a token is valid. As string parsable by time.ParseDuration()",
+          "type": "string"
+        },
+        "cookieName": {
+          "description": "Cookie that should be checked for a JWT token.",
+          "type": "string"
+        },
+        "validateUser": {
+          "description": "Deny login for users not in database (but defined in JWT). Overwrite roles in JWT with database roles.",
+          "type": "boolean"
+        },
+        "trustedIssuer": {
+          "description": "Issuer that should be accepted when validating external JWTs ",
+          "type": "string"
+        },
+        "syncUserOnLogin": {
+          "description": "Add non-existent user to DB at login attempt with values provided in JWT.",
+          "type": "boolean"
+        }
+      },
+      "required": ["max-age"]
+    },
+    "oidc": {
+      "provider": {
+        "description": "",
+        "type": "string"
+      },
+      "syncUserOnLogin": {
+        "description": "",
+        "type": "boolean"
+      },
+      "updateUserOnLogin": {
+        "description": "",
+        "type": "boolean"
+      },
+      "required": ["provider"]
+    },
+    "ldap": {
+      "description": "For LDAP Authentication and user synchronisation.",
+      "type": "object",
+      "properties": {
+        "url": {
+          "description": "URL of LDAP directory server.",
+          "type": "string"
+        },
+        "user_base": {
+          "description": "Base DN of user tree root.",
+          "type": "string"
+        },
+        "search_dn": {
+          "description": "DN for authenticating LDAP admin account with general read rights.",
+          "type": "string"
+        },
+        "user_bind": {
+          "description": "Expression used to authenticate users via LDAP bind. Must contain uid={username}.",
+          "type": "string"
+        },
+        "user_filter": {
+          "description": "Filter to extract users for syncing.",
+          "type": "string"
+        },
+        "username_attr": {
+          "description": "Attribute with full username. Default: gecos",
+          "type": "string"
+        },
+        "sync_interval": {
+          "description": "Interval used for syncing local user table with LDAP directory. Parsed using time.ParseDuration.",
+          "type": "string"
+        },
+        "sync_del_old_users": {
+          "description": "Delete obsolete users in database.",
+          "type": "boolean"
+        },
+        "syncUserOnLogin": {
+          "description": "Add non-existent user to DB at login attempt if user exists in Ldap directory",
+          "type": "boolean"
+        }
+      },
+      "required": ["url", "user_base", "search_dn", "user_bind", "user_filter"]
+    },
+  "required": ["jwts"]
+	}`

internal/config/config.go

@@ -1,72 +1,158 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// Package config implements the program configuration data structures, validation and parsing
 package config
 
 import (
 	"bytes"
 	"encoding/json"
-	"log"
-	"os"
+	"time"
 
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/resampler"
 )
 
-var Keys schema.ProgramConfig = schema.ProgramConfig{
+type ProgramConfig struct {
+	// Address where the http (or https) server will listen on (for example: 'localhost:80').
+	Addr string `json:"addr"`
+
+	// Addresses from which secured admin API endpoints can be reached, can be wildcard "*"
+	APIAllowedIPs []string `json:"apiAllowedIPs"`
+
+	APISubjects *NATSConfig `json:"apiSubjects"`
+
+	// Drop root permissions once .env was read and the port was taken.
+	User  string `json:"user"`
+	Group string `json:"group"`
+
+	// Disable authentication (for everything: API, Web-UI, ...)
+	DisableAuthentication bool `json:"disable-authentication"`
+
+	// If `embed-static-files` is true (default), the frontend files are directly
+	// embeded into the go binary and expected to be in web/frontend. Only if
+	// it is false the files in `static-files` are served instead.
+	EmbedStaticFiles bool   `json:"embed-static-files"`
+	StaticFiles      string `json:"static-files"`
+
+	// 'sqlite3' or 'mysql' (mysql will work for mariadb as well)
+	DBDriver string `json:"db-driver"`
+
+	// For sqlite3 a filename, for mysql a DSN in this format: https://github.com/go-sql-driver/mysql#dsn-data-source-name (Without query parameters!).
+	DB string `json:"db"`
+
+	// Keep all metric data in the metric data repositories,
+	// do not write to the job-archive.
+	DisableArchive bool `json:"disable-archive"`
+
+	EnableJobTaggers bool `json:"enable-job-taggers"`
+
+	// Validate json input against schema
+	Validate bool `json:"validate"`
+
+	// If 0 or empty, the session does not expire!
+	SessionMaxAge string `json:"session-max-age"`
+
+	// If both those options are not empty, use HTTPS using those certificates.
+	HTTPSCertFile string `json:"https-cert-file"`
+	HTTPSKeyFile  string `json:"https-key-file"`
+
+	// If not the empty string and `addr` does not end in ":80",
+	// redirect every request incoming at port 80 to that url.
+	RedirectHTTPTo string `json:"redirect-http-to"`
+
+	// Where to store MachineState files
+	MachineStateDir string `json:"machine-state-dir"`
+
+	// If not zero, automatically mark jobs as stopped running X seconds longer than their walltime.
+	StopJobsExceedingWalltime int `json:"stop-jobs-exceeding-walltime"`
+
+	// Defines time X in seconds in which jobs are considered to be "short" and will be filtered in specific views.
+	ShortRunningJobsDuration int `json:"short-running-jobs-duration"`
+
+	// Energy Mix CO2 Emission Constant [g/kWh]
+	// If entered, displays estimated CO2 emission for job based on jobs totalEnergy
+	EmissionConstant int `json:"emission-constant"`
+
+	// If exists, will enable dynamic zoom in frontend metric plots using the configured values
+	EnableResampling *ResampleConfig `json:"resampling"`
+}
+
+type ResampleConfig struct {
+	// Minimum number of points to trigger resampling of data
+	MinimumPoints int `json:"minimumPoints"`
+	// Array of resampling target resolutions, in seconds; Example: [600,300,60]
+	Resolutions []int `json:"resolutions"`
+	// Trigger next zoom level at less than this many visible datapoints
+	Trigger int `json:"trigger"`
+}
+
+type NATSConfig struct {
+	SubjectJobStart  string `json:"subjectJobStart"`
+	SubjectJobStop   string `json:"subjectJobStop"`
+	SubjectNodeState string `json:"subjectNodeState"`
+}
+
+type IntRange struct {
+	From int `json:"from"`
+	To   int `json:"to"`
+}
+
+type TimeRange struct {
+	From  *time.Time `json:"from"`
+	To    *time.Time `json:"to"`
+	Range string     `json:"range,omitempty"`
+}
+
+type FilterRanges struct {
+	Duration  *IntRange  `json:"duration"`
+	NumNodes  *IntRange  `json:"numNodes"`
+	StartTime *TimeRange `json:"startTime"`
+}
+
+type ClusterConfig struct {
+	Name                 string          `json:"name"`
+	FilterRanges         *FilterRanges   `json:"filterRanges"`
+	MetricDataRepository json.RawMessage `json:"metricDataRepository"`
+}
+
+var Clusters []*ClusterConfig
+
+var Keys ProgramConfig = ProgramConfig{
 	Addr:                      "localhost:8080",
 	DisableAuthentication:     false,
 	EmbedStaticFiles:          true,
 	DBDriver:                  "sqlite3",
 	DB:                        "./var/job.db",
-	Archive:                   json.RawMessage(`{\"kind\":\"file\",\"path\":\"./var/job-archive\"}`),
 	DisableArchive:            false,
 	Validate:                  false,
 	SessionMaxAge:             "168h",
 	StopJobsExceedingWalltime: 0,
 	ShortRunningJobsDuration:  5 * 60,
-	UiDefaults: map[string]interface{}{
-		"analysis_view_histogramMetrics":         []string{"flops_any", "mem_bw", "mem_used"},
-		"analysis_view_scatterPlotMetrics":       [][]string{{"flops_any", "mem_bw"}, {"flops_any", "cpu_load"}, {"cpu_load", "mem_bw"}},
-		"job_view_nodestats_selectedMetrics":     []string{"flops_any", "mem_bw", "mem_used"},
-		"job_view_selectedMetrics":               []string{"flops_any", "mem_bw", "mem_used"},
-		"job_view_showFootprint":                 true,
-		"job_list_usePaging":                     false,
-		"plot_general_colorBackground":           true,
-		"plot_general_colorscheme":               []string{"#00bfff", "#0000ff", "#ff00ff", "#ff0000", "#ff8000", "#ffff00", "#80ff00"},
-		"plot_general_lineWidth":                 3,
-		"plot_list_jobsPerPage":                  50,
-		"plot_list_selectedMetrics":              []string{"cpu_load", "mem_used", "flops_any", "mem_bw"},
-		"plot_view_plotsPerRow":                  3,
-		"plot_view_showPolarplot":                true,
-		"plot_view_showRoofline":                 true,
-		"plot_view_showStatTable":                true,
-		"system_view_selectedMetric":             "cpu_load",
-		"analysis_view_selectedTopEntity":        "user",
-		"analysis_view_selectedTopCategory":      "totalWalltime",
-		"status_view_selectedTopUserCategory":    "totalJobs",
-		"status_view_selectedTopProjectCategory": "totalJobs",
-	},
 }
 
-func Init(flagConfigFile string) {
-	raw, err := os.ReadFile(flagConfigFile)
-	if err != nil {
-		if !os.IsNotExist(err) {
-			log.Fatalf("CONFIG ERROR: %v", err)
-		}
-	} else {
-		if err := schema.Validate(schema.Config, bytes.NewReader(raw)); err != nil {
-			log.Fatalf("Validate config: %v\n", err)
-		}
-		dec := json.NewDecoder(bytes.NewReader(raw))
-		dec.DisallowUnknownFields()
-		if err := dec.Decode(&Keys); err != nil {
-			log.Fatalf("could not decode: %v", err)
-		}
+func Init(mainConfig json.RawMessage, clusterConfig json.RawMessage) {
+	Validate(configSchema, mainConfig)
+	dec := json.NewDecoder(bytes.NewReader(mainConfig))
+	dec.DisallowUnknownFields()
+	if err := dec.Decode(&Keys); err != nil {
+		cclog.Abortf("Config Init: Could not decode config file '%s'.\nError: %s\n", mainConfig, err.Error())
+	}
 
-		if Keys.Clusters == nil || len(Keys.Clusters) < 1 {
-			log.Fatal("At least one cluster required in config!")
-		}
+	Validate(clustersSchema, clusterConfig)
+	dec = json.NewDecoder(bytes.NewReader(clusterConfig))
+	dec.DisallowUnknownFields()
+	if err := dec.Decode(&Clusters); err != nil {
+		cclog.Abortf("Config Init: Could not decode config file '%s'.\nError: %s\n", mainConfig, err.Error())
+	}
+
+	if len(Clusters) < 1 {
+		cclog.Abort("Config Init: At least one cluster required in config. Exited with error.")
+	}
+
+	if Keys.EnableResampling != nil && Keys.EnableResampling.MinimumPoints > 0 {
+		resampler.SetMinimumRequiredPoints(Keys.EnableResampling.MinimumPoints)
 	}
 }

internal/config/config_test.go

@@ -1,16 +1,30 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package config
 
 import (
 	"testing"
+
+	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 )
 
 func TestInit(t *testing.T) {
 	fp := "../../configs/config.json"
-	Init(fp)
+	ccconf.Init(fp)
+	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
+		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
+			Init(cfg, clustercfg)
+		} else {
+			cclog.Abort("Cluster configuration must be present")
+		}
+	} else {
+		cclog.Abort("Main configuration must be present")
+	}
+
 	if Keys.Addr != "0.0.0.0:443" {
 		t.Errorf("wrong addr\ngot: %s \nwant: 0.0.0.0:443", Keys.Addr)
 	}
@@ -18,7 +32,17 @@ func TestInit(t *testing.T) {
 
 func TestInitMinimal(t *testing.T) {
 	fp := "../../configs/config-demo.json"
-	Init(fp)
+	ccconf.Init(fp)
+	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
+		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
+			Init(cfg, clustercfg)
+		} else {
+			cclog.Abort("Cluster configuration must be present")
+		}
+	} else {
+		cclog.Abort("Main configuration must be present")
+	}
+
 	if Keys.Addr != "127.0.0.1:8080" {
 		t.Errorf("wrong addr\ngot: %s \nwant: 127.0.0.1:8080", Keys.Addr)
 	}

internal/config/default_metrics.go

@@ -1,3 +1,8 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
 package config
 
 import (
@@ -6,6 +11,8 @@ import (
 	"strings"
 )
 
+// DEPRECATED: SUPERSEDED BY NEW USER CONFIG - userConfig.go / web.go
+
 type DefaultMetricsCluster struct {
 	Name           string `json:"name"`
 	DefaultMetrics string `json:"default_metrics"`

internal/config/schema.go

@@ -0,0 +1,205 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package config
+
+var configSchema = `
+	{
+  "type": "object",
+  "properties": {
+    "addr": {
+      "description": "Address where the http (or https) server will listen on (for example: 'localhost:80').",
+      "type": "string"
+    },
+    "apiAllowedIPs": {
+      "description": "Addresses from which secured API endpoints can be reached",
+      "type": "array",
+      "items": {
+        "type": "string"
+      }
+    },
+    "user": {
+      "description": "Drop root permissions once .env was read and the port was taken. Only applicable if using privileged port.",
+      "type": "string"
+    },
+    "group": {
+      "description": "Drop root permissions once .env was read and the port was taken. Only applicable if using privileged port.",
+      "type": "string"
+    },
+    "disable-authentication": {
+      "description": "Disable authentication (for everything: API, Web-UI, ...).",
+      "type": "boolean"
+    },
+    "embed-static-files": {
+      "description": "If all files in web/frontend/public should be served from within the binary itself (they are embedded) or not.",
+      "type": "boolean"
+    },
+    "static-files": {
+      "description": "Folder where static assets can be found, if embed-static-files is false.",
+      "type": "string"
+    },
+    "db": {
+      "description": "For sqlite3 a filename, for mysql a DSN in this format: https://github.com/go-sql-driver/mysql#dsn-data-source-name (Without query parameters!).",
+      "type": "string"
+    },
+    "disable-archive": {
+      "description": "Keep all metric data in the metric data repositories, do not write to the job-archive.",
+      "type": "boolean"
+    },
+    "enable-job-taggers": {
+      "description": "Turn on automatic application and jobclass taggers",
+      "type": "boolean"
+    },
+    "validate": {
+      "description": "Validate all input json documents against json schema.",
+      "type": "boolean"
+    },
+    "session-max-age": {
+      "description": "Specifies for how long a session shall be valid  as a string parsable by time.ParseDuration(). If 0 or empty, the session/token does not expire!",
+      "type": "string"
+    },
+    "https-cert-file": {
+      "description": "Filepath to SSL certificate. If also https-key-file is set use HTTPS using those certificates.",
+      "type": "string"
+    },
+    "https-key-file": {
+      "description": "Filepath to SSL key file. If also https-cert-file is set use HTTPS using those certificates.",
+      "type": "string"
+    },
+    "redirect-http-to": {
+      "description": "If not the empty string and addr does not end in :80, redirect every request incoming at port 80 to that url.",
+      "type": "string"
+    },
+    "stop-jobs-exceeding-walltime": {
+      "description": "If not zero, automatically mark jobs as stopped running X seconds longer than their walltime. Only applies if walltime is set for job.",
+      "type": "integer"
+    },
+    "short-running-jobs-duration": {
+      "description": "Do not show running jobs shorter than X seconds.",
+      "type": "integer"
+    },
+    "emission-constant": {
+      "description": ".",
+      "type": "integer"
+    },
+    "cron-frequency": {
+      "description": "Frequency of cron job workers.",
+      "type": "object",
+      "properties": {
+        "duration-worker": {
+          "description": "Duration Update Worker [Defaults to '5m']",
+          "type": "string"
+        },
+        "footprint-worker": {
+          "description": "Metric-Footprint Update Worker [Defaults to '10m']",
+          "type": "string"
+        }
+      }
+    },
+    "enable-resampling": {
+      "description": "Enable dynamic zoom in frontend metric plots.",
+      "type": "object",
+      "properties": {
+        "minimumPoints": {
+          "description": "Minimum points to trigger resampling of time-series data.",
+          "type": "integer"
+        },
+        "trigger": {
+          "description": "Trigger next zoom level at less than this many visible datapoints.",
+          "type": "integer"
+        },
+        "resolutions": {
+          "description": "Array of resampling target resolutions, in seconds.",
+          "type": "array",
+          "items": {
+            "type": "integer"
+          }
+        }
+      },
+      "required": ["trigger", "resolutions"]
+    }
+	},
+  "required": ["apiAllowedIPs"]
+	}`
+
+var clustersSchema = `
+  {
+    "type": "array",
+    "items": {
+      "type": "object",
+      "properties": {
+        "name": {
+          "description": "The name of the cluster.",
+          "type": "string"
+        },
+        "metricDataRepository": {
+          "description": "Type of the metric data repository for this cluster",
+          "type": "object",
+          "properties": {
+            "kind": {
+              "type": "string",
+                "enum": ["influxdb", "prometheus", "cc-metric-store", "cc-metric-store-internal", "test"]
+            },
+            "url": {
+              "type": "string"
+            },
+            "token": {
+              "type": "string"
+            }
+          },
+          "required": ["kind"]
+        },
+        "filterRanges": {
+          "description": "This option controls the slider ranges for the UI controls of numNodes, duration, and startTime.",
+          "type": "object",
+          "properties": {
+            "numNodes": {
+              "description": "UI slider range for number of nodes",
+              "type": "object",
+              "properties": {
+                "from": {
+                  "type": "integer"
+                },
+                "to": {
+                  "type": "integer"
+                }
+              },
+              "required": ["from", "to"]
+            },
+            "duration": {
+              "description": "UI slider range for duration",
+              "type": "object",
+              "properties": {
+                "from": {
+                  "type": "integer"
+                },
+                "to": {
+                  "type": "integer"
+                }
+              },
+              "required": ["from", "to"]
+            },
+            "startTime": {
+              "description": "UI slider range for start time",
+              "type": "object",
+              "properties": {
+                "from": {
+                  "type": "string",
+                  "format": "date-time"
+                },
+                "to": {
+                  "type": "null"
+                }
+              },
+              "required": ["from", "to"]
+            }
+          },
+          "required": ["numNodes", "duration", "startTime"]
+        }
+      },
+      "required": ["name", "metricDataRepository", "filterRanges"],
+      "minItems": 1
+    }
+  }`

internal/config/validate.go

@@ -0,0 +1,29 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package config
+
+import (
+	"encoding/json"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/santhosh-tekuri/jsonschema/v5"
+)
+
+func Validate(schema string, instance json.RawMessage) {
+	sch, err := jsonschema.CompileString("schema.json", schema)
+	if err != nil {
+		cclog.Fatalf("%#v", err)
+	}
+
+	var v any
+	if err := json.Unmarshal([]byte(instance), &v); err != nil {
+		cclog.Fatal(err)
+	}
+
+	if err = sch.Validate(v); err != nil {
+		cclog.Fatalf("%#v", err)
+	}
+}

internal/graph/model/models.go

@@ -1,5 +1,6 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package model

internal/graph/model/models_gen.go

@@ -3,14 +3,28 @@
 package model
 
 import (
+	"bytes"
 	"fmt"
 	"io"
 	"strconv"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	"github.com/ClusterCockpit/cc-backend/internal/config"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
+type ClusterMetricWithName struct {
+	Name     string         `json:"name"`
+	Unit     *schema.Unit   `json:"unit,omitempty"`
+	Timestep int            `json:"timestep"`
+	Data     []schema.Float `json:"data"`
+}
+
+type ClusterMetrics struct {
+	NodeCount int                      `json:"nodeCount"`
+	Metrics   []*ClusterMetricWithName `json:"metrics"`
+}
+
 type Count struct {
 	Name  string `json:"name"`
 	Count int    `json:"count"`
@@ -50,6 +64,7 @@ type IntRangeOutput struct {
 
 type JobFilter struct {
 	Tags            []string          `json:"tags,omitempty"`
+	DbID            []string          `json:"dbId,omitempty"`
 	JobID           *StringInput      `json:"jobId,omitempty"`
 	ArrayJobID      *int              `json:"arrayJobId,omitempty"`
 	User            *StringInput      `json:"user,omitempty"`
@@ -57,16 +72,16 @@ type JobFilter struct {
 	JobName         *StringInput      `json:"jobName,omitempty"`
 	Cluster         *StringInput      `json:"cluster,omitempty"`
 	Partition       *StringInput      `json:"partition,omitempty"`
-	Duration        *schema.IntRange  `json:"duration,omitempty"`
+	Duration        *config.IntRange  `json:"duration,omitempty"`
 	Energy          *FloatRange       `json:"energy,omitempty"`
 	MinRunningFor   *int              `json:"minRunningFor,omitempty"`
-	NumNodes        *schema.IntRange  `json:"numNodes,omitempty"`
-	NumAccelerators *schema.IntRange  `json:"numAccelerators,omitempty"`
-	NumHWThreads    *schema.IntRange  `json:"numHWThreads,omitempty"`
-	StartTime       *schema.TimeRange `json:"startTime,omitempty"`
+	NumNodes        *config.IntRange  `json:"numNodes,omitempty"`
+	NumAccelerators *config.IntRange  `json:"numAccelerators,omitempty"`
+	NumHWThreads    *config.IntRange  `json:"numHWThreads,omitempty"`
+	StartTime       *config.TimeRange `json:"startTime,omitempty"`
 	State           []schema.JobState `json:"state,omitempty"`
 	MetricStats     []*MetricStatItem `json:"metricStats,omitempty"`
-	Exclusive       *int              `json:"exclusive,omitempty"`
+	Shared          *string           `json:"shared,omitempty"`
 	Node            *StringInput      `json:"node,omitempty"`
 }
 
@@ -81,11 +96,6 @@ type JobLinkResultList struct {
 	Count     *int       `json:"count,omitempty"`
 }
 
-type JobMetricStatWithName struct {
-	Name  string                   `json:"name"`
-	Stats *schema.MetricStatistics `json:"stats"`
-}
-
 type JobMetricWithName struct {
 	Name   string             `json:"name"`
 	Scope  schema.MetricScope `json:"scope"`
@@ -100,9 +110,23 @@ type JobResultList struct {
 	HasNextPage *bool         `json:"hasNextPage,omitempty"`
 }
 
+type JobStats struct {
+	ID              int           `json:"id"`
+	JobID           string        `json:"jobId"`
+	StartTime       int           `json:"startTime"`
+	Duration        int           `json:"duration"`
+	Cluster         string        `json:"cluster"`
+	SubCluster      string        `json:"subCluster"`
+	NumNodes        int           `json:"numNodes"`
+	NumHWThreads    *int          `json:"numHWThreads,omitempty"`
+	NumAccelerators *int          `json:"numAccelerators,omitempty"`
+	Stats           []*NamedStats `json:"stats"`
+}
+
 type JobsStatistics struct {
 	ID             string               `json:"id"`
 	Name           string               `json:"name"`
+	TotalUsers     int                  `json:"totalUsers"`
 	TotalJobs      int                  `json:"totalJobs"`
 	RunningJobs    int                  `json:"runningJobs"`
 	ShortJobs      int                  `json:"shortJobs"`
@@ -147,12 +171,49 @@ type MetricStatItem struct {
 type Mutation struct {
 }
 
+type NamedStats struct {
+	Name string                   `json:"name"`
+	Data *schema.MetricStatistics `json:"data"`
+}
+
+type NamedStatsWithScope struct {
+	Name  string             `json:"name"`
+	Scope schema.MetricScope `json:"scope"`
+	Stats []*ScopedStats     `json:"stats"`
+}
+
+type NodeFilter struct {
+	Hostname       *StringInput           `json:"hostname,omitempty"`
+	Cluster        *StringInput           `json:"cluster,omitempty"`
+	Subcluster     *StringInput           `json:"subcluster,omitempty"`
+	SchedulerState *schema.SchedulerState `json:"schedulerState,omitempty"`
+	HealthState    *string                `json:"healthState,omitempty"`
+	TimeStart      *int                   `json:"timeStart,omitempty"`
+}
+
 type NodeMetrics struct {
 	Host       string               `json:"host"`
+	State      string               `json:"state"`
 	SubCluster string               `json:"subCluster"`
 	Metrics    []*JobMetricWithName `json:"metrics"`
 }
 
+type NodeStateResultList struct {
+	Items []*schema.Node `json:"items"`
+	Count *int           `json:"count,omitempty"`
+}
+
+type NodeStates struct {
+	State string `json:"state"`
+	Count int    `json:"count"`
+}
+
+type NodeStatesTimed struct {
+	State  string `json:"state"`
+	Counts []int  `json:"counts"`
+	Times  []int  `json:"times"`
+}
+
 type NodesResultList struct {
 	Items       []*NodeMetrics `json:"items"`
 	Offset      *int           `json:"offset,omitempty"`
@@ -173,6 +234,12 @@ type PageRequest struct {
 	Page         int `json:"page"`
 }
 
+type ScopedStats struct {
+	Hostname string                   `json:"hostname"`
+	ID       *string                  `json:"id,omitempty"`
+	Data     *schema.MetricStatistics `json:"data"`
+}
+
 type StringInput struct {
 	Eq         *string  `json:"eq,omitempty"`
 	Neq        *string  `json:"neq,omitempty"`
@@ -203,20 +270,22 @@ type User struct {
 type Aggregate string
 
 const (
-	AggregateUser    Aggregate = "USER"
-	AggregateProject Aggregate = "PROJECT"
-	AggregateCluster Aggregate = "CLUSTER"
+	AggregateUser       Aggregate = "USER"
+	AggregateProject    Aggregate = "PROJECT"
+	AggregateCluster    Aggregate = "CLUSTER"
+	AggregateSubcluster Aggregate = "SUBCLUSTER"
 )
 
 var AllAggregate = []Aggregate{
 	AggregateUser,
 	AggregateProject,
 	AggregateCluster,
+	AggregateSubcluster,
 }
 
 func (e Aggregate) IsValid() bool {
 	switch e {
-	case AggregateUser, AggregateProject, AggregateCluster:
+	case AggregateUser, AggregateProject, AggregateCluster, AggregateSubcluster:
 		return true
 	}
 	return false
@@ -243,11 +312,26 @@ func (e Aggregate) MarshalGQL(w io.Writer) {
 	fmt.Fprint(w, strconv.Quote(e.String()))
 }
 
+func (e *Aggregate) UnmarshalJSON(b []byte) error {
+	s, err := strconv.Unquote(string(b))
+	if err != nil {
+		return err
+	}
+	return e.UnmarshalGQL(s)
+}
+
+func (e Aggregate) MarshalJSON() ([]byte, error) {
+	var buf bytes.Buffer
+	e.MarshalGQL(&buf)
+	return buf.Bytes(), nil
+}
+
 type SortByAggregate string
 
 const (
 	SortByAggregateTotalwalltime  SortByAggregate = "TOTALWALLTIME"
 	SortByAggregateTotaljobs      SortByAggregate = "TOTALJOBS"
+	SortByAggregateTotalusers     SortByAggregate = "TOTALUSERS"
 	SortByAggregateTotalnodes     SortByAggregate = "TOTALNODES"
 	SortByAggregateTotalnodehours SortByAggregate = "TOTALNODEHOURS"
 	SortByAggregateTotalcores     SortByAggregate = "TOTALCORES"
@@ -259,6 +343,7 @@ const (
 var AllSortByAggregate = []SortByAggregate{
 	SortByAggregateTotalwalltime,
 	SortByAggregateTotaljobs,
+	SortByAggregateTotalusers,
 	SortByAggregateTotalnodes,
 	SortByAggregateTotalnodehours,
 	SortByAggregateTotalcores,
@@ -269,7 +354,7 @@ var AllSortByAggregate = []SortByAggregate{
 
 func (e SortByAggregate) IsValid() bool {
 	switch e {
-	case SortByAggregateTotalwalltime, SortByAggregateTotaljobs, SortByAggregateTotalnodes, SortByAggregateTotalnodehours, SortByAggregateTotalcores, SortByAggregateTotalcorehours, SortByAggregateTotalaccs, SortByAggregateTotalacchours:
+	case SortByAggregateTotalwalltime, SortByAggregateTotaljobs, SortByAggregateTotalusers, SortByAggregateTotalnodes, SortByAggregateTotalnodehours, SortByAggregateTotalcores, SortByAggregateTotalcorehours, SortByAggregateTotalaccs, SortByAggregateTotalacchours:
 		return true
 	}
 	return false
@@ -296,6 +381,20 @@ func (e SortByAggregate) MarshalGQL(w io.Writer) {
 	fmt.Fprint(w, strconv.Quote(e.String()))
 }
 
+func (e *SortByAggregate) UnmarshalJSON(b []byte) error {
+	s, err := strconv.Unquote(string(b))
+	if err != nil {
+		return err
+	}
+	return e.UnmarshalGQL(s)
+}
+
+func (e SortByAggregate) MarshalJSON() ([]byte, error) {
+	var buf bytes.Buffer
+	e.MarshalGQL(&buf)
+	return buf.Bytes(), nil
+}
+
 type SortDirectionEnum string
 
 const (
@@ -336,3 +435,17 @@ func (e *SortDirectionEnum) UnmarshalGQL(v any) error {
 func (e SortDirectionEnum) MarshalGQL(w io.Writer) {
 	fmt.Fprint(w, strconv.Quote(e.String()))
 }
+
+func (e *SortDirectionEnum) UnmarshalJSON(b []byte) error {
+	s, err := strconv.Unquote(string(b))
+	if err != nil {
+		return err
+	}
+	return e.UnmarshalGQL(s)
+}
+
+func (e SortDirectionEnum) MarshalJSON() ([]byte, error) {
+	var buf bytes.Buffer
+	e.MarshalGQL(&buf)
+	return buf.Bytes(), nil
+}

internal/graph/resolver.go

@@ -4,7 +4,7 @@ import (
 	"sync"
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 	"github.com/jmoiron/sqlx"
 )
 
@@ -32,7 +32,7 @@ func Init() {
 
 func GetResolverInstance() *Resolver {
 	if resolverInstance == nil {
-		log.Fatal("Authentication module not initialized!")
+		cclog.Fatal("Authentication module not initialized!")
 	}
 
 	return resolverInstance

internal/graph/schema.resolvers.go

@@ -1,13 +1,15 @@
 package graph
 
-// This file will be automatically regenerated based on the schema, any resolver implementations
+// This file will be automatically regenerated based on the schema, any resolver
+// implementations
 // will be copied through when generating and any unknown code will be moved to the end.
-// Code generated by github.com/99designs/gqlgen version v0.17.66
+// Code generated by github.com/99designs/gqlgen version v0.17.84
 
 import (
 	"context"
 	"errors"
 	"fmt"
+	"math"
 	"regexp"
 	"slices"
 	"strconv"
@@ -20,8 +22,8 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
 // Partitions is the resolver for the partitions field.
@@ -29,15 +31,21 @@ func (r *clusterResolver) Partitions(ctx context.Context, obj *schema.Cluster) (
 	return r.Repo.Partitions(obj.Name)
 }
 
+// StartTime is the resolver for the startTime field.
+func (r *jobResolver) StartTime(ctx context.Context, obj *schema.Job) (*time.Time, error) {
+	timestamp := time.Unix(obj.StartTime, 0)
+	return &timestamp, nil
+}
+
 // Tags is the resolver for the tags field.
 func (r *jobResolver) Tags(ctx context.Context, obj *schema.Job) ([]*schema.Tag, error) {
-	return r.Repo.GetTags(repository.GetUserFromContext(ctx), &obj.ID)
+	return r.Repo.GetTags(repository.GetUserFromContext(ctx), obj.ID)
 }
 
 // ConcurrentJobs is the resolver for the concurrentJobs field.
 func (r *jobResolver) ConcurrentJobs(ctx context.Context, obj *schema.Job) (*model.JobLinkResultList, error) {
 	// FIXME: Make the hardcoded duration configurable
-	if obj.Exclusive != 1 && obj.Duration > 600 {
+	if obj.Shared != "none" && obj.Duration > 600 {
 		return r.Repo.FindConcurrentJobs(ctx, obj)
 	}
 
@@ -48,7 +56,7 @@ func (r *jobResolver) ConcurrentJobs(ctx context.Context, obj *schema.Job) (*mod
 func (r *jobResolver) Footprint(ctx context.Context, obj *schema.Job) ([]*model.FootprintValue, error) {
 	rawFootprint, err := r.Repo.FetchFootprint(obj)
 	if err != nil {
-		log.Warn("Error while fetching job footprint data")
+		cclog.Warn("Error while fetching job footprint data")
 		return nil, err
 	}
 
@@ -73,21 +81,21 @@ func (r *jobResolver) Footprint(ctx context.Context, obj *schema.Job) ([]*model.
 func (r *jobResolver) EnergyFootprint(ctx context.Context, obj *schema.Job) ([]*model.EnergyFootprintValue, error) {
 	rawEnergyFootprint, err := r.Repo.FetchEnergyFootprint(obj)
 	if err != nil {
-		log.Warn("Error while fetching job energy footprint data")
+		cclog.Warn("Error while fetching job energy footprint data")
 		return nil, err
 	}
 
 	res := []*model.EnergyFootprintValue{}
 	for name, value := range rawEnergyFootprint {
 		// Suboptimal: Nearly hardcoded metric name expectations
-		matchCpu := regexp.MustCompile(`cpu|Cpu|CPU`)
+		matchCPU := regexp.MustCompile(`cpu|Cpu|CPU`)
 		matchAcc := regexp.MustCompile(`acc|Acc|ACC`)
 		matchMem := regexp.MustCompile(`mem|Mem|MEM`)
 		matchCore := regexp.MustCompile(`core|Core|CORE`)
 
 		hwType := ""
 		switch test := name; { // NOtice ';' for var declaration
-		case matchCpu.MatchString(test):
+		case matchCPU.MatchString(test):
 			hwType = "CPU"
 		case matchAcc.MatchString(test):
 			hwType = "Accelerator"
@@ -125,40 +133,75 @@ func (r *metricValueResolver) Name(ctx context.Context, obj *schema.MetricValue)
 
 // CreateTag is the resolver for the createTag field.
 func (r *mutationResolver) CreateTag(ctx context.Context, typeArg string, name string, scope string) (*schema.Tag, error) {
-	id, err := r.Repo.CreateTag(typeArg, name, scope)
-	if err != nil {
-		log.Warn("Error while creating tag")
-		return nil, err
+	user := repository.GetUserFromContext(ctx)
+	if user == nil {
+		return nil, fmt.Errorf("no user in context")
 	}
 
-	return &schema.Tag{ID: id, Type: typeArg, Name: name, Scope: scope}, nil
+	// Test Access: Admins && Admin Tag OR Support/Admin and Global Tag OR Everyone && Private Tag
+	if user.HasRole(schema.RoleAdmin) && scope == "admin" ||
+		user.HasAnyRole([]schema.Role{schema.RoleAdmin, schema.RoleSupport}) && scope == "global" ||
+		user.Username == scope {
+		// Create in DB
+		id, err := r.Repo.CreateTag(typeArg, name, scope)
+		if err != nil {
+			cclog.Warn("Error while creating tag")
+			return nil, err
+		}
+		return &schema.Tag{ID: id, Type: typeArg, Name: name, Scope: scope}, nil
+	} else {
+		cclog.Warnf("Not authorized to create tag with scope: %s", scope)
+		return nil, fmt.Errorf("not authorized to create tag with scope: %s", scope)
+	}
 }
 
 // DeleteTag is the resolver for the deleteTag field.
 func (r *mutationResolver) DeleteTag(ctx context.Context, id string) (string, error) {
+	// This Uses ID string <-> ID string, removeTagFromList uses []string <-> []int
 	panic(fmt.Errorf("not implemented: DeleteTag - deleteTag"))
 }
 
 // AddTagsToJob is the resolver for the addTagsToJob field.
 func (r *mutationResolver) AddTagsToJob(ctx context.Context, job string, tagIds []string) ([]*schema.Tag, error) {
-	// Selectable Tags Pre-Filtered by Scope in Frontend: No backend check required
+	user := repository.GetUserFromContext(ctx)
+	if user == nil {
+		return nil, fmt.Errorf("no user in context")
+	}
+
 	jid, err := strconv.ParseInt(job, 10, 64)
 	if err != nil {
-		log.Warn("Error while adding tag to job")
+		cclog.Warn("Error while adding tag to job")
 		return nil, err
 	}
 
 	tags := []*schema.Tag{}
-	for _, tagId := range tagIds {
-		tid, err := strconv.ParseInt(tagId, 10, 64)
+	for _, tagID := range tagIds {
+		// Get ID
+		tid, err := strconv.ParseInt(tagID, 10, 64)
 		if err != nil {
-			log.Warn("Error while parsing tag id")
+			cclog.Warn("Error while parsing tag id")
 			return nil, err
 		}
 
-		if tags, err = r.Repo.AddTag(repository.GetUserFromContext(ctx), jid, tid); err != nil {
-			log.Warn("Error while adding tag")
-			return nil, err
+		// Test Exists
+		_, _, tscope, exists := r.Repo.TagInfo(tid)
+		if !exists {
+			cclog.Warnf("Tag does not exist (ID): %d", tid)
+			return nil, fmt.Errorf("tag does not exist (ID): %d", tid)
+		}
+
+		// Test Access: Admins && Admin Tag OR Support/Admin and Global Tag OR Everyone && Private Tag
+		if user.HasRole(schema.RoleAdmin) && tscope == "admin" ||
+			user.HasAnyRole([]schema.Role{schema.RoleAdmin, schema.RoleSupport}) && tscope == "global" ||
+			user.Username == tscope {
+			// Add to Job
+			if tags, err = r.Repo.AddTag(user, jid, tid); err != nil {
+				cclog.Warn("Error while adding tag")
+				return nil, err
+			}
+		} else {
+			cclog.Warnf("Not authorized to add tag: %d", tid)
+			return nil, fmt.Errorf("not authorized to add tag: %d", tid)
 		}
 	}
 
@@ -167,40 +210,127 @@ func (r *mutationResolver) AddTagsToJob(ctx context.Context, job string, tagIds
 
 // RemoveTagsFromJob is the resolver for the removeTagsFromJob field.
 func (r *mutationResolver) RemoveTagsFromJob(ctx context.Context, job string, tagIds []string) ([]*schema.Tag, error) {
-	// Removable Tags Pre-Filtered by Scope in Frontend: No backend check required
+	user := repository.GetUserFromContext(ctx)
+	if user == nil {
+		return nil, fmt.Errorf("no user in context")
+	}
+
 	jid, err := strconv.ParseInt(job, 10, 64)
 	if err != nil {
-		log.Warn("Error while parsing job id")
+		cclog.Warn("Error while parsing job id")
 		return nil, err
 	}
 
 	tags := []*schema.Tag{}
-	for _, tagId := range tagIds {
-		tid, err := strconv.ParseInt(tagId, 10, 64)
+	for _, tagID := range tagIds {
+		// Get ID
+		tid, err := strconv.ParseInt(tagID, 10, 64)
 		if err != nil {
-			log.Warn("Error while parsing tag id")
+			cclog.Warn("Error while parsing tag id")
 			return nil, err
 		}
 
-		if tags, err = r.Repo.RemoveTag(repository.GetUserFromContext(ctx), jid, tid); err != nil {
-			log.Warn("Error while removing tag")
-			return nil, err
+		// Test Exists
+		_, _, tscope, exists := r.Repo.TagInfo(tid)
+		if !exists {
+			cclog.Warnf("Tag does not exist (ID): %d", tid)
+			return nil, fmt.Errorf("tag does not exist (ID): %d", tid)
 		}
+
+		// Test Access: Admins && Admin Tag OR Support/Admin and Global Tag OR Everyone && Private Tag
+		if user.HasRole(schema.RoleAdmin) && tscope == "admin" ||
+			user.HasAnyRole([]schema.Role{schema.RoleAdmin, schema.RoleSupport}) && tscope == "global" ||
+			user.Username == tscope {
+			// Remove from Job
+			if tags, err = r.Repo.RemoveTag(user, jid, tid); err != nil {
+				cclog.Warn("Error while removing tag")
+				return nil, err
+			}
+		} else {
+			cclog.Warnf("Not authorized to remove tag: %d", tid)
+			return nil, fmt.Errorf("not authorized to remove tag: %d", tid)
+		}
+
 	}
 
 	return tags, nil
 }
 
+// RemoveTagFromList is the resolver for the removeTagFromList field.
+func (r *mutationResolver) RemoveTagFromList(ctx context.Context, tagIds []string) ([]int, error) {
+	// Needs Contextuser
+	user := repository.GetUserFromContext(ctx)
+	if user == nil {
+		return nil, fmt.Errorf("no user in context")
+	}
+
+	tags := []int{}
+	for _, tagID := range tagIds {
+		// Get ID
+		tid, err := strconv.ParseInt(tagID, 10, 64)
+		if err != nil {
+			cclog.Warn("Error while parsing tag id for removal")
+			return nil, err
+		}
+
+		// Test Exists
+		_, _, tscope, exists := r.Repo.TagInfo(tid)
+		if !exists {
+			cclog.Warnf("Tag does not exist (ID): %d", tid)
+			return nil, fmt.Errorf("tag does not exist (ID): %d", tid)
+		}
+
+		// Test Access: Admins && Admin Tag OR Everyone && Private Tag
+		if user.HasRole(schema.RoleAdmin) && (tscope == "global" || tscope == "admin") || user.Username == tscope {
+			// Remove from DB
+			if err = r.Repo.RemoveTagById(tid); err != nil {
+				cclog.Warn("Error while removing tag")
+				return nil, err
+			} else {
+				tags = append(tags, int(tid))
+			}
+		} else {
+			cclog.Warnf("Not authorized to remove tag: %d", tid)
+			return nil, fmt.Errorf("not authorized to remove tag: %d", tid)
+		}
+	}
+	return tags, nil
+}
+
 // UpdateConfiguration is the resolver for the updateConfiguration field.
 func (r *mutationResolver) UpdateConfiguration(ctx context.Context, name string, value string) (*string, error) {
 	if err := repository.GetUserCfgRepo().UpdateConfig(name, value, repository.GetUserFromContext(ctx)); err != nil {
-		log.Warn("Error while updating user config")
+		cclog.Warn("Error while updating user config")
 		return nil, err
 	}
 
 	return nil, nil
 }
 
+// ID is the resolver for the id field.
+func (r *nodeResolver) ID(ctx context.Context, obj *schema.Node) (string, error) {
+	panic(fmt.Errorf("not implemented: ID - id"))
+}
+
+// SchedulerState is the resolver for the schedulerState field.
+func (r *nodeResolver) SchedulerState(ctx context.Context, obj *schema.Node) (schema.SchedulerState, error) {
+	if obj.NodeState != "" {
+		return obj.NodeState, nil
+	} else {
+		return "", fmt.Errorf("no SchedulerState (NodeState) on Object")
+	}
+}
+
+// HealthState is the resolver for the healthState field.
+func (r *nodeResolver) HealthState(ctx context.Context, obj *schema.Node) (string, error) {
+	panic(fmt.Errorf("not implemented: HealthState - healthState"))
+}
+
+// MetaData is the resolver for the metaData field.
+func (r *nodeResolver) MetaData(ctx context.Context, obj *schema.Node) (any, error) {
+	panic(fmt.Errorf("not implemented: MetaData - metaData"))
+}
+
 // Clusters is the resolver for the clusters field.
 func (r *queryResolver) Clusters(ctx context.Context) ([]*schema.Cluster, error) {
 	return archive.Clusters, nil
@@ -213,6 +343,14 @@ func (r *queryResolver) Tags(ctx context.Context) ([]*schema.Tag, error) {
 
 // GlobalMetrics is the resolver for the globalMetrics field.
 func (r *queryResolver) GlobalMetrics(ctx context.Context) ([]*schema.GlobalMetricListItem, error) {
+	user := repository.GetUserFromContext(ctx)
+
+	if user != nil {
+		if user.HasRole(schema.RoleUser) || user.HasRole(schema.RoleManager) {
+			return archive.GlobalUserMetricList, nil
+		}
+	}
+
 	return archive.GlobalMetricList, nil
 }
 
@@ -225,7 +363,7 @@ func (r *queryResolver) User(ctx context.Context, username string) (*model.User,
 func (r *queryResolver) AllocatedNodes(ctx context.Context, cluster string) ([]*model.Count, error) {
 	data, err := r.Repo.AllocatedNodes(cluster)
 	if err != nil {
-		log.Warn("Error while fetching allocated nodes")
+		cclog.Warn("Error while fetching allocated nodes")
 		return nil, err
 	}
 
@@ -240,17 +378,82 @@ func (r *queryResolver) AllocatedNodes(ctx context.Context, cluster string) ([]*
 	return counts, nil
 }
 
+// Node is the resolver for the node field.
+func (r *queryResolver) Node(ctx context.Context, id string) (*schema.Node, error) {
+	repo := repository.GetNodeRepository()
+	numericID, err := strconv.ParseInt(id, 10, 64)
+	if err != nil {
+		cclog.Warn("Error while parsing job id")
+		return nil, err
+	}
+	return repo.GetNodeByID(numericID, false)
+}
+
+// Nodes is the resolver for the nodes field.
+func (r *queryResolver) Nodes(ctx context.Context, filter []*model.NodeFilter, order *model.OrderByInput) (*model.NodeStateResultList, error) {
+	repo := repository.GetNodeRepository()
+	nodes, err := repo.QueryNodes(ctx, filter, nil, order) // Ignore Paging, Order Unused
+	count := len(nodes)
+	return &model.NodeStateResultList{Items: nodes, Count: &count}, err
+}
+
+// NodeStates is the resolver for the nodeStates field.
+func (r *queryResolver) NodeStates(ctx context.Context, filter []*model.NodeFilter) ([]*model.NodeStates, error) {
+	repo := repository.GetNodeRepository()
+
+	stateCounts, serr := repo.CountStates(ctx, filter, "node_state")
+	if serr != nil {
+		cclog.Warnf("Error while counting nodeStates: %s", serr.Error())
+		return nil, serr
+	}
+
+	healthCounts, herr := repo.CountStates(ctx, filter, "health_state")
+	if herr != nil {
+		cclog.Warnf("Error while counting healthStates: %s", herr.Error())
+		return nil, herr
+	}
+
+	allCounts := append(stateCounts, healthCounts...)
+
+	return allCounts, nil
+}
+
+// NodeStatesTimed is the resolver for the nodeStatesTimed field.
+func (r *queryResolver) NodeStatesTimed(ctx context.Context, filter []*model.NodeFilter, typeArg string) ([]*model.NodeStatesTimed, error) {
+	repo := repository.GetNodeRepository()
+
+	if typeArg == "node" {
+		stateCounts, serr := repo.CountStatesTimed(ctx, filter, "node_state")
+		if serr != nil {
+			cclog.Warnf("Error while counting nodeStates in time: %s", serr.Error())
+			return nil, serr
+		}
+		return stateCounts, nil
+	}
+
+	if typeArg == "health" {
+		healthCounts, herr := repo.CountStatesTimed(ctx, filter, "health_state")
+		if herr != nil {
+			cclog.Warnf("Error while counting healthStates in time: %s", herr.Error())
+			return nil, herr
+		}
+		return healthCounts, nil
+	}
+
+	return nil, errors.New("unknown Node State Query Type")
+}
+
 // Job is the resolver for the job field.
 func (r *queryResolver) Job(ctx context.Context, id string) (*schema.Job, error) {
-	numericId, err := strconv.ParseInt(id, 10, 64)
+	numericID, err := strconv.ParseInt(id, 10, 64)
 	if err != nil {
-		log.Warn("Error while parsing job id")
+		cclog.Warn("Error while parsing job id")
 		return nil, err
 	}
 
-	job, err := r.Repo.FindById(ctx, numericId)
+	job, err := r.Repo.FindByID(ctx, numericID)
 	if err != nil {
-		log.Warn("Error while finding job by id")
+		cclog.Warn("Error while finding job by id")
 		return nil, err
 	}
 
@@ -277,13 +480,13 @@ func (r *queryResolver) JobMetrics(ctx context.Context, id string, metrics []str
 
 	job, err := r.Query().Job(ctx, id)
 	if err != nil {
-		log.Warn("Error while querying job for metrics")
+		cclog.Warn("Error while querying job for metrics")
 		return nil, err
 	}
 
 	data, err := metricDataDispatcher.LoadData(job, metrics, scopes, ctx, *resolution)
 	if err != nil {
-		log.Warn("Error while loading job data")
+		cclog.Warn("Error while loading job data")
 		return nil, err
 	}
 
@@ -301,36 +504,67 @@ func (r *queryResolver) JobMetrics(ctx context.Context, id string, metrics []str
 	return res, err
 }
 
-// JobMetricStats is the resolver for the jobMetricStats field.
-func (r *queryResolver) JobMetricStats(ctx context.Context, id string, metrics []string) ([]*model.JobMetricStatWithName, error) {
-
+// JobStats is the resolver for the jobStats field.
+func (r *queryResolver) JobStats(ctx context.Context, id string, metrics []string) ([]*model.NamedStats, error) {
 	job, err := r.Query().Job(ctx, id)
 	if err != nil {
-		log.Warn("Error while querying job for metrics")
+		cclog.Warnf("Error while querying job %s for metadata", id)
 		return nil, err
 	}
 
-	data, err := metricDataDispatcher.LoadStatData(job, metrics, ctx)
+	data, err := metricDataDispatcher.LoadJobStats(job, metrics, ctx)
 	if err != nil {
-		log.Warn("Error while loading job stat data")
+		cclog.Warnf("Error while loading jobStats data for job id %s", id)
 		return nil, err
 	}
 
-	res := []*model.JobMetricStatWithName{}
+	res := []*model.NamedStats{}
 	for name, md := range data {
-		res = append(res, &model.JobMetricStatWithName{
-			Name:  name,
-			Stats: &md,
+		res = append(res, &model.NamedStats{
+			Name: name,
+			Data: &md,
 		})
 	}
 
 	return res, err
 }
 
-// JobsFootprints is the resolver for the jobsFootprints field.
-func (r *queryResolver) JobsFootprints(ctx context.Context, filter []*model.JobFilter, metrics []string) (*model.Footprints, error) {
-	// NOTE: Legacy Naming! This resolver is for normalized histograms in analysis view only - *Not* related to DB "footprint" column!
-	return r.jobsFootprints(ctx, filter, metrics)
+// ScopedJobStats is the resolver for the scopedJobStats field.
+func (r *queryResolver) ScopedJobStats(ctx context.Context, id string, metrics []string, scopes []schema.MetricScope) ([]*model.NamedStatsWithScope, error) {
+	job, err := r.Query().Job(ctx, id)
+	if err != nil {
+		cclog.Warnf("Error while querying job %s for metadata", id)
+		return nil, err
+	}
+
+	data, err := metricDataDispatcher.LoadScopedJobStats(job, metrics, scopes, ctx)
+	if err != nil {
+		cclog.Warnf("Error while loading scopedJobStats data for job id %s", id)
+		return nil, err
+	}
+
+	res := make([]*model.NamedStatsWithScope, 0)
+	for name, scoped := range data {
+		for scope, stats := range scoped {
+
+			mdlStats := make([]*model.ScopedStats, 0)
+			for _, stat := range stats {
+				mdlStats = append(mdlStats, &model.ScopedStats{
+					Hostname: stat.Hostname,
+					ID:       stat.Id,
+					Data:     stat.Data,
+				})
+			}
+
+			res = append(res, &model.NamedStatsWithScope{
+				Name:  name,
+				Scope: scope,
+				Stats: mdlStats,
+			})
+		}
+	}
+
+	return res, nil
 }
 
 // Jobs is the resolver for the jobs field.
@@ -344,40 +578,35 @@ func (r *queryResolver) Jobs(ctx context.Context, filter []*model.JobFilter, pag
 
 	jobs, err := r.Repo.QueryJobs(ctx, filter, page, order)
 	if err != nil {
-		log.Warn("Error while querying jobs")
+		cclog.Warn("Error while querying jobs")
 		return nil, err
 	}
 
 	count, err := r.Repo.CountJobs(ctx, filter)
 	if err != nil {
-		log.Warn("Error while counting jobs")
+		cclog.Warn("Error while counting jobs")
 		return nil, err
 	}
 
-	if !config.Keys.UiDefaults["job_list_usePaging"].(bool) {
-		hasNextPage := false
-		// page.Page += 1 		   : Simple, but expensive
-		// Example Page 4 @ 10 IpP : Does item 41 exist?
-		// Minimal Page 41 @ 1 IpP : If len(result) is 1, Page 5 @ 10 IpP exists.
-		nextPage := &model.PageRequest{
-			ItemsPerPage: 1,
-			Page:         ((page.Page * page.ItemsPerPage) + 1),
-		}
-
-		nextJobs, err := r.Repo.QueryJobs(ctx, filter, nextPage, order)
-		if err != nil {
-			log.Warn("Error while querying next jobs")
-			return nil, err
-		}
-
-		if len(nextJobs) == 1 {
-			hasNextPage = true
-		}
-
-		return &model.JobResultList{Items: jobs, Count: &count, HasNextPage: &hasNextPage}, nil
-	} else {
-		return &model.JobResultList{Items: jobs, Count: &count}, nil
+	// Note: Even if App-Default 'config.Keys.UiDefaults["job_list_usePaging"]' is set, always return hasNextPage boolean.
+	// Users can decide in frontend to use continuous scroll, even if app-default is paging!
+	/*
+	  Example Page 4 @ 10 IpP : Does item 41 exist?
+	  Minimal Page 41 @ 1 IpP : If len(result) is 1, Page 5 @ 10 IpP exists.
+	*/
+	nextPage := &model.PageRequest{
+		ItemsPerPage: 1,
+		Page:         ((page.Page * page.ItemsPerPage) + 1),
 	}
+	nextJobs, err := r.Repo.QueryJobs(ctx, filter, nextPage, order)
+	if err != nil {
+		cclog.Warn("Error while querying next jobs")
+		return nil, err
+	}
+
+	hasNextPage := len(nextJobs) == 1
+
+	return &model.JobResultList{Items: jobs, Count: &count, HasNextPage: &hasNextPage}, nil
 }
 
 // JobsStatistics is the resolver for the jobsStatistics field.
@@ -386,10 +615,10 @@ func (r *queryResolver) JobsStatistics(ctx context.Context, filter []*model.JobF
 	var stats []*model.JobsStatistics
 
 	// Top Level Defaults
-	var defaultDurationBins string = "1h"
-	var defaultMetricBins int = 10
+	defaultDurationBins := "1h"
+	defaultMetricBins := 10
 
-	if requireField(ctx, "totalJobs") || requireField(ctx, "totalWalltime") || requireField(ctx, "totalNodes") || requireField(ctx, "totalCores") ||
+	if requireField(ctx, "totalJobs") || requireField(ctx, "totalUsers") || requireField(ctx, "totalWalltime") || requireField(ctx, "totalNodes") || requireField(ctx, "totalCores") ||
 		requireField(ctx, "totalAccs") || requireField(ctx, "totalNodeHours") || requireField(ctx, "totalCoreHours") || requireField(ctx, "totalAccHours") {
 		if groupBy == nil {
 			stats, err = r.Repo.JobsStats(ctx, filter)
@@ -456,6 +685,62 @@ func (r *queryResolver) JobsStatistics(ctx context.Context, filter []*model.JobF
 	return stats, nil
 }
 
+// JobsMetricStats is the resolver for the jobsMetricStats field.
+func (r *queryResolver) JobsMetricStats(ctx context.Context, filter []*model.JobFilter, metrics []string) ([]*model.JobStats, error) {
+	// No Paging, Fixed Order by StartTime ASC
+	order := &model.OrderByInput{
+		Field: "startTime",
+		Type:  "col",
+		Order: "ASC",
+	}
+
+	jobs, err := r.Repo.QueryJobs(ctx, filter, nil, order)
+	if err != nil {
+		cclog.Warn("Error while querying jobs for comparison")
+		return nil, err
+	}
+
+	res := []*model.JobStats{}
+	for _, job := range jobs {
+		data, err := metricDataDispatcher.LoadJobStats(job, metrics, ctx)
+		if err != nil {
+			cclog.Warnf("Error while loading comparison jobStats data for job id %d", job.JobID)
+			continue
+			// return nil, err
+		}
+
+		sres := []*model.NamedStats{}
+		for name, md := range data {
+			sres = append(sres, &model.NamedStats{
+				Name: name,
+				Data: &md,
+			})
+		}
+
+		numThreadsInt := int(job.NumHWThreads)
+		numAccsInt := int(job.NumAcc)
+		res = append(res, &model.JobStats{
+			ID:              int(*job.ID),
+			JobID:           strconv.Itoa(int(job.JobID)),
+			StartTime:       int(job.StartTime),
+			Duration:        int(job.Duration),
+			Cluster:         job.Cluster,
+			SubCluster:      job.SubCluster,
+			NumNodes:        int(job.NumNodes),
+			NumHWThreads:    &numThreadsInt,
+			NumAccelerators: &numAccsInt,
+			Stats:           sres,
+		})
+	}
+	return res, err
+}
+
+// JobsFootprints is the resolver for the jobsFootprints field.
+func (r *queryResolver) JobsFootprints(ctx context.Context, filter []*model.JobFilter, metrics []string) (*model.Footprints, error) {
+	// NOTE: Legacy Naming! This resolver is for normalized histograms in analysis view only - *Not* related to DB "footprint" column!
+	return r.jobsFootprints(ctx, filter, metrics)
+}
+
 // RooflineHeatmap is the resolver for the rooflineHeatmap field.
 func (r *queryResolver) RooflineHeatmap(ctx context.Context, filter []*model.JobFilter, rows int, cols int, minX float64, minY float64, maxX float64, maxY float64) ([][]float64, error) {
 	return r.rooflineHeatmap(ctx, filter, rows, cols, minX, minY, maxX, maxY)
@@ -476,19 +761,23 @@ func (r *queryResolver) NodeMetrics(ctx context.Context, cluster string, nodes [
 
 	data, err := metricDataDispatcher.LoadNodeData(cluster, metrics, nodes, scopes, from, to, ctx)
 	if err != nil {
-		log.Warn("error while loading node data")
+		cclog.Warn("error while loading node data")
 		return nil, err
 	}
 
+	nodeRepo := repository.GetNodeRepository()
+	stateMap, _ := nodeRepo.MapNodes(cluster)
+
 	nodeMetrics := make([]*model.NodeMetrics, 0, len(data))
 	for hostname, metrics := range data {
 		host := &model.NodeMetrics{
 			Host:    hostname,
+			State:   stateMap[hostname],
 			Metrics: make([]*model.JobMetricWithName, 0, len(metrics)*len(scopes)),
 		}
 		host.SubCluster, err = archive.GetSubClusterByNode(cluster, hostname)
 		if err != nil {
-			log.Warnf("error in nodeMetrics resolver: %s", err)
+			cclog.Warnf("error in nodeMetrics resolver: %s", err)
 		}
 
 		for metric, scopedMetrics := range metrics {
@@ -508,7 +797,7 @@ func (r *queryResolver) NodeMetrics(ctx context.Context, cluster string, nodes [
 }
 
 // NodeMetricsList is the resolver for the nodeMetricsList field.
-func (r *queryResolver) NodeMetricsList(ctx context.Context, cluster string, subCluster string, nodeFilter string, scopes []schema.MetricScope, metrics []string, from time.Time, to time.Time, page *model.PageRequest, resolution *int) (*model.NodesResultList, error) {
+func (r *queryResolver) NodeMetricsList(ctx context.Context, cluster string, subCluster string, stateFilter string, nodeFilter string, scopes []schema.MetricScope, metrics []string, from time.Time, to time.Time, page *model.PageRequest, resolution *int) (*model.NodesResultList, error) {
 	if resolution == nil { // Load from Config
 		if config.Keys.EnableResampling != nil {
 			defaultRes := slices.Max(config.Keys.EnableResampling.Resolutions)
@@ -524,15 +813,21 @@ func (r *queryResolver) NodeMetricsList(ctx context.Context, cluster string, sub
 		return nil, errors.New("you need to be administrator or support staff for this query")
 	}
 
+	nodeRepo := repository.GetNodeRepository()
+	nodes, stateMap, countNodes, hasNextPage, nerr := nodeRepo.GetNodesForList(ctx, cluster, subCluster, stateFilter, nodeFilter, page)
+	if nerr != nil {
+		return nil, errors.New("could not retrieve node list required for resolving NodeMetricsList")
+	}
+
 	if metrics == nil {
 		for _, mc := range archive.GetCluster(cluster).MetricConfig {
 			metrics = append(metrics, mc.Name)
 		}
 	}
 
-	data, totalNodes, hasNextPage, err := metricDataDispatcher.LoadNodeListData(cluster, subCluster, nodeFilter, metrics, scopes, *resolution, from, to, page, ctx)
+	data, err := metricDataDispatcher.LoadNodeListData(cluster, subCluster, nodes, metrics, scopes, *resolution, from, to, ctx)
 	if err != nil {
-		log.Warn("error while loading node data")
+		cclog.Warn("error while loading node data (Resolver.NodeMetricsList")
 		return nil, err
 	}
 
@@ -540,11 +835,12 @@ func (r *queryResolver) NodeMetricsList(ctx context.Context, cluster string, sub
 	for hostname, metrics := range data {
 		host := &model.NodeMetrics{
 			Host:    hostname,
+			State:   stateMap[hostname],
 			Metrics: make([]*model.JobMetricWithName, 0, len(metrics)*len(scopes)),
 		}
 		host.SubCluster, err = archive.GetSubClusterByNode(cluster, hostname)
 		if err != nil {
-			log.Warnf("error in nodeMetrics resolver: %s", err)
+			cclog.Warnf("error in nodeMetrics resolver: %s", err)
 		}
 
 		for metric, scopedMetrics := range metrics {
@@ -562,13 +858,90 @@ func (r *queryResolver) NodeMetricsList(ctx context.Context, cluster string, sub
 
 	nodeMetricsListResult := &model.NodesResultList{
 		Items:       nodeMetricsList,
-		TotalNodes:  &totalNodes,
+		TotalNodes:  &countNodes,
 		HasNextPage: &hasNextPage,
 	}
 
 	return nodeMetricsListResult, nil
 }
 
+// ClusterMetrics is the resolver for the clusterMetrics field.
+func (r *queryResolver) ClusterMetrics(ctx context.Context, cluster string, metrics []string, from time.Time, to time.Time) (*model.ClusterMetrics, error) {
+	user := repository.GetUserFromContext(ctx)
+	if user != nil && !user.HasAnyRole([]schema.Role{schema.RoleAdmin, schema.RoleSupport}) {
+		return nil, errors.New("you need to be administrator or support staff for this query")
+	}
+
+	if metrics == nil {
+		for _, mc := range archive.GetCluster(cluster).MetricConfig {
+			metrics = append(metrics, mc.Name)
+		}
+	}
+
+	// 'nodes' == nil -> Defaults to all nodes of cluster for existing query workflow
+	scopes := []schema.MetricScope{"node"}
+	data, err := metricDataDispatcher.LoadNodeData(cluster, metrics, nil, scopes, from, to, ctx)
+	if err != nil {
+		cclog.Warn("error while loading node data")
+		return nil, err
+	}
+
+	clusterMetricData := make([]*model.ClusterMetricWithName, 0)
+	clusterMetrics := model.ClusterMetrics{NodeCount: 0, Metrics: clusterMetricData}
+
+	collectorTimestep := make(map[string]int)
+	collectorUnit := make(map[string]schema.Unit)
+	collectorData := make(map[string][]schema.Float)
+
+	for _, metrics := range data {
+		clusterMetrics.NodeCount += 1
+		for metric, scopedMetrics := range metrics {
+			_, ok := collectorData[metric]
+			if !ok {
+				collectorData[metric] = make([]schema.Float, 0)
+				for _, scopedMetric := range scopedMetrics {
+					// Collect Info
+					collectorTimestep[metric] = scopedMetric.Timestep
+					collectorUnit[metric] = scopedMetric.Unit
+					// Collect Initial Data
+					for _, ser := range scopedMetric.Series {
+						collectorData[metric] = append(collectorData[metric], ser.Data...)
+					}
+				}
+			} else {
+				// Sum up values by index
+				for _, scopedMetric := range scopedMetrics {
+					// For This Purpose (Cluster_Wide-Sum of Node Metrics) OK
+					for _, ser := range scopedMetric.Series {
+						for i, val := range ser.Data {
+							collectorData[metric][i] += val
+						}
+					}
+				}
+			}
+		}
+	}
+
+	for metricName, data := range collectorData {
+		cu := collectorUnit[metricName]
+		roundedData := make([]schema.Float, 0)
+		for _, val := range data {
+			roundedData = append(roundedData, schema.Float((math.Round(float64(val)*100.0) / 100.0)))
+		}
+
+		cm := model.ClusterMetricWithName{
+			Name:     metricName,
+			Unit:     &cu,
+			Timestep: collectorTimestep[metricName],
+			Data:     roundedData,
+		}
+
+		clusterMetrics.Metrics = append(clusterMetrics.Metrics, &cm)
+	}
+
+	return &clusterMetrics, nil
+}
+
 // NumberOfNodes is the resolver for the numberOfNodes field.
 func (r *subClusterResolver) NumberOfNodes(ctx context.Context, obj *schema.SubCluster) (int, error) {
 	nodeList, err := archive.ParseNodeList(obj.Nodes)
@@ -590,15 +963,21 @@ func (r *Resolver) MetricValue() generated.MetricValueResolver { return &metricV
 // Mutation returns generated.MutationResolver implementation.
 func (r *Resolver) Mutation() generated.MutationResolver { return &mutationResolver{r} }
 
+// Node returns generated.NodeResolver implementation.
+func (r *Resolver) Node() generated.NodeResolver { return &nodeResolver{r} }
+
 // Query returns generated.QueryResolver implementation.
 func (r *Resolver) Query() generated.QueryResolver { return &queryResolver{r} }
 
 // SubCluster returns generated.SubClusterResolver implementation.
 func (r *Resolver) SubCluster() generated.SubClusterResolver { return &subClusterResolver{r} }
 
-type clusterResolver struct{ *Resolver }
-type jobResolver struct{ *Resolver }
-type metricValueResolver struct{ *Resolver }
-type mutationResolver struct{ *Resolver }
-type queryResolver struct{ *Resolver }
-type subClusterResolver struct{ *Resolver }
+type (
+	clusterResolver     struct{ *Resolver }
+	jobResolver         struct{ *Resolver }
+	metricValueResolver struct{ *Resolver }
+	mutationResolver    struct{ *Resolver }
+	nodeResolver        struct{ *Resolver }
+	queryResolver       struct{ *Resolver }
+	subClusterResolver  struct{ *Resolver }
+)

internal/graph/util.go

@@ -1,20 +1,21 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package graph
 
 import (
 	"context"
 	"fmt"
 	"math"
+	"slices"
 
 	"github.com/99designs/gqlgen/graphql"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/internal/metricDataDispatcher"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
-	// "github.com/ClusterCockpit/cc-backend/pkg/archive"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
 const MAX_JOBS_FOR_ANALYSIS = 500
@@ -28,7 +29,7 @@ func (r *queryResolver) rooflineHeatmap(
 ) ([][]float64, error) {
 	jobs, err := r.Repo.QueryJobs(ctx, filter, &model.PageRequest{Page: 1, ItemsPerPage: MAX_JOBS_FOR_ANALYSIS + 1}, nil)
 	if err != nil {
-		log.Error("Error while querying jobs for roofline")
+		cclog.Error("Error while querying jobs for roofline")
 		return nil, err
 	}
 	if len(jobs) > MAX_JOBS_FOR_ANALYSIS {
@@ -56,13 +57,13 @@ func (r *queryResolver) rooflineHeatmap(
 
 		jobdata, err := metricDataDispatcher.LoadData(job, []string{"flops_any", "mem_bw"}, []schema.MetricScope{schema.MetricScopeNode}, ctx, 0)
 		if err != nil {
-			log.Errorf("Error while loading roofline metrics for job %d", job.ID)
+			cclog.Errorf("Error while loading roofline metrics for job %d", job.ID)
 			return nil, err
 		}
 
 		flops_, membw_ := jobdata["flops_any"], jobdata["mem_bw"]
 		if flops_ == nil && membw_ == nil {
-			log.Infof("rooflineHeatmap(): 'flops_any' or 'mem_bw' missing for job %d", job.ID)
+			cclog.Infof("rooflineHeatmap(): 'flops_any' or 'mem_bw' missing for job %d", job.ID)
 			continue
 			// return nil, fmt.Errorf("GRAPH/UTIL > 'flops_any' or 'mem_bw' missing for job %d", job.ID)
 		}
@@ -70,7 +71,7 @@ func (r *queryResolver) rooflineHeatmap(
 		flops, ok1 := flops_["node"]
 		membw, ok2 := membw_["node"]
 		if !ok1 || !ok2 {
-			log.Info("rooflineHeatmap() query not implemented for where flops_any or mem_bw not available at 'node' level")
+			cclog.Info("rooflineHeatmap() query not implemented for where flops_any or mem_bw not available at 'node' level")
 			continue
 			// TODO/FIXME:
 			// return nil, errors.New("GRAPH/UTIL > todo: rooflineHeatmap() query not implemented for where flops_any or mem_bw not available at 'node' level")
@@ -105,7 +106,7 @@ func (r *queryResolver) rooflineHeatmap(
 func (r *queryResolver) jobsFootprints(ctx context.Context, filter []*model.JobFilter, metrics []string) (*model.Footprints, error) {
 	jobs, err := r.Repo.QueryJobs(ctx, filter, &model.PageRequest{Page: 1, ItemsPerPage: MAX_JOBS_FOR_ANALYSIS + 1}, nil)
 	if err != nil {
-		log.Error("Error while querying jobs for footprint")
+		cclog.Error("Error while querying jobs for footprint")
 		return nil, err
 	}
 	if len(jobs) > MAX_JOBS_FOR_ANALYSIS {
@@ -128,7 +129,7 @@ func (r *queryResolver) jobsFootprints(ctx context.Context, filter []*model.JobF
 		}
 
 		if err := metricDataDispatcher.LoadAverages(job, metrics, avgs, ctx); err != nil {
-			log.Error("Error while loading averages for footprint")
+			cclog.Error("Error while loading averages for footprint")
 			return nil, err
 		}
 
@@ -186,11 +187,5 @@ func (r *queryResolver) jobsFootprints(ctx context.Context, filter []*model.JobF
 func requireField(ctx context.Context, name string) bool {
 	fields := graphql.CollectAllFields(ctx)
 
-	for _, f := range fields {
-		if f == name {
-			return true
-		}
-	}
-
-	return false
+	return slices.Contains(fields, name)
 }

internal/importer/README.md

@@ -0,0 +1,132 @@
+# Importer Package
+
+The `importer` package provides functionality for importing job data into the ClusterCockpit database from archived job files.
+
+## Overview
+
+This package supports two primary import workflows:
+
+1. **Bulk Database Initialization** - Reinitialize the entire job database from archived jobs
+2. **Individual Job Import** - Import specific jobs from metadata/data file pairs
+
+Both workflows enrich job metadata by calculating performance footprints and energy consumption metrics before persisting to the database.
+
+## Main Entry Points
+
+### InitDB()
+
+Reinitializes the job database from all archived jobs.
+
+```go
+if err := importer.InitDB(); err != nil {
+    log.Fatal(err)
+}
+```
+
+This function:
+- Flushes existing job, tag, and jobtag tables
+- Iterates through all jobs in the configured archive
+- Enriches each job with calculated metrics
+- Inserts jobs into the database in batched transactions (100 jobs per batch)
+- Continues on individual job failures, logging errors
+
+**Use Case**: Initial database setup or complete database rebuild from archive.
+
+### HandleImportFlag(flag string)
+
+Imports jobs from specified file pairs.
+
+```go
+// Format: "<meta.json>:<data.json>[,<meta2.json>:<data2.json>,...]"
+flag := "/path/to/meta.json:/path/to/data.json"
+if err := importer.HandleImportFlag(flag); err != nil {
+    log.Fatal(err)
+}
+```
+
+This function:
+- Parses the comma-separated file pairs
+- Validates metadata and job data against schemas (if validation enabled)
+- Enriches each job with footprints and energy metrics
+- Imports jobs into both the archive and database
+- Fails fast on the first error
+
+**Use Case**: Importing specific jobs from external sources or manual job additions.
+
+## Job Enrichment
+
+Both import workflows use `enrichJobMetadata()` to calculate:
+
+### Performance Footprints
+
+Performance footprints are calculated from metric averages based on the subcluster configuration:
+
+```go
+job.Footprint["mem_used_avg"] = 45.2  // GB
+job.Footprint["cpu_load_avg"] = 0.87   // percentage
+```
+
+### Energy Metrics
+
+Energy consumption is calculated from power metrics using the formula:
+
+```
+Energy (kWh) = (Power (W) × Duration (s) / 3600) / 1000
+```
+
+For each energy metric:
+```go
+job.EnergyFootprint["acc_power"] = 12.5  // kWh
+job.Energy = 150.2  // Total energy in kWh
+```
+
+**Note**: Energy calculations for metrics with unit "energy" (Joules) are not yet implemented.
+
+## Data Validation
+
+### SanityChecks(job *schema.Job)
+
+Validates job metadata before database insertion:
+
+- Cluster exists in configuration
+- Subcluster is valid (assigns if needed)
+- Job state is valid
+- Resources and user fields are populated
+- Node counts and hardware thread counts are positive
+- Resource count matches declared node count
+
+## Normalization Utilities
+
+The package includes utilities for normalizing metric values to appropriate SI prefixes:
+
+### Normalize(avg float64, prefix string)
+
+Adjusts values and SI prefixes for readability:
+
+```go
+factor, newPrefix := importer.Normalize(2048.0, "M")  
+// Converts 2048 MB → ~2.0 GB
+// Returns: factor for conversion, "G"
+```
+
+This is useful for automatically scaling metrics (e.g., memory, storage) to human-readable units.
+
+## Dependencies
+
+- `github.com/ClusterCockpit/cc-backend/internal/repository` - Database operations
+- `github.com/ClusterCockpit/cc-backend/pkg/archive` - Job archive access
+- `github.com/ClusterCockpit/cc-lib/schema` - Job schema definitions
+- `github.com/ClusterCockpit/cc-lib/ccLogger` - Logging
+- `github.com/ClusterCockpit/cc-lib/ccUnits` - SI unit handling
+
+## Error Handling
+
+- **InitDB**: Continues processing on individual job failures, logs errors, returns summary
+- **HandleImportFlag**: Fails fast on first error, returns immediately
+- Both functions log detailed error context for debugging
+
+## Performance
+
+- **Transaction Batching**: InitDB processes jobs in batches of 100 for optimal database performance
+- **Tag Caching**: Tag IDs are cached during import to minimize database queries
+- **Progress Reporting**: InitDB prints progress updates during bulk operations

internal/importer/handleImport.go

@@ -1,5 +1,5 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package importer
@@ -8,18 +8,32 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"math"
 	"os"
 	"strings"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
-// Import all jobs specified as `<path-to-meta.json>:<path-to-data.json>,...`
+// HandleImportFlag imports jobs from file pairs specified in a comma-separated flag string.
+//
+// The flag format is: "<path-to-meta.json>:<path-to-data.json>[,<path-to-meta2.json>:<path-to-data2.json>,...]"
+//
+// For each job pair, this function:
+//  1. Reads and validates the metadata JSON file (schema.Job)
+//  2. Reads and validates the job data JSON file (schema.JobData)
+//  3. Enriches the job with calculated footprints and energy metrics
+//  4. Validates the job using SanityChecks()
+//  5. Imports the job into the archive
+//  6. Inserts the job into the database with associated tags
+//
+// Schema validation is performed if config.Keys.Validate is true.
+//
+// Returns an error if file reading, validation, enrichment, or database operations fail.
+// The function stops processing on the first error encountered.
 func HandleImportFlag(flag string) error {
 	r := repository.GetJobRepository()
 
@@ -31,7 +45,7 @@ func HandleImportFlag(flag string) error {
 
 		raw, err := os.ReadFile(files[0])
 		if err != nil {
-			log.Warn("Error while reading metadata file for import")
+			cclog.Warn("Error while reading metadata file for import")
 			return err
 		}
 
@@ -42,15 +56,18 @@ func HandleImportFlag(flag string) error {
 		}
 		dec := json.NewDecoder(bytes.NewReader(raw))
 		dec.DisallowUnknownFields()
-		job := schema.JobMeta{BaseJob: schema.JobDefaults}
+		job := schema.Job{
+			Shared:           "none",
+			MonitoringStatus: schema.MonitoringStatusRunningOrArchiving,
+		}
 		if err = dec.Decode(&job); err != nil {
-			log.Warn("Error while decoding raw json metadata for import")
+			cclog.Warn("Error while decoding raw json metadata for import")
 			return err
 		}
 
 		raw, err = os.ReadFile(files[1])
 		if err != nil {
-			log.Warn("Error while reading jobdata file for import")
+			cclog.Warn("Error while reading jobdata file for import")
 			return err
 		}
 
@@ -63,108 +80,41 @@ func HandleImportFlag(flag string) error {
 		dec.DisallowUnknownFields()
 		jobData := schema.JobData{}
 		if err = dec.Decode(&jobData); err != nil {
-			log.Warn("Error while decoding raw json jobdata for import")
+			cclog.Warn("Error while decoding raw json jobdata for import")
 			return err
 		}
 
 		job.MonitoringStatus = schema.MonitoringStatusArchivingSuccessful
 
-		sc, err := archive.GetSubCluster(job.Cluster, job.SubCluster)
-		if err != nil {
-			log.Errorf("cannot get subcluster: %s", err.Error())
+		if err = enrichJobMetadata(&job); err != nil {
+			cclog.Errorf("Error enriching job metadata: %v", err)
 			return err
 		}
 
-		job.Footprint = make(map[string]float64)
-
-		for _, fp := range sc.Footprint {
-			statType := "avg"
-
-			if i, err := archive.MetricIndex(sc.MetricConfig, fp); err != nil {
-				statType = sc.MetricConfig[i].Footprint
-			}
-
-			name := fmt.Sprintf("%s_%s", fp, statType)
-
-			job.Footprint[name] = repository.LoadJobStat(&job, fp, statType)
-		}
-
-		job.RawFootprint, err = json.Marshal(job.Footprint)
-		if err != nil {
-			log.Warn("Error while marshaling job footprint")
-			return err
-		}
-
-		job.EnergyFootprint = make(map[string]float64)
-
-		// Total Job Energy Outside Loop
-		totalEnergy := 0.0
-		for _, fp := range sc.EnergyFootprint {
-			// Always Init Metric Energy Inside Loop
-			metricEnergy := 0.0
-			if i, err := archive.MetricIndex(sc.MetricConfig, fp); err == nil {
-				// Note: For DB data, calculate and save as kWh
-				if sc.MetricConfig[i].Energy == "energy" { // this metric has energy as unit (Joules)
-					log.Warnf("Update EnergyFootprint for Job %d and Metric %s on cluster %s: Set to 'energy' in cluster.json: Not implemented, will return 0.0", job.JobID, job.Cluster, fp)
-					// FIXME: Needs sum as stats type
-				} else if sc.MetricConfig[i].Energy == "power" { // this metric has power as unit (Watt)
-					// Energy: Power (in Watts) * Time (in Seconds)
-					// Unit: (W * (s / 3600)) / 1000 = kWh
-					// Round 2 Digits: round(Energy * 100) / 100
-					// Here: (All-Node Metric Average * Number of Nodes) * (Job Duration in Seconds / 3600) / 1000
-					// Note: Shared Jobs handled correctly since "Node Average" is based on partial resources, while "numNodes" factor is 1
-					rawEnergy := ((repository.LoadJobStat(&job, fp, "avg") * float64(job.NumNodes)) * (float64(job.Duration) / 3600.0)) / 1000.0
-					metricEnergy = math.Round(rawEnergy*100.0) / 100.0
-				}
-			} else {
-				log.Warnf("Error while collecting energy metric %s for job, DB ID '%v', return '0.0'", fp, job.ID)
-			}
-
-			job.EnergyFootprint[fp] = metricEnergy
-			totalEnergy += metricEnergy
-		}
-
-		job.Energy = (math.Round(totalEnergy*100.0) / 100.0)
-		if job.RawEnergyFootprint, err = json.Marshal(job.EnergyFootprint); err != nil {
-			log.Warnf("Error while marshaling energy footprint for job INTO BYTES, DB ID '%v'", job.ID)
-			return err
-		}
-
-		job.RawResources, err = json.Marshal(job.Resources)
-		if err != nil {
-			log.Warn("Error while marshaling job resources")
-			return err
-		}
-		job.RawMetaData, err = json.Marshal(job.MetaData)
-		if err != nil {
-			log.Warn("Error while marshaling job metadata")
-			return err
-		}
-
-		if err = SanityChecks(&job.BaseJob); err != nil {
-			log.Warn("BaseJob SanityChecks failed")
+		if err = SanityChecks(&job); err != nil {
+			cclog.Warn("BaseJob SanityChecks failed")
 			return err
 		}
 
 		if err = archive.GetHandle().ImportJob(&job, &jobData); err != nil {
-			log.Error("Error while importing job")
+			cclog.Error("Error while importing job")
 			return err
 		}
 
 		id, err := r.InsertJob(&job)
 		if err != nil {
-			log.Warn("Error while job db insert")
+			cclog.Warn("Error while job db insert")
 			return err
 		}
 
 		for _, tag := range job.Tags {
 			if err := r.ImportTag(id, tag.Type, tag.Name, tag.Scope); err != nil {
-				log.Error("Error while adding or creating tag on import")
+				cclog.Error("Error while adding or creating tag on import")
 				return err
 			}
 		}
 
-		log.Infof("successfully imported a new job (jobId: %d, cluster: %s, dbid: %d)", job.JobID, job.Cluster, id)
+		cclog.Infof("successfully imported a new job (jobId: %d, cluster: %s, dbid: %d)", job.JobID, job.Cluster, id)
 	}
 	return nil
 }

internal/importer/importer_test.go

@@ -1,5 +1,5 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package importer_test
@@ -16,9 +16,12 @@ import (
 	"github.com/ClusterCockpit/cc-backend/internal/importer"
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
+	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 )
 
+// copyFile copies a file from source path to destination path.
+// Used by tests to set up test fixtures.
 func copyFile(s string, d string) error {
 	r, err := os.Open(s)
 	if err != nil {
@@ -34,17 +37,26 @@ func copyFile(s string, d string) error {
 	return nil
 }
 
+// setup initializes a test environment for importer tests.
+//
+// Creates a temporary directory with:
+//   - A test job archive with cluster configuration
+//   - A SQLite database initialized with schema
+//   - Configuration files loaded
+//
+// Returns a JobRepository instance for test assertions.
 func setup(t *testing.T) *repository.JobRepository {
 	const testconfig = `{
+		"main": {
 	"addr":            "0.0.0.0:8080",
 	"validate": false,
+  "apiAllowedIPs": [
+    "*"
+  ]},
 	"archive": {
 		"kind": "file",
 		"path": "./var/job-archive"
 	},
-    "jwts": {
-        "max-age": "2m"
-    },
 	"clusters": [
 	{
 	   "name": "testcluster",
@@ -75,18 +87,18 @@ func setup(t *testing.T) *repository.JobRepository {
 	 }
 	]}`
 
-	log.Init("info", true)
+	cclog.Init("info", true)
 	tmpdir := t.TempDir()
 
 	jobarchive := filepath.Join(tmpdir, "job-archive")
-	if err := os.Mkdir(jobarchive, 0777); err != nil {
+	if err := os.Mkdir(jobarchive, 0o777); err != nil {
 		t.Fatal(err)
 	}
-	if err := os.WriteFile(filepath.Join(jobarchive, "version.txt"), []byte(fmt.Sprintf("%d", 2)), 0666); err != nil {
+	if err := os.WriteFile(filepath.Join(jobarchive, "version.txt"), fmt.Appendf(nil, "%d", 3), 0o666); err != nil {
 		t.Fatal(err)
 	}
 	fritzArchive := filepath.Join(tmpdir, "job-archive", "fritz")
-	if err := os.Mkdir(fritzArchive, 0777); err != nil {
+	if err := os.Mkdir(fritzArchive, 0o777); err != nil {
 		t.Fatal(err)
 	}
 	if err := copyFile(filepath.Join("testdata", "cluster-fritz.json"),
@@ -101,11 +113,23 @@ func setup(t *testing.T) *repository.JobRepository {
 	}
 
 	cfgFilePath := filepath.Join(tmpdir, "config.json")
-	if err := os.WriteFile(cfgFilePath, []byte(testconfig), 0666); err != nil {
+	if err := os.WriteFile(cfgFilePath, []byte(testconfig), 0o666); err != nil {
 		t.Fatal(err)
 	}
 
-	config.Init(cfgFilePath)
+	ccconf.Init(cfgFilePath)
+
+	// Load and check main configuration
+	if cfg := ccconf.GetPackageConfig("main"); cfg != nil {
+		if clustercfg := ccconf.GetPackageConfig("clusters"); clustercfg != nil {
+			config.Init(cfg, clustercfg)
+		} else {
+			t.Fatal("Cluster configuration must be present")
+		}
+	} else {
+		t.Fatal("Main configuration must be present")
+	}
+
 	archiveCfg := fmt.Sprintf("{\"kind\": \"file\",\"path\": \"%s\"}", jobarchive)
 
 	if err := archive.Init(json.RawMessage(archiveCfg), config.Keys.DisableArchive); err != nil {
@@ -116,6 +140,7 @@ func setup(t *testing.T) *repository.JobRepository {
 	return repository.GetJobRepository()
 }
 
+// Result represents the expected test result for job import verification.
 type Result struct {
 	JobId     int64
 	Cluster   string
@@ -123,6 +148,8 @@ type Result struct {
 	Duration  int32
 }
 
+// readResult reads the expected test result from a golden file.
+// Golden files contain the expected job attributes after import.
 func readResult(t *testing.T, testname string) Result {
 	var r Result
 
@@ -140,6 +167,13 @@ func readResult(t *testing.T, testname string) Result {
 	return r
 }
 
+// TestHandleImportFlag tests the HandleImportFlag function with various job import scenarios.
+//
+// The test uses golden files in testdata/ to verify that jobs are correctly:
+//   - Parsed from metadata and data JSON files
+//   - Enriched with footprints and energy metrics
+//   - Inserted into the database
+//   - Retrievable with correct attributes
 func TestHandleImportFlag(t *testing.T) {
 	r := setup(t)
 
@@ -163,7 +197,7 @@ func TestHandleImportFlag(t *testing.T) {
 			}
 
 			result := readResult(t, testname)
-			job, err := r.Find(&result.JobId, &result.Cluster, &result.StartTime)
+			job, err := r.FindCached(&result.JobId, &result.Cluster, &result.StartTime)
 			if err != nil {
 				t.Fatal(err)
 			}

internal/importer/initDB.go

@@ -1,7 +1,16 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// Package importer provides functionality for importing job data into the ClusterCockpit database.
+//
+// The package supports two primary use cases:
+//  1. Bulk database initialization from archived jobs via InitDB()
+//  2. Individual job import from file pairs via HandleImportFlag()
+//
+// Both operations enrich job metadata by calculating footprints and energy metrics
+// before persisting to the database.
 package importer
 
 import (
@@ -13,8 +22,8 @@ import (
 
 	"github.com/ClusterCockpit/cc-backend/internal/repository"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
 const (
@@ -22,25 +31,38 @@ const (
 	setTagQuery = "INSERT INTO jobtag (job_id, tag_id) VALUES (?, ?)"
 )
 
-// Delete the tables "job", "tag" and "jobtag" from the database and
-// repopulate them using the jobs found in `archive`.
+// InitDB reinitializes the job database from archived job data.
+//
+// This function performs the following operations:
+//  1. Flushes existing job, tag, and jobtag tables
+//  2. Iterates through all jobs in the archive
+//  3. Enriches each job with calculated footprints and energy metrics
+//  4. Inserts jobs and tags into the database in batched transactions
+//
+// Jobs are processed in batches of 100 for optimal performance. The function
+// continues processing even if individual jobs fail, logging errors and
+// returning a summary at the end.
+//
+// Returns an error if database initialization, transaction management, or
+// critical operations fail. Individual job failures are logged but do not
+// stop the overall import process.
 func InitDB() error {
 	r := repository.GetJobRepository()
 	if err := r.Flush(); err != nil {
-		log.Errorf("repository initDB(): %v", err)
+		cclog.Errorf("repository initDB(): %v", err)
 		return err
 	}
 	starttime := time.Now()
-	log.Print("Building job table...")
+	cclog.Print("Building job table...")
 
 	t, err := r.TransactionInit()
 	if err != nil {
-		log.Warn("Error while initializing SQL transactions")
+		cclog.Warn("Error while initializing SQL transactions")
 		return err
 	}
 	tags := make(map[string]int64)
 
-	// Not using log.Print because we want the line to end with `\r` and
+	// Not using cclog.Print because we want the line to end with `\r` and
 	// this function is only ever called when a special command line flag
 	// is passed anyways.
 	fmt.Printf("%d jobs inserted...\r", 0)
@@ -52,150 +74,195 @@ func InitDB() error {
 	for jobContainer := range ar.Iter(false) {
 
 		jobMeta := jobContainer.Meta
+		if jobMeta == nil {
+			cclog.Warn("skipping job with nil metadata")
+			errorOccured++
+			continue
+		}
 
 		// Bundle 100 inserts into one transaction for better performance
 		if i%100 == 0 {
-			r.TransactionCommit(t)
+			if i > 0 {
+				if err := t.Commit(); err != nil {
+					cclog.Errorf("transaction commit error: %v", err)
+					return err
+				}
+				// Start a new transaction for the next batch
+				t, err = r.TransactionInit()
+				if err != nil {
+					cclog.Errorf("transaction init error: %v", err)
+					return err
+				}
+			}
 			fmt.Printf("%d jobs inserted...\r", i)
 		}
 
 		jobMeta.MonitoringStatus = schema.MonitoringStatusArchivingSuccessful
-		job := schema.Job{
-			BaseJob:       jobMeta.BaseJob,
-			StartTime:     time.Unix(jobMeta.StartTime, 0),
-			StartTimeUnix: jobMeta.StartTime,
-		}
 
-		sc, err := archive.GetSubCluster(jobMeta.Cluster, jobMeta.SubCluster)
-		if err != nil {
-			log.Errorf("cannot get subcluster: %s", err.Error())
-			return err
-		}
-
-		job.Footprint = make(map[string]float64)
-
-		for _, fp := range sc.Footprint {
-			statType := "avg"
-
-			if i, err := archive.MetricIndex(sc.MetricConfig, fp); err != nil {
-				statType = sc.MetricConfig[i].Footprint
-			}
-
-			name := fmt.Sprintf("%s_%s", fp, statType)
-
-			job.Footprint[name] = repository.LoadJobStat(jobMeta, fp, statType)
-		}
-
-		job.RawFootprint, err = json.Marshal(job.Footprint)
-		if err != nil {
-			log.Warn("Error while marshaling job footprint")
-			return err
-		}
-
-		job.EnergyFootprint = make(map[string]float64)
-
-		// Total Job Energy Outside Loop
-		totalEnergy := 0.0
-		for _, fp := range sc.EnergyFootprint {
-			// Always Init Metric Energy Inside Loop
-			metricEnergy := 0.0
-			if i, err := archive.MetricIndex(sc.MetricConfig, fp); err == nil {
-				// Note: For DB data, calculate and save as kWh
-				if sc.MetricConfig[i].Energy == "energy" { // this metric has energy as unit (Joules)
-					log.Warnf("Update EnergyFootprint for Job %d and Metric %s on cluster %s: Set to 'energy' in cluster.json: Not implemented, will return 0.0", jobMeta.JobID, jobMeta.Cluster, fp)
-					// FIXME: Needs sum as stats type
-				} else if sc.MetricConfig[i].Energy == "power" { // this metric has power as unit (Watt)
-					// Energy: Power (in Watts) * Time (in Seconds)
-					// Unit: (W * (s / 3600)) / 1000 = kWh
-					// Round 2 Digits: round(Energy * 100) / 100
-					// Here: (All-Node Metric Average * Number of Nodes) * (Job Duration in Seconds / 3600) / 1000
-					// Note: Shared Jobs handled correctly since "Node Average" is based on partial resources, while "numNodes" factor is 1
-					rawEnergy := ((repository.LoadJobStat(jobMeta, fp, "avg") * float64(jobMeta.NumNodes)) * (float64(jobMeta.Duration) / 3600.0)) / 1000.0
-					metricEnergy = math.Round(rawEnergy*100.0) / 100.0
-				}
-			} else {
-				log.Warnf("Error while collecting energy metric %s for job, DB ID '%v', return '0.0'", fp, jobMeta.ID)
-			}
-
-			job.EnergyFootprint[fp] = metricEnergy
-			totalEnergy += metricEnergy
-		}
-
-		job.Energy = (math.Round(totalEnergy*100.0) / 100.0)
-		if job.RawEnergyFootprint, err = json.Marshal(job.EnergyFootprint); err != nil {
-			log.Warnf("Error while marshaling energy footprint for job INTO BYTES, DB ID '%v'", jobMeta.ID)
-			return err
-		}
-
-		job.RawResources, err = json.Marshal(job.Resources)
-		if err != nil {
-			log.Errorf("repository initDB(): %v", err)
+		if err := enrichJobMetadata(jobMeta); err != nil {
+			cclog.Errorf("repository initDB(): %v", err)
 			errorOccured++
 			continue
 		}
 
-		job.RawMetaData, err = json.Marshal(job.MetaData)
-		if err != nil {
-			log.Errorf("repository initDB(): %v", err)
+		if err := SanityChecks(jobMeta); err != nil {
+			cclog.Errorf("repository initDB(): %v", err)
 			errorOccured++
 			continue
 		}
 
-		if err := SanityChecks(&job.BaseJob); err != nil {
-			log.Errorf("repository initDB(): %v", err)
+		id, jobErr := r.TransactionAddNamed(t,
+			repository.NamedJobInsert, jobMeta)
+		if jobErr != nil {
+			cclog.Errorf("repository initDB(): %v", jobErr)
 			errorOccured++
 			continue
 		}
 
-		id, err := r.TransactionAddNamed(t,
-			repository.NamedJobInsert, job)
-		if err != nil {
-			log.Errorf("repository initDB(): %v", err)
-			errorOccured++
-			continue
-		}
+		// Job successfully inserted, increment counter
+		i += 1
 
-		for _, tag := range job.Tags {
+		for _, tag := range jobMeta.Tags {
 			tagstr := tag.Name + ":" + tag.Type
-			tagId, ok := tags[tagstr]
+			tagID, ok := tags[tagstr]
 			if !ok {
-				tagId, err = r.TransactionAdd(t,
+				var err error
+				tagID, err = r.TransactionAdd(t,
 					addTagQuery,
 					tag.Name, tag.Type)
 				if err != nil {
-					log.Errorf("Error adding tag: %v", err)
+					cclog.Errorf("Error adding tag: %v", err)
 					errorOccured++
 					continue
 				}
-				tags[tagstr] = tagId
+				tags[tagstr] = tagID
 			}
 
 			r.TransactionAdd(t,
 				setTagQuery,
-				id, tagId)
-		}
-
-		if err == nil {
-			i += 1
+				id, tagID)
 		}
 	}
 
 	if errorOccured > 0 {
-		log.Warnf("Error in import of %d jobs!", errorOccured)
+		cclog.Warnf("Error in import of %d jobs!", errorOccured)
 	}
 
 	r.TransactionEnd(t)
-	log.Printf("A total of %d jobs have been registered in %.3f seconds.\n", i, time.Since(starttime).Seconds())
+	cclog.Infof("A total of %d jobs have been registered in %.3f seconds.", i, time.Since(starttime).Seconds())
 	return nil
 }
 
-// This function also sets the subcluster if necessary!
-func SanityChecks(job *schema.BaseJob) error {
+// enrichJobMetadata calculates and populates job footprints, energy metrics, and serialized fields.
+//
+// This function performs the following enrichment operations:
+//  1. Calculates job footprint metrics based on the subcluster configuration
+//  2. Computes energy footprint and total energy consumption in kWh
+//  3. Marshals footprints, resources, and metadata into JSON for database storage
+//
+// The function expects the job's MonitoringStatus and SubCluster to be already set.
+// Energy calculations convert power metrics (Watts) to energy (kWh) using the formula:
+//
+//	Energy (kWh) = (Power (W) * Duration (s) / 3600) / 1000
+//
+// Returns an error if subcluster retrieval, metric indexing, or JSON marshaling fails.
+func enrichJobMetadata(job *schema.Job) error {
+	sc, err := archive.GetSubCluster(job.Cluster, job.SubCluster)
+	if err != nil {
+		cclog.Errorf("cannot get subcluster: %s", err.Error())
+		return err
+	}
+
+	job.Footprint = make(map[string]float64)
+
+	for _, fp := range sc.Footprint {
+		statType := "avg"
+
+		if i, err := archive.MetricIndex(sc.MetricConfig, fp); err != nil {
+			statType = sc.MetricConfig[i].Footprint
+		}
+
+		name := fmt.Sprintf("%s_%s", fp, statType)
+
+		job.Footprint[name] = repository.LoadJobStat(job, fp, statType)
+	}
+
+	job.RawFootprint, err = json.Marshal(job.Footprint)
+	if err != nil {
+		cclog.Warn("Error while marshaling job footprint")
+		return err
+	}
+
+	job.EnergyFootprint = make(map[string]float64)
+
+	// Total Job Energy Outside Loop
+	totalEnergy := 0.0
+	for _, fp := range sc.EnergyFootprint {
+		// Always Init Metric Energy Inside Loop
+		metricEnergy := 0.0
+		if i, err := archive.MetricIndex(sc.MetricConfig, fp); err == nil {
+			// Note: For DB data, calculate and save as kWh
+			switch sc.MetricConfig[i].Energy {
+			case "energy": // this metric has energy as unit (Joules)
+				cclog.Warnf("Update EnergyFootprint for Job %d and Metric %s on cluster %s: Set to 'energy' in cluster.json: Not implemented, will return 0.0", job.JobID, job.Cluster, fp)
+				// FIXME: Needs sum as stats type
+			case "power": // this metric has power as unit (Watt)
+				// Energy: Power (in Watts) * Time (in Seconds)
+				// Unit: (W * (s / 3600)) / 1000 = kWh
+				// Round 2 Digits: round(Energy * 100) / 100
+				// Here: (All-Node Metric Average * Number of Nodes) * (Job Duration in Seconds / 3600) / 1000
+				// Note: Shared Jobs handled correctly since "Node Average" is based on partial resources, while "numNodes" factor is 1
+				rawEnergy := ((repository.LoadJobStat(job, fp, "avg") * float64(job.NumNodes)) * (float64(job.Duration) / 3600.0)) / 1000.0
+				metricEnergy = math.Round(rawEnergy*100.0) / 100.0
+			}
+		} else {
+			cclog.Warnf("Error while collecting energy metric %s for job, DB ID '%v', return '0.0'", fp, job.ID)
+		}
+
+		job.EnergyFootprint[fp] = metricEnergy
+		totalEnergy += metricEnergy
+	}
+
+	job.Energy = (math.Round(totalEnergy*100.0) / 100.0)
+	if job.RawEnergyFootprint, err = json.Marshal(job.EnergyFootprint); err != nil {
+		cclog.Warnf("Error while marshaling energy footprint for job INTO BYTES, DB ID '%v'", job.ID)
+		return err
+	}
+
+	job.RawResources, err = json.Marshal(job.Resources)
+	if err != nil {
+		cclog.Warn("Error while marshaling job resources")
+		return err
+	}
+
+	job.RawMetaData, err = json.Marshal(job.MetaData)
+	if err != nil {
+		cclog.Warn("Error while marshaling job metadata")
+		return err
+	}
+
+	return nil
+}
+
+// SanityChecks validates job metadata and ensures cluster/subcluster configuration is valid.
+//
+// This function performs the following validations:
+//  1. Verifies the cluster exists in the archive configuration
+//  2. Assigns and validates the subcluster (may modify job.SubCluster)
+//  3. Validates job state is a recognized value
+//  4. Ensures resources and user fields are populated
+//  5. Validates node counts and hardware thread counts are positive
+//  6. Verifies the number of resources matches the declared node count
+//
+// The function may modify the job's SubCluster field if it needs to be assigned.
+//
+// Returns an error if any validation check fails.
+func SanityChecks(job *schema.Job) error {
 	if c := archive.GetCluster(job.Cluster); c == nil {
 		return fmt.Errorf("no such cluster: %v", job.Cluster)
 	}
 	if err := archive.AssignSubCluster(job); err != nil {
-		log.Warn("Error while assigning subcluster to job")
+		cclog.Warn("Error while assigning subcluster to job")
 		return err
 	}
 	if !job.State.Valid() {
@@ -214,6 +281,14 @@ func SanityChecks(job *schema.BaseJob) error {
 	return nil
 }
 
+// checkJobData normalizes metric units in job data based on average values.
+//
+// NOTE: This function is currently unused and contains incomplete implementation.
+// It was intended to normalize byte and file-related metrics to appropriate SI prefixes,
+// but the normalization logic is commented out. Consider removing or completing this
+// function based on project requirements.
+//
+// TODO: Either implement the metric normalization or remove this dead code.
 func checkJobData(d *schema.JobData) error {
 	for _, scopes := range *d {
 		// var newUnit schema.Unit

internal/importer/normalize.go

@@ -1,5 +1,5 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package importer
@@ -7,13 +7,27 @@ package importer
 import (
 	"math"
 
-	ccunits "github.com/ClusterCockpit/cc-units"
+	ccunits "github.com/ClusterCockpit/cc-lib/ccUnits"
 )
 
+// getNormalizationFactor calculates the scaling factor needed to normalize a value
+// to a more readable range (typically between 1.0 and 1000.0).
+//
+// For values greater than 1000, the function scales down by factors of 1000 (returns negative exponent).
+// For values less than 1.0, the function scales up by factors of 1000 (returns positive exponent).
+//
+// Returns:
+//   - factor: The multiplicative factor to apply (10^(count*scale))
+//   - exponent: The power of 10 representing the adjustment (multiple of 3 for SI prefixes)
 func getNormalizationFactor(v float64) (float64, int) {
 	count := 0
 	scale := -3
 
+	// Prevent infinite loop for zero or negative values
+	if v <= 0.0 {
+		return 1.0, 0
+	}
+
 	if v > 1000.0 {
 		for v > 1000.0 {
 			v *= 1e-3
@@ -29,9 +43,22 @@ func getNormalizationFactor(v float64) (float64, int) {
 	return math.Pow10(count * scale), count * scale
 }
 
+// getExponent calculates the SI prefix exponent from a numeric prefix value.
+//
+// For example:
+//   - Input: 1000.0 (kilo) returns 3
+//   - Input: 1000000.0 (mega) returns 6
+//   - Input: 1000000000.0 (giga) returns 9
+//
+// Returns the exponent representing the power of 10 for the SI prefix.
 func getExponent(p float64) int {
 	count := 0
 
+	// Prevent infinite loop for infinity or NaN values
+	if math.IsInf(p, 0) || math.IsNaN(p) || p <= 0.0 {
+		return 0
+	}
+
 	for p > 1.0 {
 		p = p / 1000.0
 		count++
@@ -40,12 +67,42 @@ func getExponent(p float64) int {
 	return count * 3
 }
 
+// newPrefixFromFactor computes a new SI unit prefix after applying a normalization factor.
+//
+// Given an original prefix and an exponent adjustment, this function calculates
+// the resulting SI prefix. For example, if normalizing from bytes (no prefix) by
+// a factor of 10^9, the result would be the "G" (giga) prefix.
+//
+// Parameters:
+//   - op: The original SI prefix value
+//   - e: The exponent adjustment to apply
+//
+// Returns the new SI prefix after adjustment.
 func newPrefixFromFactor(op ccunits.Prefix, e int) ccunits.Prefix {
 	f := float64(op)
 	exp := math.Pow10(getExponent(f) - e)
 	return ccunits.Prefix(exp)
 }
 
+// Normalize adjusts a metric value and its SI unit prefix to a more readable range.
+//
+// This function is useful for automatically scaling metrics to appropriate units.
+// For example, normalizing 2048 MiB might result in ~2.0 GiB.
+//
+// The function analyzes the average value and determines if a different SI prefix
+// would make the number more human-readable (typically keeping values between 1 and 1000).
+//
+// Parameters:
+//   - avg: The metric value to normalize
+//   - p: The current SI prefix as a string (e.g., "K", "M", "G")
+//
+// Returns:
+//   - factor: The multiplicative factor to apply to convert the value
+//   - newPrefix: The new SI prefix string to use
+//
+// Example:
+//
+//	factor, newPrefix := Normalize(2048.0, "M")  // returns factor for MB->GB conversion, "G"
 func Normalize(avg float64, p string) (float64, string) {
 	f, e := getNormalizationFactor(avg)
 

internal/importer/normalize_test.go

@@ -1,5 +1,5 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package importer
@@ -8,9 +8,11 @@ import (
 	"fmt"
 	"testing"
 
-	ccunits "github.com/ClusterCockpit/cc-units"
+	ccunits "github.com/ClusterCockpit/cc-lib/ccUnits"
 )
 
+// TestNormalizeFactor tests the normalization of large byte values to gigabyte prefix.
+// Verifies that values in the billions are correctly scaled to the "G" (giga) prefix.
 func TestNormalizeFactor(t *testing.T) {
 	// var us string
 	s := []float64{2890031237, 23998994567, 389734042344, 390349424345}
@@ -38,6 +40,8 @@ func TestNormalizeFactor(t *testing.T) {
 	}
 }
 
+// TestNormalizeKeep tests that values already in an appropriate range maintain their prefix.
+// Verifies that when values don't require rescaling, the original "G" prefix is preserved.
 func TestNormalizeKeep(t *testing.T) {
 	s := []float64{3.0, 24.0, 390.0, 391.0}
 

internal/importer/testdata/meta-fritzError.input

@@ -1 +1 @@
-{"jobId":398955,"user":"k106eb10","project":"k106eb","cluster":"fritz","subCluster":"main","partition":"singlenode","arrayJobId":0,"numNodes":1,"numHwthreads":72,"numAcc":0,"exclusive":1,"monitoringStatus":1,"smt":0,"jobState":"completed","duration":260,"walltime":86340,"resources":[{"hostname":"f0720"}],"metaData":{"jobName":"ams_pipeline","jobScript":"#!/bin/bash  -l\n#SBATCH --job-name=ams_pipeline\n#SBATCH --time=23:59:00\n#SBATCH --partition=singlenode\n#SBATCH --ntasks=72\n#SBATCH --hint=multithread\n#SBATCH --chdir=/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11\n#SBATCH --export=NONE\nunset SLURM_EXPORT_ENV\nuss=$(whoami)\nfind /dev/shm/ -user $uss -type f -mmin +30 -delete\ncd \"/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11\"\nams_pipeline pipeline.json \u003e \"/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11/ams_pipeline_job.sh.out\" 2\u003e \"/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11/ams_pipeline_job.sh.err\"\n","slurmInfo":"\nJobId=398955 JobName=ams_pipeline\n   UserId=k106eb10(210387) GroupId=80111\n   Account=k106eb QOS=normal \n   Requeue=False Restarts=0 BatchFlag=True \n   TimeLimit=1439\n   SubmitTime=2023-02-09T14:11:22\n   Partition=singlenode \n   NodeList=f0720\n   NumNodes=1 NumCPUs=72 NumTasks=72 CPUs/Task=1\n   NTasksPerNode:Socket:Core=0:None:None\n   TRES_req=cpu=72,mem=250000M,node=1,billing=72\n   TRES_alloc=cpu=72,node=1,billing=72\n   Command=/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11/ams_pipeline_job.sh\n   WorkDir=/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11\n   StdErr=\n   StdOut=ams_pipeline.o%j\n"},"startTime":1675956725,"statistics":{"clock":{"unit":{"base":"Hz","prefix":"M"},"avg":2335.254,"min":800.418,"max":2734.922},"cpu_load":{"unit":{"base":""},"avg":52.72,"min":34.46,"max":71.91},"cpu_power":{"unit":{"base":"W"},"avg":407.767,"min":93.932,"max":497.636},"cpu_user":{"unit":{"base":""},"avg":63.678,"min":19.872,"max":96.633},"flops_any":{"unit":{"base":"F/s","prefix":"G"},"avg":635.672,"min":0,"max":1332.874},"flops_dp":{"unit":{"base":"F/s","prefix":"G"},"avg":261.006,"min":0,"max":382.294},"flops_sp":{"unit":{"base":"F/s","prefix":"G"},"avg":113.659,"min":0,"max":568.286},"ib_recv":{"unit":{"base":"B/s"},"avg":27981.111,"min":69.4,"max":48084.589},"ib_recv_pkts":{"unit":{"base":"packets/s"},"avg":398.939,"min":0.5,"max":693.817},"ib_xmit":{"unit":{"base":"B/s"},"avg":188.513,"min":39.597,"max":724.568},"ib_xmit_pkts":{"unit":{"base":"packets/s"},"avg":0.867,"min":0.2,"max":2.933},"ipc":{"unit":{"base":"IPC"},"avg":0.944,"min":0.564,"max":1.291},"mem_bw":{"unit":{"base":"B/s","prefix":"G"},"avg":79.565,"min":0.021,"max":116.02},"mem_power":{"unit":{"base":"W"},"avg":24.692,"min":7.883,"max":31.318},"mem_used":{"unit":{"base":"B","prefix":"G"},"avg":22.566,"min":8.225,"max":27.613},"nfs4_read":{"unit":{"base":"B/s","prefix":"M"},"avg":647,"min":0,"max":1946},"nfs4_total":{"unit":{"base":"B/s","prefix":"M"},"avg":6181.6,"min":1270,"max":11411},"nfs4_write":{"unit":{"base":"B/s","prefix":"M"},"avg":22.4,"min":11,"max":29},"vectorization_ratio":{"unit":{"base":"%"},"avg":77.351,"min":0,"max":98.837}}}
+{"jobId":398955,"user":"k106eb10","project":"k106eb","cluster":"fritz","subCluster":"main","partition":"singlenode","arrayJobId":0,"numNodes":1,"numHwthreads":72,"numAcc":0,"shared":"none","monitoringStatus":1,"smt":0,"jobState":"completed","duration":260,"walltime":86340,"resources":[{"hostname":"f0720"}],"metaData":{"jobName":"ams_pipeline","jobScript":"#!/bin/bash  -l\n#SBATCH --job-name=ams_pipeline\n#SBATCH --time=23:59:00\n#SBATCH --partition=singlenode\n#SBATCH --ntasks=72\n#SBATCH --hint=multithread\n#SBATCH --chdir=/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11\n#SBATCH --export=NONE\nunset SLURM_EXPORT_ENV\nuss=$(whoami)\nfind /dev/shm/ -user $uss -type f -mmin +30 -delete\ncd \"/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11\"\nams_pipeline pipeline.json \u003e \"/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11/ams_pipeline_job.sh.out\" 2\u003e \"/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11/ams_pipeline_job.sh.err\"\n","slurmInfo":"\nJobId=398955 JobName=ams_pipeline\n   UserId=k106eb10(210387) GroupId=80111\n   Account=k106eb QOS=normal \n   Requeue=False Restarts=0 BatchFlag=True \n   TimeLimit=1439\n   SubmitTime=2023-02-09T14:11:22\n   Partition=singlenode \n   NodeList=f0720\n   NumNodes=1 NumCPUs=72 NumTasks=72 CPUs/Task=1\n   NTasksPerNode:Socket:Core=0:None:None\n   TRES_req=cpu=72,mem=250000M,node=1,billing=72\n   TRES_alloc=cpu=72,node=1,billing=72\n   Command=/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11/ams_pipeline_job.sh\n   WorkDir=/home/atuin/k106eb/k106eb10/ACE/Ni-Al/DFT/VASP_PBE_500_0.125_0.1_NM/AlNi/binaries/bulk/base-hcp/occ-shaken/hcp16.occ.4.shake.0/cfg/NiAl3NiAl11\n   StdErr=\n   StdOut=ams_pipeline.o%j\n"},"startTime":1675956725,"statistics":{"clock":{"unit":{"base":"Hz","prefix":"M"},"avg":2335.254,"min":800.418,"max":2734.922},"cpu_load":{"unit":{"base":""},"avg":52.72,"min":34.46,"max":71.91},"cpu_power":{"unit":{"base":"W"},"avg":407.767,"min":93.932,"max":497.636},"cpu_user":{"unit":{"base":""},"avg":63.678,"min":19.872,"max":96.633},"flops_any":{"unit":{"base":"F/s","prefix":"G"},"avg":635.672,"min":0,"max":1332.874},"flops_dp":{"unit":{"base":"F/s","prefix":"G"},"avg":261.006,"min":0,"max":382.294},"flops_sp":{"unit":{"base":"F/s","prefix":"G"},"avg":113.659,"min":0,"max":568.286},"ib_recv":{"unit":{"base":"B/s"},"avg":27981.111,"min":69.4,"max":48084.589},"ib_recv_pkts":{"unit":{"base":"packets/s"},"avg":398.939,"min":0.5,"max":693.817},"ib_xmit":{"unit":{"base":"B/s"},"avg":188.513,"min":39.597,"max":724.568},"ib_xmit_pkts":{"unit":{"base":"packets/s"},"avg":0.867,"min":0.2,"max":2.933},"ipc":{"unit":{"base":"IPC"},"avg":0.944,"min":0.564,"max":1.291},"mem_bw":{"unit":{"base":"B/s","prefix":"G"},"avg":79.565,"min":0.021,"max":116.02},"mem_power":{"unit":{"base":"W"},"avg":24.692,"min":7.883,"max":31.318},"mem_used":{"unit":{"base":"B","prefix":"G"},"avg":22.566,"min":8.225,"max":27.613},"nfs4_read":{"unit":{"base":"B/s","prefix":"M"},"avg":647,"min":0,"max":1946},"nfs4_total":{"unit":{"base":"B/s","prefix":"M"},"avg":6181.6,"min":1270,"max":11411},"nfs4_write":{"unit":{"base":"B/s","prefix":"M"},"avg":22.4,"min":11,"max":29},"vectorization_ratio":{"unit":{"base":"%"},"avg":77.351,"min":0,"max":98.837}}}

internal/importer/testdata/meta-fritzMinimal.input

@@ -1 +1 @@
-{"jobId":398764,"user":"k106eb10","project":"k106eb","cluster":"fritz","subCluster":"main","numNodes":1,"exclusive":1,"jobState":"completed","duration":177,"resources":[{"hostname":"f0649"}],"startTime":1675954353,"statistics":{"clock":{"unit":{"base":"Hz","prefix":"M"},"avg":1336.519,"min":801.564,"max":2348.215},"cpu_load":{"unit":{"base":""},"avg":31.64,"min":17.36,"max":45.54},"cpu_power":{"unit":{"base":"W"},"avg":150.018,"min":93.672,"max":261.592},"cpu_user":{"unit":{"base":""},"avg":28.518,"min":0.09,"max":57.343},"flops_any":{"unit":{"base":"F/s","prefix":"G"},"avg":45.012,"min":0,"max":135.037},"flops_dp":{"unit":{"base":"F/s","prefix":"G"},"avg":22.496,"min":0,"max":67.488},"flops_sp":{"unit":{"base":"F/s","prefix":"G"},"avg":0.02,"min":0,"max":0.061},"ib_recv":{"unit":{"base":"B/s"},"avg":14442.82,"min":219.998,"max":42581.368},"ib_recv_pkts":{"unit":{"base":"packets/s"},"avg":201.532,"min":1.25,"max":601.345},"ib_xmit":{"unit":{"base":"B/s"},"avg":282.098,"min":56.2,"max":569.363},"ib_xmit_pkts":{"unit":{"base":"packets/s"},"avg":1.228,"min":0.433,"max":2},"ipc":{"unit":{"base":"IPC"},"avg":0.77,"min":0.564,"max":0.906},"mem_bw":{"unit":{"base":"B/s","prefix":"G"},"avg":4.872,"min":0.025,"max":14.552},"mem_power":{"unit":{"base":"W"},"avg":7.725,"min":6.286,"max":10.556},"mem_used":{"unit":{"base":"B","prefix":"G"},"avg":6.162,"min":6.103,"max":6.226},"nfs4_read":{"unit":{"base":"B/s","prefix":"M"},"avg":1045.333,"min":311,"max":1525},"nfs4_total":{"unit":{"base":"B/s","prefix":"M"},"avg":6430,"min":2796,"max":11518},"nfs4_write":{"unit":{"base":"B/s","prefix":"M"},"avg":24.333,"min":0,"max":38},"vectorization_ratio":{"unit":{"base":"%"},"avg":25.528,"min":0,"max":76.585}}}
+{"jobId":398764,"user":"k106eb10","project":"k106eb","cluster":"fritz","subCluster":"main","numNodes":1,"shared":"none","jobState":"completed","duration":177,"resources":[{"hostname":"f0649"}],"startTime":1675954353,"statistics":{"clock":{"unit":{"base":"Hz","prefix":"M"},"avg":1336.519,"min":801.564,"max":2348.215},"cpu_load":{"unit":{"base":""},"avg":31.64,"min":17.36,"max":45.54},"cpu_power":{"unit":{"base":"W"},"avg":150.018,"min":93.672,"max":261.592},"cpu_user":{"unit":{"base":""},"avg":28.518,"min":0.09,"max":57.343},"flops_any":{"unit":{"base":"F/s","prefix":"G"},"avg":45.012,"min":0,"max":135.037},"flops_dp":{"unit":{"base":"F/s","prefix":"G"},"avg":22.496,"min":0,"max":67.488},"flops_sp":{"unit":{"base":"F/s","prefix":"G"},"avg":0.02,"min":0,"max":0.061},"ib_recv":{"unit":{"base":"B/s"},"avg":14442.82,"min":219.998,"max":42581.368},"ib_recv_pkts":{"unit":{"base":"packets/s"},"avg":201.532,"min":1.25,"max":601.345},"ib_xmit":{"unit":{"base":"B/s"},"avg":282.098,"min":56.2,"max":569.363},"ib_xmit_pkts":{"unit":{"base":"packets/s"},"avg":1.228,"min":0.433,"max":2},"ipc":{"unit":{"base":"IPC"},"avg":0.77,"min":0.564,"max":0.906},"mem_bw":{"unit":{"base":"B/s","prefix":"G"},"avg":4.872,"min":0.025,"max":14.552},"mem_power":{"unit":{"base":"W"},"avg":7.725,"min":6.286,"max":10.556},"mem_used":{"unit":{"base":"B","prefix":"G"},"avg":6.162,"min":6.103,"max":6.226},"nfs4_read":{"unit":{"base":"B/s","prefix":"M"},"avg":1045.333,"min":311,"max":1525},"nfs4_total":{"unit":{"base":"B/s","prefix":"M"},"avg":6430,"min":2796,"max":11518},"nfs4_write":{"unit":{"base":"B/s","prefix":"M"},"avg":24.333,"min":0,"max":38},"vectorization_ratio":{"unit":{"base":"%"},"avg":25.528,"min":0,"max":76.585}}}

internal/memorystore/api.go

@@ -0,0 +1,227 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"errors"
+	"math"
+
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/util"
+)
+
+var (
+	ErrInvalidTimeRange = errors.New("[METRICSTORE]> invalid time range: 'from' must be before 'to'")
+	ErrEmptyCluster     = errors.New("[METRICSTORE]> cluster name cannot be empty")
+)
+
+type APIMetricData struct {
+	Error      *string           `json:"error,omitempty"`
+	Data       schema.FloatArray `json:"data,omitempty"`
+	From       int64             `json:"from"`
+	To         int64             `json:"to"`
+	Resolution int64             `json:"resolution"`
+	Avg        schema.Float      `json:"avg"`
+	Min        schema.Float      `json:"min"`
+	Max        schema.Float      `json:"max"`
+}
+
+type APIQueryRequest struct {
+	Cluster     string     `json:"cluster"`
+	Queries     []APIQuery `json:"queries"`
+	ForAllNodes []string   `json:"for-all-nodes"`
+	From        int64      `json:"from"`
+	To          int64      `json:"to"`
+	WithStats   bool       `json:"with-stats"`
+	WithData    bool       `json:"with-data"`
+	WithPadding bool       `json:"with-padding"`
+}
+
+type APIQueryResponse struct {
+	Queries []APIQuery        `json:"queries,omitempty"`
+	Results [][]APIMetricData `json:"results"`
+}
+
+type APIQuery struct {
+	Type        *string      `json:"type,omitempty"`
+	SubType     *string      `json:"subtype,omitempty"`
+	Metric      string       `json:"metric"`
+	Hostname    string       `json:"host"`
+	Resolution  int64        `json:"resolution"`
+	TypeIds     []string     `json:"type-ids,omitempty"`
+	SubTypeIds  []string     `json:"subtype-ids,omitempty"`
+	ScaleFactor schema.Float `json:"scale-by,omitempty"`
+	Aggregate   bool         `json:"aggreg"`
+}
+
+// TODO: Optimize this, just like the stats endpoint!
+func (data *APIMetricData) AddStats() {
+	n := 0
+	sum, min, max := 0.0, math.MaxFloat64, -math.MaxFloat64
+	for _, x := range data.Data {
+		if x.IsNaN() {
+			continue
+		}
+
+		n += 1
+		sum += float64(x)
+		min = math.Min(min, float64(x))
+		max = math.Max(max, float64(x))
+	}
+
+	if n > 0 {
+		avg := sum / float64(n)
+		data.Avg = schema.Float(avg)
+		data.Min = schema.Float(min)
+		data.Max = schema.Float(max)
+	} else {
+		data.Avg, data.Min, data.Max = schema.NaN, schema.NaN, schema.NaN
+	}
+}
+
+func (data *APIMetricData) ScaleBy(f schema.Float) {
+	if f == 0 || f == 1 {
+		return
+	}
+
+	data.Avg *= f
+	data.Min *= f
+	data.Max *= f
+	for i := 0; i < len(data.Data); i++ {
+		data.Data[i] *= f
+	}
+}
+
+func (data *APIMetricData) PadDataWithNull(ms *MemoryStore, from, to int64, metric string) {
+	minfo, ok := ms.Metrics[metric]
+	if !ok {
+		return
+	}
+
+	if (data.From / minfo.Frequency) > (from / minfo.Frequency) {
+		padfront := int((data.From / minfo.Frequency) - (from / minfo.Frequency))
+		ndata := make([]schema.Float, 0, padfront+len(data.Data))
+		for range padfront {
+			ndata = append(ndata, schema.NaN)
+		}
+		for j := 0; j < len(data.Data); j++ {
+			ndata = append(ndata, data.Data[j])
+		}
+		data.Data = ndata
+	}
+}
+
+func FetchData(req APIQueryRequest) (*APIQueryResponse, error) {
+	if req.From > req.To {
+		return nil, ErrInvalidTimeRange
+	}
+	if req.Cluster == "" && req.ForAllNodes != nil {
+		return nil, ErrEmptyCluster
+	}
+
+	req.WithData = true
+	ms := GetMemoryStore()
+
+	response := APIQueryResponse{
+		Results: make([][]APIMetricData, 0, len(req.Queries)),
+	}
+	if req.ForAllNodes != nil {
+		nodes := ms.ListChildren([]string{req.Cluster})
+		for _, node := range nodes {
+			for _, metric := range req.ForAllNodes {
+				q := APIQuery{
+					Metric:   metric,
+					Hostname: node,
+				}
+				req.Queries = append(req.Queries, q)
+				response.Queries = append(response.Queries, q)
+			}
+		}
+	}
+
+	for _, query := range req.Queries {
+		sels := make([]util.Selector, 0, 1)
+		if query.Aggregate || query.Type == nil {
+			sel := util.Selector{{String: req.Cluster}, {String: query.Hostname}}
+			if query.Type != nil {
+				if len(query.TypeIds) == 1 {
+					sel = append(sel, util.SelectorElement{String: *query.Type + query.TypeIds[0]})
+				} else {
+					ids := make([]string, len(query.TypeIds))
+					for i, id := range query.TypeIds {
+						ids[i] = *query.Type + id
+					}
+					sel = append(sel, util.SelectorElement{Group: ids})
+				}
+
+				if query.SubType != nil {
+					if len(query.SubTypeIds) == 1 {
+						sel = append(sel, util.SelectorElement{String: *query.SubType + query.SubTypeIds[0]})
+					} else {
+						ids := make([]string, len(query.SubTypeIds))
+						for i, id := range query.SubTypeIds {
+							ids[i] = *query.SubType + id
+						}
+						sel = append(sel, util.SelectorElement{Group: ids})
+					}
+				}
+			}
+			sels = append(sels, sel)
+		} else {
+			for _, typeID := range query.TypeIds {
+				if query.SubType != nil {
+					for _, subTypeID := range query.SubTypeIds {
+						sels = append(sels, util.Selector{
+							{String: req.Cluster},
+							{String: query.Hostname},
+							{String: *query.Type + typeID},
+							{String: *query.SubType + subTypeID},
+						})
+					}
+				} else {
+					sels = append(sels, util.Selector{
+						{String: req.Cluster},
+						{String: query.Hostname},
+						{String: *query.Type + typeID},
+					})
+				}
+			}
+		}
+
+		// log.Printf("query: %#v\n", query)
+		// log.Printf("sels: %#v\n", sels)
+		var err error
+		res := make([]APIMetricData, 0, len(sels))
+		for _, sel := range sels {
+			data := APIMetricData{}
+
+			data.Data, data.From, data.To, data.Resolution, err = ms.Read(sel, query.Metric, req.From, req.To, query.Resolution)
+			if err != nil {
+				msg := err.Error()
+				data.Error = &msg
+				res = append(res, data)
+				continue
+			}
+
+			if req.WithStats {
+				data.AddStats()
+			}
+			if query.ScaleFactor != 0 {
+				data.ScaleBy(query.ScaleFactor)
+			}
+			if req.WithPadding {
+				data.PadDataWithNull(ms, req.From, req.To, query.Metric)
+			}
+			if !req.WithData {
+				data.Data = nil
+			}
+			res = append(res, data)
+		}
+		response.Results = append(response.Results, res)
+	}
+
+	return &response, nil
+}

internal/memorystore/archive.go

@@ -0,0 +1,196 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"archive/zip"
+	"bufio"
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"path/filepath"
+	"sync"
+	"sync/atomic"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+)
+
+func Archiving(wg *sync.WaitGroup, ctx context.Context) {
+	go func() {
+		defer wg.Done()
+		d, err := time.ParseDuration(Keys.Archive.Interval)
+		if err != nil {
+			cclog.Fatalf("[METRICSTORE]> error parsing archive interval duration: %v\n", err)
+		}
+		if d <= 0 {
+			return
+		}
+
+		ticker := time.NewTicker(d)
+		defer ticker.Stop()
+
+		for {
+			select {
+			case <-ctx.Done():
+				return
+			case <-ticker.C:
+				t := time.Now().Add(-d)
+				cclog.Infof("[METRICSTORE]> start archiving checkpoints (older than %s)...", t.Format(time.RFC3339))
+				n, err := ArchiveCheckpoints(Keys.Checkpoints.RootDir,
+					Keys.Archive.RootDir, t.Unix(), Keys.Archive.DeleteInstead)
+
+				if err != nil {
+					cclog.Errorf("[METRICSTORE]> archiving failed: %s", err.Error())
+				} else {
+					cclog.Infof("[METRICSTORE]> done: %d files zipped and moved to archive", n)
+				}
+			}
+		}
+	}()
+}
+
+var ErrNoNewArchiveData error = errors.New("all data already archived")
+
+// ZIP all checkpoint files older than `from` together and write them to the `archiveDir`,
+// deleting them from the `checkpointsDir`.
+func ArchiveCheckpoints(checkpointsDir, archiveDir string, from int64, deleteInstead bool) (int, error) {
+	entries1, err := os.ReadDir(checkpointsDir)
+	if err != nil {
+		return 0, err
+	}
+
+	type workItem struct {
+		cdir, adir    string
+		cluster, host string
+	}
+
+	var wg sync.WaitGroup
+	n, errs := int32(0), int32(0)
+	work := make(chan workItem, Keys.NumWorkers)
+
+	wg.Add(Keys.NumWorkers)
+	for worker := 0; worker < Keys.NumWorkers; worker++ {
+		go func() {
+			defer wg.Done()
+			for workItem := range work {
+				m, err := archiveCheckpoints(workItem.cdir, workItem.adir, from, deleteInstead)
+				if err != nil {
+					cclog.Errorf("error while archiving %s/%s: %s", workItem.cluster, workItem.host, err.Error())
+					atomic.AddInt32(&errs, 1)
+				}
+				atomic.AddInt32(&n, int32(m))
+			}
+		}()
+	}
+
+	for _, de1 := range entries1 {
+		entries2, e := os.ReadDir(filepath.Join(checkpointsDir, de1.Name()))
+		if e != nil {
+			err = e
+		}
+
+		for _, de2 := range entries2 {
+			cdir := filepath.Join(checkpointsDir, de1.Name(), de2.Name())
+			adir := filepath.Join(archiveDir, de1.Name(), de2.Name())
+			work <- workItem{
+				adir: adir, cdir: cdir,
+				cluster: de1.Name(), host: de2.Name(),
+			}
+		}
+	}
+
+	close(work)
+	wg.Wait()
+
+	if err != nil {
+		return int(n), err
+	}
+
+	if errs > 0 {
+		return int(n), fmt.Errorf("%d errors happened while archiving (%d successes)", errs, n)
+	}
+	return int(n), nil
+}
+
+// Helper function for `ArchiveCheckpoints`.
+func archiveCheckpoints(dir string, archiveDir string, from int64, deleteInstead bool) (int, error) {
+	entries, err := os.ReadDir(dir)
+	if err != nil {
+		return 0, err
+	}
+
+	extension := Keys.Checkpoints.FileFormat
+	files, err := findFiles(entries, from, extension, false)
+	if err != nil {
+		return 0, err
+	}
+
+	if deleteInstead {
+		n := 0
+		for _, checkpoint := range files {
+			filename := filepath.Join(dir, checkpoint)
+			if err = os.Remove(filename); err != nil {
+				return n, err
+			}
+			n += 1
+		}
+		return n, nil
+	}
+
+	filename := filepath.Join(archiveDir, fmt.Sprintf("%d.zip", from))
+	f, err := os.OpenFile(filename, os.O_CREATE|os.O_WRONLY, CheckpointFilePerms)
+	if err != nil && os.IsNotExist(err) {
+		err = os.MkdirAll(archiveDir, CheckpointDirPerms)
+		if err == nil {
+			f, err = os.OpenFile(filename, os.O_CREATE|os.O_WRONLY, CheckpointFilePerms)
+		}
+	}
+	if err != nil {
+		return 0, err
+	}
+	defer f.Close()
+	bw := bufio.NewWriter(f)
+	defer bw.Flush()
+	zw := zip.NewWriter(bw)
+	defer zw.Close()
+
+	n := 0
+	for _, checkpoint := range files {
+		// Use closure to ensure file is closed immediately after use,
+		// avoiding file descriptor leak from defer in loop
+		err := func() error {
+			filename := filepath.Join(dir, checkpoint)
+			r, err := os.Open(filename)
+			if err != nil {
+				return err
+			}
+			defer r.Close()
+
+			w, err := zw.Create(checkpoint)
+			if err != nil {
+				return err
+			}
+
+			if _, err = io.Copy(w, r); err != nil {
+				return err
+			}
+
+			if err = os.Remove(filename); err != nil {
+				return err
+			}
+			return nil
+		}()
+		if err != nil {
+			return n, err
+		}
+		n += 1
+	}
+
+	return n, nil
+}

internal/memorystore/avroCheckpoint.go

@@ -0,0 +1,477 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"bufio"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"os"
+	"path"
+	"sort"
+	"strconv"
+	"strings"
+	"sync"
+	"sync/atomic"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/linkedin/goavro/v2"
+)
+
+var NumAvroWorkers int = DefaultAvroWorkers
+var startUp bool = true
+
+func (as *AvroStore) ToCheckpoint(dir string, dumpAll bool) (int, error) {
+	levels := make([]*AvroLevel, 0)
+	selectors := make([][]string, 0)
+	as.root.lock.RLock()
+	// Cluster
+	for sel1, l1 := range as.root.children {
+		l1.lock.RLock()
+		// Node
+		for sel2, l2 := range l1.children {
+			l2.lock.RLock()
+			// Frequency
+			for sel3, l3 := range l2.children {
+				levels = append(levels, l3)
+				selectors = append(selectors, []string{sel1, sel2, sel3})
+			}
+			l2.lock.RUnlock()
+		}
+		l1.lock.RUnlock()
+	}
+	as.root.lock.RUnlock()
+
+	type workItem struct {
+		level    *AvroLevel
+		dir      string
+		selector []string
+	}
+
+	n, errs := int32(0), int32(0)
+
+	var wg sync.WaitGroup
+	wg.Add(NumAvroWorkers)
+	work := make(chan workItem, NumAvroWorkers*2)
+	for range NumAvroWorkers {
+		go func() {
+			defer wg.Done()
+
+			for workItem := range work {
+				from := getTimestamp(workItem.dir)
+
+				if err := workItem.level.toCheckpoint(workItem.dir, from, dumpAll); err != nil {
+					if err == ErrNoNewArchiveData {
+						continue
+					}
+
+					cclog.Errorf("error while checkpointing %#v: %s", workItem.selector, err.Error())
+					atomic.AddInt32(&errs, 1)
+				} else {
+					atomic.AddInt32(&n, 1)
+				}
+			}
+		}()
+	}
+
+	for i := range len(levels) {
+		dir := path.Join(dir, path.Join(selectors[i]...))
+		work <- workItem{
+			level:    levels[i],
+			dir:      dir,
+			selector: selectors[i],
+		}
+	}
+
+	close(work)
+	wg.Wait()
+
+	if errs > 0 {
+		return int(n), fmt.Errorf("%d errors happend while creating avro checkpoints (%d successes)", errs, n)
+	}
+
+	startUp = false
+
+	return int(n), nil
+}
+
+// getTimestamp returns the timestamp from the directory name
+func getTimestamp(dir string) int64 {
+	// Extract the resolution and timestamp from the directory name
+	// The existing avro file will be in epoch timestamp format
+	// iterate over all the files in the directory and find the maximum timestamp
+	// and return it
+
+	resolution := path.Base(dir)
+	dir = path.Dir(dir)
+
+	files, err := os.ReadDir(dir)
+	if err != nil {
+		return 0
+	}
+	var maxTS int64 = 0
+
+	if len(files) == 0 {
+		return 0
+	}
+
+	for _, file := range files {
+		if file.IsDir() {
+			continue
+		}
+		name := file.Name()
+
+		if len(name) < 5 || !strings.HasSuffix(name, ".avro") || !strings.HasPrefix(name, resolution+"_") {
+			continue
+		}
+
+		ts, err := strconv.ParseInt(name[strings.Index(name, "_")+1:len(name)-5], 10, 64)
+		if err != nil {
+			fmt.Printf("error while parsing timestamp: %s\n", err.Error())
+			continue
+		}
+
+		if ts > maxTS {
+			maxTS = ts
+		}
+	}
+
+	interval, _ := time.ParseDuration(Keys.Checkpoints.Interval)
+	updateTime := time.Unix(maxTS, 0).Add(interval).Add(time.Duration(CheckpointBufferMinutes-1) * time.Minute).Unix()
+
+	if startUp {
+		return 0
+	}
+
+	if updateTime < time.Now().Unix() {
+		return 0
+	}
+
+	return maxTS
+}
+
+func (l *AvroLevel) toCheckpoint(dir string, from int64, dumpAll bool) error {
+	l.lock.Lock()
+	defer l.lock.Unlock()
+
+	// fmt.Printf("Checkpointing directory: %s\n", dir)
+	// filepath contains the resolution
+	intRes, _ := strconv.Atoi(path.Base(dir))
+
+	// find smallest overall timestamp in l.data map and delete it from l.data
+	minTS := int64(1<<63 - 1)
+	for ts, dat := range l.data {
+		if ts < minTS && len(dat) != 0 {
+			minTS = ts
+		}
+	}
+
+	if from == 0 && minTS != int64(1<<63-1) {
+		from = minTS
+	}
+
+	if from == 0 {
+		return ErrNoNewArchiveData
+	}
+
+	var schema string
+	var codec *goavro.Codec
+	recordList := make([]map[string]any, 0)
+
+	var f *os.File
+
+	filePath := dir + fmt.Sprintf("_%d.avro", from)
+
+	var err error
+
+	fp_, err_ := os.Stat(filePath)
+	if errors.Is(err_, os.ErrNotExist) {
+		err = os.MkdirAll(path.Dir(dir), 0o755)
+		if err != nil {
+			return fmt.Errorf("failed to create directory: %v", err)
+		}
+	} else if fp_.Size() != 0 {
+		f, err = os.Open(filePath)
+		if err != nil {
+			return fmt.Errorf("failed to open existing avro file: %v", err)
+		}
+
+		br := bufio.NewReader(f)
+
+		reader, err := goavro.NewOCFReader(br)
+		if err != nil {
+			return fmt.Errorf("failed to create OCF reader: %v", err)
+		}
+		codec = reader.Codec()
+		schema = codec.Schema()
+
+		f.Close()
+	}
+
+	timeRef := time.Now().Add(time.Duration(-CheckpointBufferMinutes+1) * time.Minute).Unix()
+
+	if dumpAll {
+		timeRef = time.Now().Unix()
+	}
+
+	// Empty values
+	if len(l.data) == 0 {
+		// we checkpoint avro files every 60 seconds
+		repeat := 60 / intRes
+
+		for range repeat {
+			recordList = append(recordList, make(map[string]any))
+		}
+	}
+
+	readFlag := true
+
+	for ts := range l.data {
+		flag := false
+		if ts < timeRef {
+			data := l.data[ts]
+
+			schemaGen, err := generateSchema(data)
+			if err != nil {
+				return err
+			}
+
+			flag, schema, err = compareSchema(schema, schemaGen)
+			if err != nil {
+				return fmt.Errorf("failed to compare read and generated schema: %v", err)
+			}
+			if flag && readFlag && !errors.Is(err_, os.ErrNotExist) {
+
+				f.Close()
+
+				f, err = os.Open(filePath)
+				if err != nil {
+					return fmt.Errorf("failed to open Avro file: %v", err)
+				}
+
+				br := bufio.NewReader(f)
+
+				ocfReader, err := goavro.NewOCFReader(br)
+				if err != nil {
+					return fmt.Errorf("failed to create OCF reader while changing schema: %v", err)
+				}
+
+				for ocfReader.Scan() {
+					record, err := ocfReader.Read()
+					if err != nil {
+						return fmt.Errorf("failed to read record: %v", err)
+					}
+
+					recordList = append(recordList, record.(map[string]any))
+				}
+
+				f.Close()
+
+				err = os.Remove(filePath)
+				if err != nil {
+					return fmt.Errorf("failed to delete file: %v", err)
+				}
+
+				readFlag = false
+			}
+			codec, err = goavro.NewCodec(schema)
+			if err != nil {
+				return fmt.Errorf("failed to create codec after merged schema: %v", err)
+			}
+
+			recordList = append(recordList, generateRecord(data))
+			delete(l.data, ts)
+		}
+	}
+
+	if len(recordList) == 0 {
+		return ErrNoNewArchiveData
+	}
+
+	f, err = os.OpenFile(filePath, os.O_CREATE|os.O_APPEND|os.O_RDWR, 0o644)
+	if err != nil {
+		return fmt.Errorf("failed to append new avro file: %v", err)
+	}
+
+	// fmt.Printf("Codec : %#v\n", codec)
+
+	writer, err := goavro.NewOCFWriter(goavro.OCFConfig{
+		W:               f,
+		Codec:           codec,
+		CompressionName: goavro.CompressionDeflateLabel,
+	})
+	if err != nil {
+		return fmt.Errorf("failed to create OCF writer: %v", err)
+	}
+
+	// Append the new record
+	if err := writer.Append(recordList); err != nil {
+		return fmt.Errorf("failed to append record: %v", err)
+	}
+
+	f.Close()
+
+	return nil
+}
+
+func compareSchema(schemaRead, schemaGen string) (bool, string, error) {
+	var genSchema, readSchema AvroSchema
+
+	if schemaRead == "" {
+		return false, schemaGen, nil
+	}
+
+	// Unmarshal the schema strings into AvroSchema structs
+	if err := json.Unmarshal([]byte(schemaGen), &genSchema); err != nil {
+		return false, "", fmt.Errorf("failed to parse generated schema: %v", err)
+	}
+	if err := json.Unmarshal([]byte(schemaRead), &readSchema); err != nil {
+		return false, "", fmt.Errorf("failed to parse read schema: %v", err)
+	}
+
+	sort.Slice(genSchema.Fields, func(i, j int) bool {
+		return genSchema.Fields[i].Name < genSchema.Fields[j].Name
+	})
+
+	sort.Slice(readSchema.Fields, func(i, j int) bool {
+		return readSchema.Fields[i].Name < readSchema.Fields[j].Name
+	})
+
+	// Check if schemas are identical
+	schemasEqual := true
+	if len(genSchema.Fields) <= len(readSchema.Fields) {
+
+		for i := range genSchema.Fields {
+			if genSchema.Fields[i].Name != readSchema.Fields[i].Name {
+				schemasEqual = false
+				break
+			}
+		}
+
+		// If schemas are identical, return the read schema
+		if schemasEqual {
+			return false, schemaRead, nil
+		}
+	}
+
+	// Create a map to hold unique fields from both schemas
+	fieldMap := make(map[string]AvroField)
+
+	// Add fields from the read schema
+	for _, field := range readSchema.Fields {
+		fieldMap[field.Name] = field
+	}
+
+	// Add or update fields from the generated schema
+	for _, field := range genSchema.Fields {
+		fieldMap[field.Name] = field
+	}
+
+	// Create a union schema by collecting fields from the map
+	var mergedFields []AvroField
+	for _, field := range fieldMap {
+		mergedFields = append(mergedFields, field)
+	}
+
+	// Sort fields by name for consistency
+	sort.Slice(mergedFields, func(i, j int) bool {
+		return mergedFields[i].Name < mergedFields[j].Name
+	})
+
+	// Create the merged schema
+	mergedSchema := AvroSchema{
+		Type:   "record",
+		Name:   genSchema.Name,
+		Fields: mergedFields,
+	}
+
+	// Check if schemas are identical
+	schemasEqual = len(mergedSchema.Fields) == len(readSchema.Fields)
+	if schemasEqual {
+		for i := range mergedSchema.Fields {
+			if mergedSchema.Fields[i].Name != readSchema.Fields[i].Name {
+				schemasEqual = false
+				break
+			}
+		}
+
+		if schemasEqual {
+			return false, schemaRead, nil
+		}
+	}
+
+	// Marshal the merged schema back to JSON
+	mergedSchemaJSON, err := json.Marshal(mergedSchema)
+	if err != nil {
+		return false, "", fmt.Errorf("failed to marshal merged schema: %v", err)
+	}
+
+	return true, string(mergedSchemaJSON), nil
+}
+
+func generateSchema(data map[string]schema.Float) (string, error) {
+	// Define the Avro schema structure
+	schema := map[string]any{
+		"type":   "record",
+		"name":   "DataRecord",
+		"fields": []map[string]any{},
+	}
+
+	fieldTracker := make(map[string]struct{})
+
+	for key := range data {
+		if _, exists := fieldTracker[key]; !exists {
+			key = correctKey(key)
+
+			field := map[string]any{
+				"name":    key,
+				"type":    "double",
+				"default": -1.0,
+			}
+			schema["fields"] = append(schema["fields"].([]map[string]any), field)
+			fieldTracker[key] = struct{}{}
+		}
+	}
+
+	schemaString, err := json.Marshal(schema)
+	if err != nil {
+		return "", fmt.Errorf("failed to marshal schema: %v", err)
+	}
+
+	return string(schemaString), nil
+}
+
+func generateRecord(data map[string]schema.Float) map[string]any {
+	record := make(map[string]any)
+
+	// Iterate through each map in data
+	for key, value := range data {
+		key = correctKey(key)
+
+		// Set the value in the record
+		// avro only accepts basic types
+		record[key] = value.Double()
+	}
+
+	return record
+}
+
+func correctKey(key string) string {
+	key = strings.ReplaceAll(key, "_", "_0x5F_")
+	key = strings.ReplaceAll(key, ":", "_0x3A_")
+	key = strings.ReplaceAll(key, ".", "_0x2E_")
+	return key
+}
+
+func ReplaceKey(key string) string {
+	key = strings.ReplaceAll(key, "_0x2E_", ".")
+	key = strings.ReplaceAll(key, "_0x3A_", ":")
+	key = strings.ReplaceAll(key, "_0x5F_", "_")
+	return key
+}

internal/memorystore/avroHelper.go

@@ -0,0 +1,84 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"context"
+	"slices"
+	"strconv"
+	"sync"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+)
+
+func DataStaging(wg *sync.WaitGroup, ctx context.Context) {
+	// AvroPool is a pool of Avro writers.
+	go func() {
+		if Keys.Checkpoints.FileFormat == "json" {
+			wg.Done() // Mark this goroutine as done
+			return    // Exit the goroutine
+		}
+
+		defer wg.Done()
+
+		var avroLevel *AvroLevel
+		oldSelector := make([]string, 0)
+
+		for {
+			select {
+			case <-ctx.Done():
+				return
+			case val := <-LineProtocolMessages:
+				// Fetch the frequency of the metric from the global configuration
+				freq, err := GetMetricFrequency(val.MetricName)
+				if err != nil {
+					cclog.Errorf("Error fetching metric frequency: %s\n", err)
+					continue
+				}
+
+				metricName := ""
+
+				for _, selectorName := range val.Selector {
+					metricName += selectorName + SelectorDelimiter
+				}
+
+				metricName += val.MetricName
+
+				// Create a new selector for the Avro level
+				// The selector is a slice of strings that represents the path to the
+				// Avro level. It is created by appending the cluster, node, and metric
+				// name to the selector.
+				var selector []string
+				selector = append(selector, val.Cluster, val.Node, strconv.FormatInt(freq, 10))
+
+				if !stringSlicesEqual(oldSelector, selector) {
+					// Get the Avro level for the metric
+					avroLevel = avroStore.root.findAvroLevelOrCreate(selector)
+
+					// If the Avro level is nil, create a new one
+					if avroLevel == nil {
+						cclog.Errorf("Error creating or finding the level with cluster : %s, node : %s, metric : %s\n", val.Cluster, val.Node, val.MetricName)
+					}
+					oldSelector = slices.Clone(selector)
+				}
+
+				avroLevel.addMetric(metricName, val.Value, val.Timestamp, int(freq))
+			}
+		}
+	}()
+}
+
+func stringSlicesEqual(a, b []string) bool {
+	if len(a) != len(b) {
+		return false
+	}
+	for i := range a {
+		if a[i] != b[i] {
+			return false
+		}
+	}
+	return true
+}

internal/memorystore/avroStruct.go

@@ -0,0 +1,167 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"sync"
+
+	"github.com/ClusterCockpit/cc-lib/schema"
+)
+
+var (
+	LineProtocolMessages = make(chan *AvroStruct)
+	// SelectorDelimiter separates hierarchical selector components in metric names for Avro encoding
+	SelectorDelimiter = "_SEL_"
+)
+
+var CheckpointBufferMinutes = DefaultCheckpointBufferMin
+
+type AvroStruct struct {
+	MetricName string
+	Cluster    string
+	Node       string
+	Selector   []string
+	Value      schema.Float
+	Timestamp  int64
+}
+
+type AvroStore struct {
+	root AvroLevel
+}
+
+var avroStore AvroStore
+
+type AvroLevel struct {
+	children map[string]*AvroLevel
+	data     map[int64]map[string]schema.Float
+	lock     sync.RWMutex
+}
+
+type AvroField struct {
+	Name    string `json:"name"`
+	Type    any    `json:"type"`
+	Default any    `json:"default,omitempty"`
+}
+
+type AvroSchema struct {
+	Type   string      `json:"type"`
+	Name   string      `json:"name"`
+	Fields []AvroField `json:"fields"`
+}
+
+func (l *AvroLevel) findAvroLevelOrCreate(selector []string) *AvroLevel {
+	if len(selector) == 0 {
+		return l
+	}
+
+	// Allow concurrent reads:
+	l.lock.RLock()
+	var child *AvroLevel
+	var ok bool
+	if l.children == nil {
+		// Children map needs to be created...
+		l.lock.RUnlock()
+	} else {
+		child, ok := l.children[selector[0]]
+		l.lock.RUnlock()
+		if ok {
+			return child.findAvroLevelOrCreate(selector[1:])
+		}
+	}
+
+	// The level does not exist, take write lock for unique access:
+	l.lock.Lock()
+	// While this thread waited for the write lock, another thread
+	// could have created the child node.
+	if l.children != nil {
+		child, ok = l.children[selector[0]]
+		if ok {
+			l.lock.Unlock()
+			return child.findAvroLevelOrCreate(selector[1:])
+		}
+	}
+
+	child = &AvroLevel{
+		data:     make(map[int64]map[string]schema.Float, 0),
+		children: nil,
+	}
+
+	if l.children != nil {
+		l.children[selector[0]] = child
+	} else {
+		l.children = map[string]*AvroLevel{selector[0]: child}
+	}
+	l.lock.Unlock()
+	return child.findAvroLevelOrCreate(selector[1:])
+}
+
+func (l *AvroLevel) addMetric(metricName string, value schema.Float, timestamp int64, Freq int) {
+	l.lock.Lock()
+	defer l.lock.Unlock()
+
+	KeyCounter := int(CheckpointBufferMinutes * 60 / Freq)
+
+	// Create keys in advance for the given amount of time
+	if len(l.data) != KeyCounter {
+		if len(l.data) == 0 {
+			for i := range KeyCounter {
+				l.data[timestamp+int64(i*Freq)] = make(map[string]schema.Float, 0)
+			}
+		} else {
+			// Get the last timestamp
+			var lastTS int64
+			for ts := range l.data {
+				if ts > lastTS {
+					lastTS = ts
+				}
+			}
+			// Create keys for the next KeyCounter timestamps
+			l.data[lastTS+int64(Freq)] = make(map[string]schema.Float, 0)
+		}
+	}
+
+	closestTS := int64(0)
+	minDiff := int64(Freq) + 1 // Start with diff just outside the valid range
+	found := false
+
+	// Iterate over timestamps and choose the one which is within range.
+	// Since its epoch time, we check if the difference is less than 60 seconds.
+	for ts, dat := range l.data {
+		// Check if timestamp is within range
+		diff := timestamp - ts
+		if diff < -int64(Freq) || diff > int64(Freq) {
+			continue
+		}
+
+		// Metric already present at this timestamp — skip
+		if _, ok := dat[metricName]; ok {
+			continue
+		}
+
+		// Check if this is the closest timestamp so far
+		if Abs(diff) < minDiff {
+			minDiff = Abs(diff)
+			closestTS = ts
+			found = true
+		}
+	}
+
+	if found {
+		l.data[closestTS][metricName] = value
+	}
+}
+
+func GetAvroStore() *AvroStore {
+	return &avroStore
+}
+
+// Abs returns the absolute value of x.
+func Abs(x int64) int64 {
+	if x < 0 {
+		return -x
+	}
+	return x
+}

internal/memorystore/buffer.go

@@ -0,0 +1,190 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"errors"
+	"sync"
+
+	"github.com/ClusterCockpit/cc-lib/schema"
+)
+
+// BufferCap is the default buffer capacity.
+// buffer.data will only ever grow up to its capacity and a new link
+// in the buffer chain will be created if needed so that no copying
+// of data or reallocation needs to happen on writes.
+const BufferCap int = DefaultBufferCapacity
+
+var bufferPool sync.Pool = sync.Pool{
+	New: func() any {
+		return &buffer{
+			data: make([]schema.Float, 0, BufferCap),
+		}
+	},
+}
+
+var (
+	ErrNoData           error = errors.New("[METRICSTORE]> no data for this metric/level")
+	ErrDataDoesNotAlign error = errors.New("[METRICSTORE]> data from lower granularities does not align")
+)
+
+// Each metric on each level has it's own buffer.
+// This is where the actual values go.
+// If `cap(data)` is reached, a new buffer is created and
+// becomes the new head of a buffer list.
+type buffer struct {
+	prev      *buffer
+	next      *buffer
+	data      []schema.Float
+	frequency int64
+	start     int64
+	archived  bool
+	closed    bool
+}
+
+func newBuffer(ts, freq int64) *buffer {
+	b := bufferPool.Get().(*buffer)
+	b.frequency = freq
+	b.start = ts - (freq / 2)
+	b.prev = nil
+	b.next = nil
+	b.archived = false
+	b.closed = false
+	b.data = b.data[:0]
+	return b
+}
+
+// If a new buffer was created, the new head is returnd.
+// Otherwise, the existing buffer is returnd.
+// Normaly, only "newer" data should be written, but if the value would
+// end up in the same buffer anyways it is allowed.
+func (b *buffer) write(ts int64, value schema.Float) (*buffer, error) {
+	if ts < b.start {
+		return nil, errors.New("[METRICSTORE]> cannot write value to buffer from past")
+	}
+
+	// idx := int((ts - b.start + (b.frequency / 3)) / b.frequency)
+	idx := int((ts - b.start) / b.frequency)
+	if idx >= cap(b.data) {
+		newbuf := newBuffer(ts, b.frequency)
+		newbuf.prev = b
+		b.next = newbuf
+		b = newbuf
+		idx = 0
+	}
+
+	// Overwriting value or writing value from past
+	if idx < len(b.data) {
+		b.data[idx] = value
+		return b, nil
+	}
+
+	// Fill up unwritten slots with NaN
+	for i := len(b.data); i < idx; i++ {
+		b.data = append(b.data, schema.NaN)
+	}
+
+	b.data = append(b.data, value)
+	return b, nil
+}
+
+func (b *buffer) end() int64 {
+	return b.firstWrite() + int64(len(b.data))*b.frequency
+}
+
+func (b *buffer) firstWrite() int64 {
+	return b.start + (b.frequency / 2)
+}
+
+// Return all known values from `from` to `to`. Gaps of information are represented as NaN.
+// Simple linear interpolation is done between the two neighboring cells if possible.
+// If values at the start or end are missing, instead of NaN values, the second and thrid
+// return values contain the actual `from`/`to`.
+// This function goes back the buffer chain if `from` is older than the currents buffer start.
+// The loaded values are added to `data` and `data` is returned, possibly with a shorter length.
+// If `data` is not long enough to hold all values, this function will panic!
+func (b *buffer) read(from, to int64, data []schema.Float) ([]schema.Float, int64, int64, error) {
+	if from < b.firstWrite() {
+		if b.prev != nil {
+			return b.prev.read(from, to, data)
+		}
+		from = b.firstWrite()
+	}
+
+	i := 0
+	t := from
+	for ; t < to; t += b.frequency {
+		idx := int((t - b.start) / b.frequency)
+		if idx >= cap(b.data) {
+			if b.next == nil {
+				break
+			}
+			b = b.next
+			idx = 0
+		}
+
+		if idx >= len(b.data) {
+			if b.next == nil || to <= b.next.start {
+				break
+			}
+			data[i] += schema.NaN
+		} else if t < b.start {
+			data[i] += schema.NaN
+		} else {
+			data[i] += b.data[idx]
+		}
+		i++
+	}
+
+	return data[:i], from, t, nil
+}
+
+// Returns true if this buffer needs to be freed.
+func (b *buffer) free(t int64) (delme bool, n int) {
+	if b.prev != nil {
+		delme, m := b.prev.free(t)
+		n += m
+		if delme {
+			b.prev.next = nil
+			if cap(b.prev.data) == BufferCap {
+				bufferPool.Put(b.prev)
+			}
+			b.prev = nil
+		}
+	}
+
+	end := b.end()
+	if end < t {
+		return true, n + 1
+	}
+
+	return false, n
+}
+
+// Call `callback` on every buffer that contains data in the range from `from` to `to`.
+func (b *buffer) iterFromTo(from, to int64, callback func(b *buffer) error) error {
+	if b == nil {
+		return nil
+	}
+
+	if err := b.prev.iterFromTo(from, to, callback); err != nil {
+		return err
+	}
+
+	if from <= b.end() && b.start <= to {
+		return callback(b)
+	}
+
+	return nil
+}
+
+func (b *buffer) count() int64 {
+	res := int64(len(b.data))
+	if b.prev != nil {
+		res += b.prev.count()
+	}
+	return res
+}

internal/memorystore/checkpoint.go

@@ -0,0 +1,761 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"bufio"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io/fs"
+	"os"
+	"path"
+	"path/filepath"
+	"runtime"
+	"sort"
+	"strconv"
+	"strings"
+	"sync"
+	"sync/atomic"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/linkedin/goavro/v2"
+)
+
+const (
+	CheckpointFilePerms = 0o644
+	CheckpointDirPerms  = 0o755
+	GCTriggerInterval   = DefaultGCTriggerInterval
+)
+
+// Whenever changed, update MarshalJSON as well!
+type CheckpointMetrics struct {
+	Data      []schema.Float `json:"data"`
+	Frequency int64          `json:"frequency"`
+	Start     int64          `json:"start"`
+}
+
+type CheckpointFile struct {
+	Metrics  map[string]*CheckpointMetrics `json:"metrics"`
+	Children map[string]*CheckpointFile    `json:"children"`
+	From     int64                         `json:"from"`
+	To       int64                         `json:"to"`
+}
+
+var lastCheckpoint time.Time
+
+func Checkpointing(wg *sync.WaitGroup, ctx context.Context) {
+	lastCheckpoint = time.Now()
+
+	if Keys.Checkpoints.FileFormat == "json" {
+		ms := GetMemoryStore()
+
+		go func() {
+			defer wg.Done()
+			d, err := time.ParseDuration(Keys.Checkpoints.Interval)
+			if err != nil {
+				cclog.Fatal(err)
+			}
+			if d <= 0 {
+				return
+			}
+
+			ticker := time.NewTicker(d)
+			defer ticker.Stop()
+
+			for {
+				select {
+				case <-ctx.Done():
+					return
+				case <-ticker.C:
+					cclog.Infof("[METRICSTORE]> start checkpointing (starting at %s)...", lastCheckpoint.Format(time.RFC3339))
+					now := time.Now()
+					n, err := ms.ToCheckpoint(Keys.Checkpoints.RootDir,
+						lastCheckpoint.Unix(), now.Unix())
+					if err != nil {
+						cclog.Errorf("[METRICSTORE]> checkpointing failed: %s", err.Error())
+					} else {
+						cclog.Infof("[METRICSTORE]> done: %d checkpoint files created", n)
+						lastCheckpoint = now
+					}
+				}
+			}
+		}()
+	} else {
+		go func() {
+			defer wg.Done()
+
+			select {
+			case <-ctx.Done():
+				return
+			case <-time.After(time.Duration(CheckpointBufferMinutes) * time.Minute):
+				GetAvroStore().ToCheckpoint(Keys.Checkpoints.RootDir, false)
+			}
+
+			ticker := time.NewTicker(DefaultAvroCheckpointInterval)
+			defer ticker.Stop()
+
+			for {
+				select {
+				case <-ctx.Done():
+					return
+				case <-ticker.C:
+					GetAvroStore().ToCheckpoint(Keys.Checkpoints.RootDir, false)
+				}
+			}
+		}()
+	}
+}
+
+// As `Float` implements a custom MarshalJSON() function,
+// serializing an array of such types has more overhead
+// than one would assume (because of extra allocations, interfaces and so on).
+func (cm *CheckpointMetrics) MarshalJSON() ([]byte, error) {
+	buf := make([]byte, 0, 128+len(cm.Data)*8)
+	buf = append(buf, `{"frequency":`...)
+	buf = strconv.AppendInt(buf, cm.Frequency, 10)
+	buf = append(buf, `,"start":`...)
+	buf = strconv.AppendInt(buf, cm.Start, 10)
+	buf = append(buf, `,"data":[`...)
+	for i, x := range cm.Data {
+		if i != 0 {
+			buf = append(buf, ',')
+		}
+		if x.IsNaN() {
+			buf = append(buf, `null`...)
+		} else {
+			buf = strconv.AppendFloat(buf, float64(x), 'f', 1, 32)
+		}
+	}
+	buf = append(buf, `]}`...)
+	return buf, nil
+}
+
+// Metrics stored at the lowest 2 levels are not stored away (root and cluster)!
+// On a per-host basis a new JSON file is created. I have no idea if this will scale.
+// The good thing: Only a host at a time is locked, so this function can run
+// in parallel to writes/reads.
+func (m *MemoryStore) ToCheckpoint(dir string, from, to int64) (int, error) {
+	levels := make([]*Level, 0)
+	selectors := make([][]string, 0)
+	m.root.lock.RLock()
+	for sel1, l1 := range m.root.children {
+		l1.lock.RLock()
+		for sel2, l2 := range l1.children {
+			levels = append(levels, l2)
+			selectors = append(selectors, []string{sel1, sel2})
+		}
+		l1.lock.RUnlock()
+	}
+	m.root.lock.RUnlock()
+
+	type workItem struct {
+		level    *Level
+		dir      string
+		selector []string
+	}
+
+	n, errs := int32(0), int32(0)
+
+	var wg sync.WaitGroup
+	wg.Add(Keys.NumWorkers)
+	work := make(chan workItem, Keys.NumWorkers*2)
+	for worker := 0; worker < Keys.NumWorkers; worker++ {
+		go func() {
+			defer wg.Done()
+
+			for workItem := range work {
+				if err := workItem.level.toCheckpoint(workItem.dir, from, to, m); err != nil {
+					if err == ErrNoNewArchiveData {
+						continue
+					}
+
+					cclog.Errorf("[METRICSTORE]> error while checkpointing %#v: %s", workItem.selector, err.Error())
+					atomic.AddInt32(&errs, 1)
+				} else {
+					atomic.AddInt32(&n, 1)
+				}
+			}
+		}()
+	}
+
+	for i := 0; i < len(levels); i++ {
+		dir := path.Join(dir, path.Join(selectors[i]...))
+		work <- workItem{
+			level:    levels[i],
+			dir:      dir,
+			selector: selectors[i],
+		}
+	}
+
+	close(work)
+	wg.Wait()
+
+	if errs > 0 {
+		return int(n), fmt.Errorf("[METRICSTORE]> %d errors happened while creating checkpoints (%d successes)", errs, n)
+	}
+	return int(n), nil
+}
+
+func (l *Level) toCheckpointFile(from, to int64, m *MemoryStore) (*CheckpointFile, error) {
+	l.lock.RLock()
+	defer l.lock.RUnlock()
+
+	retval := &CheckpointFile{
+		From:     from,
+		To:       to,
+		Metrics:  make(map[string]*CheckpointMetrics),
+		Children: make(map[string]*CheckpointFile),
+	}
+
+	for metric, minfo := range m.Metrics {
+		b := l.metrics[minfo.offset]
+		if b == nil {
+			continue
+		}
+
+		allArchived := true
+		b.iterFromTo(from, to, func(b *buffer) error {
+			if !b.archived {
+				allArchived = false
+			}
+			return nil
+		})
+
+		if allArchived {
+			continue
+		}
+
+		data := make([]schema.Float, (to-from)/b.frequency+1)
+		data, start, end, err := b.read(from, to, data)
+		if err != nil {
+			return nil, err
+		}
+
+		for i := int((end - start) / b.frequency); i < len(data); i++ {
+			data[i] = schema.NaN
+		}
+
+		retval.Metrics[metric] = &CheckpointMetrics{
+			Frequency: b.frequency,
+			Start:     start,
+			Data:      data,
+		}
+	}
+
+	for name, child := range l.children {
+		val, err := child.toCheckpointFile(from, to, m)
+		if err != nil {
+			return nil, err
+		}
+
+		if val != nil {
+			retval.Children[name] = val
+		}
+	}
+
+	if len(retval.Children) == 0 && len(retval.Metrics) == 0 {
+		return nil, nil
+	}
+
+	return retval, nil
+}
+
+func (l *Level) toCheckpoint(dir string, from, to int64, m *MemoryStore) error {
+	cf, err := l.toCheckpointFile(from, to, m)
+	if err != nil {
+		return err
+	}
+
+	if cf == nil {
+		return ErrNoNewArchiveData
+	}
+
+	filepath := path.Join(dir, fmt.Sprintf("%d.json", from))
+	f, err := os.OpenFile(filepath, os.O_CREATE|os.O_WRONLY, CheckpointFilePerms)
+	if err != nil && os.IsNotExist(err) {
+		err = os.MkdirAll(dir, CheckpointDirPerms)
+		if err == nil {
+			f, err = os.OpenFile(filepath, os.O_CREATE|os.O_WRONLY, CheckpointFilePerms)
+		}
+	}
+	if err != nil {
+		return err
+	}
+	defer f.Close()
+
+	bw := bufio.NewWriter(f)
+	if err = json.NewEncoder(bw).Encode(cf); err != nil {
+		return err
+	}
+
+	return bw.Flush()
+}
+
+func (m *MemoryStore) FromCheckpoint(dir string, from int64, extension string) (int, error) {
+	var wg sync.WaitGroup
+	work := make(chan [2]string, Keys.NumWorkers)
+	n, errs := int32(0), int32(0)
+
+	wg.Add(Keys.NumWorkers)
+	for worker := 0; worker < Keys.NumWorkers; worker++ {
+		go func() {
+			defer wg.Done()
+			for host := range work {
+				lvl := m.root.findLevelOrCreate(host[:], len(m.Metrics))
+				nn, err := lvl.fromCheckpoint(m, filepath.Join(dir, host[0], host[1]), from, extension)
+				if err != nil {
+					cclog.Errorf("[METRICSTORE]> error while loading checkpoints for %s/%s: %s", host[0], host[1], err.Error())
+					atomic.AddInt32(&errs, 1)
+				}
+				atomic.AddInt32(&n, int32(nn))
+			}
+		}()
+	}
+
+	i := 0
+	clustersDir, err := os.ReadDir(dir)
+	for _, clusterDir := range clustersDir {
+		if !clusterDir.IsDir() {
+			err = errors.New("[METRICSTORE]> expected only directories at first level of checkpoints/ directory")
+			goto done
+		}
+
+		hostsDir, e := os.ReadDir(filepath.Join(dir, clusterDir.Name()))
+		if e != nil {
+			err = e
+			goto done
+		}
+
+		for _, hostDir := range hostsDir {
+			if !hostDir.IsDir() {
+				err = errors.New("[METRICSTORE]> expected only directories at second level of checkpoints/ directory")
+				goto done
+			}
+
+			i++
+			if i%Keys.NumWorkers == 0 && i > GCTriggerInterval {
+				// Forcing garbage collection runs here regulary during the loading of checkpoints
+				// will decrease the total heap size after loading everything back to memory is done.
+				// While loading data, the heap will grow fast, so the GC target size will double
+				// almost always. By forcing GCs here, we can keep it growing more slowly so that
+				// at the end, less memory is wasted.
+				runtime.GC()
+			}
+
+			work <- [2]string{clusterDir.Name(), hostDir.Name()}
+		}
+	}
+done:
+	close(work)
+	wg.Wait()
+
+	if err != nil {
+		return int(n), err
+	}
+
+	if errs > 0 {
+		return int(n), fmt.Errorf("[METRICSTORE]> %d errors happened while creating checkpoints (%d successes)", errs, n)
+	}
+	return int(n), nil
+}
+
+// Metrics stored at the lowest 2 levels are not loaded (root and cluster)!
+// This function can only be called once and before the very first write or read.
+// Different host's data is loaded to memory in parallel.
+func (m *MemoryStore) FromCheckpointFiles(dir string, from int64) (int, error) {
+	if _, err := os.Stat(dir); os.IsNotExist(err) {
+		// The directory does not exist, so create it using os.MkdirAll()
+		err := os.MkdirAll(dir, CheckpointDirPerms) // CheckpointDirPerms sets the permissions for the directory
+		if err != nil {
+			cclog.Fatalf("[METRICSTORE]> Error creating directory: %#v\n", err)
+		}
+		cclog.Debugf("[METRICSTORE]> %#v Directory created successfully", dir)
+	}
+
+	// Config read (replace with your actual config read)
+	fileFormat := Keys.Checkpoints.FileFormat
+	if fileFormat == "" {
+		fileFormat = "avro"
+	}
+
+	// Map to easily get the fallback format
+	oppositeFormat := map[string]string{
+		"json": "avro",
+		"avro": "json",
+	}
+
+	// First, attempt to load the specified format
+	if found, err := checkFilesWithExtension(dir, fileFormat); err != nil {
+		return 0, fmt.Errorf("[METRICSTORE]> error checking files with extension: %v", err)
+	} else if found {
+		cclog.Infof("[METRICSTORE]> Loading %s files because fileformat is %s", fileFormat, fileFormat)
+		return m.FromCheckpoint(dir, from, fileFormat)
+	}
+
+	// If not found, attempt the opposite format
+	altFormat := oppositeFormat[fileFormat]
+	if found, err := checkFilesWithExtension(dir, altFormat); err != nil {
+		return 0, fmt.Errorf("[METRICSTORE]> error checking files with extension: %v", err)
+	} else if found {
+		cclog.Infof("[METRICSTORE]> Loading %s files but fileformat is %s", altFormat, fileFormat)
+		return m.FromCheckpoint(dir, from, altFormat)
+	}
+
+	cclog.Print("[METRICSTORE]> No valid checkpoint files found in the directory")
+	return 0, nil
+}
+
+func checkFilesWithExtension(dir string, extension string) (bool, error) {
+	found := false
+
+	err := filepath.Walk(dir, func(path string, info os.FileInfo, err error) error {
+		if err != nil {
+			return fmt.Errorf("[METRICSTORE]> error accessing path %s: %v", path, err)
+		}
+		if !info.IsDir() && filepath.Ext(info.Name()) == "."+extension {
+			found = true
+			return nil
+		}
+		return nil
+	})
+	if err != nil {
+		return false, fmt.Errorf("[METRICSTORE]> error walking through directories: %s", err)
+	}
+
+	return found, nil
+}
+
+func (l *Level) loadAvroFile(m *MemoryStore, f *os.File, from int64) error {
+	br := bufio.NewReader(f)
+
+	fileName := f.Name()[strings.LastIndex(f.Name(), "/")+1:]
+	resolution, err := strconv.ParseInt(fileName[0:strings.Index(fileName, "_")], 10, 64)
+	if err != nil {
+		return fmt.Errorf("[METRICSTORE]> error while reading avro file (resolution parsing) : %s", err)
+	}
+
+	fromTimestamp, err := strconv.ParseInt(fileName[strings.Index(fileName, "_")+1:len(fileName)-5], 10, 64)
+
+	// Same logic according to lineprotocol
+	fromTimestamp -= (resolution / 2)
+
+	if err != nil {
+		return fmt.Errorf("[METRICSTORE]> error converting timestamp from the avro file : %s", err)
+	}
+
+	// fmt.Printf("File : %s with resolution : %d\n", fileName, resolution)
+
+	var recordCounter int64 = 0
+
+	// Create a new OCF reader from the buffered reader
+	ocfReader, err := goavro.NewOCFReader(br)
+	if err != nil {
+		return fmt.Errorf("[METRICSTORE]> error creating OCF reader: %w", err)
+	}
+
+	metricsData := make(map[string]schema.FloatArray)
+
+	for ocfReader.Scan() {
+		datum, err := ocfReader.Read()
+		if err != nil {
+			return fmt.Errorf("[METRICSTORE]> error while reading avro file : %s", err)
+		}
+
+		record, ok := datum.(map[string]any)
+		if !ok {
+			return fmt.Errorf("[METRICSTORE]> failed to assert datum as map[string]interface{}")
+		}
+
+		for key, value := range record {
+			metricsData[key] = append(metricsData[key], schema.ConvertToFloat(value.(float64)))
+		}
+
+		recordCounter += 1
+	}
+
+	to := (fromTimestamp + (recordCounter / (60 / resolution) * 60))
+	if to < from {
+		return nil
+	}
+
+	for key, floatArray := range metricsData {
+		metricName := ReplaceKey(key)
+
+		if strings.Contains(metricName, SelectorDelimiter) {
+			subString := strings.Split(metricName, SelectorDelimiter)
+
+			lvl := l
+
+			for i := 0; i < len(subString)-1; i++ {
+
+				sel := subString[i]
+
+				if lvl.children == nil {
+					lvl.children = make(map[string]*Level)
+				}
+
+				child, ok := lvl.children[sel]
+				if !ok {
+					child = &Level{
+						metrics:  make([]*buffer, len(m.Metrics)),
+						children: nil,
+					}
+					lvl.children[sel] = child
+				}
+				lvl = child
+			}
+
+			leafMetricName := subString[len(subString)-1]
+			err = lvl.createBuffer(m, leafMetricName, floatArray, fromTimestamp, resolution)
+			if err != nil {
+				return fmt.Errorf("[METRICSTORE]> error while creating buffers from avroReader : %s", err)
+			}
+		} else {
+			err = l.createBuffer(m, metricName, floatArray, fromTimestamp, resolution)
+			if err != nil {
+				return fmt.Errorf("[METRICSTORE]> error while creating buffers from avroReader : %s", err)
+			}
+		}
+
+	}
+
+	return nil
+}
+
+func (l *Level) createBuffer(m *MemoryStore, metricName string, floatArray schema.FloatArray, from int64, resolution int64) error {
+	n := len(floatArray)
+	b := &buffer{
+		frequency: resolution,
+		start:     from,
+		data:      floatArray[0:n:n],
+		prev:      nil,
+		next:      nil,
+		archived:  true,
+	}
+
+	minfo, ok := m.Metrics[metricName]
+	if !ok {
+		return nil
+	}
+
+	prev := l.metrics[minfo.offset]
+	if prev == nil {
+		l.metrics[minfo.offset] = b
+	} else {
+		if prev.start > b.start {
+			return fmt.Errorf("[METRICSTORE]> buffer start time %d is before previous buffer start %d", b.start, prev.start)
+		}
+
+		b.prev = prev
+		prev.next = b
+
+		missingCount := ((int(b.start) - int(prev.start)) - len(prev.data)*int(b.frequency))
+		if missingCount > 0 {
+			missingCount /= int(b.frequency)
+
+			for range missingCount {
+				prev.data = append(prev.data, schema.NaN)
+			}
+
+			prev.data = prev.data[0:len(prev.data):len(prev.data)]
+		}
+	}
+	l.metrics[minfo.offset] = b
+
+	return nil
+}
+
+func (l *Level) loadJSONFile(m *MemoryStore, f *os.File, from int64) error {
+	br := bufio.NewReader(f)
+	cf := &CheckpointFile{}
+	if err := json.NewDecoder(br).Decode(cf); err != nil {
+		return err
+	}
+
+	if cf.To != 0 && cf.To < from {
+		return nil
+	}
+
+	if err := l.loadFile(cf, m); err != nil {
+		return err
+	}
+
+	return nil
+}
+
+func (l *Level) loadFile(cf *CheckpointFile, m *MemoryStore) error {
+	for name, metric := range cf.Metrics {
+		n := len(metric.Data)
+		b := &buffer{
+			frequency: metric.Frequency,
+			start:     metric.Start,
+			data:      metric.Data[0:n:n],
+			prev:      nil,
+			next:      nil,
+			archived:  true,
+		}
+
+		minfo, ok := m.Metrics[name]
+		if !ok {
+			continue
+		}
+
+		prev := l.metrics[minfo.offset]
+		if prev == nil {
+			l.metrics[minfo.offset] = b
+		} else {
+			if prev.start > b.start {
+				return fmt.Errorf("[METRICSTORE]> buffer start time %d is before previous buffer start %d", b.start, prev.start)
+			}
+
+			b.prev = prev
+			prev.next = b
+		}
+		l.metrics[minfo.offset] = b
+	}
+
+	if len(cf.Children) > 0 && l.children == nil {
+		l.children = make(map[string]*Level)
+	}
+
+	for sel, childCf := range cf.Children {
+		child, ok := l.children[sel]
+		if !ok {
+			child = &Level{
+				metrics:  make([]*buffer, len(m.Metrics)),
+				children: nil,
+			}
+			l.children[sel] = child
+		}
+
+		if err := child.loadFile(childCf, m); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+func (l *Level) fromCheckpoint(m *MemoryStore, dir string, from int64, extension string) (int, error) {
+	direntries, err := os.ReadDir(dir)
+	if err != nil {
+		if os.IsNotExist(err) {
+			return 0, nil
+		}
+
+		return 0, err
+	}
+
+	allFiles := make([]fs.DirEntry, 0)
+	filesLoaded := 0
+	for _, e := range direntries {
+		if e.IsDir() {
+			child := &Level{
+				metrics:  make([]*buffer, len(m.Metrics)),
+				children: make(map[string]*Level),
+			}
+
+			files, err := child.fromCheckpoint(m, path.Join(dir, e.Name()), from, extension)
+			filesLoaded += files
+			if err != nil {
+				return filesLoaded, err
+			}
+
+			l.children[e.Name()] = child
+		} else if strings.HasSuffix(e.Name(), "."+extension) {
+			allFiles = append(allFiles, e)
+		} else {
+			continue
+		}
+	}
+
+	files, err := findFiles(allFiles, from, extension, true)
+	if err != nil {
+		return filesLoaded, err
+	}
+
+	loaders := map[string]func(*MemoryStore, *os.File, int64) error{
+		"json": l.loadJSONFile,
+		"avro": l.loadAvroFile,
+	}
+
+	loader := loaders[extension]
+
+	for _, filename := range files {
+		// Use a closure to ensure file is closed immediately after use
+		err := func() error {
+			f, err := os.Open(path.Join(dir, filename))
+			if err != nil {
+				return err
+			}
+			defer f.Close()
+
+			return loader(m, f, from)
+		}()
+		if err != nil {
+			return filesLoaded, err
+		}
+
+		filesLoaded += 1
+	}
+
+	return filesLoaded, nil
+}
+
+// This will probably get very slow over time!
+// A solution could be some sort of an index file in which all other files
+// and the timespan they contain is listed.
+func findFiles(direntries []fs.DirEntry, t int64, extension string, findMoreRecentFiles bool) ([]string, error) {
+	nums := map[string]int64{}
+	for _, e := range direntries {
+		if !strings.HasSuffix(e.Name(), "."+extension) {
+			continue
+		}
+
+		ts, err := strconv.ParseInt(e.Name()[strings.Index(e.Name(), "_")+1:len(e.Name())-5], 10, 64)
+		if err != nil {
+			return nil, err
+		}
+		nums[e.Name()] = ts
+	}
+
+	sort.Slice(direntries, func(i, j int) bool {
+		a, b := direntries[i], direntries[j]
+		return nums[a.Name()] < nums[b.Name()]
+	})
+
+	filenames := make([]string, 0)
+	for i := range direntries {
+		e := direntries[i]
+		ts1 := nums[e.Name()]
+
+		if findMoreRecentFiles && t <= ts1 {
+			filenames = append(filenames, e.Name())
+		}
+		if i == len(direntries)-1 {
+			continue
+		}
+
+		enext := direntries[i+1]
+		ts2 := nums[enext.Name()]
+
+		if findMoreRecentFiles {
+			if ts1 < t && t < ts2 {
+				filenames = append(filenames, e.Name())
+			}
+		} else {
+			if ts2 < t {
+				filenames = append(filenames, e.Name())
+			}
+		}
+	}
+
+	return filenames, nil
+}

internal/memorystore/config.go

@@ -0,0 +1,117 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"fmt"
+	"time"
+)
+
+const (
+	DefaultMaxWorkers             = 10
+	DefaultBufferCapacity         = 512
+	DefaultGCTriggerInterval      = 100
+	DefaultAvroWorkers            = 4
+	DefaultCheckpointBufferMin    = 3
+	DefaultAvroCheckpointInterval = time.Minute
+)
+
+var InternalCCMSFlag bool = false
+
+type MetricStoreConfig struct {
+	// Number of concurrent workers for checkpoint and archive operations.
+	// If not set or 0, defaults to min(runtime.NumCPU()/2+1, 10)
+	NumWorkers  int `json:"num-workers"`
+	Checkpoints struct {
+		FileFormat string `json:"file-format"`
+		Interval   string `json:"interval"`
+		RootDir    string `json:"directory"`
+		Restore    string `json:"restore"`
+	} `json:"checkpoints"`
+	Debug struct {
+		DumpToFile string `json:"dump-to-file"`
+		EnableGops bool   `json:"gops"`
+	} `json:"debug"`
+	RetentionInMemory string `json:"retention-in-memory"`
+	Archive           struct {
+		Interval      string `json:"interval"`
+		RootDir       string `json:"directory"`
+		DeleteInstead bool   `json:"delete-instead"`
+	} `json:"archive"`
+	Subscriptions []struct {
+		// Channel name
+		SubscribeTo string `json:"subscribe-to"`
+
+		// Allow lines without a cluster tag, use this as default, optional
+		ClusterTag string `json:"cluster-tag"`
+	} `json:"subscriptions"`
+}
+
+var Keys MetricStoreConfig
+
+// AggregationStrategy for aggregation over multiple values at different cpus/sockets/..., not time!
+type AggregationStrategy int
+
+const (
+	NoAggregation AggregationStrategy = iota
+	SumAggregation
+	AvgAggregation
+)
+
+func AssignAggregationStrategy(str string) (AggregationStrategy, error) {
+	switch str {
+	case "":
+		return NoAggregation, nil
+	case "sum":
+		return SumAggregation, nil
+	case "avg":
+		return AvgAggregation, nil
+	default:
+		return NoAggregation, fmt.Errorf("[METRICSTORE]> unknown aggregation strategy: %s", str)
+	}
+}
+
+type MetricConfig struct {
+	// Interval in seconds at which measurements are stored
+	Frequency int64
+
+	// Can be 'sum', 'avg' or null. Describes how to aggregate metrics from the same timestep over the hierarchy.
+	Aggregation AggregationStrategy
+
+	// Private, used internally...
+	offset int
+}
+
+var Metrics map[string]MetricConfig
+
+func GetMetricFrequency(metricName string) (int64, error) {
+	if metric, ok := Metrics[metricName]; ok {
+		return metric.Frequency, nil
+	}
+	return 0, fmt.Errorf("[METRICSTORE]> metric %s not found", metricName)
+}
+
+// AddMetric adds logic to add metrics. Redundant metrics should be updated with max frequency.
+// use metric.Name to check if the metric already exists.
+// if not, add it to the Metrics map.
+func AddMetric(name string, metric MetricConfig) error {
+	if Metrics == nil {
+		Metrics = make(map[string]MetricConfig, 0)
+	}
+
+	if existingMetric, ok := Metrics[name]; ok {
+		if existingMetric.Frequency != metric.Frequency {
+			if existingMetric.Frequency < metric.Frequency {
+				existingMetric.Frequency = metric.Frequency
+				Metrics[name] = existingMetric
+			}
+		}
+	} else {
+		Metrics[name] = metric
+	}
+
+	return nil
+}

internal/memorystore/configSchema.go

@@ -0,0 +1,95 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+const configSchema = `{
+    "type": "object",
+    "description": "Configuration specific to built-in metric-store.",
+    "properties": {
+        "checkpoints": {
+            "description": "Configuration for checkpointing the metrics within metric-store",
+            "type": "object",
+            "properties": {
+                "file-format": {
+                    "description": "Specify the type of checkpoint file. There are 2 variants: 'avro' and 'json'. If nothing is specified, 'avro' is default.",
+                    "type": "string"
+                },
+                "interval": {
+                    "description": "Interval at which the metrics should be checkpointed.",
+                    "type": "string"
+                },
+                "directory": {
+                    "description": "Specify the parent directy in which the checkpointed files should be placed.",
+                    "type": "string"
+                },
+                "restore": {
+                    "description": "When cc-backend starts up, look for checkpointed files that are less than X hours old and load metrics from these selected checkpoint files.",
+                    "type": "string"
+                }
+            }
+        },
+        "archive": {
+            "description": "Configuration for archiving the already checkpointed files.",
+            "type": "object",
+            "properties": {
+                "interval": {
+                    "description": "Interval at which the checkpointed files should be archived.",
+                    "type": "string"
+                },
+                "directory": {
+                    "description": "Specify the parent directy in which the archived files should be placed.",
+                    "type": "string"
+                }
+            }
+        },
+        "retention-in-memory": {
+            "description": "Keep the metrics within memory for given time interval. Retention for X hours, then the metrics would be freed.",
+            "type": "string"
+        },
+        "nats": {
+            "description": "Configuration for accepting published data through NATS.",
+            "type": "array",
+            "items": {
+                "type": "object",
+                "properties": {
+                    "address": {
+                        "description": "Address of the NATS server.",
+                        "type": "string"
+                    },
+                    "username": {
+                        "description": "Optional: If configured with username/password method.",
+                        "type": "string"
+                    },
+                    "password": {
+                        "description": "Optional: If configured with username/password method.",
+                        "type": "string"
+                    },
+                    "creds-file-path": {
+                        "description": "Optional: If configured with Credential File method. Path to your NATS cred file.",
+                        "type": "string"
+                    },
+                    "subscriptions": {
+                        "description": "Array of various subscriptions. Allows to subscibe to different subjects and publishers.",
+                        "type": "array",
+                        "items": {
+                            "type": "object",
+                            "properties": {
+                                "subscribe-to": {
+                                    "description": "Channel name",
+                                    "type": "string"
+                                },
+                                "cluster-tag": {
+                                    "description": "Optional: Allow lines without a cluster tag, use this as default",
+                                    "type": "string"
+                                }
+                            }
+                        }
+                    }
+                }
+            }
+        }
+    }
+}`

internal/memorystore/debug.go

@@ -0,0 +1,112 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"bufio"
+	"fmt"
+	"strconv"
+)
+
+func (b *buffer) debugDump(buf []byte) []byte {
+	if b.prev != nil {
+		buf = b.prev.debugDump(buf)
+	}
+
+	start, len, end := b.start, len(b.data), b.start+b.frequency*int64(len(b.data))
+	buf = append(buf, `{"start":`...)
+	buf = strconv.AppendInt(buf, start, 10)
+	buf = append(buf, `,"len":`...)
+	buf = strconv.AppendInt(buf, int64(len), 10)
+	buf = append(buf, `,"end":`...)
+	buf = strconv.AppendInt(buf, end, 10)
+	if b.archived {
+		buf = append(buf, `,"saved":true`...)
+	}
+	if b.next != nil {
+		buf = append(buf, `},`...)
+	} else {
+		buf = append(buf, `}`...)
+	}
+	return buf
+}
+
+func (l *Level) debugDump(m *MemoryStore, w *bufio.Writer, lvlname string, buf []byte, depth int) ([]byte, error) {
+	l.lock.RLock()
+	defer l.lock.RUnlock()
+	for i := 0; i < depth; i++ {
+		buf = append(buf, '\t')
+	}
+	buf = append(buf, '"')
+	buf = append(buf, lvlname...)
+	buf = append(buf, "\":{\n"...)
+	depth += 1
+	objitems := 0
+	for name, mc := range m.Metrics {
+		if b := l.metrics[mc.offset]; b != nil {
+			for i := 0; i < depth; i++ {
+				buf = append(buf, '\t')
+			}
+
+			buf = append(buf, '"')
+			buf = append(buf, name...)
+			buf = append(buf, `":[`...)
+			buf = b.debugDump(buf)
+			buf = append(buf, "],\n"...)
+			objitems++
+		}
+	}
+
+	for name, lvl := range l.children {
+		_, err := w.Write(buf)
+		if err != nil {
+			return nil, err
+		}
+
+		buf = buf[0:0]
+		buf, err = lvl.debugDump(m, w, name, buf, depth)
+		if err != nil {
+			return nil, err
+		}
+
+		buf = append(buf, ',', '\n')
+		objitems++
+	}
+
+	// remove final `,`:
+	if objitems > 0 {
+		buf = append(buf[0:len(buf)-1], '\n')
+	}
+
+	depth -= 1
+	for i := 0; i < depth; i++ {
+		buf = append(buf, '\t')
+	}
+	buf = append(buf, '}')
+	return buf, nil
+}
+
+func (m *MemoryStore) DebugDump(w *bufio.Writer, selector []string) error {
+	lvl := m.root.findLevel(selector)
+	if lvl == nil {
+		return fmt.Errorf("[METRICSTORE]> not found: %#v", selector)
+	}
+
+	buf := make([]byte, 0, 2048)
+	buf = append(buf, "{"...)
+
+	buf, err := lvl.debugDump(m, w, "data", buf, 0)
+	if err != nil {
+		return err
+	}
+
+	buf = append(buf, "}\n"...)
+	if _, err = w.Write(buf); err != nil {
+		return err
+	}
+
+	return w.Flush()
+}

internal/memorystore/healthcheck.go

@@ -0,0 +1,92 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"bufio"
+	"fmt"
+	"time"
+)
+
+// MaxMissingDataPoints is a threshold that allows a node to be healthy with certain number of data points missing.
+// Suppose a node does not receive last 5 data points, then healthCheck endpoint will still say a
+// node is healthy. Anything more than 5 missing points in metrics of the node will deem the node unhealthy.
+const MaxMissingDataPoints int64 = 5
+
+// MaxUnhealthyMetrics is a threshold which allows upto certain number of metrics in a node to be unhealthly.
+// Works with MaxMissingDataPoints. Say 5 metrics (including submetrics) do not receive the last
+// MaxMissingDataPoints data points, then the node will be deemed healthy. Any more metrics that does
+// not receive data for MaxMissingDataPoints data points will deem the node unhealthy.
+const MaxUnhealthyMetrics int64 = 5
+
+func (b *buffer) healthCheck() int64 {
+	// Check if the buffer is empty
+	if b.data == nil {
+		return 1
+	}
+
+	bufferEnd := b.start + b.frequency*int64(len(b.data))
+	t := time.Now().Unix()
+
+	// Check if the buffer is too old
+	if t-bufferEnd > MaxMissingDataPoints*b.frequency {
+		return 1
+	}
+
+	return 0
+}
+
+func (l *Level) healthCheck(m *MemoryStore, count int64) (int64, error) {
+	l.lock.RLock()
+	defer l.lock.RUnlock()
+
+	for _, mc := range m.Metrics {
+		if b := l.metrics[mc.offset]; b != nil {
+			count += b.healthCheck()
+		}
+	}
+
+	for _, lvl := range l.children {
+		c, err := lvl.healthCheck(m, 0)
+		if err != nil {
+			return 0, err
+		}
+		count += c
+	}
+
+	return count, nil
+}
+
+func (m *MemoryStore) HealthCheck(w *bufio.Writer, selector []string) error {
+	lvl := m.root.findLevel(selector)
+	if lvl == nil {
+		return fmt.Errorf("[METRICSTORE]> not found: %#v", selector)
+	}
+
+	buf := make([]byte, 0, 25)
+	// buf = append(buf, "{"...)
+
+	var count int64 = 0
+
+	unhealthyMetricsCount, err := lvl.healthCheck(m, count)
+	if err != nil {
+		return err
+	}
+
+	if unhealthyMetricsCount < MaxUnhealthyMetrics {
+		buf = append(buf, "Healthy"...)
+	} else {
+		buf = append(buf, "Unhealthy"...)
+	}
+
+	// buf = append(buf, "}\n"...)
+
+	if _, err = w.Write(buf); err != nil {
+		return err
+	}
+
+	return w.Flush()
+}

internal/memorystore/level.go

@@ -0,0 +1,192 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"sync"
+	"unsafe"
+
+	"github.com/ClusterCockpit/cc-lib/util"
+)
+
+// Could also be called "node" as this forms a node in a tree structure.
+// Called Level because "node" might be confusing here.
+// Can be both a leaf or a inner node. In this tree structue, inner nodes can
+// also hold data (in `metrics`).
+type Level struct {
+	children map[string]*Level
+	metrics  []*buffer
+	lock     sync.RWMutex
+}
+
+// Find the correct level for the given selector, creating it if
+// it does not exist. Example selector in the context of the
+// ClusterCockpit could be: []string{ "emmy", "host123", "cpu0" }.
+// This function would probably benefit a lot from `level.children` beeing a `sync.Map`?
+func (l *Level) findLevelOrCreate(selector []string, nMetrics int) *Level {
+	if len(selector) == 0 {
+		return l
+	}
+
+	// Allow concurrent reads:
+	l.lock.RLock()
+	var child *Level
+	var ok bool
+	if l.children == nil {
+		// Children map needs to be created...
+		l.lock.RUnlock()
+	} else {
+		child, ok = l.children[selector[0]]
+		l.lock.RUnlock()
+		if ok {
+			return child.findLevelOrCreate(selector[1:], nMetrics)
+		}
+	}
+
+	// The level does not exist, take write lock for unique access:
+	l.lock.Lock()
+	// While this thread waited for the write lock, another thread
+	// could have created the child node.
+	if l.children != nil {
+		child, ok = l.children[selector[0]]
+		if ok {
+			l.lock.Unlock()
+			return child.findLevelOrCreate(selector[1:], nMetrics)
+		}
+	}
+
+	child = &Level{
+		metrics:  make([]*buffer, nMetrics),
+		children: nil,
+	}
+
+	if l.children != nil {
+		l.children[selector[0]] = child
+	} else {
+		l.children = map[string]*Level{selector[0]: child}
+	}
+	l.lock.Unlock()
+	return child.findLevelOrCreate(selector[1:], nMetrics)
+}
+
+func (l *Level) free(t int64) (int, error) {
+	l.lock.Lock()
+	defer l.lock.Unlock()
+
+	n := 0
+	for i, b := range l.metrics {
+		if b != nil {
+			delme, m := b.free(t)
+			n += m
+			if delme {
+				if cap(b.data) == BufferCap {
+					bufferPool.Put(b)
+				}
+				l.metrics[i] = nil
+			}
+		}
+	}
+
+	for _, l := range l.children {
+		m, err := l.free(t)
+		n += m
+		if err != nil {
+			return n, err
+		}
+	}
+
+	return n, nil
+}
+
+func (l *Level) sizeInBytes() int64 {
+	l.lock.RLock()
+	defer l.lock.RUnlock()
+	size := int64(0)
+
+	for _, b := range l.metrics {
+		if b != nil {
+			size += b.count() * int64(unsafe.Sizeof(util.Float(0)))
+		}
+	}
+
+	for _, child := range l.children {
+		size += child.sizeInBytes()
+	}
+
+	return size
+}
+
+func (l *Level) findLevel(selector []string) *Level {
+	if len(selector) == 0 {
+		return l
+	}
+
+	l.lock.RLock()
+	defer l.lock.RUnlock()
+
+	lvl := l.children[selector[0]]
+	if lvl == nil {
+		return nil
+	}
+
+	return lvl.findLevel(selector[1:])
+}
+
+func (l *Level) findBuffers(selector util.Selector, offset int, f func(b *buffer) error) error {
+	l.lock.RLock()
+	defer l.lock.RUnlock()
+
+	if len(selector) == 0 {
+		b := l.metrics[offset]
+		if b != nil {
+			return f(b)
+		}
+
+		for _, lvl := range l.children {
+			err := lvl.findBuffers(nil, offset, f)
+			if err != nil {
+				return err
+			}
+		}
+		return nil
+	}
+
+	sel := selector[0]
+	if len(sel.String) != 0 && l.children != nil {
+		lvl, ok := l.children[sel.String]
+		if ok {
+			err := lvl.findBuffers(selector[1:], offset, f)
+			if err != nil {
+				return err
+			}
+		}
+		return nil
+	}
+
+	if sel.Group != nil && l.children != nil {
+		for _, key := range sel.Group {
+			lvl, ok := l.children[key]
+			if ok {
+				err := lvl.findBuffers(selector[1:], offset, f)
+				if err != nil {
+					return err
+				}
+			}
+		}
+		return nil
+	}
+
+	if sel.Any && l.children != nil {
+		for _, lvl := range l.children {
+			if err := lvl.findBuffers(selector[1:], offset, f); err != nil {
+				return err
+			}
+		}
+		return nil
+	}
+
+	return nil
+}

internal/memorystore/lineprotocol.go

@@ -0,0 +1,258 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"context"
+	"fmt"
+	"sync"
+	"time"
+
+	"github.com/ClusterCockpit/cc-backend/pkg/nats"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/influxdata/line-protocol/v2/lineprotocol"
+)
+
+func ReceiveNats(ms *MemoryStore,
+	workers int,
+	ctx context.Context,
+) error {
+	nc := nats.GetClient()
+
+	if nc == nil {
+		cclog.Warn("NATS client not initialized")
+		return nil
+	}
+
+	var wg sync.WaitGroup
+
+	msgs := make(chan []byte, workers*2)
+
+	for _, sc := range Keys.Subscriptions {
+		clusterTag := sc.ClusterTag
+		if workers > 1 {
+			wg.Add(workers)
+
+			for range workers {
+				go func() {
+					for m := range msgs {
+						dec := lineprotocol.NewDecoderWithBytes(m)
+						if err := DecodeLine(dec, ms, clusterTag); err != nil {
+							cclog.Errorf("error: %s", err.Error())
+						}
+					}
+
+					wg.Done()
+				}()
+			}
+
+			nc.Subscribe(sc.SubscribeTo, func(subject string, data []byte) {
+				msgs <- data
+			})
+		} else {
+			nc.Subscribe(sc.SubscribeTo, func(subject string, data []byte) {
+				dec := lineprotocol.NewDecoderWithBytes(data)
+				if err := DecodeLine(dec, ms, clusterTag); err != nil {
+					cclog.Errorf("error: %s", err.Error())
+				}
+			})
+		}
+		cclog.Infof("NATS subscription to '%s' established", sc.SubscribeTo)
+	}
+
+	close(msgs)
+	wg.Wait()
+
+	return nil
+}
+
+// Place `prefix` in front of `buf` but if possible,
+// do that inplace in `buf`.
+func reorder(buf, prefix []byte) []byte {
+	n := len(prefix)
+	m := len(buf)
+	if cap(buf) < m+n {
+		return append(prefix[:n:n], buf...)
+	} else {
+		buf = buf[:n+m]
+		for i := m - 1; i >= 0; i-- {
+			buf[i+n] = buf[i]
+		}
+		for i := range n {
+			buf[i] = prefix[i]
+		}
+		return buf
+	}
+}
+
+// Decode lines using dec and make write calls to the MemoryStore.
+// If a line is missing its cluster tag, use clusterDefault as default.
+func DecodeLine(dec *lineprotocol.Decoder,
+	ms *MemoryStore,
+	clusterDefault string,
+) error {
+	// Reduce allocations in loop:
+	t := time.Now()
+	metric, metricBuf := Metric{}, make([]byte, 0, 16)
+	selector := make([]string, 0, 4)
+	typeBuf, subTypeBuf := make([]byte, 0, 16), make([]byte, 0)
+
+	// Optimize for the case where all lines in a "batch" are about the same
+	// cluster and host. By using `WriteToLevel` (level = host), we do not need
+	// to take the root- and cluster-level lock as often.
+	var lvl *Level = nil
+	prevCluster, prevHost := "", ""
+
+	var ok bool
+	for dec.Next() {
+		rawmeasurement, err := dec.Measurement()
+		if err != nil {
+			return err
+		}
+
+		// Needs to be copied because another call to dec.* would
+		// invalidate the returned slice.
+		metricBuf = append(metricBuf[:0], rawmeasurement...)
+
+		// The go compiler optimizes map[string(byteslice)] lookups:
+		metric.MetricConfig, ok = ms.Metrics[string(rawmeasurement)]
+		if !ok {
+			continue
+		}
+
+		typeBuf, subTypeBuf := typeBuf[:0], subTypeBuf[:0]
+		cluster, host := clusterDefault, ""
+		for {
+			key, val, err := dec.NextTag()
+			if err != nil {
+				return err
+			}
+			if key == nil {
+				break
+			}
+
+			// The go compiler optimizes string([]byte{...}) == "...":
+			switch string(key) {
+			case "cluster":
+				if string(val) == prevCluster {
+					cluster = prevCluster
+				} else {
+					cluster = string(val)
+					lvl = nil
+				}
+			case "hostname", "host":
+				if string(val) == prevHost {
+					host = prevHost
+				} else {
+					host = string(val)
+					lvl = nil
+				}
+			case "type":
+				if string(val) == "node" {
+					break
+				}
+
+				// We cannot be sure that the "type" tag comes before the "type-id" tag:
+				if len(typeBuf) == 0 {
+					typeBuf = append(typeBuf, val...)
+				} else {
+					typeBuf = reorder(typeBuf, val)
+				}
+			case "type-id":
+				typeBuf = append(typeBuf, val...)
+			case "subtype":
+				// We cannot be sure that the "subtype" tag comes before the "stype-id" tag:
+				if len(subTypeBuf) == 0 {
+					subTypeBuf = append(subTypeBuf, val...)
+				} else {
+					subTypeBuf = reorder(subTypeBuf, val)
+					// subTypeBuf = reorder(typeBuf, val)
+				}
+			case "stype-id":
+				subTypeBuf = append(subTypeBuf, val...)
+			default:
+			}
+		}
+
+		// If the cluster or host changed, the lvl was set to nil
+		if lvl == nil {
+			selector = selector[:2]
+			selector[0], selector[1] = cluster, host
+			lvl = ms.GetLevel(selector)
+			prevCluster, prevHost = cluster, host
+		}
+
+		// subtypes:
+		selector = selector[:0]
+		if len(typeBuf) > 0 {
+			selector = append(selector, string(typeBuf)) // <- Allocation :(
+			if len(subTypeBuf) > 0 {
+				selector = append(selector, string(subTypeBuf))
+			}
+		}
+
+		for {
+			key, val, err := dec.NextField()
+			if err != nil {
+				return err
+			}
+
+			if key == nil {
+				break
+			}
+
+			if string(key) != "value" {
+				return fmt.Errorf("host %s: unknown field: '%s' (value: %#v)", host, string(key), val)
+			}
+
+			if val.Kind() == lineprotocol.Float {
+				metric.Value = schema.Float(val.FloatV())
+			} else if val.Kind() == lineprotocol.Int {
+				metric.Value = schema.Float(val.IntV())
+			} else if val.Kind() == lineprotocol.Uint {
+				metric.Value = schema.Float(val.UintV())
+			} else {
+				return fmt.Errorf("host %s: unsupported value type in message: %s", host, val.Kind().String())
+			}
+		}
+
+		if t, err = dec.Time(lineprotocol.Second, t); err != nil {
+			t = time.Now()
+			if t, err = dec.Time(lineprotocol.Millisecond, t); err != nil {
+				t = time.Now()
+				if t, err = dec.Time(lineprotocol.Microsecond, t); err != nil {
+					t = time.Now()
+					if t, err = dec.Time(lineprotocol.Nanosecond, t); err != nil {
+						return fmt.Errorf("host %s: timestamp : %#v with error : %#v", host, t, err.Error())
+					}
+				}
+			}
+		}
+
+		if err != nil {
+			return fmt.Errorf("host %s: timestamp : %#v with error : %#v", host, t, err.Error())
+		}
+
+		time := t.Unix()
+
+		if Keys.Checkpoints.FileFormat != "json" {
+			LineProtocolMessages <- &AvroStruct{
+				MetricName: string(metricBuf),
+				Cluster:    cluster,
+				Node:       host,
+				Selector:   append([]string{}, selector...),
+				Value:      metric.Value,
+				Timestamp:  time,
+			}
+		}
+
+		if err := ms.WriteToLevel(lvl, selector, time, []Metric{metric}); err != nil {
+			return err
+		}
+	}
+	return nil
+}

internal/memorystore/memorystore.go

@@ -0,0 +1,423 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+// Package memorystore provides an efficient in-memory time-series metric storage system
+// with support for hierarchical data organization, checkpointing, and archiving.
+//
+// The package organizes metrics in a tree structure (cluster → host → component) and
+// provides concurrent read/write access to metric data with configurable aggregation strategies.
+// Background goroutines handle periodic checkpointing (JSON or Avro format), archiving old data,
+// and enforcing retention policies.
+//
+// Key features:
+//   - In-memory metric storage with configurable retention
+//   - Hierarchical data organization (selectors)
+//   - Concurrent checkpoint/archive workers
+//   - Support for sum and average aggregation
+//   - NATS integration for metric ingestion
+package memorystore
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"runtime"
+	"sync"
+	"time"
+
+	"github.com/ClusterCockpit/cc-backend/internal/config"
+	"github.com/ClusterCockpit/cc-backend/pkg/archive"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/resampler"
+	"github.com/ClusterCockpit/cc-lib/schema"
+	"github.com/ClusterCockpit/cc-lib/util"
+)
+
+var (
+	singleton  sync.Once
+	msInstance *MemoryStore
+	// shutdownFunc stores the context cancellation function created in Init
+	// and is called during Shutdown to cancel all background goroutines
+	shutdownFunc context.CancelFunc
+)
+
+type Metric struct {
+	Name         string
+	Value        schema.Float
+	MetricConfig MetricConfig
+}
+
+type MemoryStore struct {
+	Metrics map[string]MetricConfig
+	root    Level
+}
+
+func Init(rawConfig json.RawMessage, wg *sync.WaitGroup) {
+	startupTime := time.Now()
+
+	if rawConfig != nil {
+		config.Validate(configSchema, rawConfig)
+		dec := json.NewDecoder(bytes.NewReader(rawConfig))
+		// dec.DisallowUnknownFields()
+		if err := dec.Decode(&Keys); err != nil {
+			cclog.Abortf("[METRICSTORE]> Metric Store Config Init: Could not decode config file '%s'.\nError: %s\n", rawConfig, err.Error())
+		}
+	}
+
+	// Set NumWorkers from config or use default
+	if Keys.NumWorkers <= 0 {
+		Keys.NumWorkers = min(runtime.NumCPU()/2+1, DefaultMaxWorkers)
+	}
+	cclog.Debugf("[METRICSTORE]> Using %d workers for checkpoint/archive operations\n", Keys.NumWorkers)
+
+	// Helper function to add metric configuration
+	addMetricConfig := func(mc schema.MetricConfig) {
+		agg, err := AssignAggregationStrategy(mc.Aggregation)
+		if err != nil {
+			cclog.Warnf("Could not find aggregation strategy for metric config '%s': %s", mc.Name, err.Error())
+		}
+
+		AddMetric(mc.Name, MetricConfig{
+			Frequency:   int64(mc.Timestep),
+			Aggregation: agg,
+		})
+	}
+
+	for _, c := range archive.Clusters {
+		for _, mc := range c.MetricConfig {
+			addMetricConfig(*mc)
+		}
+
+		for _, sc := range c.SubClusters {
+			for _, mc := range sc.MetricConfig {
+				addMetricConfig(mc)
+			}
+		}
+	}
+
+	// Pass the config.MetricStoreKeys
+	InitMetrics(Metrics)
+
+	ms := GetMemoryStore()
+
+	d, err := time.ParseDuration(Keys.Checkpoints.Restore)
+	if err != nil {
+		cclog.Fatal(err)
+	}
+
+	restoreFrom := startupTime.Add(-d)
+	cclog.Infof("[METRICSTORE]> Loading checkpoints newer than %s\n", restoreFrom.Format(time.RFC3339))
+	files, err := ms.FromCheckpointFiles(Keys.Checkpoints.RootDir, restoreFrom.Unix())
+	loadedData := ms.SizeInBytes() / 1024 / 1024 // In MB
+	if err != nil {
+		cclog.Fatalf("[METRICSTORE]> Loading checkpoints failed: %s\n", err.Error())
+	} else {
+		cclog.Infof("[METRICSTORE]> Checkpoints loaded (%d files, %d MB, that took %fs)\n", files, loadedData, time.Since(startupTime).Seconds())
+	}
+
+	// Try to use less memory by forcing a GC run here and then
+	// lowering the target percentage. The default of 100 means
+	// that only once the ratio of new allocations execeds the
+	// previously active heap, a GC is triggered.
+	// Forcing a GC here will set the "previously active heap"
+	// to a minumum.
+	runtime.GC()
+
+	ctx, shutdown := context.WithCancel(context.Background())
+
+	wg.Add(4)
+
+	Retention(wg, ctx)
+	Checkpointing(wg, ctx)
+	Archiving(wg, ctx)
+	DataStaging(wg, ctx)
+
+	// Note: Signal handling has been removed from this function.
+	// The caller is responsible for handling shutdown signals and calling
+	// the shutdown() function when appropriate.
+	// Store the shutdown function for later use by Shutdown()
+	shutdownFunc = shutdown
+
+	err = ReceiveNats(ms, 1, ctx)
+	if err != nil {
+		cclog.Fatal(err)
+	}
+}
+
+// InitMetrics creates a new, initialized instance of a MemoryStore.
+// Will panic if values in the metric configurations are invalid.
+func InitMetrics(metrics map[string]MetricConfig) {
+	singleton.Do(func() {
+		offset := 0
+		for key, cfg := range metrics {
+			if cfg.Frequency == 0 {
+				panic("[METRICSTORE]> invalid frequency")
+			}
+
+			metrics[key] = MetricConfig{
+				Frequency:   cfg.Frequency,
+				Aggregation: cfg.Aggregation,
+				offset:      offset,
+			}
+			offset += 1
+		}
+
+		msInstance = &MemoryStore{
+			root: Level{
+				metrics:  make([]*buffer, len(metrics)),
+				children: make(map[string]*Level),
+			},
+			Metrics: metrics,
+		}
+	})
+}
+
+func GetMemoryStore() *MemoryStore {
+	if msInstance == nil {
+		cclog.Fatalf("[METRICSTORE]> MemoryStore not initialized!")
+	}
+
+	return msInstance
+}
+
+func Shutdown() {
+	// Cancel the context to signal all background goroutines to stop
+	if shutdownFunc != nil {
+		shutdownFunc()
+	}
+
+	cclog.Infof("[METRICSTORE]> Writing to '%s'...\n", Keys.Checkpoints.RootDir)
+	var files int
+	var err error
+
+	ms := GetMemoryStore()
+
+	if Keys.Checkpoints.FileFormat == "json" {
+		files, err = ms.ToCheckpoint(Keys.Checkpoints.RootDir, lastCheckpoint.Unix(), time.Now().Unix())
+	} else {
+		files, err = GetAvroStore().ToCheckpoint(Keys.Checkpoints.RootDir, true)
+		close(LineProtocolMessages)
+	}
+
+	if err != nil {
+		cclog.Errorf("[METRICSTORE]> Writing checkpoint failed: %s\n", err.Error())
+	}
+	cclog.Infof("[METRICSTORE]> Done! (%d files written)\n", files)
+}
+
+func getName(m *MemoryStore, i int) string {
+	for key, val := range m.Metrics {
+		if val.offset == i {
+			return key
+		}
+	}
+	return ""
+}
+
+func Retention(wg *sync.WaitGroup, ctx context.Context) {
+	ms := GetMemoryStore()
+
+	go func() {
+		defer wg.Done()
+		d, err := time.ParseDuration(Keys.RetentionInMemory)
+		if err != nil {
+			cclog.Fatal(err)
+		}
+		if d <= 0 {
+			return
+		}
+
+		tickInterval := d / 2
+		if tickInterval <= 0 {
+			return
+		}
+		ticker := time.NewTicker(tickInterval)
+		defer ticker.Stop()
+
+		for {
+			select {
+			case <-ctx.Done():
+				return
+			case <-ticker.C:
+				t := time.Now().Add(-d)
+				cclog.Infof("[METRICSTORE]> start freeing buffers (older than %s)...\n", t.Format(time.RFC3339))
+				freed, err := ms.Free(nil, t.Unix())
+				if err != nil {
+					cclog.Errorf("[METRICSTORE]> freeing up buffers failed: %s\n", err.Error())
+				} else {
+					cclog.Infof("[METRICSTORE]> done: %d buffers freed\n", freed)
+				}
+			}
+		}
+	}()
+}
+
+// Write all values in `metrics` to the level specified by `selector` for time `ts`.
+// Look at `findLevelOrCreate` for how selectors work.
+func (m *MemoryStore) Write(selector []string, ts int64, metrics []Metric) error {
+	var ok bool
+	for i, metric := range metrics {
+		if metric.MetricConfig.Frequency == 0 {
+			metric.MetricConfig, ok = m.Metrics[metric.Name]
+			if !ok {
+				metric.MetricConfig.Frequency = 0
+			}
+			metrics[i] = metric
+		}
+	}
+
+	return m.WriteToLevel(&m.root, selector, ts, metrics)
+}
+
+func (m *MemoryStore) GetLevel(selector []string) *Level {
+	return m.root.findLevelOrCreate(selector, len(m.Metrics))
+}
+
+// WriteToLevel assumes that `minfo` in `metrics` is filled in
+func (m *MemoryStore) WriteToLevel(l *Level, selector []string, ts int64, metrics []Metric) error {
+	l = l.findLevelOrCreate(selector, len(m.Metrics))
+	l.lock.Lock()
+	defer l.lock.Unlock()
+
+	for _, metric := range metrics {
+		if metric.MetricConfig.Frequency == 0 {
+			continue
+		}
+
+		b := l.metrics[metric.MetricConfig.offset]
+		if b == nil {
+			// First write to this metric and level
+			b = newBuffer(ts, metric.MetricConfig.Frequency)
+			l.metrics[metric.MetricConfig.offset] = b
+		}
+
+		nb, err := b.write(ts, metric.Value)
+		if err != nil {
+			return err
+		}
+
+		// Last write created a new buffer...
+		if b != nb {
+			l.metrics[metric.MetricConfig.offset] = nb
+		}
+	}
+	return nil
+}
+
+// Read returns all values for metric `metric` from `from` to `to` for the selected level(s).
+// If the level does not hold the metric itself, the data will be aggregated recursively from the children.
+// The second and third return value are the actual from/to for the data. Those can be different from
+// the range asked for if no data was available.
+func (m *MemoryStore) Read(selector util.Selector, metric string, from, to, resolution int64) ([]schema.Float, int64, int64, int64, error) {
+	if from > to {
+		return nil, 0, 0, 0, errors.New("[METRICSTORE]> invalid time range")
+	}
+
+	minfo, ok := m.Metrics[metric]
+	if !ok {
+		return nil, 0, 0, 0, errors.New("[METRICSTORE]> unknown metric: " + metric)
+	}
+
+	n, data := 0, make([]schema.Float, (to-from)/minfo.Frequency+1)
+
+	err := m.root.findBuffers(selector, minfo.offset, func(b *buffer) error {
+		cdata, cfrom, cto, err := b.read(from, to, data)
+		if err != nil {
+			return err
+		}
+
+		if n == 0 {
+			from, to = cfrom, cto
+		} else if from != cfrom || to != cto || len(data) != len(cdata) {
+			missingfront, missingback := int((from-cfrom)/minfo.Frequency), int((to-cto)/minfo.Frequency)
+			if missingfront != 0 {
+				return ErrDataDoesNotAlign
+			}
+
+			newlen := len(cdata) - missingback
+			if newlen < 1 {
+				return ErrDataDoesNotAlign
+			}
+			cdata = cdata[0:newlen]
+			if len(cdata) != len(data) {
+				return ErrDataDoesNotAlign
+			}
+
+			from, to = cfrom, cto
+		}
+
+		data = cdata
+		n += 1
+		return nil
+	})
+
+	if err != nil {
+		return nil, 0, 0, 0, err
+	} else if n == 0 {
+		return nil, 0, 0, 0, errors.New("[METRICSTORE]> metric or host not found")
+	} else if n > 1 {
+		if minfo.Aggregation == AvgAggregation {
+			normalize := 1. / schema.Float(n)
+			for i := 0; i < len(data); i++ {
+				data[i] *= normalize
+			}
+		} else if minfo.Aggregation != SumAggregation {
+			return nil, 0, 0, 0, errors.New("[METRICSTORE]> invalid aggregation")
+		}
+	}
+
+	data, resolution, err = resampler.LargestTriangleThreeBucket(data, minfo.Frequency, resolution)
+	if err != nil {
+		return nil, 0, 0, 0, err
+	}
+
+	return data, from, to, resolution, nil
+}
+
+// Free releases all buffers for the selected level and all its children that
+// contain only values older than `t`.
+func (m *MemoryStore) Free(selector []string, t int64) (int, error) {
+	return m.GetLevel(selector).free(t)
+}
+
+func (m *MemoryStore) FreeAll() error {
+	for k := range m.root.children {
+		delete(m.root.children, k)
+	}
+
+	return nil
+}
+
+func (m *MemoryStore) SizeInBytes() int64 {
+	return m.root.sizeInBytes()
+}
+
+// ListChildren , given a selector, returns a list of all children of the level
+// selected.
+func (m *MemoryStore) ListChildren(selector []string) []string {
+	lvl := &m.root
+	for lvl != nil && len(selector) != 0 {
+		lvl.lock.RLock()
+		next := lvl.children[selector[0]]
+		lvl.lock.RUnlock()
+		lvl = next
+		selector = selector[1:]
+	}
+
+	if lvl == nil {
+		return nil
+	}
+
+	lvl.lock.RLock()
+	defer lvl.lock.RUnlock()
+
+	children := make([]string, 0, len(lvl.children))
+	for child := range lvl.children {
+		children = append(children, child)
+	}
+
+	return children
+}

internal/memorystore/memorystore_test.go

@@ -0,0 +1,156 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"testing"
+
+	"github.com/ClusterCockpit/cc-lib/schema"
+)
+
+func TestAssignAggregationStrategy(t *testing.T) {
+	tests := []struct {
+		name     string
+		input    string
+		expected AggregationStrategy
+		wantErr  bool
+	}{
+		{"empty string", "", NoAggregation, false},
+		{"sum", "sum", SumAggregation, false},
+		{"avg", "avg", AvgAggregation, false},
+		{"invalid", "invalid", NoAggregation, true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result, err := AssignAggregationStrategy(tt.input)
+			if (err != nil) != tt.wantErr {
+				t.Errorf("AssignAggregationStrategy(%q) error = %v, wantErr %v", tt.input, err, tt.wantErr)
+				return
+			}
+			if result != tt.expected {
+				t.Errorf("AssignAggregationStrategy(%q) = %v, want %v", tt.input, result, tt.expected)
+			}
+		})
+	}
+}
+
+func TestAddMetric(t *testing.T) {
+	// Reset Metrics before test
+	Metrics = make(map[string]MetricConfig)
+
+	err := AddMetric("test_metric", MetricConfig{
+		Frequency:   60,
+		Aggregation: SumAggregation,
+	})
+	if err != nil {
+		t.Errorf("AddMetric() error = %v", err)
+	}
+
+	if _, ok := Metrics["test_metric"]; !ok {
+		t.Error("AddMetric() did not add metric to Metrics map")
+	}
+
+	// Test updating with higher frequency
+	err = AddMetric("test_metric", MetricConfig{
+		Frequency:   120,
+		Aggregation: SumAggregation,
+	})
+	if err != nil {
+		t.Errorf("AddMetric() error = %v", err)
+	}
+
+	if Metrics["test_metric"].Frequency != 120 {
+		t.Errorf("AddMetric() frequency = %d, want 120", Metrics["test_metric"].Frequency)
+	}
+
+	// Test updating with lower frequency (should not update)
+	err = AddMetric("test_metric", MetricConfig{
+		Frequency:   30,
+		Aggregation: SumAggregation,
+	})
+	if err != nil {
+		t.Errorf("AddMetric() error = %v", err)
+	}
+
+	if Metrics["test_metric"].Frequency != 120 {
+		t.Errorf("AddMetric() frequency = %d, want 120 (should not downgrade)", Metrics["test_metric"].Frequency)
+	}
+}
+
+func TestGetMetricFrequency(t *testing.T) {
+	// Reset Metrics before test
+	Metrics = map[string]MetricConfig{
+		"test_metric": {
+			Frequency:   60,
+			Aggregation: SumAggregation,
+		},
+	}
+
+	freq, err := GetMetricFrequency("test_metric")
+	if err != nil {
+		t.Errorf("GetMetricFrequency() error = %v", err)
+	}
+	if freq != 60 {
+		t.Errorf("GetMetricFrequency() = %d, want 60", freq)
+	}
+
+	_, err = GetMetricFrequency("nonexistent")
+	if err == nil {
+		t.Error("GetMetricFrequency() expected error for nonexistent metric")
+	}
+}
+
+func TestBufferWrite(t *testing.T) {
+	b := newBuffer(100, 10)
+
+	// Test writing value
+	nb, err := b.write(100, schema.Float(42.0))
+	if err != nil {
+		t.Errorf("buffer.write() error = %v", err)
+	}
+	if nb != b {
+		t.Error("buffer.write() created new buffer unexpectedly")
+	}
+	if len(b.data) != 1 {
+		t.Errorf("buffer.write() len(data) = %d, want 1", len(b.data))
+	}
+	if b.data[0] != schema.Float(42.0) {
+		t.Errorf("buffer.write() data[0] = %v, want 42.0", b.data[0])
+	}
+
+	// Test writing value from past (should error)
+	_, err = b.write(50, schema.Float(10.0))
+	if err == nil {
+		t.Error("buffer.write() expected error for past timestamp")
+	}
+}
+
+func TestBufferRead(t *testing.T) {
+	b := newBuffer(100, 10)
+	
+	// Write some test data
+	b.write(100, schema.Float(1.0))
+	b.write(110, schema.Float(2.0))
+	b.write(120, schema.Float(3.0))
+
+	// Read data
+	data := make([]schema.Float, 3)
+	result, from, to, err := b.read(100, 130, data)
+	if err != nil {
+		t.Errorf("buffer.read() error = %v", err)
+	}
+	// Buffer read should return from as firstWrite (start + freq/2)
+	if from != 100 {
+		t.Errorf("buffer.read() from = %d, want 100", from)
+	}
+	if to != 130 {
+		t.Errorf("buffer.read() to = %d, want 130", to)
+	}
+	if len(result) != 3 {
+		t.Errorf("buffer.read() len(result) = %d, want 3", len(result))
+	}
+}

internal/memorystore/stats.go

@@ -0,0 +1,124 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package memorystore
+
+import (
+	"errors"
+	"math"
+
+	"github.com/ClusterCockpit/cc-lib/util"
+)
+
+type Stats struct {
+	Samples int
+	Avg     util.Float
+	Min     util.Float
+	Max     util.Float
+}
+
+func (b *buffer) stats(from, to int64) (Stats, int64, int64, error) {
+	if from < b.start {
+		if b.prev != nil {
+			return b.prev.stats(from, to)
+		}
+		from = b.start
+	}
+
+	// TODO: Check if b.closed and if so and the full buffer is queried,
+	// use b.statistics instead of iterating over the buffer.
+
+	samples := 0
+	sum, min, max := 0.0, math.MaxFloat32, -math.MaxFloat32
+
+	var t int64
+	for t = from; t < to; t += b.frequency {
+		idx := int((t - b.start) / b.frequency)
+		if idx >= cap(b.data) {
+			b = b.next
+			if b == nil {
+				break
+			}
+			idx = 0
+		}
+
+		if t < b.start || idx >= len(b.data) {
+			continue
+		}
+
+		xf := float64(b.data[idx])
+		if math.IsNaN(xf) {
+			continue
+		}
+
+		samples += 1
+		sum += xf
+		min = math.Min(min, xf)
+		max = math.Max(max, xf)
+	}
+
+	return Stats{
+		Samples: samples,
+		Avg:     util.Float(sum) / util.Float(samples),
+		Min:     util.Float(min),
+		Max:     util.Float(max),
+	}, from, t, nil
+}
+
+// Returns statistics for the requested metric on the selected node/level.
+// Data is aggregated to the selected level the same way as in `MemoryStore.Read`.
+// If `Stats.Samples` is zero, the statistics should not be considered as valid.
+func (m *MemoryStore) Stats(selector util.Selector, metric string, from, to int64) (*Stats, int64, int64, error) {
+	if from > to {
+		return nil, 0, 0, errors.New("invalid time range")
+	}
+
+	minfo, ok := m.Metrics[metric]
+	if !ok {
+		return nil, 0, 0, errors.New("unknown metric: " + metric)
+	}
+
+	n, samples := 0, 0
+	avg, min, max := util.Float(0), math.MaxFloat32, -math.MaxFloat32
+	err := m.root.findBuffers(selector, minfo.offset, func(b *buffer) error {
+		stats, cfrom, cto, err := b.stats(from, to)
+		if err != nil {
+			return err
+		}
+
+		if n == 0 {
+			from, to = cfrom, cto
+		} else if from != cfrom || to != cto {
+			return ErrDataDoesNotAlign
+		}
+
+		samples += stats.Samples
+		avg += stats.Avg
+		min = math.Min(min, float64(stats.Min))
+		max = math.Max(max, float64(stats.Max))
+		n += 1
+		return nil
+	})
+	if err != nil {
+		return nil, 0, 0, err
+	}
+
+	if n == 0 {
+		return nil, 0, 0, ErrNoData
+	}
+
+	if minfo.Aggregation == AvgAggregation {
+		avg /= util.Float(n)
+	} else if n > 1 && minfo.Aggregation != SumAggregation {
+		return nil, 0, 0, errors.New("invalid aggregation")
+	}
+
+	return &Stats{
+		Samples: samples,
+		Avg:     avg,
+		Min:     util.Float(min),
+		Max:     util.Float(max),
+	}, from, to, nil
+}

internal/metricDataDispatcher/dataLoader.go

@@ -1,5 +1,5 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package metricDataDispatcher
@@ -11,13 +11,12 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/internal/metricdata"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/lrucache"
-	"github.com/ClusterCockpit/cc-backend/pkg/resampler"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/lrucache"
+	"github.com/ClusterCockpit/cc-lib/resampler"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
 var cache *lrucache.Cache = lrucache.New(128 * 1024 * 1024)
@@ -41,7 +40,7 @@ func LoadData(job *schema.Job,
 	ctx context.Context,
 	resolution int,
 ) (schema.JobData, error) {
-	data := cache.Get(cacheKey(job, metrics, scopes, resolution), func() (_ interface{}, ttl time.Duration, size int) {
+	data := cache.Get(cacheKey(job, metrics, scopes, resolution), func() (_ any, ttl time.Duration, size int) {
 		var jd schema.JobData
 		var err error
 
@@ -68,10 +67,10 @@ func LoadData(job *schema.Job,
 			jd, err = repo.LoadData(job, metrics, scopes, ctx, resolution)
 			if err != nil {
 				if len(jd) != 0 {
-					log.Warnf("partial error: %s", err.Error())
+					cclog.Warnf("partial error: %s", err.Error())
 					// return err, 0, 0 // Reactivating will block archiving on one partial error
 				} else {
-					log.Error("Error while loading job data from metric repository")
+					cclog.Error("Error while loading job data from metric repository")
 					return err, 0, 0
 				}
 			}
@@ -80,25 +79,25 @@ func LoadData(job *schema.Job,
 			var jd_temp schema.JobData
 			jd_temp, err = archive.GetHandle().LoadJobData(job)
 			if err != nil {
-				log.Error("Error while loading job data from archive")
+				cclog.Error("Error while loading job data from archive")
 				return err, 0, 0
 			}
 
-			//Deep copy the cached archive hashmap
+			// Deep copy the cached archive hashmap
 			jd = metricdata.DeepCopy(jd_temp)
 
-			//Resampling for archived data.
-			//Pass the resolution from frontend here.
+			// Resampling for archived data.
+			// Pass the resolution from frontend here.
 			for _, v := range jd {
 				for _, v_ := range v {
-					timestep := 0
+					timestep := int64(0)
 					for i := 0; i < len(v_.Series); i += 1 {
-						v_.Series[i].Data, timestep, err = resampler.LargestTriangleThreeBucket(v_.Series[i].Data, v_.Timestep, resolution)
+						v_.Series[i].Data, timestep, err = resampler.LargestTriangleThreeBucket(v_.Series[i].Data, int64(v_.Timestep), int64(resolution))
 						if err != nil {
 							return err, 0, 0
 						}
 					}
-					v_.Timestep = timestep
+					v_.Timestep = int(timestep)
 				}
 			}
 
@@ -178,7 +177,7 @@ func LoadData(job *schema.Job,
 	})
 
 	if err, ok := data.(error); ok {
-		log.Error("Error in returned dataset")
+		cclog.Error("Error in returned dataset")
 		return nil, err
 	}
 
@@ -203,7 +202,7 @@ func LoadAverages(
 
 	stats, err := repo.LoadStats(job, metrics, ctx) // #166 how to handle stats for acc normalizazion?
 	if err != nil {
-		log.Errorf("Error while loading statistics for job %v (User %v, Project %v)", job.JobID, job.User, job.Project)
+		cclog.Errorf("Error while loading statistics for job %v (User %v, Project %v)", job.JobID, job.User, job.Project)
 		return err
 	}
 
@@ -224,8 +223,33 @@ func LoadAverages(
 	return nil
 }
 
-// Used for polar plots in frontend
-func LoadStatData(
+// Used for statsTable in frontend: Return scoped statistics by metric.
+func LoadScopedJobStats(
+	job *schema.Job,
+	metrics []string,
+	scopes []schema.MetricScope,
+	ctx context.Context,
+) (schema.ScopedJobStats, error) {
+	if job.State != schema.JobStateRunning && !config.Keys.DisableArchive {
+		return archive.LoadScopedStatsFromArchive(job, metrics, scopes)
+	}
+
+	repo, err := metricdata.GetMetricDataRepo(job.Cluster)
+	if err != nil {
+		return nil, fmt.Errorf("job %d: no metric data repository configured for '%s'", job.JobID, job.Cluster)
+	}
+
+	scopedStats, err := repo.LoadScopedStats(job, metrics, scopes, ctx)
+	if err != nil {
+		cclog.Errorf("error while loading scoped statistics for job %d (User %s, Project %s)", job.JobID, job.User, job.Project)
+		return nil, err
+	}
+
+	return scopedStats, nil
+}
+
+// Used for polar plots in frontend: Aggregates statistics for all nodes to single values for job per metric.
+func LoadJobStats(
 	job *schema.Job,
 	metrics []string,
 	ctx context.Context,
@@ -237,12 +261,12 @@ func LoadStatData(
 	data := make(map[string]schema.MetricStatistics, len(metrics))
 	repo, err := metricdata.GetMetricDataRepo(job.Cluster)
 	if err != nil {
-		return data, fmt.Errorf("METRICDATA/METRICDATA > no metric data repository configured for '%s'", job.Cluster)
+		return data, fmt.Errorf("job %d: no metric data repository configured for '%s'", job.JobID, job.Cluster)
 	}
 
 	stats, err := repo.LoadStats(job, metrics, ctx)
 	if err != nil {
-		log.Errorf("Error while loading statistics for job %v (User %v, Project %v)", job.JobID, job.User, job.Project)
+		cclog.Errorf("error while loading statistics for job %d (User %s, Project %s)", job.JobID, job.User, job.Project)
 		return data, err
 	}
 
@@ -292,9 +316,9 @@ func LoadNodeData(
 	data, err := repo.LoadNodeData(cluster, metrics, nodes, scopes, from, to, ctx)
 	if err != nil {
 		if len(data) != 0 {
-			log.Warnf("partial error: %s", err.Error())
+			cclog.Warnf("partial error: %s", err.Error())
 		} else {
-			log.Error("Error while loading node data from metric repository")
+			cclog.Error("Error while loading node data from metric repository")
 			return nil, err
 		}
 	}
@@ -307,17 +331,17 @@ func LoadNodeData(
 }
 
 func LoadNodeListData(
-	cluster, subCluster, nodeFilter string,
+	cluster, subCluster string,
+	nodes []string,
 	metrics []string,
 	scopes []schema.MetricScope,
 	resolution int,
 	from, to time.Time,
-	page *model.PageRequest,
 	ctx context.Context,
-) (map[string]schema.JobData, int, bool, error) {
+) (map[string]schema.JobData, error) {
 	repo, err := metricdata.GetMetricDataRepo(cluster)
 	if err != nil {
-		return nil, 0, false, fmt.Errorf("METRICDATA/METRICDATA > no metric data repository configured for '%s'", cluster)
+		return nil, fmt.Errorf("METRICDATA/METRICDATA > no metric data repository configured for '%s'", cluster)
 	}
 
 	if metrics == nil {
@@ -326,13 +350,13 @@ func LoadNodeListData(
 		}
 	}
 
-	data, totalNodes, hasNextPage, err := repo.LoadNodeListData(cluster, subCluster, nodeFilter, metrics, scopes, resolution, from, to, page, ctx)
+	data, err := repo.LoadNodeListData(cluster, subCluster, nodes, metrics, scopes, resolution, from, to, ctx)
 	if err != nil {
 		if len(data) != 0 {
-			log.Warnf("partial error: %s", err.Error())
+			cclog.Warnf("partial error: %s", err.Error())
 		} else {
-			log.Error("Error while loading node data from metric repository")
-			return nil, totalNodes, hasNextPage, err
+			cclog.Error("Error while loading node data from metric repository")
+			return nil, err
 		}
 	}
 
@@ -350,8 +374,8 @@ func LoadNodeListData(
 	}
 
 	if data == nil {
-		return nil, totalNodes, hasNextPage, fmt.Errorf("METRICDATA/METRICDATA > the metric data repository for '%s' does not support this query", cluster)
+		return nil, fmt.Errorf("METRICDATA/METRICDATA > the metric data repository for '%s' does not support this query", cluster)
 	}
 
-	return data, totalNodes, hasNextPage, nil
+	return data, nil
 }

internal/metricdata/cc-metric-store.go

@@ -11,15 +11,12 @@ import (
 	"encoding/json"
 	"fmt"
 	"net/http"
-	"sort"
-	"strconv"
 	"strings"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
 type CCMetricStoreConfig struct {
@@ -82,7 +79,7 @@ type ApiMetricData struct {
 func (ccms *CCMetricStore) Init(rawConfig json.RawMessage) error {
 	var config CCMetricStoreConfig
 	if err := json.Unmarshal(rawConfig, &config); err != nil {
-		log.Warn("Error while unmarshaling raw json config")
+		cclog.Warn("Error while unmarshaling raw json config")
 		return err
 	}
 
@@ -129,13 +126,13 @@ func (ccms *CCMetricStore) doRequest(
 ) (*ApiQueryResponse, error) {
 	buf := &bytes.Buffer{}
 	if err := json.NewEncoder(buf).Encode(body); err != nil {
-		log.Warn("Error while encoding request body")
+		cclog.Errorf("Error while encoding request body: %s", err.Error())
 		return nil, err
 	}
 
 	req, err := http.NewRequestWithContext(ctx, http.MethodGet, ccms.queryEndpoint, buf)
 	if err != nil {
-		log.Warn("Error while building request body")
+		cclog.Errorf("Error while building request body: %s", err.Error())
 		return nil, err
 	}
 	if ccms.jwt != "" {
@@ -151,7 +148,7 @@ func (ccms *CCMetricStore) doRequest(
 
 	res, err := ccms.client.Do(req)
 	if err != nil {
-		log.Error("Error while performing request")
+		cclog.Errorf("Error while performing request: %s", err.Error())
 		return nil, err
 	}
 
@@ -161,7 +158,7 @@ func (ccms *CCMetricStore) doRequest(
 
 	var resBody ApiQueryResponse
 	if err := json.NewDecoder(bufio.NewReader(res.Body)).Decode(&resBody); err != nil {
-		log.Warn("Error while decoding result body")
+		cclog.Errorf("Error while decoding result body: %s", err.Error())
 		return nil, err
 	}
 
@@ -177,14 +174,14 @@ func (ccms *CCMetricStore) LoadData(
 ) (schema.JobData, error) {
 	queries, assignedScope, err := ccms.buildQueries(job, metrics, scopes, resolution)
 	if err != nil {
-		log.Warn("Error while building queries")
+		cclog.Errorf("Error while building queries for jobId %d, Metrics %v, Scopes %v: %s", job.JobID, metrics, scopes, err.Error())
 		return nil, err
 	}
 
 	req := ApiQueryRequest{
 		Cluster:   job.Cluster,
-		From:      job.StartTime.Unix(),
-		To:        job.StartTime.Add(time.Duration(job.Duration) * time.Second).Unix(),
+		From:      job.StartTime,
+		To:        job.StartTime + int64(job.Duration),
 		Queries:   queries,
 		WithStats: true,
 		WithData:  true,
@@ -192,7 +189,7 @@ func (ccms *CCMetricStore) LoadData(
 
 	resBody, err := ccms.doRequest(ctx, &req)
 	if err != nil {
-		log.Error("Error while performing request")
+		cclog.Errorf("Error while performing request: %s", err.Error())
 		return nil, err
 	}
 
@@ -270,14 +267,6 @@ func (ccms *CCMetricStore) LoadData(
 	return jobData, nil
 }
 
-var (
-	hwthreadString     = string(schema.MetricScopeHWThread)
-	coreString         = string(schema.MetricScopeCore)
-	memoryDomainString = string(schema.MetricScopeMemoryDomain)
-	socketString       = string(schema.MetricScopeSocket)
-	acceleratorString  = string(schema.MetricScopeAccelerator)
-)
-
 func (ccms *CCMetricStore) buildQueries(
 	job *schema.Job,
 	metrics []string,
@@ -298,10 +287,24 @@ func (ccms *CCMetricStore) buildQueries(
 		mc := archive.GetMetricConfig(job.Cluster, metric)
 		if mc == nil {
 			// return nil, fmt.Errorf("METRICDATA/CCMS > metric '%s' is not specified for cluster '%s'", metric, job.Cluster)
-			log.Infof("metric '%s' is not specified for cluster '%s'", metric, job.Cluster)
+			cclog.Infof("metric '%s' is not specified for cluster '%s'", metric, job.Cluster)
 			continue
 		}
 
+		// Skip if metric is removed for subcluster
+		if len(mc.SubClusters) != 0 {
+			isRemoved := false
+			for _, scConfig := range mc.SubClusters {
+				if scConfig.Name == job.SubCluster && scConfig.Remove {
+					isRemoved = true
+					break
+				}
+			}
+			if isRemoved {
+				continue
+			}
+		}
+
 		// Avoid duplicates...
 		handledScopes := make([]schema.MetricScope, 0, 3)
 
@@ -557,23 +560,16 @@ func (ccms *CCMetricStore) LoadStats(
 	ctx context.Context,
 ) (map[string]map[string]schema.MetricStatistics, error) {
 
-	// metricConfigs := archive.GetCluster(job.Cluster).MetricConfig
-	// resolution := 9000
-
-	// for _, mc := range metricConfigs {
-	// 	resolution = min(resolution, mc.Timestep)
-	// }
-
 	queries, _, err := ccms.buildQueries(job, metrics, []schema.MetricScope{schema.MetricScopeNode}, 0) // #166 Add scope shere for analysis view accelerator normalization?
 	if err != nil {
-		log.Warn("Error while building query")
+		cclog.Errorf("Error while building queries for jobId %d, Metrics %v: %s", job.JobID, metrics, err.Error())
 		return nil, err
 	}
 
 	req := ApiQueryRequest{
 		Cluster:   job.Cluster,
-		From:      job.StartTime.Unix(),
-		To:        job.StartTime.Add(time.Duration(job.Duration) * time.Second).Unix(),
+		From:      job.StartTime,
+		To:        job.StartTime + int64(job.Duration),
 		Queries:   queries,
 		WithStats: true,
 		WithData:  false,
@@ -581,7 +577,7 @@ func (ccms *CCMetricStore) LoadStats(
 
 	resBody, err := ccms.doRequest(ctx, &req)
 	if err != nil {
-		log.Error("Error while performing request")
+		cclog.Errorf("Error while performing request: %s", err.Error())
 		return nil, err
 	}
 
@@ -591,9 +587,8 @@ func (ccms *CCMetricStore) LoadStats(
 		metric := ccms.toLocalName(query.Metric)
 		data := res[0]
 		if data.Error != nil {
-			log.Infof("fetching %s for node %s failed: %s", metric, query.Hostname, *data.Error)
+			cclog.Errorf("fetching %s for node %s failed: %s", metric, query.Hostname, *data.Error)
 			continue
-			// return nil, fmt.Errorf("METRICDATA/CCMS > fetching %s for node %s failed: %s", metric, query.Hostname, *data.Error)
 		}
 
 		metricdata, ok := stats[metric]
@@ -603,9 +598,8 @@ func (ccms *CCMetricStore) LoadStats(
 		}
 
 		if data.Avg.IsNaN() || data.Min.IsNaN() || data.Max.IsNaN() {
-			log.Infof("fetching %s for node %s failed: one of avg/min/max is NaN", metric, query.Hostname)
+			cclog.Warnf("fetching %s for node %s failed: one of avg/min/max is NaN", metric, query.Hostname)
 			continue
-			// return nil, fmt.Errorf("METRICDATA/CCMS > fetching %s for node %s failed: %s", metric, query.Hostname, "avg/min/max is NaN")
 		}
 
 		metricdata[query.Hostname] = schema.MetricStatistics{
@@ -618,7 +612,98 @@ func (ccms *CCMetricStore) LoadStats(
 	return stats, nil
 }
 
-// TODO: Support sub-node-scope metrics! For this, the partition of a node needs to be known!
+// Used for Job-View Statistics Table
+func (ccms *CCMetricStore) LoadScopedStats(
+	job *schema.Job,
+	metrics []string,
+	scopes []schema.MetricScope,
+	ctx context.Context,
+) (schema.ScopedJobStats, error) {
+	queries, assignedScope, err := ccms.buildQueries(job, metrics, scopes, 0)
+	if err != nil {
+		cclog.Errorf("Error while building queries for jobId %d, Metrics %v, Scopes %v: %s", job.JobID, metrics, scopes, err.Error())
+		return nil, err
+	}
+
+	req := ApiQueryRequest{
+		Cluster:   job.Cluster,
+		From:      job.StartTime,
+		To:        job.StartTime + int64(job.Duration),
+		Queries:   queries,
+		WithStats: true,
+		WithData:  false,
+	}
+
+	resBody, err := ccms.doRequest(ctx, &req)
+	if err != nil {
+		cclog.Errorf("Error while performing request: %s", err.Error())
+		return nil, err
+	}
+
+	var errors []string
+	scopedJobStats := make(schema.ScopedJobStats)
+
+	for i, row := range resBody.Results {
+		query := req.Queries[i]
+		metric := ccms.toLocalName(query.Metric)
+		scope := assignedScope[i]
+
+		if _, ok := scopedJobStats[metric]; !ok {
+			scopedJobStats[metric] = make(map[schema.MetricScope][]*schema.ScopedStats)
+		}
+
+		if _, ok := scopedJobStats[metric][scope]; !ok {
+			scopedJobStats[metric][scope] = make([]*schema.ScopedStats, 0)
+		}
+
+		for ndx, res := range row {
+			if res.Error != nil {
+				/* Build list for "partial errors", if any */
+				errors = append(errors, fmt.Sprintf("failed to fetch '%s' from host '%s': %s", query.Metric, query.Hostname, *res.Error))
+				continue
+			}
+
+			id := (*string)(nil)
+			if query.Type != nil {
+				id = new(string)
+				*id = query.TypeIds[ndx]
+			}
+
+			if res.Avg.IsNaN() || res.Min.IsNaN() || res.Max.IsNaN() {
+				// "schema.Float()" because regular float64 can not be JSONed when NaN.
+				res.Avg = schema.Float(0)
+				res.Min = schema.Float(0)
+				res.Max = schema.Float(0)
+			}
+
+			scopedJobStats[metric][scope] = append(scopedJobStats[metric][scope], &schema.ScopedStats{
+				Hostname: query.Hostname,
+				Id:       id,
+				Data: &schema.MetricStatistics{
+					Avg: float64(res.Avg),
+					Min: float64(res.Min),
+					Max: float64(res.Max),
+				},
+			})
+		}
+
+		// So that one can later check len(scopedJobStats[metric][scope]): Remove from map if empty
+		if len(scopedJobStats[metric][scope]) == 0 {
+			delete(scopedJobStats[metric], scope)
+			if len(scopedJobStats[metric]) == 0 {
+				delete(scopedJobStats, metric)
+			}
+		}
+	}
+
+	if len(errors) != 0 {
+		/* Returns list for "partial errors" */
+		return scopedJobStats, fmt.Errorf("METRICDATA/CCMS > Errors: %s", strings.Join(errors, ", "))
+	}
+	return scopedJobStats, nil
+}
+
+// Used for Systems-View Node-Overview
 func (ccms *CCMetricStore) LoadNodeData(
 	cluster string,
 	metrics, nodes []string,
@@ -652,7 +737,7 @@ func (ccms *CCMetricStore) LoadNodeData(
 
 	resBody, err := ccms.doRequest(ctx, &req)
 	if err != nil {
-		log.Error(fmt.Sprintf("Error while performing request %#v\n", err))
+		cclog.Errorf("Error while performing request: %s", err.Error())
 		return nil, err
 	}
 
@@ -710,66 +795,22 @@ func (ccms *CCMetricStore) LoadNodeData(
 	return data, nil
 }
 
+// Used for Systems-View Node-List
 func (ccms *CCMetricStore) LoadNodeListData(
-	cluster, subCluster, nodeFilter string,
+	cluster, subCluster string,
+	nodes []string,
 	metrics []string,
 	scopes []schema.MetricScope,
 	resolution int,
 	from, to time.Time,
-	page *model.PageRequest,
 	ctx context.Context,
-) (map[string]schema.JobData, int, bool, error) {
-
-	// 0) Init additional vars
-	var totalNodes int = 0
-	var hasNextPage bool = false
-
-	// 1) Get list of all nodes
-	var nodes []string
-	if subCluster != "" {
-		scNodes := archive.NodeLists[cluster][subCluster]
-		nodes = scNodes.PrintList()
-	} else {
-		subClusterNodeLists := archive.NodeLists[cluster]
-		for _, nodeList := range subClusterNodeLists {
-			nodes = append(nodes, nodeList.PrintList()...)
-		}
-	}
-
-	// 2) Filter nodes
-	if nodeFilter != "" {
-		filteredNodes := []string{}
-		for _, node := range nodes {
-			if strings.Contains(node, nodeFilter) {
-				filteredNodes = append(filteredNodes, node)
-			}
-		}
-		nodes = filteredNodes
-	}
-
-	// 2.1) Count total nodes && Sort nodes -> Sorting invalidated after ccms return ...
-	totalNodes = len(nodes)
-	sort.Strings(nodes)
-
-	// 3) Apply paging
-	if len(nodes) > page.ItemsPerPage {
-		start := (page.Page - 1) * page.ItemsPerPage
-		end := start + page.ItemsPerPage
-		if end > len(nodes) {
-			end = len(nodes)
-			hasNextPage = false
-		} else {
-			hasNextPage = true
-		}
-		nodes = nodes[start:end]
-	}
-
-	// Note: Order of node data is not guaranteed after this point, but contents match page and filter criteria
+) (map[string]schema.JobData, error) {
 
+	// Note: Order of node data is not guaranteed after this point
 	queries, assignedScope, err := ccms.buildNodeQueries(cluster, subCluster, nodes, metrics, scopes, resolution)
 	if err != nil {
-		log.Warn("Error while building queries")
-		return nil, totalNodes, hasNextPage, err
+		cclog.Errorf("Error while building node queries for Cluster %s, SubCLuster %s, Metrics %v, Scopes %v: %s", cluster, subCluster, metrics, scopes, err.Error())
+		return nil, err
 	}
 
 	req := ApiQueryRequest{
@@ -783,8 +824,8 @@ func (ccms *CCMetricStore) LoadNodeListData(
 
 	resBody, err := ccms.doRequest(ctx, &req)
 	if err != nil {
-		log.Error(fmt.Sprintf("Error while performing request %#v\n", err))
-		return nil, totalNodes, hasNextPage, err
+		cclog.Errorf("Error while performing request: %s", err.Error())
+		return nil, err
 	}
 
 	var errors []string
@@ -864,10 +905,10 @@ func (ccms *CCMetricStore) LoadNodeListData(
 
 	if len(errors) != 0 {
 		/* Returns list of "partial errors" */
-		return data, totalNodes, hasNextPage, fmt.Errorf("METRICDATA/CCMS > Errors: %s", strings.Join(errors, ", "))
+		return data, fmt.Errorf("METRICDATA/CCMS > Errors: %s", strings.Join(errors, ", "))
 	}
 
-	return data, totalNodes, hasNextPage, nil
+	return data, nil
 }
 
 func (ccms *CCMetricStore) buildNodeQueries(
@@ -888,7 +929,7 @@ func (ccms *CCMetricStore) buildNodeQueries(
 	if subCluster != "" {
 		subClusterTopol, scterr = archive.GetSubCluster(cluster, subCluster)
 		if scterr != nil {
-			// TODO: Log
+			cclog.Errorf("could not load cluster %s subCluster %s topology: %s", cluster, subCluster, scterr.Error())
 			return nil, nil, scterr
 		}
 	}
@@ -898,10 +939,24 @@ func (ccms *CCMetricStore) buildNodeQueries(
 		mc := archive.GetMetricConfig(cluster, metric)
 		if mc == nil {
 			// return nil, fmt.Errorf("METRICDATA/CCMS > metric '%s' is not specified for cluster '%s'", metric, cluster)
-			log.Infof("metric '%s' is not specified for cluster '%s'", metric, cluster)
+			cclog.Warnf("metric '%s' is not specified for cluster '%s'", metric, cluster)
 			continue
 		}
 
+		// Skip if metric is removed for subcluster
+		if mc.SubClusters != nil {
+			isRemoved := false
+			for _, scConfig := range mc.SubClusters {
+				if scConfig.Name == subCluster && scConfig.Remove {
+					isRemoved = true
+					break
+				}
+			}
+			if isRemoved {
+				continue
+			}
+		}
+
 		// Avoid duplicates...
 		handledScopes := make([]schema.MetricScope, 0, 3)
 
@@ -1165,11 +1220,3 @@ func (ccms *CCMetricStore) buildNodeQueries(
 
 	return queries, assignedScope, nil
 }
-
-func intToStringSlice(is []int) []string {
-	ss := make([]string, len(is))
-	for i, x := range is {
-		ss[i] = strconv.Itoa(x)
-	}
-	return ss
-}

internal/metricdata/influxdb-v2.go

@@ -1,333 +0,0 @@
-// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-package metricdata
-
-import (
-	"context"
-	"crypto/tls"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"strings"
-	"time"
-
-	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
-	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
-	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
-)
-
-type InfluxDBv2DataRepositoryConfig struct {
-	Url     string `json:"url"`
-	Token   string `json:"token"`
-	Bucket  string `json:"bucket"`
-	Org     string `json:"org"`
-	SkipTls bool   `json:"skiptls"`
-}
-
-type InfluxDBv2DataRepository struct {
-	client              influxdb2.Client
-	queryClient         influxdb2Api.QueryAPI
-	bucket, measurement string
-}
-
-func (idb *InfluxDBv2DataRepository) Init(rawConfig json.RawMessage) error {
-	var config InfluxDBv2DataRepositoryConfig
-	if err := json.Unmarshal(rawConfig, &config); err != nil {
-		log.Warn("Error while unmarshaling raw json config")
-		return err
-	}
-
-	idb.client = influxdb2.NewClientWithOptions(config.Url, config.Token, influxdb2.DefaultOptions().SetTLSConfig(&tls.Config{InsecureSkipVerify: config.SkipTls}))
-	idb.queryClient = idb.client.QueryAPI(config.Org)
-	idb.bucket = config.Bucket
-
-	return nil
-}
-
-func (idb *InfluxDBv2DataRepository) formatTime(t time.Time) string {
-	return t.Format(time.RFC3339) // Like “2006-01-02T15:04:05Z07:00”
-}
-
-func (idb *InfluxDBv2DataRepository) epochToTime(epoch int64) time.Time {
-	return time.Unix(epoch, 0)
-}
-
-func (idb *InfluxDBv2DataRepository) LoadData(
-	job *schema.Job,
-	metrics []string,
-	scopes []schema.MetricScope,
-	ctx context.Context,
-	resolution int) (schema.JobData, error) {
-
-	measurementsConds := make([]string, 0, len(metrics))
-	for _, m := range metrics {
-		measurementsConds = append(measurementsConds, fmt.Sprintf(`r["_measurement"] == "%s"`, m))
-	}
-	measurementsCond := strings.Join(measurementsConds, " or ")
-
-	hostsConds := make([]string, 0, len(job.Resources))
-	for _, h := range job.Resources {
-		if h.HWThreads != nil || h.Accelerators != nil {
-			// TODO
-			return nil, errors.New("METRICDATA/INFLUXV2 > the InfluxDB metric data repository does not yet support HWThreads or Accelerators")
-		}
-		hostsConds = append(hostsConds, fmt.Sprintf(`r["hostname"] == "%s"`, h.Hostname))
-	}
-	hostsCond := strings.Join(hostsConds, " or ")
-
-	jobData := make(schema.JobData) // Empty Schema: map[<string>FIELD]map[<MetricScope>SCOPE]<*JobMetric>METRIC
-	// Requested Scopes
-	for _, scope := range scopes {
-		query := ""
-		switch scope {
-		case "node":
-			// Get Finest Granularity, Groupy By Measurement and Hostname (== Metric / Node), Calculate Mean for 60s windows
-			// log.Info("Scope 'node' requested. ")
-			query = fmt.Sprintf(`
-								from(bucket: "%s")
-								|> range(start: %s, stop: %s)
-								|> filter(fn: (r) => (%s) and (%s) )
-								|> drop(columns: ["_start", "_stop"])
-								|> group(columns: ["hostname", "_measurement"])
-		            |> aggregateWindow(every: 60s, fn: mean)
-								|> drop(columns: ["_time"])`,
-				idb.bucket,
-				idb.formatTime(job.StartTime), idb.formatTime(idb.epochToTime(job.StartTimeUnix+int64(job.Duration)+int64(1))),
-				measurementsCond, hostsCond)
-		case "socket":
-			log.Info("Scope 'socket' requested, but not yet supported: Will return 'node' scope only. ")
-			continue
-		case "core":
-			log.Info(" Scope 'core' requested, but not yet supported: Will return 'node' scope only. ")
-			continue
-			// Get Finest Granularity only, Set NULL to 0.0
-			// query = fmt.Sprintf(`
-			//  	from(bucket: "%s")
-			//  	|> range(start: %s, stop: %s)
-			//  	|> filter(fn: (r) => %s )
-			//  	|> filter(fn: (r) => %s )
-			//  	|> drop(columns: ["_start", "_stop", "cluster"])
-			//  	|> map(fn: (r) => (if exists r._value then {r with _value: r._value} else {r with _value: 0.0}))`,
-			//  	idb.bucket,
-			//  	idb.formatTime(job.StartTime), idb.formatTime(idb.epochToTime(job.StartTimeUnix + int64(job.Duration) + int64(1) )),
-			//  	measurementsCond, hostsCond)
-		default:
-			log.Infof("Unknown scope '%s' requested: Will return 'node' scope.", scope)
-			continue
-			// return nil, errors.New("METRICDATA/INFLUXV2 > the InfluxDB metric data repository does not yet support other scopes than 'node'")
-		}
-
-		rows, err := idb.queryClient.Query(ctx, query)
-		if err != nil {
-			log.Error("Error while performing query")
-			return nil, err
-		}
-
-		// Init Metrics: Only Node level now -> TODO: Matching /check on scope level ...
-		for _, metric := range metrics {
-			jobMetric, ok := jobData[metric]
-			if !ok {
-				mc := archive.GetMetricConfig(job.Cluster, metric)
-				jobMetric = map[schema.MetricScope]*schema.JobMetric{
-					scope: { // uses scope var from above!
-						Unit:             mc.Unit,
-						Timestep:         mc.Timestep,
-						Series:           make([]schema.Series, 0, len(job.Resources)),
-						StatisticsSeries: nil, // Should be: &schema.StatsSeries{},
-					},
-				}
-			}
-			jobData[metric] = jobMetric
-		}
-
-		// Process Result: Time-Data
-		field, host, hostSeries := "", "", schema.Series{}
-		// typeId := 0
-		switch scope {
-		case "node":
-			for rows.Next() {
-				row := rows.Record()
-				if host == "" || host != row.ValueByKey("hostname").(string) || rows.TableChanged() {
-					if host != "" {
-						// Append Series before reset
-						jobData[field][scope].Series = append(jobData[field][scope].Series, hostSeries)
-					}
-					field, host = row.Measurement(), row.ValueByKey("hostname").(string)
-					hostSeries = schema.Series{
-						Hostname:   host,
-						Statistics: schema.MetricStatistics{}, //TODO Add Statistics
-						Data:       make([]schema.Float, 0),
-					}
-				}
-				val, ok := row.Value().(float64)
-				if ok {
-					hostSeries.Data = append(hostSeries.Data, schema.Float(val))
-				} else {
-					hostSeries.Data = append(hostSeries.Data, schema.Float(0))
-				}
-			}
-		case "socket":
-			continue
-		case "core":
-			continue
-			// Include Series.Id in hostSeries
-			// for rows.Next() {
-			// 		row := rows.Record()
-			// 		if ( host == "" || host != row.ValueByKey("hostname").(string) || typeId != row.ValueByKey("type-id").(int) || rows.TableChanged() ) {
-			// 		 		if ( host != "" ) {
-			// 						// Append Series before reset
-			// 		 		  	jobData[field][scope].Series = append(jobData[field][scope].Series, hostSeries)
-			// 		 		}
-			// 		 		field, host, typeId = row.Measurement(), row.ValueByKey("hostname").(string), row.ValueByKey("type-id").(int)
-			// 		 		hostSeries  = schema.Series{
-			// 		 				Hostname:   host,
-			// 						Id:					&typeId,
-			// 		 				Statistics: nil,
-			// 		 				Data:       make([]schema.Float, 0),
-			// 		 		}
-			// 		}
-			// 		val := row.Value().(float64)
-			// 		hostSeries.Data = append(hostSeries.Data, schema.Float(val))
-			// }
-		default:
-			log.Infof("Unknown scope '%s' requested: Will return 'node' scope.", scope)
-			continue
-			// return nil, errors.New("the InfluxDB metric data repository does not yet support other scopes than 'node, core'")
-		}
-		// Append last Series
-		jobData[field][scope].Series = append(jobData[field][scope].Series, hostSeries)
-	}
-
-	// Get Stats
-	stats, err := idb.LoadStats(job, metrics, ctx)
-	if err != nil {
-		log.Warn("Error while loading statistics")
-		return nil, err
-	}
-
-	for _, scope := range scopes {
-		if scope == "node" { // No 'socket/core' support yet
-			for metric, nodes := range stats {
-				for node, stats := range nodes {
-					for index, _ := range jobData[metric][scope].Series {
-						if jobData[metric][scope].Series[index].Hostname == node {
-							jobData[metric][scope].Series[index].Statistics = schema.MetricStatistics{Avg: stats.Avg, Min: stats.Min, Max: stats.Max}
-						}
-					}
-				}
-			}
-		}
-	}
-
-	return jobData, nil
-}
-
-func (idb *InfluxDBv2DataRepository) LoadStats(
-	job *schema.Job,
-	metrics []string,
-	ctx context.Context) (map[string]map[string]schema.MetricStatistics, error) {
-
-	stats := map[string]map[string]schema.MetricStatistics{}
-
-	hostsConds := make([]string, 0, len(job.Resources))
-	for _, h := range job.Resources {
-		if h.HWThreads != nil || h.Accelerators != nil {
-			// TODO
-			return nil, errors.New("METRICDATA/INFLUXV2 > the InfluxDB metric data repository does not yet support HWThreads or Accelerators")
-		}
-		hostsConds = append(hostsConds, fmt.Sprintf(`r["hostname"] == "%s"`, h.Hostname))
-	}
-	hostsCond := strings.Join(hostsConds, " or ")
-
-	// lenMet := len(metrics)
-
-	for _, metric := range metrics {
-		// log.Debugf("<< You are here: %s (Index %d of %d metrics)", metric, index, lenMet)
-
-		query := fmt.Sprintf(`
-				  data = from(bucket: "%s")
-				  |> range(start: %s, stop: %s)
-				  |> filter(fn: (r) => r._measurement == "%s" and r._field == "value" and (%s))
-				  union(tables: [data |> mean(column: "_value") |> set(key: "_field", value: "avg"),
-				                 data |>  min(column: "_value") |> set(key: "_field", value: "min"),
-				                 data |>  max(column: "_value") |> set(key: "_field", value: "max")])
-				  |> pivot(rowKey: ["hostname"], columnKey: ["_field"], valueColumn: "_value")
-				  |> group()`,
-			idb.bucket,
-			idb.formatTime(job.StartTime), idb.formatTime(idb.epochToTime(job.StartTimeUnix+int64(job.Duration)+int64(1))),
-			metric, hostsCond)
-
-		rows, err := idb.queryClient.Query(ctx, query)
-		if err != nil {
-			log.Error("Error while performing query")
-			return nil, err
-		}
-
-		nodes := map[string]schema.MetricStatistics{}
-		for rows.Next() {
-			row := rows.Record()
-			host := row.ValueByKey("hostname").(string)
-
-			avg, avgok := row.ValueByKey("avg").(float64)
-			if !avgok {
-				// log.Debugf(">> Assertion error for metric %s, statistic AVG. Expected 'float64', got %v", metric, avg)
-				avg = 0.0
-			}
-			min, minok := row.ValueByKey("min").(float64)
-			if !minok {
-				// log.Debugf(">> Assertion error for metric %s, statistic MIN. Expected 'float64', got %v", metric, min)
-				min = 0.0
-			}
-			max, maxok := row.ValueByKey("max").(float64)
-			if !maxok {
-				// log.Debugf(">> Assertion error for metric %s, statistic MAX. Expected 'float64', got %v", metric, max)
-				max = 0.0
-			}
-
-			nodes[host] = schema.MetricStatistics{
-				Avg: avg,
-				Min: min,
-				Max: max,
-			}
-		}
-		stats[metric] = nodes
-	}
-
-	return stats, nil
-}
-
-func (idb *InfluxDBv2DataRepository) LoadNodeData(
-	cluster string,
-	metrics, nodes []string,
-	scopes []schema.MetricScope,
-	from, to time.Time,
-	ctx context.Context) (map[string]map[string][]*schema.JobMetric, error) {
-
-	// TODO : Implement to be used in Analysis- und System/Node-View
-	log.Infof("LoadNodeData unimplemented for InfluxDBv2DataRepository, Args: cluster %s, metrics %v, nodes %v, scopes %v", cluster, metrics, nodes, scopes)
-
-	return nil, errors.New("METRICDATA/INFLUXV2 > unimplemented for InfluxDBv2DataRepository")
-}
-
-func (idb *InfluxDBv2DataRepository) LoadNodeListData(
-	cluster, subCluster, nodeFilter string,
-	metrics []string,
-	scopes []schema.MetricScope,
-	resolution int,
-	from, to time.Time,
-	page *model.PageRequest,
-	ctx context.Context,
-) (map[string]schema.JobData, int, bool, error) {
-
-	var totalNodes int = 0
-	var hasNextPage bool = false
-	// TODO : Implement to be used in NodeList-View
-	log.Infof("LoadNodeListData unimplemented for InfluxDBv2DataRepository, Args: cluster %s, metrics %v, nodeFilter %v, scopes %v", cluster, metrics, nodeFilter, scopes)
-
-	return nil, totalNodes, hasNextPage, errors.New("METRICDATA/INFLUXV2 > unimplemented for InfluxDBv2DataRepository")
-}

internal/metricdata/metricdata.go

@@ -1,7 +1,8 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package metricdata
 
 import (
@@ -11,9 +12,9 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/config"
-	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	"github.com/ClusterCockpit/cc-backend/internal/memorystore"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
 type MetricDataRepository interface {
@@ -24,26 +25,29 @@ type MetricDataRepository interface {
 	// Return the JobData for the given job, only with the requested metrics.
 	LoadData(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error)
 
-	// Return a map of metrics to a map of nodes to the metric statistics of the job. node scope assumed for now.
+	// Return a map of metrics to a map of nodes to the metric statistics of the job. node scope only.
 	LoadStats(job *schema.Job, metrics []string, ctx context.Context) (map[string]map[string]schema.MetricStatistics, error)
 
+	// Return a map of metrics to a map of scopes to the scoped metric statistics of the job.
+	LoadScopedStats(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context) (schema.ScopedJobStats, error)
+
 	// Return a map of hosts to a map of metrics at the requested scopes (currently only node) for that node.
 	LoadNodeData(cluster string, metrics, nodes []string, scopes []schema.MetricScope, from, to time.Time, ctx context.Context) (map[string]map[string][]*schema.JobMetric, error)
 
 	// Return a map of hosts to a map of metrics to a map of scopes for multiple nodes.
-	LoadNodeListData(cluster, subCluster, nodeFilter string, metrics []string, scopes []schema.MetricScope, resolution int, from, to time.Time, page *model.PageRequest, ctx context.Context) (map[string]schema.JobData, int, bool, error)
+	LoadNodeListData(cluster, subCluster string, nodes, metrics []string, scopes []schema.MetricScope, resolution int, from, to time.Time, ctx context.Context) (map[string]schema.JobData, error)
 }
 
 var metricDataRepos map[string]MetricDataRepository = map[string]MetricDataRepository{}
 
 func Init() error {
-	for _, cluster := range config.Keys.Clusters {
+	for _, cluster := range config.Clusters {
 		if cluster.MetricDataRepository != nil {
 			var kind struct {
 				Kind string `json:"kind"`
 			}
 			if err := json.Unmarshal(cluster.MetricDataRepository, &kind); err != nil {
-				log.Warn("Error while unmarshaling raw json MetricDataRepository")
+				cclog.Warn("Error while unmarshaling raw json MetricDataRepository")
 				return err
 			}
 
@@ -51,8 +55,9 @@ func Init() error {
 			switch kind.Kind {
 			case "cc-metric-store":
 				mdr = &CCMetricStore{}
-			case "influxdb":
-				mdr = &InfluxDBv2DataRepository{}
+			case "cc-metric-store-internal":
+				mdr = &CCMetricStoreInternal{}
+				memorystore.InternalCCMSFlag = true
 			case "prometheus":
 				mdr = &PrometheusDataRepository{}
 			case "test":
@@ -62,7 +67,7 @@ func Init() error {
 			}
 
 			if err := mdr.Init(cluster.MetricDataRepository); err != nil {
-				log.Errorf("Error initializing MetricDataRepository %v for cluster %v", kind.Kind, cluster.Name)
+				cclog.Errorf("Error initializing MetricDataRepository %v for cluster %v", kind.Kind, cluster.Name)
 				return err
 			}
 			metricDataRepos[cluster.Name] = mdr

internal/metricdata/prometheus.go

@@ -1,5 +1,5 @@
 // Copyright (C) 2022 DKRZ
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package metricdata
@@ -20,10 +20,9 @@ import (
 	"text/template"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	promapi "github.com/prometheus/client_golang/api"
 	promv1 "github.com/prometheus/client_golang/api/prometheus/v1"
 	promcfg "github.com/prometheus/common/config"
@@ -160,7 +159,7 @@ func (pdb *PrometheusDataRepository) Init(rawConfig json.RawMessage) error {
 	var config PrometheusDataRepositoryConfig
 	// parse config
 	if err := json.Unmarshal(rawConfig, &config); err != nil {
-		log.Warn("Error while unmarshaling raw json config")
+		cclog.Warn("Error while unmarshaling raw json config")
 		return err
 	}
 	// support basic authentication
@@ -179,7 +178,7 @@ func (pdb *PrometheusDataRepository) Init(rawConfig json.RawMessage) error {
 		RoundTripper: rt,
 	})
 	if err != nil {
-		log.Error("Error while initializing new prometheus client")
+		cclog.Error("Error while initializing new prometheus client")
 		return err
 	}
 	// init query client
@@ -192,9 +191,9 @@ func (pdb *PrometheusDataRepository) Init(rawConfig json.RawMessage) error {
 	for metric, templ := range config.Templates {
 		pdb.templates[metric], err = template.New(metric).Parse(templ)
 		if err == nil {
-			log.Debugf("Added PromQL template for %s: %s", metric, templ)
+			cclog.Debugf("Added PromQL template for %s: %s", metric, templ)
 		} else {
-			log.Warnf("Failed to parse PromQL template %s for metric %s", templ, metric)
+			cclog.Warnf("Failed to parse PromQL template %s for metric %s", templ, metric)
 		}
 	}
 	return nil
@@ -221,7 +220,7 @@ func (pdb *PrometheusDataRepository) FormatQuery(
 			return "", errors.New(fmt.Sprintf("METRICDATA/PROMETHEUS > Error compiling template %v", templ))
 		} else {
 			query := buf.String()
-			log.Debugf("PromQL: %s", query)
+			cclog.Debugf("PromQL: %s", query)
 			return query, nil
 		}
 	} else {
@@ -279,13 +278,13 @@ func (pdb *PrometheusDataRepository) LoadData(
 	for i, resource := range job.Resources {
 		nodes[i] = resource.Hostname
 	}
-	from := job.StartTime
-	to := job.StartTime.Add(time.Duration(job.Duration) * time.Second)
+	from := time.Unix(job.StartTime, 0)
+	to := time.Unix(job.StartTime+int64(job.Duration), 0)
 
 	for _, scope := range scopes {
 		if scope != schema.MetricScopeNode {
 			logOnce.Do(func() {
-				log.Infof("Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
+				cclog.Infof("Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
 			})
 			continue
 		}
@@ -293,12 +292,12 @@ func (pdb *PrometheusDataRepository) LoadData(
 		for _, metric := range metrics {
 			metricConfig := archive.GetMetricConfig(job.Cluster, metric)
 			if metricConfig == nil {
-				log.Warnf("Error in LoadData: Metric %s for cluster %s not configured", metric, job.Cluster)
+				cclog.Warnf("Error in LoadData: Metric %s for cluster %s not configured", metric, job.Cluster)
 				return nil, errors.New("Prometheus config error")
 			}
 			query, err := pdb.FormatQuery(metric, scope, nodes, job.Cluster)
 			if err != nil {
-				log.Warn("Error while formatting prometheus query")
+				cclog.Warn("Error while formatting prometheus query")
 				return nil, err
 			}
 
@@ -310,11 +309,11 @@ func (pdb *PrometheusDataRepository) LoadData(
 			}
 			result, warnings, err := pdb.queryClient.QueryRange(ctx, query, r)
 			if err != nil {
-				log.Errorf("Prometheus query error in LoadData: %v\nQuery: %s", err, query)
+				cclog.Errorf("Prometheus query error in LoadData: %v\nQuery: %s", err, query)
 				return nil, errors.New("Prometheus query error")
 			}
 			if len(warnings) > 0 {
-				log.Warnf("Warnings: %v\n", warnings)
+				cclog.Warnf("Warnings: %v\n", warnings)
 			}
 
 			// init data structures
@@ -360,7 +359,7 @@ func (pdb *PrometheusDataRepository) LoadStats(
 
 	data, err := pdb.LoadData(job, metrics, []schema.MetricScope{schema.MetricScopeNode}, ctx, 0 /*resolution here*/)
 	if err != nil {
-		log.Warn("Error while loading job for stats")
+		cclog.Warn("Error while loading job for stats")
 		return nil, err
 	}
 	for metric, metricData := range data {
@@ -391,19 +390,19 @@ func (pdb *PrometheusDataRepository) LoadNodeData(
 	for _, scope := range scopes {
 		if scope != schema.MetricScopeNode {
 			logOnce.Do(func() {
-				log.Infof("Note: Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
+				cclog.Infof("Note: Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
 			})
 			continue
 		}
 		for _, metric := range metrics {
 			metricConfig := archive.GetMetricConfig(cluster, metric)
 			if metricConfig == nil {
-				log.Warnf("Error in LoadNodeData: Metric %s for cluster %s not configured", metric, cluster)
+				cclog.Warnf("Error in LoadNodeData: Metric %s for cluster %s not configured", metric, cluster)
 				return nil, errors.New("Prometheus config error")
 			}
 			query, err := pdb.FormatQuery(metric, scope, nodes, cluster)
 			if err != nil {
-				log.Warn("Error while formatting prometheus query")
+				cclog.Warn("Error while formatting prometheus query")
 				return nil, err
 			}
 
@@ -415,11 +414,11 @@ func (pdb *PrometheusDataRepository) LoadNodeData(
 			}
 			result, warnings, err := pdb.queryClient.QueryRange(ctx, query, r)
 			if err != nil {
-				log.Errorf("Prometheus query error in LoadNodeData: %v\n", err)
+				cclog.Errorf("Prometheus query error in LoadNodeData: %v\n", err)
 				return nil, errors.New("Prometheus query error")
 			}
 			if len(warnings) > 0 {
-				log.Warnf("Warnings: %v\n", warnings)
+				cclog.Warnf("Warnings: %v\n", warnings)
 			}
 
 			step := int64(metricConfig.Timestep)
@@ -444,24 +443,145 @@ func (pdb *PrometheusDataRepository) LoadNodeData(
 		}
 	}
 	t1 := time.Since(t0)
-	log.Debugf("LoadNodeData of %v nodes took %s", len(data), t1)
+	cclog.Debugf("LoadNodeData of %v nodes took %s", len(data), t1)
 	return data, nil
 }
 
+// Implemented by NHR@FAU; Used in Job-View StatsTable
+func (pdb *PrometheusDataRepository) LoadScopedStats(
+	job *schema.Job,
+	metrics []string,
+	scopes []schema.MetricScope,
+	ctx context.Context,
+) (schema.ScopedJobStats, error) {
+	// Assumption: pdb.loadData() only returns series node-scope - use node scope for statsTable
+	scopedJobStats := make(schema.ScopedJobStats)
+	data, err := pdb.LoadData(job, metrics, []schema.MetricScope{schema.MetricScopeNode}, ctx, 0 /*resolution here*/)
+	if err != nil {
+		cclog.Warn("Error while loading job for scopedJobStats")
+		return nil, err
+	}
+
+	for metric, metricData := range data {
+		for _, scope := range scopes {
+			if scope != schema.MetricScopeNode {
+				logOnce.Do(func() {
+					cclog.Infof("Note: Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
+				})
+				continue
+			}
+
+			if _, ok := scopedJobStats[metric]; !ok {
+				scopedJobStats[metric] = make(map[schema.MetricScope][]*schema.ScopedStats)
+			}
+
+			if _, ok := scopedJobStats[metric][scope]; !ok {
+				scopedJobStats[metric][scope] = make([]*schema.ScopedStats, 0)
+			}
+
+			for _, series := range metricData[scope].Series {
+				scopedJobStats[metric][scope] = append(scopedJobStats[metric][scope], &schema.ScopedStats{
+					Hostname: series.Hostname,
+					Data:     &series.Statistics,
+				})
+			}
+		}
+	}
+
+	return scopedJobStats, nil
+}
+
+// Implemented by NHR@FAU; Used in NodeList-View
 func (pdb *PrometheusDataRepository) LoadNodeListData(
-	cluster, subCluster, nodeFilter string,
+	cluster, subCluster string,
+	nodes []string,
 	metrics []string,
 	scopes []schema.MetricScope,
 	resolution int,
 	from, to time.Time,
-	page *model.PageRequest,
 	ctx context.Context,
-) (map[string]schema.JobData, int, bool, error) {
+) (map[string]schema.JobData, error) {
+	// Assumption: pdb.loadData() only returns series node-scope - use node scope for NodeList
 
-	var totalNodes int = 0
-	var hasNextPage bool = false
-	// TODO : Implement to be used in NodeList-View
-	log.Infof("LoadNodeListData unimplemented for PrometheusDataRepository, Args: cluster %s, metrics %v, nodeFilter %v, scopes %v", cluster, metrics, nodeFilter, scopes)
+	// Fetch Data, based on pdb.LoadNodeData()
+	t0 := time.Now()
+	// Map of hosts of jobData
+	data := make(map[string]schema.JobData)
 
-	return nil, totalNodes, hasNextPage, errors.New("METRICDATA/INFLUXV2 > unimplemented for PrometheusDataRepository")
+	// query db for each metric
+	// TODO: scopes seems to be always empty
+	if len(scopes) == 0 || !contains(scopes, schema.MetricScopeNode) {
+		scopes = append(scopes, schema.MetricScopeNode)
+	}
+
+	for _, scope := range scopes {
+		if scope != schema.MetricScopeNode {
+			logOnce.Do(func() {
+				cclog.Infof("Note: Scope '%s' requested, but not yet supported: Will return 'node' scope only.", scope)
+			})
+			continue
+		}
+
+		for _, metric := range metrics {
+			metricConfig := archive.GetMetricConfig(cluster, metric)
+			if metricConfig == nil {
+				cclog.Warnf("Error in LoadNodeListData: Metric %s for cluster %s not configured", metric, cluster)
+				return nil, errors.New("Prometheus config error")
+			}
+			query, err := pdb.FormatQuery(metric, scope, nodes, cluster)
+			if err != nil {
+				cclog.Warn("Error while formatting prometheus query")
+				return nil, err
+			}
+
+			// ranged query over all nodes
+			r := promv1.Range{
+				Start: from,
+				End:   to,
+				Step:  time.Duration(metricConfig.Timestep * 1e9),
+			}
+			result, warnings, err := pdb.queryClient.QueryRange(ctx, query, r)
+			if err != nil {
+				cclog.Errorf("Prometheus query error in LoadNodeData: %v\n", err)
+				return nil, errors.New("Prometheus query error")
+			}
+			if len(warnings) > 0 {
+				cclog.Warnf("Warnings: %v\n", warnings)
+			}
+
+			step := int64(metricConfig.Timestep)
+			steps := int64(to.Sub(from).Seconds()) / step
+
+			// iter rows of host, metric, values
+			for _, row := range result.(promm.Matrix) {
+				hostname := strings.TrimSuffix(string(row.Metric["exported_instance"]), pdb.suffix)
+
+				hostdata, ok := data[hostname]
+				if !ok {
+					hostdata = make(schema.JobData)
+					data[hostname] = hostdata
+				}
+
+				metricdata, ok := hostdata[metric]
+				if !ok {
+					metricdata = make(map[schema.MetricScope]*schema.JobMetric)
+					data[hostname][metric] = metricdata
+				}
+
+				// output per host, metric and scope
+				scopeData, ok := metricdata[scope]
+				if !ok {
+					scopeData = &schema.JobMetric{
+						Unit:     metricConfig.Unit,
+						Timestep: metricConfig.Timestep,
+						Series:   []schema.Series{pdb.RowToSeries(from, step, steps, row)},
+					}
+					data[hostname][metric][scope] = scopeData
+				}
+			}
+		}
+	}
+	t1 := time.Since(t0)
+	cclog.Debugf("LoadNodeListData of %v nodes took %s", len(data), t1)
+	return data, nil
 }

internal/metricdata/utils.go

@@ -1,7 +1,8 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package metricdata
 
 import (
@@ -9,15 +10,14 @@ import (
 	"encoding/json"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	"github.com/ClusterCockpit/cc-lib/schema"
 )
 
 var TestLoadDataCallback func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) = func(job *schema.Job, metrics []string, scopes []schema.MetricScope, ctx context.Context, resolution int) (schema.JobData, error) {
 	panic("TODO")
 }
 
-// Only a mock for unit-testing.
+// TestMetricDataRepository is only a mock for unit-testing.
 type TestMetricDataRepository struct{}
 
 func (tmdr *TestMetricDataRepository) Init(_ json.RawMessage) error {
@@ -29,15 +29,25 @@ func (tmdr *TestMetricDataRepository) LoadData(
 	metrics []string,
 	scopes []schema.MetricScope,
 	ctx context.Context,
-	resolution int) (schema.JobData, error) {
-
+	resolution int,
+) (schema.JobData, error) {
 	return TestLoadDataCallback(job, metrics, scopes, ctx, resolution)
 }
 
 func (tmdr *TestMetricDataRepository) LoadStats(
 	job *schema.Job,
-	metrics []string, ctx context.Context) (map[string]map[string]schema.MetricStatistics, error) {
+	metrics []string,
+	ctx context.Context,
+) (map[string]map[string]schema.MetricStatistics, error) {
+	panic("TODO")
+}
 
+func (tmdr *TestMetricDataRepository) LoadScopedStats(
+	job *schema.Job,
+	metrics []string,
+	scopes []schema.MetricScope,
+	ctx context.Context,
+) (schema.ScopedJobStats, error) {
 	panic("TODO")
 }
 
@@ -46,30 +56,27 @@ func (tmdr *TestMetricDataRepository) LoadNodeData(
 	metrics, nodes []string,
 	scopes []schema.MetricScope,
 	from, to time.Time,
-	ctx context.Context) (map[string]map[string][]*schema.JobMetric, error) {
-
+	ctx context.Context,
+) (map[string]map[string][]*schema.JobMetric, error) {
 	panic("TODO")
 }
 
 func (tmdr *TestMetricDataRepository) LoadNodeListData(
-	cluster, subCluster, nodeFilter string,
+	cluster, subCluster string,
+	nodes []string,
 	metrics []string,
 	scopes []schema.MetricScope,
 	resolution int,
 	from, to time.Time,
-	page *model.PageRequest,
 	ctx context.Context,
-) (map[string]schema.JobData, int, bool, error) {
-
+) (map[string]schema.JobData, error) {
 	panic("TODO")
 }
 
-func DeepCopy(jd_temp schema.JobData) schema.JobData {
-	var jd schema.JobData
-
-	jd = make(schema.JobData, len(jd_temp))
-	for k, v := range jd_temp {
-		jd[k] = make(map[schema.MetricScope]*schema.JobMetric, len(jd_temp[k]))
+func DeepCopy(jdTemp schema.JobData) schema.JobData {
+	jd := make(schema.JobData, len(jdTemp))
+	for k, v := range jdTemp {
+		jd[k] = make(map[schema.MetricScope]*schema.JobMetric, len(jdTemp[k]))
 		for k_, v_ := range v {
 			jd[k][k_] = new(schema.JobMetric)
 			jd[k][k_].Series = make([]schema.Series, len(v_.Series))

internal/repository/config.go

@@ -0,0 +1,68 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+
+package repository
+
+import "time"
+
+// RepositoryConfig holds configuration for repository operations.
+// All fields have sensible defaults, so this configuration is optional.
+type RepositoryConfig struct {
+	// CacheSize is the LRU cache size in bytes for job metadata and energy footprints.
+	// Default: 1MB (1024 * 1024 bytes)
+	CacheSize int
+
+	// MaxOpenConnections is the maximum number of open database connections.
+	// Default: 4
+	MaxOpenConnections int
+
+	// MaxIdleConnections is the maximum number of idle database connections.
+	// Default: 4
+	MaxIdleConnections int
+
+	// ConnectionMaxLifetime is the maximum amount of time a connection may be reused.
+	// Default: 1 hour
+	ConnectionMaxLifetime time.Duration
+
+	// ConnectionMaxIdleTime is the maximum amount of time a connection may be idle.
+	// Default: 1 hour
+	ConnectionMaxIdleTime time.Duration
+
+	// MinRunningJobDuration is the minimum duration in seconds for a job to be
+	// considered in "running jobs" queries. This filters out very short jobs.
+	// Default: 600 seconds (10 minutes)
+	MinRunningJobDuration int
+}
+
+// DefaultConfig returns the default repository configuration.
+// These values are optimized for typical deployments.
+func DefaultConfig() *RepositoryConfig {
+	return &RepositoryConfig{
+		CacheSize:             1 * 1024 * 1024, // 1MB
+		MaxOpenConnections:    4,
+		MaxIdleConnections:    4,
+		ConnectionMaxLifetime: time.Hour,
+		ConnectionMaxIdleTime: time.Hour,
+		MinRunningJobDuration: 600, // 10 minutes
+	}
+}
+
+// repoConfig is the package-level configuration instance.
+// It is initialized with defaults and can be overridden via SetConfig.
+var repoConfig *RepositoryConfig = DefaultConfig()
+
+// SetConfig sets the repository configuration.
+// This must be called before any repository initialization (Connect, GetJobRepository, etc.).
+// If not called, default values from DefaultConfig() are used.
+func SetConfig(cfg *RepositoryConfig) {
+	if cfg != nil {
+		repoConfig = cfg
+	}
+}
+
+// GetConfig returns the current repository configuration.
+func GetConfig() *RepositoryConfig {
+	return repoConfig
+}

internal/repository/dbConnection.go

@@ -1,15 +1,18 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package repository
 
 import (
 	"database/sql"
+	"fmt"
+	"net/url"
 	"sync"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 	"github.com/jmoiron/sqlx"
 	"github.com/mattn/go-sqlite3"
 	"github.com/qustavo/sqlhooks/v2"
@@ -33,6 +36,21 @@ type DatabaseOptions struct {
 	ConnectionMaxIdleTime time.Duration
 }
 
+func setupSqlite(db *sql.DB) error {
+	pragmas := []string{
+		"temp_store = memory",
+	}
+
+	for _, pragma := range pragmas {
+		_, err := db.Exec("PRAGMA " + pragma)
+		if err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
 func Connect(driver string, db string) {
 	var err error
 	var dbHandle *sqlx.DB
@@ -40,36 +58,45 @@ func Connect(driver string, db string) {
 	dbConnOnce.Do(func() {
 		opts := DatabaseOptions{
 			URL:                   db,
-			MaxOpenConnections:    4,
-			MaxIdleConnections:    4,
-			ConnectionMaxLifetime: time.Hour,
-			ConnectionMaxIdleTime: time.Hour,
+			MaxOpenConnections:    repoConfig.MaxOpenConnections,
+			MaxIdleConnections:    repoConfig.MaxIdleConnections,
+			ConnectionMaxLifetime: repoConfig.ConnectionMaxLifetime,
+			ConnectionMaxIdleTime: repoConfig.ConnectionMaxIdleTime,
 		}
 
 		switch driver {
 		case "sqlite3":
-			// - Set WAL mode (not strictly necessary each time because it's persisted in the database, but good for first run)
-			// - Set busy timeout, so concurrent writers wait on each other instead of erroring immediately
-			// - Enable foreign key checks
-			opts.URL += "?_journal=WAL&_timeout=5000&_fk=true"
+			// TODO: Have separate DB handles for Writes and Reads
+			// Optimize SQLite connection: https://kerkour.com/sqlite-for-servers
+			connectionURLParams := make(url.Values)
+			connectionURLParams.Add("_txlock", "immediate")
+			connectionURLParams.Add("_journal_mode", "WAL")
+			connectionURLParams.Add("_busy_timeout", "5000")
+			connectionURLParams.Add("_synchronous", "NORMAL")
+			connectionURLParams.Add("_cache_size", "1000000000")
+			connectionURLParams.Add("_foreign_keys", "true")
+			opts.URL = fmt.Sprintf("file:%s?%s", opts.URL, connectionURLParams.Encode())
 
-			if log.Loglevel() == "debug" {
+			if cclog.Loglevel() == "debug" {
 				sql.Register("sqlite3WithHooks", sqlhooks.Wrap(&sqlite3.SQLiteDriver{}, &Hooks{}))
 				dbHandle, err = sqlx.Open("sqlite3WithHooks", opts.URL)
 			} else {
 				dbHandle, err = sqlx.Open("sqlite3", opts.URL)
 			}
+
+			err = setupSqlite(dbHandle.DB)
 			if err != nil {
-				log.Fatal(err)
+				cclog.Abortf("Failed sqlite db setup.\nError: %s\n", err.Error())
 			}
 		case "mysql":
 			opts.URL += "?multiStatements=true"
 			dbHandle, err = sqlx.Open("mysql", opts.URL)
-			if err != nil {
-				log.Fatalf("sqlx.Open() error: %v", err)
-			}
 		default:
-			log.Fatalf("unsupported database driver: %s", driver)
+			cclog.Abortf("DB Connection: Unsupported database driver '%s'.\n", driver)
+		}
+
+		if err != nil {
+			cclog.Abortf("DB Connection: Could not connect to '%s' database with sqlx.Open().\nError: %s\n", driver, err.Error())
 		}
 
 		dbHandle.SetMaxOpenConns(opts.MaxOpenConnections)
@@ -80,14 +107,14 @@ func Connect(driver string, db string) {
 		dbConnInstance = &DBConnection{DB: dbHandle, Driver: driver}
 		err = checkDBVersion(driver, dbHandle.DB)
 		if err != nil {
-			log.Fatal(err)
+			cclog.Abortf("DB Connection: Failed DB version check.\nError: %s\n", err.Error())
 		}
 	})
 }
 
 func GetConnection() *DBConnection {
 	if dbConnInstance == nil {
-		log.Fatalf("Database connection not initialized!")
+		cclog.Fatalf("Database connection not initialized!")
 	}
 
 	return dbConnInstance

internal/repository/hooks.go

@@ -1,5 +1,5 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package repository
@@ -8,21 +8,21 @@ import (
 	"context"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 )
 
 // Hooks satisfies the sqlhook.Hooks interface
 type Hooks struct{}
 
 // Before hook will print the query with it's args and return the context with the timestamp
-func (h *Hooks) Before(ctx context.Context, query string, args ...interface{}) (context.Context, error) {
-	log.Debugf("SQL query %s %q", query, args)
+func (h *Hooks) Before(ctx context.Context, query string, args ...any) (context.Context, error) {
+	cclog.Debugf("SQL query %s %q", query, args)
 	return context.WithValue(ctx, "begin", time.Now()), nil
 }
 
 // After hook will get the timestamp registered on the Before hook and print the elapsed time
-func (h *Hooks) After(ctx context.Context, query string, args ...interface{}) (context.Context, error) {
+func (h *Hooks) After(ctx context.Context, query string, args ...any) (context.Context, error) {
 	begin := ctx.Value("begin").(time.Time)
-	log.Debugf("Took: %s\n", time.Since(begin))
+	cclog.Debugf("Took: %s\n", time.Since(begin))
 	return ctx, nil
 }

internal/repository/job.go

@@ -1,7 +1,64 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
+// Package repository provides the data access layer for cc-backend using the repository pattern.
+//
+// The repository pattern abstracts database operations and provides a clean interface for
+// data access. Each major entity (Job, User, Node, Tag) has its own repository with CRUD
+// operations and specialized queries.
+//
+// # Database Connection
+//
+// Initialize the database connection before using any repository:
+//
+//	repository.Connect("sqlite3", "./var/job.db")
+//	// or for MySQL:
+//	repository.Connect("mysql", "user:password@tcp(localhost:3306)/dbname")
+//
+// # Configuration
+//
+// Optional: Configure repository settings before initialization:
+//
+//	repository.SetConfig(&repository.RepositoryConfig{
+//	    CacheSize: 2 * 1024 * 1024,     // 2MB cache
+//	    MaxOpenConnections: 8,           // Connection pool size
+//	    MinRunningJobDuration: 300,      // Filter threshold
+//	})
+//
+// If not configured, sensible defaults are used automatically.
+//
+// # Repositories
+//
+//   - JobRepository: Job lifecycle management and querying
+//   - UserRepository: User management and authentication
+//   - NodeRepository: Cluster node state tracking
+//   - Tags: Job tagging and categorization
+//
+// # Caching
+//
+// Repositories use LRU caching to improve performance. Cache keys are constructed
+// as "type:id" (e.g., "metadata:123"). Cache is automatically invalidated on
+// mutations to maintain consistency.
+//
+// # Transaction Support
+//
+// For batch operations, use transactions:
+//
+//	t, err := jobRepo.TransactionInit()
+//	if err != nil {
+//	    return err
+//	}
+//	defer t.Rollback() // Rollback if not committed
+//
+//	// Perform operations...
+//	jobRepo.TransactionAdd(t, query, args...)
+//
+//	// Commit when done
+//	if err := t.Commit(); err != nil {
+//	    return err
+//	}
 package repository
 
 import (
@@ -9,16 +66,16 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"maps"
 	"math"
 	"strconv"
 	"sync"
 	"time"
 
-	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
 	"github.com/ClusterCockpit/cc-backend/pkg/archive"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/lrucache"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/lrucache"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	sq "github.com/Masterminds/squirrel"
 	"github.com/jmoiron/sqlx"
 )
@@ -33,6 +90,7 @@ type JobRepository struct {
 	stmtCache *sq.StmtCache
 	cache     *lrucache.Cache
 	driver    string
+	Mutex     sync.Mutex
 }
 
 func GetJobRepository() *JobRepository {
@@ -44,45 +102,56 @@ func GetJobRepository() *JobRepository {
 			driver: db.Driver,
 
 			stmtCache: sq.NewStmtCache(db.DB),
-			cache:     lrucache.New(1024 * 1024),
+			cache:     lrucache.New(repoConfig.CacheSize),
 		}
 	})
 	return jobRepoInstance
 }
 
 var jobColumns []string = []string{
-	"job.id", "job.job_id", "job.hpc_user", "job.project", "job.cluster", "job.subcluster", "job.start_time", "job.cluster_partition", "job.array_job_id",
-	"job.num_nodes", "job.num_hwthreads", "job.num_acc", "job.exclusive", "job.monitoring_status", "job.smt", "job.job_state",
-	"job.duration", "job.walltime", "job.resources", "job.footprint", "job.energy",
+	"job.id", "job.job_id", "job.hpc_user", "job.project", "job.cluster", "job.subcluster",
+	"job.start_time", "job.cluster_partition", "job.array_job_id", "job.num_nodes",
+	"job.num_hwthreads", "job.num_acc", "job.shared", "job.monitoring_status",
+	"job.smt", "job.job_state", "job.duration", "job.walltime", "job.resources",
+	"job.footprint", "job.energy",
 }
 
-func scanJob(row interface{ Scan(...interface{}) error }) (*schema.Job, error) {
+var jobCacheColumns []string = []string{
+	"job_cache.id", "job_cache.job_id", "job_cache.hpc_user", "job_cache.project", "job_cache.cluster",
+	"job_cache.subcluster", "job_cache.start_time", "job_cache.cluster_partition",
+	"job_cache.array_job_id", "job_cache.num_nodes", "job_cache.num_hwthreads",
+	"job_cache.num_acc", "job_cache.shared", "job_cache.monitoring_status", "job_cache.smt",
+	"job_cache.job_state", "job_cache.duration", "job_cache.walltime", "job_cache.resources",
+	"job_cache.footprint", "job_cache.energy",
+}
+
+func scanJob(row interface{ Scan(...any) error }) (*schema.Job, error) {
 	job := &schema.Job{}
 
 	if err := row.Scan(
-		&job.ID, &job.JobID, &job.User, &job.Project, &job.Cluster, &job.SubCluster, &job.StartTimeUnix, &job.Partition, &job.ArrayJobId,
-		&job.NumNodes, &job.NumHWThreads, &job.NumAcc, &job.Exclusive, &job.MonitoringStatus, &job.SMT, &job.State,
+		&job.ID, &job.JobID, &job.User, &job.Project, &job.Cluster, &job.SubCluster,
+		&job.StartTime, &job.Partition, &job.ArrayJobID, &job.NumNodes, &job.NumHWThreads,
+		&job.NumAcc, &job.Shared, &job.MonitoringStatus, &job.SMT, &job.State,
 		&job.Duration, &job.Walltime, &job.RawResources, &job.RawFootprint, &job.Energy); err != nil {
-		log.Warnf("Error while scanning rows (Job): %v", err)
+		cclog.Warnf("Error while scanning rows (Job): %v", err)
 		return nil, err
 	}
 
 	if err := json.Unmarshal(job.RawResources, &job.Resources); err != nil {
-		log.Warn("Error while unmarshaling raw resources json")
+		cclog.Warn("Error while unmarshaling raw resources json")
 		return nil, err
 	}
 	job.RawResources = nil
 
 	if err := json.Unmarshal(job.RawFootprint, &job.Footprint); err != nil {
-		log.Warnf("Error while unmarshaling raw footprint json: %v", err)
+		cclog.Warnf("Error while unmarshaling raw footprint json: %v", err)
 		return nil, err
 	}
 	job.RawFootprint = nil
 
-	job.StartTime = time.Unix(job.StartTimeUnix, 0)
 	// Always ensure accurate duration for running jobs
 	if job.State == schema.JobStateRunning {
-		job.Duration = int32(time.Since(job.StartTime).Seconds())
+		job.Duration = int32(time.Now().Unix() - job.StartTime)
 	}
 
 	return job, nil
@@ -97,7 +166,7 @@ func (r *JobRepository) Optimize() error {
 			return err
 		}
 	case "mysql":
-		log.Info("Optimize currently not supported for mysql driver")
+		cclog.Info("Optimize currently not supported for mysql driver")
 	}
 
 	return nil
@@ -138,17 +207,6 @@ func (r *JobRepository) Flush() error {
 	return nil
 }
 
-func scanJobLink(row interface{ Scan(...interface{}) error }) (*model.JobLink, error) {
-	jobLink := &model.JobLink{}
-	if err := row.Scan(
-		&jobLink.ID, &jobLink.JobID); err != nil {
-		log.Warn("Error while scanning rows (jobLink)")
-		return nil, err
-	}
-
-	return jobLink, nil
-}
-
 func (r *JobRepository) FetchMetadata(job *schema.Job) (map[string]string, error) {
 	start := time.Now()
 	cachekey := fmt.Sprintf("metadata:%d", job.ID)
@@ -159,7 +217,7 @@ func (r *JobRepository) FetchMetadata(job *schema.Job) (map[string]string, error
 
 	if err := sq.Select("job.meta_data").From("job").Where("job.id = ?", job.ID).
 		RunWith(r.stmtCache).QueryRow().Scan(&job.RawMetaData); err != nil {
-		log.Warn("Error while scanning for job metadata")
+		cclog.Warn("Error while scanning for job metadata")
 		return nil, err
 	}
 
@@ -168,12 +226,12 @@ func (r *JobRepository) FetchMetadata(job *schema.Job) (map[string]string, error
 	}
 
 	if err := json.Unmarshal(job.RawMetaData, &job.MetaData); err != nil {
-		log.Warn("Error while unmarshaling raw metadata json")
+		cclog.Warn("Error while unmarshaling raw metadata json")
 		return nil, err
 	}
 
 	r.cache.Put(cachekey, job.MetaData, len(job.RawMetaData), 24*time.Hour)
-	log.Debugf("Timer FetchMetadata %s", time.Since(start))
+	cclog.Debugf("Timer FetchMetadata %s", time.Since(start))
 	return job.MetaData, nil
 }
 
@@ -182,16 +240,14 @@ func (r *JobRepository) UpdateMetadata(job *schema.Job, key, val string) (err er
 	r.cache.Del(cachekey)
 	if job.MetaData == nil {
 		if _, err = r.FetchMetadata(job); err != nil {
-			log.Warnf("Error while fetching metadata for job, DB ID '%v'", job.ID)
+			cclog.Warnf("Error while fetching metadata for job, DB ID '%v'", job.ID)
 			return err
 		}
 	}
 
 	if job.MetaData != nil {
 		cpy := make(map[string]string, len(job.MetaData)+1)
-		for k, v := range job.MetaData {
-			cpy[k] = v
-		}
+		maps.Copy(cpy, job.MetaData)
 		cpy[key] = val
 		job.MetaData = cpy
 	} else {
@@ -199,7 +255,7 @@ func (r *JobRepository) UpdateMetadata(job *schema.Job, key, val string) (err er
 	}
 
 	if job.RawMetaData, err = json.Marshal(job.MetaData); err != nil {
-		log.Warnf("Error while marshaling metadata for job, DB ID '%v'", job.ID)
+		cclog.Warnf("Error while marshaling metadata for job, DB ID '%v'", job.ID)
 		return err
 	}
 
@@ -207,7 +263,7 @@ func (r *JobRepository) UpdateMetadata(job *schema.Job, key, val string) (err er
 		Set("meta_data", job.RawMetaData).
 		Where("job.id = ?", job.ID).
 		RunWith(r.stmtCache).Exec(); err != nil {
-		log.Warnf("Error while updating metadata for job, DB ID '%v'", job.ID)
+		cclog.Warnf("Error while updating metadata for job, DB ID '%v'", job.ID)
 		return err
 	}
 
@@ -220,7 +276,7 @@ func (r *JobRepository) FetchFootprint(job *schema.Job) (map[string]float64, err
 
 	if err := sq.Select("job.footprint").From("job").Where("job.id = ?", job.ID).
 		RunWith(r.stmtCache).QueryRow().Scan(&job.RawFootprint); err != nil {
-		log.Warn("Error while scanning for job footprint")
+		cclog.Warn("Error while scanning for job footprint")
 		return nil, err
 	}
 
@@ -229,11 +285,11 @@ func (r *JobRepository) FetchFootprint(job *schema.Job) (map[string]float64, err
 	}
 
 	if err := json.Unmarshal(job.RawFootprint, &job.Footprint); err != nil {
-		log.Warn("Error while unmarshaling raw footprint json")
+		cclog.Warn("Error while unmarshaling raw footprint json")
 		return nil, err
 	}
 
-	log.Debugf("Timer FetchFootprint %s", time.Since(start))
+	cclog.Debugf("Timer FetchFootprint %s", time.Since(start))
 	return job.Footprint, nil
 }
 
@@ -247,7 +303,7 @@ func (r *JobRepository) FetchEnergyFootprint(job *schema.Job) (map[string]float6
 
 	if err := sq.Select("job.energy_footprint").From("job").Where("job.id = ?", job.ID).
 		RunWith(r.stmtCache).QueryRow().Scan(&job.RawEnergyFootprint); err != nil {
-		log.Warn("Error while scanning for job energy_footprint")
+		cclog.Warn("Error while scanning for job energy_footprint")
 		return nil, err
 	}
 
@@ -256,40 +312,83 @@ func (r *JobRepository) FetchEnergyFootprint(job *schema.Job) (map[string]float6
 	}
 
 	if err := json.Unmarshal(job.RawEnergyFootprint, &job.EnergyFootprint); err != nil {
-		log.Warn("Error while unmarshaling raw energy footprint json")
+		cclog.Warn("Error while unmarshaling raw energy footprint json")
 		return nil, err
 	}
 
 	r.cache.Put(cachekey, job.EnergyFootprint, len(job.EnergyFootprint), 24*time.Hour)
-	log.Debugf("Timer FetchEnergyFootprint %s", time.Since(start))
+	cclog.Debugf("Timer FetchEnergyFootprint %s", time.Since(start))
 	return job.EnergyFootprint, nil
 }
 
-func (r *JobRepository) DeleteJobsBefore(startTime int64) (int, error) {
+func (r *JobRepository) DeleteJobsBefore(startTime int64, omitTagged bool) (int, error) {
 	var cnt int
 	q := sq.Select("count(*)").From("job").Where("job.start_time < ?", startTime)
-	q.RunWith(r.DB).QueryRow().Scan(cnt)
+
+	if omitTagged {
+		q = q.Where("NOT EXISTS (SELECT 1 FROM jobtag WHERE jobtag.job_id = job.id)")
+	}
+
+	if err := q.RunWith(r.DB).QueryRow().Scan(&cnt); err != nil {
+		cclog.Errorf("Error counting jobs before %d: %v", startTime, err)
+		return 0, err
+	}
+
+	// Invalidate cache for jobs being deleted (get job IDs first)
+	if cnt > 0 {
+		var jobIds []int64
+		selectQuery := sq.Select("id").From("job").Where("job.start_time < ?", startTime)
+
+		if omitTagged {
+			selectQuery = selectQuery.Where("NOT EXISTS (SELECT 1 FROM jobtag WHERE jobtag.job_id = job.id)")
+		}
+
+		rows, err := selectQuery.RunWith(r.DB).Query()
+		if err == nil {
+			defer rows.Close()
+			for rows.Next() {
+				var id int64
+				if err := rows.Scan(&id); err == nil {
+					jobIds = append(jobIds, id)
+				}
+			}
+			// Invalidate cache entries
+			for _, id := range jobIds {
+				r.cache.Del(fmt.Sprintf("metadata:%d", id))
+				r.cache.Del(fmt.Sprintf("energyFootprint:%d", id))
+			}
+		}
+	}
+
 	qd := sq.Delete("job").Where("job.start_time < ?", startTime)
+
+	if omitTagged {
+		qd = qd.Where("NOT EXISTS (SELECT 1 FROM jobtag WHERE jobtag.job_id = job.id)")
+	}
 	_, err := qd.RunWith(r.DB).Exec()
 
 	if err != nil {
 		s, _, _ := qd.ToSql()
-		log.Errorf(" DeleteJobsBefore(%d) with %s: error %#v", startTime, s, err)
+		cclog.Errorf(" DeleteJobsBefore(%d) with %s: error %#v", startTime, s, err)
 	} else {
-		log.Debugf("DeleteJobsBefore(%d): Deleted %d jobs", startTime, cnt)
+		cclog.Debugf("DeleteJobsBefore(%d): Deleted %d jobs", startTime, cnt)
 	}
 	return cnt, err
 }
 
-func (r *JobRepository) DeleteJobById(id int64) error {
+func (r *JobRepository) DeleteJobByID(id int64) error {
+	// Invalidate cache entries before deletion
+	r.cache.Del(fmt.Sprintf("metadata:%d", id))
+	r.cache.Del(fmt.Sprintf("energyFootprint:%d", id))
+
 	qd := sq.Delete("job").Where("job.id = ?", id)
 	_, err := qd.RunWith(r.DB).Exec()
 
 	if err != nil {
 		s, _, _ := qd.ToSql()
-		log.Errorf("DeleteJobById(%d) with %s : error %#v", id, s, err)
+		cclog.Errorf("DeleteJobById(%d) with %s : error %#v", id, s, err)
 	} else {
-		log.Debugf("DeleteJobById(%d): Success", id)
+		cclog.Debugf("DeleteJobById(%d): Success", id)
 	}
 	return err
 }
@@ -338,10 +437,10 @@ func (r *JobRepository) FindColumnValue(user *schema.User, searchterm string, ta
 
 		// theSql, args, theErr := theQuery.ToSql()
 		// if theErr != nil {
-		// 	log.Warn("Error while converting query to sql")
+		// 	cclog.Warn("Error while converting query to sql")
 		// 	return "", err
 		// }
-		// log.Debugf("SQL query (FindColumnValue): `%s`, args: %#v", theSql, args)
+		// cclog.Debugf("SQL query (FindColumnValue): `%s`, args: %#v", theSql, args)
 
 		err := theQuery.RunWith(r.stmtCache).QueryRow().Scan(&result)
 
@@ -352,7 +451,7 @@ func (r *JobRepository) FindColumnValue(user *schema.User, searchterm string, ta
 		}
 		return "", ErrNotFound
 	} else {
-		log.Infof("Non-Admin User %s : Requested Query '%s' on table '%s' : Forbidden", user.Name, query, table)
+		cclog.Infof("Non-Admin User %s : Requested Query '%s' on table '%s' : Forbidden", user.Name, query, table)
 		return "", ErrForbidden
 	}
 }
@@ -371,7 +470,7 @@ func (r *JobRepository) FindColumnValues(user *schema.User, query string, table
 				err := rows.Scan(&result)
 				if err != nil {
 					rows.Close()
-					log.Warnf("Error while scanning rows: %v", err)
+					cclog.Warnf("Error while scanning rows: %v", err)
 					return emptyResult, err
 				}
 				results = append(results, result)
@@ -381,7 +480,7 @@ func (r *JobRepository) FindColumnValues(user *schema.User, query string, table
 		return emptyResult, ErrNotFound
 
 	} else {
-		log.Infof("Non-Admin User %s : Requested Query '%s' on table '%s' : Forbidden", user.Name, query, table)
+		cclog.Infof("Non-Admin User %s : Requested Query '%s' on table '%s' : Forbidden", user.Name, query, table)
 		return emptyResult, ErrForbidden
 	}
 }
@@ -389,7 +488,7 @@ func (r *JobRepository) FindColumnValues(user *schema.User, query string, table
 func (r *JobRepository) Partitions(cluster string) ([]string, error) {
 	var err error
 	start := time.Now()
-	partitions := r.cache.Get("partitions:"+cluster, func() (interface{}, time.Duration, int) {
+	partitions := r.cache.Get("partitions:"+cluster, func() (any, time.Duration, int) {
 		parts := []string{}
 		if err = r.DB.Select(&parts, `SELECT DISTINCT job.cluster_partition FROM job WHERE job.cluster = ?;`, cluster); err != nil {
 			return nil, 0, 1000
@@ -400,7 +499,7 @@ func (r *JobRepository) Partitions(cluster string) ([]string, error) {
 	if err != nil {
 		return nil, err
 	}
-	log.Debugf("Timer Partitions %s", time.Since(start))
+	cclog.Debugf("Timer Partitions %s", time.Since(start))
 	return partitions.([]string), nil
 }
 
@@ -414,7 +513,7 @@ func (r *JobRepository) AllocatedNodes(cluster string) (map[string]map[string]in
 		Where("job.cluster = ?", cluster).
 		RunWith(r.stmtCache).Query()
 	if err != nil {
-		log.Error("Error while running query")
+		cclog.Error("Error while running query")
 		return nil, err
 	}
 
@@ -425,11 +524,11 @@ func (r *JobRepository) AllocatedNodes(cluster string) (map[string]map[string]in
 		var resources []*schema.Resource
 		var subcluster string
 		if err := rows.Scan(&raw, &subcluster); err != nil {
-			log.Warn("Error while scanning rows")
+			cclog.Warn("Error while scanning rows")
 			return nil, err
 		}
 		if err := json.Unmarshal(raw, &resources); err != nil {
-			log.Warn("Error while unmarshaling raw resources json")
+			cclog.Warn("Error while unmarshaling raw resources json")
 			return nil, err
 		}
 
@@ -444,63 +543,91 @@ func (r *JobRepository) AllocatedNodes(cluster string) (map[string]map[string]in
 		}
 	}
 
-	log.Debugf("Timer AllocatedNodes %s", time.Since(start))
+	cclog.Debugf("Timer AllocatedNodes %s", time.Since(start))
 	return subclusters, nil
 }
 
 // FIXME: Set duration to requested walltime?
 func (r *JobRepository) StopJobsExceedingWalltimeBy(seconds int) error {
 	start := time.Now()
+	currentTime := time.Now().Unix()
 	res, err := sq.Update("job").
 		Set("monitoring_status", schema.MonitoringStatusArchivingFailed).
 		Set("duration", 0).
 		Set("job_state", schema.JobStateFailed).
 		Where("job.job_state = 'running'").
 		Where("job.walltime > 0").
-		Where(fmt.Sprintf("(%d - job.start_time) > (job.walltime + %d)", time.Now().Unix(), seconds)).
+		Where("(? - job.start_time) > (job.walltime + ?)", currentTime, seconds).
 		RunWith(r.DB).Exec()
 	if err != nil {
-		log.Warn("Error while stopping jobs exceeding walltime")
+		cclog.Warn("Error while stopping jobs exceeding walltime")
 		return err
 	}
 
 	rowsAffected, err := res.RowsAffected()
 	if err != nil {
-		log.Warn("Error while fetching affected rows after stopping due to exceeded walltime")
+		cclog.Warn("Error while fetching affected rows after stopping due to exceeded walltime")
 		return err
 	}
 
 	if rowsAffected > 0 {
-		log.Infof("%d jobs have been marked as failed due to running too long", rowsAffected)
+		cclog.Infof("%d jobs have been marked as failed due to running too long", rowsAffected)
 	}
-	log.Debugf("Timer StopJobsExceedingWalltimeBy %s", time.Since(start))
+	cclog.Debugf("Timer StopJobsExceedingWalltimeBy %s", time.Since(start))
 	return nil
 }
 
+func (r *JobRepository) FindJobIdsByTag(tagID int64) ([]int64, error) {
+	query := sq.Select("job.id").From("job").
+		Join("jobtag ON jobtag.job_id = job.id").
+		Where(sq.Eq{"jobtag.tag_id": tagID}).Distinct()
+	rows, err := query.RunWith(r.stmtCache).Query()
+	if err != nil {
+		cclog.Error("Error while running query")
+		return nil, err
+	}
+	jobIds := make([]int64, 0, 100)
+
+	for rows.Next() {
+		var jobID int64
+
+		if err := rows.Scan(&jobID); err != nil {
+			rows.Close()
+			cclog.Warn("Error while scanning rows")
+			return nil, err
+		}
+
+		jobIds = append(jobIds, jobID)
+	}
+
+	return jobIds, nil
+}
+
+// FIXME: Reconsider filtering short jobs with harcoded threshold
 func (r *JobRepository) FindRunningJobs(cluster string) ([]*schema.Job, error) {
 	query := sq.Select(jobColumns...).From("job").
-		Where(fmt.Sprintf("job.cluster = '%s'", cluster)).
+		Where("job.cluster = ?", cluster).
 		Where("job.job_state = 'running'").
-		Where("job.duration > 600")
+		Where("job.duration > ?", repoConfig.MinRunningJobDuration)
 
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
-		log.Error("Error while running query")
+		cclog.Error("Error while running query")
 		return nil, err
 	}
+	defer rows.Close()
 
 	jobs := make([]*schema.Job, 0, 50)
 	for rows.Next() {
 		job, err := scanJob(rows)
 		if err != nil {
-			rows.Close()
-			log.Warn("Error while scanning rows")
+			cclog.Warn("Error while scanning rows")
 			return nil, err
 		}
 		jobs = append(jobs, job)
 	}
 
-	log.Infof("Return job count %d", len(jobs))
+	cclog.Infof("Return job count %d", len(jobs))
 	return jobs, nil
 }
 
@@ -517,7 +644,7 @@ func (r *JobRepository) UpdateDuration() error {
 	return nil
 }
 
-func (r *JobRepository) FindJobsBetween(startTimeBegin int64, startTimeEnd int64) ([]*schema.Job, error) {
+func (r *JobRepository) FindJobsBetween(startTimeBegin int64, startTimeEnd int64, omitTagged bool) ([]*schema.Job, error) {
 	var query sq.SelectBuilder
 
 	if startTimeBegin == startTimeEnd || startTimeBegin > startTimeEnd {
@@ -525,43 +652,49 @@ func (r *JobRepository) FindJobsBetween(startTimeBegin int64, startTimeEnd int64
 	}
 
 	if startTimeBegin == 0 {
-		log.Infof("Find jobs before %d", startTimeEnd)
-		query = sq.Select(jobColumns...).From("job").Where(fmt.Sprintf(
-			"job.start_time < %d", startTimeEnd))
+		cclog.Infof("Find jobs before %d", startTimeEnd)
+		query = sq.Select(jobColumns...).From("job").Where("job.start_time < ?", startTimeEnd)
 	} else {
-		log.Infof("Find jobs between %d and %d", startTimeBegin, startTimeEnd)
-		query = sq.Select(jobColumns...).From("job").Where(fmt.Sprintf(
-			"job.start_time BETWEEN %d AND %d", startTimeBegin, startTimeEnd))
+		cclog.Infof("Find jobs between %d and %d", startTimeBegin, startTimeEnd)
+		query = sq.Select(jobColumns...).From("job").Where("job.start_time BETWEEN ? AND ?", startTimeBegin, startTimeEnd)
+	}
+
+	if omitTagged {
+		query = query.Where("NOT EXISTS (SELECT 1 FROM jobtag WHERE jobtag.job_id = job.id)")
 	}
 
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
-		log.Error("Error while running query")
+		cclog.Error("Error while running query")
 		return nil, err
 	}
+	defer rows.Close()
 
 	jobs := make([]*schema.Job, 0, 50)
 	for rows.Next() {
 		job, err := scanJob(rows)
 		if err != nil {
-			rows.Close()
-			log.Warn("Error while scanning rows")
+			cclog.Warn("Error while scanning rows")
 			return nil, err
 		}
 		jobs = append(jobs, job)
 	}
 
-	log.Infof("Return job count %d", len(jobs))
+	cclog.Infof("Return job count %d", len(jobs))
 	return jobs, nil
 }
 
 func (r *JobRepository) UpdateMonitoringStatus(job int64, monitoringStatus int32) (err error) {
+	// Invalidate cache entries as monitoring status affects job state
+	r.cache.Del(fmt.Sprintf("metadata:%d", job))
+	r.cache.Del(fmt.Sprintf("energyFootprint:%d", job))
+
 	stmt := sq.Update("job").
 		Set("monitoring_status", monitoringStatus).
 		Where("job.id = ?", job)
 
 	_, err = stmt.RunWith(r.stmtCache).Exec()
-	return
+	return err
 }
 
 func (r *JobRepository) Execute(stmt sq.UpdateBuilder) error {
@@ -581,12 +714,12 @@ func (r *JobRepository) MarkArchived(
 
 func (r *JobRepository) UpdateEnergy(
 	stmt sq.UpdateBuilder,
-	jobMeta *schema.JobMeta,
+	jobMeta *schema.Job,
 ) (sq.UpdateBuilder, error) {
 	/* Note: Only Called for Running Jobs during Intermediate Update or on Archiving */
 	sc, err := archive.GetSubCluster(jobMeta.Cluster, jobMeta.SubCluster)
 	if err != nil {
-		log.Errorf("cannot get subcluster: %s", err.Error())
+		cclog.Errorf("cannot get subcluster: %s", err.Error())
 		return stmt, err
 	}
 	energyFootprint := make(map[string]float64)
@@ -598,10 +731,11 @@ func (r *JobRepository) UpdateEnergy(
 		metricEnergy := 0.0
 		if i, err := archive.MetricIndex(sc.MetricConfig, fp); err == nil {
 			// Note: For DB data, calculate and save as kWh
-			if sc.MetricConfig[i].Energy == "energy" { // this metric has energy as unit (Joules or Wh)
-				log.Warnf("Update EnergyFootprint for Job %d and Metric %s on cluster %s: Set to 'energy' in cluster.json: Not implemented, will return 0.0", jobMeta.JobID, jobMeta.Cluster, fp)
+			switch sc.MetricConfig[i].Energy {
+			case "energy": // this metric has energy as unit (Joules or Wh)
+				cclog.Warnf("Update EnergyFootprint for Job %d and Metric %s on cluster %s: Set to 'energy' in cluster.json: Not implemented, will return 0.0", jobMeta.JobID, jobMeta.Cluster, fp)
 				// FIXME: Needs sum as stats type
-			} else if sc.MetricConfig[i].Energy == "power" { // this metric has power as unit (Watt)
+			case "power": // this metric has power as unit (Watt)
 				// Energy: Power (in Watts) * Time (in Seconds)
 				// Unit: (W * (s / 3600)) / 1000 = kWh
 				// Round 2 Digits: round(Energy * 100) / 100
@@ -611,18 +745,18 @@ func (r *JobRepository) UpdateEnergy(
 				metricEnergy = math.Round(rawEnergy*100.0) / 100.0
 			}
 		} else {
-			log.Warnf("Error while collecting energy metric %s for job, DB ID '%v', return '0.0'", fp, jobMeta.ID)
+			cclog.Warnf("Error while collecting energy metric %s for job, DB ID '%v', return '0.0'", fp, jobMeta.ID)
 		}
 
 		energyFootprint[fp] = metricEnergy
 		totalEnergy += metricEnergy
 
-		// log.Infof("Metric %s Average %f -> %f kWh | Job %d Total -> %f kWh", fp, LoadJobStat(jobMeta, fp, "avg"), energy, jobMeta.JobID, totalEnergy)
+		// cclog.Infof("Metric %s Average %f -> %f kWh | Job %d Total -> %f kWh", fp, LoadJobStat(jobMeta, fp, "avg"), energy, jobMeta.JobID, totalEnergy)
 	}
 
 	var rawFootprint []byte
 	if rawFootprint, err = json.Marshal(energyFootprint); err != nil {
-		log.Warnf("Error while marshaling energy footprint for job INTO BYTES, DB ID '%v'", jobMeta.ID)
+		cclog.Warnf("Error while marshaling energy footprint for job INTO BYTES, DB ID '%v'", jobMeta.ID)
 		return stmt, err
 	}
 
@@ -631,12 +765,12 @@ func (r *JobRepository) UpdateEnergy(
 
 func (r *JobRepository) UpdateFootprint(
 	stmt sq.UpdateBuilder,
-	jobMeta *schema.JobMeta,
+	jobMeta *schema.Job,
 ) (sq.UpdateBuilder, error) {
 	/* Note: Only Called for Running Jobs during Intermediate Update or on Archiving */
 	sc, err := archive.GetSubCluster(jobMeta.Cluster, jobMeta.SubCluster)
 	if err != nil {
-		log.Errorf("cannot get subcluster: %s", err.Error())
+		cclog.Errorf("cannot get subcluster: %s", err.Error())
 		return stmt, err
 	}
 	footprint := make(map[string]float64)
@@ -650,7 +784,7 @@ func (r *JobRepository) UpdateFootprint(
 		}
 
 		if statType != "avg" && statType != "min" && statType != "max" {
-			log.Warnf("unknown statType for footprint update: %s", statType)
+			cclog.Warnf("unknown statType for footprint update: %s", statType)
 			return stmt, fmt.Errorf("unknown statType for footprint update: %s", statType)
 		}
 
@@ -664,7 +798,7 @@ func (r *JobRepository) UpdateFootprint(
 
 	var rawFootprint []byte
 	if rawFootprint, err = json.Marshal(footprint); err != nil {
-		log.Warnf("Error while marshaling footprint for job INTO BYTES, DB ID '%v'", jobMeta.ID)
+		cclog.Warnf("Error while marshaling footprint for job INTO BYTES, DB ID '%v'", jobMeta.ID)
 		return stmt, err
 	}
 

internal/repository/jobCreate.go

@@ -1,44 +1,95 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package repository
 
 import (
 	"encoding/json"
 	"fmt"
 
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
-const NamedJobInsert string = `INSERT INTO job (
+const NamedJobCacheInsert string = `INSERT INTO job_cache (
 	job_id, hpc_user, project, cluster, subcluster, cluster_partition, array_job_id, num_nodes, num_hwthreads, num_acc,
-	exclusive, monitoring_status, smt, job_state, start_time, duration, walltime, footprint, energy, energy_footprint, resources, meta_data
+	shared, monitoring_status, smt, job_state, start_time, duration, walltime, footprint, energy, energy_footprint, resources, meta_data
 ) VALUES (
 	:job_id, :hpc_user, :project, :cluster, :subcluster, :cluster_partition, :array_job_id, :num_nodes, :num_hwthreads, :num_acc,
-  :exclusive, :monitoring_status, :smt, :job_state, :start_time, :duration, :walltime, :footprint,  :energy, :energy_footprint, :resources, :meta_data
+  :shared, :monitoring_status, :smt, :job_state, :start_time, :duration, :walltime, :footprint,  :energy, :energy_footprint, :resources, :meta_data
 );`
 
-func (r *JobRepository) InsertJob(job *schema.JobMeta) (int64, error) {
-	res, err := r.DB.NamedExec(NamedJobInsert, job)
+const NamedJobInsert string = `INSERT INTO job (
+	job_id, hpc_user, project, cluster, subcluster, cluster_partition, array_job_id, num_nodes, num_hwthreads, num_acc,
+	shared, monitoring_status, smt, job_state, start_time, duration, walltime, footprint, energy, energy_footprint, resources, meta_data
+) VALUES (
+	:job_id, :hpc_user, :project, :cluster, :subcluster, :cluster_partition, :array_job_id, :num_nodes, :num_hwthreads, :num_acc,
+  :shared, :monitoring_status, :smt, :job_state, :start_time, :duration, :walltime, :footprint,  :energy, :energy_footprint, :resources, :meta_data
+);`
+
+func (r *JobRepository) InsertJob(job *schema.Job) (int64, error) {
+	r.Mutex.Lock()
+	defer r.Mutex.Unlock()
+
+	res, err := r.DB.NamedExec(NamedJobCacheInsert, job)
 	if err != nil {
-		log.Warn("Error while NamedJobInsert")
+		cclog.Warn("Error while NamedJobInsert")
 		return 0, err
 	}
 	id, err := res.LastInsertId()
 	if err != nil {
-		log.Warn("Error while getting last insert ID")
+		cclog.Warn("Error while getting last insert ID")
 		return 0, err
 	}
 
 	return id, nil
 }
 
+func (r *JobRepository) SyncJobs() ([]*schema.Job, error) {
+	r.Mutex.Lock()
+	defer r.Mutex.Unlock()
+
+	query := sq.Select(jobCacheColumns...).From("job_cache")
+
+	rows, err := query.RunWith(r.stmtCache).Query()
+	if err != nil {
+		cclog.Errorf("Error while running query %v", err)
+		return nil, err
+	}
+	defer rows.Close()
+
+	jobs := make([]*schema.Job, 0, 50)
+	for rows.Next() {
+		job, err := scanJob(rows)
+		if err != nil {
+			cclog.Warn("Error while scanning rows")
+			return nil, err
+		}
+		jobs = append(jobs, job)
+	}
+
+	_, err = r.DB.Exec(
+		"INSERT INTO job (job_id, cluster, subcluster, start_time, hpc_user, project, cluster_partition, array_job_id, num_nodes, num_hwthreads, num_acc, shared, monitoring_status, smt, job_state, duration, walltime, footprint, energy, energy_footprint, resources, meta_data) SELECT job_id, cluster, subcluster, start_time, hpc_user, project, cluster_partition, array_job_id, num_nodes, num_hwthreads, num_acc, shared, monitoring_status, smt, job_state, duration, walltime, footprint, energy, energy_footprint, resources, meta_data FROM job_cache")
+	if err != nil {
+		cclog.Warnf("Error while Job sync: %v", err)
+		return nil, err
+	}
+
+	_, err = r.DB.Exec("DELETE FROM job_cache")
+	if err != nil {
+		cclog.Warnf("Error while Job cache clean: %v", err)
+		return nil, err
+	}
+
+	return jobs, nil
+}
+
 // Start inserts a new job in the table, returning the unique job ID.
 // Statistics are not transfered!
-func (r *JobRepository) Start(job *schema.JobMeta) (id int64, err error) {
+func (r *JobRepository) Start(job *schema.Job) (id int64, err error) {
 	job.RawFootprint, err = json.Marshal(job.Footprint)
 	if err != nil {
 		return -1, fmt.Errorf("REPOSITORY/JOB > encoding footprint field failed: %w", err)
@@ -59,17 +110,39 @@ func (r *JobRepository) Start(job *schema.JobMeta) (id int64, err error) {
 
 // Stop updates the job with the database id jobId using the provided arguments.
 func (r *JobRepository) Stop(
-	jobId int64,
+	jobID int64,
 	duration int32,
 	state schema.JobState,
 	monitoringStatus int32,
 ) (err error) {
+	// Invalidate cache entries as job state is changing
+	r.cache.Del(fmt.Sprintf("metadata:%d", jobID))
+	r.cache.Del(fmt.Sprintf("energyFootprint:%d", jobID))
+
 	stmt := sq.Update("job").
 		Set("job_state", state).
 		Set("duration", duration).
 		Set("monitoring_status", monitoringStatus).
-		Where("job.id = ?", jobId)
+		Where("job.id = ?", jobID)
 
 	_, err = stmt.RunWith(r.stmtCache).Exec()
-	return
+	return err
+}
+
+func (r *JobRepository) StopCached(
+	jobID int64,
+	duration int32,
+	state schema.JobState,
+	monitoringStatus int32,
+) (err error) {
+	// Note: StopCached updates job_cache table, not the main job table
+	// Cache invalidation happens when job is synced to main table
+	stmt := sq.Update("job_cache").
+		Set("job_state", state).
+		Set("duration", duration).
+		Set("monitoring_status", monitoringStatus).
+		Where("job_cache.id = ?", jobID)
+
+	_, err = stmt.RunWith(r.stmtCache).Exec()
+	return err
 }

internal/repository/jobFind.go

@@ -1,7 +1,8 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package repository
 
 import (
@@ -11,8 +12,8 @@ import (
 	"time"
 
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
@@ -22,13 +23,13 @@ import (
 // It returns a pointer to a schema.Job data structure and an error variable.
 // To check if no job was found test err == sql.ErrNoRows
 func (r *JobRepository) Find(
-	jobId *int64,
+	jobID *int64,
 	cluster *string,
 	startTime *int64,
 ) (*schema.Job, error) {
 	start := time.Now()
 	q := sq.Select(jobColumns...).From("job").
-		Where("job.job_id = ?", *jobId)
+		Where("job.job_id = ?", *jobID)
 
 	if cluster != nil {
 		q = q.Where("job.cluster = ?", *cluster)
@@ -39,23 +40,43 @@ func (r *JobRepository) Find(
 
 	q = q.OrderBy("job.id DESC") // always use newest matching job by db id if more than one match
 
-	log.Debugf("Timer Find %s", time.Since(start))
+	cclog.Debugf("Timer Find %s", time.Since(start))
 	return scanJob(q.RunWith(r.stmtCache).QueryRow())
 }
 
-// Find executes a SQL query to find a specific batch job.
-// The job is queried using the batch job id, the cluster name,
-// and the start time of the job in UNIX epoch time seconds.
-// It returns a pointer to a schema.Job data structure and an error variable.
-// To check if no job was found test err == sql.ErrNoRows
+func (r *JobRepository) FindCached(
+	jobID *int64,
+	cluster *string,
+	startTime *int64,
+) (*schema.Job, error) {
+	q := sq.Select(jobCacheColumns...).From("job_cache").
+		Where("job_cache.job_id = ?", *jobID)
+
+	if cluster != nil {
+		q = q.Where("job_cache.cluster = ?", *cluster)
+	}
+	if startTime != nil {
+		q = q.Where("job_cache.start_time = ?", *startTime)
+	}
+
+	q = q.OrderBy("job_cache.id DESC") // always use newest matching job by db id if more than one match
+
+	return scanJob(q.RunWith(r.stmtCache).QueryRow())
+}
+
+// FindAll executes a SQL query to find all batch jobs matching the given criteria.
+// Jobs are queried using the batch job id, and optionally filtered by cluster name
+// and start time (UNIX epoch time seconds).
+// It returns a slice of pointers to schema.Job data structures and an error variable.
+// An empty slice is returned if no matching jobs are found.
 func (r *JobRepository) FindAll(
-	jobId *int64,
+	jobID *int64,
 	cluster *string,
 	startTime *int64,
 ) ([]*schema.Job, error) {
 	start := time.Now()
 	q := sq.Select(jobColumns...).From("job").
-		Where("job.job_id = ?", *jobId)
+		Where("job.job_id = ?", *jobID)
 
 	if cluster != nil {
 		q = q.Where("job.cluster = ?", *cluster)
@@ -66,30 +87,66 @@ func (r *JobRepository) FindAll(
 
 	rows, err := q.RunWith(r.stmtCache).Query()
 	if err != nil {
-		log.Error("Error while running query")
+		cclog.Error("Error while running query")
 		return nil, err
 	}
+	defer rows.Close()
 
 	jobs := make([]*schema.Job, 0, 10)
 	for rows.Next() {
 		job, err := scanJob(rows)
 		if err != nil {
-			log.Warn("Error while scanning rows")
+			cclog.Warn("Error while scanning rows")
 			return nil, err
 		}
 		jobs = append(jobs, job)
 	}
-	log.Debugf("Timer FindAll %s", time.Since(start))
+	cclog.Debugf("Timer FindAll %s", time.Since(start))
 	return jobs, nil
 }
 
-// FindById executes a SQL query to find a specific batch job.
+// GetJobList returns job IDs for non-running jobs.
+// This is useful to process large job counts and intended to be used
+// together with FindById to process jobs one by one.
+// Use limit and offset for pagination. Use limit=0 to get all results (not recommended for large datasets).
+func (r *JobRepository) GetJobList(limit int, offset int) ([]int64, error) {
+	query := sq.Select("id").From("job").
+		Where("job.job_state != 'running'")
+
+	// Add pagination if limit is specified
+	if limit > 0 {
+		query = query.Limit(uint64(limit)).Offset(uint64(offset))
+	}
+
+	rows, err := query.RunWith(r.stmtCache).Query()
+	if err != nil {
+		cclog.Error("Error while running query")
+		return nil, err
+	}
+	defer rows.Close()
+
+	jl := make([]int64, 0, 1000)
+	for rows.Next() {
+		var id int64
+		err := rows.Scan(&id)
+		if err != nil {
+			cclog.Warn("Error while scanning rows")
+			return nil, err
+		}
+		jl = append(jl, id)
+	}
+
+	cclog.Infof("Return job count %d", len(jl))
+	return jl, nil
+}
+
+// FindByID executes a SQL query to find a specific batch job.
 // The job is queried using the database id.
 // It returns a pointer to a schema.Job data structure and an error variable.
 // To check if no job was found test err == sql.ErrNoRows
-func (r *JobRepository) FindById(ctx context.Context, jobId int64) (*schema.Job, error) {
+func (r *JobRepository) FindByID(ctx context.Context, jobID int64) (*schema.Job, error) {
 	q := sq.Select(jobColumns...).
-		From("job").Where("job.id = ?", jobId)
+		From("job").Where("job.id = ?", jobID)
 
 	q, qerr := SecurityCheck(ctx, q)
 	if qerr != nil {
@@ -99,14 +156,14 @@ func (r *JobRepository) FindById(ctx context.Context, jobId int64) (*schema.Job,
 	return scanJob(q.RunWith(r.stmtCache).QueryRow())
 }
 
-// FindByIdWithUser executes a SQL query to find a specific batch job.
+// FindByIDWithUser executes a SQL query to find a specific batch job.
 // The job is queried using the database id. The user is passed directly,
 // instead as part of the context.
 // It returns a pointer to a schema.Job data structure and an error variable.
 // To check if no job was found test err == sql.ErrNoRows
-func (r *JobRepository) FindByIdWithUser(user *schema.User, jobId int64) (*schema.Job, error) {
+func (r *JobRepository) FindByIDWithUser(user *schema.User, jobID int64) (*schema.Job, error) {
 	q := sq.Select(jobColumns...).
-		From("job").Where("job.id = ?", jobId)
+		From("job").Where("job.id = ?", jobID)
 
 	q, qerr := SecurityCheckWithUser(user, q)
 	if qerr != nil {
@@ -116,24 +173,24 @@ func (r *JobRepository) FindByIdWithUser(user *schema.User, jobId int64) (*schem
 	return scanJob(q.RunWith(r.stmtCache).QueryRow())
 }
 
-// FindByIdDirect executes a SQL query to find a specific batch job.
+// FindByIDDirect executes a SQL query to find a specific batch job.
 // The job is queried using the database id.
 // It returns a pointer to a schema.Job data structure and an error variable.
 // To check if no job was found test err == sql.ErrNoRows
-func (r *JobRepository) FindByIdDirect(jobId int64) (*schema.Job, error) {
+func (r *JobRepository) FindByIDDirect(jobID int64) (*schema.Job, error) {
 	q := sq.Select(jobColumns...).
-		From("job").Where("job.id = ?", jobId)
+		From("job").Where("job.id = ?", jobID)
 	return scanJob(q.RunWith(r.stmtCache).QueryRow())
 }
 
-// FindByJobId executes a SQL query to find a specific batch job.
+// FindByJobID executes a SQL query to find a specific batch job.
 // The job is queried using the slurm id and the clustername.
 // It returns a pointer to a schema.Job data structure and an error variable.
 // To check if no job was found test err == sql.ErrNoRows
-func (r *JobRepository) FindByJobId(ctx context.Context, jobId int64, startTime int64, cluster string) (*schema.Job, error) {
+func (r *JobRepository) FindByJobID(ctx context.Context, jobID int64, startTime int64, cluster string) (*schema.Job, error) {
 	q := sq.Select(jobColumns...).
 		From("job").
-		Where("job.job_id = ?", jobId).
+		Where("job.job_id = ?", jobID).
 		Where("job.cluster = ?", cluster).
 		Where("job.start_time = ?", startTime)
 
@@ -149,10 +206,10 @@ func (r *JobRepository) FindByJobId(ctx context.Context, jobId int64, startTime
 // The job is queried using the slurm id,a username and the cluster.
 // It returns a bool.
 // If job was found, user is owner: test err != sql.ErrNoRows
-func (r *JobRepository) IsJobOwner(jobId int64, startTime int64, user string, cluster string) bool {
+func (r *JobRepository) IsJobOwner(jobID int64, startTime int64, user string, cluster string) bool {
 	q := sq.Select("id").
 		From("job").
-		Where("job.job_id = ?", jobId).
+		Where("job.job_id = ?", jobID).
 		Where("job.hpc_user = ?", user).
 		Where("job.cluster = ?", cluster).
 		Where("job.start_time = ?", startTime)
@@ -178,7 +235,7 @@ func (r *JobRepository) FindConcurrentJobs(
 	var startTime int64
 	var stopTime int64
 
-	startTime = job.StartTimeUnix
+	startTime = job.StartTime
 	hostname := job.Resources[0].Hostname
 
 	if job.State == schema.JobStateRunning {
@@ -194,59 +251,63 @@ func (r *JobRepository) FindConcurrentJobs(
 
 	queryRunning := query.Where("job.job_state = ?").Where("(job.start_time BETWEEN ? AND ? OR job.start_time < ?)",
 		"running", startTimeTail, stopTimeTail, startTime)
-	queryRunning = queryRunning.Where("job.resources LIKE ?", fmt.Sprint("%", hostname, "%"))
+	// Get At Least One Exact Hostname Match from JSON Resources Array in Database
+	queryRunning = queryRunning.Where("EXISTS (SELECT 1 FROM json_each(job.resources) WHERE json_extract(value, '$.hostname') = ?)", hostname)
 
 	query = query.Where("job.job_state != ?").Where("((job.start_time BETWEEN ? AND ?) OR (job.start_time + job.duration) BETWEEN ? AND ? OR (job.start_time < ?) AND (job.start_time + job.duration) > ?)",
 		"running", startTimeTail, stopTimeTail, startTimeFront, stopTimeTail, startTime, stopTime)
-	query = query.Where("job.resources LIKE ?", fmt.Sprint("%", hostname, "%"))
+	// Get At Least One Exact Hostname Match from JSON Resources Array in Database
+	query = query.Where("EXISTS (SELECT 1 FROM json_each(job.resources) WHERE json_extract(value, '$.hostname') = ?)", hostname)
 
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
-		log.Errorf("Error while running query: %v", err)
+		cclog.Errorf("Error while running query: %v", err)
 		return nil, err
 	}
+	defer rows.Close()
 
 	items := make([]*model.JobLink, 0, 10)
 	queryString := fmt.Sprintf("cluster=%s", job.Cluster)
 
 	for rows.Next() {
-		var id, jobId, startTime sql.NullInt64
+		var id, jobID, startTime sql.NullInt64
 
-		if err = rows.Scan(&id, &jobId, &startTime); err != nil {
-			log.Warn("Error while scanning rows")
+		if err = rows.Scan(&id, &jobID, &startTime); err != nil {
+			cclog.Warn("Error while scanning rows")
 			return nil, err
 		}
 
 		if id.Valid {
-			queryString += fmt.Sprintf("&jobId=%d", int(jobId.Int64))
+			queryString += fmt.Sprintf("&jobId=%d", int(jobID.Int64))
 			items = append(items,
 				&model.JobLink{
 					ID:    fmt.Sprint(id.Int64),
-					JobID: int(jobId.Int64),
+					JobID: int(jobID.Int64),
 				})
 		}
 	}
 
 	rows, err = queryRunning.RunWith(r.stmtCache).Query()
 	if err != nil {
-		log.Errorf("Error while running query: %v", err)
+		cclog.Errorf("Error while running query: %v", err)
 		return nil, err
 	}
+	defer rows.Close()
 
 	for rows.Next() {
-		var id, jobId, startTime sql.NullInt64
+		var id, jobID, startTime sql.NullInt64
 
-		if err := rows.Scan(&id, &jobId, &startTime); err != nil {
-			log.Warn("Error while scanning rows")
+		if err := rows.Scan(&id, &jobID, &startTime); err != nil {
+			cclog.Warn("Error while scanning rows")
 			return nil, err
 		}
 
 		if id.Valid {
-			queryString += fmt.Sprintf("&jobId=%d", int(jobId.Int64))
+			queryString += fmt.Sprintf("&jobId=%d", int(jobID.Int64))
 			items = append(items,
 				&model.JobLink{
 					ID:    fmt.Sprint(id.Int64),
-					JobID: int(jobId.Int64),
+					JobID: int(jobID.Int64),
 				})
 		}
 	}

internal/repository/jobHooks.go

@@ -0,0 +1,57 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-backend.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+package repository
+
+import (
+	"sync"
+
+	"github.com/ClusterCockpit/cc-lib/schema"
+)
+
+type JobHook interface {
+	JobStartCallback(job *schema.Job)
+	JobStopCallback(job *schema.Job)
+}
+
+var (
+	initOnce sync.Once
+	hooks    []JobHook
+)
+
+func RegisterJobJook(hook JobHook) {
+	initOnce.Do(func() {
+		hooks = make([]JobHook, 0)
+	})
+
+	if hook != nil {
+		hooks = append(hooks, hook)
+	}
+}
+
+func CallJobStartHooks(jobs []*schema.Job) {
+	if hooks == nil {
+		return
+	}
+
+	for _, hook := range hooks {
+		if hook != nil {
+			for _, job := range jobs {
+				hook.JobStartCallback(job)
+			}
+		}
+	}
+}
+
+func CallJobStopHooks(job *schema.Job) {
+	if hooks == nil {
+		return
+	}
+
+	for _, hook := range hooks {
+		if hook != nil {
+			hook.JobStopCallback(job)
+		}
+	}
+}

internal/repository/jobQuery.go

@@ -1,5 +1,5 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package repository
@@ -12,9 +12,10 @@ import (
 	"strings"
 	"time"
 
+	"github.com/ClusterCockpit/cc-backend/internal/config"
 	"github.com/ClusterCockpit/cc-backend/internal/graph/model"
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	sq "github.com/Masterminds/squirrel"
 )
 
@@ -67,7 +68,8 @@ func (r *JobRepository) QueryJobs(
 
 	rows, err := query.RunWith(r.stmtCache).Query()
 	if err != nil {
-		log.Errorf("Error while running query: %v", err)
+		queryString, queryVars, _ := query.ToSql()
+		cclog.Errorf("Error while running query '%s' %v: %v", queryString, queryVars, err)
 		return nil, err
 	}
 
@@ -76,7 +78,7 @@ func (r *JobRepository) QueryJobs(
 		job, err := scanJob(rows)
 		if err != nil {
 			rows.Close()
-			log.Warn("Error while scanning rows (Jobs)")
+			cclog.Warn("Error while scanning rows (Jobs)")
 			return nil, err
 		}
 		jobs = append(jobs, job)
@@ -122,7 +124,7 @@ func SecurityCheckWithUser(user *schema.User, query sq.SelectBuilder) (sq.Select
 		if len(user.Projects) != 0 {
 			return query.Where(sq.Or{sq.Eq{"job.project": user.Projects}, sq.Eq{"job.hpc_user": user.Username}}), nil
 		} else {
-			log.Debugf("Manager-User '%s' has no defined projects to lookup! Query only personal jobs ...", user.Username)
+			cclog.Debugf("Manager-User '%s' has no defined projects to lookup! Query only personal jobs ...", user.Username)
 			return query.Where("job.hpc_user = ?", user.Username), nil
 		}
 	case user.HasRole(schema.RoleUser): // User : Only personal jobs
@@ -145,6 +147,11 @@ func BuildWhereClause(filter *model.JobFilter, query sq.SelectBuilder) sq.Select
 		// This is an OR-Logic query: Returns all distinct jobs with at least one of the requested tags; TODO: AND-Logic query?
 		query = query.Join("jobtag ON jobtag.job_id = job.id").Where(sq.Eq{"jobtag.tag_id": filter.Tags}).Distinct()
 	}
+	if filter.DbID != nil {
+		dbIDs := make([]string, len(filter.DbID))
+		copy(dbIDs, filter.DbID)
+		query = query.Where(sq.Eq{"job.id": dbIDs})
+	}
 	if filter.JobID != nil {
 		query = buildStringCondition("job.job_id", filter.JobID, query)
 	}
@@ -176,8 +183,8 @@ func BuildWhereClause(filter *model.JobFilter, query sq.SelectBuilder) sq.Select
 		now := time.Now().Unix() // There does not seam to be a portable way to get the current unix timestamp accross different DBs.
 		query = query.Where("(job.job_state != 'running' OR (? - job.start_time) > ?)", now, *filter.MinRunningFor)
 	}
-	if filter.Exclusive != nil {
-		query = query.Where("job.exclusive = ?", *filter.Exclusive)
+	if filter.Shared != nil {
+		query = query.Where("job.shared = ?", *filter.Shared)
 	}
 	if filter.State != nil {
 		states := make([]string, len(filter.State))
@@ -197,7 +204,7 @@ func BuildWhereClause(filter *model.JobFilter, query sq.SelectBuilder) sq.Select
 		query = buildIntCondition("job.num_hwthreads", filter.NumHWThreads, query)
 	}
 	if filter.Node != nil {
-		query = buildStringCondition("job.resources", filter.Node, query)
+		query = buildResourceJsonCondition("hostname", filter.Node, query)
 	}
 	if filter.Energy != nil {
 		query = buildFloatCondition("job.energy", filter.Energy, query)
@@ -210,7 +217,7 @@ func BuildWhereClause(filter *model.JobFilter, query sq.SelectBuilder) sq.Select
 	return query
 }
 
-func buildIntCondition(field string, cond *schema.IntRange, query sq.SelectBuilder) sq.SelectBuilder {
+func buildIntCondition(field string, cond *config.IntRange, query sq.SelectBuilder) sq.SelectBuilder {
 	return query.Where(field+" BETWEEN ? AND ?", cond.From, cond.To)
 }
 
@@ -218,7 +225,7 @@ func buildFloatCondition(field string, cond *model.FloatRange, query sq.SelectBu
 	return query.Where(field+" BETWEEN ? AND ?", cond.From, cond.To)
 }
 
-func buildTimeCondition(field string, cond *schema.TimeRange, query sq.SelectBuilder) sq.SelectBuilder {
+func buildTimeCondition(field string, cond *config.TimeRange, query sq.SelectBuilder) sq.SelectBuilder {
 	if cond.From != nil && cond.To != nil {
 		return query.Where(field+" BETWEEN ? AND ?", cond.From.Unix(), cond.To.Unix())
 	} else if cond.From != nil {
@@ -238,7 +245,7 @@ func buildTimeCondition(field string, cond *schema.TimeRange, query sq.SelectBui
 		case "last30d":
 			then = now - (60 * 60 * 24 * 30)
 		default:
-			log.Debugf("No known named timeRange: startTime.range = %s", cond.Range)
+			cclog.Debugf("No known named timeRange: startTime.range = %s", cond.Range)
 			return query
 		}
 		return query.Where(field+" BETWEEN ? AND ?", then, now)
@@ -299,6 +306,28 @@ func buildMetaJsonCondition(jsonField string, cond *model.StringInput, query sq.
 	return query
 }
 
+func buildResourceJsonCondition(jsonField string, cond *model.StringInput, query sq.SelectBuilder) sq.SelectBuilder {
+	// Verify and Search Only in Valid Jsons
+	query = query.Where("JSON_VALID(resources)")
+	// add "AND" Sql query Block for field match
+	if cond.Eq != nil {
+		return query.Where("EXISTS (SELECT 1 FROM json_each(job.resources) WHERE json_extract(value, \"$."+jsonField+"\") = ?)", *cond.Eq)
+	}
+	if cond.Neq != nil { // Currently Unused
+		return query.Where("EXISTS (SELECT 1 FROM json_each(job.resources) WHERE json_extract(value, \"$."+jsonField+"\") != ?)", *cond.Neq)
+	}
+	if cond.StartsWith != nil { // Currently Unused
+		return query.Where("EXISTS (SELECT 1 FROM json_each(job.resources) WHERE json_extract(value, \"$."+jsonField+"\")) LIKE ?)", fmt.Sprint(*cond.StartsWith, "%"))
+	}
+	if cond.EndsWith != nil { // Currently Unused
+		return query.Where("EXISTS (SELECT 1 FROM json_each(job.resources) WHERE json_extract(value, \"$."+jsonField+"\") LIKE ?)", fmt.Sprint("%", *cond.EndsWith))
+	}
+	if cond.Contains != nil {
+		return query.Where("EXISTS (SELECT 1 FROM json_each(job.resources) WHERE json_extract(value, \"$."+jsonField+"\") LIKE ?)", fmt.Sprint("%", *cond.Contains, "%"))
+	}
+	return query
+}
+
 var (
 	matchFirstCap = regexp.MustCompile("(.)([A-Z][a-z]+)")
 	matchAllCap   = regexp.MustCompile("([a-z0-9])([A-Z])")
@@ -307,7 +336,7 @@ var (
 func toSnakeCase(str string) string {
 	for _, c := range str {
 		if c == '\'' || c == '\\' {
-			log.Panic("toSnakeCase() attack vector!")
+			cclog.Panic("toSnakeCase() attack vector!")
 		}
 	}
 

internal/repository/job_test.go

@@ -1,5 +1,5 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
 package repository
@@ -8,39 +8,40 @@ import (
 	"context"
 	"fmt"
 	"testing"
+	"time"
 
-	"github.com/ClusterCockpit/cc-backend/pkg/schema"
+	"github.com/ClusterCockpit/cc-lib/schema"
 	_ "github.com/mattn/go-sqlite3"
 )
 
 func TestFind(t *testing.T) {
 	r := setup(t)
 
-	jobId, cluster, startTime := int64(398998), "fritz", int64(1675957496)
-	job, err := r.Find(&jobId, &cluster, &startTime)
+	jobID, cluster, startTime := int64(398800), "fritz", int64(1675954712)
+	job, err := r.Find(&jobID, &cluster, &startTime)
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	// fmt.Printf("%+v", job)
 
-	if job.ID != 5 {
-		t.Errorf("wrong summary for diagnostic 3\ngot: %d \nwant: 1366", job.JobID)
+	if *job.ID != 345 {
+		t.Errorf("wrong summary for diagnostic \ngot: %d \nwant: 345", job.JobID)
 	}
 }
 
 func TestFindById(t *testing.T) {
 	r := setup(t)
 
-	job, err := r.FindById(getContext(t), 5)
+	job, err := r.FindByID(getContext(t), 338)
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	// fmt.Printf("%+v", job)
 
-	if job.JobID != 398998 {
-		t.Errorf("wrong summary for diagnostic 3\ngot: %d \nwant: 1404396", job.JobID)
+	if job.JobID != 398793 {
+		t.Errorf("wrong summary for diagnostic \ngot: %d \nwant: 1404396", job.JobID)
 	}
 }
 
@@ -71,3 +72,61 @@ func TestGetTags(t *testing.T) {
 		t.Errorf("wrong tag count \ngot: %d \nwant: 0", counts["bandwidth"])
 	}
 }
+
+func TestFindJobsBetween(t *testing.T) {
+	r := setup(t)
+
+	// 1. Find a job to use (Find all jobs)
+	// We use a large time range to ensure we get something if it exists
+	jobs, err := r.FindJobsBetween(0, 9999999999, false)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(jobs) == 0 {
+		t.Fatal("No jobs in test db")
+	}
+
+	targetJob := jobs[0]
+
+	// 2. Create a tag
+	tagName := fmt.Sprintf("testtag_%d", time.Now().UnixNano())
+	tagId, err := r.CreateTag("testtype", tagName, "global")
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// 3. Link Tag (Manually to avoid archive dependency side-effects in unit test)
+	_, err = r.DB.Exec("INSERT INTO jobtag (job_id, tag_id) VALUES (?, ?)", *targetJob.ID, tagId)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	// 4. Search with omitTagged = false (Should find the job)
+	jobsFound, err := r.FindJobsBetween(0, 9999999999, false)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	var found bool
+	for _, j := range jobsFound {
+		if *j.ID == *targetJob.ID {
+			found = true
+			break
+		}
+	}
+	if !found {
+		t.Errorf("Target job %d should be found when omitTagged=false", *targetJob.ID)
+	}
+
+	// 5. Search with omitTagged = true (Should NOT find the job)
+	jobsFiltered, err := r.FindJobsBetween(0, 9999999999, true)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	for _, j := range jobsFiltered {
+		if *j.ID == *targetJob.ID {
+			t.Errorf("Target job %d should NOT be found when omitTagged=true", *targetJob.ID)
+		}
+	}
+}

internal/repository/migration.go

@@ -1,7 +1,8 @@
 // Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
+// All rights reserved. This file is part of cc-backend.
 // Use of this source code is governed by a MIT-style
 // license that can be found in the LICENSE file.
+
 package repository
 
 import (
@@ -9,14 +10,14 @@ import (
 	"embed"
 	"fmt"
 
-	"github.com/ClusterCockpit/cc-backend/pkg/log"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 	"github.com/golang-migrate/migrate/v4"
 	"github.com/golang-migrate/migrate/v4/database/mysql"
 	"github.com/golang-migrate/migrate/v4/database/sqlite3"
 	"github.com/golang-migrate/migrate/v4/source/iofs"
 )
 
-const Version uint = 8
+const Version uint = 10
 
 //go:embed migrations/*
 var migrationFiles embed.FS
@@ -54,13 +55,13 @@ func checkDBVersion(backend string, db *sql.DB) error {
 			return err
 		}
 	default:
-		log.Fatalf("unsupported database backend: %s", backend)
+		cclog.Abortf("Migration: Unsupported database backend '%s'.\n", backend)
 	}
 
 	v, dirty, err := m.Version()
 	if err != nil {
 		if err == migrate.ErrNilVersion {
-			log.Warn("Legacy database without version or missing database file!")
+			cclog.Warn("Legacy database without version or missing database file!")
 		} else {
 			return err
 		}
@@ -84,7 +85,7 @@ func getMigrateInstance(backend string, db string) (m *migrate.Migrate, err erro
 	case "sqlite3":
 		d, err := iofs.New(migrationFiles, "migrations/sqlite3")
 		if err != nil {
-			log.Fatal(err)
+			cclog.Fatal(err)
 		}
 
 		m, err = migrate.NewWithSourceInstance("iofs", d, fmt.Sprintf("sqlite3://%s?_foreign_keys=on", db))
@@ -102,7 +103,7 @@ func getMigrateInstance(backend string, db string) (m *migrate.Migrate, err erro
 			return m, err
 		}
 	default:
-		log.Fatalf("unsupported database backend: %s", backend)
+		cclog.Abortf("Migration: Unsupported database backend '%s'.\n", backend)
 	}
 
 	return m, nil
@@ -115,8 +116,17 @@ func MigrateDB(backend string, db string) error {
 	}
 
 	v, dirty, err := m.Version()
+	if err != nil {
+		if err == migrate.ErrNilVersion {
+			cclog.Info("Legacy database without version or missing database file!")
+		} else {
+			return err
+		}
+	}
 
-	log.Infof("unsupported database version %d, need %d.\nPlease backup your database file and run cc-backend -migrate-db", v, Version)
+	if v < Version {
+		cclog.Infof("unsupported database version %d, need %d.\nPlease backup your database file and run cc-backend -migrate-db", v, Version)
+	}
 
 	if dirty {
 		return fmt.Errorf("last migration to version %d has failed, please fix the db manually and force version with -force-db flag", Version)
@@ -124,7 +134,7 @@ func MigrateDB(backend string, db string) error {
 
 	if err := m.Up(); err != nil {
 		if err == migrate.ErrNoChange {
-			log.Info("DB already up to date!")
+			cclog.Info("DB already up to date!")
 		} else {
 			return err
 		}
@@ -142,7 +152,7 @@ func RevertDB(backend string, db string) error {
 
 	if err := m.Migrate(Version - 1); err != nil {
 		if err == migrate.ErrNoChange {
-			log.Info("DB already up to date!")
+			cclog.Info("DB already up to date!")
 		} else {
 			return err
 		}

internal/repository/migrations/sqlite3/09_add-job-cache.down.sql

@@ -0,0 +1 @@
+DROP TABLE IF EXISTS job_cache;

internal/repository/migrations/sqlite3/09_add-job-cache.up.sql

@@ -0,0 +1,231 @@
+CREATE TABLE "job_cache" (
+    id INTEGER PRIMARY KEY,
+    job_id BIGINT NOT NULL,
+    cluster VARCHAR(255) NOT NULL,
+    subcluster VARCHAR(255) NOT NULL,
+    submit_time BIGINT NOT NULL DEFAULT 0, -- Unix timestamp
+    start_time BIGINT NOT NULL DEFAULT 0, -- Unix timestamp
+    hpc_user VARCHAR(255) NOT NULL,
+    project VARCHAR(255) NOT NULL,
+    cluster_partition VARCHAR(255),
+    array_job_id BIGINT,
+    duration INT NOT NULL,
+    walltime INT NOT NULL,
+    job_state VARCHAR(255) NOT NULL
+    CHECK (job_state IN (
+        'boot_fail', 'cancelled', 'completed', 'deadline',
+        'failed', 'node_fail', 'out_of_memory', 'pending',
+        'preempted', 'running', 'suspended', 'timeout'
+    )),
+    meta_data TEXT,          -- JSON
+    resources TEXT NOT NULL, -- JSON
+    num_nodes INT NOT NULL,
+    num_hwthreads INT,
+    num_acc INT,
+    smt TINYINT NOT NULL DEFAULT 1 CHECK (smt IN (0, 1)),
+    shared TEXT NOT NULL
+    CHECK (shared IN ("none", "single_user", "multi_user")),
+    monitoring_status TINYINT NOT NULL DEFAULT 1
+    CHECK (monitoring_status IN (0, 1, 2, 3)),
+    energy REAL NOT NULL DEFAULT 0.0,
+    energy_footprint TEXT DEFAULT NULL,
+    footprint TEXT DEFAULT NULL,
+    UNIQUE (job_id, cluster, start_time)
+);
+
+CREATE TABLE "job_new" (
+    id INTEGER PRIMARY KEY,
+    job_id BIGINT NOT NULL,
+    cluster TEXT NOT NULL,
+    subcluster TEXT NOT NULL,
+    submit_time BIGINT NOT NULL DEFAULT 0, -- Unix timestamp
+    start_time BIGINT NOT NULL DEFAULT 0, -- Unix timestamp
+    hpc_user TEXT NOT NULL,
+    project TEXT NOT NULL,
+    cluster_partition TEXT,
+    array_job_id BIGINT,
+    duration INT NOT NULL,
+    walltime INT NOT NULL,
+    job_state TEXT NOT NULL
+    CHECK (job_state IN (
+        'boot_fail', 'cancelled', 'completed', 'deadline',
+        'failed', 'node_fail', 'out_of_memory', 'pending',
+        'preempted', 'running', 'suspended', 'timeout'
+    )),
+    meta_data TEXT,          -- JSON
+    resources TEXT NOT NULL, -- JSON
+    num_nodes INT NOT NULL,
+    num_hwthreads INT,
+    num_acc INT,
+    smt INT NOT NULL DEFAULT 1,
+    shared TEXT NOT NULL
+    CHECK (shared IN ("none", "single_user", "multi_user")),
+    monitoring_status TINYINT NOT NULL DEFAULT 1
+    CHECK (monitoring_status IN (0, 1, 2, 3)),
+    energy REAL NOT NULL DEFAULT 0.0,
+    energy_footprint TEXT DEFAULT NULL,
+    footprint TEXT DEFAULT NULL,
+    UNIQUE (job_id, cluster, start_time)
+);
+
+
+CREATE TABLE IF NOT EXISTS lookup_exclusive (
+    id INTEGER PRIMARY KEY,
+    name TEXT NOT NULL UNIQUE
+);
+
+INSERT INTO lookup_exclusive (id, name) VALUES
+(0, 'multi_user'),
+(1, 'none'),
+(2, 'single_user');
+
+INSERT INTO job_new (
+    id, job_id, cluster, subcluster, submit_time, start_time, hpc_user, project,
+    cluster_partition, array_job_id, duration, walltime, job_state, meta_data, resources,
+    num_nodes, num_hwthreads, num_acc, smt, shared, monitoring_status, energy,
+    energy_footprint, footprint
+) SELECT
+    id,
+    job_id,
+    cluster,
+    subcluster,
+    0,
+    start_time,
+    hpc_user,
+    project,
+    cluster_partition,
+    array_job_id,
+    duration,
+    walltime,
+    job_state,
+    meta_data,
+    resources,
+    num_nodes,
+    num_hwthreads,
+    num_acc,
+    smt,
+    (
+        SELECT name FROM lookup_exclusive
+        WHERE id = job.exclusive
+    ),
+    monitoring_status,
+    energy,
+    energy_footprint,
+    footprint
+FROM job;
+
+DROP TABLE lookup_exclusive;
+DROP TABLE job; -- Deletes All Existing 'job' Indices; Recreate after Renaming
+ALTER TABLE job_new RENAME TO job;
+
+-- Recreate Indices from 08_add-footprint, include new submit_time indices
+-- Cluster Filter
+CREATE INDEX IF NOT EXISTS jobs_cluster ON job (cluster);
+CREATE INDEX IF NOT EXISTS jobs_cluster_user ON job (cluster, hpc_user);
+CREATE INDEX IF NOT EXISTS jobs_cluster_project ON job (cluster, project);
+CREATE INDEX IF NOT EXISTS jobs_cluster_subcluster ON job (cluster, subcluster);
+-- Cluster Filter Sorting
+CREATE INDEX IF NOT EXISTS jobs_cluster_starttime ON job (cluster, start_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_submittime ON job (cluster, submit_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_duration ON job (cluster, duration);
+CREATE INDEX IF NOT EXISTS jobs_cluster_numnodes ON job (cluster, num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_cluster_numhwthreads ON job (cluster, num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_cluster_numacc ON job (cluster, num_acc);
+CREATE INDEX IF NOT EXISTS jobs_cluster_energy ON job (cluster, energy);
+
+-- Cluster+Partition Filter
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition ON job (cluster, cluster_partition);
+-- Cluster+Partition Filter Sorting
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_starttime ON job (cluster, cluster_partition, start_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_submittime ON job (cluster, cluster_partition, submit_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_duration ON job (cluster, cluster_partition, duration);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_numnodes ON job (cluster, cluster_partition, num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_numhwthreads ON job (cluster, cluster_partition, num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_numacc ON job (cluster, cluster_partition, num_acc);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_energy ON job (cluster, cluster_partition, energy);
+
+-- Cluster+Partition+Jobstate Filter
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate ON job (cluster, cluster_partition, job_state);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_user ON job (cluster, cluster_partition, job_state, hpc_user);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_project ON job (cluster, cluster_partition, job_state, project);
+-- Cluster+Partition+Jobstate Filter Sorting
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_starttime ON job (cluster, cluster_partition, job_state, start_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_submittime ON job (cluster, cluster_partition, job_state, submit_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_duration ON job (cluster, cluster_partition, job_state, duration);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_numnodes ON job (cluster, cluster_partition, job_state, num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_numhwthreads ON job (cluster, cluster_partition, job_state, num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_numacc ON job (cluster, cluster_partition, job_state, num_acc);
+CREATE INDEX IF NOT EXISTS jobs_cluster_partition_jobstate_energy ON job (cluster, cluster_partition, job_state, energy);
+
+-- Cluster+JobState Filter
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate ON job (cluster, job_state);
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_user ON job (cluster, job_state, hpc_user);
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_project ON job (cluster, job_state, project);
+-- Cluster+JobState Filter Sorting
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_starttime ON job (cluster, job_state, start_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_submittime ON job (cluster, job_state, submit_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_duration ON job (cluster, job_state, duration);
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_numnodes ON job (cluster, job_state, num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_numhwthreads ON job (cluster, job_state, num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_numacc ON job (cluster, job_state, num_acc);
+CREATE INDEX IF NOT EXISTS jobs_cluster_jobstate_energy ON job (cluster, job_state, energy);
+
+-- User Filter
+CREATE INDEX IF NOT EXISTS jobs_user ON job (hpc_user);
+-- User Filter Sorting
+CREATE INDEX IF NOT EXISTS jobs_user_starttime ON job (hpc_user, start_time);
+CREATE INDEX IF NOT EXISTS jobs_user_duration ON job (hpc_user, duration);
+CREATE INDEX IF NOT EXISTS jobs_user_numnodes ON job (hpc_user, num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_user_numhwthreads ON job (hpc_user, num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_user_numacc ON job (hpc_user, num_acc);
+CREATE INDEX IF NOT EXISTS jobs_user_energy ON job (hpc_user, energy);
+
+-- Project Filter
+CREATE INDEX IF NOT EXISTS jobs_project ON job (project);
+CREATE INDEX IF NOT EXISTS jobs_project_user ON job (project, hpc_user);
+-- Project Filter Sorting
+CREATE INDEX IF NOT EXISTS jobs_project_starttime ON job (project, start_time);
+CREATE INDEX IF NOT EXISTS jobs_project_duration ON job (project, duration);
+CREATE INDEX IF NOT EXISTS jobs_project_numnodes ON job (project, num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_project_numhwthreads ON job (project, num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_project_numacc ON job (project, num_acc);
+CREATE INDEX IF NOT EXISTS jobs_project_energy ON job (project, energy);
+
+-- JobState Filter
+CREATE INDEX IF NOT EXISTS jobs_jobstate ON job (job_state);
+CREATE INDEX IF NOT EXISTS jobs_jobstate_user ON job (job_state, hpc_user);
+CREATE INDEX IF NOT EXISTS jobs_jobstate_project ON job (job_state, project);
+CREATE INDEX IF NOT EXISTS jobs_jobstate_cluster ON job (job_state, cluster);
+-- JobState Filter Sorting
+CREATE INDEX IF NOT EXISTS jobs_jobstate_starttime ON job (job_state, start_time);
+CREATE INDEX IF NOT EXISTS jobs_jobstate_duration ON job (job_state, duration);
+CREATE INDEX IF NOT EXISTS jobs_jobstate_numnodes ON job (job_state, num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_jobstate_numhwthreads ON job (job_state, num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_jobstate_numacc ON job (job_state, num_acc);
+CREATE INDEX IF NOT EXISTS jobs_jobstate_energy ON job (job_state, energy);
+
+-- ArrayJob Filter
+CREATE INDEX IF NOT EXISTS jobs_arrayjobid_starttime ON job (array_job_id, start_time);
+CREATE INDEX IF NOT EXISTS jobs_cluster_arrayjobid_starttime ON job (cluster, array_job_id, start_time);
+
+-- Sorting without active filters
+CREATE INDEX IF NOT EXISTS jobs_starttime ON job (start_time);
+CREATE INDEX IF NOT EXISTS jobs_duration ON job (duration);
+CREATE INDEX IF NOT EXISTS jobs_numnodes ON job (num_nodes);
+CREATE INDEX IF NOT EXISTS jobs_numhwthreads ON job (num_hwthreads);
+CREATE INDEX IF NOT EXISTS jobs_numacc ON job (num_acc);
+CREATE INDEX IF NOT EXISTS jobs_energy ON job (energy);
+
+-- Single filters with default starttime sorting
+CREATE INDEX IF NOT EXISTS jobs_duration_starttime ON job (duration, start_time);
+CREATE INDEX IF NOT EXISTS jobs_numnodes_starttime ON job (num_nodes, start_time);
+CREATE INDEX IF NOT EXISTS jobs_numhwthreads_starttime ON job (num_hwthreads, start_time);
+CREATE INDEX IF NOT EXISTS jobs_numacc_starttime ON job (num_acc, start_time);
+CREATE INDEX IF NOT EXISTS jobs_energy_starttime ON job (energy, start_time);
+
+-- Optimize DB index usage
+PRAGMA optimize;
+
+-- Optimize DB size: https://sqlite.org/lang_vacuum.html 
+-- Not allowed within a migration transaction; Keep command here for documentation and recommendation
+-- Command: 'VACUUM;'