Add batch_size option to httpSink

.github/ci-config.json

@@ -3,6 +3,6 @@
   "collectors" : ".github/ci-collectors.json",
   "receivers" : ".github/ci-receivers.json",
   "router" : ".github/ci-router.json",
-  "interval": "5s",
+  "interval": 5,
-  "duration": "1s"
+  "duration": 1
 }

.github/ci-sinks.json

@@ -1,8 +1,6 @@
 {
   "testoutput" : {
     "type" : "stdout",
-    "meta_as_tags" : [
+    "meta_as_tags" : true
-      "unit"
-    ]
   }
 }

.github/workflows/Release.yml

@@ -8,17 +8,16 @@ on:
  push:
   tags:
   - '**'
- workflow_dispatch:
 
 jobs:
 
   #
-  # Build on AlmaLinux 8 using go-toolset
+  # Build on AlmaLinux 8.5 using go-toolset
   #
   AlmaLinux-RPM-build:
     runs-on: ubuntu-latest
     # See: https://hub.docker.com/_/almalinux
-    container: almalinux:8
+    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:
@@ -28,46 +27,37 @@ jobs:
 
     # Use dnf to install development packages
     - name: Install development packages
-      run: |
+      run: dnf --assumeyes group install "Development Tools" "RPM Development Tools"
-          dnf --assumeyes group install "Development Tools" "RPM Development Tools"
-          dnf --assumeyes install 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@v4
+      uses: actions/checkout@v2
       with:
         submodules: recursive
         fetch-depth: 0
 
     # Use dnf to install build dependencies
     - name: Install build dependencies
-      run: |
+      run: dnf --assumeyes builddep scripts/cc-metric-collector.spec
-          dnf --assumeyes install \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
 
     - name: RPM build MetricCollector
       id: rpmbuild
-      run: |
+      run: make RPM
-          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+    
-          make RPM
+    # AlmaLinux 8.5 is a derivate of RedHat Enterprise Linux 8 (UBI8),
-
-    # AlmaLinux 8 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 'alma8'. It uses the move operation
+    # This step replaces the substring 'el8' to 'alma85'. It uses the move operation
-    # because it is unclear whether the default AlmaLinux 8 container contains the
+    # 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/alma8/)
+    - name: Rename RPMs (s/el8/alma85/)
       id: rpmrename
       run: |
         OLD_RPM="${{steps.rpmbuild.outputs.RPM}}"
         OLD_SRPM="${{steps.rpmbuild.outputs.SRPM}}"
-        NEW_RPM="${OLD_RPM/el8/alma8}"
+        NEW_RPM="${OLD_RPM/el8/alma85}"
-        NEW_SRPM=${OLD_SRPM/el8/alma8}
+        NEW_SRPM=${OLD_SRPM/el8/alma85}
         mv "${OLD_RPM}" "${NEW_RPM}"
         mv "${OLD_SRPM}" "${NEW_SRPM}"
         echo "::set-output name=SRPM::${NEW_SRPM}"
@@ -77,12 +67,12 @@ jobs:
     - name: Save RPM as artifact
       uses: actions/upload-artifact@v2
       with:
-        name: cc-metric-collector RPM for AlmaLinux 8
+        name: cc-metric-collector RPM for AlmaLinux 8.5
         path: ${{ steps.rpmrename.outputs.RPM }}
     - name: Save SRPM as artifact
       uses: actions/upload-artifact@v2
       with:
-        name: cc-metric-collector SRPM for AlmaLinux 8
+        name: cc-metric-collector SRPM for AlmaLinux 8.5
         path: ${{ steps.rpmrename.outputs.SRPM }}
 
   #
@@ -90,8 +80,8 @@ jobs:
   #
   UBI-8-RPM-build:
     runs-on: ubuntu-latest
-    # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c35984d70cc534b3a3784e?container-tabs=gti
+    # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
-    container: registry.access.redhat.com/ubi8/ubi:8.8-1032.1692772289
+    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}}
@@ -100,31 +90,24 @@ jobs:
 
     # 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
+      run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros rpm-build-libs rpm-libs gcc make python38 git
 
     # 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@v4
+      uses: actions/checkout@v2
       with:
         submodules: recursive
         fetch-depth: 0
 
     # Use dnf to install build dependencies
     - name: Install build dependencies
-      run: |
+      run: dnf --assumeyes --disableplugin=subscription-manager builddep scripts/cc-metric-collector.spec
-          dnf --assumeyes --disableplugin=subscription-manager install \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
 
     - name: RPM build MetricCollector
       id: rpmbuild
-      run: |
+      run: make RPM
-          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
-          make RPM
 
     # See: https://github.com/actions/upload-artifact
     - name: Save RPM as artifact
@@ -138,76 +121,25 @@ jobs:
         name: cc-metric-collector SRPM for UBI 8
         path: ${{ steps.rpmbuild.outputs.SRPM }}
 
-  #
-  # Build on Ubuntu 22.04 using official go 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 : ${{steps.debrename.outputs.DEB}}
-    steps:
-    # Use apt to install development packages
-    - name: Install development packages
-      run: |
-          apt update && apt --assume-yes upgrade
-          apt --assume-yes install build-essential sed git wget bash
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v4
-      with:
-        submodules: recursive
-        fetch-depth: 0
-    # Use official golang package
-    - name: Install Golang
-      run: |
-          wget -q https://go.dev/dl/go1.21.1.linux-amd64.tar.gz --output-document=- | \
-          tar --directory=/usr/local --extract --gzip
-          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
-          go version
-    - name: DEB build MetricCollector
-      id: dpkg-build
-      run: |
-          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
-          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
-          make DEB
-    - name: Rename DEB (add '_ubuntu22.04')
-      id: debrename
-      run: |
-        OLD_DEB_NAME=$(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-metric-collector 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]
+    needs: [AlmaLinux-RPM-build, UBI-8-RPM-build]
 
     steps:
     # See: https://github.com/actions/download-artifact
-    - name: Download AlmaLinux 8 RPM
+    - name: Download AlmaLinux 8.5 RPM
       uses: actions/download-artifact@v2
       with:
-        name: cc-metric-collector RPM for AlmaLinux 8
+        name: cc-metric-collector RPM for AlmaLinux 8.5
-    - name: Download AlmaLinux 8 SRPM
+    - name: Download AlmaLinux 8.5 SRPM
       uses: actions/download-artifact@v2
       with:
-        name: cc-metric-collector SRPM for AlmaLinux 8
+        name: cc-metric-collector SRPM for AlmaLinux 8.5
-
+    
     - name: Download UBI 8 RPM
       uses: actions/download-artifact@v2
       with:
@@ -217,11 +149,6 @@ jobs:
       with:
         name: cc-metric-collector SRPM for UBI 8
 
-    - name: Download Ubuntu 22.04 DEB
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-metric-collector 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.
@@ -231,21 +158,18 @@ jobs:
     - name: Set RPM variables
       id: files
       run: |
-        ALMA_8_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
+        ALMA_85_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
-        ALMA_8_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
+        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}}")
+        echo "ALMA_85_RPM::${ALMA_85_RPM}"
-        echo "ALMA_8_RPM::${ALMA_8_RPM}"
+        echo "ALMA_85_SRPM::${ALMA_85_SRPM}"
-        echo "ALMA_8_SRPM::${ALMA_8_SRPM}"
         echo "UBI_8_RPM::${UBI_8_RPM}"
         echo "UBI_8_SRPM::${UBI_8_SRPM}"
-        echo "U_2004_DEB::${U_2004_DEB}"
+        echo "::set-output name=ALMA_85_RPM::${ALMA_85_RPM}"
-        echo "::set-output name=ALMA_8_RPM::${ALMA_8_RPM}"
+        echo "::set-output name=ALMA_85_SRPM::${ALMA_85_SRPM}"
-        echo "::set-output name=ALMA_8_SRPM::${ALMA_8_SRPM}"
         echo "::set-output name=UBI_8_RPM::${UBI_8_RPM}"
         echo "::set-output name=UBI_8_SRPM::${UBI_8_SRPM}"
-        echo "::set-output name=U_2004_DEB::${U_2004_DEB}"
 
     # See: https://github.com/softprops/action-gh-release
     - name: Release
@@ -254,8 +178,7 @@ jobs:
       with:
         name: cc-metric-collector-${{github.ref_name}}
         files: |
-         ${{ steps.files.outputs.ALMA_8_RPM }}
+         ${{ steps.files.outputs.ALMA_85_RPM }}
-         ${{ steps.files.outputs.ALMA_8_SRPM }}
+         ${{ steps.files.outputs.ALMA_85_SRPM }}
          ${{ steps.files.outputs.UBI_8_RPM }}
-         ${{ steps.files.outputs.UBI_8_SRPM }}
+         ${{ steps.files.outputs.UBI_8_SRPM }}
-         ${{ steps.files.outputs.U_2004_DEB }}

.github/workflows/runonce.yml

@@ -4,31 +4,32 @@
 name: Run Test
 
 # Run on event push
-on:
+on: push
-  push:
-  workflow_dispatch:
 
 jobs:
-
   #
-  # Job build-1-20
+  # Job build-1-17
-  # Build on latest Ubuntu using golang version 1.20
+  # Build on latest Ubuntu using golang version 1.17 
   #
-  build-1-20:
+  build-1-17:
     runs-on: ubuntu-latest
     steps:
     # See: https://github.com/marketplace/actions/checkout
     # Checkout git repository and submodules
     - name: Checkout
-      uses: actions/checkout@v4
+      uses: actions/checkout@v2
       with:
         submodules: recursive
 
     # See: https://github.com/marketplace/actions/setup-go-environment
     - name: Setup Golang
-      uses: actions/setup-go@v4
+      uses: actions/setup-go@v2
       with:
-        go-version: '1.20'
+        go-version: '^1.17.7'
+
+    # Install libganglia
+    - name: Setup Ganglia
+      run: sudo apt install ganglia-monitor libganglia1
 
     - name: Build MetricCollector
       run: make
@@ -37,141 +38,31 @@ jobs:
       run: ./cc-metric-collector --once --config .github/ci-config.json
 
   #
-  # Job build-1-21
+  # Job build-1-16
-  # Build on latest Ubuntu using golang version 1.21
+  # Build on latest Ubuntu using golang version 1.16
   #
-  build-1-21:
+  build-1-16:
     runs-on: ubuntu-latest
     steps:
     # See: https://github.com/marketplace/actions/checkout
     # Checkout git repository and submodules
     - name: Checkout
-      uses: actions/checkout@v4
+      uses: actions/checkout@v2
       with:
         submodules: recursive
 
     # See: https://github.com/marketplace/actions/setup-go-environment
     - name: Setup Golang
-      uses: actions/setup-go@v4
+      uses: actions/setup-go@v2
       with:
-        go-version: '1.21'
+        go-version: '^1.16.7' # The version AlmaLinux 8.5 uses
+
+    # Install libganglia
+    - name: Setup Ganglia
+      run: sudo apt install ganglia-monitor libganglia1
 
     - name: Build MetricCollector
       run: make
 
     - name: Run MetricCollector once
       run: ./cc-metric-collector --once --config .github/ci-config.json
-
-  #
-  # Build on AlmaLinux 8 using go-toolset
-  #
-  AlmaLinux-RPM-build:
-    runs-on: ubuntu-latest
-    # See: https://hub.docker.com/_/almalinux
-    container: almalinux:8
-    # The job outputs link to the outputs of the 'rpmrename' step
-    # Only job outputs can be used in child jobs
-    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
-
-    # 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@v4
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: |
-          dnf --assumeyes install \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
-
-    - name: RPM build MetricCollector
-      id: rpmbuild
-      run: |
-          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
-          make RPM
-
-  #
-  # Build on UBI 8 using go-toolset
-  #
-  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:8.8-1032.1692772289
-    # The job outputs link to the outputs of the 'rpmbuild' step
-    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@v4
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: |
-          dnf --assumeyes --disableplugin=subscription-manager install \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.20.6-2.module_el8+658+f14b2092.x86_64.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.20.6-2.module_el8+658+f14b2092.noarch.rpm \
-              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.20.6-1.module_el8+602+8bb8a8d6.x86_64.rpm
-
-    - name: RPM build MetricCollector
-      id: rpmbuild
-      run: |
-          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
-          make RPM
-
-  #
-  # Build on Ubuntu 22.04 using official go package
-  #
-  Ubuntu-jammy-build:
-    runs-on: ubuntu-latest
-    container: ubuntu:22.04
-
-    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
-    # 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@v4
-      with:
-        submodules: recursive
-        fetch-depth: 0
-    # Use official golang package
-    - name: Install Golang
-      run: |
-          wget -q https://go.dev/dl/go1.21.1.linux-amd64.tar.gz --output-document=- | \
-          tar --directory=/usr/local --extract --gzip
-          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
-          go version
-    - name: DEB build MetricCollector
-      id: dpkg-build
-      run: |
-          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
-          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
-          make DEB

.zenodo.json

@@ -1,29 +0,0 @@
-{
-  "title": "cc-metric-collector",
-  "description": "Monitoring agent for ClusterCockpit.",
-  "creators": [
-    {
-      "affiliation": "Regionales Rechenzentrum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg",
-      "name": "Thomas Gruber",
-      "orcid": "0000-0001-5560-6964"
-    },
-    {
-      "affiliation": "Steinbuch Centre for Computing, Karlsruher Institut für Technologie",
-      "name": "Holger Obermaier",
-      "orcid": "0000-0002-6830-6626"
-    }
-  ],
-  "upload_type": "software",
-  "license": "MIT",
-  "access_right": "open",
-  "keywords": [
-    "performance-monitoring",
-    "cluster-monitoring",
-    "open-source"
-  ],
-  "communities": [
-    {
-      "identifier": "clustercockpit"
-    }
-  ]
-}

Makefile

@@ -16,16 +16,15 @@ COMPONENT_DIRS   := collectors \
 			internal/multiChanTicker
 
 BINDIR = bin
-GOBIN = $(shell which go)
 
 
 .PHONY: all
 all: $(APP)
 
-$(APP): $(GOSRC) go.mod
+$(APP): $(GOSRC)
 	make -C collectors
-	$(GOBIN) get
+	go get
-	$(GOBIN) build -o $(APP) $(GOSRC_APP)
+	go build -o $(APP) $(GOSRC_APP)
 
 install: $(APP)
 	@WORKSPACE=$(PREFIX)
@@ -52,25 +51,25 @@ clean:
 
 .PHONY: fmt
 fmt:
-	$(GOBIN) fmt $(GOSRC_COLLECTORS)
+	go fmt $(GOSRC_COLLECTORS)
-	$(GOBIN) fmt $(GOSRC_SINKS)
+	go fmt $(GOSRC_SINKS)
-	$(GOBIN) fmt $(GOSRC_RECEIVERS)
+	go fmt $(GOSRC_RECEIVERS)
-	$(GOBIN) fmt $(GOSRC_APP)
+	go fmt $(GOSRC_APP)
-	@for F in $(GOSRC_INTERNAL); do $(GOBIN) fmt $$F; done
+	@for F in $(GOSRC_INTERNAL); do go fmt $$F; done
 
 
 # Examine Go source code and reports suspicious constructs
 .PHONY: vet
 vet:
-	$(GOBIN) vet ./...
+	go vet ./...
 
 
 # Run linter for the Go programming language.
 # Using static analysis, it finds bugs and performance issues, offers simplifications, and enforces style rules
 .PHONY: staticcheck
 staticcheck:
-	$(GOBIN) install honnef.co/go/tools/cmd/staticcheck@latest
+	go install honnef.co/go/tools/cmd/staticcheck@latest
-	$$($(GOBIN) env GOPATH)/bin/staticcheck ./...
+	$$(go env GOPATH)/bin/staticcheck ./...
 
 .ONESHELL:
 .PHONY: RPM
@@ -84,7 +83,7 @@ RPM: scripts/cc-metric-collector.spec
 	@COMMITISH="HEAD"
 	@VERS=$$(git describe --tags $${COMMITISH})
 	@VERS=$${VERS#v}
-	@VERS=$$(echo $${VERS} | sed -e s+'-'+'_'+g)
+	@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
 	@eval $$(rpmspec --query --queryformat "NAME='%{name}' VERSION='%{version}' RELEASE='%{release}' NVR='%{NVR}' NVRA='%{NVRA}'" --define="VERS $${VERS}" "$${SPECFILE}")
 	@PREFIX="$${NAME}-$${VERSION}"
 	@FORMAT="tar.gz"
@@ -96,8 +95,10 @@ RPM: scripts/cc-metric-collector.spec
 	@if [[ "$${GITHUB_ACTIONS}" == true ]]; then
 	@     RPMFILE="$${RPMDIR}/$${ARCH}/$${NVRA}.rpm"
 	@     SRPMFILE="$${SRPMDIR}/$${NVR}.src.rpm"
-	@     echo "SRPM=$${SRPMFILE}" >> $${GITHUB_OUTPUT}
+	@     echo "RPM: $${RPMFILE}"
-	@     echo "RPM=$${RPMFILE}" >> $${GITHUB_OUTPUT}
+	@     echo "SRPM: $${SRPMFILE}"
+	@     echo "::set-output name=SRPM::$${SRPMFILE}"
+	@     echo "::set-output name=RPM::$${RPMFILE}"
 	@fi
 
 .PHONY: DEB
@@ -106,24 +107,21 @@ DEB: scripts/cc-metric-collector.deb.control $(APP)
 	@WORKSPACE=$${PWD}/.dpkgbuild
 	@DEBIANDIR=$${WORKSPACE}/debian
 	@DEBIANBINDIR=$${WORKSPACE}/DEBIAN
-	@mkdir --parents --verbose $${WORKSPACE} $${DEBIANBINDIR}
+	@mkdir --parents --verbose $$WORKSPACE $$DEBIANBINDIR
 	#@mkdir --parents --verbose $$DEBIANDIR
 	@CONTROLFILE="$${BASEDIR}/scripts/cc-metric-collector.deb.control"
 	@COMMITISH="HEAD"
 	@VERS=$$(git describe --tags --abbrev=0 $${COMMITISH})
-	@if [ -z "$${VERS}" ]; then VERS=${GITHUB_REF_NAME}; fi
 	@VERS=$${VERS#v}
+	@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
 	@ARCH=$$(uname -m)
-	@ARCH=$$(echo $${ARCH} | sed -e s+'_'+'-'+g)
+	@ARCH=$$(echo $$ARCH | sed -e s+'_'+'-'+g)
-	@if [ "$${ARCH}" = "x86-64" ]; then ARCH=amd64; fi
 	@PREFIX="$${NAME}-$${VERSION}_$${ARCH}"
-	@SIZE_BYTES=$$(du -bcs --exclude=.dpkgbuild "$${WORKSPACE}"/ | awk '{print $$1}' | head -1 | sed -e 's/^0\+//')
+	@SIZE_BYTES=$$(du -bcs --exclude=.dpkgbuild "$$WORKSPACE"/ | awk '{print $$1}' | head -1 | sed -e 's/^0\+//')
-	@SIZE="$$(awk -v size="$${SIZE_BYTES}" 'BEGIN {print (size/1024)+1}' | awk '{print int($$0)}')"
+	@SIZE="$$(awk -v size="$$SIZE_BYTES" 'BEGIN {print (size/1024)+1}' | awk '{print int($$0)}')"
-	@sed -e s+"{VERSION}"+"$${VERS}"+g -e s+"{INSTALLED_SIZE}"+"$${SIZE}"+g -e s+"{ARCH}"+"$${ARCH}"+g $${CONTROLFILE} > $${DEBIANBINDIR}/control
+	#@sed -e s+"{VERSION}"+"$$VERS"+g -e s+"{INSTALLED_SIZE}"+"$$SIZE"+g -e s+"{ARCH}"+"$$ARCH"+g $$CONTROLFILE > $${DEBIANDIR}/control
+	@sed -e s+"{VERSION}"+"$$VERS"+g -e s+"{INSTALLED_SIZE}"+"$$SIZE"+g -e s+"{ARCH}"+"$$ARCH"+g $$CONTROLFILE > $${DEBIANBINDIR}/control
 	@make PREFIX=$${WORKSPACE} install
 	@DEB_FILE="cc-metric-collector_$${VERS}_$${ARCH}.deb"
-	@dpkg-deb -b $${WORKSPACE} "$${DEB_FILE}"
+	@dpkg-deb -b $${WORKSPACE} "$$DEB_FILE"
-	@if [ "$${GITHUB_ACTIONS}" = "true" ]; then
-	@     echo "DEB=$${DEB_FILE}" >> $${GITHUB_OUTPUT}
-	@fi
 	@rm -r "$${WORKSPACE}"

README.md

@@ -1,6 +1,5 @@
 # cc-metric-collector
-
+A node agent for measuring, processing and forwarding node level metrics. It is part of the ClusterCockpit ecosystem.
-A node agent for measuring, processing and forwarding node level metrics. It is part of the [ClusterCockpit ecosystem](./docs/introduction.md).
 
 The metric collector sends (and receives) metric in the [InfluxDB line protocol](https://docs.influxdata.com/influxdb/cloud/reference/syntax/line-protocol/) as it provides flexibility while providing a separation between tags (like index columns in relational databases) and fields (like data columns).
 
@@ -8,14 +7,10 @@ There is a single timer loop that triggers all collectors serially, collects the
 
 The receiver runs as a go routine side-by-side with the timer loop and asynchronously forwards received metrics to the sink.
 
-
-[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.7438287.svg)](https://doi.org/10.5281/zenodo.7438287)
-
-
 # Configuration
 
 Configuration is implemented using a single json document that is distributed over network and may be persisted as file.
-Supported metrics are documented [here](https://github.com/ClusterCockpit/cc-specifications/blob/master/interfaces/lineprotocol/README.md).
+Supported metrics are documented [here](https://github.com/ClusterCockpit/cc-specifications/blob/master/metrics/lineprotocol_alternative.md).
 
 There is a main configuration file with basic settings that point to the other configuration files for the different components.
 
@@ -25,20 +20,20 @@ There is a main configuration file with basic settings that point to the other c
   "collectors" : "collectors.json",
   "receivers" : "receivers.json",
   "router" : "router.json",
-  "interval": "10s",
+  "interval": 10,
-  "duration": "1s"
+  "duration": 1
 }
 ```
 
-The `interval` defines how often the metrics should be read and send to the sink. The `duration` tells collectors how long one measurement has to take. This is important for some collectors, like the `likwid` collector. For more information, see [here](./docs/configuration.md).
+The `interval` defines how often the metrics should be read and send to the sink. The `duration` tells collectors how long one measurement has to take. This is important for some collectors, like the `likwid` collector.
 
 See the component READMEs for their configuration:
-
 * [`collectors`](./collectors/README.md)
 * [`sinks`](./sinks/README.md)
 * [`receivers`](./receivers/README.md)
 * [`router`](./internal/metricRouter/README.md)
 
+
 # Installation
 
 ```
@@ -48,7 +43,6 @@ $ go get (requires at least golang 1.16)
 $ make
 ```
 
-For more information, see [here](./docs/building.md).
 
 # Running
 
@@ -62,7 +56,6 @@ Usage of metric-collector:
   -once
     	Run all collectors only once
 ```
-
 # Scenarios
 
 The metric collector was designed with flexibility in mind, so it can be used in many scenarios. Here are a few:
@@ -100,12 +93,11 @@ flowchart TD
 ```
 
 # Contributing
-
 The ClusterCockpit ecosystem is designed to be used by different HPC computing centers. Since configurations and setups differ between the centers, the centers likely have to put some work into the cc-metric-collector to gather all desired metrics.
 
 You are free to open an issue to request a collector but we would also be happy about PRs.
 
-# Contact
+# Contact 
 
 * [Matrix.org ClusterCockpit General chat](https://matrix.to/#/#clustercockpit-dev:matrix.org)
 * [Matrix.org ClusterCockpit Development chat](https://matrix.to/#/#clustercockpit:matrix.org)

cc-metric-collector.go

@@ -15,15 +15,15 @@ import (
 	"sync"
 	"time"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	mr "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 type CentralConfigFile struct {
-	Interval            string `json:"interval"`
+	Interval            int    `json:"interval"`
-	Duration            string `json:"duration"`
+	Duration            int    `json:"duration"`
 	CollectorConfigFile string `json:"collectors"`
 	RouterConfigFile    string `json:"router"`
 	SinkConfigFile      string `json:"sinks"`
@@ -173,36 +173,16 @@ func mainFunc() int {
 		cclog.Error("Error reading configuration file ", rcfg.CliArgs["configfile"], ": ", err.Error())
 		return 1
 	}
-
+	if rcfg.ConfigFile.Interval <= 0 || time.Duration(rcfg.ConfigFile.Interval)*time.Second <= 0 {
-	// Properly use duration parser with inputs like '60s', '5m' or similar
+		cclog.Error("Configuration value 'interval' must be greater than zero")
-	if len(rcfg.ConfigFile.Interval) > 0 {
-		t, err := time.ParseDuration(rcfg.ConfigFile.Interval)
-		if err != nil {
-			cclog.Error("Configuration value 'interval' no valid duration")
-		}
-		rcfg.Interval = t
-		if rcfg.Interval == 0 {
-			cclog.Error("Configuration value 'interval' must be greater than zero")
-			return 1
-		}
-	}
-
-	// Properly use duration parser with inputs like '60s', '5m' or similar
-	if len(rcfg.ConfigFile.Duration) > 0 {
-		t, err := time.ParseDuration(rcfg.ConfigFile.Duration)
-		if err != nil {
-			cclog.Error("Configuration value 'duration' no valid duration")
-		}
-		rcfg.Duration = t
-		if rcfg.Duration == 0 {
-			cclog.Error("Configuration value 'duration' must be greater than zero")
-			return 1
-		}
-	}
-	if rcfg.Duration > rcfg.Interval {
-		cclog.Error("The interval should be greater than duration")
 		return 1
 	}
+	rcfg.Interval = time.Duration(rcfg.ConfigFile.Interval) * time.Second
+	if rcfg.ConfigFile.Duration <= 0 || time.Duration(rcfg.ConfigFile.Duration)*time.Second <= 0 {
+		cclog.Error("Configuration value 'duration' must be greater than zero")
+		return 1
+	}
+	rcfg.Duration = time.Duration(rcfg.ConfigFile.Duration) * time.Second
 
 	if len(rcfg.ConfigFile.RouterConfigFile) == 0 {
 		cclog.Error("Metric router configuration file must be set")
@@ -291,7 +271,7 @@ func mainFunc() int {
 
 	// Wait until one tick has passed. This is a workaround
 	if rcfg.CliArgs["once"] == "true" {
-		x := 1.2 * float64(rcfg.Interval.Seconds())
+		x := 1.2 * float64(rcfg.ConfigFile.Interval)
 		time.Sleep(time.Duration(int(x)) * time.Second)
 		shutdownSignal <- os.Interrupt
 	}

collectors.json

@@ -12,7 +12,6 @@
             "proc_total"
         ]
     },
-    "memstat": {},
     "netstat": {
         "include_devices": [
             "enp5s0"
@@ -34,8 +33,5 @@
                 "type-id": "1"
             }
         }
-    },
-    "topprocs": {
-        "num_procs": 5
     }
 }

collectors/Makefile

@@ -1,33 +1,25 @@
-# LIKWID version
-LIKWID_VERSION := 5.3.0
-LIKWID_INSTALLED_FOLDER := $(shell dirname $$(which likwid-topology 2>/dev/null) 2>/dev/null)
-
-LIKWID_FOLDER := $(CURDIR)/likwid
 
 all: likwid
 
+
+# LIKWID version
+LIKWID_VERSION = 5.2.1
+
 .ONESHELL:
 .PHONY: likwid
 likwid:
-	if [ -n "$(LIKWID_INSTALLED_FOLDER)" ]; then
+	INSTALL_FOLDER="$${PWD}/likwid"
-	    # Using likwid include files from system installation
+	BUILD_FOLDER="$${PWD}/likwidbuild"
-	    INCLUDE_DIR="$(LIKWID_INSTALLED_FOLDER)/../include"
+	if [ -d $${INSTALL_FOLDER} ]; then rm -r $${INSTALL_FOLDER}; fi
-	    mkdir --parents --verbose "$(LIKWID_FOLDER)"
+	mkdir --parents --verbose  $${INSTALL_FOLDER} $${BUILD_FOLDER}
-	    cp "$${INCLUDE_DIR}"/*.h "$(LIKWID_FOLDER)"
+	wget -P "$${BUILD_FOLDER}" ftp://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz
-	else
+	tar -C $${BUILD_FOLDER} -xf $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION).tar.gz
-	    # Using likwid include files from downloaded tar archive
+	install -Dpm 0644 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/likwid*.h $${INSTALL_FOLDER}/
-	    if [ -d "$(LIKWID_FOLDER)" ]; then
+	install -Dpm 0644 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/bstrlib.h $${INSTALL_FOLDER}/
-	        rm --recursive "$(LIKWID_FOLDER)"
+	rm -r $${BUILD_FOLDER}
-	    fi
-	    BUILD_FOLDER="$${PWD}/likwidbuild"
-	    mkdir --parents --verbose  "$${BUILD_FOLDER}"
-	    wget --output-document=- http://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz |
-	        tar --directory="$${BUILD_FOLDER}" --extract --gz
-		install -D --verbose --preserve-timestamps --mode=0644 --target-directory="$(LIKWID_FOLDER)" "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/likwid*.h "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/bstrlib.h
-	    rm --recursive "$${BUILD_FOLDER}"
-	fi
 
 
-.PHONY: clean
 clean:
 	rm -rf likwid
+
+.PHONY: clean

collectors/README.md

@@ -35,11 +35,10 @@ In contrast to the configuration files for sinks and receivers, the collectors c
 * [`nfs4stat`](./nfs4Metric.md)
 * [`cpufreq`](./cpufreqMetric.md)
 * [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
-* [`numastats`](./numastatsMetric.md)
+* [`numastat`](./numastatMetric.md)
 * [`gpfs`](./gpfsMetric.md)
 * [`beegfs_meta`](./beegfsmetaMetric.md)
 * [`beegfs_storage`](./beegfsstorageMetric.md)
-* [`rocm_smi`](./rocmsmiMetric.md)
 
 ## Todos
 
@@ -51,7 +50,7 @@ A collector reads data from any source, parses it to metrics and submits these m
 * `Name() string`: Return the name of the collector
 * `Init(config json.RawMessage) error`: Initializes the collector using the given collector-specific config in JSON. Check if needed files/commands exists, ...
 * `Initialized() bool`: Check if a collector is successfully initialized
-* `Read(duration time.Duration, output chan ccMetric.CCMetric)`: Read, parse and submit data to the `output` channel as [`CCMetric`](../internal/ccMetric/README.md). If the collector has to measure anything for some duration, use the provided function argument `duration`.
+* `Read(duration time.Duration, output chan ccMetric.CCMetric)`: Read, parse and submit data to the `output` channel as [`CCMetric`](../internal/ccMetric/README.md). If the collector has to measure anything for some duration, use the provided function argument `duration`. 
 * `Close()`: Closes down the collector.
 
 It is recommanded to call `setup()` in the `Init()` function.

collectors/beegfsmetaMetric.go

@@ -5,7 +5,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io"
+	"io/ioutil"
 	"os"
 	"os/exec"
 	"os/user"
@@ -14,8 +14,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
@@ -55,7 +55,6 @@ func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
 
 	m.name = "BeegfsMetaCollector"
 	m.setup()
-	m.parallel = true
 	// Set default beegfs-ctl binary
 
 	m.config.Beegfs = DEFAULT_BEEGFS_CMD
@@ -115,7 +114,7 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetr
 		return
 	}
 	//get mounpoint
-	buffer, _ := os.ReadFile(string("/proc/mounts"))
+	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
 	mounts := strings.Split(string(buffer), "\n")
 	var mountpoints []string
 	for _, line := range mounts {
@@ -157,9 +156,9 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetr
 		if err != nil {
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
-			data, _ := io.ReadAll(cmdStderr)
+			data, _ := ioutil.ReadAll(cmdStderr)
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = io.ReadAll(cmdStdout)
+			data, _ = ioutil.ReadAll(cmdStdout)
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stdout: \"%s\"\n", string(data))
 			return
 		}

collectors/beegfsstorageMetric.go

@@ -5,7 +5,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io"
+	"io/ioutil"
 	"os"
 	"os/exec"
 	"os/user"
@@ -14,8 +14,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 // Struct for the collector-specific JSON config
@@ -48,7 +48,6 @@ func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
 
 	m.name = "BeegfsStorageCollector"
 	m.setup()
-	m.parallel = true
 	// Set default beegfs-ctl binary
 
 	m.config.Beegfs = DEFAULT_BEEGFS_CMD
@@ -108,7 +107,7 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
 		return
 	}
 	//get mounpoint
-	buffer, _ := os.ReadFile(string("/proc/mounts"))
+	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
 	mounts := strings.Split(string(buffer), "\n")
 	var mountpoints []string
 	for _, line := range mounts {
@@ -149,9 +148,9 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
 		if err != nil {
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
-			data, _ := io.ReadAll(cmdStderr)
+			data, _ := ioutil.ReadAll(cmdStderr)
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = io.ReadAll(cmdStdout)
+			data, _ = ioutil.ReadAll(cmdStdout)
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stdout: \"%s\"\n", string(data))
 			return
 		}

collectors/collectorManager.go

@@ -6,56 +6,47 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
+	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
 )
 
 // Map of all available metric collectors
 var AvailableCollectors = map[string]MetricCollector{
 
-	"likwid":          new(LikwidCollector),
+	"likwid":           new(LikwidCollector),
-	"loadavg":         new(LoadavgCollector),
+	"loadavg":          new(LoadavgCollector),
-	"memstat":         new(MemstatCollector),
+	"memstat":          new(MemstatCollector),
-	"netstat":         new(NetstatCollector),
+	"netstat":          new(NetstatCollector),
-	"ibstat":          new(InfinibandCollector),
+	"ibstat":           new(InfinibandCollector),
-	"lustrestat":      new(LustreCollector),
+	"lustrestat":       new(LustreCollector),
-	"cpustat":         new(CpustatCollector),
+	"cpustat":          new(CpustatCollector),
-	"topprocs":        new(TopProcsCollector),
+	"topprocs":         new(TopProcsCollector),
-	"nvidia":          new(NvidiaCollector),
+	"nvidia":           new(NvidiaCollector),
-	"customcmd":       new(CustomCmdCollector),
+	"customcmd":        new(CustomCmdCollector),
-	"iostat":          new(IOstatCollector),
+	"iostat":           new(IOstatCollector),
-	"diskstat":        new(DiskstatCollector),
+	"diskstat":         new(DiskstatCollector),
-	"tempstat":        new(TempCollector),
+	"tempstat":         new(TempCollector),
-	"ipmistat":        new(IpmiCollector),
+	"ipmistat":         new(IpmiCollector),
-	"gpfs":            new(GpfsCollector),
+	"gpfs":             new(GpfsCollector),
-	"cpufreq":         new(CPUFreqCollector),
+	"cpufreq":          new(CPUFreqCollector),
-	"cpufreq_cpuinfo": new(CPUFreqCpuInfoCollector),
+	"cpufreq_cpuinfo":  new(CPUFreqCpuInfoCollector),
-	"nfs3stat":        new(Nfs3Collector),
+	"nfs3stat":         new(Nfs3Collector),
-	"nfs4stat":        new(Nfs4Collector),
+	"nfs4stat":         new(Nfs4Collector),
-	"numastats":       new(NUMAStatsCollector),
+	"numastats":        new(NUMAStatsCollector),
-	"beegfs_meta":     new(BeegfsMetaCollector),
+	"beegfs_meta":      new(BeegfsMetaCollector),
-	"beegfs_storage":  new(BeegfsStorageCollector),
+	"beegfs_storage":   new(BeegfsStorageCollector),
-	"rapl":            new(RAPLCollector),
-	"rocm_smi":        new(RocmSmiCollector),
-	"self":            new(SelfCollector),
-	"schedstat":       new(SchedstatCollector),
-	"nfsiostat":       new(NfsIOStatCollector),
-	"likwidenergy":    new(LikwidEnergyCollector),
 }
 
 // Metric collector manager data structure
 type collectorManager struct {
-	collectors   []MetricCollector          // List of metric collectors to read in parallel
+	collectors []MetricCollector          // List of metric collectors to use
-	serial       []MetricCollector          // List of metric collectors to read serially
+	output     chan lp.CCMetric           // Output channels
-	output       chan lp.CCMetric           // Output channels
+	done       chan bool                  // channel to finish / stop metric collector manager
-	done         chan bool                  // channel to finish / stop metric collector manager
+	ticker     mct.MultiChanTicker        // periodically ticking once each interval
-	ticker       mct.MultiChanTicker        // periodically ticking once each interval
+	duration   time.Duration              // duration (for metrics that measure over a given duration)
-	duration     time.Duration              // duration (for metrics that measure over a given duration)
+	wg         *sync.WaitGroup            // wait group for all goroutines in cc-metric-collector
-	wg           *sync.WaitGroup            // wait group for all goroutines in cc-metric-collector
+	config     map[string]json.RawMessage // json encoded config for collector manager
-	config       map[string]json.RawMessage // json encoded config for collector manager
-	collector_wg sync.WaitGroup             // internally used wait group for the parallel reading of collector
-	parallel_run bool                       // Flag whether the collectors are currently read in parallel
 }
 
 // Metric collector manager access functions
@@ -75,7 +66,6 @@ type CollectorManager interface {
 // Initialization is done for all configured collectors
 func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error {
 	cm.collectors = make([]MetricCollector, 0)
-	cm.serial = make([]MetricCollector, 0)
 	cm.output = nil
 	cm.done = make(chan bool)
 	cm.wg = wg
@@ -110,11 +100,7 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
 			continue
 		}
 		cclog.ComponentDebug("CollectorManager", "ADD COLLECTOR", collector.Name())
-		if collector.Parallel() {
+		cm.collectors = append(cm.collectors, collector)
-			cm.collectors = append(cm.collectors, collector)
-		} else {
-			cm.serial = append(cm.serial, collector)
-		}
 	}
 	return nil
 }
@@ -130,10 +116,6 @@ func (cm *collectorManager) Start() {
 		// Collector manager is done
 		done := func() {
 			// close all metric collectors
-			if cm.parallel_run {
-				cm.collector_wg.Wait()
-				cm.parallel_run = false
-			}
 			for _, c := range cm.collectors {
 				c.Close()
 			}
@@ -148,26 +130,7 @@ func (cm *collectorManager) Start() {
 				done()
 				return
 			case t := <-tick:
-				cm.parallel_run = true
 				for _, c := range cm.collectors {
-					// Wait for done signal or execute the collector
-					select {
-					case <-cm.done:
-						done()
-						return
-					default:
-						// Read metrics from collector c via goroutine
-						cclog.ComponentDebug("CollectorManager", c.Name(), t)
-						cm.collector_wg.Add(1)
-						go func(myc MetricCollector) {
-							myc.Read(cm.duration, cm.output)
-							cm.collector_wg.Done()
-						}(c)
-					}
-				}
-				cm.collector_wg.Wait()
-				cm.parallel_run = false
-				for _, c := range cm.serial {
 					// Wait for done signal or execute the collector
 					select {
 					case <-cm.done:

collectors/cpufreqCpuinfoMetric.go

@@ -10,22 +10,33 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
+//
 // CPUFreqCollector
 // a metric collector to measure the current frequency of the CPUs
 // as obtained from /proc/cpuinfo
 // Only measure on the first hyperthread
+//
 type CPUFreqCpuInfoCollectorTopology struct {
-	isHT   bool
+	processor               string // logical processor number (continuous, starting at 0)
-	tagSet map[string]string
+	coreID                  string // socket local core ID
+	coreID_int              int64
+	physicalPackageID       string // socket / package ID
+	physicalPackageID_int   int64
+	numPhysicalPackages     string // number of  sockets / packages
+	numPhysicalPackages_int int64
+	isHT                    bool
+	numNonHT                string // number of non hyperthreading processors
+	numNonHT_int            int64
+	tagSet                  map[string]string
 }
 
 type CPUFreqCpuInfoCollector struct {
 	metricCollector
-	topology []CPUFreqCpuInfoCollectorTopology
+	topology []*CPUFreqCpuInfoCollectorTopology
 }
 
 func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
@@ -37,7 +48,6 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 	m.setup()
 
 	m.name = "CPUFreqCpuInfoCollector"
-	m.parallel = true
 	m.meta = map[string]string{
 		"source": m.name,
 		"group":  "CPU",
@@ -54,9 +64,11 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 	// Collect topology information from file cpuinfo
 	foundFreq := false
 	processor := ""
+	var numNonHT_int int64 = 0
 	coreID := ""
 	physicalPackageID := ""
-	m.topology = make([]CPUFreqCpuInfoCollectorTopology, 0)
+	var maxPhysicalPackageID int64 = 0
+	m.topology = make([]*CPUFreqCpuInfoCollectorTopology, 0)
 	coreSeenBefore := make(map[string]bool)
 
 	// Read cpuinfo file, line by line
@@ -85,22 +97,41 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 			len(coreID) > 0 &&
 			len(physicalPackageID) > 0 {
 
+			topology := new(CPUFreqCpuInfoCollectorTopology)
+
+			// Processor
+			topology.processor = processor
+
+			// Core ID
+			topology.coreID = coreID
+			topology.coreID_int, err = strconv.ParseInt(coreID, 10, 64)
+			if err != nil {
+				return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
+			}
+
+			// Physical package ID
+			topology.physicalPackageID = physicalPackageID
+			topology.physicalPackageID_int, err = strconv.ParseInt(physicalPackageID, 10, 64)
+			if err != nil {
+				return fmt.Errorf("unable to convert physicalPackageID '%s' to int64: %v", physicalPackageID, err)
+			}
+
+			// increase maximun socket / package ID, when required
+			if topology.physicalPackageID_int > maxPhysicalPackageID {
+				maxPhysicalPackageID = topology.physicalPackageID_int
+			}
+
+			// is hyperthread?
 			globalID := physicalPackageID + ":" + coreID
+			topology.isHT = coreSeenBefore[globalID]
+			coreSeenBefore[globalID] = true
+			if !topology.isHT {
+				// increase number on non hyper thread cores
+				numNonHT_int++
+			}
 
 			// store collected topology information
-			m.topology = append(m.topology,
+			m.topology = append(m.topology, topology)
-				CPUFreqCpuInfoCollectorTopology{
-					isHT: coreSeenBefore[globalID],
-					tagSet: map[string]string{
-						"type":       "hwthread",
-						"type-id":    processor,
-						"package_id": physicalPackageID,
-					},
-				},
-			)
-
-			// mark core as seen before
-			coreSeenBefore[globalID] = true
 
 			// reset topology information
 			foundFreq = false
@@ -110,9 +141,19 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 		}
 	}
 
-	// Check if at least one CPU with frequency information was detected
+	numPhysicalPackageID_int := maxPhysicalPackageID + 1
-	if len(m.topology) == 0 {
+	numPhysicalPackageID := fmt.Sprint(numPhysicalPackageID_int)
-		return fmt.Errorf("No CPU frequency info found in %s", cpuInfoFile)
+	numNonHT := fmt.Sprint(numNonHT_int)
+	for _, t := range m.topology {
+		t.numPhysicalPackages = numPhysicalPackageID
+		t.numPhysicalPackages_int = numPhysicalPackageID_int
+		t.numNonHT = numNonHT
+		t.numNonHT_int = numNonHT_int
+		t.tagSet = map[string]string{
+			"type":       "cpu",
+			"type-id":    t.processor,
+			"package_id": t.physicalPackageID,
+		}
 	}
 
 	m.init = true

collectors/cpufreqCpuinfoMetric.md

@@ -1,11 +1,10 @@
-## `cpufreq_cpuinfo` collector
 
+## `cpufreq_cpuinfo` collector
 ```json
   "cpufreq_cpuinfo": {}
 ```
 
-The `cpufreq_cpuinfo` collector reads the clock frequency from `/proc/cpuinfo` and outputs a handful **hwthread** metrics.
+The `cpufreq_cpuinfo` collector reads the clock frequency from `/proc/cpuinfo` and outputs a handful **cpu** metrics.
 
 Metrics:
-
 * `cpufreq`

collectors/cpufreqMetric.go

@@ -3,29 +3,40 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"os"
+	"io/ioutil"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	"github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 	"golang.org/x/sys/unix"
 )
 
 type CPUFreqCollectorTopology struct {
-	scalingCurFreqFile string
+	processor               string // logical processor number (continuous, starting at 0)
-	tagSet             map[string]string
+	coreID                  string // socket local core ID
+	coreID_int              int64
+	physicalPackageID       string // socket / package ID
+	physicalPackageID_int   int64
+	numPhysicalPackages     string // number of  sockets / packages
+	numPhysicalPackages_int int64
+	isHT                    bool
+	numNonHT                string // number of non hyperthreading processors
+	numNonHT_int            int64
+	scalingCurFreqFile      string
+	tagSet                  map[string]string
 }
 
+//
 // CPUFreqCollector
 // a metric collector to measure the current frequency of the CPUs
 // as obtained from the hardware (in KHz)
-// Only measure on the first hyper-thread
+// Only measure on the first hyper thread
 //
 // See: https://www.kernel.org/doc/html/latest/admin-guide/pm/cpufreq.html
+//
 type CPUFreqCollector struct {
 	metricCollector
 	topology []CPUFreqCollectorTopology
@@ -42,7 +53,6 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 
 	m.name = "CPUFreqCollector"
 	m.setup()
-	m.parallel = true
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -52,41 +62,111 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	m.meta = map[string]string{
 		"source": m.name,
 		"group":  "CPU",
-		"unit":   "Hz",
+		"unit":   "MHz",
 	}
 
-	m.topology = make([]CPUFreqCollectorTopology, 0)
+	// Loop for all CPU directories
-	for _, c := range ccTopology.CpuData() {
+	baseDir := "/sys/devices/system/cpu"
+	globPattern := filepath.Join(baseDir, "cpu[0-9]*")
+	cpuDirs, err := filepath.Glob(globPattern)
+	if err != nil {
+		return fmt.Errorf("unable to glob files with pattern '%s': %v", globPattern, err)
+	}
+	if cpuDirs == nil {
+		return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
+	}
 
-		// Skip hyper threading CPUs
+	// Initialize CPU topology
-		if c.CpuID != c.CoreCPUsList[0] {
+	m.topology = make([]CPUFreqCollectorTopology, len(cpuDirs))
-			continue
+	for _, cpuDir := range cpuDirs {
+		processor := strings.TrimPrefix(cpuDir, "/sys/devices/system/cpu/cpu")
+		processor_int, err := strconv.ParseInt(processor, 10, 64)
+		if err != nil {
+			return fmt.Errorf("unable to convert cpuID '%s' to int64: %v", processor, err)
+		}
+
+		// Read package ID
+		physicalPackageIDFile := filepath.Join(cpuDir, "topology", "physical_package_id")
+		line, err := ioutil.ReadFile(physicalPackageIDFile)
+		if err != nil {
+			return fmt.Errorf("unable to read physical package ID from file '%s': %v", physicalPackageIDFile, err)
+		}
+		physicalPackageID := strings.TrimSpace(string(line))
+		physicalPackageID_int, err := strconv.ParseInt(physicalPackageID, 10, 64)
+		if err != nil {
+			return fmt.Errorf("unable to convert packageID '%s' to int64: %v", physicalPackageID, err)
+		}
+
+		// Read core ID
+		coreIDFile := filepath.Join(cpuDir, "topology", "core_id")
+		line, err = ioutil.ReadFile(coreIDFile)
+		if err != nil {
+			return fmt.Errorf("unable to read core ID from file '%s': %v", coreIDFile, err)
+		}
+		coreID := strings.TrimSpace(string(line))
+		coreID_int, err := strconv.ParseInt(coreID, 10, 64)
+		if err != nil {
+			return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
 		}
 
 		// Check access to current frequency file
-		scalingCurFreqFile := filepath.Join("/sys/devices/system/cpu", fmt.Sprintf("cpu%d", c.CpuID), "cpufreq/scaling_cur_freq")
+		scalingCurFreqFile := filepath.Join(cpuDir, "cpufreq", "scaling_cur_freq")
-		err := unix.Access(scalingCurFreqFile, unix.R_OK)
+		err = unix.Access(scalingCurFreqFile, unix.R_OK)
 		if err != nil {
 			return fmt.Errorf("unable to access file '%s': %v", scalingCurFreqFile, err)
 		}
 
-		m.topology = append(m.topology,
+		t := &m.topology[processor_int]
-			CPUFreqCollectorTopology{
+		t.processor = processor
-				tagSet: map[string]string{
+		t.physicalPackageID = physicalPackageID
-					"type":       "hwthread",
+		t.physicalPackageID_int = physicalPackageID_int
-					"type-id":    fmt.Sprint(c.CpuID),
+		t.coreID = coreID
-					"package_id": fmt.Sprint(c.Socket),
+		t.coreID_int = coreID_int
-				},
+		t.scalingCurFreqFile = scalingCurFreqFile
-				scalingCurFreqFile: scalingCurFreqFile,
+	}
-			},
+
-		)
+	// is processor a hyperthread?
+	coreSeenBefore := make(map[string]bool)
+	for i := range m.topology {
+		t := &m.topology[i]
+
+		globalID := t.physicalPackageID + ":" + t.coreID
+		t.isHT = coreSeenBefore[globalID]
+		coreSeenBefore[globalID] = true
+	}
+
+	// number of non hyper thread cores and packages / sockets
+	var numNonHT_int int64 = 0
+	var maxPhysicalPackageID int64 = 0
+	for i := range m.topology {
+		t := &m.topology[i]
+
+		// Update maxPackageID
+		if t.physicalPackageID_int > maxPhysicalPackageID {
+			maxPhysicalPackageID = t.physicalPackageID_int
+		}
+
+		if !t.isHT {
+			numNonHT_int++
+		}
+	}
+
+	numPhysicalPackageID_int := maxPhysicalPackageID + 1
+	numPhysicalPackageID := fmt.Sprint(numPhysicalPackageID_int)
+	numNonHT := fmt.Sprint(numNonHT_int)
+	for i := range m.topology {
+		t := &m.topology[i]
+		t.numPhysicalPackages = numPhysicalPackageID
+		t.numPhysicalPackages_int = numPhysicalPackageID_int
+		t.numNonHT = numNonHT
+		t.numNonHT_int = numNonHT_int
+		t.tagSet = map[string]string{
+			"type":       "cpu",
+			"type-id":    t.processor,
+			"package_id": t.physicalPackageID,
+		}
 	}
 
-	// Initialized
-	cclog.ComponentDebug(
-		m.name,
-		"initialized",
-		len(m.topology), "non-hyper-threading CPUs")
 	m.init = true
 	return nil
 }
@@ -101,8 +181,13 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	for i := range m.topology {
 		t := &m.topology[i]
 
+		// skip hyperthreads
+		if t.isHT {
+			continue
+		}
+
 		// Read current frequency
-		line, err := os.ReadFile(t.scalingCurFreqFile)
+		line, err := ioutil.ReadFile(t.scalingCurFreqFile)
 		if err != nil {
 			cclog.ComponentError(
 				m.name,

collectors/cpufreqMetric.md

@@ -1,13 +1,11 @@
 ## `cpufreq_cpuinfo` collector
-
 ```json
   "cpufreq": {
     "exclude_metrics": []
   }
 ```
 
-The `cpufreq` collector reads the clock frequency from `/sys/devices/system/cpu/cpu*/cpufreq` and outputs a handful **hwthread** metrics.
+The `cpufreq` collector reads the clock frequency from `/sys/devices/system/cpu/cpu*/cpufreq` and outputs a handful **cpu** metrics.
 
 Metrics:
-
+* `cpufreq`
-* `cpufreq`

collectors/cpustatMetric.go

@@ -9,9 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	sysconf "github.com/tklauser/go-sysconf"
 )
 
 const CPUSTATFILE = `/proc/stat`
@@ -22,18 +21,15 @@ type CpustatCollectorConfig struct {
 
 type CpustatCollector struct {
 	metricCollector
-	config        CpustatCollectorConfig
+	config   CpustatCollectorConfig
-	lastTimestamp time.Time // Store time stamp of last tick to derive values
+	matches  map[string]int
-	matches       map[string]int
+	cputags  map[string]map[string]string
-	cputags       map[string]map[string]string
+	nodetags map[string]string
-	nodetags      map[string]string
-	olddata       map[string]map[string]int64
 }
 
 func (m *CpustatCollector) Init(config json.RawMessage) error {
 	m.name = "CpustatCollector"
 	m.setup()
-	m.parallel = true
 	m.meta = map[string]string{"source": m.name, "group": "CPU", "unit": "Percent"}
 	m.nodetags = map[string]string{"type": "node"}
 	if len(config) > 0 {
@@ -79,57 +75,36 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
 	// Pre-generate tags for all CPUs
 	num_cpus := 0
 	m.cputags = make(map[string]map[string]string)
-	m.olddata = make(map[string]map[string]int64)
 	scanner := bufio.NewScanner(file)
 	for scanner.Scan() {
 		line := scanner.Text()
 		linefields := strings.Fields(line)
-		if strings.Compare(linefields[0], "cpu") == 0 {
+		if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
-			m.olddata["cpu"] = make(map[string]int64)
-			for k, v := range m.matches {
-				m.olddata["cpu"][k], _ = strconv.ParseInt(linefields[v], 0, 64)
-			}
-		} else if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
 			cpustr := strings.TrimLeft(linefields[0], "cpu")
 			cpu, _ := strconv.Atoi(cpustr)
-			m.cputags[linefields[0]] = map[string]string{"type": "hwthread", "type-id": fmt.Sprintf("%d", cpu)}
+			m.cputags[linefields[0]] = map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", cpu)}
-			m.olddata[linefields[0]] = make(map[string]int64)
-			for k, v := range m.matches {
-				m.olddata[linefields[0]][k], _ = strconv.ParseInt(linefields[v], 0, 64)
-			}
 			num_cpus++
 		}
 	}
-	m.lastTimestamp = time.Now()
 	m.init = true
 	return nil
 }
 
-func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
+func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric) {
 	values := make(map[string]float64)
-	clktck, _ := sysconf.Sysconf(sysconf.SC_CLK_TCK)
+	total := 0.0
 	for match, index := range m.matches {
 		if len(match) > 0 {
 			x, err := strconv.ParseInt(linefields[index], 0, 64)
 			if err == nil {
-				vdiff := x - m.olddata[linefields[0]][match]
+				values[match] = float64(x)
-				m.olddata[linefields[0]][match] = x // Store new value for next run
+				total += values[match]
-				values[match] = float64(vdiff) / float64(tsdelta.Seconds()) / float64(clktck)
 			}
 		}
 	}
-
+	t := time.Now()
-	sum := float64(0)
 	for name, value := range values {
-		sum += value
+		y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": (value * 100.0) / total}, t)
-		y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value * 100}, now)
-		if err == nil {
-			output <- y
-		}
-	}
-	if v, ok := values["cpu_idle"]; ok {
-		sum -= v
-		y, err := lp.New("cpu_used", tags, m.meta, map[string]interface{}{"value": sum * 100}, now)
 		if err == nil {
 			output <- y
 		}
@@ -141,9 +116,6 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		return
 	}
 	num_cpus := 0
-	now := time.Now()
-	tsdelta := now.Sub(m.lastTimestamp)
-
 	file, err := os.Open(string(CPUSTATFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
@@ -155,9 +127,9 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		line := scanner.Text()
 		linefields := strings.Fields(line)
 		if strings.Compare(linefields[0], "cpu") == 0 {
-			m.parseStatLine(linefields, m.nodetags, output, now, tsdelta)
+			m.parseStatLine(linefields, m.nodetags, output)
 		} else if strings.HasPrefix(linefields[0], "cpu") {
-			m.parseStatLine(linefields, m.cputags[linefields[0]], output, now, tsdelta)
+			m.parseStatLine(linefields, m.cputags[linefields[0]], output)
 			num_cpus++
 		}
 	}
@@ -166,13 +138,11 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		m.nodetags,
 		m.meta,
 		map[string]interface{}{"value": int(num_cpus)},
-		now,
+		time.Now(),
 	)
 	if err == nil {
 		output <- num_cpus_metric
 	}
-
-	m.lastTimestamp = now
 }
 
 func (m *CpustatCollector) Close() {

collectors/cpustatMetric.md

@@ -1,6 +1,5 @@
 
 ## `cpustat` collector
-
 ```json
   "cpustat": {
     "exclude_metrics": [
@@ -9,10 +8,9 @@
   }
 ```
 
-The `cpustat` collector reads data from `/proc/stat` and outputs a handful **node** and **hwthread** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
+The `cpustat` collector reads data from `/proc/stats` and outputs a handful **node** and **hwthread** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
 
 Metrics:
-
 * `cpu_user`
 * `cpu_nice`
 * `cpu_system`
@@ -23,4 +21,3 @@ Metrics:
 * `cpu_steal`
 * `cpu_guest`
 * `cpu_guest_nice`
-* `cpu_used` = `cpu_* - cpu_idle`

collectors/customCmdMetric.go

@@ -3,13 +3,13 @@ package collectors
 import (
 	"encoding/json"
 	"errors"
+	"io/ioutil"
 	"log"
-	"os"
 	"os/exec"
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 )
 
@@ -33,7 +33,6 @@ type CustomCmdCollector struct {
 func (m *CustomCmdCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "CustomCmdCollector"
-	m.parallel = true
 	m.meta = map[string]string{"source": m.name, "group": "Custom"}
 	if len(config) > 0 {
 		err = json.Unmarshal(config, &m.config)
@@ -48,12 +47,12 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
 		command := exec.Command(cmdfields[0], strings.Join(cmdfields[1:], " "))
 		command.Wait()
 		_, err = command.Output()
-		if err == nil {
+		if err != nil {
 			m.commands = append(m.commands, c)
 		}
 	}
 	for _, f := range m.config.Files {
-		_, err = os.ReadFile(f)
+		_, err = ioutil.ReadFile(f)
 		if err == nil {
 			m.files = append(m.files, f)
 		} else {
@@ -106,7 +105,7 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 		}
 	}
 	for _, file := range m.files {
-		buffer, err := os.ReadFile(file)
+		buffer, err := ioutil.ReadFile(file)
 		if err != nil {
 			log.Print(err)
 			return

collectors/diskstatMetric.go

@@ -8,8 +8,8 @@ import (
 	"syscall"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 //	"log"
@@ -29,7 +29,6 @@ type DiskstatCollector struct {
 
 func (m *DiskstatCollector) Init(config json.RawMessage) error {
 	m.name = "DiskstatCollector"
-	m.parallel = true
 	m.meta = map[string]string{"source": m.name, "group": "Disk"}
 	m.setup()
 	if len(config) > 0 {
@@ -78,18 +77,11 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric
 			continue
 		}
 		path := strings.Replace(linefields[1], `\040`, " ", -1)
-		stat := syscall.Statfs_t{
+		stat := syscall.Statfs_t{}
-			Blocks: 0,
-			Bsize:  0,
-			Bfree:  0,
-		}
 		err := syscall.Statfs(path, &stat)
 		if err != nil {
 			continue
 		}
-		if stat.Blocks == 0 || stat.Bsize == 0 {
-			continue
-		}
 		tags := map[string]string{"type": "node", "device": linefields[0]}
 		total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)
 		y, err := lp.New("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now())
@@ -103,11 +95,9 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric
 			y.AddMeta("unit", "GBytes")
 			output <- y
 		}
-		if total > 0 {
+		perc := (100 * (total - free)) / total
-			perc := (100 * (total - free)) / total
+		if perc > part_max_used {
-			if perc > part_max_used {
+			part_max_used = perc
-				part_max_used = perc
-			}
 		}
 	}
 	y, err := lp.New("part_max_used", map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": int(part_max_used)}, time.Now())

collectors/gpfsMetric.go

@@ -5,7 +5,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io"
+	"io/ioutil"
 	"log"
 	"os/exec"
 	"os/user"
@@ -13,8 +13,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 const DEFAULT_GPFS_CMD = "mmpmon"
@@ -31,7 +31,6 @@ type GpfsCollector struct {
 		Mmpmon            string   `json:"mmpmon_path,omitempty"`
 		ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
 		SendBandwidths    bool     `json:"send_bandwidths"`
-		SendTotalValues   bool     `json:"send_total_values"`
 	}
 	skipFS        map[string]struct{}
 	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
@@ -47,7 +46,6 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "GpfsCollector"
 	m.setup()
-	m.parallel = true
 
 	// Set default mmpmon binary
 	m.config.Mmpmon = DEFAULT_GPFS_CMD
@@ -119,8 +117,8 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	cmd.Stderr = cmdStderr
 	err := cmd.Run()
 	if err != nil {
-		dataStdErr, _ := io.ReadAll(cmdStderr)
+		dataStdErr, _ := ioutil.ReadAll(cmdStderr)
-		dataStdOut, _ := io.ReadAll(cmdStdout)
+		dataStdOut, _ := ioutil.ReadAll(cmdStdout)
 		cclog.ComponentError(
 			m.name,
 			fmt.Sprintf("Read(): Failed to execute command \"%s\": %v\n", cmd.String(), err),
@@ -217,33 +215,13 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert bytes read '%s' to int64: %v", key_value["_br_"], err))
 			continue
 		}
-		if y, err :=
+		if y, err := lp.New("gpfs_bytes_read", m.tags, m.meta, map[string]interface{}{"value": bytesRead}, timestamp); err == nil {
-			lp.New(
-				"gpfs_bytes_read",
-				m.tags,
-				m.meta,
-				map[string]interface{}{
-					"value": bytesRead,
-				},
-				timestamp,
-			); err == nil {
-			y.AddMeta("unit", "bytes")
 			output <- y
 		}
 		if m.config.SendBandwidths {
 			if lastBytesRead := m.lastState[filesystem].bytesRead; lastBytesRead >= 0 {
 				bwRead := float64(bytesRead-lastBytesRead) / timeDiff
-				if y, err :=
+				if y, err := lp.New("gpfs_bw_read", m.tags, m.meta, map[string]interface{}{"value": bwRead}, timestamp); err == nil {
-					lp.New(
-						"gpfs_bw_read",
-						m.tags,
-						m.meta,
-						map[string]interface{}{
-							"value": bwRead,
-						},
-						timestamp,
-					); err == nil {
-					y.AddMeta("unit", "bytes/sec")
 					output <- y
 				}
 			}
@@ -257,33 +235,13 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert bytes written '%s' to int64: %v", key_value["_bw_"], err))
 			continue
 		}
-		if y, err :=
+		if y, err := lp.New("gpfs_bytes_written", m.tags, m.meta, map[string]interface{}{"value": bytesWritten}, timestamp); err == nil {
-			lp.New(
-				"gpfs_bytes_written",
-				m.tags,
-				m.meta,
-				map[string]interface{}{
-					"value": bytesWritten,
-				},
-				timestamp,
-			); err == nil {
-			y.AddMeta("unit", "bytes")
 			output <- y
 		}
 		if m.config.SendBandwidths {
 			if lastBytesWritten := m.lastState[filesystem].bytesRead; lastBytesWritten >= 0 {
 				bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff
-				if y, err :=
+				if y, err := lp.New("gpfs_bw_write", m.tags, m.meta, map[string]interface{}{"value": bwWrite}, timestamp); err == nil {
-					lp.New(
-						"gpfs_bw_write",
-						m.tags,
-						m.meta,
-						map[string]interface{}{
-							"value": bwWrite,
-						},
-						timestamp,
-					); err == nil {
-					y.AddMeta("unit", "bytes/sec")
 					output <- y
 				}
 			}
@@ -367,47 +325,6 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 		if y, err := lp.New("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
 			output <- y
 		}
-
-		// Total values
-		if m.config.SendTotalValues {
-			bytesTotal := bytesRead + bytesWritten
-			if y, err :=
-				lp.New("gpfs_bytes_total",
-					m.tags,
-					m.meta,
-					map[string]interface{}{
-						"value": bytesTotal,
-					},
-					timestamp,
-				); err == nil {
-				y.AddMeta("unit", "bytes")
-				output <- y
-			}
-			iops := numReads + numWrites
-			if y, err :=
-				lp.New("gpfs_iops",
-					m.tags,
-					m.meta,
-					map[string]interface{}{
-						"value": iops,
-					},
-					timestamp,
-				); err == nil {
-				output <- y
-			}
-			metaops := numInodeUpdates + numCloses + numOpens + numReaddirs
-			if y, err :=
-				lp.New("gpfs_metaops",
-					m.tags,
-					m.meta,
-					map[string]interface{}{
-						"value": metaops,
-					},
-					timestamp,
-				); err == nil {
-				output <- y
-			}
-		}
 	}
 }
 

collectors/gpfsMetric.md

@@ -6,8 +6,7 @@
     "exclude_filesystem": [
       "fs1"
     ],
-    "send_bandwidths": true,
+    "send_bandwidths" : true
-    "send_total_values": true
   }
 ```
 
@@ -27,12 +26,8 @@ Metrics:
 * `gpfs_num_opens`
 * `gpfs_num_closes`
 * `gpfs_num_reads`
-* `gpfs_num_writes`
 * `gpfs_num_readdirs`
 * `gpfs_num_inode_updates`
-* `gpfs_bytes_total = gpfs_bytes_read + gpfs_bytes_written` (if `send_total_values == true`)
-* `gpfs_iops = gpfs_num_reads + gpfs_num_writes` (if `send_total_values == true`)
-* `gpfs_metaops = gpfs_num_inode_updates + gpfs_num_closes + gpfs_num_opens + gpfs_num_readdirs` (if `send_total_values == true`)
 * `gpfs_bw_read` (if `send_bandwidths == true`)
 * `gpfs_bw_write` (if `send_bandwidths == true`)
 

collectors/infinibandMetric.go

@@ -2,10 +2,11 @@ package collectors
 
 import (
 	"fmt"
+	"io/ioutil"
 	"os"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	"golang.org/x/sys/unix"
 
 	"encoding/json"
@@ -18,22 +19,17 @@ import (
 const IB_BASEPATH = "/sys/class/infiniband/"
 
 type InfinibandCollectorMetric struct {
-	name             string
+	path string
-	path             string
+	unit string
-	unit             string
-	scale            int64
-	addToIBTotal     bool
-	addToIBTotalPkgs bool
-	currentState     int64
-	lastState        int64
 }
 
 type InfinibandCollectorInfo struct {
-	LID              string                      // IB local Identifier (LID)
+	LID              string                               // IB local Identifier (LID)
-	device           string                      // IB device
+	device           string                               // IB device
-	port             string                      // IB device port
+	port             string                               // IB device port
-	portCounterFiles []InfinibandCollectorMetric // mapping counter name -> InfinibandCollectorMetric
+	portCounterFiles map[string]InfinibandCollectorMetric // mapping counter name -> InfinibandCollectorMetric
-	tagSet           map[string]string           // corresponding tag list
+	tagSet           map[string]string                    // corresponding tag list
+	lastState        map[string]int64                     // State from last measurement
 }
 
 type InfinibandCollector struct {
@@ -41,10 +37,9 @@ type InfinibandCollector struct {
 	config struct {
 		ExcludeDevices     []string `json:"exclude_devices,omitempty"` // IB device to exclude e.g. mlx5_0
 		SendAbsoluteValues bool     `json:"send_abs_values"`           // Send absolut values as read from sys filesystem
-		SendTotalValues    bool     `json:"send_total_values"`         // Send computed total values
 		SendDerivedValues  bool     `json:"send_derived_values"`       // Send derived values e.g. rates
 	}
-	info          []InfinibandCollectorInfo
+	info          []*InfinibandCollectorInfo
 	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
 }
 
@@ -59,7 +54,6 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "InfinibandCollector"
 	m.setup()
-	m.parallel = true
 	m.meta = map[string]string{
 		"source": m.name,
 		"group":  "Network",
@@ -89,7 +83,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	for _, path := range ibDirs {
 
 		// Skip, when no LID is assigned
-		line, err := os.ReadFile(filepath.Join(path, "lid"))
+		line, err := ioutil.ReadFile(filepath.Join(path, "lid"))
 		if err != nil {
 			continue
 		}
@@ -117,39 +111,11 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 
 		// Check access to counter files
 		countersDir := filepath.Join(path, "counters")
-		portCounterFiles := []InfinibandCollectorMetric{
+		portCounterFiles := map[string]InfinibandCollectorMetric{
-			{
+			"ib_recv":      {path: filepath.Join(countersDir, "port_rcv_data"), unit: "bytes"},
-				name:         "ib_recv",
+			"ib_xmit":      {path: filepath.Join(countersDir, "port_xmit_data"), unit: "bytes"},
-				path:         filepath.Join(countersDir, "port_rcv_data"),
+			"ib_recv_pkts": {path: filepath.Join(countersDir, "port_rcv_packets"), unit: "packets"},
-				unit:         "bytes",
+			"ib_xmit_pkts": {path: filepath.Join(countersDir, "port_xmit_packets"), unit: "packets"},
-				scale:        4,
-				addToIBTotal: true,
-				lastState:    -1,
-			},
-			{
-				name:         "ib_xmit",
-				path:         filepath.Join(countersDir, "port_xmit_data"),
-				unit:         "bytes",
-				scale:        4,
-				addToIBTotal: true,
-				lastState:    -1,
-			},
-			{
-				name:             "ib_recv_pkts",
-				path:             filepath.Join(countersDir, "port_rcv_packets"),
-				unit:             "packets",
-				scale:            1,
-				addToIBTotalPkgs: true,
-				lastState:        -1,
-			},
-			{
-				name:             "ib_xmit_pkts",
-				path:             filepath.Join(countersDir, "port_xmit_packets"),
-				unit:             "packets",
-				scale:            1,
-				addToIBTotalPkgs: true,
-				lastState:        -1,
-			},
 		}
 		for _, counter := range portCounterFiles {
 			err := unix.Access(counter.path, unix.R_OK)
@@ -158,8 +124,14 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 			}
 		}
 
+		// Initialize last state
+		lastState := make(map[string]int64)
+		for counter := range portCounterFiles {
+			lastState[counter] = -1
+		}
+
 		m.info = append(m.info,
-			InfinibandCollectorInfo{
+			&InfinibandCollectorInfo{
 				LID:              LID,
 				device:           device,
 				port:             port,
@@ -170,6 +142,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 					"port":   port,
 					"lid":    LID,
 				},
+				lastState: lastState,
 			})
 	}
 
@@ -196,15 +169,11 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 	// Save current timestamp
 	m.lastTimestamp = now
 
-	for i := range m.info {
+	for _, info := range m.info {
-		info := &m.info[i]
+		for counterName, counterDef := range info.portCounterFiles {
-
-		var ib_total, ib_total_pkts int64
-		for i := range info.portCounterFiles {
-			counterDef := &info.portCounterFiles[i]
 
 			// Read counter file
-			line, err := os.ReadFile(counterDef.path)
+			line, err := ioutil.ReadFile(counterDef.path)
 			if err != nil {
 				cclog.ComponentError(
 					m.name,
@@ -218,26 +187,13 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 			if err != nil {
 				cclog.ComponentError(
 					m.name,
-					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterDef.name, data, err))
+					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterName, data, err))
 				continue
 			}
-			// Scale raw value
-			v *= counterDef.scale
-
-			// Save current state
-			counterDef.currentState = v
 
 			// Send absolut values
 			if m.config.SendAbsoluteValues {
-				if y, err :=
+				if y, err := lp.New(counterName, info.tagSet, m.meta, map[string]interface{}{"value": v}, now); err == nil {
-					lp.New(
-						counterDef.name,
-						info.tagSet,
-						m.meta,
-						map[string]interface{}{
-							"value": counterDef.currentState,
-						},
-						now); err == nil {
 					y.AddMeta("unit", counterDef.unit)
 					output <- y
 				}
@@ -245,64 +201,18 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 
 			// Send derived values
 			if m.config.SendDerivedValues {
-				if counterDef.lastState >= 0 {
+				if info.lastState[counterName] >= 0 {
-					rate := float64((counterDef.currentState - counterDef.lastState)) / timeDiff
+					rate := float64((v - info.lastState[counterName])) / timeDiff
-					if y, err :=
+					if y, err := lp.New(counterName+"_bw", info.tagSet, m.meta, map[string]interface{}{"value": rate}, now); err == nil {
-						lp.New(
-							counterDef.name+"_bw",
-							info.tagSet,
-							m.meta,
-							map[string]interface{}{
-								"value": rate,
-							},
-							now); err == nil {
 						y.AddMeta("unit", counterDef.unit+"/sec")
 						output <- y
-
 					}
 				}
-				counterDef.lastState = counterDef.currentState
+				// Save current state
-			}
+				info.lastState[counterName] = v
-
-			// Sum up total values
-			if m.config.SendTotalValues {
-				switch {
-				case counterDef.addToIBTotal:
-					ib_total += counterDef.currentState
-				case counterDef.addToIBTotalPkgs:
-					ib_total_pkts += counterDef.currentState
-				}
 			}
 		}
 
-		// Send total values
-		if m.config.SendTotalValues {
-			if y, err :=
-				lp.New(
-					"ib_total",
-					info.tagSet,
-					m.meta,
-					map[string]interface{}{
-						"value": ib_total,
-					},
-					now); err == nil {
-				y.AddMeta("unit", "bytes")
-				output <- y
-			}
-
-			if y, err :=
-				lp.New(
-					"ib_total_pkts",
-					info.tagSet,
-					m.meta,
-					map[string]interface{}{
-						"value": ib_total_pkts,
-					},
-					now); err == nil {
-				y.AddMeta("unit", "packets")
-				output <- y
-			}
-		}
 	}
 }
 

collectors/infinibandMetric.md

@@ -17,16 +17,13 @@ LID file (`/sys/class/infiniband/<dev>/ports/<port>/lid`)
 
 The devices can be filtered with the `exclude_devices` option in the configuration.
 
-For each found LID the collector reads data through the sysfs files below `/sys/class/infiniband/<device>`. (See: <https://www.kernel.org/doc/Documentation/ABI/stable/sysfs-class-infiniband>)
+For each found LID the collector reads data through the sysfs files below `/sys/class/infiniband/<device>`.
 
 Metrics:
-
 * `ib_recv`
 * `ib_xmit`
 * `ib_recv_pkts`
 * `ib_xmit_pkts`
-* `ib_total = ib_recv + ib_xmit` (if `send_total_values == true`)
-* `ib_total_pkts = ib_recv_pkts + ib_xmit_pkts` (if `send_total_values == true`)
 * `ib_recv_bw` (if `send_derived_values == true`)
 * `ib_xmit_bw` (if `send_derived_values == true`)
 * `ib_recv_pkts_bw` (if `send_derived_values == true`)

collectors/iostatMetric.go

@@ -4,8 +4,8 @@ import (
 	"bufio"
 	"os"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 
 	//	"log"
 	"encoding/json"
@@ -37,7 +37,6 @@ type IOstatCollector struct {
 func (m *IOstatCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "IOstatCollector"
-	m.parallel = true
 	m.meta = map[string]string{"source": m.name, "group": "Disk"}
 	m.setup()
 	if len(config) > 0 {

collectors/ipmiMetric.go

@@ -1,57 +1,50 @@
 package collectors
 
 import (
-	"bufio"
-	"bytes"
 	"encoding/json"
 	"errors"
-	"fmt"
-	"io"
 	"log"
+	"os"
 	"os/exec"
 	"strconv"
 	"strings"
 	"time"
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
+const IPMITOOL_PATH = `ipmitool`
 const IPMISENSORS_PATH = `ipmi-sensors`
 
+type IpmiCollectorConfig struct {
+	ExcludeDevices  []string `json:"exclude_devices"`
+	IpmitoolPath    string   `json:"ipmitool_path"`
+	IpmisensorsPath string   `json:"ipmisensors_path"`
+}
+
 type IpmiCollector struct {
 	metricCollector
-	config struct {
+	//tags        map[string]string
-		ExcludeDevices  []string `json:"exclude_devices"`
+	//matches     map[string]string
-		IpmitoolPath    string   `json:"ipmitool_path"`
+	config      IpmiCollectorConfig
-		IpmisensorsPath string   `json:"ipmisensors_path"`
-	}
 	ipmitool    string
 	ipmisensors string
 }
 
 func (m *IpmiCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
 	m.name = "IpmiCollector"
 	m.setup()
-	m.parallel = true
+	m.meta = map[string]string{"source": m.name, "group": "IPMI"}
-	m.meta = map[string]string{
+	m.config.IpmitoolPath = string(IPMITOOL_PATH)
-		"source": m.name,
+	m.config.IpmisensorsPath = string(IPMISENSORS_PATH)
-		"group":  "IPMI",
+	m.ipmitool = ""
-	}
+	m.ipmisensors = ""
-	// default path to IPMI tools
-	m.config.IpmitoolPath = "ipmitool"
-	m.config.IpmisensorsPath = "ipmi-sensors"
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	// Check if executables ipmitool or ipmisensors are found
 	p, err := exec.LookPath(m.config.IpmitoolPath)
 	if err == nil {
 		m.ipmitool = p
@@ -68,33 +61,25 @@ func (m *IpmiCollector) Init(config json.RawMessage) error {
 }
 
 func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
-
-	// Setup ipmitool command
 	command := exec.Command(cmd, "sensor")
-	stdout, _ := command.StdoutPipe()
+	command.Wait()
-	errBuf := new(bytes.Buffer)
+	stdout, err := command.Output()
-	command.Stderr = errBuf
+	if err != nil {
-
+		log.Print(err)
-	// start command
-	if err := command.Start(); err != nil {
-		cclog.ComponentError(
-			m.name,
-			fmt.Sprintf("readIpmiTool(): Failed to start command \"%s\": %v", command.String(), err),
-		)
 		return
 	}
 
-	// Read command output
+	ll := strings.Split(string(stdout), "\n")
-	scanner := bufio.NewScanner(stdout)
+
-	for scanner.Scan() {
+	for _, line := range ll {
-		lv := strings.Split(scanner.Text(), "|")
+		lv := strings.Split(line, "|")
 		if len(lv) < 3 {
 			continue
 		}
-		v, err := strconv.ParseFloat(strings.TrimSpace(lv[1]), 64)
+		v, err := strconv.ParseFloat(strings.Trim(lv[1], " "), 64)
 		if err == nil {
-			name := strings.ToLower(strings.Replace(strings.TrimSpace(lv[0]), " ", "_", -1))
+			name := strings.ToLower(strings.Replace(strings.Trim(lv[0], " "), " ", "_", -1))
-			unit := strings.TrimSpace(lv[2])
+			unit := strings.Trim(lv[2], " ")
 			if unit == "Volts" {
 				unit = "Volts"
 			} else if unit == "degrees C" {
@@ -112,17 +97,6 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
 			}
 		}
 	}
-
-	// Wait for command end
-	if err := command.Wait(); err != nil {
-		errMsg, _ := io.ReadAll(errBuf)
-		cclog.ComponentError(
-			m.name,
-			fmt.Sprintf("readIpmiTool(): Failed to wait for the end of command \"%s\": %v\n", command.String(), err),
-			fmt.Sprintf("readIpmiTool(): command stderr: \"%s\"\n", string(errMsg)),
-		)
-		return
-	}
 }
 
 func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
@@ -156,16 +130,16 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
 }
 
 func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-
-	// Check if already initialized
-	if !m.init {
-		return
-	}
-
 	if len(m.config.IpmitoolPath) > 0 {
-		m.readIpmiTool(m.config.IpmitoolPath, output)
+		_, err := os.Stat(m.config.IpmitoolPath)
+		if err == nil {
+			m.readIpmiTool(m.config.IpmitoolPath, output)
+		}
 	} else if len(m.config.IpmisensorsPath) > 0 {
-		m.readIpmiSensors(m.config.IpmisensorsPath, output)
+		_, err := os.Stat(m.config.IpmisensorsPath)
+		if err == nil {
+			m.readIpmiSensors(m.config.IpmisensorsPath, output)
+		}
 	}
 }
 

collectors/ipmiMetric.md

@@ -8,6 +8,9 @@
   }
 ```
 
-The `ipmistat` collector reads data from `ipmitool` (`ipmitool sensor`) or `ipmi-sensors` (`ipmi-sensors --sdr-cache-recreate --comma-separated-output`).
+The `ipmistat` collector reads data from `ipmitool` (`ipmitool sensor`) or `ipmi-sensors` (`ipmi-sensors --sdr-cache-recreate --comma-separated-output`). 
 
 The metrics depend on the output of the underlying tools but contain temperature, power and energy metrics.
+
+
+

collectors/likwidMetric.go

@@ -12,10 +12,10 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"io/ioutil"
 	"math"
 	"os"
 	"os/signal"
-	"os/user"
 	"sort"
 	"strconv"
 	"strings"
@@ -24,31 +24,25 @@ import (
 	"time"
 	"unsafe"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 	"github.com/NVIDIA/go-nvml/pkg/dl"
-	"github.com/fsnotify/fsnotify"
-	"golang.design/x/thread"
 )
 
 const (
 	LIKWID_LIB_NAME       = "liblikwid.so"
 	LIKWID_LIB_DL_FLAGS   = dl.RTLD_LAZY | dl.RTLD_GLOBAL
 	LIKWID_DEF_ACCESSMODE = "direct"
-	LIKWID_DEF_LOCKFILE   = "/var/run/likwid.lock"
 )
 
 type LikwidCollectorMetricConfig struct {
-	Name               string `json:"name"` // Name of the metric
+	Name    string `json:"name"` // Name of the metric
-	Calc               string `json:"calc"` // Calculation for the metric using
+	Calc    string `json:"calc"` // Calculation for the metric using
-	Type               string `json:"type"` // Metric type (aka node, socket, cpu, ...)
+	Type    string `json:"type"` // Metric type (aka node, socket, cpu, ...)
-	Publish            bool   `json:"publish"`
+	Publish bool   `json:"publish"`
-	SendCoreTotalVal   bool   `json:"send_core_total_values,omitempty"`
+	Unit    string `json:"unit"` // Unit of metric if any
-	SendSocketTotalVal bool   `json:"send_socket_total_values,omitempty"`
-	SendNodeTotalVal   bool   `json:"send_node_total_values,omitempty"`
-	Unit               string `json:"unit"` // Unit of metric if any
 }
 
 type LikwidCollectorEventsetConfig struct {
@@ -62,7 +56,7 @@ type LikwidEventsetConfig struct {
 	eorder   []*C.char
 	estr     *C.char
 	go_estr  string
-	results  map[int]map[string]float64
+	results  map[int]map[string]interface{}
 	metrics  map[int]map[string]float64
 }
 
@@ -74,26 +68,22 @@ type LikwidCollectorConfig struct {
 	AccessMode     string                          `json:"access_mode,omitempty"`
 	DaemonPath     string                          `json:"accessdaemon_path,omitempty"`
 	LibraryPath    string                          `json:"liblikwid_path,omitempty"`
-	LockfilePath   string                          `json:"lockfile_path,omitempty"`
 }
 
 type LikwidCollector struct {
 	metricCollector
-	cpulist       []C.int
+	cpulist      []C.int
-	cpu2tid       map[int]int
+	cpu2tid      map[int]int
-	sock2tid      map[int]int
+	sock2tid     map[int]int
-	tid2core      map[int]int
+	metrics      map[C.int]map[string]int
-	tid2socket    map[int]int
+	groups       []C.int
-	metrics       map[C.int]map[string]int
+	config       LikwidCollectorConfig
-	groups        []C.int
+	gmresults    map[int]map[string]float64
-	config        LikwidCollectorConfig
+	basefreq     float64
-	basefreq      float64
+	running      bool
-	running       bool
+	initialized  bool
-	initialized   bool
+	likwidGroups map[C.int]LikwidEventsetConfig
-	needs_reinit  bool
+	lock         sync.Mutex
-	likwidGroups  map[C.int]LikwidEventsetConfig
-	lock          sync.Mutex
-	measureThread thread.Thread
 }
 
 type LikwidMetric struct {
@@ -103,18 +93,6 @@ type LikwidMetric struct {
 	group_idx int
 }
 
-func checkMetricType(t string) bool {
-	valid := map[string]bool{
-		"node":         true,
-		"socket":       true,
-		"hwthread":     true,
-		"core":         true,
-		"memoryDomain": true,
-	}
-	_, ok := valid[t]
-	return ok
-}
-
 func eventsToEventStr(events map[string]string) string {
 	elist := make([]string, 0)
 	for k, v := range events {
@@ -138,10 +116,10 @@ func genLikwidEventSet(input LikwidCollectorEventsetConfig) LikwidEventsetConfig
 		elist = append(elist, c_counter)
 	}
 	estr := strings.Join(tmplist, ",")
-	res := make(map[int]map[string]float64)
+	res := make(map[int]map[string]interface{})
 	met := make(map[int]map[string]float64)
 	for _, i := range topo.CpuList() {
-		res[i] = make(map[string]float64)
+		res[i] = make(map[string]interface{})
 		for k := range input.Events {
 			res[i][k] = 0.0
 		}
@@ -161,7 +139,7 @@ func genLikwidEventSet(input LikwidCollectorEventsetConfig) LikwidEventsetConfig
 }
 
 func testLikwidMetricFormula(formula string, params []string) bool {
-	myparams := make(map[string]float64)
+	myparams := make(map[string]interface{})
 	for _, p := range params {
 		myparams[p] = float64(1.0)
 	}
@@ -176,13 +154,12 @@ func getBaseFreq() float64 {
 	}
 	var freq float64 = math.NaN()
 	for _, f := range files {
-		buffer, err := os.ReadFile(f)
+		buffer, err := ioutil.ReadFile(f)
 		if err == nil {
 			data := strings.Replace(string(buffer), "\n", "", -1)
 			x, err := strconv.ParseInt(data, 0, 64)
 			if err == nil {
-				freq = float64(x)
+				freq = float64(x) * 1e6
-				break
 			}
 		}
 	}
@@ -191,22 +168,19 @@ func getBaseFreq() float64 {
 		C.power_init(0)
 		info := C.get_powerInfo()
 		if float64(info.baseFrequency) != 0 {
-			freq = float64(info.baseFrequency)
+			freq = float64(info.baseFrequency) * 1e6
 		}
 		C.power_finalize()
 	}
-	return freq * 1e3
+	return freq
 }
 
 func (m *LikwidCollector) Init(config json.RawMessage) error {
 	m.name = "LikwidCollector"
-	m.parallel = false
 	m.initialized = false
-	m.needs_reinit = true
 	m.running = false
 	m.config.AccessMode = LIKWID_DEF_ACCESSMODE
 	m.config.LibraryPath = LIKWID_LIB_NAME
-	m.config.LockfilePath = LIKWID_DEF_LOCKFILE
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -230,7 +204,7 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 
 	m.meta = map[string]string{"group": "PerfCounter"}
 	cclog.ComponentDebug(m.name, "Get cpulist and init maps and lists")
-	cpulist := topo.HwthreadList()
+	cpulist := topo.CpuList()
 	m.cpulist = make([]C.int, len(cpulist))
 	m.cpu2tid = make(map[int]int)
 	for i, c := range cpulist {
@@ -240,6 +214,13 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 
 	m.likwidGroups = make(map[C.int]LikwidEventsetConfig)
 
+	// m.results = make(map[int]map[int]map[string]interface{})
+	// m.mresults = make(map[int]map[int]map[string]float64)
+	m.gmresults = make(map[int]map[string]float64)
+	for _, tid := range m.cpu2tid {
+		m.gmresults[tid] = make(map[string]float64)
+	}
+
 	// This is for the global metrics computation test
 	totalMetrics := 0
 	// Generate parameter list for the metric computing test
@@ -257,16 +238,12 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 			}
 			for _, metric := range evset.Metrics {
 				// Try to evaluate the metric
-				cclog.ComponentDebug(m.name, "Checking", metric.Name)
+				if testLikwidMetricFormula(metric.Calc, params) {
-				if !checkMetricType(metric.Type) {
+					// Add the computable metric to the parameter list for the global metrics
-					cclog.ComponentError(m.name, "Metric", metric.Name, "uses invalid type", metric.Type)
-					metric.Calc = ""
-				} else if !testLikwidMetricFormula(metric.Calc, params) {
-					cclog.ComponentError(m.name, "Metric", metric.Name, "cannot be calculated with given counters")
-					metric.Calc = ""
-				} else {
 					globalParams = append(globalParams, metric.Name)
 					totalMetrics++
+				} else {
+					metric.Calc = ""
 				}
 			}
 		} else {
@@ -276,14 +253,8 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 	}
 	for _, metric := range m.config.Metrics {
 		// Try to evaluate the global metric
-		if !checkMetricType(metric.Type) {
+		if !testLikwidMetricFormula(metric.Calc, globalParams) {
-			cclog.ComponentError(m.name, "Metric", metric.Name, "uses invalid type", metric.Type)
+			cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed")
-			metric.Calc = ""
-		} else if !testLikwidMetricFormula(metric.Calc, globalParams) {
-			cclog.ComponentError(m.name, "Metric", metric.Name, "cannot be calculated with given counters")
-			metric.Calc = ""
-		} else if !checkMetricType(metric.Type) {
-			cclog.ComponentError(m.name, "Metric", metric.Name, "has invalid type")
 			metric.Calc = ""
 		} else {
 			totalMetrics++
@@ -296,243 +267,56 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 		cclog.ComponentError(m.name, err.Error())
 		return err
 	}
-
-	ret := C.topology_init()
-	if ret != 0 {
-		err := errors.New("failed to initialize topology module")
-		cclog.ComponentError(m.name, err.Error())
-		return err
-	}
-	m.measureThread = thread.New()
-	switch m.config.AccessMode {
-	case "direct":
-		C.HPMmode(0)
-	case "accessdaemon":
-		if len(m.config.DaemonPath) > 0 {
-			p := os.Getenv("PATH")
-			os.Setenv("PATH", m.config.DaemonPath+":"+p)
-		}
-		C.HPMmode(1)
-		retCode := C.HPMinit()
-		if retCode != 0 {
-			err := fmt.Errorf("C.HPMinit() failed with return code %v", retCode)
-			cclog.ComponentError(m.name, err.Error())
-		}
-		for _, c := range m.cpulist {
-			m.measureThread.Call(
-				func() {
-					retCode := C.HPMaddThread(c)
-					if retCode != 0 {
-						err := fmt.Errorf("C.HPMaddThread(%v) failed with return code %v", c, retCode)
-						cclog.ComponentError(m.name, err.Error())
-					}
-				})
-		}
-	}
-	m.sock2tid = make(map[int]int)
-	tmp := make([]C.int, 1)
-	for _, sid := range topo.SocketList() {
-		cstr := C.CString(fmt.Sprintf("S%d:0", sid))
-		ret = C.cpustr_to_cpulist(cstr, &tmp[0], 1)
-		if ret > 0 {
-			m.sock2tid[sid] = m.cpu2tid[int(tmp[0])]
-		}
-		C.free(unsafe.Pointer(cstr))
-	}
-
-	cpuData := topo.CpuData()
-	m.tid2core = make(map[int]int, len(cpuData))
-	m.tid2socket = make(map[int]int, len(cpuData))
-	for i := range cpuData {
-		c := &cpuData[i]
-		// Hardware thread ID to core ID mapping
-		if len(c.CoreCPUsList) > 0 {
-			m.tid2core[c.CpuID] = c.CoreCPUsList[0]
-		} else {
-			m.tid2core[c.CpuID] = c.CpuID
-		}
-		// Hardware thead ID to socket ID mapping
-		m.tid2socket[c.CpuID] = c.Socket
-	}
-
-	m.basefreq = getBaseFreq()
 	m.init = true
 	return nil
 }
 
 // take a measurement for 'interval' seconds of event set index 'group'
-func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig, interval time.Duration) (bool, error) {
+func (m *LikwidCollector) takeMeasurement(evset LikwidEventsetConfig, interval time.Duration) (bool, error) {
 	var ret C.int
-	var gid C.int = -1
-	sigchan := make(chan os.Signal, 1)
-
-	// Watch changes for the lock file ()
-	watcher, err := fsnotify.NewWatcher()
-	if err != nil {
-		cclog.ComponentError(m.name, err.Error())
-		return true, err
-	}
-	defer watcher.Close()
-	if len(m.config.LockfilePath) > 0 {
-		info, err := os.Stat(m.config.LockfilePath)
-		if err != nil {
-			return true, err
-		}
-		uid := info.Sys().(*syscall.Stat_t).Uid
-		if uid != uint32(os.Getuid()) {
-			usr, err := user.LookupId(fmt.Sprint(uid))
-			if err == nil {
-				return true, fmt.Errorf("Access to performance counters locked by %s", usr.Username)
-			} else {
-				return true, fmt.Errorf("Access to performance counters locked by %d", uid)
-			}
-		}
-		err = watcher.Add(m.config.LockfilePath)
-		if err != nil {
-			cclog.ComponentError(m.name, err.Error())
-		}
-	}
 	m.lock.Lock()
-	defer m.lock.Unlock()
+	if m.initialized {
-
+		ret = C.perfmon_setupCounters(evset.gid)
-	// Initialize the performance monitoring feature by creating basic data structures
+		if ret != 0 {
-	select {
+			var err error = nil
-	case e := <-watcher.Events:
+			var skip bool = false
-		ret = -1
+			if ret == -37 {
-		if e.Op != fsnotify.Chmod {
+				skip = true
-			ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
+			} else {
-		}
+				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
-	default:
-		ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
-	}
-	if ret != 0 {
-		return true, fmt.Errorf("failed to initialize library, error %d", ret)
-	}
-	signal.Notify(sigchan, os.Interrupt)
-	signal.Notify(sigchan, syscall.SIGCHLD)
-
-	// Add an event string to LIKWID
-	select {
-	case <-sigchan:
-		gid = -1
-	case e := <-watcher.Events:
-		gid = -1
-		if e.Op != fsnotify.Chmod {
-			gid = C.perfmon_addEventSet(evset.estr)
-		}
-	default:
-		gid = C.perfmon_addEventSet(evset.estr)
-	}
-	if gid < 0 {
-		return true, fmt.Errorf("failed to add events %s, error %d", evset.go_estr, gid)
-	} else {
-		evset.gid = gid
-	}
-
-	// Setup all performance monitoring counters of an eventSet
-	select {
-	case <-sigchan:
-		ret = -1
-	case e := <-watcher.Events:
-		if e.Op != fsnotify.Chmod {
-			ret = C.perfmon_setupCounters(gid)
-		}
-	default:
-		ret = C.perfmon_setupCounters(gid)
-	}
-	if ret != 0 {
-		return true, fmt.Errorf("failed to setup events '%s', error %d", evset.go_estr, ret)
-	}
-
-	// Start counters
-	select {
-	case <-sigchan:
-		ret = -1
-	case e := <-watcher.Events:
-		if e.Op != fsnotify.Chmod {
-			ret = C.perfmon_startCounters()
-		}
-	default:
-		ret = C.perfmon_startCounters()
-	}
-	if ret != 0 {
-		return true, fmt.Errorf("failed to start events '%s', error %d", evset.go_estr, ret)
-	}
-	select {
-	case <-sigchan:
-		ret = -1
-	case e := <-watcher.Events:
-		if e.Op != fsnotify.Chmod {
-			ret = C.perfmon_readCounters()
-		}
-	default:
-		ret = C.perfmon_readCounters()
-	}
-	if ret != 0 {
-		return true, fmt.Errorf("failed to read events '%s', error %d", evset.go_estr, ret)
-	}
-
-	// Wait
-	time.Sleep(interval)
-
-	// Read counters
-	select {
-	case <-sigchan:
-		ret = -1
-	case e := <-watcher.Events:
-		if e.Op != fsnotify.Chmod {
-			ret = C.perfmon_readCounters()
-		}
-	default:
-		ret = C.perfmon_readCounters()
-	}
-	if ret != 0 {
-		return true, fmt.Errorf("failed to read events '%s', error %d", evset.go_estr, ret)
-	}
-
-	// Store counters
-	for eidx, counter := range evset.eorder {
-		gctr := C.GoString(counter)
-		for _, tid := range m.cpu2tid {
-			res := C.perfmon_getLastResult(gid, C.int(eidx), C.int(tid))
-			fres := float64(res)
-			if m.config.InvalidToZero && (math.IsNaN(fres) || math.IsInf(fres, 0)) {
-				fres = 0.0
 			}
-			evset.results[tid][gctr] = fres
+			m.lock.Unlock()
+			return skip, err
 		}
-	}
+		ret = C.perfmon_startCounters()
-
+		if ret != 0 {
-	// Store time in seconds the event group was measured the last time
+			var err error = nil
-	for _, tid := range m.cpu2tid {
+			var skip bool = false
-		evset.results[tid]["time"] = float64(C.perfmon_getLastTimeOfGroup(gid))
+			if ret == -37 {
-	}
+				skip = true
-
+			} else {
-	// Stop counters
+				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
-	select {
+			}
-	case <-sigchan:
+			m.lock.Unlock()
-		ret = -1
+			return skip, err
-	case e := <-watcher.Events:
-		if e.Op != fsnotify.Chmod {
-			ret = C.perfmon_stopCounters()
 		}
-	default:
+		m.running = true
+		time.Sleep(interval)
+		m.running = false
 		ret = C.perfmon_stopCounters()
-	}
+		if ret != 0 {
-	if ret != 0 {
+			var err error = nil
-		return true, fmt.Errorf("failed to stop events '%s', error %d", evset.go_estr, ret)
+			var skip bool = false
-	}
+			if ret == -37 {
-
+				skip = true
-	// Deallocates all internal data that is used during performance monitoring
+			} else {
-	signal.Stop(sigchan)
+				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
-	select {
+			}
-	case e := <-watcher.Events:
+			m.lock.Unlock()
-		if e.Op != fsnotify.Chmod {
+			return skip, err
-			C.perfmon_finalize()
 		}
-	default:
-		C.perfmon_finalize()
 	}
+	m.lock.Unlock()
 	return false, nil
 }
 
@@ -540,8 +324,19 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
 func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
 	invClock := float64(1.0 / m.basefreq)
 
-	for _, tid := range m.cpu2tid {
+	// Go over events and get the results
-		evset.results[tid]["inverseClock"] = invClock
+	for eidx, counter := range evset.eorder {
+		gctr := C.GoString(counter)
+		for _, tid := range m.cpu2tid {
+			res := C.perfmon_getLastResult(evset.gid, C.int(eidx), C.int(tid))
+			fres := float64(res)
+			if m.config.InvalidToZero && (math.IsNaN(fres) || math.IsInf(fres, 0)) {
+				fres = 0.0
+			}
+			evset.results[tid][gctr] = fres
+			evset.results[tid]["time"] = interval.Seconds()
+			evset.results[tid]["inverseClock"] = invClock
+		}
 	}
 
 	// Go over the event set metrics, derive the value out of the event:counter values and send it
@@ -552,9 +347,6 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
 		if metric.Type == "socket" {
 			scopemap = m.sock2tid
 		}
-		// Send all metrics with same time stamp
-		// This function does only computiation, counter measurement is done before
-		now := time.Now()
 		for domain, tid := range scopemap {
 			if tid >= 0 && len(metric.Calc) > 0 {
 				value, err := agg.EvalFloat64Condition(metric.Calc, evset.results[tid])
@@ -567,151 +359,31 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
 				}
 				evset.metrics[tid][metric.Name] = value
 				// Now we have the result, send it with the proper tags
-				if !math.IsNaN(value) && metric.Publish {
+				if !math.IsNaN(value) {
-					fields := map[string]interface{}{"value": value}
+					if metric.Publish {
-					y, err :=
+						fields := map[string]interface{}{"value": value}
-						lp.New(
+						y, err := lp.New(metric.Name, map[string]string{"type": metric.Type}, m.meta, fields, time.Now())
-							metric.Name,
+						if err == nil {
-							map[string]string{
+							if metric.Type != "node" {
-								"type": metric.Type,
+								y.AddTag("type-id", fmt.Sprintf("%d", domain))
-							},
+							}
-							m.meta,
+							if len(metric.Unit) > 0 {
-							fields,
+								y.AddMeta("unit", metric.Unit)
-							now,
+							}
-						)
+							output <- y
-					if err == nil {
-						if metric.Type != "node" {
-							y.AddTag("type-id", fmt.Sprintf("%d", domain))
 						}
-						if len(metric.Unit) > 0 {
-							y.AddMeta("unit", metric.Unit)
-						}
-						output <- y
 					}
 				}
 			}
 		}
-
-		// Send per core aggregated values
-		if metric.SendCoreTotalVal {
-			totalCoreValues := make(map[int]float64)
-			for _, tid := range scopemap {
-				if tid >= 0 && len(metric.Calc) > 0 {
-					coreID := m.tid2core[tid]
-					value := evset.metrics[tid][metric.Name]
-					if !math.IsNaN(value) && metric.Publish {
-						totalCoreValues[coreID] += value
-					}
-				}
-			}
-
-			for coreID, value := range totalCoreValues {
-				y, err :=
-					lp.New(
-						metric.Name,
-						map[string]string{
-							"type":    "core",
-							"type-id": fmt.Sprintf("%d", coreID),
-						},
-						m.meta,
-						map[string]interface{}{
-							"value": value,
-						},
-						now,
-					)
-				if err != nil {
-					continue
-				}
-				if len(metric.Unit) > 0 {
-					y.AddMeta("unit", metric.Unit)
-				}
-				output <- y
-			}
-		}
-
-		// Send per socket aggregated values
-		if metric.SendSocketTotalVal {
-			totalSocketValues := make(map[int]float64)
-			for _, tid := range scopemap {
-				if tid >= 0 && len(metric.Calc) > 0 {
-					socketID := m.tid2socket[tid]
-					value := evset.metrics[tid][metric.Name]
-					if !math.IsNaN(value) && metric.Publish {
-						totalSocketValues[socketID] += value
-					}
-				}
-			}
-
-			for socketID, value := range totalSocketValues {
-				y, err :=
-					lp.New(
-						metric.Name,
-						map[string]string{
-							"type":    "socket",
-							"type-id": fmt.Sprintf("%d", socketID),
-						},
-						m.meta,
-						map[string]interface{}{
-							"value": value,
-						},
-						now,
-					)
-				if err != nil {
-					continue
-				}
-				if len(metric.Unit) > 0 {
-					y.AddMeta("unit", metric.Unit)
-				}
-				output <- y
-			}
-		}
-
-		// Send per node aggregated value
-		if metric.SendNodeTotalVal {
-			var totalNodeValue float64 = 0.0
-			for _, tid := range scopemap {
-				if tid >= 0 && len(metric.Calc) > 0 {
-					value := evset.metrics[tid][metric.Name]
-					if !math.IsNaN(value) && metric.Publish {
-						totalNodeValue += value
-					}
-				}
-			}
-
-			y, err :=
-				lp.New(
-					metric.Name,
-					map[string]string{
-						"type": "node",
-					},
-					m.meta,
-					map[string]interface{}{
-						"value": totalNodeValue,
-					},
-					now,
-				)
-			if err != nil {
-				continue
-			}
-			if len(metric.Unit) > 0 {
-				y.AddMeta("unit", metric.Unit)
-			}
-			output <- y
-		}
 	}
 
 	return nil
 }
 
 // Go over the global metrics, derive the value out of the event sets' metric values and send it
-func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
+func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan lp.CCMetric) error {
-	// Send all metrics with same time stamp
-	// This function does only computiation, counter measurement is done before
-	now := time.Now()
-
 	for _, metric := range m.config.Metrics {
-		// The metric scope is determined in the Init() function
-		// Get the map scope-id -> tids
 		scopemap := m.cpu2tid
 		if metric.Type == "socket" {
 			scopemap = m.sock2tid
@@ -719,8 +391,8 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
 		for domain, tid := range scopemap {
 			if tid >= 0 {
 				// Here we generate parameter list
-				params := make(map[string]float64)
+				params := make(map[string]interface{})
-				for _, evset := range groups {
+				for _, evset := range m.likwidGroups {
 					for mname, mres := range evset.metrics[tid] {
 						params[mname] = mres
 					}
@@ -734,21 +406,13 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
 				if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {
 					value = 0.0
 				}
+				m.gmresults[tid][metric.Name] = value
 				// Now we have the result, send it with the proper tags
 				if !math.IsNaN(value) {
 					if metric.Publish {
-						y, err :=
+						tags := map[string]string{"type": metric.Type}
-							lp.New(
+						fields := map[string]interface{}{"value": value}
-								metric.Name,
+						y, err := lp.New(metric.Name, tags, m.meta, fields, time.Now())
-								map[string]string{
-									"type": metric.Type,
-								},
-								m.meta,
-								map[string]interface{}{
-									"value": value,
-								},
-								now,
-							)
 						if err == nil {
 							if metric.Type != "node" {
 								y.AddTag("type-id", fmt.Sprintf("%d", domain))
@@ -766,50 +430,163 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
 	return nil
 }
 
-func (m *LikwidCollector) ReadThread(interval time.Duration, output chan lp.CCMetric) {
+func (m *LikwidCollector) LateInit() error {
-	var err error = nil
+	var ret C.int
-	groups := make([]LikwidEventsetConfig, 0)
+	if m.initialized {
-
+		return nil
-	for evidx, evset := range m.config.Eventsets {
-		e := genLikwidEventSet(evset)
-		e.internal = evidx
-		skip := false
-		if !skip {
-			// measure event set 'i' for 'interval' seconds
-			skip, err = m.takeMeasurement(evidx, e, interval)
-			if err != nil {
-				cclog.ComponentError(m.name, err.Error())
-				return
-			}
-		}
-
-		if !skip {
-			// read measurements and derive event set metrics
-			m.calcEventsetMetrics(e, interval, output)
-		}
-		groups = append(groups, e)
 	}
-	// calculate global metrics
+	switch m.config.AccessMode {
-	m.calcGlobalMetrics(groups, interval, output)
+	case "direct":
+		C.HPMmode(0)
+	case "accessdaemon":
+		if len(m.config.DaemonPath) > 0 {
+			p := os.Getenv("PATH")
+			os.Setenv("PATH", m.config.DaemonPath+":"+p)
+		}
+		C.HPMmode(1)
+	}
+	cclog.ComponentDebug(m.name, "initialize LIKWID topology")
+	ret = C.topology_init()
+	if ret != 0 {
+		err := errors.New("failed to initialize LIKWID topology")
+		cclog.ComponentError(m.name, err.Error())
+		return err
+	}
+
+	m.sock2tid = make(map[int]int)
+	tmp := make([]C.int, 1)
+	for _, sid := range topo.SocketList() {
+		cstr := C.CString(fmt.Sprintf("S%d:0", sid))
+		ret = C.cpustr_to_cpulist(cstr, &tmp[0], 1)
+		if ret > 0 {
+			m.sock2tid[sid] = m.cpu2tid[int(tmp[0])]
+		}
+		C.free(unsafe.Pointer(cstr))
+	}
+
+	m.basefreq = getBaseFreq()
+	cclog.ComponentDebug(m.name, "BaseFreq", m.basefreq)
+
+	cclog.ComponentDebug(m.name, "initialize LIKWID perfmon module")
+	ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
+	if ret != 0 {
+		var err error = nil
+		C.topology_finalize()
+		if ret != -22 {
+			err = errors.New("failed to initialize LIKWID perfmon")
+			cclog.ComponentError(m.name, err.Error())
+		} else {
+			err = errors.New("access to LIKWID perfmon locked")
+		}
+		return err
+	}
+
+	// While adding the events, we test the metrics whether they can be computed at all
+	for i, evset := range m.config.Eventsets {
+		var gid C.int
+		if len(evset.Events) > 0 {
+			skip := false
+			likwidGroup := genLikwidEventSet(evset)
+			for _, g := range m.likwidGroups {
+				if likwidGroup.go_estr == g.go_estr {
+					skip = true
+					break
+				}
+			}
+			if skip {
+				continue
+			}
+			// Now we add the list of events to likwid
+			gid = C.perfmon_addEventSet(likwidGroup.estr)
+			if gid >= 0 {
+				likwidGroup.gid = gid
+				likwidGroup.internal = i
+				m.likwidGroups[gid] = likwidGroup
+			}
+		} else {
+			cclog.ComponentError(m.name, "Invalid Likwid eventset config, no events given")
+			continue
+		}
+
+	}
+
+	// If no event set could be added, shut down LikwidCollector
+	if len(m.likwidGroups) == 0 {
+		C.perfmon_finalize()
+		C.topology_finalize()
+		err := errors.New("no LIKWID performance group initialized")
+		cclog.ComponentError(m.name, err.Error())
+		return err
+	}
+	sigchan := make(chan os.Signal, 1)
+	signal.Notify(sigchan, syscall.SIGCHLD)
+	signal.Notify(sigchan, os.Interrupt)
+	go func() {
+		<-sigchan
+
+		signal.Stop(sigchan)
+		m.initialized = false
+	}()
+	m.initialized = true
+	return nil
 }
 
 // main read function taking multiple measurement rounds, each 'interval' seconds long
 func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	var skip bool = false
+	var err error
 	if !m.init {
 		return
 	}
-	m.measureThread.Call(func() {
+
-		m.ReadThread(interval, output)
+	if !m.initialized {
-	})
+		m.lock.Lock()
+		err = m.LateInit()
+		if err != nil {
+			m.lock.Unlock()
+			return
+		}
+		m.initialized = true
+		m.lock.Unlock()
+	}
+
+	if m.initialized && !skip {
+		for _, evset := range m.likwidGroups {
+			if !skip {
+				// measure event set 'i' for 'interval' seconds
+				skip, err = m.takeMeasurement(evset, interval)
+				if err != nil {
+					cclog.ComponentError(m.name, err.Error())
+					return
+				}
+			}
+
+			if !skip {
+				// read measurements and derive event set metrics
+				m.calcEventsetMetrics(evset, interval, output)
+			}
+		}
+		if !skip {
+			// use the event set metrics to derive the global metrics
+			m.calcGlobalMetrics(interval, output)
+		}
+	}
 }
 
 func (m *LikwidCollector) Close() {
 	if m.init {
 		m.init = false
+		cclog.ComponentDebug(m.name, "Closing ...")
 		m.lock.Lock()
-		m.measureThread.Terminate()
+		if m.initialized {
-		m.initialized = false
+			cclog.ComponentDebug(m.name, "Finalize LIKWID perfmon module")
+			C.perfmon_finalize()
+			m.initialized = false
+		}
 		m.lock.Unlock()
+		cclog.ComponentDebug(m.name, "Finalize LIKWID topology module")
 		C.topology_finalize()
+
+		cclog.ComponentDebug(m.name, "Closing done")
 	}
 }

collectors/likwidMetric.md

@@ -7,10 +7,6 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
   "likwid": {
     "force_overwrite" : false,
     "invalid_to_zero" : false,
-    "liblikwid_path" : "/path/to/liblikwid.so",
-    "accessdaemon_path" : "/folder/that/contains/likwid-accessD",
-    "access_mode" : "direct or accessdaemon or perf_event",
-    "lockfile_path" : "/var/run/likwid.lock",
     "eventsets": [
       {
         "events" : {
@@ -23,7 +19,7 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
             "calc": "COUNTER0 + COUNTER1",
             "publish": false,
             "unit": "myunit",
-            "type": "hwthread"
+            "type": "cpu"
           }
         ]
       }
@@ -34,46 +30,41 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
         "calc": "sum_01",
         "publish": true,
         "unit": "myunit",
-        "type": "hwthread"
+        "type": "cpu"
       }
     ]
   }
 ```
 
 The `likwid` configuration consists of two parts, the `eventsets` and `globalmetrics`:
-
 - An event set list itself has two parts, the `events` and a set of derivable `metrics`. Each of the `events` is a `counter:event` pair in LIKWID's syntax. The `metrics` are a list of formulas to derive the metric value from the measurements of the `events`' values. Each metric has a name, the formula, a type and a publish flag. There is an optional `unit` field. Counter names can be used like variables in the formulas, so `PMC0+PMC1` sums the measurements for the both events configured in the counters `PMC0` and `PMC1`. You can optionally use `time` for the measurement time and `inverseClock` for `1.0/baseCpuFrequency`. The type tells the LikwidCollector whether it is a metric for each hardware thread (`cpu`) or each CPU socket (`socket`). You may specify a unit for the metric with `unit`. The last one is the publishing flag. It tells the LikwidCollector whether a metric should be sent to the router or is only used internally to compute a global metric.
-- The `globalmetrics` are metrics which require data from multiple event set measurements to be derived. The inputs are the metrics in the event sets. Similar to the metrics in the event sets, the global metrics are defined by a name, a formula, a type and a publish flag. See event set metrics for details. The only difference is that there is no access to the raw event measurements anymore but only to the metrics. Also `time` and `inverseClock` cannot be used anymore. So, the idea is to derive a metric in the `eventsets` section and reuse it in the `globalmetrics` part. If you need a metric only for deriving the global metrics, disable forwarding of the event set metrics (`"publish": false`). **Be aware** that the combination might be misleading because the "behavior" of a metric changes over time and the multiple measurements might count different computing phases. Similar to the metrics in the eventset, you can specify a metric unit with the `unit` field.
+- The `globalmetrics` are metrics which require data from multiple event set measurements to be derived. The inputs are the metrics in the event sets. Similar to the metrics in the event sets, the global metrics are defined by a name, a formula, a scope and a publish flag. See event set metrics for details. The only difference is that there is no access to the raw event measurements anymore but only to the metrics. Also `time` and `inverseClock` cannot be used anymore. So, the idea is to derive a metric in the `eventsets` section and reuse it in the `globalmetrics` part. If you need a metric only for deriving the global metrics, disable forwarding of the event set metrics (`"publish": false`). **Be aware** that the combination might be misleading because the "behavior" of a metric changes over time and the multiple measurements might count different computing phases. Similar to the metrics in the eventset, you can specify a metric unit with the `unit` field.
 
 Additional options:
-
 - `force_overwrite`: Same as setting `LIKWID_FORCE=1`. In case counters are already in-use, LIKWID overwrites their configuration to do its measurements
 - `invalid_to_zero`: In some cases, the calculations result in `NaN` or `Inf`. With this option, all `NaN` and `Inf` values are replaces with `0.0`. See below in [seperate section](./likwidMetric.md#invalid_to_zero-option)
 - `access_mode`: Specify LIKWID access mode: `direct` for direct register access as root user or `accessdaemon`. The access mode `perf_event` is current untested.
 - `accessdaemon_path`: Folder of the accessDaemon `likwid-accessD` (like `/usr/local/sbin`)
 - `liblikwid_path`: Location of `liblikwid.so` including file name like `/usr/local/lib/liblikwid.so`
-- `lockfile_path`: Location of LIKWID's lock file if multiple tools should access the hardware counters. Default `/var/run/likwid.lock`
 
-### Available metric types
+### Available metric scopes
 
 Hardware performance counters are scattered all over the system nowadays. A counter coveres a specific part of the system. While there are hardware thread specific counter for CPU cycles, instructions and so on, some others are specific for a whole CPU socket/package. To address that, the LikwidCollector provides the specification of a `type` for each metric.
 
-- `hwthread` : One metric per CPU hardware thread with the tags `"type" : "hwthread"` and `"type-id" : "$hwthread_id"`
+- `cpu` : One metric per CPU hardware thread with the tags `"type" : "cpu"` and `"type-id" : "$cpu_id"`
 - `socket` : One metric per CPU socket/package with the tags `"type" : "socket"` and `"type-id" : "$socket_id"`
 
-**Note:** You cannot specify `socket` type for a metric that is measured at `hwthread` type, so some kind of expert knowledge or lookup work in the [Likwid Wiki](https://github.com/RRZE-HPC/likwid/wiki) is required. Get the type of each counter from the *Architecture* pages and as soon as one counter in a metric is socket-specific, the whole metric is socket-specific.
+**Note:** You should not specify the `socket` type for a metric that is measured at `cpu` scope and vice versa, so some kind of expert knowledge or lookup work in the [Likwid Wiki](https://github.com/RRZE-HPC/likwid/wiki) is required. Get the scope of each counter from the *Architecture* pages and as soon as one counter in a metric is socket-specific, the whole metric is socket-specific.
 
 As a guideline:
-
+- All counters `FIXCx`, `PMCy` and `TMAz` have the scope `cpu`
-- All counters `FIXCx`, `PMCy` and `TMAz` have the type `hwthread`
+- All counters names containing `BOX` have the scope `socket`
-- All counters names containing `BOX` have the type `socket`
+- All `PWRx` counters have scope `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `cpu` scope (AMD Zen)
-- All `PWRx` counters have type `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `hwthread` type
+- All `DFCx` counters have scope `socket`
-- All `DFCx` counters have type `socket`
 
 ### Help with the configuration
 
 The configuration for the `likwid` collector is quite complicated. Most users don't use LIKWID with the event:counter notation but rely on the performance groups defined by the LIKWID team for each architecture. In order to help with the `likwid` collector configuration, we included a script `scripts/likwid_perfgroup_to_cc_config.py` that creates the configuration of an `eventset` from a performance group (using a LIKWID installation in `$PATH`):
-
 ```
 $ likwid-perfctr -i
 [...]
@@ -99,7 +90,7 @@ $ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
       "name": "Runtime (RDTSC) [s]",
       "publish": true,
       "unit": "seconds"
-      "type": "hwthread"
+      "scope": "cpu"
     },
     {
       "..." : "..."
@@ -115,28 +106,20 @@ You can copy this JSON and add it to the `eventsets` list. If you specify multip
 LIKWID checks the file `/var/run/likwid.lock` before performing any interfering operations. Who is allowed to access the counters is determined by the owner of the file. If it does not exist, it is created for the current user. So, if you want to temporarly allow counter access to a user (e.g. in a job):
 
 Before (SLURM prolog, ...)
-
+```
-```bash
+$ chown $JOBUSER /var/run/likwid.lock
-chown $JOBUSER /var/run/likwid.lock
 ```
 
 After (SLURM epilog, ...)
-
+```
-```bash
+$ chown $CCUSER /var/run/likwid.lock
-chown $CCUSER /var/run/likwid.lock
 ```
 
 ### `invalid_to_zero` option
-
 In some cases LIKWID returns `0.0` for some events that are further used in processing and maybe used as divisor in a calculation. After evaluation of a metric, the result might be `NaN` or `+-Inf`. These resulting metrics are commonly not created and forwarded to the router because the [InfluxDB line protocol](https://docs.influxdata.com/influxdb/cloud/reference/syntax/line-protocol/#float) does not support these special floating-point values. If you want to have them sent, this option forces these metric values to be `0.0` instead.
 
 One might think this does not happen often but often used metrics in the world of performance engineering like Instructions-per-Cycle (IPC) or more frequently the actual CPU clock are derived with events like `CPU_CLK_UNHALTED_CORE` (Intel) which do not increment in halted state (as the name implies). In there are different power management systems in a chip which can cause a hardware thread to go in such a state. Moreover, if no cycles are executed by the core, also many other events are not incremented as well (like `INSTR_RETIRED_ANY` for retired instructions and part of IPC).
 
-### `send_*_total values` option
-
-- `send_core_total_values`: Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per CPU core.
-- `send_socket_total_values` Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per CPU socket.
-- `send_node_total_values` Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per node.
 
 ### Example configuration
 
@@ -164,20 +147,20 @@ One might think this does not happen often but often used metrics in the world o
           {
             "name": "ipc",
             "calc": "PMC0/PMC1",
-            "type": "hwthread",
+            "type": "cpu",
             "publish": true
           },
           {
             "name": "flops_any",
             "calc": "0.000001*PMC2/time",
             "unit": "MFlops/s",
-            "type": "hwthread",
+            "type": "cpu",
             "publish": true
           },
           {
             "name": "clock",
             "calc": "0.000001*(FIXC1/FIXC2)/inverseClock",
-            "type": "hwthread",
+            "type": "cpu",
             "unit": "MHz",
             "publish": true
           },
@@ -236,34 +219,3 @@ One might think this does not happen often but often used metrics in the world o
   }
 ```
 
-### How to get the eventsets and metrics from LIKWID
-
-The `likwid` collector reads hardware performance counters at a **hwthread** and **socket** level. The configuration looks quite complicated but it is basically copy&paste from [LIKWID's performance groups](https://github.com/RRZE-HPC/likwid/tree/master/groups). The collector made multiple iterations and tried to use the performance groups but it lacked flexibility. The current way of configuration provides most flexibility.
-
-The logic is as following: There are multiple eventsets, each consisting of a list of counters+events and a list of metrics. If you compare a common performance group with the example setting above, there is not much difference:
-
-```
-EVENTSET                         ->   "events": {
-FIXC1 ACTUAL_CPU_CLOCK           ->     "FIXC1": "ACTUAL_CPU_CLOCK",
-FIXC2 MAX_CPU_CLOCK              ->     "FIXC2": "MAX_CPU_CLOCK",
-PMC0  RETIRED_INSTRUCTIONS       ->     "PMC0" : "RETIRED_INSTRUCTIONS",
-PMC1  CPU_CLOCKS_UNHALTED        ->     "PMC1" : "CPU_CLOCKS_UNHALTED",
-PMC2  RETIRED_SSE_AVX_FLOPS_ALL  ->     "PMC2": "RETIRED_SSE_AVX_FLOPS_ALL",
-PMC3  MERGE                      ->     "PMC3": "MERGE",
-                                 ->   }
-```
-
-The metrics are following the same procedure:
-
-```
-METRICS                          ->   "metrics": [
-IPC   PMC0/PMC1                  ->     {
-                                 ->       "name" : "IPC",
-                                 ->       "calc" : "PMC0/PMC1",
-                                 ->       "type": "hwthread",
-                                 ->       "publish": true
-                                 ->     }
-                                 ->   ]
-```
-
-The script `scripts/likwid_perfgroup_to_cc_config.py` might help you.

collectors/likwidenergyMetric.go

@@ -1,281 +0,0 @@
-package collectors
-
-/*
-#cgo CFLAGS: -I./likwid
-#cgo LDFLAGS: -Wl,--unresolved-symbols=ignore-in-object-files
-#include <stdlib.h>
-#include <likwid.h>
-*/
-import "C"
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
-	"github.com/NVIDIA/go-nvml/pkg/dl"
-)
-
-const (
-	LIKWIDENERGY_LIB_NAME       = "liblikwid.so"
-	LIKWIDENERGY_LIB_DL_FLAGS   = dl.RTLD_LAZY | dl.RTLD_GLOBAL
-	LIKWIDENERGY_DEF_ACCESSMODE = "direct"
-	LIKWIDENERGY_DEF_LOCKFILE   = "/var/run/likwid.lock"
-)
-
-// These are the fields we read from the JSON configuration
-type LikwidEnergyCollectorConfig struct {
-	AccessMode   string `json:"access_mode,omitempty"`
-	DaemonPath   string `json:"accessdaemon_path,omitempty"`
-	LibraryPath  string `json:"liblikwid_path,omitempty"`
-	LockfilePath string `json:"lockfile_path,omitempty"`
-	SendDiff     bool   `json:"send_difference,omitempty"`
-	SendAbs      bool   `json:"send_absolute,omitempty"`
-}
-
-type LikwidEnergyDomainEntry struct {
-	readcpu int
-	value   uint32
-	total   uint64
-	tags    map[string]string
-}
-
-type LikwidEnergyDomain struct {
-	values      map[int]LikwidEnergyDomainEntry
-	granularity string
-	metricname  string
-	domaintype  int
-	energyUnit  float64
-}
-
-// This contains all variables we need during execution and the variables
-// defined by metricCollector (name, init, ...)
-type LikwidEnergyCollector struct {
-	metricCollector
-	config  LikwidEnergyCollectorConfig // the configuration structure
-	meta    map[string]string           // default meta information
-	tags    map[string]string           // default tags
-	domains map[int]LikwidEnergyDomain
-}
-
-// Init initializes the sample collector
-// Called once by the collector manager
-// All tags, meta data tags and metrics that do not change over the runtime should be set here
-func (m *LikwidEnergyCollector) Init(config json.RawMessage) error {
-	var err error = nil
-	// Always set the name early in Init() to use it in cclog.Component* functions
-	m.name = "LikwidEnergyCollector"
-	// This is for later use, also call it early
-	m.setup()
-	// Tell whether the collector should be run in parallel with others (reading files, ...)
-	// or it should be run serially, mostly for collectors actually doing measurements
-	// because they should not measure the execution of the other collectors
-	m.parallel = true
-	// Define meta information sent with each metric
-	// (Can also be dynamic or this is the basic set with extension through AddMeta())
-	m.meta = map[string]string{"source": m.name, "group": "LIKWID", "unit": "Joules"}
-	// Define tags sent with each metric
-	// The 'type' tag is always needed, it defines the granularity of the metric
-	// node -> whole system
-	// socket -> CPU socket (requires socket ID as 'type-id' tag)
-	// die -> CPU die (requires CPU die ID as 'type-id' tag)
-	// memoryDomain -> NUMA domain (requires NUMA domain ID as 'type-id' tag)
-	// llc -> Last level cache (requires last level cache ID as 'type-id' tag)
-	// core -> single CPU core that may consist of multiple hardware threads (SMT) (requires core ID as 'type-id' tag)
-	// hwthtread -> single CPU hardware thread (requires hardware thread ID as 'type-id' tag)
-	// accelerator -> A accelerator device like GPU or FPGA (requires an accelerator ID as 'type-id' tag)
-	m.tags = map[string]string{}
-	// Read in the JSON configuration
-	m.config.AccessMode = LIKWID_DEF_ACCESSMODE
-	m.config.LibraryPath = LIKWID_LIB_NAME
-	m.config.LockfilePath = LIKWID_DEF_LOCKFILE
-	m.config.SendAbs = true
-	m.config.SendDiff = true
-	if len(config) > 0 {
-		err = json.Unmarshal(config, &m.config)
-		if err != nil {
-			cclog.ComponentError(m.name, "Error reading config:", err.Error())
-			return err
-		}
-	}
-	cclog.ComponentDebug(m.name, "Opening ", m.config.LibraryPath)
-	lib := dl.New(m.config.LibraryPath, LIKWID_LIB_DL_FLAGS)
-	if lib == nil {
-		return fmt.Errorf("error instantiating DynamicLibrary for %s", m.config.LibraryPath)
-	}
-	err = lib.Open()
-	if err != nil {
-		return fmt.Errorf("error opening %s: %v", m.config.LibraryPath, err)
-	}
-	cclog.ComponentDebug(m.name, "Init topology ", m.config.AccessMode)
-	ret := C.topology_init()
-	if ret != 0 {
-		return fmt.Errorf("error initializing topology: %d", ret)
-	}
-	cclog.ComponentDebug(m.name, "Setting accessmode ", m.config.AccessMode)
-	switch m.config.AccessMode {
-	case "direct":
-		C.HPMmode(0)
-	case "accessdaemon":
-		if len(m.config.DaemonPath) > 0 {
-			p := os.Getenv("PATH")
-			os.Setenv("PATH", m.config.DaemonPath+":"+p)
-		}
-		C.HPMmode(1)
-		retCode := C.HPMinit()
-		if retCode != 0 {
-			err := fmt.Errorf("C.HPMinit() failed with return code %v", retCode)
-			cclog.ComponentError(m.name, err.Error())
-		}
-	}
-	initCpus := make([]int, 0)
-	ret = C.HPMaddThread(0)
-	if ret != 0 {
-		return fmt.Errorf("error initializing access: %d", ret)
-	}
-	initCpus = append(initCpus, 0)
-
-	cinfo := C.get_cpuInfo()
-	domainnames := make(map[int]string)
-	if cinfo.isIntel == C.int(1) {
-		domainnames[0] = "pkg"
-		domainnames[1] = "pp0"
-		domainnames[2] = "pp1"
-		domainnames[3] = "dram"
-		domainnames[4] = "platform"
-	} else {
-		switch cinfo.family {
-		case 0x17:
-			domainnames[0] = "core"
-			domainnames[1] = "pkg"
-		case 0x19:
-			switch cinfo.model {
-			case 0x01, 0x21, 0x50:
-				domainnames[0] = "core"
-				domainnames[1] = "pkg"
-			case 0x61, 0x11:
-				domainnames[0] = "core"
-				domainnames[1] = "l3"
-			}
-		}
-	}
-
-	// Set up everything that the collector requires during the Read() execution
-	// Check files required, test execution of some commands, create data structure
-	// for all topological entities (sockets, NUMA domains, ...)
-	// Return some useful error message in case of any failures
-	cclog.ComponentDebug(m.name, "Initializing Power module")
-	ret = C.power_init(0)
-	if ret == C.int(0) {
-		cclog.ComponentPrint(m.name, "No RAPL support")
-	}
-	m.domains = make(map[int]LikwidEnergyDomain)
-	Pinfo := C.get_powerInfo()
-	for i := 0; i < int(Pinfo.numDomains); i++ {
-		d := Pinfo.domains[C.int(i)]
-		name := domainnames[int(d._type)]
-		domain := LikwidEnergyDomain{
-			values:      make(map[int]LikwidEnergyDomainEntry),
-			metricname:  fmt.Sprintf("likwidenergy_%s", strings.ToLower(name)),
-			granularity: "socket",
-			domaintype:  int(d._type),
-			energyUnit:  float64(C.power_getEnergyUnit(C.int(d._type))),
-		}
-		if name == "core" {
-			domain.granularity = "core"
-		}
-
-		for _, c := range topo.GetTypeList(domain.granularity) {
-			clist := topo.GetSocketHwthreads(c)
-			if len(clist) > 0 {
-				var cur C.PowerData
-				if _, ok := intArrayContains(initCpus, clist[0]); !ok {
-					initCpus = append(initCpus, clist[0])
-					C.HPMaddThread(C.int(clist[0]))
-				}
-				cclog.ComponentDebug(m.name, "Reading current value on CPU ", clist[0], " for ", domain.metricname, "on", domain.granularity, c)
-				ret = C.power_start(&cur, C.int(clist[0]), C.PowerType(domain.domaintype))
-				cclog.ComponentDebug(m.name, "Reading ", uint64(cur.before))
-				if ret == 0 {
-					domain.values[c] = LikwidEnergyDomainEntry{
-						readcpu: clist[0],
-						value:   uint32(cur.before),
-						total:   uint64(cur.before),
-						tags: map[string]string{
-							"type":    domain.granularity,
-							"type-id": fmt.Sprintf("%d", c),
-						},
-					}
-
-				}
-			}
-		}
-		cclog.ComponentDebug(m.name, "Adding domain ", domain.metricname, " with granularity ", domain.granularity)
-		m.domains[domain.domaintype] = domain
-	}
-
-	// Set this flag only if everything is initialized properly, all required files exist, ...
-	m.init = true
-	return err
-}
-
-// Read collects all metrics belonging to the sample collector
-// and sends them through the output channel to the collector manager
-func (m *LikwidEnergyCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	// Create a sample metric
-	timestamp := time.Now()
-
-	for dt, domain := range m.domains {
-		for i, entry := range domain.values {
-			var cur C.PowerData
-			ret := C.power_start(&cur, C.int(entry.readcpu), C.PowerType(dt))
-			if ret == 0 {
-				now := uint32(cur.before)
-				diff := now - entry.value
-				if now < entry.value {
-					diff = (^uint32(0)) - entry.value
-					diff += now
-				}
-				if m.config.SendDiff {
-					y, err := lp.New(domain.metricname, entry.tags, m.meta, map[string]interface{}{"value": float64(diff) * domain.energyUnit}, timestamp)
-					if err == nil {
-						for k, v := range m.tags {
-							y.AddTag(k, v)
-						}
-						// Send it to output channel
-						output <- y
-					}
-				}
-				if m.config.SendAbs {
-					total := float64(entry.total + uint64(diff))
-
-					y, err := lp.New(fmt.Sprintf("%s_abs", domain.metricname), entry.tags, m.meta, map[string]interface{}{"value": total * domain.energyUnit}, timestamp)
-					if err == nil {
-						for k, v := range m.tags {
-							y.AddTag(k, v)
-						}
-						// Send it to output channel
-						output <- y
-					}
-				}
-				entry.value = uint32(cur.before)
-				entry.total += uint64(diff)
-				domain.values[i] = entry
-			}
-		}
-	}
-
-}
-
-// Close metric collector: close network connection, close files, close libraries, ...
-// Called once by the collector manager
-func (m *LikwidEnergyCollector) Close() {
-	C.power_finalize()
-	C.topology_finalize()
-	// Unset flag
-	m.init = false
-}

collectors/likwidenergyMetric.md

@@ -1,20 +0,0 @@
-## `likwidenergy` collector
-
-In contrast to the more general [`likwid` collector](./likwidMetric.md), this collector just reads the RAPL counters to provide energy metrics. In contrast to the `likwid` collector, this collector keeps the energy counters running the whole time and not just of a measurement interval. It covers all RAPL domains (`PKG`, `DRAM`, `PP0`, `PP1`, ...). Depending whether the domain is per socket, per L3 segment or per core, metrics are read and send.
-
-```json
-{
-    "likwidenergy" : {
-        "liblikwid_path" : "/path/to/liblikwid.so",
-        "accessdaemon_path" : "/folder/that/contains/likwid-accessD",
-        "access_mode" : "direct or accessdaemon",
-        "send_difference": true,
-        "send_absolute": true
-    }
-}
-```
-
-The first three entries (`liblikwid_path`, `accessdaemon_path` and `access_mode`) are required to set up the access to the RAPL counters. The `access_mode` = `perf_event` is not supported at the moment.
-
-With `send_differences` the difference to the last measurement is provided to the system. With `send_absolute`, the absolute value since start of the system is submitted as metric. It reads the counter at initialization and then updates the value after each measurement.
-

collectors/loadavgMetric.go

@@ -3,13 +3,13 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"os"
+	"io/ioutil"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 //
@@ -36,7 +36,6 @@ type LoadavgCollector struct {
 
 func (m *LoadavgCollector) Init(config json.RawMessage) error {
 	m.name = "LoadavgCollector"
-	m.parallel = true
 	m.setup()
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
@@ -72,7 +71,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	if !m.init {
 		return
 	}
-	buffer, err := os.ReadFile(LOADAVGFILE)
+	buffer, err := ioutil.ReadFile(LOADAVGFILE)
 	if err != nil {
 		if err != nil {
 			cclog.ComponentError(

collectors/lustreMetric.go

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 const LUSTRE_SYSFS = `/sys/fs/lustre`
@@ -101,7 +101,7 @@ func getMetricData(lines []string, prefix string, offset int) (int64, error) {
 // 	llitedir := filepath.Join(LUSTRE_SYSFS, "llite")
 // 	devdir := filepath.Join(llitedir, device)
 // 	statsfile := filepath.Join(devdir, "stats")
-// 	buffer, err := os.ReadFile(statsfile)
+// 	buffer, err := ioutil.ReadFile(statsfile)
 // 	if err != nil {
 // 		return make([]string, 0)
 // 	}
@@ -288,7 +288,6 @@ var LustreDeriveMetrics = []LustreMetricDefinition{
 func (m *LustreCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "LustreCollector"
-	m.parallel = true
 	if len(config) > 0 {
 		err = json.Unmarshal(config, &m.config)
 		if err != nil {

collectors/memstatMetric.go

@@ -12,8 +12,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 const MEMSTATFILE = "/proc/meminfo"
@@ -68,8 +68,7 @@ func getStats(filename string) map[string]MemstatStats {
 		} else if len(linefields) == 5 {
 			v, err := strconv.ParseFloat(linefields[3], 64)
 			if err == nil {
-				cclog.ComponentDebug("getStats", strings.Trim(linefields[2], ":"), v, linefields[4])
+				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
-				stats[strings.Trim(linefields[2], ":")] = MemstatStats{
 					value: v,
 					unit:  linefields[4],
 				}
@@ -82,7 +81,6 @@ func getStats(filename string) map[string]MemstatStats {
 func (m *MemstatCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "MemstatCollector"
-	m.parallel = true
 	m.config.NodeStats = true
 	m.config.NumaStats = false
 	if len(config) > 0 {
@@ -188,20 +186,16 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 			unit := ""
 			if totalVal, total := stats["MemTotal"]; total {
 				if freeVal, free := stats["MemFree"]; free {
-					memUsed = totalVal.value - freeVal.value
-					if len(totalVal.unit) > 0 {
-						unit = totalVal.unit
-					} else if len(freeVal.unit) > 0 {
-						unit = freeVal.unit
-					}
 					if bufVal, buffers := stats["Buffers"]; buffers {
-						memUsed -= bufVal.value
-						if len(bufVal.unit) > 0 && len(unit) == 0 {
-							unit = bufVal.unit
-						}
 						if cacheVal, cached := stats["Cached"]; cached {
-							memUsed -= cacheVal.value
+							memUsed = totalVal.value - (freeVal.value + bufVal.value + cacheVal.value)
-							if len(cacheVal.unit) > 0 && len(unit) == 0 {
+							if len(totalVal.unit) > 0 {
+								unit = totalVal.unit
+							} else if len(freeVal.unit) > 0 {
+								unit = freeVal.unit
+							} else if len(bufVal.unit) > 0 {
+								unit = bufVal.unit
+							} else if len(cacheVal.unit) > 0 {
 								unit = cacheVal.unit
 							}
 						}

collectors/metricCollector.go

@@ -3,25 +3,27 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
+	"io/ioutil"
+	"log"
+	"strconv"
+	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 type MetricCollector interface {
-	Name() string                      // Name of the metric collector
+	Name() string                                         // Name of the metric collector
-	Init(config json.RawMessage) error // Initialize metric collector
+	Init(config json.RawMessage) error                    // Initialize metric collector
-	Initialized() bool                 // Is metric collector initialized?
+	Initialized() bool                                    // Is metric collector initialized?
-	Parallel() bool
 	Read(duration time.Duration, output chan lp.CCMetric) // Read metrics from metric collector
 	Close()                                               // Close / finish metric collector
 }
 
 type metricCollector struct {
-	name     string            // name of the metric
+	name string            // name of the metric
-	init     bool              // is metric collector initialized?
+	init bool              // is metric collector initialized?
-	parallel bool              // can the metric collector be executed in parallel with others
+	meta map[string]string // static meta data tags
-	meta     map[string]string // static meta data tags
 }
 
 // Name returns the name of the metric collector
@@ -29,11 +31,6 @@ func (c *metricCollector) Name() string {
 	return c.name
 }
 
-// Name returns the name of the metric collector
-func (c *metricCollector) Parallel() bool {
-	return c.parallel
-}
-
 // Setup is for future use
 func (c *metricCollector) setup() error {
 	return nil
@@ -68,6 +65,58 @@ func stringArrayContains(array []string, str string) (int, bool) {
 	return -1, false
 }
 
+// SocketList returns the list of physical sockets as read from /proc/cpuinfo
+func SocketList() []int {
+	buffer, err := ioutil.ReadFile("/proc/cpuinfo")
+	if err != nil {
+		log.Print(err)
+		return nil
+	}
+	ll := strings.Split(string(buffer), "\n")
+	var packs []int
+	for _, line := range ll {
+		if strings.HasPrefix(line, "physical id") {
+			lv := strings.Fields(line)
+			id, err := strconv.ParseInt(lv[3], 10, 32)
+			if err != nil {
+				log.Print(err)
+				return packs
+			}
+			_, found := intArrayContains(packs, int(id))
+			if !found {
+				packs = append(packs, int(id))
+			}
+		}
+	}
+	return packs
+}
+
+// CpuList returns the list of physical CPUs (in contrast to logical CPUs) as read from /proc/cpuinfo
+func CpuList() []int {
+	buffer, err := ioutil.ReadFile("/proc/cpuinfo")
+	if err != nil {
+		log.Print(err)
+		return nil
+	}
+	ll := strings.Split(string(buffer), "\n")
+	var cpulist []int
+	for _, line := range ll {
+		if strings.HasPrefix(line, "processor") {
+			lv := strings.Fields(line)
+			id, err := strconv.ParseInt(lv[2], 10, 32)
+			if err != nil {
+				log.Print(err)
+				return cpulist
+			}
+			_, found := intArrayContains(cpulist, int(id))
+			if !found {
+				cpulist = append(cpulist, int(id))
+			}
+		}
+	}
+	return cpulist
+}
+
 // RemoveFromStringList removes the string r from the array of strings s
 // If r is not contained in the array an error is returned
 func RemoveFromStringList(s []string, r string) ([]string, error) {

collectors/netstatMetric.go

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 const NETSTATFILE = "/proc/net/dev"
@@ -39,7 +39,6 @@ type NetstatCollector struct {
 
 func (m *NetstatCollector) Init(config json.RawMessage) error {
 	m.name = "NetstatCollector"
-	m.parallel = true
 	m.setup()
 	m.lastTimestamp = time.Now()
 
@@ -102,7 +101,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 
 		// Check if device is a included device
 		if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
-			tags := map[string]string{"stype": "network", "stype-id": dev, "type": "node"}
+			tags := map[string]string{"device": dev, "type": "node"}
 			meta_unit_byte := map[string]string{"source": m.name, "group": "Network", "unit": "bytes"}
 			meta_unit_byte_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "bytes/sec"}
 			meta_unit_pkts := map[string]string{"source": m.name, "group": "Network", "unit": "packets"}

collectors/netstatMetric.md

@@ -23,5 +23,5 @@ Metrics:
 * `net_pkts_in_bw` (`unit=packets/sec` if `send_derived_values == true`)
 * `net_pkts_out_bw` (`unit=packets/sec` if `send_derived_values == true`)
 
-The device name is added as tag `stype=network,stype-id=<device>`.
+The device name is added as tag `device`.
 

collectors/nfsMetric.go

@@ -11,7 +11,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 // First part contains the code for the general NfsCollector.
@@ -114,7 +114,6 @@ func (m *nfsCollector) MainInit(config json.RawMessage) error {
 	m.data = make(map[string]NfsCollectorData)
 	m.initStats()
 	m.init = true
-	m.parallel = true
 	return nil
 }
 

collectors/nfsiostatMetric.go

@@ -1,166 +0,0 @@
-package collectors
-
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"regexp"
-	"strconv"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-)
-
-// These are the fields we read from the JSON configuration
-type NfsIOStatCollectorConfig struct {
-	ExcludeMetrics          []string `json:"exclude_metrics,omitempty"`
-	ExcludeFilesystem       []string `json:"exclude_filesystem,omitempty"`
-	UseServerAddressAsSType bool     `json:"use_server_as_stype,omitempty"`
-}
-
-// This contains all variables we need during execution and the variables
-// defined by metricCollector (name, init, ...)
-type NfsIOStatCollector struct {
-	metricCollector
-	config NfsIOStatCollectorConfig    // the configuration structure
-	meta   map[string]string           // default meta information
-	tags   map[string]string           // default tags
-	data   map[string]map[string]int64 // data storage for difference calculation
-	key    string                      // which device info should be used as subtype ID? 'server' or 'mntpoint', see NfsIOStatCollectorConfig.UseServerAddressAsSType
-}
-
-var deviceRegex = regexp.MustCompile(`device (?P<server>[^ ]+) mounted on (?P<mntpoint>[^ ]+) with fstype nfs(?P<version>\d*) statvers=[\d\.]+`)
-var bytesRegex = regexp.MustCompile(`\s+bytes:\s+(?P<nread>[^ ]+) (?P<nwrite>[^ ]+) (?P<dread>[^ ]+) (?P<dwrite>[^ ]+) (?P<nfsread>[^ ]+) (?P<nfswrite>[^ ]+) (?P<pageread>[^ ]+) (?P<pagewrite>[^ ]+)`)
-
-func resolve_regex_fields(s string, regex *regexp.Regexp) map[string]string {
-	fields := make(map[string]string)
-	groups := regex.SubexpNames()
-	for _, match := range regex.FindAllStringSubmatch(s, -1) {
-		for groupIdx, group := range match {
-			if len(groups[groupIdx]) > 0 {
-				fields[groups[groupIdx]] = group
-			}
-		}
-	}
-	return fields
-}
-
-func (m *NfsIOStatCollector) readNfsiostats() map[string]map[string]int64 {
-	data := make(map[string]map[string]int64)
-	filename := "/proc/self/mountstats"
-	stats, err := os.ReadFile(filename)
-	if err != nil {
-		return data
-	}
-
-	lines := strings.Split(string(stats), "\n")
-	var current map[string]string = nil
-	for _, l := range lines {
-		// Is this a device line with mount point, remote target and NFS version?
-		dev := resolve_regex_fields(l, deviceRegex)
-		if len(dev) > 0 {
-			if _, ok := stringArrayContains(m.config.ExcludeFilesystem, dev[m.key]); !ok {
-				current = dev
-				if len(current["version"]) == 0 {
-					current["version"] = "3"
-				}
-			}
-		}
-
-		if len(current) > 0 {
-			// Byte line parsing (if found the device for it)
-			bytes := resolve_regex_fields(l, bytesRegex)
-			if len(bytes) > 0 {
-				data[current[m.key]] = make(map[string]int64)
-				for name, sval := range bytes {
-					if _, ok := stringArrayContains(m.config.ExcludeMetrics, name); !ok {
-						val, err := strconv.ParseInt(sval, 10, 64)
-						if err == nil {
-							data[current[m.key]][name] = val
-						}
-					}
-
-				}
-				current = nil
-			}
-		}
-	}
-	return data
-}
-
-func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
-	var err error = nil
-	m.name = "NfsIOStatCollector"
-	m.setup()
-	m.parallel = true
-	m.meta = map[string]string{"source": m.name, "group": "NFS", "unit": "bytes"}
-	m.tags = map[string]string{"type": "node"}
-	m.config.UseServerAddressAsSType = false
-	if len(config) > 0 {
-		err = json.Unmarshal(config, &m.config)
-		if err != nil {
-			cclog.ComponentError(m.name, "Error reading config:", err.Error())
-			return err
-		}
-	}
-	m.key = "mntpoint"
-	if m.config.UseServerAddressAsSType {
-		m.key = "server"
-	}
-	m.data = m.readNfsiostats()
-	m.init = true
-	return err
-}
-
-func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	timestamp := time.Now()
-
-	// Get the current values for all mountpoints
-	newdata := m.readNfsiostats()
-
-	for mntpoint, values := range newdata {
-		// Was the mount point already present in the last iteration
-		if old, ok := m.data[mntpoint]; ok {
-			// Calculate the difference of old and new values
-			for i := range values {
-				x := values[i] - old[i]
-				y, err := lp.New(fmt.Sprintf("nfsio_%s", i), m.tags, m.meta, map[string]interface{}{"value": x}, timestamp)
-				if err == nil {
-					if strings.HasPrefix(i, "page") {
-						y.AddMeta("unit", "4K_Pages")
-					}
-					y.AddTag("stype", "filesystem")
-					y.AddTag("stype-id", mntpoint)
-					// Send it to output channel
-					output <- y
-				}
-				// Update old to the new value for the next iteration
-				old[i] = values[i]
-			}
-		} else {
-			// First time we see this mount point, store all values
-			m.data[mntpoint] = values
-		}
-	}
-	// Reset entries that do not exist anymore
-	for mntpoint := range m.data {
-		found := false
-		for new := range newdata {
-			if new == mntpoint {
-				found = true
-				break
-			}
-		}
-		if !found {
-			m.data[mntpoint] = nil
-		}
-	}
-
-}
-
-func (m *NfsIOStatCollector) Close() {
-	// Unset flag
-	m.init = false
-}

collectors/nfsiostatMetric.md

@@ -1,27 +0,0 @@
-## `nfsiostat` collector
-
-```json
-  "nfsiostat": {
-    "exclude_metrics": [
-      "nfsio_oread"
-    ],
-    "exclude_filesystems" : [
-        "/mnt",
-    ],
-    "use_server_as_stype": false
-  }
-```
-
-The `nfsiostat` collector reads data from `/proc/self/mountstats` and outputs a handful **node** metrics for each NFS filesystem. If a metric or filesystem is not required, it can be excluded from forwarding it to the sink.
-
-Metrics:
-* `nfsio_nread`: Bytes transferred by normal `read()` calls
-* `nfsio_nwrite`: Bytes transferred by normal `write()` calls
-* `nfsio_oread`: Bytes transferred by `read()` calls with `O_DIRECT`
-* `nfsio_owrite`: Bytes transferred by `write()` calls with `O_DIRECT`
-* `nfsio_pageread`: Pages transferred by `read()` calls
-* `nfsio_pagewrite`: Pages transferred by `write()` calls
-* `nfsio_nfsread`: Bytes transferred for reading from the server
-* `nfsio_nfswrite`: Pages transferred by writing to the server
-
-The `nfsiostat` collector adds the mountpoint to the tags as `stype=filesystem,stype-id=<mountpoint>`. If the server address should be used instead of the mountpoint, use the `use_server_as_stype` config setting.

collectors/numastatsMetric.go

@@ -10,42 +10,33 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-// Non-Uniform Memory Access (NUMA) policy hit/miss statistics
+//
+// Numa policy hit/miss statistics
 //
 // numa_hit:
-//
+//   A process wanted to allocate memory from this node, and succeeded.
-//	A process wanted to allocate memory from this node, and succeeded.
-//
 // numa_miss:
-//
+//   A process wanted to allocate memory from another node,
-//	A process wanted to allocate memory from another node,
+//   but ended up with memory from this node.
-//	but ended up with memory from this node.
-//
 // numa_foreign:
-//
+//   A process wanted to allocate on this node,
-//	A process wanted to allocate on this node,
+//   but ended up with memory from another node.
-//	but ended up with memory from another node.
-//
 // local_node:
-//
+//   A process ran on this node's CPU,
-//	A process ran on this node's CPU,
+//   and got memory from this node.
-//	and got memory from this node.
-//
 // other_node:
-//
+//   A process ran on a different node's CPU
-//	A process ran on a different node's CPU
+//   and got memory from this node.
-//	and got memory from this node.
-//
 // interleave_hit:
-//
+//   Interleaving wanted to allocate from this node
-//	Interleaving wanted to allocate from this node
+//   and succeeded.
-//	and succeeded.
 //
 // See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
+//
 type NUMAStatsCollectorTopolgy struct {
 	file   string
 	tagSet map[string]string
@@ -63,7 +54,6 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
 	}
 
 	m.name = "NUMAStatsCollector"
-	m.parallel = true
 	m.setup()
 	m.meta = map[string]string{
 		"source": m.name,
@@ -91,8 +81,6 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
 			})
 	}
 
-	// Initialized
-	cclog.ComponentDebug(m.name, "initialized", len(m.topology), "NUMA domains")
 	m.init = true
 	return nil
 }

collectors/numastatsMetric.md

@@ -1,17 +1,15 @@
 
 ## `numastat` collector
-
 ```json
-  "numastats": {}
+  "numastat": {}
 ```
 
-The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: <https://www.kernel.org/doc/html/latest/admin-guide/numastat.html>
+The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
 
 Metrics:
-
 * `numastats_numa_hit`: A process wanted to allocate memory from this node, and succeeded.
 * `numastats_numa_miss`: A process wanted to allocate memory from another node, but ended up with memory from this node.
 * `numastats_numa_foreign`: A process wanted to allocate on this node, but ended up with memory from another node.
 * `numastats_local_node`: A process ran on this node's CPU, and got memory from this node.
 * `numastats_other_node`: A process ran on a different node's CPU, and got memory from this node.
-* `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded.
+* `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded.

collectors/nvidiaMetric.md

@@ -3,74 +3,38 @@
 
 ```json
   "nvidia": {
-    "exclude_devices": [
+    "exclude_devices" : [
-      "0","1", "0000000:ff:01.0"
+      "0","1"
     ],
     "exclude_metrics": [
-      "nv_fb_mem_used",
+      "nv_fb_memory",
       "nv_fan"
-    ],
+    ]
-    "process_mig_devices": false,
-    "use_pci_info_as_type_id": true,
-    "add_pci_info_tag": false,
-    "add_uuid_meta": false,
-    "add_board_number_meta": false,
-    "add_serial_meta": false,
-    "use_uuid_for_mig_device": false,
-    "use_slice_for_mig_device": false
   }
 ```
 
-The `nvidia` collector can be configured to leave out specific devices with the `exclude_devices` option. It takes IDs as supplied to the NVML with `nvmlDeviceGetHandleByIndex()` or the PCI address in NVML format (`%08X:%02X:%02X.0`). Metrics (listed below) that should not be sent to the MetricRouter can be excluded with the `exclude_metrics` option. Commonly only the physical GPUs are monitored. If MIG devices should be analyzed as well, set `process_mig_devices` (adds `stype=mig,stype-id=<mig_index>`). With the options `use_uuid_for_mig_device` and `use_slice_for_mig_device`, the `<mig_index>` can be replaced with the UUID (e.g. `MIG-6a9f7cc8-6d5b-5ce0-92de-750edc4d8849`) or the MIG slice name (e.g. `1g.5gb`).
-
-The metrics sent by the `nvidia` collector use `accelerator` as `type` tag. For the `type-id`, it uses the device handle index by default. With the `use_pci_info_as_type_id` option, the PCI ID is used instead. If both values should be added as tags, activate the `add_pci_info_tag` option. It uses the device handle index as `type-id` and adds the PCI ID as separate `pci_identifier` tag.
-
-Optionally, it is possible to add the UUID, the board part number and the serial to the meta informations. They are not sent to the sinks (if not configured otherwise).
-
-
 Metrics:
 * `nv_util`
 * `nv_mem_util`
-* `nv_fb_mem_total`
+* `nv_mem_total`
-* `nv_fb_mem_used`
+* `nv_fb_memory`
-* `nv_bar1_mem_total`
-* `nv_bar1_mem_used`
 * `nv_temp`
 * `nv_fan`
 * `nv_ecc_mode`
 * `nv_perf_state`
-* `nv_power_usage`
+* `nv_power_usage_report`
-* `nv_graphics_clock`
+* `nv_graphics_clock_report`
-* `nv_sm_clock`
+* `nv_sm_clock_report`
-* `nv_mem_clock`
+* `nv_mem_clock_report`
-* `nv_video_clock`
 * `nv_max_graphics_clock`
 * `nv_max_sm_clock`
 * `nv_max_mem_clock`
-* `nv_max_video_clock`
+* `nv_ecc_db_error`
-* `nv_ecc_uncorrected_error`
+* `nv_ecc_sb_error`
-* `nv_ecc_corrected_error`
+* `nv_power_man_limit`
-* `nv_power_max_limit`
 * `nv_encoder_util`
 * `nv_decoder_util`
-* `nv_remapped_rows_corrected`
-* `nv_remapped_rows_uncorrected`
-* `nv_remapped_rows_pending`
-* `nv_remapped_rows_failure`
-* `nv_compute_processes`
-* `nv_graphics_processes`
-* `nv_violation_power`
-* `nv_violation_thermal`
-* `nv_violation_sync_boost`
-* `nv_violation_board_limit`
-* `nv_violation_low_util`
-* `nv_violation_reliability`
-* `nv_violation_below_app_clock`
-* `nv_violation_below_base_clock`
-* `nv_nvlink_crc_flit_errors`
-* `nv_nvlink_crc_errors`
-* `nv_nvlink_ecc_errors`
-* `nv_nvlink_replay_errors`
-* `nv_nvlink_recovery_errors`
 
-Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`. 
+It uses a separate `type` in the metrics. The output metric looks like this:
+`<name>,type=accelerator,type-id=<nvidia-gpu-id> value=<metric value> <timestamp>`
+

collectors/raplMetric.go

@@ -1,262 +0,0 @@
-package collectors
-
-import (
-	"encoding/json"
-	"fmt"
-	"os"
-	"path/filepath"
-	"strconv"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-)
-
-// running average power limit (RAPL) monitoring attributes for a zone
-type RAPLZoneInfo struct {
-	// tags describing the RAPL zone:
-	// * zone_name, subzone_name: e.g. psys, dram, core, uncore, package-0
-	// * zone_id: e.g. 0:1 (zone 0 sub zone 1)
-	tags            map[string]string
-	energyFilepath  string    // path to a file containing the zones current energy counter in micro joules
-	energy          int64     // current reading of the energy counter in micro joules
-	energyTimestamp time.Time // timestamp when energy counter was read
-	maxEnergyRange  int64     // Range of the above energy counter in micro-joules
-}
-
-type RAPLCollector struct {
-	metricCollector
-	config struct {
-		// Exclude IDs for RAPL zones, e.g.
-		// * 0 for zone 0
-		// * 0:1 for zone 0 subzone 1
-		ExcludeByID []string `json:"exclude_device_by_id,omitempty"`
-		// Exclude names for RAPL zones, e.g. psys, dram, core, uncore, package-0
-		ExcludeByName []string `json:"exclude_device_by_name,omitempty"`
-	}
-	RAPLZoneInfo []RAPLZoneInfo
-	meta         map[string]string // default meta information
-}
-
-// Init initializes the running average power limit (RAPL) collector
-func (m *RAPLCollector) Init(config json.RawMessage) error {
-
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
-	var err error = nil
-	m.name = "RAPLCollector"
-	m.setup()
-	m.parallel = true
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "energy",
-		"unit":   "Watt",
-	}
-
-	// Read in the JSON configuration
-	if len(config) > 0 {
-		err = json.Unmarshal(config, &m.config)
-		if err != nil {
-			cclog.ComponentError(m.name, "Error reading config:", err.Error())
-			return err
-		}
-	}
-
-	// Configure excluded RAPL zones
-	isIDExcluded := make(map[string]bool)
-	if m.config.ExcludeByID != nil {
-		for _, ID := range m.config.ExcludeByID {
-			isIDExcluded[ID] = true
-		}
-	}
-	isNameExcluded := make(map[string]bool)
-	if m.config.ExcludeByName != nil {
-		for _, name := range m.config.ExcludeByName {
-			isNameExcluded[name] = true
-		}
-	}
-
-	// readZoneInfo reads RAPL monitoring attributes for a zone given by zonePath
-	// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
-	readZoneInfo := func(zonePath string) (z struct {
-		name            string    // zones name e.g. psys, dram, core, uncore, package-0
-		energyFilepath  string    // path to a file containing the zones current energy counter in micro joules
-		energy          int64     // current reading of the energy counter in micro joules
-		energyTimestamp time.Time // timestamp when energy counter was read
-		maxEnergyRange  int64     // Range of the above energy counter in micro-joules
-		ok              bool      // Are all information available?
-	}) {
-		// zones name e.g. psys, dram, core, uncore, package-0
-		foundName := false
-		if v, err :=
-			os.ReadFile(
-				filepath.Join(zonePath, "name")); err == nil {
-			foundName = true
-			z.name = strings.TrimSpace(string(v))
-		}
-
-		// path to a file containing the zones current energy counter in micro joules
-		z.energyFilepath = filepath.Join(zonePath, "energy_uj")
-
-		// current reading of the energy counter in micro joules
-		foundEnergy := false
-		if v, err := os.ReadFile(z.energyFilepath); err == nil {
-			// timestamp when energy counter was read
-			z.energyTimestamp = time.Now()
-			if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
-				foundEnergy = true
-				z.energy = i
-			}
-		}
-
-		// Range of the above energy counter in micro-joules
-		foundMaxEnergyRange := false
-		if v, err :=
-			os.ReadFile(
-				filepath.Join(zonePath, "max_energy_range_uj")); err == nil {
-			if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
-				foundMaxEnergyRange = true
-				z.maxEnergyRange = i
-			}
-		}
-
-		// Are all information available?
-		z.ok = foundName && foundEnergy && foundMaxEnergyRange
-
-		return
-	}
-
-	powerCapPrefix := "/sys/devices/virtual/powercap"
-	controlType := "intel-rapl"
-	controlTypePath := filepath.Join(powerCapPrefix, controlType)
-
-	// Find all RAPL zones
-	zonePrefix := filepath.Join(controlTypePath, controlType+":")
-	zonesPath, err := filepath.Glob(zonePrefix + "*")
-	if err != nil || zonesPath == nil {
-		return fmt.Errorf("unable to find any zones under %s", controlTypePath)
-	}
-
-	for _, zonePath := range zonesPath {
-		zoneID := strings.TrimPrefix(zonePath, zonePrefix)
-		z := readZoneInfo(zonePath)
-		if z.ok &&
-			!isIDExcluded[zoneID] &&
-			!isNameExcluded[z.name] {
-
-			// Add RAPL monitoring attributes for a zone
-			m.RAPLZoneInfo =
-				append(
-					m.RAPLZoneInfo,
-					RAPLZoneInfo{
-						tags: map[string]string{
-							"id":        zoneID,
-							"zone_name": z.name,
-						},
-						energyFilepath:  z.energyFilepath,
-						energy:          z.energy,
-						energyTimestamp: z.energyTimestamp,
-						maxEnergyRange:  z.maxEnergyRange,
-					})
-		}
-
-		// find all sub zones for the given zone
-		subZonePrefix := filepath.Join(zonePath, controlType+":"+zoneID+":")
-		subZonesPath, err := filepath.Glob(subZonePrefix + "*")
-		if err != nil || subZonesPath == nil {
-			continue
-		}
-
-		for _, subZonePath := range subZonesPath {
-			subZoneID := strings.TrimPrefix(subZonePath, subZonePrefix)
-			sz := readZoneInfo(subZonePath)
-			if len(zoneID) > 0 && len(z.name) > 0 &&
-				sz.ok &&
-				!isIDExcluded[zoneID+":"+subZoneID] &&
-				!isNameExcluded[sz.name] {
-				m.RAPLZoneInfo =
-					append(
-						m.RAPLZoneInfo,
-						RAPLZoneInfo{
-							tags: map[string]string{
-								"id":            zoneID + ":" + subZoneID,
-								"zone_name":     z.name,
-								"sub_zone_name": sz.name,
-							},
-							energyFilepath:  sz.energyFilepath,
-							energy:          sz.energy,
-							energyTimestamp: sz.energyTimestamp,
-							maxEnergyRange:  sz.maxEnergyRange,
-						})
-			}
-		}
-	}
-
-	if m.RAPLZoneInfo == nil {
-		return fmt.Errorf("no running average power limit (RAPL) device found in %s", controlTypePath)
-
-	}
-
-	// Initialized
-	cclog.ComponentDebug(
-		m.name,
-		"initialized",
-		len(m.RAPLZoneInfo),
-		"zones with running average power limit (RAPL) monitoring attributes")
-	m.init = true
-
-	return err
-}
-
-// Read reads running average power limit (RAPL) monitoring attributes for all initialized zones
-// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
-func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-
-	for i := range m.RAPLZoneInfo {
-		p := &m.RAPLZoneInfo[i]
-
-		// Read current value of the energy counter in micro joules
-		if v, err := os.ReadFile(p.energyFilepath); err == nil {
-			energyTimestamp := time.Now()
-			if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
-				energy := i
-
-				// Compute average power (Δ energy / Δ time)
-				energyDiff := energy - p.energy
-				if energyDiff < 0 {
-					// Handle overflow:
-					// ( p.maxEnergyRange - p.energy ) + energy
-					// = p.maxEnergyRange + ( energy - p.energy )
-					// = p.maxEnergyRange + diffEnergy
-					energyDiff += p.maxEnergyRange
-				}
-				timeDiff := energyTimestamp.Sub(p.energyTimestamp)
-				averagePower := float64(energyDiff) / float64(timeDiff.Microseconds())
-
-				y, err := lp.New(
-					"rapl_average_power",
-					p.tags,
-					m.meta,
-					map[string]interface{}{"value": averagePower},
-					energyTimestamp)
-				if err == nil {
-					output <- y
-				}
-
-				// Save current energy counter state
-				p.energy = energy
-				p.energyTimestamp = energyTimestamp
-			}
-		}
-	}
-}
-
-// Close closes running average power limit (RAPL) metric collector
-func (m *RAPLCollector) Close() {
-	// Unset flag
-	m.init = false
-}

collectors/raplMetric.md

@@ -1,18 +0,0 @@
-# Running average power limit (RAPL) metric collector
-
-This collector reads running average power limit (RAPL) monitoring attributes to compute average power consumption metrics. See <https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes>.
-
-The Likwid metric collector provides similar functionality.
-
-## Configuration
-
-```json
-  "rapl": {
-    "exclude_device_by_id": ["0:1", "0:2"],
-    "exclude_device_by_name": ["psys"]
-  }
-```
-
-## Metrics
-
-* `rapl_average_power`: average power consumption in Watt. The average is computed over the entire runtime from the last measurement to the current measurement

collectors/rocmsmiMetric.go

@@ -1,319 +0,0 @@
-package collectors
-
-import (
-	"encoding/json"
-	"errors"
-	"fmt"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-	"github.com/ClusterCockpit/go-rocm-smi/pkg/rocm_smi"
-)
-
-type RocmSmiCollectorConfig struct {
-	ExcludeMetrics     []string `json:"exclude_metrics,omitempty"`
-	ExcludeDevices     []string `json:"exclude_devices,omitempty"`
-	AddPciInfoTag      bool     `json:"add_pci_info_tag,omitempty"`
-	UsePciInfoAsTypeId bool     `json:"use_pci_info_as_type_id,omitempty"`
-	AddSerialMeta      bool     `json:"add_serial_meta,omitempty"`
-}
-
-type RocmSmiCollectorDevice struct {
-	device         rocm_smi.DeviceHandle
-	index          int
-	tags           map[string]string // default tags
-	meta           map[string]string // default meta information
-	excludeMetrics map[string]bool   // copy of exclude metrics from config
-}
-
-type RocmSmiCollector struct {
-	metricCollector
-	config  RocmSmiCollectorConfig // the configuration structure
-	devices []RocmSmiCollectorDevice
-}
-
-// Functions to implement MetricCollector interface
-// Init(...), Read(...), Close()
-// See: metricCollector.go
-
-// Init initializes the sample collector
-// Called once by the collector manager
-// All tags, meta data tags and metrics that do not change over the runtime should be set here
-func (m *RocmSmiCollector) Init(config json.RawMessage) error {
-	var err error = nil
-	// Always set the name early in Init() to use it in cclog.Component* functions
-	m.name = "RocmSmiCollector"
-	// This is for later use, also call it early
-	m.setup()
-	// Define meta information sent with each metric
-	// (Can also be dynamic or this is the basic set with extension through AddMeta())
-	//m.meta = map[string]string{"source": m.name, "group": "AMD"}
-	// Define tags sent with each metric
-	// The 'type' tag is always needed, it defines the granulatity of the metric
-	// node -> whole system
-	// socket -> CPU socket (requires socket ID as 'type-id' tag)
-	// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
-	//m.tags = map[string]string{"type": "node"}
-	// Read in the JSON configuration
-	if len(config) > 0 {
-		err = json.Unmarshal(config, &m.config)
-		if err != nil {
-			cclog.ComponentError(m.name, "Error reading config:", err.Error())
-			return err
-		}
-	}
-
-	ret := rocm_smi.Init()
-	if ret != rocm_smi.STATUS_SUCCESS {
-		err = errors.New("failed to initialize ROCm SMI library")
-		cclog.ComponentError(m.name, err.Error())
-		return err
-	}
-
-	numDevs, ret := rocm_smi.NumMonitorDevices()
-	if ret != rocm_smi.STATUS_SUCCESS {
-		err = errors.New("failed to get number of GPUs from ROCm SMI library")
-		cclog.ComponentError(m.name, err.Error())
-		return err
-	}
-
-	exclDev := func(s string) bool {
-		skip_device := false
-		for _, excl := range m.config.ExcludeDevices {
-			if excl == s {
-				skip_device = true
-				break
-			}
-		}
-		return skip_device
-	}
-
-	m.devices = make([]RocmSmiCollectorDevice, 0)
-
-	for i := 0; i < numDevs; i++ {
-		str_i := fmt.Sprintf("%d", i)
-		if exclDev(str_i) {
-			continue
-		}
-		device, ret := rocm_smi.DeviceGetHandleByIndex(i)
-		if ret != rocm_smi.STATUS_SUCCESS {
-			err = fmt.Errorf("failed to get handle for GPU %d", i)
-			cclog.ComponentError(m.name, err.Error())
-			return err
-		}
-
-		pciInfo, ret := rocm_smi.DeviceGetPciInfo(device)
-		if ret != rocm_smi.STATUS_SUCCESS {
-			err = fmt.Errorf("failed to get PCI information for GPU %d", i)
-			cclog.ComponentError(m.name, err.Error())
-			return err
-		}
-
-		pciId := fmt.Sprintf(
-			"%08X:%02X:%02X.%X",
-			pciInfo.Domain,
-			pciInfo.Bus,
-			pciInfo.Device,
-			pciInfo.Function)
-
-		if exclDev(pciId) {
-			continue
-		}
-
-		dev := RocmSmiCollectorDevice{
-			device: device,
-			tags: map[string]string{
-				"type":    "accelerator",
-				"type-id": str_i,
-			},
-			meta: map[string]string{
-				"source": m.name,
-				"group":  "AMD",
-			},
-		}
-		if m.config.UsePciInfoAsTypeId {
-			dev.tags["type-id"] = pciId
-		} else if m.config.AddPciInfoTag {
-			dev.tags["pci_identifier"] = pciId
-		}
-
-		if m.config.AddSerialMeta {
-			serial, ret := rocm_smi.DeviceGetSerialNumber(device)
-			if ret != rocm_smi.STATUS_SUCCESS {
-				cclog.ComponentError(m.name, "Unable to get serial number for device at index", i, ":", rocm_smi.StatusStringNoError(ret))
-			} else {
-				dev.meta["serial"] = serial
-			}
-		}
-		// Add excluded metrics
-		dev.excludeMetrics = map[string]bool{}
-		for _, e := range m.config.ExcludeMetrics {
-			dev.excludeMetrics[e] = true
-		}
-		dev.index = i
-		m.devices = append(m.devices, dev)
-	}
-
-	// Set this flag only if everything is initialized properly, all required files exist, ...
-	m.init = true
-	return err
-}
-
-// Read collects all metrics belonging to the sample collector
-// and sends them through the output channel to the collector manager
-func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	// Create a sample metric
-	timestamp := time.Now()
-
-	for _, dev := range m.devices {
-		metrics, ret := rocm_smi.DeviceGetMetrics(dev.device)
-		if ret != rocm_smi.STATUS_SUCCESS {
-			cclog.ComponentError(m.name, "Unable to get metrics for device at index", dev.index, ":", rocm_smi.StatusStringNoError(ret))
-			continue
-		}
-
-		if !dev.excludeMetrics["rocm_gfx_util"] {
-			value := metrics.Average_gfx_activity
-			y, err := lp.New("rocm_gfx_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_umc_util"] {
-			value := metrics.Average_umc_activity
-			y, err := lp.New("rocm_umc_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_mm_util"] {
-			value := metrics.Average_mm_activity
-			y, err := lp.New("rocm_mm_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_avg_power"] {
-			value := metrics.Average_socket_power
-			y, err := lp.New("rocm_avg_power", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_temp_mem"] {
-			value := metrics.Temperature_mem
-			y, err := lp.New("rocm_temp_mem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_temp_hotspot"] {
-			value := metrics.Temperature_hotspot
-			y, err := lp.New("rocm_temp_hotspot", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_temp_edge"] {
-			value := metrics.Temperature_edge
-			y, err := lp.New("rocm_temp_edge", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_temp_vrgfx"] {
-			value := metrics.Temperature_vrgfx
-			y, err := lp.New("rocm_temp_vrgfx", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_temp_vrsoc"] {
-			value := metrics.Temperature_vrsoc
-			y, err := lp.New("rocm_temp_vrsoc", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_temp_vrmem"] {
-			value := metrics.Temperature_vrmem
-			y, err := lp.New("rocm_temp_vrmem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_gfx_clock"] {
-			value := metrics.Average_gfxclk_frequency
-			y, err := lp.New("rocm_gfx_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_soc_clock"] {
-			value := metrics.Average_socclk_frequency
-			y, err := lp.New("rocm_soc_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_u_clock"] {
-			value := metrics.Average_uclk_frequency
-			y, err := lp.New("rocm_u_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_v0_clock"] {
-			value := metrics.Average_vclk0_frequency
-			y, err := lp.New("rocm_v0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_v1_clock"] {
-			value := metrics.Average_vclk1_frequency
-			y, err := lp.New("rocm_v1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_d0_clock"] {
-			value := metrics.Average_dclk0_frequency
-			y, err := lp.New("rocm_d0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_d1_clock"] {
-			value := metrics.Average_dclk1_frequency
-			y, err := lp.New("rocm_d1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-		if !dev.excludeMetrics["rocm_temp_hbm"] {
-			for i := 0; i < rocm_smi.NUM_HBM_INSTANCES; i++ {
-				value := metrics.Temperature_hbm[i]
-				y, err := lp.New("rocm_temp_hbm", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
-				if err == nil {
-					y.AddTag("stype", "device")
-					y.AddTag("stype-id", fmt.Sprintf("%d", i))
-					output <- y
-				}
-			}
-		}
-	}
-
-}
-
-// Close metric collector: close network connection, close files, close libraries, ...
-// Called once by the collector manager
-func (m *RocmSmiCollector) Close() {
-	// Unset flag
-	ret := rocm_smi.Shutdown()
-	if ret != rocm_smi.STATUS_SUCCESS {
-		cclog.ComponentError(m.name, "Failed to shutdown ROCm SMI library")
-	}
-	m.init = false
-}

collectors/rocmsmiMetric.md

@@ -1,47 +0,0 @@
-
-## `rocm_smi` collector
-
-```json
-  "rocm_smi": {
-    "exclude_devices": [
-      "0","1", "0000000:ff:01.0"
-    ],
-    "exclude_metrics": [
-      "rocm_mm_util",
-      "rocm_temp_vrsoc"
-    ],
-    "use_pci_info_as_type_id": true,
-    "add_pci_info_tag": false,
-    "add_serial_meta": false,
-  }
-```
-
-The `rocm_smi` collector can be configured to leave out specific devices with the `exclude_devices` option. It takes logical IDs in the list of available devices or the PCI address similar to NVML format (`%08X:%02X:%02X.0`). Metrics (listed below) that should not be sent to the MetricRouter can be excluded with the `exclude_metrics` option. 
-
-The metrics sent by the `rocm_smi` collector use `accelerator` as `type` tag. For the `type-id`, it uses the device handle index by default. With the `use_pci_info_as_type_id` option, the PCI ID is used instead. If both values should be added as tags, activate the `add_pci_info_tag` option. It uses the device handle index as `type-id` and adds the PCI ID as separate `pci_identifier` tag.
-
-Optionally, it is possible to add the serial to the meta informations. They are not sent to the sinks (if not configured otherwise).
-
-
-Metrics:
-* `rocm_gfx_util`
-* `rocm_umc_util`
-* `rocm_mm_util`
-* `rocm_avg_power`
-* `rocm_temp_mem`
-* `rocm_temp_hotspot`
-* `rocm_temp_edge`
-* `rocm_temp_vrgfx`
-* `rocm_temp_vrsoc`
-* `rocm_temp_vrmem`
-* `rocm_gfx_clock`
-* `rocm_soc_clock`
-* `rocm_u_clock`
-* `rocm_v0_clock`
-* `rocm_v1_clock`
-* `rocm_d0_clock`
-* `rocm_d1_clock`
-* `rocm_temp_hbm`
-
-
-Some metrics add the additional sub type tag (`stype`) like the `rocm_temp_hbm` metrics set `stype=device,stype-id=<HBM_slice_number>`. 

collectors/sampleMetric.go

@@ -4,8 +4,8 @@ import (
 	"encoding/json"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 // These are the fields we read from the JSON configuration
@@ -17,9 +17,9 @@ type SampleCollectorConfig struct {
 // defined by metricCollector (name, init, ...)
 type SampleCollector struct {
 	metricCollector
-	config SampleCollectorConfig // the configuration structure
+	config SampleTimerCollectorConfig // the configuration structure
-	meta   map[string]string     // default meta information
+	meta   map[string]string          // default meta information
-	tags   map[string]string     // default tags
+	tags   map[string]string          // default tags
 }
 
 // Functions to implement MetricCollector interface
@@ -35,23 +35,14 @@ func (m *SampleCollector) Init(config json.RawMessage) error {
 	m.name = "InternalCollector"
 	// This is for later use, also call it early
 	m.setup()
-	// Tell whether the collector should be run in parallel with others (reading files, ...)
-	// or it should be run serially, mostly for collectors actually doing measurements
-	// because they should not measure the execution of the other collectors
-	m.parallel = true
 	// Define meta information sent with each metric
 	// (Can also be dynamic or this is the basic set with extension through AddMeta())
 	m.meta = map[string]string{"source": m.name, "group": "SAMPLE"}
 	// Define tags sent with each metric
-	// The 'type' tag is always needed, it defines the granularity of the metric
+	// The 'type' tag is always needed, it defines the granulatity of the metric
 	// node -> whole system
 	// socket -> CPU socket (requires socket ID as 'type-id' tag)
-	// die -> CPU die (requires CPU die ID as 'type-id' tag)
+	// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
-	// memoryDomain -> NUMA domain (requires NUMA domain ID as 'type-id' tag)
-	// llc -> Last level cache (requires last level cache ID as 'type-id' tag)
-	// core -> single CPU core that may consist of multiple hardware threads (SMT) (requires core ID as 'type-id' tag)
-	// hwthtread -> single CPU hardware thread (requires hardware thread ID as 'type-id' tag)
-	// accelerator -> A accelerator device like GPU or FPGA (requires an accelerator ID as 'type-id' tag)
 	m.tags = map[string]string{"type": "node"}
 	// Read in the JSON configuration
 	if len(config) > 0 {

collectors/sampleTimerMetric.go

@@ -5,8 +5,8 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 // These are the fields we read from the JSON configuration
@@ -38,7 +38,7 @@ func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
 	// (Can also be dynamic or this is the basic set with extension through AddMeta())
 	m.meta = map[string]string{"source": m.name, "group": "SAMPLE"}
 	// Define tags sent with each metric
-	// The 'type' tag is always needed, it defines the granularity of the metric
+	// The 'type' tag is always needed, it defines the granulatity of the metric
 	// node -> whole system
 	// socket -> CPU socket (requires socket ID as 'type-id' tag)
 	// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
@@ -60,7 +60,7 @@ func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
 
 	// Storage for output channel
 	m.output = nil
-	// Management channel for the timer function.
+	// Mangement channel for the timer function.
 	m.done = make(chan bool)
 	// Create the own ticker
 	m.ticker = time.NewTicker(m.interval)
@@ -94,7 +94,7 @@ func (m *SampleTimerCollector) ReadMetrics(timestamp time.Time) {
 
 	value := 1.0
 
-	// If you want to measure something for a specific amount of time, use interval
+	// If you want to measure something for a specific amout of time, use interval
 	// start := readState()
 	// time.Sleep(interval)
 	// stop := readState()

collectors/schedstatMetric.go

@@ -1,154 +0,0 @@
-package collectors
-
-import (
-	"bufio"
-	"encoding/json"
-	"fmt"
-	"math"
-	"os"
-	"strconv"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-)
-
-const SCHEDSTATFILE = `/proc/schedstat`
-
-// These are the fields we read from the JSON configuration
-type SchedstatCollectorConfig struct {
-	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-}
-
-// This contains all variables we need during execution and the variables
-// defined by metricCollector (name, init, ...)
-type SchedstatCollector struct {
-	metricCollector
-	config        SchedstatCollectorConfig     // the configuration structure
-	lastTimestamp time.Time                    // Store time stamp of last tick to derive values
-	meta          map[string]string            // default meta information
-	cputags       map[string]map[string]string // default tags
-	olddata       map[string]map[string]int64  // default tags
-}
-
-// Functions to implement MetricCollector interface
-// Init(...), Read(...), Close()
-// See: metricCollector.go
-
-// Init initializes the sample collector
-// Called once by the collector manager
-// All tags, meta data tags and metrics that do not change over the runtime should be set here
-func (m *SchedstatCollector) Init(config json.RawMessage) error {
-	var err error = nil
-	// Always set the name early in Init() to use it in cclog.Component* functions
-	m.name = "SchedstatCollector"
-	// This is for later use, also call it early
-	m.setup()
-	// Tell whether the collector should be run in parallel with others (reading files, ...)
-	// or it should be run serially, mostly for collectors acutally doing measurements
-	// because they should not measure the execution of the other collectors
-	m.parallel = true
-	// Define meta information sent with each metric
-	// (Can also be dynamic or this is the basic set with extension through AddMeta())
-	m.meta = map[string]string{"source": m.name, "group": "SCHEDSTAT"}
-
-	// Read in the JSON configuration
-	if len(config) > 0 {
-		err = json.Unmarshal(config, &m.config)
-		if err != nil {
-			cclog.ComponentError(m.name, "Error reading config:", err.Error())
-			return err
-		}
-	}
-
-	// Check input file
-	file, err := os.Open(string(SCHEDSTATFILE))
-	if err != nil {
-		cclog.ComponentError(m.name, err.Error())
-	}
-	defer file.Close()
-
-	// Pre-generate tags for all CPUs
-	num_cpus := 0
-	m.cputags = make(map[string]map[string]string)
-	m.olddata = make(map[string]map[string]int64)
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		line := scanner.Text()
-		linefields := strings.Fields(line)
-		if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
-			cpustr := strings.TrimLeft(linefields[0], "cpu")
-			cpu, _ := strconv.Atoi(cpustr)
-			running, _ := strconv.ParseInt(linefields[7], 10, 64)
-			waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
-			m.cputags[linefields[0]] = map[string]string{"type": "hwthread", "type-id": fmt.Sprintf("%d", cpu)}
-			m.olddata[linefields[0]] = map[string]int64{"running": running, "waiting": waiting}
-			num_cpus++
-		}
-	}
-
-	// Save current timestamp
-	m.lastTimestamp = time.Now()
-
-	// Set this flag only if everything is initialized properly, all required files exist, ...
-	m.init = true
-	return err
-}
-
-func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
-	running, _ := strconv.ParseInt(linefields[7], 10, 64)
-	waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
-	diff_running := running - m.olddata[linefields[0]]["running"]
-	diff_waiting := waiting - m.olddata[linefields[0]]["waiting"]
-
-	var l_running float64 = float64(diff_running) / tsdelta.Seconds() / (math.Pow(1000, 3))
-	var l_waiting float64 = float64(diff_waiting) / tsdelta.Seconds() / (math.Pow(1000, 3))
-
-	m.olddata[linefields[0]]["running"] = running
-	m.olddata[linefields[0]]["waiting"] = waiting
-	value := l_running + l_waiting
-
-	y, err := lp.New("cpu_load_core", tags, m.meta, map[string]interface{}{"value": value}, now)
-	if err == nil {
-		// Send it to output channel
-		output <- y
-	}
-}
-
-// Read collects all metrics belonging to the sample collector
-// and sends them through the output channel to the collector manager
-func (m *SchedstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	if !m.init {
-		return
-	}
-
-	//timestamps
-	now := time.Now()
-	tsdelta := now.Sub(m.lastTimestamp)
-
-	file, err := os.Open(string(SCHEDSTATFILE))
-	if err != nil {
-		cclog.ComponentError(m.name, err.Error())
-	}
-	defer file.Close()
-
-	scanner := bufio.NewScanner(file)
-	for scanner.Scan() {
-		line := scanner.Text()
-		linefields := strings.Fields(line)
-		if strings.HasPrefix(linefields[0], "cpu") {
-			m.ParseProcLine(linefields, m.cputags[linefields[0]], output, now, tsdelta)
-		}
-	}
-
-	m.lastTimestamp = now
-
-}
-
-// Close metric collector: close network connection, close files, close libraries, ...
-// Called once by the collector manager
-func (m *SchedstatCollector) Close() {
-	// Unset flag
-	m.init = false
-}

collectors/schedstatMetric.md

@@ -1,11 +0,0 @@
-
-## `schedstat` collector
-```json
-  "schedstat": {
-  }
-```
-
-The `schedstat` collector reads data from /proc/schedstat and calculates a load value, separated by hwthread. This might be useful to detect bad cpu pinning on shared nodes etc. 
-
-Metric:
-* `cpu_load_core`

collectors/selfMetric.go

@@ -1,144 +0,0 @@
-package collectors
-
-import (
-	"encoding/json"
-	"runtime"
-	"syscall"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-)
-
-type SelfCollectorConfig struct {
-	MemStats   bool `json:"read_mem_stats"`
-	GoRoutines bool `json:"read_goroutines"`
-	CgoCalls   bool `json:"read_cgo_calls"`
-	Rusage     bool `json:"read_rusage"`
-}
-
-type SelfCollector struct {
-	metricCollector
-	config SelfCollectorConfig // the configuration structure
-	meta   map[string]string   // default meta information
-	tags   map[string]string   // default tags
-}
-
-func (m *SelfCollector) Init(config json.RawMessage) error {
-	var err error = nil
-	m.name = "SelfCollector"
-	m.setup()
-	m.parallel = true
-	m.meta = map[string]string{"source": m.name, "group": "Self"}
-	m.tags = map[string]string{"type": "node"}
-	if len(config) > 0 {
-		err = json.Unmarshal(config, &m.config)
-		if err != nil {
-			cclog.ComponentError(m.name, "Error reading config:", err.Error())
-			return err
-		}
-	}
-	m.init = true
-	return err
-}
-
-func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	timestamp := time.Now()
-
-	if m.config.MemStats {
-		var memstats runtime.MemStats
-		runtime.ReadMemStats(&memstats)
-
-		y, err := lp.New("total_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.TotalAlloc}, timestamp)
-		if err == nil {
-			y.AddMeta("unit", "Bytes")
-			output <- y
-		}
-		y, err = lp.New("heap_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapAlloc}, timestamp)
-		if err == nil {
-			y.AddMeta("unit", "Bytes")
-			output <- y
-		}
-		y, err = lp.New("heap_sys", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapSys}, timestamp)
-		if err == nil {
-			y.AddMeta("unit", "Bytes")
-			output <- y
-		}
-		y, err = lp.New("heap_idle", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapIdle}, timestamp)
-		if err == nil {
-			y.AddMeta("unit", "Bytes")
-			output <- y
-		}
-		y, err = lp.New("heap_inuse", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapInuse}, timestamp)
-		if err == nil {
-			y.AddMeta("unit", "Bytes")
-			output <- y
-		}
-		y, err = lp.New("heap_released", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapReleased}, timestamp)
-		if err == nil {
-			y.AddMeta("unit", "Bytes")
-			output <- y
-		}
-		y, err = lp.New("heap_objects", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapObjects}, timestamp)
-		if err == nil {
-			output <- y
-		}
-	}
-	if m.config.GoRoutines {
-		y, err := lp.New("num_goroutines", m.tags, m.meta, map[string]interface{}{"value": runtime.NumGoroutine()}, timestamp)
-		if err == nil {
-			output <- y
-		}
-	}
-	if m.config.CgoCalls {
-		y, err := lp.New("num_cgo_calls", m.tags, m.meta, map[string]interface{}{"value": runtime.NumCgoCall()}, timestamp)
-		if err == nil {
-			output <- y
-		}
-	}
-	if m.config.Rusage {
-		var rusage syscall.Rusage
-		err := syscall.Getrusage(syscall.RUSAGE_SELF, &rusage)
-		if err == nil {
-			sec, nsec := rusage.Utime.Unix()
-			t := float64(sec) + (float64(nsec) * 1e-9)
-			y, err := lp.New("rusage_user_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
-			if err == nil {
-				y.AddMeta("unit", "seconds")
-				output <- y
-			}
-			sec, nsec = rusage.Stime.Unix()
-			t = float64(sec) + (float64(nsec) * 1e-9)
-			y, err = lp.New("rusage_system_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
-			if err == nil {
-				y.AddMeta("unit", "seconds")
-				output <- y
-			}
-			y, err = lp.New("rusage_vol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nvcsw}, timestamp)
-			if err == nil {
-				output <- y
-			}
-			y, err = lp.New("rusage_invol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nivcsw}, timestamp)
-			if err == nil {
-				output <- y
-			}
-			y, err = lp.New("rusage_signals", m.tags, m.meta, map[string]interface{}{"value": rusage.Nsignals}, timestamp)
-			if err == nil {
-				output <- y
-			}
-			y, err = lp.New("rusage_major_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Majflt}, timestamp)
-			if err == nil {
-				output <- y
-			}
-			y, err = lp.New("rusage_minor_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Minflt}, timestamp)
-			if err == nil {
-				output <- y
-			}
-		}
-
-	}
-}
-
-func (m *SelfCollector) Close() {
-	m.init = false
-}

collectors/selfMetric.md

@@ -1,34 +0,0 @@
-## `self` collector
-
-```json
-  "self": {
-    "read_mem_stats" : true,
-    "read_goroutines" : true,
-    "read_cgo_calls" : true,
-    "read_rusage" : true
-  }
-```
-
-The `self` collector reads the data from the `runtime` and `syscall` packages, so monitors the execution of the cc-metric-collector itself.
-
-Metrics:
-* If `read_mem_stats == true`:
-  * `total_alloc`: The metric reports cumulative bytes allocated for heap objects.
-  * `heap_alloc`: The metric reports bytes of allocated heap objects.
-  * `heap_sys`: The metric reports bytes of heap memory obtained from the OS.
-  * `heap_idle`: The metric reports bytes in idle (unused) spans.
-  * `heap_inuse`: The metric reports bytes in in-use spans.
-  * `heap_released`: The metric reports bytes of physical memory returned to the OS.
-  * `heap_objects`: The metric reports the number of allocated heap objects.
-* If `read_goroutines == true`:
-  * `num_goroutines`: The metric reports the number of goroutines that currently exist.
-* If `read_cgo_calls == true`:
-  * `num_cgo_calls`: The metric reports the number of cgo calls made by the current process.
-* If `read_rusage == true`:
-  * `rusage_user_time`: The metric reports the amount of time that this process has been scheduled in user mode.
-  * `rusage_system_time`: The metric reports the amount of time that this process has been scheduled in kernel mode.
-  * `rusage_vol_ctx_switch`: The metric reports the amount of voluntary context switches.
-  * `rusage_invol_ctx_switch`: The metric reports the amount of involuntary context switches.
-  * `rusage_signals`: The metric reports the number of signals received.
-  * `rusage_major_pgfaults`: The metric reports the number of major faults the process has made which have required loading a memory page from disk.
-  * `rusage_minor_pgfaults`: The metric reports the number of minor faults the process has made which have not required loading a memory page from disk.

collectors/tempMetric.go

@@ -3,14 +3,14 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"os"
+	"io/ioutil"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 // See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html
@@ -50,7 +50,6 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 	}
 
 	m.name = "TempCollector"
-	m.parallel = true
 	m.setup()
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
@@ -83,14 +82,14 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 
 		// sensor name
 		nameFile := filepath.Join(filepath.Dir(file), "name")
-		name, err := os.ReadFile(nameFile)
+		name, err := ioutil.ReadFile(nameFile)
 		if err == nil {
 			sensor.name = strings.TrimSpace(string(name))
 		}
 
 		// sensor label
 		labelFile := strings.TrimSuffix(file, "_input") + "_label"
-		label, err := os.ReadFile(labelFile)
+		label, err := ioutil.ReadFile(labelFile)
 		if err == nil {
 			sensor.label = strings.TrimSpace(string(label))
 		}
@@ -117,10 +116,6 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		}
 
 		// Sensor file
-		_, err = os.ReadFile(file)
-		if err != nil {
-			continue
-		}
 		sensor.file = file
 
 		// Sensor tags
@@ -139,7 +134,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		// max temperature
 		if m.config.ReportMaxTemp {
 			maxTempFile := strings.TrimSuffix(file, "_input") + "_max"
-			if buffer, err := os.ReadFile(maxTempFile); err == nil {
+			if buffer, err := ioutil.ReadFile(maxTempFile); err == nil {
 				if x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64); err == nil {
 					sensor.maxTempName = strings.Replace(sensor.metricName, "temp", "max_temp", 1)
 					sensor.maxTemp = x / 1000
@@ -150,7 +145,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		// critical temperature
 		if m.config.ReportCriticalTemp {
 			criticalTempFile := strings.TrimSuffix(file, "_input") + "_crit"
-			if buffer, err := os.ReadFile(criticalTempFile); err == nil {
+			if buffer, err := ioutil.ReadFile(criticalTempFile); err == nil {
 				if x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64); err == nil {
 					sensor.critTempName = strings.Replace(sensor.metricName, "temp", "crit_temp", 1)
 					sensor.critTemp = x / 1000
@@ -175,7 +170,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 	for _, sensor := range m.sensors {
 		// Read sensor file
-		buffer, err := os.ReadFile(sensor.file)
+		buffer, err := ioutil.ReadFile(sensor.file)
 		if err != nil {
 			cclog.ComponentError(
 				m.name,

collectors/topprocsMetric.go

@@ -9,7 +9,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 const MAX_NUM_PROCS = 10
@@ -28,7 +28,6 @@ type TopProcsCollector struct {
 func (m *TopProcsCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "TopProcsCollector"
-	m.parallel = true
 	m.tags = map[string]string{"type": "node"}
 	m.meta = map[string]string{"source": m.name, "group": "TopProcs"}
 	if len(config) > 0 {

config.json

@@ -1,8 +1,8 @@
 {
-  "sinks": "./sinks.json",
+  "sinks": "sinks.json",
-  "collectors" : "./collectors.json",
+  "collectors" : "collectors.json",
-  "receivers" : "./receivers.json",
+  "receivers" : "receivers.json",
-  "router" : "./router.json",
+  "router" : "router.json",
-  "interval": "10s",
+  "interval": 10,
-  "duration": "1s"
+  "duration": 1
 }

docs/building.md

@@ -1,74 +0,0 @@
-# Building the cc-metric-collector
-
-In most cases, a simple `make` in the main folder is enough to get a `cc-metric-collector` binary. It is basically a `go build` but some collectors require additional tasks. There is currently no Golang interface to LIKWID, so it uses `cgo` to create bindings but `cgo` requires the LIKWID header files. Therefore, it checks whether LIKWID is installed and if not it downloads LIKWID and copies the headers.
-
-## System integration
-
-The main configuration settings for system integration are pre-defined in `scripts/cc-metric-collector.config`. The file contains the UNIX user and group used for execution, the PID file location and other settings. Adjust it accordingly and copy it to `/etc/default/cc-metric-collector`
-
-```bash
-$ install --mode 644 \
-          --owner $CC_USER \
-          --group $CC_GROUP \
-          scripts/cc-metric-collector.config /etc/default/cc-metric-collector
-$ edit /etc/default/cc-metric-collector
-```
-
-### SysVinit and similar
-
-If you are using a init system based in `/etc/init.d` daemons, you can use the sample `scripts/cc-metric-collector.init`. It reads the basic configuration from `/etc/default/cc-metric-collector`
-
-```bash
-$ install --mode 755 \
-          --owner $CC_USER \
-          --group $CC_GROUP \
-          scripts/cc-metric-collector.init /etc/init.d/cc-metric-collector
-```
-
-### Systemd
-
-If you are using `systemd` as init system, you can use the sample systemd service file `scripts/cc-metric-collector.service`, the configuration file `scripts/cc-metric-collector.config`.
-
-```bash
-$ install --mode 644  \
-          --owner $CC_USER \
-          --group $CC_GROUP \
-           scripts/cc-metric-collector.service /etc/systemd/system/cc-metric-collector.service
-$ systemctl enable cc-metric-collector
-```
-
-## Packaging
-
-### RPM
-
-In order to get a RPM packages for cc-metric-collector, just use:
-
-```bash
-$ make RPM
-```
-
-It uses the RPM SPEC file `scripts/cc-metric-collector.spec` and requires the RPM tools (`rpm` and `rpmspec`) and `git`.
-
-### DEB
-
-In order to get very simple Debian packages for cc-metric-collector, just use:
-
-```bash
-$ make DEB
-```
-
-It uses the DEB control file `scripts/cc-metric-collector.control` and requires `dpkg-deb`, `awk`, `sed` and `git`. It creates only a binary deb package.
-
-_This option is not well tested and therefore experimental_
-
-### Customizing RPMs or DEB packages
-
-If you want to customize the RPMs or DEB packages for your local system, use the following workflow.
-
-- (if there is already a fork in the private account, delete it and wait until Github realizes the deletion)
-- Fork the cc-metric-collector repository (if Github hasn't realized it, it creates a fork named cc-metric-collector2)
-- Go to private cc-metric-collector repository and enable Github Actions
-- Do changes to the scripts, code, ... Commit and push your changes.
-- Tag the new commit with `v0.x.y-<myversion>` (`git tag v0.x.y-<myversion>`)
-- Push tags to repository (`git push --tags`)
-- Wait until the Release action finishes. It creates fresh RPMs and DEBs in your private repository on the Releases page.

docs/introduction.md

@@ -1,23 +0,0 @@
-# The ClusterCockpit Project
-
-The ClusterCockpit project is a joined project of computing centers in Europe to set up a cluster monitoring stack for small to mid-sized computing centers under the lead of NHR@FAU.
-
-# The ClusterCockpit Stack
-
-In cluster environment, there are commonly a lot of systems dedicated for computation, backend servers for file systems and frontend servers for the user interaction and cluster control. The ClusterCockpit Stack is mainly used for monitoring the compute systems with some interaction to the frontend servers. It consists of multiple components:
-
-- cc-metric-collector: Monitor resource usage on the compute systems
-- cc-metric-store: In-memory database
-- cc-backend & cc-frontend: The web-based visualizer
-
-# CC Metric Collector
-
-The CC Metric Collector project was started to provide a useful set of metrics for HPC and data science related compute systems. It runs as a system daemon and gathers system data periodically to forward the metrics to one or more databases. One of the provided backends can be used for the cc-metric-store but many others exist like InfluxDB time-series databases, the Ganglia Monitoring System or the Prometheus Monitoring System.
-
-The data is gathered by so-called "Collectors", forwarded to an internal router for on-the-fly manipulation (tagging, aggregation, ...) which pushes the metrics to the different metric writers called "Sinks". There is a forth component, the "Receivers", which receive data through some networking system like a HTTP server at any time.
-
-# CC Metric Store
-The CC Metric Store is a data management system with short-term in-memory and long-term file-base metric storage.
-
-# CC Backend and CC Frontend
-The CC Backend and Frontend form together the web interface for ClusterCockpit.

go.mod

@@ -1,41 +1,16 @@
 module github.com/ClusterCockpit/cc-metric-collector
 
-go 1.20
+go 1.16
 
 require (
-	github.com/ClusterCockpit/cc-units v0.4.0
+	github.com/NVIDIA/go-nvml v0.11.6-0
-	github.com/ClusterCockpit/go-rocm-smi v0.3.0
+	github.com/PaesslerAG/gval v1.1.2
-	github.com/NVIDIA/go-nvml v0.12.0-2
+	github.com/gorilla/mux v1.8.0
-	github.com/PaesslerAG/gval v1.2.2
+	github.com/influxdata/influxdb-client-go/v2 v2.8.1
-	github.com/fsnotify/fsnotify v1.7.0
-	github.com/gorilla/mux v1.8.1
-	github.com/influxdata/influxdb-client-go/v2 v2.13.0
 	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
-	github.com/influxdata/line-protocol/v2 v2.2.1
+	github.com/nats-io/nats-server/v2 v2.8.0 // indirect
-	github.com/nats-io/nats.go v1.32.0
+	github.com/nats-io/nats.go v1.14.0
-	github.com/prometheus/client_golang v1.18.0
+	github.com/prometheus/client_golang v1.12.1
-	github.com/stmcginnis/gofish v0.15.0
+	github.com/stmcginnis/gofish v0.13.0
-	github.com/tklauser/go-sysconf v0.3.13
+	golang.org/x/sys v0.0.0-20220412211240-33da011f77ad
-	golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
-	golang.org/x/exp v0.0.0-20240119083558-1b970713d09a
-	golang.org/x/sys v0.16.0
-)
-
-require (
-	github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
-	github.com/beorn7/perks v1.0.1 // indirect
-	github.com/cespare/xxhash/v2 v2.2.0 // indirect
-	github.com/google/uuid v1.5.0 // indirect
-	github.com/klauspost/compress v1.17.4 // indirect
-	github.com/nats-io/nkeys v0.4.7 // indirect
-	github.com/nats-io/nuid v1.0.1 // indirect
-	github.com/oapi-codegen/runtime v1.1.1 // indirect
-	github.com/prometheus/client_model v0.5.0 // indirect
-	github.com/prometheus/common v0.46.0 // indirect
-	github.com/prometheus/procfs v0.12.0 // indirect
-	github.com/shopspring/decimal v1.3.1 // indirect
-	github.com/tklauser/numcpus v0.7.0 // indirect
-	golang.org/x/crypto v0.18.0 // indirect
-	golang.org/x/net v0.20.0 // indirect
-	google.golang.org/protobuf v1.32.0 // indirect
 )

go.sum

@@ -1,116 +1,145 @@
-github.com/ClusterCockpit/cc-units v0.4.0 h1:zP5DOu99GmErW0tCDf0gcLrlWt42RQ9dpoONEOh4cI0=
+github.com/NVIDIA/go-nvml v0.11.1-0 h1:XHSz3zZKC4NCP2ja1rI7++DXFhA+uDhdYa3MykCTGHY=
-github.com/ClusterCockpit/cc-units v0.4.0/go.mod h1:3S3PAhAayS3pbgcT4q9Vn9VJw22Op51X0YimtG77zBw=
+github.com/NVIDIA/go-nvml v0.11.1-0/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
-github.com/ClusterCockpit/go-rocm-smi v0.3.0 h1:1qZnSpG7/NyLtc7AjqnUL9Jb8xtqG1nMVgp69rJfaR8=
+github.com/PaesslerAG/gval v1.1.2 h1:EROKxV4/fAKWb0Qoj7NOxmHZA7gcpjOV9XgiRZMRCUU=
-github.com/ClusterCockpit/go-rocm-smi v0.3.0/go.mod h1:+I3UMeX3OlizXDf1WpGD43W4KGZZGVSGmny6rTeOnWA=
+github.com/PaesslerAG/gval v1.1.2/go.mod h1:Fa8gfkCmUsELXgayr8sfL/sw+VzCVoa03dcOcR/if2w=
-github.com/NVIDIA/go-nvml v0.11.6-0/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
-github.com/NVIDIA/go-nvml v0.12.0-2 h1:Sg239yy7jmopu/cuvYauoMj9fOpcGMngxVxxS1EBXeY=
-github.com/NVIDIA/go-nvml v0.12.0-2/go.mod h1:7ruy85eOM73muOc/I37euONSwEyFqZsv5ED9AogD4G0=
-github.com/PaesslerAG/gval v1.2.2 h1:Y7iBzhgE09IGTt5QgGQ2IdaYYYOU134YGHBThD+wm9E=
-github.com/PaesslerAG/gval v1.2.2/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac=
-github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI=
 github.com/PaesslerAG/jsonpath v0.1.0/go.mod h1:4BzmtoM/PI8fPO4aQGIusjGxGir2BzcV0grWtFzq1Y8=
-github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk=
+github.com/cyberdelia/templates v0.0.0-20141128023046-ca7fffd4298c/go.mod h1:GyV+0YP4qX0UQ7r2MoYZ+AvYDp12OF5yg4q8rGnyNh4=
-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/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 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
-github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-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/frankban/quicktest v1.11.0/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
+github.com/deepmap/oapi-codegen v1.8.2 h1:SegyeYGcdi0jLLrpbCMoJxnUUn8GBXHsvr4rbzjuhfU=
-github.com/frankban/quicktest v1.11.2/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
+github.com/deepmap/oapi-codegen v1.8.2/go.mod h1:YLgSKSDv/bZQB7N4ws6luhozi3cEdRktEqrX88CvjIw=
-github.com/frankban/quicktest v1.13.0 h1:yNZif1OkDfNoDfb9zZa9aXIpejNR4F23Wely0c+Qdqk=
+github.com/dgrijalva/jwt-go v3.2.0+incompatible/go.mod h1:E3ru+11k8xSBh+hMPgOLZmtrrCbhqsmaPHjLKYnJCaQ=
-github.com/frankban/quicktest v1.13.0/go.mod h1:qLE0fzW0VuyUAJgPU19zByoIr0HtCHN/r/VLSOOIySU=
+github.com/getkin/kin-openapi v0.61.0/go.mod h1:7Yn5whZr5kJi6t+kShccXS8ae1APpYTW6yheSwk8Yi4=
-github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
+github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
-github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
+github.com/go-chi/chi/v5 v5.0.0/go.mod h1:BBug9lr0cqtdAhsu6R4AAdvufI0/XBzAQSsUqJpoZOs=
-github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/go-openapi/jsonpointer v0.19.5/go.mod h1:Pl9vOtqEWErmShwVjC8pYs9cog34VGT37dQOVbmoatg=
+github.com/go-openapi/swag v0.19.5/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
+github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
+github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA=
+github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs=
+github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
+github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
+github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
+github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
+github.com/golang/protobuf v1.5.2 h1:ROPKBNFfQgOUMifHyP+KYbvpjbdoFNs+aK7DXlji0Tw=
+github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
+github.com/golang/snappy v0.0.3/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
+github.com/golangci/lint-1 v0.0.0-20181222135242-d2cdd8c08219/go.mod h1:/X8TswGSh1pIozq4ZwCfxS0WA5JGXguxk94ar/4c87Y=
+github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.4.0/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 v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
+github.com/gorilla/mux v1.8.0/go.mod h1:DVbg23sWSpFRCP0SfiEN6jmj59UnW/n46BH5rLB71So=
-github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/influxdata/influxdb-client-go/v2 v2.7.0 h1:QgP5mlBE9sGnzplpnf96pr+p7uqlIlL4W2GAP3n+XZg=
-github.com/google/uuid v1.5.0 h1:1p67kYwdtXjb0gL0BPiP1Av9wiZPo5A8z2cWkTZ+eyU=
+github.com/influxdata/influxdb-client-go/v2 v2.7.0/go.mod h1:Y/0W1+TZir7ypoQZYd2IrnVOKB3Tq6oegAQeSVN/+EU=
-github.com/google/uuid v1.5.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/influxdata/line-protocol v0.0.0-20200327222509-2487e7298839/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
-github.com/gorilla/mux v1.8.1 h1:TuBL49tXwgrFYWhqrNgrUNEY92u81SPhu7sTdzQEiWY=
-github.com/gorilla/mux v1.8.1/go.mod h1:AKf9I4AEqPTmMytcMc0KkNouC66V3BtZ4qD5fmWSiMQ=
-github.com/influxdata/influxdb-client-go/v2 v2.13.0 h1:ioBbLmR5NMbAjP4UVA5r9b5xGjpABD7j65pI8kFphDM=
-github.com/influxdata/influxdb-client-go/v2 v2.13.0/go.mod h1:k+spCbt9hcvqvUiz0sr5D8LolXHqAAOfPw9v/RIRHl4=
 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/klauspost/compress v1.13.4 h1:0zhec2I8zGnjWcKyLl6i3gPqKANCCn5e9xmviEEeX6s=
-github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937 h1:MHJNQ+p99hFATQm6ORoLmpUCF7ovjwEFshs/NHzAbig=
+github.com/klauspost/compress v1.13.4/go.mod h1:8dP1Hq4DHOhN9w426knH3Rhby4rFm6D8eO+e+Dq5Gzg=
-github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937/go.mod h1:BKR9c0uHSmRgM/se9JhFHtTT7JTO67X23MtKMHtZcpo=
+github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
-github.com/influxdata/line-protocol/v2 v2.0.0-20210312151457-c52fdecb625a/go.mod h1:6+9Xt5Sq1rWx+glMgxhcg2c0DUaehK+5TDcPZ76GypY=
+github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
-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/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
-github.com/klauspost/compress v1.17.4 h1:Ej5ixsIri7BrIjBkRZLTo6ghwrEtHFk7ijlczPW4fZ4=
-github.com/klauspost/compress v1.17.4/go.mod h1:/dCuZOvVtNoHsyb+cuJD3itjs3NbnF6KH9zAO4BDxPM=
-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 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
 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/labstack/echo/v4 v4.2.1/go.mod h1:AA49e0DZ8kk5jTOOCKNuPR6oTnBS0dYiM4FW1e6jwpg=
-github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/labstack/gommon v0.3.0/go.mod h1:MULnywXg0yavhxWKc+lOruYdAhDwPK9wf0OL7NoOu+k=
-github.com/nats-io/nats.go v1.32.0 h1:Bx9BZS+aXYlxW08k8Gd3yR2s73pV5XSoAQUyp1Kwvp0=
+github.com/mailru/easyjson v0.0.0-20190614124828-94de47d64c63/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
-github.com/nats-io/nats.go v1.32.0/go.mod h1:Ubdu4Nh9exXdSz0RVWRFBbRfrbSxOYd26oF0wkWclB8=
+github.com/mailru/easyjson v0.0.0-20190626092158-b2ccc519800e/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
-github.com/nats-io/nkeys v0.4.7 h1:RwNJbbIdYCoClSDNY7QVKZlyb/wfT6ugvFCiKy6vDvI=
+github.com/matryer/moq v0.0.0-20190312154309-6cfb0558e1bd/go.mod h1:9ELz6aaclSIGnZBoaSLZ3NAl1VTufbOrXBPvtcy6WiQ=
-github.com/nats-io/nkeys v0.4.7/go.mod h1:kqXRgRDPlGy7nGaEDMuYzmiJCIAAWDK0IMBtDmGD0nc=
+github.com/mattn/go-colorable v0.1.2/go.mod h1:U0ppj6V5qS13XJ6of8GYAs25YV2eR4EVcfRqFIhoBtE=
+github.com/mattn/go-colorable v0.1.7/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
+github.com/mattn/go-colorable v0.1.8/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
+github.com/mattn/go-isatty v0.0.8/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
+github.com/mattn/go-isatty v0.0.9/go.mod h1:YNRxwqDuOph6SZLI9vUUz6OYw3QyUt7WiY2yME+cCiQ=
+github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Kysco4FUpU=
+github.com/minio/highwayhash v1.0.1 h1:dZ6IIu8Z14VlC0VpfKofAhCy74wu/Qb5gcn52yWoz/0=
+github.com/minio/highwayhash v1.0.1/go.mod h1:BQskDq+xkJ12lmlUUi7U0M5Swg3EWR+dLTk+kldvVxY=
+github.com/nats-io/jwt/v2 v2.2.1-0.20220113022732-58e87895b296 h1:vU9tpM3apjYlLLeY23zRWJ9Zktr5jp+mloR942LEOpY=
+github.com/nats-io/jwt/v2 v2.2.1-0.20220113022732-58e87895b296/go.mod h1:0tqz9Hlu6bCBFLWAASKhE5vUA4c24L9KPUUgvwumE/k=
+github.com/nats-io/nats-server/v2 v2.7.0 h1:UpqcAM93FI7AHlCyI2FD5QcV3QuHNCauQF2LBVU0238=
+github.com/nats-io/nats-server/v2 v2.7.0/go.mod h1:cjxtMhZsZovK1XS2iiapCduR8HuqB/YpFamL0qntIcw=
+github.com/nats-io/nats.go v1.13.1-0.20211122170419-d7c1d78a50fc h1:SHr4MUUZJ/fAC0uSm2OzWOJYsHpapmR86mpw7q1qPXU=
+github.com/nats-io/nats.go v1.13.1-0.20211122170419-d7c1d78a50fc/go.mod h1:BPko4oXsySz4aSWeFgOHLZs3G4Jq4ZAyE6/zMCxRT6w=
+github.com/nats-io/nkeys v0.3.0 h1:cgM5tL53EvYRU+2YLXIK0G2mJtK12Ft9oeooSZMA2G8=
+github.com/nats-io/nkeys v0.3.0/go.mod h1:gvUNGjVcM2IPr5rCsRsC6Wb3Hr2CQAm08dsxtV6A5y4=
 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/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
-github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmtpMYro=
+github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
-github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg=
+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 v1.18.0 h1:HzFfmkOzH5Q8L8G+kSJKUx5dtG87sewO+FoDDqP5Tbk=
-github.com/prometheus/client_golang v1.18.0/go.mod h1:T+GXkCk5wSJyOqMIzVgvvjFDlkOQntgjkJWKrN5txjA=
-github.com/prometheus/client_model v0.5.0 h1:VQw1hfvPvk3Uv6Qf29VrPF32JB6rtbgI6cYPYQjL0Qw=
-github.com/prometheus/client_model v0.5.0/go.mod h1:dTiFglRmd66nLR9Pv9f0mZi7B7fk5Pm3gvsjB5tr+kI=
-github.com/prometheus/common v0.46.0 h1:doXzt5ybi1HBKpsZOL0sSkaNHJJqkyfEWZGGqqScV0Y=
-github.com/prometheus/common v0.46.0/go.mod h1:Tp0qkxpb9Jsg54QMe+EAmqXkSV7Evdy1BTn+g2pa/hQ=
-github.com/prometheus/procfs v0.12.0 h1:jluTpSng7V9hY0O2R9DzzJHYb2xULk9VTR1V1R/k6Bo=
-github.com/prometheus/procfs v0.12.0/go.mod h1:pcuDEFsWDnvcgNzo4EEweacyhjeA9Zk3cnaOZAZEfOo=
-github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
-github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
-github.com/shopspring/decimal v1.3.1 h1:2Usl1nmF/WZucqkFZhnfFYxxxu8LG21F6nPQBE5gKV8=
-github.com/shopspring/decimal v1.3.1/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
-github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
-github.com/stmcginnis/gofish v0.15.0 h1:8TG41+lvJk/0Nf8CIIYErxbMlQUy80W0JFRZP3Ld82A=
-github.com/stmcginnis/gofish v0.15.0/go.mod h1:BLDSFTp8pDlf/xDbLZa+F7f7eW0E/CHCboggsu8CznI=
 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/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
-github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
-github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
+github.com/stretchr/testify v1.5.1 h1:nOGnQDM7FYENwehXlg/kFVnos3rEvtKTjRvOWSzb6H4=
-github.com/stretchr/testify v1.8.4 h1:CcVxjf3Q8PM0mHUKJCdn+eZZtm5yQwehR5yeSVQQcUk=
+github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
-github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
+github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
-github.com/tklauser/go-sysconf v0.3.13 h1:GBUpcahXSpR2xN01jhkNAbTLRk2Yzgggk8IM08lq3r4=
+github.com/valyala/fasttemplate v1.0.1/go.mod h1:UQGH1tvbgY+Nz5t2n7tXsz52dQxojPUpymEIMZ47gx8=
-github.com/tklauser/go-sysconf v0.3.13/go.mod h1:zwleP4Q4OehZHGn4CYZDipCgg9usW5IJePewFCGVEa0=
+github.com/valyala/fasttemplate v1.2.1/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
-github.com/tklauser/numcpus v0.7.0 h1:yjuerZP127QG9m5Zh/mSO4wqurYil27tHrqwRoRjpr4=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
-github.com/tklauser/numcpus v0.7.0/go.mod h1:bb6dMVcj8A42tSE7i32fsIUCbQNllK5iDguyOZRUzAY=
+golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
-golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1 h1:P7S/GeHBAFEZIYp0ePPs2kHXoazz8q2KsyxHyQVGCJg=
+golang.org/x/crypto v0.0.0-20200820211705-5c72a883971a/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
-golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1/go.mod h1:9CWpnTUmlQkfdpdutA1nNf4iE5lAVt3QZOu0Z6hahBE=
+golang.org/x/crypto v0.0.0-20201221181555-eec23a3978ad/go.mod h1:jdWPYTVW3xRLrWPugEBEK3UY2ZEsg3UU495nc5E+M+I=
-golang.org/x/crypto v0.18.0 h1:PGVlW0xEltQnzFZ55hkuX5+KLyrMYhHld1YHO4AKcdc=
+golang.org/x/crypto v0.0.0-20210314154223-e6e6c4f2bb5b/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
-golang.org/x/crypto v0.18.0/go.mod h1:R0j02AL6hcrfOiy9T4ZYp/rcWeMxM3L6QYxlOuEG1mg=
+golang.org/x/crypto v0.0.0-20220112180741-5e0467b6c7ce h1:Roh6XWxHFKrPgC/EQhVubSAGQ6Ozk6IdxHSzt1mR0EI=
-golang.org/x/exp v0.0.0-20240119083558-1b970713d09a h1:Q8/wZp0KX97QFTc2ywcOE0YRjZPVIx+MXInMzdvQqcA=
+golang.org/x/crypto v0.0.0-20220112180741-5e0467b6c7ce/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
-golang.org/x/exp v0.0.0-20240119083558-1b970713d09a/go.mod h1:idGWGoKP1toJGkd5/ig9ZLuPcZBC3ewk7SzmH0uou08=
+golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
-golang.org/x/net v0.20.0 h1:aCL9BSgETF1k+blQaYUBx9hJ9LOGP3gAVemcZlf1Kpo=
+golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
-golang.org/x/net v0.20.0/go.mod h1:z8BVo6PvndSri0LbOE3hAn0apkU+1YvI6E70E9jsnvY=
+golang.org/x/net v0.0.0-20200822124328-c89045814202/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
-golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/net v0.0.0-20210119194325-5f4716e94777/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/sys v0.16.0 h1:xWw16ngr6ZMtmxDyKyIgsE93KNKz5HKmMa3b8ALHidU=
+golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/sys v0.16.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2 h1:CIJ76btIcR3eFI5EgSo6k1qKw9KJexJuRLI9G7Hp5wE=
+golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sys v0.0.0-20190130150945-aca44879d564/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190813064441-fde4db37ae7a/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200223170610-d5e6a3e2c0ae/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200826173525-f9321e4c35a6/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220111092808-5a964db01320/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220114195835-da31bd327af9 h1:XfKQ4OlFl8okEOr5UvAqFRVj8pY/4yfcXrddB8qAbU0=
+golang.org/x/sys v0.0.0-20220114195835-da31bd327af9/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+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 v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/time v0.0.0-20201208040808-7e3f01d25324/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
+golang.org/x/time v0.0.0-20210220033141-f8bda1e9f3ba/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
+golang.org/x/time v0.0.0-20211116232009-f0f3c7e86c11 h1:GZokNIeuVkl3aZHJchRrr13WCsols02MLUcz1U9is6M=
+golang.org/x/time v0.0.0-20211116232009-f0f3c7e86c11/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
+golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20191125144606-a911d9008d1f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-google.golang.org/protobuf v1.32.0 h1:pPC6BG5ex8PDFnkbrGU3EixyhKcQ2aDuBS36lqK/C7I=
+google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
-google.golang.org/protobuf v1.32.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
+google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
+google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
+google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE=
+google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
+google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
+google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
+google.golang.org/protobuf v1.27.1 h1:SnqbnDw1V7RiZcXPx5MEeqPv2s79L9i7BJUlG/+RurQ=
+google.golang.org/protobuf v1.27.1/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
+gopkg.in/Knetic/govaluate.v2 v2.3.0 h1:naJVc9CZlWA8rC8f5mvECJD7jreTrn7FvGXjBthkHJQ=
+gopkg.in/Knetic/govaluate.v2 v2.3.0/go.mod h1:NW0gr10J8s7aNghEg6uhdxiEaBvc0+8VgJjVViHUKp4=
 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 v1.0.0-20180628173108-788fd7840127 h1:qIbj1fsPNlZgppZ+VLlY7N33q108Sa+fhmuc+sWQYwY=
-gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
-gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v2 v2.3.0 h1:clyUAQHOM3G0M3f5vQj7LuJrETvjVot3Z5el9nffUtU=
-gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=

internal/ccMetric/README.md

@@ -0,0 +1,32 @@
+# ClusterCockpit metrics
+
+As described in the [ClusterCockpit specifications](https://github.com/ClusterCockpit/cc-specifications), the whole ClusterCockpit stack uses metrics in the InfluxDB line protocol format. This is also the input and output format for the ClusterCockpit Metric Collector but internally it uses an extended format while processing, named CCMetric.
+
+It is basically a copy of the [InfluxDB line protocol](https://github.com/influxdata/line-protocol) `MutableMetric` interface with one extension. Besides the tags and fields, it contains a list of meta information (re-using the `Tag` structure of the original protocol):
+
+```golang
+type ccMetric struct {
+    name   string            // same as
+    tags   []*influx.Tag     // original
+    fields []*influx.Field   // Influx
+    tm     time.Time         // line-protocol
+    meta   []*influx.Tag
+}
+
+type CCMetric interface {
+    influx.MutableMetric        // the same functions as defined by influx.MutableMetric
+    RemoveTag(key string)       // this is not published by the original influx.MutableMetric
+    Meta() map[string]string
+    MetaList() []*inlux.Tag
+    AddMeta(key, value string)
+    HasMeta(key string) bool
+    GetMeta(key string) (string, bool)
+    RemoveMeta(key string)
+}
+```
+
+The `CCMetric` interface provides the same functions as the `MutableMetric` like `{Add, Remove, Has}{Tag, Field}` and additionally provides `{Add, Remove, Has}Meta`.
+
+The InfluxDB protocol creates a new metric with `influx.New(name, tags, fields, time)` while CCMetric uses `ccMetric.New(name, tags, meta, fields, time)` where `tags` and `meta` are both of type `map[string]string`.
+
+You can copy a CCMetric with `FromMetric(other CCMetric) CCMetric`. If you get an `influx.Metric` from a function, like the line protocol parser, you can use `FromInfluxMetric(other influx.Metric) CCMetric` to get a CCMetric out of it (see `NatsReceiver` for an example).

internal/ccMetric/ccMetric.go

@@ -7,7 +7,6 @@ import (
 	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
 	write "github.com/influxdata/influxdb-client-go/v2/api/write"
 	lp "github.com/influxdata/line-protocol" // MIT license
-	"golang.org/x/exp/maps"
 )
 
 // Most functions are derived from github.com/influxdata/line-protocol/metric.go
@@ -51,7 +50,6 @@ type CCMetric interface {
 	GetField(key string) (value interface{}, ok bool) // Get a field addressed by its key
 	HasField(key string) (ok bool)                    // Check if a field key is present
 	RemoveField(key string)                           // Remove a field addressed by its key
-	String() string                                   // Return line-protocol like string
 }
 
 // String implements the stringer interface for data type ccMetric
@@ -65,11 +63,9 @@ func (m *ccMetric) String() string {
 // ToLineProtocol generates influxDB line protocol for data type ccMetric
 func (m *ccMetric) ToPoint(metaAsTags map[string]bool) (p *write.Point) {
 	p = influxdb2.NewPoint(m.name, m.tags, m.fields, m.tm)
-	for key, use_as_tag := range metaAsTags {
+	for key, ok1 := range metaAsTags {
-		if use_as_tag {
+		if val, ok2 := m.GetMeta(key); ok1 && ok2 {
-			if value, ok := m.GetMeta(key); ok {
+			p.AddTag(key, val)
-				p.AddTag(key, value)
-			}
 		}
 	}
 	return p
@@ -196,13 +192,19 @@ func New(
 ) (CCMetric, error) {
 	m := &ccMetric{
 		name:   name,
-		tags:   maps.Clone(tags),
+		tags:   make(map[string]string, len(tags)),
-		meta:   maps.Clone(meta),
+		meta:   make(map[string]string, len(meta)),
 		fields: make(map[string]interface{}, len(fields)),
 		tm:     tm,
 	}
 
-	// deep copy fields
+	// deep copy tags, meta data tags and fields
+	for k, v := range tags {
+		m.tags[k] = v
+	}
+	for k, v := range meta {
+		m.meta[k] = v
+	}
 	for k, v := range fields {
 		v := convertField(v)
 		if v == nil {
@@ -215,15 +217,26 @@ func New(
 }
 
 // FromMetric copies the metric <other>
-func FromMetric(other CCMetric) CCMetric {
+func FromMetric(other ccMetric) CCMetric {
-
+	m := &ccMetric{
-	return &ccMetric{
 		name:   other.Name(),
-		tags:   maps.Clone(other.Tags()),
+		tags:   make(map[string]string, len(other.tags)),
-		meta:   maps.Clone(other.Meta()),
+		meta:   make(map[string]string, len(other.meta)),
-		fields: maps.Clone(other.Fields()),
+		fields: make(map[string]interface{}, len(other.fields)),
 		tm:     other.Time(),
 	}
+
+	// deep copy tags, meta data tags and fields
+	for key, value := range other.tags {
+		m.tags[key] = value
+	}
+	for key, value := range other.meta {
+		m.meta[key] = value
+	}
+	for key, value := range other.fields {
+		m.fields[key] = value
+	}
+	return m
 }
 
 // FromInfluxMetric copies the influxDB line protocol metric <other>
@@ -247,10 +260,8 @@ func FromInfluxMetric(other lp.Metric) CCMetric {
 }
 
 // convertField converts data types of fields by the following schemata:
-//
+//                         *float32, *float64,                      float32, float64 -> float64
-//	                       *float32, *float64,                      float32, float64 -> float64
+//  *int,  *int8,  *int16,   *int32,   *int64,  int,  int8,  int16,   int32,   int64 ->   int64
-//	*int,  *int8,  *int16,   *int32,   *int64,  int,  int8,  int16,   int32,   int64 ->   int64
-//
 // *uint, *uint8, *uint16,  *uint32,  *uint64, uint, uint8, uint16,  uint32,  uint64 ->  uint64
 // *[]byte, *string,                           []byte, string                        -> string
 // *bool,                                      bool                                  -> bool

internal/ccTopology/ccTopology.go

@@ -0,0 +1,427 @@
+package ccTopology
+
+import (
+	"fmt"
+	"io/ioutil"
+	"log"
+	"os"
+	"path/filepath"
+	"regexp"
+	"strconv"
+	"strings"
+
+	cclogger "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+)
+
+const SYSFS_NUMABASE = `/sys/devices/system/node`
+const SYSFS_CPUBASE = `/sys/devices/system/cpu`
+const PROCFS_CPUINFO = `/proc/cpuinfo`
+
+// intArrayContains scans an array of ints if the value str is present in the array
+// If the specified value is found, the corresponding array index is returned.
+// The bool value is used to signal success or failure
+func intArrayContains(array []int, str int) (int, bool) {
+	for i, a := range array {
+		if a == str {
+			return i, true
+		}
+	}
+	return -1, false
+}
+
+func fileToInt(path string) int {
+	buffer, err := ioutil.ReadFile(path)
+	if err != nil {
+		log.Print(err)
+		cclogger.ComponentError("ccTopology", "Reading", path, ":", err.Error())
+		return -1
+	}
+	sbuffer := strings.Replace(string(buffer), "\n", "", -1)
+	var id int64
+	//_, err = fmt.Scanf("%d", sbuffer, &id)
+	id, err = strconv.ParseInt(sbuffer, 10, 32)
+	if err != nil {
+		cclogger.ComponentError("ccTopology", "Parsing", path, ":", sbuffer, err.Error())
+		return -1
+	}
+	return int(id)
+}
+
+func SocketList() []int {
+	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
+	if err != nil {
+		log.Print(err)
+		return nil
+	}
+	ll := strings.Split(string(buffer), "\n")
+	var packs []int
+	for _, line := range ll {
+		if strings.HasPrefix(line, "physical id") {
+			lv := strings.Fields(line)
+			id, err := strconv.ParseInt(lv[3], 10, 32)
+			if err != nil {
+				log.Print(err)
+				return packs
+			}
+			_, found := intArrayContains(packs, int(id))
+			if !found {
+				packs = append(packs, int(id))
+			}
+		}
+	}
+	return packs
+}
+
+func CpuList() []int {
+	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
+	if err != nil {
+		log.Print(err)
+		return nil
+	}
+	ll := strings.Split(string(buffer), "\n")
+	cpulist := make([]int, 0)
+	for _, line := range ll {
+		if strings.HasPrefix(line, "processor") {
+			lv := strings.Fields(line)
+			id, err := strconv.ParseInt(lv[2], 10, 32)
+			if err != nil {
+				log.Print(err)
+				return cpulist
+			}
+			_, found := intArrayContains(cpulist, int(id))
+			if !found {
+				cpulist = append(cpulist, int(id))
+			}
+		}
+	}
+	return cpulist
+}
+
+func CoreList() []int {
+	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
+	if err != nil {
+		log.Print(err)
+		return nil
+	}
+	ll := strings.Split(string(buffer), "\n")
+	corelist := make([]int, 0)
+	for _, line := range ll {
+		if strings.HasPrefix(line, "core id") {
+			lv := strings.Fields(line)
+			id, err := strconv.ParseInt(lv[3], 10, 32)
+			if err != nil {
+				log.Print(err)
+				return corelist
+			}
+			_, found := intArrayContains(corelist, int(id))
+			if !found {
+				corelist = append(corelist, int(id))
+			}
+		}
+	}
+	return corelist
+}
+
+func NumaNodeList() []int {
+	numaList := make([]int, 0)
+	globPath := filepath.Join(string(SYSFS_NUMABASE), "node*")
+	regexPath := filepath.Join(string(SYSFS_NUMABASE), "node(\\d+)")
+	regex := regexp.MustCompile(regexPath)
+	files, err := filepath.Glob(globPath)
+	if err != nil {
+		cclogger.ComponentError("CCTopology", "NumaNodeList", err.Error())
+	}
+	for _, f := range files {
+		if !regex.MatchString(f) {
+			continue
+		}
+		finfo, err := os.Lstat(f)
+		if err != nil {
+			continue
+		}
+		if !finfo.IsDir() {
+			continue
+		}
+		matches := regex.FindStringSubmatch(f)
+		if len(matches) == 2 {
+			id, err := strconv.Atoi(matches[1])
+			if err == nil {
+				if _, found := intArrayContains(numaList, id); !found {
+					numaList = append(numaList, id)
+				}
+			}
+		}
+
+	}
+	return numaList
+}
+
+func DieList() []int {
+	cpulist := CpuList()
+	dielist := make([]int, 0)
+	for _, c := range cpulist {
+		diepath := filepath.Join(string(SYSFS_CPUBASE), fmt.Sprintf("cpu%d", c), "topology/die_id")
+		dieid := fileToInt(diepath)
+		if dieid > 0 {
+			_, found := intArrayContains(dielist, int(dieid))
+			if !found {
+				dielist = append(dielist, int(dieid))
+			}
+		}
+	}
+	if len(dielist) > 0 {
+		return dielist
+	}
+	return SocketList()
+}
+
+type CpuEntry struct {
+	Cpuid      int
+	SMT        int
+	Core       int
+	Socket     int
+	Numadomain int
+	Die        int
+}
+
+func CpuData() []CpuEntry {
+
+	fileToInt := func(path string) int {
+		buffer, err := ioutil.ReadFile(path)
+		if err != nil {
+			log.Print(err)
+			//cclogger.ComponentError("ccTopology", "Reading", path, ":", err.Error())
+			return -1
+		}
+		sbuffer := strings.Replace(string(buffer), "\n", "", -1)
+		var id int64
+		//_, err = fmt.Scanf("%d", sbuffer, &id)
+		id, err = strconv.ParseInt(sbuffer, 10, 32)
+		if err != nil {
+			cclogger.ComponentError("ccTopology", "Parsing", path, ":", sbuffer, err.Error())
+			return -1
+		}
+		return int(id)
+	}
+	getCore := func(basepath string) int {
+		return fileToInt(fmt.Sprintf("%s/core_id", basepath))
+	}
+
+	getSocket := func(basepath string) int {
+		return fileToInt(fmt.Sprintf("%s/physical_package_id", basepath))
+	}
+
+	getDie := func(basepath string) int {
+		return fileToInt(fmt.Sprintf("%s/die_id", basepath))
+	}
+
+	getSMT := func(cpuid int, basepath string) int {
+		buffer, err := ioutil.ReadFile(fmt.Sprintf("%s/thread_siblings_list", basepath))
+		if err != nil {
+			cclogger.ComponentError("CCTopology", "CpuData:getSMT", err.Error())
+		}
+		threadlist := make([]int, 0)
+		sbuffer := strings.Replace(string(buffer), "\n", "", -1)
+		for _, x := range strings.Split(sbuffer, ",") {
+			id, err := strconv.ParseInt(x, 10, 32)
+			if err != nil {
+				cclogger.ComponentError("CCTopology", "CpuData:getSMT", err.Error())
+			}
+			threadlist = append(threadlist, int(id))
+		}
+		for i, x := range threadlist {
+			if x == cpuid {
+				return i
+			}
+		}
+		return 1
+	}
+
+	getNumaDomain := func(basepath string) int {
+		globPath := filepath.Join(basepath, "node*")
+		regexPath := filepath.Join(basepath, "node(\\d+)")
+		regex := regexp.MustCompile(regexPath)
+		files, err := filepath.Glob(globPath)
+		if err != nil {
+			cclogger.ComponentError("CCTopology", "CpuData:getNumaDomain", err.Error())
+		}
+		for _, f := range files {
+			finfo, err := os.Lstat(f)
+			if err == nil && finfo.IsDir() {
+				matches := regex.FindStringSubmatch(f)
+				if len(matches) == 2 {
+					id, err := strconv.Atoi(matches[1])
+					if err == nil {
+						return id
+					}
+				}
+			}
+		}
+		return 0
+	}
+
+	clist := make([]CpuEntry, 0)
+	for _, c := range CpuList() {
+		clist = append(clist, CpuEntry{Cpuid: c})
+	}
+	for i, centry := range clist {
+		centry.Socket = -1
+		centry.Numadomain = -1
+		centry.Die = -1
+		centry.Core = -1
+		// Set base directory for topology lookup
+		cpustr := fmt.Sprintf("cpu%d", centry.Cpuid)
+		base := filepath.Join("/sys/devices/system/cpu", cpustr)
+		topoBase := filepath.Join(base, "topology")
+
+		// Lookup CPU core id
+		centry.Core = getCore(topoBase)
+
+		// Lookup CPU socket id
+		centry.Socket = getSocket(topoBase)
+
+		// Lookup CPU die id
+		centry.Die = getDie(topoBase)
+		if centry.Die < 0 {
+			centry.Die = centry.Socket
+		}
+
+		// Lookup SMT thread id
+		centry.SMT = getSMT(centry.Cpuid, topoBase)
+
+		// Lookup NUMA domain id
+		centry.Numadomain = getNumaDomain(base)
+
+		// Update values in output list
+		clist[i] = centry
+	}
+	return clist
+}
+
+type CpuInformation struct {
+	NumHWthreads   int
+	SMTWidth       int
+	NumSockets     int
+	NumDies        int
+	NumCores       int
+	NumNumaDomains int
+}
+
+func CpuInfo() CpuInformation {
+	var c CpuInformation
+
+	smtList := make([]int, 0)
+	numaList := make([]int, 0)
+	dieList := make([]int, 0)
+	socketList := make([]int, 0)
+	coreList := make([]int, 0)
+	cdata := CpuData()
+	for _, d := range cdata {
+		if _, ok := intArrayContains(smtList, d.SMT); !ok {
+			smtList = append(smtList, d.SMT)
+		}
+		if _, ok := intArrayContains(numaList, d.Numadomain); !ok {
+			numaList = append(numaList, d.Numadomain)
+		}
+		if _, ok := intArrayContains(dieList, d.Die); !ok {
+			dieList = append(dieList, d.Die)
+		}
+		if _, ok := intArrayContains(socketList, d.Socket); !ok {
+			socketList = append(socketList, d.Socket)
+		}
+		if _, ok := intArrayContains(coreList, d.Core); !ok {
+			coreList = append(coreList, d.Core)
+		}
+	}
+	c.NumNumaDomains = len(numaList)
+	c.SMTWidth = len(smtList)
+	c.NumDies = len(dieList)
+	c.NumCores = len(coreList)
+	c.NumSockets = len(socketList)
+	c.NumHWthreads = len(cdata)
+	return c
+}
+
+func GetCpuSocket(cpuid int) int {
+	cdata := CpuData()
+	for _, d := range cdata {
+		if d.Cpuid == cpuid {
+			return d.Socket
+		}
+	}
+	return -1
+}
+
+func GetCpuNumaDomain(cpuid int) int {
+	cdata := CpuData()
+	for _, d := range cdata {
+		if d.Cpuid == cpuid {
+			return d.Numadomain
+		}
+	}
+	return -1
+}
+
+func GetCpuDie(cpuid int) int {
+	cdata := CpuData()
+	for _, d := range cdata {
+		if d.Cpuid == cpuid {
+			return d.Die
+		}
+	}
+	return -1
+}
+
+func GetCpuCore(cpuid int) int {
+	cdata := CpuData()
+	for _, d := range cdata {
+		if d.Cpuid == cpuid {
+			return d.Core
+		}
+	}
+	return -1
+}
+
+func GetSocketCpus(socket int) []int {
+	all := CpuData()
+	cpulist := make([]int, 0)
+	for _, d := range all {
+		if d.Socket == socket {
+			cpulist = append(cpulist, d.Cpuid)
+		}
+	}
+	return cpulist
+}
+
+func GetNumaDomainCpus(domain int) []int {
+	all := CpuData()
+	cpulist := make([]int, 0)
+	for _, d := range all {
+		if d.Numadomain == domain {
+			cpulist = append(cpulist, d.Cpuid)
+		}
+	}
+	return cpulist
+}
+
+func GetDieCpus(die int) []int {
+	all := CpuData()
+	cpulist := make([]int, 0)
+	for _, d := range all {
+		if d.Die == die {
+			cpulist = append(cpulist, d.Cpuid)
+		}
+	}
+	return cpulist
+}
+
+func GetCoreCpus(core int) []int {
+	all := CpuData()
+	cpulist := make([]int, 0)
+	for _, d := range all {
+		if d.Core == core {
+			cpulist = append(cpulist, d.Cpuid)
+		}
+	}
+	return cpulist
+}

internal/metricAggregator/metricAggregator.go

@@ -9,10 +9,10 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
+	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
 
 	"github.com/PaesslerAG/gval"
 )
@@ -121,12 +121,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 	vars["endtime"] = endtime
 	for _, f := range c.functions {
 		cclog.ComponentDebug("MetricCache", "COLLECT", f.Name, "COND", f.Condition)
-		var valuesFloat64 []float64
+		values := make([]float64, 0)
-		var valuesFloat32 []float32
-		var valuesInt []int
-		var valuesInt32 []int32
-		var valuesInt64 []int64
-		var valuesBool []bool
 		matches := make([]lp.CCMetric, 0)
 		for _, m := range metrics {
 			vars["metric"] = m
@@ -141,17 +136,17 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 				if valid {
 					switch x := v.(type) {
 					case float64:
-						valuesFloat64 = append(valuesFloat64, x)
+						values = append(values, x)
 					case float32:
-						valuesFloat32 = append(valuesFloat32, x)
 					case int:
-						valuesInt = append(valuesInt, x)
-					case int32:
-						valuesInt32 = append(valuesInt32, x)
 					case int64:
-						valuesInt64 = append(valuesInt64, x)
+						values = append(values, float64(x))
 					case bool:
-						valuesBool = append(valuesBool, x)
+						if x {
+							values = append(values, float64(1.0))
+						} else {
+							values = append(values, float64(0.0))
+						}
 					default:
 						cclog.ComponentError("MetricCache", "COLLECT ADD VALUE", v, "FAILED")
 					}
@@ -160,59 +155,13 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 			}
 		}
 		delete(vars, "metric")
-
+		cclog.ComponentDebug("MetricCache", "EVALUATE", f.Name, "METRICS", len(values), "CALC", f.Function)
-		// Check, that only values of one type were collected
+		vars["values"] = values
-		countValueTypes := 0
-		if len(valuesFloat64) > 0 {
-			countValueTypes += 1
-		}
-		if len(valuesFloat32) > 0 {
-			countValueTypes += 1
-		}
-		if len(valuesInt) > 0 {
-			countValueTypes += 1
-		}
-		if len(valuesInt32) > 0 {
-			countValueTypes += 1
-		}
-		if len(valuesInt64) > 0 {
-			countValueTypes += 1
-		}
-		if len(valuesBool) > 0 {
-			countValueTypes += 1
-		}
-		if countValueTypes > 1 {
-			cclog.ComponentError("MetricCache", "Collected values of different types")
-		}
-
-		var len_values int
-		switch {
-		case len(valuesFloat64) > 0:
-			vars["values"] = valuesFloat64
-			len_values = len(valuesFloat64)
-		case len(valuesFloat32) > 0:
-			vars["values"] = valuesFloat32
-			len_values = len(valuesFloat32)
-		case len(valuesInt) > 0:
-			vars["values"] = valuesInt
-			len_values = len(valuesInt)
-		case len(valuesInt32) > 0:
-			vars["values"] = valuesInt32
-			len_values = len(valuesInt32)
-		case len(valuesInt64) > 0:
-			vars["values"] = valuesInt64
-			len_values = len(valuesInt64)
-		case len(valuesBool) > 0:
-			vars["values"] = valuesBool
-			len_values = len(valuesBool)
-		}
-		cclog.ComponentDebug("MetricCache", "EVALUATE", f.Name, "METRICS", len_values, "CALC", f.Function)
-
 		vars["metrics"] = matches
-		if len_values > 0 {
+		if len(values) > 0 {
 			value, err := gval.Evaluate(f.Function, vars, c.language)
 			if err != nil {
-				cclog.ComponentError("MetricCache", "EVALUATE", f.Name, "METRICS", len_values, "CALC", f.Function, ":", err.Error())
+				cclog.ComponentError("MetricCache", "EVALUATE", f.Name, "METRICS", len(values), "CALC", f.Function, ":", err.Error())
 				break
 			}
 
@@ -367,7 +316,7 @@ func EvalBoolCondition(condition string, params map[string]interface{}) (bool, e
 	return value, err
 }
 
-func EvalFloat64Condition(condition string, params map[string]float64) (float64, error) {
+func EvalFloat64Condition(condition string, params map[string]interface{}) (float64, error) {
 	evaluables.mutex.Lock()
 	evaluable, ok := evaluables.mapping[condition]
 	evaluables.mutex.Unlock()

internal/metricAggregator/metricAggregatorFunctions.go

@@ -3,167 +3,162 @@ package metricAggregator
 import (
 	"errors"
 	"fmt"
+	"math"
 	"regexp"
+	"sort"
 	"strings"
 
-	"golang.org/x/exp/slices"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-
+	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
-	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 )
 
 /*
  * Arithmetic functions on value arrays
  */
 
-func sumAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
+// Sum up values
-	if len(values) == 0 {
+func sumfunc(args ...interface{}) (interface{}, error) {
-		return 0.0, errors.New("sum function requires at least one argument")
+	s := 0.0
+	values, ok := args[0].([]float64)
+	if ok {
+		cclog.ComponentDebug("MetricCache", "SUM FUNC START")
+		for _, x := range values {
+			s += x
+		}
+		cclog.ComponentDebug("MetricCache", "SUM FUNC END", s)
+	} else {
+		cclog.ComponentDebug("MetricCache", "SUM FUNC CAST FAILED")
 	}
-	var sum T
+	return s, nil
-	for _, value := range values {
-		sum += value
-	}
-	return sum, nil
 }
 
-// Sum up values
+// Get the minimum value
-func sumfunc(args interface{}) (interface{}, error) {
+func minfunc(args ...interface{}) (interface{}, error) {
-
+	var err error = nil
-	var err error
+	switch values := args[0].(type) {
-	switch values := args.(type) {
 	case []float64:
-		return sumAnyType(values)
+		var s float64 = math.MaxFloat64
+		for _, x := range values {
+			if x < s {
+				s = x
+			}
+		}
+		return s, nil
 	case []float32:
-		return sumAnyType(values)
+		var s float32 = math.MaxFloat32
+		for _, x := range values {
+			if x < s {
+				s = x
+			}
+		}
+		return s, nil
 	case []int:
-		return sumAnyType(values)
+		var s int = int(math.MaxInt32)
+		for _, x := range values {
+			if x < s {
+				s = x
+			}
+		}
+		return s, nil
 	case []int64:
-		return sumAnyType(values)
+		var s int64 = math.MaxInt64
+		for _, x := range values {
+			if x < s {
+				s = x
+			}
+		}
+		return s, nil
 	case []int32:
-		return sumAnyType(values)
+		var s int32 = math.MaxInt32
+		for _, x := range values {
+			if x < s {
+				s = x
+			}
+		}
+		return s, nil
 	default:
-		err = errors.New("function 'sum' only on list of values (float64, float32, int, int32, int64)")
+		err = errors.New("function 'min' only on list of values (float64, float32, int, int32, int64)")
 	}
 
 	return 0.0, err
 }
 
-func minAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
-	if len(values) == 0 {
-		return 0.0, errors.New("min function requires at least one argument")
-	}
-	return slices.Min(values), nil
-}
-
-// Get the minimum value
-func minfunc(args interface{}) (interface{}, error) {
-	switch values := args.(type) {
-	case []float64:
-		return minAnyType(values)
-	case []float32:
-		return minAnyType(values)
-	case []int:
-		return minAnyType(values)
-	case []int64:
-		return minAnyType(values)
-	case []int32:
-		return minAnyType(values)
-	default:
-		return 0.0, errors.New("function 'min' only on list of values (float64, float32, int, int32, int64)")
-	}
-}
-
-func avgAnyType[T float64 | float32 | int | int32 | int64](values []T) (float64, error) {
-	if len(values) == 0 {
-		return 0.0, errors.New("average function requires at least one argument")
-	}
-	sum, err := sumAnyType[T](values)
-	return float64(sum) / float64(len(values)), err
-}
-
 // Get the average or mean value
-func avgfunc(args interface{}) (interface{}, error) {
+func avgfunc(args ...interface{}) (interface{}, error) {
-	switch values := args.(type) {
+	switch values := args[0].(type) {
 	case []float64:
-		return avgAnyType(values)
+		var s float64 = 0
+		for _, x := range values {
+			s += x
+		}
+		return s / float64(len(values)), nil
 	case []float32:
-		return avgAnyType(values)
+		var s float32 = 0
+		for _, x := range values {
+			s += x
+		}
+		return s / float32(len(values)), nil
 	case []int:
-		return avgAnyType(values)
+		var s int = 0
+		for _, x := range values {
+			s += x
+		}
+		return s / len(values), nil
 	case []int64:
-		return avgAnyType(values)
+		var s int64 = 0
-	case []int32:
+		for _, x := range values {
-		return avgAnyType(values)
+			s += x
-	default:
+		}
-		return 0.0, errors.New("function 'average' only on list of values (float64, float32, int, int32, int64)")
+		return s / int64(len(values)), nil
 	}
-}
+	return 0.0, nil
-
-func maxAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
-	if len(values) == 0 {
-		return 0.0, errors.New("max function requires at least one argument")
-	}
-	return slices.Max(values), nil
 }
 
 // Get the maximum value
-func maxfunc(args interface{}) (interface{}, error) {
+func maxfunc(args ...interface{}) (interface{}, error) {
-	switch values := args.(type) {
+	s := 0.0
-	case []float64:
+	values, ok := args[0].([]float64)
-		return maxAnyType(values)
+	if ok {
-	case []float32:
+		for _, x := range values {
-		return maxAnyType(values)
+			if x > s {
-	case []int:
+				s = x
-		return maxAnyType(values)
+			}
-	case []int64:
+		}
-		return maxAnyType(values)
-	case []int32:
-		return maxAnyType(values)
-	default:
-		return 0.0, errors.New("function 'max' only on list of values (float64, float32, int, int32, int64)")
 	}
-}
+	return s, nil
-
-func medianAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
-	if len(values) == 0 {
-		return 0.0, errors.New("median function requires at least one argument")
-	}
-	slices.Sort(values)
-	var median T
-	if midPoint := len(values) % 2; midPoint == 0 {
-		median = (values[midPoint-1] + values[midPoint]) / 2
-	} else {
-		median = values[midPoint]
-	}
-	return median, nil
 }
 
 // Get the median value
-func medianfunc(args interface{}) (interface{}, error) {
+func medianfunc(args ...interface{}) (interface{}, error) {
-	switch values := args.(type) {
+	switch values := args[0].(type) {
 	case []float64:
-		return medianAnyType(values)
+		sort.Float64s(values)
-	case []float32:
+		return values[len(values)/2], nil
-		return medianAnyType(values)
+	// case []float32:
+	// 	sort.Float64s(values)
+	// 	return values[len(values)/2], nil
 	case []int:
-		return medianAnyType(values)
+		sort.Ints(values)
-	case []int64:
+		return values[len(values)/2], nil
-		return medianAnyType(values)
+
-	case []int32:
+		// case []int64:
-		return medianAnyType(values)
+		// 	sort.Ints(values)
-	default:
+		// 	return values[len(values)/2], nil
-		return 0.0, errors.New("function 'median' only on list of values (float64, float32, int, int32, int64)")
+		// case []int32:
+		// 	sort.Ints(values)
+		// 	return values[len(values)/2], nil
 	}
+	return 0.0, errors.New("function 'median()' only on lists of type float64 and int")
 }
 
 /*
  * Get number of values in list. Returns always an int
  */
 
-func lenfunc(args interface{}) (interface{}, error) {
+func lenfunc(args ...interface{}) (interface{}, error) {
 	var err error = nil
 	var length int = 0
-	switch values := args.(type) {
+	switch values := args[0].(type) {
 	case []float64:
 		length = len(values)
 	case []float32:
@@ -248,49 +243,49 @@ func matchfunc(args ...interface{}) (interface{}, error) {
  */
 
 // for a given cpuid, it returns the core id
-func getCpuCoreFunc(args interface{}) (interface{}, error) {
+func getCpuCoreFunc(args ...interface{}) (interface{}, error) {
-	switch cpuid := args.(type) {
+	switch cpuid := args[0].(type) {
 	case int:
-		return topo.GetHwthreadCore(cpuid), nil
+		return topo.GetCpuCore(cpuid), nil
 	}
 	return -1, errors.New("function 'getCpuCore' accepts only an 'int' cpuid")
 }
 
 // for a given cpuid, it returns the socket id
-func getCpuSocketFunc(args interface{}) (interface{}, error) {
+func getCpuSocketFunc(args ...interface{}) (interface{}, error) {
-	switch cpuid := args.(type) {
+	switch cpuid := args[0].(type) {
 	case int:
-		return topo.GetHwthreadSocket(cpuid), nil
+		return topo.GetCpuSocket(cpuid), nil
 	}
 	return -1, errors.New("function 'getCpuCore' accepts only an 'int' cpuid")
 }
 
 // for a given cpuid, it returns the id of the NUMA node
-func getCpuNumaDomainFunc(args interface{}) (interface{}, error) {
+func getCpuNumaDomainFunc(args ...interface{}) (interface{}, error) {
-	switch cpuid := args.(type) {
+	switch cpuid := args[0].(type) {
 	case int:
-		return topo.GetHwthreadNumaDomain(cpuid), nil
+		return topo.GetCpuNumaDomain(cpuid), nil
 	}
 	return -1, errors.New("function 'getCpuNuma' accepts only an 'int' cpuid")
 }
 
 // for a given cpuid, it returns the id of the CPU die
-func getCpuDieFunc(args interface{}) (interface{}, error) {
+func getCpuDieFunc(args ...interface{}) (interface{}, error) {
-	switch cpuid := args.(type) {
+	switch cpuid := args[0].(type) {
 	case int:
-		return topo.GetHwthreadDie(cpuid), nil
+		return topo.GetCpuDie(cpuid), nil
 	}
 	return -1, errors.New("function 'getCpuDie' accepts only an 'int' cpuid")
 }
 
 // for a given core id, it returns the list of cpuids
-func getCpuListOfCoreFunc(args interface{}) (interface{}, error) {
+func getCpuListOfCoreFunc(args ...interface{}) (interface{}, error) {
 	cpulist := make([]int, 0)
-	switch in := args.(type) {
+	switch in := args[0].(type) {
 	case int:
 		for _, c := range topo.CpuData() {
 			if c.Core == in {
-				cpulist = append(cpulist, c.CpuID)
+				cpulist = append(cpulist, c.Cpuid)
 			}
 		}
 	}
@@ -298,13 +293,13 @@ func getCpuListOfCoreFunc(args interface{}) (interface{}, error) {
 }
 
 // for a given socket id, it returns the list of cpuids
-func getCpuListOfSocketFunc(args interface{}) (interface{}, error) {
+func getCpuListOfSocketFunc(args ...interface{}) (interface{}, error) {
 	cpulist := make([]int, 0)
-	switch in := args.(type) {
+	switch in := args[0].(type) {
 	case int:
 		for _, c := range topo.CpuData() {
 			if c.Socket == in {
-				cpulist = append(cpulist, c.CpuID)
+				cpulist = append(cpulist, c.Cpuid)
 			}
 		}
 	}
@@ -312,13 +307,13 @@ func getCpuListOfSocketFunc(args interface{}) (interface{}, error) {
 }
 
 // for a given id of a NUMA domain, it returns the list of cpuids
-func getCpuListOfNumaDomainFunc(args interface{}) (interface{}, error) {
+func getCpuListOfNumaDomainFunc(args ...interface{}) (interface{}, error) {
 	cpulist := make([]int, 0)
-	switch in := args.(type) {
+	switch in := args[0].(type) {
 	case int:
 		for _, c := range topo.CpuData() {
-			if c.NumaDomain == in {
+			if c.Numadomain == in {
-				cpulist = append(cpulist, c.CpuID)
+				cpulist = append(cpulist, c.Cpuid)
 			}
 		}
 	}
@@ -326,13 +321,13 @@ func getCpuListOfNumaDomainFunc(args interface{}) (interface{}, error) {
 }
 
 // for a given CPU die id, it returns the list of cpuids
-func getCpuListOfDieFunc(args interface{}) (interface{}, error) {
+func getCpuListOfDieFunc(args ...interface{}) (interface{}, error) {
 	cpulist := make([]int, 0)
-	switch in := args.(type) {
+	switch in := args[0].(type) {
 	case int:
 		for _, c := range topo.CpuData() {
 			if c.Die == in {
-				cpulist = append(cpulist, c.CpuID)
+				cpulist = append(cpulist, c.Cpuid)
 			}
 		}
 	}
@@ -340,8 +335,8 @@ func getCpuListOfDieFunc(args interface{}) (interface{}, error) {
 }
 
 // wrapper function to get a list of all cpuids of the node
-func getCpuListOfNode() (interface{}, error) {
+func getCpuListOfNode(args ...interface{}) (interface{}, error) {
-	return topo.HwthreadList(), nil
+	return topo.CpuList(), nil
 }
 
 // helper function to get the cpuid list for a CCMetric type tag set (type and type-id)
@@ -353,14 +348,14 @@ func getCpuListOfType(args ...interface{}) (interface{}, error) {
 	case string:
 		switch typ {
 		case "node":
-			return topo.HwthreadList(), nil
+			return topo.CpuList(), nil
 		case "socket":
 			return getCpuListOfSocketFunc(args[1])
 		case "numadomain":
 			return getCpuListOfNumaDomainFunc(args[1])
 		case "core":
 			return getCpuListOfCoreFunc(args[1])
-		case "hwthread":
+		case "cpu":
 			var cpu int
 
 			switch id := args[1].(type) {

internal/metricRouter/README.md

@@ -52,11 +52,6 @@ The CCMetric router sits in between the collectors and the sinks and can be used
     ],
     "rename_metrics" : {
         "metric_12345" : "mymetric"
-    },
-    "normalize_units" : true,
-    "change_unit_prefix" : {
-      "mem_used" : "G",
-      "mem_total" : "G"
     }
 }
 ```
@@ -197,14 +192,6 @@ This option takes a list of evaluable conditions and performs them one after the
 ```
 The first line is comparable with the example in `drop_metrics`, it drops all metrics starting with `drop_metric_` and ending with a number. The second line drops all metrics of the first hardware thread (**not** recommended)
 
-# Manipulating the metric units
-
-## The `normalize_units` option
-The cc-metric-collector tries to read the data from the system as it is reported. If available, it tries to read the metric unit from the system as well (e.g. from `/proc/meminfo`). The problem is that, depending on the source, the metric units are named differently. Just think about `byte`, `Byte`, `B`, `bytes`, ...
-The [cc-units](https://github.com/ClusterCockpit/cc-units) package provides us a normalization option to use the same metric unit name for all metrics. It this option is set to true, all `unit` meta tags are normalized.
-
-## The `change_unit_prefix` section
-It is often the case that metrics are reported by the system using a rather outdated unit prefix (like `/proc/meminfo` still uses kByte despite current memory sizes are in the GByte range). If you want to change the prefix of a unit, you can do that with the help of [cc-units](https://github.com/ClusterCockpit/cc-units). The setting works on the metric name and requires the new prefix for the metric. The cc-units package determines the scaling factor.
 
 # Aggregate metric values of the current interval with the `interval_aggregates` option
 
@@ -252,22 +239,3 @@ Use cases for `interval_aggregates`:
     }
   }
 ```
-
-# Order of operations
-
-The router performs the above mentioned options in a specific order. In order to get the logic you want for a specific metric, it is crucial to know the processing order:
-
-- Add the `hostname` tag (c)
-- Manipulate the timestamp to the interval timestamp (c,r)
-- Drop metrics based on `drop_metrics` and `drop_metrics_if` (c,r)
-- Add tags based on `add_tags` (c,r)
-- Delete tags based on `del_tags` (c,r)
-- Rename metric based on `rename_metric` (c,r)
-  - Add tags based on `add_tags` to still work if the configuration uses the new name (c,r) 
-  - Delete tags based on `del_tags` to still work if the configuration uses the new name (c,r)
-- Normalize units when `normalize_units` is set (c,r)
-- Convert unit prefix based on `change_unit_prefix` (c,r)
-
-Legend:
-- 'c' if metric is coming from a collector
-- 'r' if metric is coming from a receiver

internal/metricRouter/metricCache.go

@@ -4,11 +4,11 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
-	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 type metricCachePeriod struct {

internal/metricRouter/metricRouter.go

@@ -7,12 +7,11 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
-	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
-	units "github.com/ClusterCockpit/cc-units"
 )
 
 const ROUTER_MAX_FORWARD = 50
@@ -36,8 +35,6 @@ type metricRouterConfig struct {
 	IntervalStamp     bool                                 `json:"interval_timestamp"`  // Update timestamp periodically by ticker each interval?
 	NumCacheIntervals int                                  `json:"num_cache_intervals"` // Number of intervals of cached metrics for evaluation
 	MaxForward        int                                  `json:"max_forward"`         // Number of maximal forwarded metrics at one select
-	NormalizeUnits    bool                                 `json:"normalize_units"`     // Check unit meta flag and normalize it using cc-units
-	ChangeUnitPrefix  map[string]string                    `json:"change_unit_prefix"`  // Add prefix that should be applied to the metrics
 	dropMetrics       map[string]bool                      // Internal map for O(1) lookup
 }
 
@@ -210,38 +207,6 @@ func (r *metricRouter) dropMetric(point lp.CCMetric) bool {
 	return false
 }
 
-func (r *metricRouter) prepareUnit(point lp.CCMetric) bool {
-	if r.config.NormalizeUnits {
-		if in_unit, ok := point.GetMeta("unit"); ok {
-			u := units.NewUnit(in_unit)
-			if u.Valid() {
-				point.AddMeta("unit", u.Short())
-			}
-		}
-	}
-	if newP, ok := r.config.ChangeUnitPrefix[point.Name()]; ok {
-
-		newPrefix := units.NewPrefix(newP)
-
-		if in_unit, ok := point.GetMeta("unit"); ok && newPrefix != units.InvalidPrefix {
-			u := units.NewUnit(in_unit)
-			if u.Valid() {
-				cclog.ComponentDebug("MetricRouter", "Change prefix to", newP, "for metric", point.Name())
-				conv, out_unit := units.GetUnitPrefixFactor(u, newPrefix)
-				if conv != nil && out_unit.Valid() {
-					if val, ok := point.GetField("value"); ok {
-						point.AddField("value", conv(val))
-						point.AddMeta("unit", out_unit.Short())
-					}
-				}
-			}
-
-		}
-	}
-
-	return true
-}
-
 // Start starts the metric router
 func (r *metricRouter) Start() {
 	// start timer if configured
@@ -267,11 +232,9 @@ func (r *metricRouter) Start() {
 		if new, ok := r.config.RenameMetrics[name]; ok {
 			point.SetName(new)
 			point.AddMeta("oldname", name)
-			r.DoAddTags(point)
-			r.DoDelTags(point)
 		}
-
+		r.DoAddTags(point)
-		r.prepareUnit(point)
+		r.DoDelTags(point)
 
 		for _, o := range r.outputs {
 			o <- point

internal/multiChanTicker/multiChanTicker.go

@@ -3,7 +3,7 @@ package multiChanTicker
 import (
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 )
 
 type multiChanTicker struct {

pkg/ccMetric/README.md

@@ -1,57 +0,0 @@
-# ClusterCockpit metrics
-
-As described in the [ClusterCockpit specifications](https://github.com/ClusterCockpit/cc-specifications), the whole ClusterCockpit stack uses metrics in the InfluxDB line protocol format. This is also the input and output format for the ClusterCockpit Metric Collector but internally it uses an extended format while processing, named CCMetric.
-
-It is basically a copy of the [InfluxDB line protocol](https://github.com/influxdata/line-protocol) `MutableMetric` interface with one extension. Besides the tags and fields, it contains a list of meta information (re-using the `Tag` structure of the original protocol):
-
-```golang
-type ccMetric struct {
-    name   string                 // Measurement name
-    meta   map[string]string      // map of meta data tags
-    tags   map[string]string      // map of of tags
-    fields map[string]interface{} // map of of fields
-    tm     time.Time              // timestamp
-}
-
-type CCMetric interface {
-    ToPoint(metaAsTags map[string]bool) *write.Point  // Generate influxDB point for data type ccMetric
-    ToLineProtocol(metaAsTags map[string]bool) string // Generate influxDB line protocol for data type ccMetric
-    String() string                                   // Return line-protocol like string
-
-    Name() string        // Get metric name
-    SetName(name string) // Set metric name
-
-    Time() time.Time     // Get timestamp
-    SetTime(t time.Time) // Set timestamp
-
-    Tags() map[string]string                   // Map of tags
-    AddTag(key, value string)                  // Add a tag
-    GetTag(key string) (value string, ok bool) // Get a tag by its key
-    HasTag(key string) (ok bool)               // Check if a tag key is present
-    RemoveTag(key string)                      // Remove a tag by its key
-
-    Meta() map[string]string                    // Map of meta data tags
-    AddMeta(key, value string)                  // Add a meta data tag
-    GetMeta(key string) (value string, ok bool) // Get a meta data tab addressed by its key
-    HasMeta(key string) (ok bool)               // Check if a meta data key is present
-    RemoveMeta(key string)                      // Remove a meta data tag by its key
-
-    Fields() map[string]interface{}                   // Map of fields
-    AddField(key string, value interface{})           // Add a field
-    GetField(key string) (value interface{}, ok bool) // Get a field addressed by its key
-    HasField(key string) (ok bool)                    // Check if a field key is present
-    RemoveField(key string)                           // Remove a field addressed by its key
-}
-
-func New(name string, tags map[string]string, meta map[string]string, fields map[string]interface{}, tm time.Time) (CCMetric, error)
-func FromMetric(other CCMetric) CCMetric
-func FromInfluxMetric(other lp.Metric) CCMetric
-```
-
-The `CCMetric` interface provides the same functions as the `MutableMetric` like `{Add, Get, Remove, Has}{Tag, Field}` and additionally provides `{Add, Get, Remove, Has}Meta`.
-
-The InfluxDB protocol creates a new metric with `influx.New(name, tags, fields, time)` while CCMetric uses `ccMetric.New(name, tags, meta, fields, time)` where `tags` and `meta` are both of type `map[string]string`.
-
-You can copy a CCMetric with `FromMetric(other CCMetric) CCMetric`. If you get an `influx.Metric` from a function, like the line protocol parser, you can use `FromInfluxMetric(other influx.Metric) CCMetric` to get a CCMetric out of it (see `NatsReceiver` for an example).
-
-Although the [cc-specifications](https://github.com/ClusterCockpit/cc-specifications/blob/master/interfaces/lineprotocol/README.md) defines that there is only a `value` field for the metric value, the CCMetric still can have multiple values similar to the InfluxDB line protocol.

pkg/ccTopology/ccTopology.go

@@ -1,425 +0,0 @@
-package ccTopology
-
-import (
-	"fmt"
-	"log"
-	"os"
-	"path/filepath"
-	"regexp"
-	"strconv"
-	"strings"
-
-	cclogger "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	"golang.org/x/exp/slices"
-)
-
-const SYSFS_CPUBASE = `/sys/devices/system/cpu`
-
-// Structure holding all information about a hardware thread
-// See https://www.kernel.org/doc/Documentation/ABI/stable/sysfs-devices-system-cpu
-type HwthreadEntry struct {
-	// for each CPUx:
-	CpuID        int   // CPU / hardware thread ID
-	SMT          int   // Simultaneous Multithreading ID
-	CoreCPUsList []int // CPUs within the same core
-	Core         int   // Socket local core ID
-	Socket       int   // Sockets (physical) ID
-	Die          int   // Die ID
-	NumaDomain   int   // NUMA Domain
-}
-
-var cache struct {
-	HwthreadList   []int // List of CPU hardware threads
-	SMTList        []int // List of symmetric hyper threading IDs
-	CoreList       []int // List of CPU core IDs
-	SocketList     []int // List of CPU sockets (physical) IDs
-	DieList        []int // List of CPU Die IDs
-	NumaDomainList []int // List of NUMA Domains
-
-	CpuData []HwthreadEntry
-}
-
-// fileToInt reads an integer value from a sysfs file
-// In case of an error -1 is returned
-func fileToInt(path string) int {
-	buffer, err := os.ReadFile(path)
-	if err != nil {
-		log.Print(err)
-		cclogger.ComponentError("ccTopology", "fileToInt", "Reading", path, ":", err.Error())
-		return -1
-	}
-	stringBuffer := strings.TrimSpace(string(buffer))
-	id, err := strconv.Atoi(stringBuffer)
-	if err != nil {
-		cclogger.ComponentError("ccTopology", "fileToInt", "Parsing", path, ":", stringBuffer, err.Error())
-		return -1
-	}
-	return id
-}
-
-// fileToList reads a list from a sysfs file
-// A list consists of value ranges separated by colon
-// A range can be a single value or a range of values given by a startValue-endValue
-// In case of an error nil is returned
-func fileToList(path string) []int {
-	// Read list
-	buffer, err := os.ReadFile(path)
-	if err != nil {
-		log.Print(err)
-		cclogger.ComponentError("ccTopology", "fileToList", "Reading", path, ":", err.Error())
-		return nil
-	}
-
-	// Create list
-	list := make([]int, 0)
-	stringBuffer := strings.TrimSpace(string(buffer))
-	for _, valueRangeString := range strings.Split(stringBuffer, ",") {
-		valueRange := strings.Split(valueRangeString, "-")
-		switch len(valueRange) {
-		case 1:
-			singleValue, err := strconv.Atoi(valueRange[0])
-			if err != nil {
-				cclogger.ComponentError("CCTopology", "fileToList", "Parsing", valueRange[0], ":", err.Error())
-				return nil
-			}
-			list = append(list, singleValue)
-		case 2:
-			startValue, err := strconv.Atoi(valueRange[0])
-			if err != nil {
-				cclogger.ComponentError("CCTopology", "fileToList", "Parsing", valueRange[0], ":", err.Error())
-				return nil
-			}
-			endValue, err := strconv.Atoi(valueRange[1])
-			if err != nil {
-				cclogger.ComponentError("CCTopology", "fileToList", "Parsing", valueRange[1], ":", err.Error())
-				return nil
-			}
-			for value := startValue; value <= endValue; value++ {
-				list = append(list, value)
-			}
-		}
-	}
-
-	return list
-}
-
-// init initializes the cache structure
-func init() {
-
-	getHWThreads :=
-		func() []int {
-			globPath := filepath.Join(SYSFS_CPUBASE, "cpu[0-9]*")
-			regexPath := filepath.Join(SYSFS_CPUBASE, "cpu([[:digit:]]+)")
-			regex := regexp.MustCompile(regexPath)
-
-			// File globbing for hardware threads
-			files, err := filepath.Glob(globPath)
-			if err != nil {
-				cclogger.ComponentError("CCTopology", "init:getHWThreads", err.Error())
-				return nil
-			}
-
-			hwThreadIDs := make([]int, len(files))
-			for i, file := range files {
-				// Extract hardware thread ID
-				matches := regex.FindStringSubmatch(file)
-				if len(matches) != 2 {
-					cclogger.ComponentError("CCTopology", "init:getHWThreads: Failed to extract hardware thread ID from ", file)
-					return nil
-				}
-
-				// Convert hardware thread ID to int
-				id, err := strconv.Atoi(matches[1])
-				if err != nil {
-					cclogger.ComponentError("CCTopology", "init:getHWThreads: Failed to convert to int hardware thread ID ", matches[1])
-					return nil
-				}
-
-				hwThreadIDs[i] = id
-			}
-
-			// Sort hardware thread IDs
-			slices.Sort(hwThreadIDs)
-			return hwThreadIDs
-		}
-
-	getNumaDomain :=
-		func(basePath string) int {
-			globPath := filepath.Join(basePath, "node*")
-			regexPath := filepath.Join(basePath, "node([[:digit:]]+)")
-			regex := regexp.MustCompile(regexPath)
-
-			// File globbing for NUMA node
-			files, err := filepath.Glob(globPath)
-			if err != nil {
-				cclogger.ComponentError("CCTopology", "init:getNumaDomain", err.Error())
-				return -1
-			}
-
-			// Check, that exactly one NUMA domain was found
-			if len(files) != 1 {
-				cclogger.ComponentError("CCTopology", "init:getNumaDomain", "Number of NUMA domains != 1: ", len(files))
-				return -1
-			}
-
-			// Extract NUMA node ID
-			matches := regex.FindStringSubmatch(files[0])
-			if len(matches) != 2 {
-				cclogger.ComponentError("CCTopology", "init:getNumaDomain", "Failed to extract NUMA node ID from: ", files[0])
-				return -1
-			}
-
-			id, err := strconv.Atoi(matches[1])
-			if err != nil {
-				cclogger.ComponentError("CCTopology", "init:getNumaDomain", "Failed to parse NUMA node ID from: ", matches[1])
-				return -1
-			}
-
-			return id
-		}
-
-	cache.HwthreadList = getHWThreads()
-	cache.CoreList = make([]int, len(cache.HwthreadList))
-	cache.SocketList = make([]int, len(cache.HwthreadList))
-	cache.DieList = make([]int, len(cache.HwthreadList))
-	cache.SMTList = make([]int, len(cache.HwthreadList))
-	cache.NumaDomainList = make([]int, len(cache.HwthreadList))
-	cache.CpuData = make([]HwthreadEntry, len(cache.HwthreadList))
-	for i, c := range cache.HwthreadList {
-		// Set cpuBase directory for topology lookup
-		cpuBase := filepath.Join(SYSFS_CPUBASE, fmt.Sprintf("cpu%d", c))
-		topoBase := filepath.Join(cpuBase, "topology")
-
-		// Lookup Core ID
-		cache.CoreList[i] = fileToInt(filepath.Join(topoBase, "core_id"))
-
-		// Lookup socket / physical package ID
-		cache.SocketList[i] = fileToInt(filepath.Join(topoBase, "physical_package_id"))
-
-		// Lookup CPU die id
-		cache.DieList[i] = fileToInt(filepath.Join(topoBase, "die_id"))
-		if cache.DieList[i] < 0 {
-			cache.DieList[i] = cache.SocketList[i]
-		}
-
-		// Lookup List of CPUs within the same core
-		coreCPUsList := fileToList(filepath.Join(topoBase, "core_cpus_list"))
-
-		// Find index of CPU ID in List of CPUs within the same core
-		// if not found return -1
-		cache.SMTList[i] = slices.Index(coreCPUsList, c)
-
-		// Lookup NUMA domain id
-		cache.NumaDomainList[i] = getNumaDomain(cpuBase)
-
-		cache.CpuData[i] =
-			HwthreadEntry{
-				CpuID:        cache.HwthreadList[i],
-				SMT:          cache.SMTList[i],
-				CoreCPUsList: coreCPUsList,
-				Socket:       cache.SocketList[i],
-				NumaDomain:   cache.NumaDomainList[i],
-				Die:          cache.DieList[i],
-				Core:         cache.CoreList[i],
-			}
-	}
-
-	slices.Sort(cache.HwthreadList)
-	cache.HwthreadList = slices.Compact(cache.HwthreadList)
-
-	slices.Sort(cache.SMTList)
-	cache.SMTList = slices.Compact(cache.SMTList)
-
-	slices.Sort(cache.CoreList)
-	cache.CoreList = slices.Compact(cache.CoreList)
-
-	slices.Sort(cache.SocketList)
-	cache.SocketList = slices.Compact(cache.SocketList)
-
-	slices.Sort(cache.DieList)
-	cache.DieList = slices.Compact(cache.DieList)
-
-	slices.Sort(cache.NumaDomainList)
-	cache.NumaDomainList = slices.Compact(cache.NumaDomainList)
-}
-
-// SocketList gets the list of CPU socket IDs
-func SocketList() []int {
-	return slices.Clone(cache.SocketList)
-}
-
-// HwthreadList gets the list of hardware thread IDs in the order of listing in /proc/cpuinfo
-func HwthreadList() []int {
-	return slices.Clone(cache.HwthreadList)
-}
-
-// Get list of hardware thread IDs in the order of listing in /proc/cpuinfo
-// Deprecated! Use HwthreadList()
-func CpuList() []int {
-	return HwthreadList()
-}
-
-// CoreList gets the list of CPU core IDs in the order of listing in /proc/cpuinfo
-func CoreList() []int {
-	return slices.Clone(cache.CoreList)
-}
-
-// Get list of NUMA node IDs
-func NumaNodeList() []int {
-	return slices.Clone(cache.NumaDomainList)
-}
-
-// DieList gets the list of CPU die IDs
-func DieList() []int {
-	if len(cache.DieList) > 0 {
-		return slices.Clone(cache.DieList)
-	}
-	return SocketList()
-}
-
-// GetTypeList gets the list of specified type using the naming format inside ClusterCockpit
-func GetTypeList(topology_type string) []int {
-	switch topology_type {
-	case "node":
-		return []int{0}
-	case "socket":
-		return SocketList()
-	case "die":
-		return DieList()
-	case "memoryDomain":
-		return NumaNodeList()
-	case "core":
-		return CoreList()
-	case "hwthread":
-		return HwthreadList()
-	}
-	return []int{}
-}
-
-// CpuData returns CPU data for each hardware thread
-func CpuData() []HwthreadEntry {
-	// return a deep copy to protect cache data
-	c := slices.Clone(cache.CpuData)
-	for i := range c {
-		c[i].CoreCPUsList = slices.Clone(cache.CpuData[i].CoreCPUsList)
-	}
-	return c
-}
-
-// Structure holding basic information about a CPU
-type CpuInformation struct {
-	NumHWthreads   int
-	SMTWidth       int
-	NumSockets     int
-	NumDies        int
-	NumCores       int
-	NumNumaDomains int
-}
-
-// CpuInformation reports basic information about the CPU
-func CpuInfo() CpuInformation {
-	return CpuInformation{
-		NumNumaDomains: len(cache.NumaDomainList),
-		SMTWidth:       len(cache.SMTList),
-		NumDies:        len(cache.DieList),
-		NumCores:       len(cache.CoreList),
-		NumSockets:     len(cache.SocketList),
-		NumHWthreads:   len(cache.HwthreadList),
-	}
-}
-
-// GetHwthreadSocket gets the CPU socket ID for a given hardware thread ID
-// In case hardware thread ID is not found -1 is returned
-func GetHwthreadSocket(cpuID int) int {
-	for i := range cache.CpuData {
-		d := &cache.CpuData[i]
-		if d.CpuID == cpuID {
-			return d.Socket
-		}
-	}
-	return -1
-}
-
-// GetHwthreadNumaDomain gets the NUMA domain ID for a given hardware thread ID
-// In case hardware thread ID is not found -1 is returned
-func GetHwthreadNumaDomain(cpuID int) int {
-	for i := range cache.CpuData {
-		d := &cache.CpuData[i]
-		if d.CpuID == cpuID {
-			return d.NumaDomain
-		}
-	}
-	return -1
-}
-
-// GetHwthreadDie gets the CPU die ID for a given hardware thread ID
-// In case hardware thread ID is not found -1 is returned
-func GetHwthreadDie(cpuID int) int {
-	for i := range cache.CpuData {
-		d := &cache.CpuData[i]
-		if d.CpuID == cpuID {
-			return d.Die
-		}
-	}
-	return -1
-}
-
-// GetHwthreadCore gets the CPU core ID for a given hardware thread ID
-// In case hardware thread ID is not found -1 is returned
-func GetHwthreadCore(cpuID int) int {
-	for i := range cache.CpuData {
-		d := &cache.CpuData[i]
-		if d.CpuID == cpuID {
-			return d.Core
-		}
-	}
-	return -1
-}
-
-// GetSocketHwthreads gets all hardware thread IDs associated with a CPU socket
-func GetSocketHwthreads(socket int) []int {
-	cpuList := make([]int, 0)
-	for i := range cache.CpuData {
-		d := &cache.CpuData[i]
-		if d.Socket == socket {
-			cpuList = append(cpuList, d.CpuID)
-		}
-	}
-	return cpuList
-}
-
-// GetNumaDomainHwthreads gets the all hardware thread IDs associated with a NUMA domain
-func GetNumaDomainHwthreads(numaDomain int) []int {
-	cpuList := make([]int, 0)
-	for i := range cache.CpuData {
-		d := &cache.CpuData[i]
-		if d.NumaDomain == numaDomain {
-			cpuList = append(cpuList, d.CpuID)
-		}
-	}
-	return cpuList
-}
-
-// GetDieHwthreads gets all hardware thread IDs associated with a CPU die
-func GetDieHwthreads(die int) []int {
-	cpuList := make([]int, 0)
-	for i := range cache.CpuData {
-		d := &cache.CpuData[i]
-		if d.Die == die {
-			cpuList = append(cpuList, d.CpuID)
-		}
-	}
-	return cpuList
-}
-
-// GetCoreHwthreads get all hardware thread IDs associated with a CPU core
-func GetCoreHwthreads(core int) []int {
-	cpuList := make([]int, 0)
-	for i := range cache.CpuData {
-		d := &cache.CpuData[i]
-		if d.Core == core {
-			cpuList = append(cpuList, d.CpuID)
-		}
-	}
-	return cpuList
-}

pkg/hostlist/hostlist.go

@@ -1,125 +0,0 @@
-package hostlist
-
-import (
-	"fmt"
-	"regexp"
-	"sort"
-	"strconv"
-	"strings"
-)
-
-func Expand(in string) (result []string, err error) {
-
-	// Create ranges regular expression
-	reStNumber := "[[:digit:]]+"
-	reStRange := reStNumber + "-" + reStNumber
-	reStOptionalNumberOrRange := "(" + reStNumber + ",|" + reStRange + ",)*"
-	reStNumberOrRange := "(" + reStNumber + "|" + reStRange + ")"
-	reStBraceLeft := "[[]"
-	reStBraceRight := "[]]"
-	reStRanges := reStBraceLeft +
-		reStOptionalNumberOrRange +
-		reStNumberOrRange +
-		reStBraceRight
-	reRanges := regexp.MustCompile(reStRanges)
-
-	// Create host list regular expression
-	reStDNSChars := "[a-zA-Z0-9-]+"
-	reStPrefix := "^(" + reStDNSChars + ")"
-	reStOptionalSuffix := "(" + reStDNSChars + ")?"
-	re := regexp.MustCompile(reStPrefix + "([[][0-9,-]+[]])?" + reStOptionalSuffix)
-
-	// Remove all delimiters from the input
-	in = strings.TrimLeft(in, ", ")
-
-	for len(in) > 0 {
-		if v := re.FindStringSubmatch(in); v != nil {
-
-			// Remove matched part from the input
-			lenPrefix := len(v[0])
-			in = in[lenPrefix:]
-
-			// Remove all delimiters from the input
-			in = strings.TrimLeft(in, ", ")
-
-			// matched prefix, range and suffix
-			hlPrefix := v[1]
-			hlRanges := v[2]
-			hlSuffix := v[3]
-
-			// Single node without ranges
-			if hlRanges == "" {
-				result = append(result, hlPrefix)
-				continue
-			}
-
-			// Node with ranges
-			if v := reRanges.FindStringSubmatch(hlRanges); v != nil {
-
-				// Remove braces
-				hlRanges = hlRanges[1 : len(hlRanges)-1]
-
-				// Split host ranges at ,
-				for _, hlRange := range strings.Split(hlRanges, ",") {
-
-					// Split host range at -
-					RangeStartEnd := strings.Split(hlRange, "-")
-
-					// Range is only a single number
-					if len(RangeStartEnd) == 1 {
-						result = append(result, hlPrefix+RangeStartEnd[0]+hlSuffix)
-						continue
-					}
-
-					// Range has a start and an end
-					widthRangeStart := len(RangeStartEnd[0])
-					widthRangeEnd := len(RangeStartEnd[1])
-					iStart, _ := strconv.ParseUint(RangeStartEnd[0], 10, 64)
-					iEnd, _ := strconv.ParseUint(RangeStartEnd[1], 10, 64)
-					if iStart > iEnd {
-						return nil, fmt.Errorf("single range start is greater than end: %s", hlRange)
-					}
-
-					// Create print format string for range numbers
-					doPadding := widthRangeStart == widthRangeEnd
-					widthPadding := widthRangeStart
-					var formatString string
-					if doPadding {
-						formatString = "%0" + fmt.Sprint(widthPadding) + "d"
-					} else {
-						formatString = "%d"
-					}
-					formatString = hlPrefix + formatString + hlSuffix
-
-					// Add nodes from this range
-					for i := iStart; i <= iEnd; i++ {
-						result = append(result, fmt.Sprintf(formatString, i))
-					}
-				}
-			} else {
-				return nil, fmt.Errorf("not at hostlist range: %s", hlRanges)
-			}
-		} else {
-			return nil, fmt.Errorf("not a hostlist: %s", in)
-		}
-	}
-
-	if result != nil {
-		// sort
-		sort.Strings(result)
-
-		// uniq
-		previous := 1
-		for current := 1; current < len(result); current++ {
-			if result[current-1] != result[current] {
-				if previous != current {
-					result[previous] = result[current]
-				}
-				previous++
-			}
-		}
-		result = result[:previous]
-	}
-
-	return
-}

pkg/hostlist/hostlist_test.go

@@ -1,126 +0,0 @@
-package hostlist
-
-import (
-	"testing"
-)
-
-func TestExpand(t *testing.T) {
-
-	// Compare two slices of strings
-	equal := func(a, b []string) bool {
-		if len(a) != len(b) {
-			return false
-		}
-		for i, v := range a {
-			if v != b[i] {
-				return false
-			}
-		}
-		return true
-	}
-
-	type testDefinition struct {
-		input          string
-		resultExpected []string
-		errorExpected  bool
-	}
-
-	expandTests := []testDefinition{
-		{
-			// Single node
-			input:          "n1",
-			resultExpected: []string{"n1"},
-			errorExpected:  false,
-		},
-		{
-			// Single node, duplicated
-			input:          "n1,n1",
-			resultExpected: []string{"n1"},
-			errorExpected:  false,
-		},
-		{
-			// Single node with padding
-			input:          "n[01]",
-			resultExpected: []string{"n01"},
-			errorExpected:  false,
-		},
-		{
-			// Single node with suffix
-			input:          "n[01]-p",
-			resultExpected: []string{"n01-p"},
-			errorExpected:  false,
-		},
-		{
-			// Multiple nodes with a single range
-			input:          "n[1-2]",
-			resultExpected: []string{"n1", "n2"},
-			errorExpected:  false,
-		},
-		{
-			// Multiple nodes with a single range and a single index
-			input:          "n[1-2,3]",
-			resultExpected: []string{"n1", "n2", "n3"},
-			errorExpected:  false,
-		},
-		{
-			// Multiple nodes with different prefixes
-			input:          "n[1-2],m[1,2]",
-			resultExpected: []string{"m1", "m2", "n1", "n2"},
-			errorExpected:  false,
-		},
-		{
-			// Multiple nodes with different suffixes
-			input:          "n[1-2]-p,n[1,2]-q",
-			resultExpected: []string{"n1-p", "n1-q", "n2-p", "n2-q"},
-			errorExpected:  false,
-		},
-		{
-			// Multiple nodes with and without node ranges
-			input:          " n09, n[01-04,06-07,09] , , n10,n04",
-			resultExpected: []string{"n01", "n02", "n03", "n04", "n06", "n07", "n09", "n10"},
-			errorExpected:  false,
-		},
-		{
-			// Forbidden DNS character
-			input:          "n@",
-			resultExpected: []string{},
-			errorExpected:  true,
-		},
-		{
-			// Forbidden range
-			input:          "n[1-2-2,3]",
-			resultExpected: []string{},
-			errorExpected:  true,
-		},
-		{
-			// Forbidden range limits
-			input:          "n[2-1]",
-			resultExpected: []string{},
-			errorExpected:  true,
-		},
-	}
-
-	for _, expandTest := range expandTests {
-		result, err := Expand(expandTest.input)
-
-		hasError := err != nil
-		if hasError != expandTest.errorExpected && hasError {
-			t.Errorf("Expand('%s') failed: unexpected error '%v'",
-				expandTest.input, err)
-			continue
-		}
-		if hasError != expandTest.errorExpected && !hasError {
-			t.Errorf("Expand('%s') did not fail as expected: got result '%+v'",
-				expandTest.input, result)
-			continue
-		}
-		if !hasError && !equal(result, expandTest.resultExpected) {
-			t.Errorf("Expand('%s') failed: got result '%+v', expected result '%v'",
-				expandTest.input, result, expandTest.resultExpected)
-			continue
-		}
-
-		t.Logf("Checked hostlist.Expand('%s'): result = '%+v', err = '%v'",
-			expandTest.input, result, err)
-	}
-}

receivers.json

@@ -1,44 +1,25 @@
 {
-    "natsrecv": {
+    "natsrecv" : {
         "type": "nats",
         "address": "nats://my-url",
-        "port": "4222",
+        "port" : "4222",
         "database": "testcluster"
     },
     "redfish_recv": {
         "type": "redfish",
-        "endpoint": "https://%h-bmc",
-        "client_config": [
-            {
-                "host_list": "my-host-1-[1-2]",
-                "username": "username-1",
-                "password": "password-1"
-            },
-            {
-                "host_list": "my-host-2-[1,2]",
-                "username": "username-2",
-                "password": "password-2"
-            }
-        ]
-    },
-    "ipmi_recv": {
-        "type": "ipmi",
-        "endpoint": "ipmi-sensors://%h-ipmi",
-        "exclude_metrics": [
-            "fan_speed",
-            "voltage"
-        ],
         "client_config": [
             {
+                "hostname": "my-host-1",
                 "username": "username-1",
                 "password": "password-1",
-                "host_list": "my-host-1-[1-2]"
+                "endpoint": "https://my-endpoint-1"
             },
             {
+                "hostname": "my-host-2",
                 "username": "username-2",
                 "password": "password-2",
-                "host_list": "my-host-2-[1,2]"
+                "endpoint": "https://my-endpoint-2"
             }
         ]
     }
-}
+}

receivers/README.md

@@ -2,7 +2,7 @@
 
 This folder contains the ReceiveManager and receiver implementations for the cc-metric-collector.
 
-## Configuration
+# Configuration
 
 The configuration file for the receivers is a list of configurations. The `type` field in each specifies which receiver to initialize.
 
@@ -22,11 +22,8 @@ This allows to specify
 - [`nats`](./natsReceiver.md): Receive metrics from the NATS network
 - [`prometheus`](./prometheusReceiver.md): Scrape data from a Prometheus client
 - [`http`](./httpReceiver.md): Listen for HTTP Post requests transporting metrics in InfluxDB line protocol
-- [`ipmi`](./ipmiReceiver.md): Read IPMI sensor readings
-- [`redfish`](redfishReceiver.md) Use the Redfish (specification) to query thermal and power metrics
-
-## Contributing own receivers
 
+# Contributing own receivers
 A receiver contains a few functions and is derived from the type `Receiver` (in `metricReceiver.go`):
 
 For an example, check the [sample receiver](./sampleReceiver.go)

receivers/httpReceiver.go

@@ -5,14 +5,15 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"io/ioutil"
 	"net/http"
 	"strings"
 	"sync"
-	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
+	"github.com/gorilla/mux"
+	influx "github.com/influxdata/line-protocol"
 )
 
 const HTTP_RECEIVER_PORT = "8080"
@@ -22,39 +23,22 @@ type HttpReceiverConfig struct {
 	Addr string `json:"address"`
 	Port string `json:"port"`
 	Path string `json:"path"`
-
-	// Maximum amount of time to wait for the next request when keep-alives are enabled
-	// should be larger than the measurement interval to keep the connection open
-	IdleTimeout string `json:"idle_timeout"`
-	idleTimeout time.Duration
-
-	// Controls whether HTTP keep-alives are enabled. By default, keep-alives are enabled
-	KeepAlivesEnabled bool `json:"keep_alives_enabled"`
-
-	// Basic authentication
-	Username     string `json:"username"`
-	Password     string `json:"password"`
-	useBasicAuth bool
 }
 
 type HttpReceiver struct {
 	receiver
-	meta   map[string]string
+	handler *influx.MetricHandler
-	config HttpReceiverConfig
+	parser  *influx.Parser
-	server *http.Server
+	meta    map[string]string
-	wg     sync.WaitGroup
+	config  HttpReceiverConfig
+	router  *mux.Router
+	server  *http.Server
+	wg      sync.WaitGroup
 }
 
 func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
 	r.name = fmt.Sprintf("HttpReceiver(%s)", name)
-
-	// Set default values
 	r.config.Port = HTTP_RECEIVER_PORT
-	r.config.KeepAlivesEnabled = true
-	// should be larger than the measurement interval to keep the connection open
-	r.config.IdleTimeout = "120s"
-
-	// Read config
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &r.config)
 		if err != nil {
@@ -65,47 +49,20 @@ func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
 	if len(r.config.Port) == 0 {
 		return errors.New("not all configuration variables set required by HttpReceiver")
 	}
-
-	// Check idle timeout config
-	if len(r.config.IdleTimeout) > 0 {
-		t, err := time.ParseDuration(r.config.IdleTimeout)
-		if err == nil {
-			cclog.ComponentDebug(r.name, "idleTimeout", t)
-			r.config.idleTimeout = t
-		}
-	}
-
-	// Check basic authentication config
-	if len(r.config.Username) > 0 || len(r.config.Password) > 0 {
-		r.config.useBasicAuth = true
-	}
-	if r.config.useBasicAuth && len(r.config.Username) == 0 {
-		return errors.New("basic authentication requires username")
-	}
-	if r.config.useBasicAuth && len(r.config.Password) == 0 {
-		return errors.New("basic authentication requires password")
-	}
-
 	r.meta = map[string]string{"source": r.name}
 	p := r.config.Path
 	if !strings.HasPrefix(p, "/") {
 		p = "/" + p
 	}
-	addr := fmt.Sprintf("%s:%s", r.config.Addr, r.config.Port)
+	uri := fmt.Sprintf("%s:%s%s", r.config.Addr, r.config.Port, p)
-	uri := addr + p
+	cclog.ComponentDebug(r.name, "INIT", uri)
-	cclog.ComponentDebug(r.name, "INIT", "listen on:", uri)
+	r.handler = influx.NewMetricHandler()
-
+	r.parser = influx.NewParser(r.handler)
-	// Register handler function r.ServerHttp for path p in the DefaultServeMux
+	r.parser.SetTimeFunc(DefaultTime)
-	http.HandleFunc(p, r.ServerHttp)
-
-	// Create http server
-	r.server = &http.Server{
-		Addr:        addr,
-		Handler:     nil, // handler to invoke, http.DefaultServeMux if nil
-		IdleTimeout: r.config.idleTimeout,
-	}
-	r.server.SetKeepAlivesEnabled(r.config.KeepAlivesEnabled)
 
+	r.router = mux.NewRouter()
+	r.router.Path(p).HandlerFunc(r.ServerHttp)
+	r.server = &http.Server{Addr: uri, Handler: r.router}
 	return nil
 }
 
@@ -122,97 +79,31 @@ func (r *HttpReceiver) Start() {
 }
 
 func (r *HttpReceiver) ServerHttp(w http.ResponseWriter, req *http.Request) {
-
-	// Check request method, only post method is handled
 	if req.Method != http.MethodPost {
 		http.Error(w, "Method Not Allowed", http.StatusMethodNotAllowed)
 		return
 	}
 
-	// Check basic authentication
+	body, err := ioutil.ReadAll(req.Body)
-	if r.config.useBasicAuth {
+	if err != nil {
-		username, password, ok := req.BasicAuth()
+		http.Error(w, err.Error(), http.StatusInternalServerError)
-		if !ok || username != r.config.Username || password != r.config.Password {
+		return
-			http.Error(w, "Unauthorized", http.StatusUnauthorized)
+	}
-			return
+	metrics, err := r.parser.Parse(body)
-		}
+	if err != nil {
+		http.Error(w, err.Error(), http.StatusBadRequest)
 	}
 
-	d := influx.NewDecoder(req.Body)
+	for _, m := range metrics {
-	for d.Next() {
+		y := lp.FromInfluxMetric(m)
-
+		for k, v := range r.meta {
-		// Decode measurement name
+			y.AddMeta(k, v)
-		measurement, err := d.Measurement()
-		if err != nil {
-			msg := "ServerHttp: Failed to decode measurement: " + err.Error()
-			cclog.ComponentError(r.name, msg)
-			http.Error(w, msg, http.StatusInternalServerError)
-			return
 		}
-
-		// Decode tags
-		tags := make(map[string]string)
-		for {
-			key, value, err := d.NextTag()
-			if err != nil {
-				msg := "ServerHttp: Failed to decode tag: " + err.Error()
-				cclog.ComponentError(r.name, msg)
-				http.Error(w, msg, http.StatusInternalServerError)
-				return
-			}
-			if key == nil {
-				break
-			}
-			tags[string(key)] = string(value)
-		}
-
-		// Decode fields
-		fields := make(map[string]interface{})
-		for {
-			key, value, err := d.NextField()
-			if err != nil {
-				msg := "ServerHttp: Failed to decode field: " + err.Error()
-				cclog.ComponentError(r.name, msg)
-				http.Error(w, msg, http.StatusInternalServerError)
-				return
-			}
-			if key == nil {
-				break
-			}
-			fields[string(key)] = value.Interface()
-		}
-
-		// Decode time stamp
-		t, err := d.Time(influx.Nanosecond, time.Time{})
-		if err != nil {
-			msg := "ServerHttp: Failed to decode time stamp: " + err.Error()
-			cclog.ComponentError(r.name, msg)
-			http.Error(w, msg, http.StatusInternalServerError)
-			return
-		}
-
-		y, _ := lp.New(
-			string(measurement),
-			tags,
-			r.meta,
-			fields,
-			t,
-		)
-
 		if r.sink != nil {
 			r.sink <- y
 		}
 	}
 
-	// Check for IO errors
-	err := d.Err()
-	if err != nil {
-		msg := "ServerHttp: Failed to decode: " + err.Error()
-		cclog.ComponentError(r.name, msg)
-		http.Error(w, msg, http.StatusInternalServerError)
-		return
-	}
-
 	w.WriteHeader(http.StatusOK)
 }
 

receivers/httpReceiver.md

@@ -10,10 +10,7 @@ The `http` receiver can be used receive metrics through HTTP POST requests.
     "type": "http",
     "address" : "",
     "port" : "8080",
-    "path" : "/write",
+    "path" : "/write"
-    "idle_timeout": "120s",
-    "username": "myUser",
-    "password": "myPW"
   }
 }
 ```
@@ -22,22 +19,5 @@ The `http` receiver can be used receive metrics through HTTP POST requests.
 - `address`: Listen address
 - `port`: Listen port
 - `path`: URL path for the write endpoint
-- `idle_timeout`: Maximum amount of time to wait for the next request when keep-alives are enabled should be larger than the measurement interval to keep the connection open
-- `keep_alives_enabled`: Controls whether HTTP keep-alives are enabled. By default, keep-alives are enabled.
-- `username`: username for basic authentication
-- `password`: password for basic authentication
 
 The HTTP endpoint listens to `http://<address>:<port>/<path>`
-
-### Debugging
-
-- Install [curl](https://curl.se/)
-- Use curl to send message to `http` receiver
-
-  ```bash
-  curl http://localhost:8080/write \
-  --user "myUser:myPW" \
-  --data \
-  "myMetric,hostname=myHost,type=hwthread,type-id=0,unit=Hz value=400000i 1694777161164284635
-  myMetric,hostname=myHost,type=hwthread,type-id=1,unit=Hz value=400001i 1694777161164284635"
-  ```

receivers/ipmiReceiver.go

@@ -1,534 +0,0 @@
-package receivers
-
-import (
-	"bufio"
-	"bytes"
-	"encoding/json"
-	"fmt"
-	"io"
-	"os/exec"
-	"regexp"
-	"strconv"
-	"strings"
-	"sync"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-	"github.com/ClusterCockpit/cc-metric-collector/pkg/hostlist"
-)
-
-type IPMIReceiverClientConfig struct {
-
-	// Hostname the IPMI service belongs to
-	Protocol         string            // Protocol / tool to use for IPMI sensor reading
-	DriverType       string            // Out of band IPMI driver
-	Fanout           int               // Maximum number of simultaneous IPMI connections
-	NumHosts         int               // Number of remote IPMI devices with the same configuration
-	IPMIHosts        string            // List of remote IPMI devices to communicate with
-	IPMI2HostMapping map[string]string // Mapping between IPMI device name and host name
-	Username         string            // User name to authenticate with
-	Password         string            // Password to use for authentication
-	CLIOptions       []string          // Additional command line options for ipmi-sensors
-	isExcluded       map[string]bool   // is metric excluded
-}
-
-type IPMIReceiver struct {
-	receiver
-	config struct {
-		Interval time.Duration
-
-		// Client config for each IPMI hosts
-		ClientConfigs []IPMIReceiverClientConfig
-	}
-
-	// Storage for static information
-	meta map[string]string
-
-	done chan bool      // channel to finish / stop IPMI receiver
-	wg   sync.WaitGroup // wait group for IPMI receiver
-}
-
-// doReadMetrics reads metrics from all configure IPMI hosts.
-func (r *IPMIReceiver) doReadMetric() {
-	for i := range r.config.ClientConfigs {
-		clientConfig := &r.config.ClientConfigs[i]
-		var cmd_options []string
-		if clientConfig.Protocol == "ipmi-sensors" {
-			cmd_options = append(cmd_options,
-				"--always-prefix",
-				"--sdr-cache-recreate",
-				// Attempt to interpret OEM data, such as event data, sensor readings, or general extra info
-				"--interpret-oem-data",
-				// Ignore not-available (i.e. N/A) sensors in output
-				"--ignore-not-available-sensors",
-				// Ignore unrecognized sensor events
-				"--ignore-unrecognized-events",
-				// Output fields in comma separated format
-				"--comma-separated-output",
-				// Do not output column headers
-				"--no-header-output",
-				// Output non-abbreviated units (e.g. 'Amps' instead of 'A').
-				// May aid in disambiguation of units (e.g. 'C' for Celsius or Coulombs).
-				"--non-abbreviated-units",
-				"--fanout", fmt.Sprint(clientConfig.Fanout),
-				"--driver-type", clientConfig.DriverType,
-				"--hostname", clientConfig.IPMIHosts,
-				"--username", clientConfig.Username,
-				"--password", clientConfig.Password,
-			)
-			cmd_options := append(cmd_options, clientConfig.CLIOptions...)
-
-			command := exec.Command("ipmi-sensors", cmd_options...)
-			stdout, _ := command.StdoutPipe()
-			errBuf := new(bytes.Buffer)
-			command.Stderr = errBuf
-
-			// start command
-			if err := command.Start(); err != nil {
-				cclog.ComponentError(
-					r.name,
-					fmt.Sprintf("doReadMetric(): Failed to start command \"%s\": %v", command.String(), err),
-				)
-				continue
-			}
-
-			// Read command output
-			const (
-				idxID = iota
-				idxName
-				idxType
-				idxReading
-				idxUnits
-				idxEvent
-			)
-			numPrefixRegex := regexp.MustCompile("^[[:digit:]][[:digit:]]-(.*)$")
-			scanner := bufio.NewScanner(stdout)
-			for scanner.Scan() {
-				// Read host
-				v1 := strings.Split(scanner.Text(), ": ")
-				if len(v1) != 2 {
-					continue
-				}
-				host, ok := clientConfig.IPMI2HostMapping[v1[0]]
-				if !ok {
-					continue
-				}
-
-				// Read sensors
-				v2 := strings.Split(v1[1], ",")
-				if len(v2) != 6 {
-					continue
-				}
-				// Skip sensors with non available sensor readings
-				if v2[idxReading] == "N/A" {
-					continue
-				}
-
-				metric := strings.ToLower(v2[idxType])
-				name := strings.ToLower(
-					strings.Replace(
-						strings.TrimSpace(
-							v2[idxName]), " ", "_", -1))
-				// remove prefix enumeration like 01-...
-				if v := numPrefixRegex.FindStringSubmatch(name); v != nil {
-					name = v[1]
-				}
-				unit := v2[idxUnits]
-				if unit == "Watts" {
-
-					// Power
-					metric = "power"
-					name = strings.TrimSuffix(name, "_power")
-					name = strings.TrimSuffix(name, "_pwr")
-					name = strings.TrimPrefix(name, "pwr_")
-				} else if metric == "voltage" &&
-					unit == "Volts" {
-
-					// Voltage
-					name = strings.TrimPrefix(name, "volt_")
-				} else if metric == "current" &&
-					unit == "Amps" {
-
-					// Current
-					unit = "Ampere"
-				} else if metric == "temperature" &&
-					unit == "degrees C" {
-
-					// Temperature
-					name = strings.TrimSuffix(name, "_temp")
-					unit = "degC"
-				} else if metric == "temperature" &&
-					unit == "degrees F" {
-
-					// Temperature
-					name = strings.TrimSuffix(name, "_temp")
-					unit = "degF"
-				} else if metric == "fan" && unit == "RPM" {
-
-					// Fan speed
-					metric = "fan_speed"
-					name = strings.TrimSuffix(name, "_tach")
-					name = strings.TrimPrefix(name, "spd_")
-				} else if (metric == "cooling device" ||
-					metric == "other units based sensor") &&
-					name == "system_air_flow" &&
-					unit == "CFM" {
-
-					// Air flow
-					metric = "air_flow"
-					name = strings.TrimSuffix(name, "_air_flow")
-					unit = "CubicFeetPerMinute"
-				} else if (metric == "processor" ||
-					metric == "other units based sensor") &&
-					(name == "cpu_utilization" ||
-						name == "io_utilization" ||
-						name == "mem_utilization" ||
-						name == "sys_utilization") &&
-					(unit == "unspecified" ||
-						unit == "%") {
-
-					// Utilization
-					metric = "utilization"
-					name = strings.TrimSuffix(name, "_utilization")
-					unit = "percent"
-				} else {
-					if false {
-						// Debug output for unprocessed metrics
-						fmt.Printf(
-							"host: '%s', metric: '%s', name: '%s', unit: '%s'\n",
-							host, metric, name, unit)
-					}
-					continue
-				}
-
-				// Skip excluded metrics
-				if clientConfig.isExcluded[metric] {
-					continue
-				}
-
-				// Parse sensor value
-				value, err := strconv.ParseFloat(v2[idxReading], 64)
-				if err != nil {
-					continue
-				}
-
-				y, err := lp.New(
-					metric,
-					map[string]string{
-						"hostname": host,
-						"type":     "node",
-						"name":     name,
-					},
-					map[string]string{
-						"source": r.name,
-						"group":  "IPMI",
-						"unit":   unit,
-					},
-					map[string]interface{}{
-						"value": value,
-					},
-					time.Now())
-				if err == nil {
-					r.sink <- y
-				}
-			}
-
-			// Wait for command end
-			if err := command.Wait(); err != nil {
-				errMsg, _ := io.ReadAll(errBuf)
-				cclog.ComponentError(
-					r.name,
-					fmt.Sprintf("doReadMetric(): Failed to wait for the end of command \"%s\": %v\n",
-						strings.Replace(command.String(), clientConfig.Password, "<PW>", -1), err),
-					fmt.Sprintf("doReadMetric(): command stderr: \"%s\"\n", string(errMsg)),
-				)
-			}
-		}
-	}
-}
-
-func (r *IPMIReceiver) Start() {
-	cclog.ComponentDebug(r.name, "START")
-
-	// Start IPMI receiver
-	r.wg.Add(1)
-	go func() {
-		defer r.wg.Done()
-
-		// Create ticker
-		ticker := time.NewTicker(r.config.Interval)
-		defer ticker.Stop()
-
-		for {
-			r.doReadMetric()
-
-			select {
-			case tickerTime := <-ticker.C:
-				// Check if we missed the ticker event
-				if since := time.Since(tickerTime); since > 5*time.Second {
-					cclog.ComponentInfo(r.name, "Missed ticker event for more then", since)
-				}
-
-				// process ticker event -> continue
-				continue
-			case <-r.done:
-				// process done event
-				return
-			}
-		}
-	}()
-
-	cclog.ComponentDebug(r.name, "STARTED")
-}
-
-// Close receiver: close network connection, close files, close libraries, ...
-func (r *IPMIReceiver) Close() {
-	cclog.ComponentDebug(r.name, "CLOSE")
-
-	// Send the signal and wait
-	close(r.done)
-	r.wg.Wait()
-
-	cclog.ComponentDebug(r.name, "DONE")
-}
-
-// NewIPMIReceiver creates a new instance of the redfish receiver
-// Initialize the receiver by giving it a name and reading in the config JSON
-func NewIPMIReceiver(name string, config json.RawMessage) (Receiver, error) {
-	r := new(IPMIReceiver)
-
-	// Config options from config file
-	configJSON := struct {
-		Type string `json:"type"`
-
-		// How often the IPMI sensor metrics should be read and send to the sink (default: 30 s)
-		IntervalString string `json:"interval,omitempty"`
-
-		// Maximum number of simultaneous IPMI connections (default: 64)
-		Fanout int `json:"fanout,omitempty"`
-
-		// Out of band IPMI driver (default: LAN_2_0)
-		DriverType string `json:"driver_type,omitempty"`
-
-		// Default client username, password and endpoint
-		Username *string `json:"username"` // User name to authenticate with
-		Password *string `json:"password"` // Password to use for authentication
-		Endpoint *string `json:"endpoint"` // URL of the IPMI device
-
-		// Globally excluded metrics
-		ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-
-		ClientConfigs []struct {
-			Fanout     int     `json:"fanout,omitempty"`      // Maximum number of simultaneous IPMI connections (default: 64)
-			DriverType string  `json:"driver_type,omitempty"` // Out of band IPMI driver (default: LAN_2_0)
-			HostList   string  `json:"host_list"`             // List of hosts with the same client configuration
-			Username   *string `json:"username"`              // User name to authenticate with
-			Password   *string `json:"password"`              // Password to use for authentication
-			Endpoint   *string `json:"endpoint"`              // URL of the IPMI service
-
-			// Per client excluded metrics
-			ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-
-			// Additional command line options for ipmi-sensors
-			CLIOptions []string `json:"cli_options,omitempty"`
-		} `json:"client_config"`
-	}{
-		// Set defaults values
-		// Allow overwriting these defaults by reading config JSON
-		Fanout:         64,
-		DriverType:     "LAN_2_0",
-		IntervalString: "30s",
-	}
-
-	// Set name of IPMIReceiver
-	r.name = fmt.Sprintf("IPMIReceiver(%s)", name)
-
-	// Create done channel
-	r.done = make(chan bool)
-
-	// Set static information
-	r.meta = map[string]string{"source": r.name}
-
-	// Read the IPMI receiver specific JSON config
-	if len(config) > 0 {
-		d := json.NewDecoder(bytes.NewReader(config))
-		d.DisallowUnknownFields()
-		if err := d.Decode(&configJSON); err != nil {
-			cclog.ComponentError(r.name, "Error reading config:", err.Error())
-			return nil, err
-		}
-	}
-
-	// Convert interval string representation to duration
-	var err error
-	r.config.Interval, err = time.ParseDuration(configJSON.IntervalString)
-	if err != nil {
-		err := fmt.Errorf(
-			"Failed to parse duration string interval='%s': %w",
-			configJSON.IntervalString,
-			err,
-		)
-		cclog.Error(r.name, err)
-		return nil, err
-	}
-
-	// Create client config from JSON config
-	totalNumHosts := 0
-	for i := range configJSON.ClientConfigs {
-		clientConfigJSON := &configJSON.ClientConfigs[i]
-
-		var endpoint string
-		if clientConfigJSON.Endpoint != nil {
-			endpoint = *clientConfigJSON.Endpoint
-		} else if configJSON.Endpoint != nil {
-			endpoint = *configJSON.Endpoint
-		} else {
-			err := fmt.Errorf("client config number %v requires endpoint", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-
-		fanout := configJSON.Fanout
-		if clientConfigJSON.Fanout != 0 {
-			fanout = clientConfigJSON.Fanout
-		}
-
-		driverType := configJSON.DriverType
-		if clientConfigJSON.DriverType != "" {
-			driverType = clientConfigJSON.DriverType
-		}
-		if driverType != "LAN" && driverType != "LAN_2_0" {
-			err := fmt.Errorf("client config number %v has invalid driver type %s", i, driverType)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-
-		var protocol string
-		var host_pattern string
-		if e := strings.Split(endpoint, "://"); len(e) == 2 {
-			protocol = e[0]
-			host_pattern = e[1]
-		} else {
-			err := fmt.Errorf("client config number %v has invalid endpoint %s", i, endpoint)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-
-		var username string
-		if clientConfigJSON.Username != nil {
-			username = *clientConfigJSON.Username
-		} else if configJSON.Username != nil {
-			username = *configJSON.Username
-		} else {
-			err := fmt.Errorf("client config number %v requires username", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-
-		var password string
-		if clientConfigJSON.Password != nil {
-			password = *clientConfigJSON.Password
-		} else if configJSON.Password != nil {
-			password = *configJSON.Password
-		} else {
-			err := fmt.Errorf("client config number %v requires password", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-
-		// Create mapping between IPMI host name and node host name
-		// This also guaranties that all IPMI host names are unique
-		ipmi2HostMapping := make(map[string]string)
-		hostList, err := hostlist.Expand(clientConfigJSON.HostList)
-		if err != nil {
-			err := fmt.Errorf("client config number %d failed to parse host list %s: %v",
-				i, clientConfigJSON.HostList, err)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		for _, host := range hostList {
-			ipmiHost := strings.Replace(host_pattern, "%h", host, -1)
-			ipmi2HostMapping[ipmiHost] = host
-		}
-
-		numHosts := len(ipmi2HostMapping)
-		totalNumHosts += numHosts
-		ipmiHostList := make([]string, 0, numHosts)
-		for ipmiHost := range ipmi2HostMapping {
-			ipmiHostList = append(ipmiHostList, ipmiHost)
-		}
-
-		// Additional command line options
-		for _, v := range clientConfigJSON.CLIOptions {
-			switch {
-			case v == "-u" || strings.HasPrefix(v, "--username"):
-				err := fmt.Errorf("client config number %v: do not set username in cli_options. Use json config username instead", i)
-				cclog.ComponentError(r.name, err)
-				return nil, err
-			case v == "-p" || strings.HasPrefix(v, "--password"):
-				err := fmt.Errorf("client config number %v: do not set password in cli_options. Use json config password instead", i)
-				cclog.ComponentError(r.name, err)
-				return nil, err
-			case v == "-h" || strings.HasPrefix(v, "--hostname"):
-				err := fmt.Errorf("client config number %v: do not set hostname in cli_options. Use json config host_list instead", i)
-				cclog.ComponentError(r.name, err)
-				return nil, err
-			case v == "-D" || strings.HasPrefix(v, "--driver-type"):
-				err := fmt.Errorf("client config number %v: do not set driver type in cli_options. Use json config driver_type instead", i)
-				cclog.ComponentError(r.name, err)
-				return nil, err
-			case v == "-F" || strings.HasPrefix(v, " --fanout"):
-				err := fmt.Errorf("client config number %v: do not set fanout in cli_options. Use json config fanout instead", i)
-				cclog.ComponentError(r.name, err)
-				return nil, err
-			case v == "--always-prefix" ||
-				v == "--sdr-cache-recreate" ||
-				v == "--interpret-oem-data" ||
-				v == "--ignore-not-available-sensors" ||
-				v == "--ignore-unrecognized-events" ||
-				v == "--comma-separated-output" ||
-				v == "--no-header-output" ||
-				v == "--non-abbreviated-units":
-				err := fmt.Errorf("client config number %v: Do not use option %s in cli_options, it is used internally", i, v)
-				cclog.ComponentError(r.name, err)
-				return nil, err
-			}
-		}
-		cliOptions := make([]string, 0)
-		cliOptions = append(cliOptions, clientConfigJSON.CLIOptions...)
-
-		// Is metrics excluded globally or per client
-		isExcluded := make(map[string]bool)
-		for _, key := range clientConfigJSON.ExcludeMetrics {
-			isExcluded[key] = true
-		}
-		for _, key := range configJSON.ExcludeMetrics {
-			isExcluded[key] = true
-		}
-
-		r.config.ClientConfigs = append(
-			r.config.ClientConfigs,
-			IPMIReceiverClientConfig{
-				Protocol:         protocol,
-				Fanout:           fanout,
-				DriverType:       driverType,
-				NumHosts:         numHosts,
-				IPMIHosts:        strings.Join(ipmiHostList, ","),
-				IPMI2HostMapping: ipmi2HostMapping,
-				Username:         username,
-				Password:         password,
-				CLIOptions:       cliOptions,
-				isExcluded:       isExcluded,
-			})
-	}
-
-	if totalNumHosts == 0 {
-		err := fmt.Errorf("at least one IPMI host config is required")
-		cclog.ComponentError(r.name, err)
-		return nil, err
-	}
-
-	cclog.ComponentInfo(r.name, "monitoring", totalNumHosts, "IPMI hosts")
-	return r, nil
-}

receivers/ipmiReceiver.md

@@ -1,48 +0,0 @@
-## IPMI Receiver
-
-The IPMI Receiver uses `ipmi-sensors` from the [FreeIPMI](https://www.gnu.org/software/freeipmi/) project to read IPMI sensor readings and sensor data repository (SDR) information. The available metrics depend on the sensors provided by the hardware vendor but typically contain temperature, fan speed, voltage and power metrics.
-
-### Configuration structure
-
-```json
-{
-    "<IPMI receiver name>": {
-        "type": "ipmi",
-        "interval": "30s",
-        "fanout": 256,
-        "username": "<Username>",
-        "password": "<Password>",
-        "endpoint": "ipmi-sensors://%h-bmc",
-        "exclude_metrics": [ "fan_speed", "voltage" ],
-        "client_config": [
-            {
-                "host_list": "n[1,2-4]"
-            },
-            {
-                "host_list": "n[5-6]",
-                "driver_type": "LAN",
-                "cli_options": [ "--workaround-flags=..." ],
-                "password": "<Password 2>"
-            }
-        ]
-    }
-}
-```
-
-Global settings:
-
-- `interval`: How often the IPMI sensor metrics should be read and send to the sink (default: 30 s)
-
-Global and per IPMI device settings (per IPMI device settings overwrite the global settings):
-
-- `exclude_metrics`: list of excluded metrics e.g. fan_speed, power, temperature, utilization, voltage
-- `fanout`: Maximum number of simultaneous IPMI connections (default: 64)
-- `driver_type`: Out of band IPMI driver (default: LAN_2_0)
-- `username`: User name to authenticate with
-- `password`: Password to use for authentication
-- `endpoint`: URL of the IPMI device (placeholder `%h` gets replaced by the hostname)
-
-Per IPMI device settings:
-
-- `host_list`: List of hosts with the same client configuration
-- `cli_options`: Additional command line options for ipmi-sensors

receivers/metricReceiver.go

@@ -1,7 +1,7 @@
 package receivers
 
 import (
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 type defaultReceiverConfig struct {

receivers/natsReceiver.go

@@ -6,9 +6,9 @@ import (
 	"fmt"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
+	influx "github.com/influxdata/line-protocol"
 	nats "github.com/nats-io/nats.go"
 )
 
@@ -21,85 +21,37 @@ type NatsReceiverConfig struct {
 
 type NatsReceiver struct {
 	receiver
-	nc     *nats.Conn
+	nc      *nats.Conn
-	meta   map[string]string
+	handler *influx.MetricHandler
-	config NatsReceiverConfig
+	parser  *influx.Parser
+	meta    map[string]string
+	config  NatsReceiverConfig
+}
+
+var DefaultTime = func() time.Time {
+	return time.Unix(42, 0)
 }
 
-// Start subscribes to the configured NATS subject
-// Messages wil be handled by r._NatsReceive
 func (r *NatsReceiver) Start() {
 	cclog.ComponentDebug(r.name, "START")
 	r.nc.Subscribe(r.config.Subject, r._NatsReceive)
 }
 
-// _NatsReceive receives subscribed messages from the NATS server
 func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
-
+	metrics, err := r.parser.Parse(m.Data)
-	d := influx.NewDecoderWithBytes(m.Data)
+	if err == nil {
-	for d.Next() {
+		for _, m := range metrics {
-
+			y := lp.FromInfluxMetric(m)
-		// Decode measurement name
+			for k, v := range r.meta {
-		measurement, err := d.Measurement()
+				y.AddMeta(k, v)
-		if err != nil {
-			msg := "_NatsReceive: Failed to decode measurement: " + err.Error()
-			cclog.ComponentError(r.name, msg)
-			return
-		}
-
-		// Decode tags
-		tags := make(map[string]string)
-		for {
-			key, value, err := d.NextTag()
-			if err != nil {
-				msg := "_NatsReceive: Failed to decode tag: " + err.Error()
-				cclog.ComponentError(r.name, msg)
-				return
 			}
-			if key == nil {
+			if r.sink != nil {
-				break
+				r.sink <- y
 			}
-			tags[string(key)] = string(value)
-		}
-
-		// Decode fields
-		fields := make(map[string]interface{})
-		for {
-			key, value, err := d.NextField()
-			if err != nil {
-				msg := "_NatsReceive: Failed to decode field: " + err.Error()
-				cclog.ComponentError(r.name, msg)
-				return
-			}
-			if key == nil {
-				break
-			}
-			fields[string(key)] = value.Interface()
-		}
-
-		// Decode time stamp
-		t, err := d.Time(influx.Nanosecond, time.Time{})
-		if err != nil {
-			msg := "_NatsReceive: Failed to decode time: " + err.Error()
-			cclog.ComponentError(r.name, msg)
-			return
-		}
-
-		y, _ := lp.New(
-			string(measurement),
-			tags,
-			r.meta,
-			fields,
-			t,
-		)
-
-		if r.sink != nil {
-			r.sink <- y
 		}
 	}
 }
 
-// Close closes the connection to the NATS server
 func (r *NatsReceiver) Close() {
 	if r.nc != nil {
 		cclog.ComponentDebug(r.name, "CLOSE")
@@ -107,13 +59,10 @@ func (r *NatsReceiver) Close() {
 	}
 }
 
-// NewNatsReceiver creates a new Receiver which subscribes to messages from a NATS server
 func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
 	r := new(NatsReceiver)
 	r.name = fmt.Sprintf("NatsReceiver(%s)", name)
-
+	r.config.Addr = nats.DefaultURL
-	// Read configuration file, allow overwriting default config
-	r.config.Addr = "localhost"
 	r.config.Port = "4222"
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &r.config)
@@ -127,21 +76,17 @@ func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
 		len(r.config.Subject) == 0 {
 		return nil, errors.New("not all configuration variables set required by NatsReceiver")
 	}
-
+	r.meta = map[string]string{"source": r.name}
-	// Set metadata
+	uri := fmt.Sprintf("%s:%s", r.config.Addr, r.config.Port)
-	r.meta = map[string]string{
+	cclog.ComponentDebug(r.name, "NewNatsReceiver", uri, "Subject", r.config.Subject)
-		"source": r.name,
+	if nc, err := nats.Connect(uri); err == nil {
-	}
-
-	// Connect to NATS server
-	url := fmt.Sprintf("nats://%s:%s", r.config.Addr, r.config.Port)
-	cclog.ComponentDebug(r.name, "NewNatsReceiver", url, "Subject", r.config.Subject)
-	if nc, err := nats.Connect(url); err == nil {
 		r.nc = nc
 	} else {
 		r.nc = nil
 		return nil, err
 	}
-
+	r.handler = influx.NewMetricHandler()
+	r.parser = influx.NewParser(r.handler)
+	r.parser.SetTimeFunc(DefaultTime)
 	return r, nil
 }

receivers/natsReceiver.md

@@ -19,32 +19,3 @@ The `nats` receiver can be used receive metrics from the NATS network. The `nats
 - `address`: Address of the NATS control server
 - `port`: Port of the NATS control server
 - `subject`: Subscribes to this subject and receive metrics
-
-### Debugging
-
-- Install NATS server and command line client
-- Start NATS server
-
-  ```bash
-  nats-server --net nats-server.example.org --port 4222
-  ```
-
-- Check NATS server works as expected
-
-  ```bash
-  nats --server=nats-server-db.example.org:4222 server check
-  ```
-
-- Use NATS command line client to subscribe to all messages
-
-  ```bash
-  nats --server=nats-server-db.example.org:4222 sub ">"
-  ```
-
-- Use NATS command line client to send message to NATS receiver
-
-  ```bash
-  nats --server=nats-server-db.example.org:4222 pub subject \
-  "myMetric,hostname=myHost,type=hwthread,type-id=0,unit=Hz value=400000i 1694777161164284635
-  myMetric,hostname=myHost,type=hwthread,type-id=1,unit=Hz value=400001i 1694777161164284635"
-  ```

receivers/prometheusReceiver.go

@@ -12,8 +12,8 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 type PrometheusReceiverConfig struct {

receivers/receiveManager.go

@@ -2,17 +2,14 @@ package receivers
 
 import (
 	"encoding/json"
-	"fmt"
 	"os"
 	"sync"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
-	"http":    NewHttpReceiver,
-	"ipmi":    NewIPMIReceiver,
 	"nats":    NewNatsReceiver,
 	"redfish": NewRedfishReceiver,
 }
@@ -74,13 +71,9 @@ func (rm *receiveManager) AddInput(name string, rawConfig json.RawMessage) error
 		cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "JSON config error:", err.Error())
 		return err
 	}
-	if config.Type == "" {
-		cclog.ComponentError("ReceiveManager", "SKIP", "JSON config for receiver", name, "does not contain a receiver type")
-		return fmt.Errorf("JSON config for receiver %s does not contain a receiver type", name)
-	}
 	if _, found := AvailableReceivers[config.Type]; !found {
-		cclog.ComponentError("ReceiveManager", "SKIP", "unknown receiver type:", config.Type)
+		cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "unknown receiver:", err.Error())
-		return fmt.Errorf("unknown receiver type: %s", config.Type)
+		return err
 	}
 	r, err := AvailableReceivers[config.Type](name, rawConfig)
 	if err != nil {

receivers/redfishReceiver.md

@@ -1,54 +0,0 @@
-## Redfish receiver
-
-The Redfish receiver uses the [Redfish (specification)](https://www.dmtf.org/standards/redfish) to query thermal and power metrics. Thermal metrics may include various fan speeds and temperatures. Power metrics may include the current power consumption of various hardware components. It may also include the minimum, maximum and average power consumption of these components in a given time interval. The receiver will poll each configured redfish device once in a given interval. Multiple devices can be accessed in parallel to increase throughput.
-
-### Configuration structure
-
-```json
-{
-    "<redfish receiver name>": {
-        "type": "redfish",
-        "username": "<Username>",
-        "password": "<Password>",
-        "endpoint": "https://%h-bmc",
-        "exclude_metrics": [ "min_consumed_watts" ],
-        "client_config": [
-            {
-                "host_list": "n[1,2-4]"
-            },
-            {
-                "host_list": "n5"
-                "disable_power_metrics": true
-            },
-            {
-                "host_list": "n6" ],
-                "username": "<Username 2>",
-                "password": "<Password 2>",
-                "endpoint": "https://%h-BMC",
-                "disable_thermal_metrics": true
-            }
-        ]
-    }
-}
-```
-
-Global settings:
-
-- `fanout`: Maximum number of simultaneous redfish connections (default: 64)
-- `interval`: How often the redfish power metrics should be read and send to the sink (default: 30 s)
-- `http_insecure`: Control whether a client verifies the server's certificate (default: true == do not verify server's certificate)
-- `http_timeout`: Time limit for requests made by this HTTP client (default: 10 s)
-
-Global and per redfish device settings (per redfish device settings overwrite the global settings):
-
-- `disable_power_metrics`: disable collection of power metrics
-- `disable_processor_metrics`: disable collection of processor metrics
-- `disable_thermal_metrics`: disable collection of thermal metrics
-- `exclude_metrics`: list of excluded metrics
-- `username`: User name to authenticate with
-- `password`: Password to use for authentication
-- `endpoint`: URL of the redfish service (placeholder `%h` gets replaced by the hostname)
-
-Per redfish device settings:
-
-- `host_list`: List of hosts with the same client configuration

receivers/sampleReceiver.go

@@ -4,7 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 )
 
 // SampleReceiver configuration: receiver type, listen address, port

scripts/cc-metric-collector.config

@@ -6,7 +6,7 @@ CC_HOME=/tmp
 
 LOG_DIR=/var/log
 
-DATA_DIR=/var/lib/cc-metric-collector
+DATA_DIR=/var/lib/grafana
 
 MAX_OPEN_FILES=10000
 
@@ -15,9 +15,3 @@ CONF_DIR=/etc/cc-metric-collector
 CONF_FILE=/etc/cc-metric-collector/cc-metric-collector.json
 
 RESTART_ON_UPGRADE=true
-
-# Golang runtime debugging. (see: https://pkg.go.dev/runtime)
-# GODEBUG=gctrace=1
-
-# Golang garbage collection target percentage
-# GOGC=100

scripts/cc-metric-collector.deb.rules

@@ -1,16 +0,0 @@
-
-#!/usr/bin/make -f
-# You must remove unused comment lines for the released package.
-#export DH_VERBOSE = 1
-#export DEB_BUILD_MAINT_OPTIONS = hardening=+all
-#export DEB_CFLAGS_MAINT_APPEND  = -Wall -pedantic
-#export DEB_LDFLAGS_MAINT_APPEND = -Wl,--as-needed
-
-%:
-        dh $@
-
-override_dh_auto_build:
-        make
-
-override_dh_auto_install:
-        make PREFIX=/usr install

scripts/cc-metric-collector.init

@@ -19,13 +19,13 @@
 PATH=/bin:/usr/bin:/sbin:/usr/sbin
 NAME=cc-metric-collector
 DESC="ClusterCockpit metric collector"
-DEFAULT=/etc/default/${NAME}
+DEFAULT=/etc/default/${NAME}.json
 
 CC_USER=clustercockpit
 CC_GROUP=clustercockpit
 CONF_DIR=/etc/cc-metric-collector
 PID_FILE=/var/run/$NAME.pid
-DAEMON=/usr/bin/$NAME
+DAEMON=/usr/sbin/$NAME
 CONF_FILE=${CONF_DIR}/cc-metric-collector.json
 
 umask 0027
@@ -75,7 +75,7 @@ case "$1" in
 	fi
 
 	# Start Daemon
-	start-stop-daemon --start -b --chdir "$WORK_DIR" --user "$CC_USER" -c "$CC_USER" --pidfile "$PID_FILE" --exec $DAEMON -- $CC_OPTS
+	start-stop-daemon --start -b --chdir "$WORK_DIR" --user "$CC_USER" -c "$CC_USER" --pidfile "$PID_FILE" --exec $DAEMON -- $DAEMON_OPTS
 	return=$?
 	if [ $return -eq 0 ]
 	then

scripts/cc-metric-collector.service

@@ -3,6 +3,7 @@ Description=ClusterCockpit metric collector
 Documentation=https://github.com/ClusterCockpit/cc-metric-collector
 Wants=network-online.target
 After=network-online.target
+After=postgresql.service mariadb.service mysql.service
 
 [Service]
 EnvironmentFile=/etc/default/cc-metric-collector
@@ -13,7 +14,7 @@ Restart=on-failure
 WorkingDirectory=/tmp
 RuntimeDirectory=cc-metric-collector
 RuntimeDirectoryMode=0750
-ExecStart=/usr/bin/cc-metric-collector --config=${CONF_FILE}
+ExecStart=/usr/sbin/cc-metric-collector --config=${CONF_FILE}
 LimitNOFILE=10000
 TimeoutStopSec=20
 UMask=0027

scripts/cc-metric-collector.spec

@@ -10,8 +10,6 @@ BuildRequires:  go-toolset
 BuildRequires:  systemd-rpm-macros
 # for header downloads
 BuildRequires:  wget
-# Recommended when using the sysusers_create_package macro
-Requires(pre): /usr/bin/systemd-sysusers
 
 Provides:       %{name} = %{version}
 
@@ -29,7 +27,7 @@ make
 
 
 %install
-install -Dpm 0750 %{name} %{buildroot}%{_bindir}/%{name}
+install -Dpm 0750 %{name} %{buildroot}%{_sbindir}/%{name}
 install -Dpm 0600 config.json %{buildroot}%{_sysconfdir}/%{name}/%{name}.json
 install -Dpm 0600 collectors.json %{buildroot}%{_sysconfdir}/%{name}/collectors.json
 install -Dpm 0600 sinks.json %{buildroot}%{_sysconfdir}/%{name}/sinks.json
@@ -44,7 +42,7 @@ install -Dpm 0644 scripts/%{name}.sysusers %{buildroot}%{_sysusersdir}/%{name}.c
 # go test should be here... :)
 
 %pre
-%sysusers_create_package %{name} scripts/%{name}.sysusers
+%sysusers_create_package scripts/%{name}.sysusers
 
 %post
 %systemd_post %{name}.service
@@ -54,7 +52,7 @@ install -Dpm 0644 scripts/%{name}.sysusers %{buildroot}%{_sysusersdir}/%{name}.c
 
 %files
 # Binary
-%attr(-,clustercockpit,clustercockpit) %{_bindir}/%{name}
+%attr(-,clustercockpit,clustercockpit) %{_sbindir}/%{name}
 # Config
 %dir %{_sysconfdir}/%{name}
 %attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/%{name}.json

scripts/likwid_perfgroup_to_cc_config.py

@@ -39,13 +39,13 @@ def group_to_json(groupfile):
             llist = re.split("\s+", line)
             calc = llist[-1]
             metric = " ".join(llist[:-1])
-            scope = "hwthread"
+            scope = "cpu"
             if "BOX" in calc:
                 scope = "socket"
             if "PWR" in calc:
                 scope = "socket"
 
-            m = {"name" : metric, "calc": calc, "type" : scope, "publish" : True}
+            m = {"name" : metric, "calc": calc, "scope" : scope, "publish" : True}
             metrics.append(m)
     return {"events" : events, "metrics" : metrics}
 

sinks/README.md

@@ -20,9 +20,7 @@ The configuration file for the sinks is a list of configurations. The `type` fie
 [
   "mystdout" : {
     "type" : "stdout",
-    "meta_as_tags" : [
+    "meta_as_tags" : false
-    	"unit"
-    ]
   },
   "metricstore" : {
     "type" : "http",
@@ -105,4 +103,4 @@ func NewSampleSink(name string, config json.RawMessage) (Sink, error) {
 	return s, err
 }
 
-```
+```

sinks/gangliaCommon.go

@@ -4,7 +4,7 @@ import (
 	"fmt"
 	"strings"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 func GangliaMetricName(point lp.CCMetric) string {