Update metricRouter.go

* cpustatMetric.go: Use derived values instead of absolute values

  The values in /proc/stat are absolute counters related to the boot
  time of the system. To obtain a utilization of the CPU, the changes
  in the counters must be derived according to time. To take only the
  absolute values leads to the fact that changes in the utilization,
  straight with larger values, do not become visible.

* Add new collector for /proc/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.

Co-authored-by: Michael Schwarz <post@michael-schwarz.name>

.github/ci-config.json

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

.github/ci-sinks.json

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

.github/workflows/AlmaLinux.yml

@@ -1,64 +0,0 @@
-# See: https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions
-
-# Workflow name
-name: AlmaLinux 8.5 RPM build
-
-# Run on tag push
-on:
- push:
-  tags:
-  - '**'
-
-jobs:
-
-  #
-  # Build on AlmaLinux 8.5 using go-toolset
-  #
-  AlmaLinux-RPM-build:
-    runs-on: ubuntu-latest
-    # See: https://hub.docker.com/_/almalinux
-    container: almalinux:8.5
-    steps:
-
-    # Use dnf to install development packages
-    - name: Install development packages
-      run: dnf --assumeyes group install "Development Tools" "RPM Development Tools"
-
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: dnf --assumeyes builddep scripts/cc-metric-collector.spec
-
-    - name: RPM build MetricCollector
-      id: rpmbuild
-      run: make RPM
-
-    # See: https://github.com/actions/upload-artifact
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector RPM for AlmaLinux 8.5
-        path: ${{ steps.rpmbuild.outputs.RPM }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector SRPM for AlmaLinux 8.5
-        path: ${{ steps.rpmbuild.outputs.SRPM }}
-
-    # See: https://github.com/softprops/action-gh-release
-    - name: Release
-      uses: softprops/action-gh-release@v1
-      if: startsWith(github.ref, 'refs/tags/')
-      with:
-        name: cc-metric-collector-${{github.ref_name}}
-        files: |
-         ${{ steps.rpmbuild.outputs.RPM }}
-         ${{ steps.rpmbuild.outputs.SRPM }}

.github/workflows/RedHatUniversalBaseImage.yml

@@ -1,64 +0,0 @@
-# See: https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions
-
-# Workflow name
-name: Red Hat Universal Base Image 8 RPM build
-
-# Run on tag push
-on:
- push:
-  tags:
-  - '**'
-
-jobs:
-
-  #
-  # 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:8.5-226.1645809065
-    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
-
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: dnf --assumeyes --disableplugin=subscription-manager builddep scripts/cc-metric-collector.spec
-
-    - name: RPM build MetricCollector
-      id: rpmbuild
-      run: make RPM
-
-    # See: https://github.com/actions/upload-artifact
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector RPM for UBI 8
-        path: ${{ steps.rpmbuild.outputs.RPM }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector SRPM for UBI 8
-        path: ${{ steps.rpmbuild.outputs.SRPM }}
-
-    # See: https://github.com/softprops/action-gh-release
-    - name: Release
-      uses: softprops/action-gh-release@v1
-      if: startsWith(github.ref, 'refs/tags/')
-      with:
-        name: cc-metric-collector-${{github.ref_name}}
-        files: |
-         ${{ steps.rpmbuild.outputs.RPM }}
-         ${{ steps.rpmbuild.outputs.SRPM }}

.github/workflows/Release.yml

@@ -0,0 +1,255 @@
+# See: https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions
+
+# Workflow name
+name: Release
+
+# Run on tag push
+on:
+ push:
+  tags:
+  - '**'
+
+jobs:
+
+  #
+  # Build on AlmaLinux 8.5 using go-toolset
+  #
+  AlmaLinux-RPM-build:
+    runs-on: ubuntu-latest
+    # See: https://hub.docker.com/_/almalinux
+    container: almalinux:8.5
+    # The job outputs link to the outputs of the 'rpmrename' step
+    # Only job outputs can be used in child jobs
+    outputs:
+      rpm : ${{steps.rpmrename.outputs.RPM}}
+      srpm : ${{steps.rpmrename.outputs.SRPM}}
+    steps:
+
+    # Use dnf to install development packages
+    - name: Install development packages
+      run: |
+          dnf --assumeyes group install "Development Tools" "RPM Development Tools"
+          dnf --assumeyes install wget openssl-devel diffutils delve which
+
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v2
+      with:
+        submodules: recursive
+        fetch-depth: 0
+
+    # Use dnf to install build dependencies
+    - name: Install build dependencies
+      run: |
+          wget -q http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm \
+                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm \
+                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.18.2-1.module_el8.7.0+1173+5d37c0fd.noarch.rpm \
+                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm
+          rpm -i go*.rpm
+
+    - name: RPM build MetricCollector
+      id: rpmbuild
+      run: make RPM
+
+    # AlmaLinux 8.5 is a derivate of RedHat Enterprise Linux 8 (UBI8),
+    # so the created RPM both contain the substring 'el8' in the RPM file names
+    # This step replaces the substring 'el8' to 'alma85'. It uses the move operation
+    # because it is unclear whether the default AlmaLinux 8.5 container contains the 
+    # 'rename' command. This way we also get the new names for output.
+    - name: Rename RPMs (s/el8/alma85/)
+      id: rpmrename
+      run: |
+        OLD_RPM="${{steps.rpmbuild.outputs.RPM}}"
+        OLD_SRPM="${{steps.rpmbuild.outputs.SRPM}}"
+        NEW_RPM="${OLD_RPM/el8/alma85}"
+        NEW_SRPM=${OLD_SRPM/el8/alma85}
+        mv "${OLD_RPM}" "${NEW_RPM}"
+        mv "${OLD_SRPM}" "${NEW_SRPM}"
+        echo "::set-output name=SRPM::${NEW_SRPM}"
+        echo "::set-output name=RPM::${NEW_RPM}"
+
+    # See: https://github.com/actions/upload-artifact
+    - name: Save RPM as artifact
+      uses: actions/upload-artifact@v2
+      with:
+        name: cc-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 8.5
+        path: ${{ steps.rpmrename.outputs.SRPM }}
+
+  #
+  # 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:8.5-226.1645809065
+    # The job outputs link to the outputs of the 'rpmbuild' step
+    outputs:
+      rpm : ${{steps.rpmbuild.outputs.RPM}}
+      srpm : ${{steps.rpmbuild.outputs.SRPM}}
+    steps:
+
+    # Use dnf to install development packages
+    - name: Install development packages
+      run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros rpm-build-libs rpm-libs gcc make python38 git wget openssl-devel diffutils delve which
+
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v2
+      with:
+        submodules: recursive
+        fetch-depth: 0
+
+    # Use dnf to install build dependencies
+    - name: Install build dependencies
+      run: |
+          wget -q http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm \
+                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm \
+                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.18.2-1.module_el8.7.0+1173+5d37c0fd.noarch.rpm \
+                  http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.18.2-1.module_el8.7.0+1173+5d37c0fd.x86_64.rpm
+          rpm -i go*.rpm
+
+    - name: RPM build MetricCollector
+      id: rpmbuild
+      run: make RPM
+
+    # See: https://github.com/actions/upload-artifact
+    - name: Save RPM as artifact
+      uses: actions/upload-artifact@v2
+      with:
+        name: cc-metric-collector RPM for UBI 8
+        path: ${{ steps.rpmbuild.outputs.RPM }}
+    - name: Save SRPM as artifact
+      uses: actions/upload-artifact@v2
+      with:
+        name: cc-metric-collector SRPM for UBI 8
+        path: ${{ steps.rpmbuild.outputs.SRPM }}
+
+  #
+  # Build on Ubuntu 20.04 using official go package
+  #
+  Ubuntu-focal-build:
+    runs-on: ubuntu-latest
+    container: ubuntu:20.04
+    # The job outputs link to the outputs of the 'debrename' step
+    # Only job outputs can be used in child jobs
+    outputs:
+      deb : ${{steps.debrename.outputs.DEB}}
+    steps:
+    # Use apt to install development packages
+    - name: Install development packages
+      run: |
+          apt update && apt --assume-yes upgrade
+          apt --assume-yes install build-essential sed git wget bash
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v2
+      with:
+        submodules: recursive
+        fetch-depth: 0
+    # Use official golang package
+    - name: Install Golang
+      run: |
+          wget -q https://go.dev/dl/go1.19.1.linux-amd64.tar.gz
+          tar -C /usr/local -xzf go1.19.1.linux-amd64.tar.gz
+          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
+          go version
+    - name: DEB build MetricCollector
+      id: dpkg-build
+      run: |
+          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
+          make DEB
+    - name: Rename DEB (add '_ubuntu20.04')
+      id: debrename
+      run: |
+        OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev)
+        NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu20.04.deb"
+        mv "${{steps.dpkg-build.outputs.DEB}}" "${NEW_DEB_FILE}"
+        echo "::set-output name=DEB::${NEW_DEB_FILE}"
+    # See: https://github.com/actions/upload-artifact
+    - name: Save DEB as artifact
+      uses: actions/upload-artifact@v2
+      with:
+        name: cc-metric-collector DEB for Ubuntu 20.04
+        path: ${{ steps.debrename.outputs.DEB }}
+
+  #
+  # Create release with fresh RPMs
+  #
+  Release:
+    runs-on: ubuntu-latest
+    # We need the RPMs, so add dependency
+    needs: [AlmaLinux-RPM-build, UBI-8-RPM-build, Ubuntu-focal-build]
+
+    steps:
+    # See: https://github.com/actions/download-artifact
+    - name: Download AlmaLinux 8.5 RPM
+      uses: actions/download-artifact@v2
+      with:
+        name: cc-metric-collector RPM for AlmaLinux 8.5
+    - name: Download AlmaLinux 8.5 SRPM
+      uses: actions/download-artifact@v2
+      with:
+        name: cc-metric-collector SRPM for AlmaLinux 8.5
+    
+    - name: Download UBI 8 RPM
+      uses: actions/download-artifact@v2
+      with:
+        name: cc-metric-collector RPM for UBI 8
+    - name: Download UBI 8 SRPM
+      uses: actions/download-artifact@v2
+      with:
+        name: cc-metric-collector SRPM for UBI 8
+
+    - name: Download Ubuntu 20.04 DEB
+      uses: actions/download-artifact@v2
+      with:
+        name: cc-metric-collector DEB for Ubuntu 20.04
+
+    # The download actions do not publish the name of the downloaded file,
+    # so we re-use the job outputs of the parent jobs. The files are all
+    # downloaded to the current folder.
+    # The gh-release action afterwards does not accept file lists but all
+    # files have to be listed at 'files'. The step creates one output per
+    # RPM package (2 per distro)
+    - name: Set RPM variables
+      id: files
+      run: |
+        ALMA_85_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
+        ALMA_85_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
+        UBI_8_RPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.rpm}}")
+        UBI_8_SRPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.srpm}}")
+        U_2004_DEB=$(basename "${{ needs.Ubuntu-focal-build.outputs.deb}}")
+        echo "ALMA_85_RPM::${ALMA_85_RPM}"
+        echo "ALMA_85_SRPM::${ALMA_85_SRPM}"
+        echo "UBI_8_RPM::${UBI_8_RPM}"
+        echo "UBI_8_SRPM::${UBI_8_SRPM}"
+        echo "U_2004_DEB::${U_2004_DEB}"
+        echo "::set-output name=ALMA_85_RPM::${ALMA_85_RPM}"
+        echo "::set-output name=ALMA_85_SRPM::${ALMA_85_SRPM}"
+        echo "::set-output name=UBI_8_RPM::${UBI_8_RPM}"
+        echo "::set-output name=UBI_8_SRPM::${UBI_8_SRPM}"
+        echo "::set-output name=U_2004_DEB::${U_2004_DEB}"
+
+    # See: https://github.com/softprops/action-gh-release
+    - name: Release
+      uses: softprops/action-gh-release@v1
+      if: startsWith(github.ref, 'refs/tags/')
+      with:
+        name: cc-metric-collector-${{github.ref_name}}
+        files: |
+         ${{ steps.files.outputs.ALMA_85_RPM }}
+         ${{ steps.files.outputs.ALMA_85_SRPM }}
+         ${{ steps.files.outputs.UBI_8_RPM }}
+         ${{ steps.files.outputs.UBI_8_SRPM }}
+         ${{ steps.files.outputs.U_2004_DEB }}

.github/workflows/runonce.yml

@@ -8,10 +8,10 @@ on: push
 
 jobs:
   #
-  # Job build-1-17
-  # Build on latest Ubuntu using golang version 1.17 
+  # Job build-1-18
+  # Build on latest Ubuntu using golang version 1.18
   #
-  build-1-17:
+  build-1-18:
     runs-on: ubuntu-latest
     steps:
     # See: https://github.com/marketplace/actions/checkout
@@ -23,13 +23,9 @@ jobs:
 
     # See: https://github.com/marketplace/actions/setup-go-environment
     - name: Setup Golang
-      uses: actions/setup-go@v2
+      uses: actions/setup-go@v3
       with:
-        go-version: '^1.17.7'
-
-    # Install libganglia
-    - name: Setup Ganglia
-      run: sudo apt install ganglia-monitor libganglia1
+        go-version: '1.18.2'
 
     - name: Build MetricCollector
       run: make
@@ -38,10 +34,10 @@ jobs:
       run: ./cc-metric-collector --once --config .github/ci-config.json
 
   #
-  # Job build-1-16
-  # Build on latest Ubuntu using golang version 1.16
+  # Job build-1-19
+  # Build on latest Ubuntu using golang version 1.19
   #
-  build-1-16:
+  build-1-19:
     runs-on: ubuntu-latest
     steps:
     # See: https://github.com/marketplace/actions/checkout
@@ -53,13 +49,9 @@ jobs:
 
     # See: https://github.com/marketplace/actions/setup-go-environment
     - name: Setup Golang
-      uses: actions/setup-go@v2
+      uses: actions/setup-go@v3
       with:
-        go-version: '^1.16.7' # The version AlmaLinux 8.5 uses
-
-    # Install libganglia
-    - name: Setup Ganglia
-      run: sudo apt install ganglia-monitor libganglia1
+        go-version: '1.19'
 
     - name: Build MetricCollector
       run: make

Makefile

@@ -15,47 +15,62 @@ COMPONENT_DIRS   := collectors \
 			internal/ccTopology \
 			internal/multiChanTicker
 
+BINDIR = bin
+GOBIN = $(shell which go)
+
 
 .PHONY: all
 all: $(APP)
 
 $(APP): $(GOSRC)
 	make -C collectors
-	go get
-	go build -o $(APP) $(GOSRC_APP)
+	$(GOBIN) get
+	$(GOBIN) build -o $(APP) $(GOSRC_APP)
+
+install: $(APP)
+	@WORKSPACE=$(PREFIX)
+	@if [ -z "$${WORKSPACE}" ]; then exit 1; fi
+	@mkdir --parents --verbose $${WORKSPACE}/usr/$(BINDIR)
+	@install -Dpm 755 $(APP) $${WORKSPACE}/usr/$(BINDIR)/$(APP)
+	@mkdir --parents --verbose $${WORKSPACE}/etc/cc-metric-collector $${WORKSPACE}/etc/default $${WORKSPACE}/etc/systemd/system $${WORKSPACE}/etc/init.d
+	@install -Dpm 600 config.json $${WORKSPACE}/etc/cc-metric-collector/cc-metric-collector.json
+	@sed -i -e s+"\"./"+"\"/etc/cc-metric-collector/"+g $${WORKSPACE}/etc/cc-metric-collector/cc-metric-collector.json
+	@install -Dpm 600 sinks.json $${WORKSPACE}/etc/cc-metric-collector/sinks.json
+	@install -Dpm 600 collectors.json $${WORKSPACE}/etc/cc-metric-collector/collectors.json
+	@install -Dpm 600 router.json $${WORKSPACE}/etc/cc-metric-collector/router.json
+	@install -Dpm 600 receivers.json $${WORKSPACE}/etc/cc-metric-collector/receivers.json
+	@install -Dpm 600 scripts/cc-metric-collector.config $${WORKSPACE}/etc/default/cc-metric-collector
+	@install -Dpm 644 scripts/cc-metric-collector.service $${WORKSPACE}/etc/systemd/system/cc-metric-collector.service
+	@install -Dpm 644 scripts/cc-metric-collector.init $${WORKSPACE}/etc/init.d/cc-metric-collector
+
 
 .PHONY: clean
 .ONESHELL:
 clean:
-	@for COMP in $(COMPONENT_DIRS)
-	do
-	    if [[ -e $$COMP/Makefile ]]; then
-	        make -C $$COMP clean
-	    fi
-	done
+	@for COMP in $(COMPONENT_DIRS); do if [ -e $$COMP/Makefile ]; then make -C $$COMP clean;  fi; done
 	rm -f $(APP)
 
 .PHONY: fmt
 fmt:
-	go fmt $(GOSRC_COLLECTORS)
-	go fmt $(GOSRC_SINKS)
-	go fmt $(GOSRC_RECEIVERS)
-	go fmt $(GOSRC_APP)
-	@for F in $(GOSRC_INTERNAL); do go fmt $$F; done
+	$(GOBIN) fmt $(GOSRC_COLLECTORS)
+	$(GOBIN) fmt $(GOSRC_SINKS)
+	$(GOBIN) fmt $(GOSRC_RECEIVERS)
+	$(GOBIN) fmt $(GOSRC_APP)
+	@for F in $(GOSRC_INTERNAL); do $(GOBIN) fmt $$F; done
 
 
 # Examine Go source code and reports suspicious constructs
 .PHONY: vet
 vet:
-	go vet ./...
+	$(GOBIN) 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:
-	go install honnef.co/go/tools/cmd/staticcheck@latest
-	$$(go env GOPATH)/bin/staticcheck ./...
+	$(GOBIN) install honnef.co/go/tools/cmd/staticcheck@latest
+	$$($(GOBIN) env GOPATH)/bin/staticcheck ./...
 
 .ONESHELL:
 .PHONY: RPM
@@ -69,7 +84,7 @@ RPM: scripts/cc-metric-collector.spec
 	@COMMITISH="HEAD"
 	@VERS=$$(git describe --tags $${COMMITISH})
 	@VERS=$${VERS#v}
-	@VERS=$${VERS//-/_}
+	@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}-$${VERSION}"
 	@FORMAT="tar.gz"
@@ -86,3 +101,28 @@ RPM: scripts/cc-metric-collector.spec
 	@     echo "::set-output name=SRPM::$${SRPMFILE}"
 	@     echo "::set-output name=RPM::$${RPMFILE}"
 	@fi
+
+.PHONY: DEB
+DEB: scripts/cc-metric-collector.deb.control $(APP)
+	@BASEDIR=$${PWD}
+	@WORKSPACE=$${PWD}/.dpkgbuild
+	@DEBIANDIR=$${WORKSPACE}/debian
+	@DEBIANBINDIR=$${WORKSPACE}/DEBIAN
+	@mkdir --parents --verbose $$WORKSPACE $$DEBIANBINDIR
+	#@mkdir --parents --verbose $$DEBIANDIR
+	@CONTROLFILE="$${BASEDIR}/scripts/cc-metric-collector.deb.control"
+	@COMMITISH="HEAD"
+	@VERS=$$(git describe --tags --abbrev=0 $${COMMITISH})
+	@VERS=$${VERS#v}
+	@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
+	@ARCH=$$(uname -m)
+	@ARCH=$$(echo $$ARCH | sed -e s+'_'+'-'+g)
+	@PREFIX="$${NAME}-$${VERSION}_$${ARCH}"
+	@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)}')"
+	#@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} "$$DEB_FILE"
+	@rm -r "$${WORKSPACE}"

README.md

@@ -1,5 +1,6 @@
 # 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).
 
@@ -10,7 +11,7 @@ The receiver runs as a go routine side-by-side with the timer loop and asynchron
 # 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/metrics/lineprotocol_alternative.md).
+Supported metrics are documented [here](https://github.com/ClusterCockpit/cc-specifications/blob/master/interfaces/lineprotocol/README.md).
 
 There is a main configuration file with basic settings that point to the other configuration files for the different components.
 
@@ -20,20 +21,20 @@ 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": 10,
-  "duration": 1
+  "interval": "10s",
+  "duration": "1s"
 }
 ```
 
-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.
+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).
 
 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
 
 ```
@@ -43,6 +44,7 @@ $ go get (requires at least golang 1.16)
 $ make
 ```
 
+For more information, see [here](./docs/building.md).
 
 # Running
 
@@ -56,6 +58,7 @@ 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:
@@ -93,11 +96,12 @@ 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"
-	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 type CentralConfigFile struct {
-	Interval            int    `json:"interval"`
-	Duration            int    `json:"duration"`
+	Interval            string `json:"interval"`
+	Duration            string `json:"duration"`
 	CollectorConfigFile string `json:"collectors"`
 	RouterConfigFile    string `json:"router"`
 	SinkConfigFile      string `json:"sinks"`
@@ -173,16 +173,36 @@ 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 {
-		cclog.Error("Configuration value 'interval' must be greater than zero")
+
+	// Properly use duration parser with inputs like '60s', '5m' or similar
+	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")
@@ -271,7 +291,7 @@ func mainFunc() int {
 
 	// Wait until one tick has passed. This is a workaround
 	if rcfg.CliArgs["once"] == "true" {
-		x := 1.2 * float64(rcfg.ConfigFile.Interval)
+		x := 1.2 * float64(rcfg.Interval.Seconds())
 		time.Sleep(time.Duration(int(x)) * time.Second)
 		shutdownSignal <- os.Interrupt
 	}

collectors.json

@@ -12,6 +12,13 @@
             "proc_total"
         ]
     },
+    "memstat": {},
+    "netstat": {
+        "include_devices": [
+            "enp5s0"
+        ],
+        "send_derived_values": true
+    },
     "numastats": {},
     "nvidia": {},
     "tempstat": {
@@ -27,5 +34,8 @@
                 "type-id": "1"
             }
         }
+    },
+    "topprocs": {
+        "num_procs": 5
     }
 }

collectors/Makefile

@@ -1,79 +1,31 @@
-# Use central installation
-CENTRAL_INSTALL = false
-# How to access hardware performance counters through LIKWID.
-# Recommended is 'direct' mode
-ACCESSMODE = direct
-
-#######################################################################
-# if CENTRAL_INSTALL == true
-#######################################################################
-# Path to central installation (if CENTRAL_INSTALL=true)
-LIKWID_BASE=/apps/likwid/5.2.1
-# LIKWID version (should be same major version as central installation, 5.2.x)
+# LIKWID version
 LIKWID_VERSION = 5.2.1
+LIKWID_INSTALLED_FOLDER=$(shell dirname $(shell which likwid-topology 2>/dev/null) 2>/dev/null)
 
-#######################################################################
-# if CENTRAL_INSTALL == false and ACCESSMODE == accessdaemon
-#######################################################################
-# Where to install the accessdaemon
-DAEMON_INSTALLDIR = /usr/local
-# Which user to use for the accessdaemon
-DAEMON_USER = root
-# Which group to use for the accessdaemon
-DAEMON_GROUP = root
+LIKWID_FOLDER="$(shell pwd)/likwid"
+
+all: $(LIKWID_FOLDER)/likwid.h
+
+.ONESHELL:
+.PHONY: $(LIKWID_FOLDER)/likwid.h
+$(LIKWID_FOLDER)/likwid.h:
+	if [ "$(LIKWID_INSTALLED_FOLDER)" != "" ]; then \
+		BASE="$(LIKWID_INSTALLED_FOLDER)/../include"; \
+		mkdir -p $(LIKWID_FOLDER); \
+		cp $$BASE/*.h $(LIKWID_FOLDER); \
+	else \
+		BUILD_FOLDER="$${PWD}/likwidbuild"; \
+		if [ -d $(LIKWID_FOLDER) ]; then rm -r $(LIKWID_FOLDER); fi; \
+		mkdir --parents --verbose  $(LIKWID_FOLDER) $${BUILD_FOLDER}; \
+		wget -P "$${BUILD_FOLDER}" http://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz; \
+		tar -C $${BUILD_FOLDER} -xf $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION).tar.gz; \
+		install -Dpm 0644 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/likwid*.h $(LIKWID_FOLDER)/; \
+		install -Dpm 0644 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/bstrlib.h $(LIKWID_FOLDER)/; \
+		rm -r $${BUILD_FOLDER}; \
+	fi
 
 
-
-#################################################
-# No need to change anything below this line
-#################################################
-INSTALL_FOLDER = ./likwid
-BUILD_FOLDER = ./likwid/build
-
-ifneq ($(strip $(CENTRAL_INSTALL)),true)
-LIKWID_BASE := $(shell pwd)/$(INSTALL_FOLDER)
-DAEMON_BASE := $(LIKWID_BASE)
-GROUPS_BASE := $(LIKWID_BASE)/groups
-all: $(INSTALL_FOLDER)/liblikwid.a cleanup
-else
-DAEMON_BASE= $(LIKWID_BASE)/sbin
-all: $(INSTALL_FOLDER)/liblikwid.a cleanup
-endif
-
-
-
-$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz: $(BUILD_FOLDER)
-	wget -P $(BUILD_FOLDER) ftp://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz
-
-$(BUILD_FOLDER):
-	mkdir -p $(BUILD_FOLDER)
-
-$(INSTALL_FOLDER):
-	mkdir -p $(INSTALL_FOLDER)
-
-$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION): $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz
-	tar -C $(BUILD_FOLDER) -xf $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz
-
-$(INSTALL_FOLDER)/liblikwid.a: $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION) $(INSTALL_FOLDER)
-	cd "$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)" && make "PREFIX=$(LIKWID_BASE)" "SHARED_LIBRARY=false" "ACCESSMODE=$(ACCESSMODE)" "INSTALLED_ACCESSDAEMON=$(DAEMON_INSTALLDIR)/likwid-accessD"
-	cp \
-	    $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/liblikwid.a \
-	    $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/ext/hwloc/liblikwid-hwloc.a \
-	    $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/src/includes/likwid*.h \
-	    $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/src/includes/bstrlib.h \
-	    $(INSTALL_FOLDER)
-
-$(DAEMON_INSTALLDIR)/likwid-accessD: $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/likwid-accessD
-	sudo -u $(DAEMON_USER) -g $(DAEMON_GROUP) install -m 4775 $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/likwid-accessD $(DAEMON_INSTALLDIR)/likwid-accessD
-
-prepare_collector: likwidMetric.go
-	cp likwidMetric.go likwidMetric.go.orig
-	sed -i -e s+"const GROUPPATH =.*"+"const GROUPPATH = \`$(GROUPS_BASE)\`"+g likwidMetric.go
-
-cleanup:
-	rm -rf $(BUILD_FOLDER)
-
-clean: cleanup
+clean:
 	rm -rf likwid
 
 .PHONY: clean

collectors/README.md

@@ -35,8 +35,11 @@ In contrast to the configuration files for sinks and receivers, the collectors c
 * [`nfs4stat`](./nfs4Metric.md)
 * [`cpufreq`](./cpufreqMetric.md)
 * [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
-* [`numastat`](./numastatMetric.md)
+* [`numastats`](./numastatsMetric.md)
 * [`gpfs`](./gpfsMetric.md)
+* [`beegfs_meta`](./beegfsmetaMetric.md)
+* [`beegfs_storage`](./beegfsstorageMetric.md)
+* [`rocm_smi`](./rocmsmiMetric.md)
 
 ## Todos
 

collectors/beegfsmetaMetric.go

@@ -0,0 +1,230 @@
+package collectors
+
+import (
+	"bufio"
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"io"
+	"os"
+	"os/exec"
+	"os/user"
+	"regexp"
+	"strconv"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
+
+// Struct for the collector-specific JSON config
+type BeegfsMetaCollectorConfig struct {
+	Beegfs            string   `json:"beegfs_path"`
+	ExcludeMetrics    []string `json:"exclude_metrics,omitempty"`
+	ExcludeFilesystem []string `json:"exclude_filesystem"`
+}
+
+type BeegfsMetaCollector struct {
+	metricCollector
+	tags    map[string]string
+	matches map[string]string
+	config  BeegfsMetaCollectorConfig
+	skipFS  map[string]struct{}
+}
+
+func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+	// Metrics
+	var nodeMdstat_array = [39]string{
+		"sum", "ack", "close", "entInf",
+		"fndOwn", "mkdir", "create", "rddir",
+		"refrEn", "mdsInf", "rmdir", "rmLnk",
+		"mvDirIns", "mvFiIns", "open", "ren",
+		"sChDrct", "sAttr", "sDirPat", "stat",
+		"statfs", "trunc", "symlnk", "unlnk",
+		"lookLI", "statLI", "revalLI", "openLI",
+		"createLI", "hardlnk", "flckAp", "flckEn",
+		"flckRg", "dirparent", "listXA", "getXA",
+		"rmXA", "setXA", "mirror"}
+
+	m.name = "BeegfsMetaCollector"
+	m.setup()
+	m.parallel = true
+	// Set default beegfs-ctl binary
+
+	m.config.Beegfs = DEFAULT_BEEGFS_CMD
+
+	// Read JSON configuration
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &m.config)
+		if err != nil {
+			return err
+		}
+	}
+
+	//create map with possible variables
+	m.matches = make(map[string]string)
+	for _, value := range nodeMdstat_array {
+		_, skip := stringArrayContains(m.config.ExcludeMetrics, value)
+		if skip {
+			m.matches["other"] = "0"
+		} else {
+			m.matches["beegfs_cmeta_"+value] = "0"
+		}
+	}
+
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "BeegfsMeta",
+	}
+	m.tags = map[string]string{
+		"type":       "node",
+		"filesystem": "",
+	}
+	m.skipFS = make(map[string]struct{})
+	for _, fs := range m.config.ExcludeFilesystem {
+		m.skipFS[fs] = struct{}{}
+	}
+
+	// Beegfs file system statistics can only be queried by user root
+	user, err := user.Current()
+	if err != nil {
+		return fmt.Errorf("BeegfsMetaCollector.Init(): Failed to get current user: %v", err)
+	}
+	if user.Uid != "0" {
+		return fmt.Errorf("BeegfsMetaCollector.Init(): BeeGFS file system statistics can only be queried by user root")
+	}
+
+	// Check if beegfs-ctl is in executable search path
+	_, err = exec.LookPath(m.config.Beegfs)
+	if err != nil {
+		return fmt.Errorf("BeegfsMetaCollector.Init(): Failed to find beegfs-ctl binary '%s': %v", m.config.Beegfs, err)
+	}
+	m.init = true
+	return nil
+}
+
+func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	if !m.init {
+		return
+	}
+	//get mounpoint
+	buffer, _ := os.ReadFile(string("/proc/mounts"))
+	mounts := strings.Split(string(buffer), "\n")
+	var mountpoints []string
+	for _, line := range mounts {
+		if len(line) == 0 {
+			continue
+		}
+		f := strings.Fields(line)
+		if strings.Contains(f[0], "beegfs_ondemand") {
+			// Skip excluded filesystems
+			if _, skip := m.skipFS[f[1]]; skip {
+				continue
+			}
+			mountpoints = append(mountpoints, f[1])
+		}
+	}
+
+	if len(mountpoints) == 0 {
+		return
+	}
+
+	for _, mountpoint := range mountpoints {
+		m.tags["filesystem"] = mountpoint
+
+		// bwwgfs-ctl:
+		// --clientstats: Show client IO statistics.
+		// --nodetype=meta: The node type to query (meta, storage).
+		// --interval:
+		// --mount=/mnt/beeond/: Which mount point
+		//cmd := exec.Command(m.config.Beegfs, "/root/mc/test.txt")
+		mountoption := "--mount=" + mountpoint
+		cmd := exec.Command(m.config.Beegfs, "--clientstats",
+			"--nodetype=meta", mountoption, "--allstats")
+		cmd.Stdin = strings.NewReader("\n")
+		cmdStdout := new(bytes.Buffer)
+		cmdStderr := new(bytes.Buffer)
+		cmd.Stdout = cmdStdout
+		cmd.Stderr = cmdStderr
+		err := cmd.Run()
+		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)
+			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stderr: \"%s\"\n", string(data))
+			data, _ = io.ReadAll(cmdStdout)
+			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stdout: \"%s\"\n", string(data))
+			return
+		}
+		// Read I/O statistics
+		scanner := bufio.NewScanner(cmdStdout)
+
+		sumLine := regexp.MustCompile(`^Sum:\s+\d+\s+\[[a-zA-Z]+\]+`)
+		//Line := regexp.MustCompile(`^(.*)\s+(\d)+\s+\[([a-zA-Z]+)\]+`)
+		statsLine := regexp.MustCompile(`^(.*?)\s+?(\d.*?)$`)
+		singleSpacePattern := regexp.MustCompile(`\s+`)
+		removePattern := regexp.MustCompile(`[\[|\]]`)
+
+		for scanner.Scan() {
+			readLine := scanner.Text()
+			//fmt.Println(readLine)
+			// Jump few lines, we only want the I/O stats from nodes
+			if !sumLine.MatchString(readLine) {
+				continue
+			}
+
+			match := statsLine.FindStringSubmatch(readLine)
+			// nodeName = "Sum:" or would be nodes
+			// nodeName := match[1]
+			//Remove multiple whitespaces
+			dummy := removePattern.ReplaceAllString(match[2], " ")
+			metaStats := strings.TrimSpace(singleSpacePattern.ReplaceAllString(dummy, " "))
+			split := strings.Split(metaStats, " ")
+
+			// fill map with values
+			// split[i+1] = mdname
+			// split[i] = amount of md operations
+			for i := 0; i <= len(split)-1; i += 2 {
+				if _, ok := m.matches[split[i+1]]; ok {
+					m.matches["beegfs_cmeta_"+split[i+1]] = split[i]
+				} else {
+					f1, err := strconv.ParseFloat(m.matches["other"], 32)
+					if err != nil {
+						cclog.ComponentError(
+							m.name,
+							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
+						continue
+					}
+					f2, err := strconv.ParseFloat(split[i], 32)
+					if err != nil {
+						cclog.ComponentError(
+							m.name,
+							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
+						continue
+					}
+					//mdStat["other"] = fmt.Sprintf("%f", f1+f2)
+					m.matches["beegfs_cstorage_other"] = fmt.Sprintf("%f", f1+f2)
+				}
+			}
+
+			for key, data := range m.matches {
+				value, _ := strconv.ParseFloat(data, 32)
+				y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+				if err == nil {
+					output <- y
+				}
+			}
+		}
+	}
+}
+
+func (m *BeegfsMetaCollector) Close() {
+	m.init = false
+}

collectors/beegfsmetaMetric.md

@@ -0,0 +1,75 @@
+## `BeeGFS on Demand` collector
+This Collector is to collect BeeGFS on Demand (BeeOND) metadata clientstats.
+
+```json
+  "beegfs_meta": {
+	"beegfs_path": "/usr/bin/beegfs-ctl",
+    "exclude_filesystem": [
+      "/mnt/ignore_me"
+    ],
+    "exclude_metrics": [     
+          "ack",
+          "entInf",
+          "fndOwn"
+    ]
+  }
+```
+
+The `BeeGFS On Demand (BeeOND)` collector uses the `beegfs-ctl` command to read performance metrics for
+BeeGFS filesystems.
+
+The reported filesystems can be filtered with the `exclude_filesystem` option
+in the configuration.
+
+The path to the `beegfs-ctl` command can be configured with the `beegfs_path` option
+in the configuration.
+
+When using the `exclude_metrics` option, the excluded metrics are summed as `other`.
+
+Important: The metrics listed below, are similar to the naming of BeeGFS. The Collector prefixes these with `beegfs_cstorage`(beegfs client storage).
+
+For example beegfs metric `open`-> `beegfs_cstorage_open`
+
+Available Metrics:
+
+* sum
+* ack
+* close
+* entInf
+* fndOwn
+* mkdir
+* create
+* rddir
+* refrEnt
+* mdsInf
+* rmdir
+* rmLnk
+* mvDirIns
+* mvFiIns
+* open
+* ren
+* sChDrct
+* sAttr
+* sDirPat
+* stat
+* statfs
+* trunc
+* symlnk
+* unlnk
+* lookLI
+* statLI
+* revalLI
+* openLI
+* createLI
+* hardlnk
+* flckAp
+* flckEn
+* flckRg
+* dirparent
+* listXA
+* getXA
+* rmXA
+* setXA
+* mirror
+
+The collector adds a `filesystem` tag to all metrics

collectors/beegfsstorageMetric.go

@@ -0,0 +1,222 @@
+package collectors
+
+import (
+	"bufio"
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"io"
+	"os"
+	"os/exec"
+	"os/user"
+	"regexp"
+	"strconv"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+// Struct for the collector-specific JSON config
+type BeegfsStorageCollectorConfig struct {
+	Beegfs            string   `json:"beegfs_path"`
+	ExcludeMetrics    []string `json:"exclude_metrics,omitempty"`
+	ExcludeFilesystem []string `json:"exclude_filesystem"`
+}
+
+type BeegfsStorageCollector struct {
+	metricCollector
+	tags    map[string]string
+	matches map[string]string
+	config  BeegfsStorageCollectorConfig
+	skipFS  map[string]struct{}
+}
+
+func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+	// Metrics
+	var storageStat_array = [18]string{
+		"sum", "ack", "sChDrct", "getFSize",
+		"sAttr", "statfs", "trunc", "close",
+		"fsync", "ops-rd", "MiB-rd/s", "ops-wr",
+		"MiB-wr/s", "gendbg", "hrtbeat", "remNode",
+		"storInf", "unlnk"}
+
+	m.name = "BeegfsStorageCollector"
+	m.setup()
+	m.parallel = true
+	// Set default beegfs-ctl binary
+
+	m.config.Beegfs = DEFAULT_BEEGFS_CMD
+
+	// Read JSON configuration
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &m.config)
+		if err != nil {
+			return err
+		}
+	}
+	println(m.config.Beegfs)
+	//create map with possible variables
+	m.matches = make(map[string]string)
+	for _, value := range storageStat_array {
+		_, skip := stringArrayContains(m.config.ExcludeMetrics, value)
+		if skip {
+			m.matches["other"] = "0"
+		} else {
+			m.matches["beegfs_cstorage_"+value] = "0"
+		}
+	}
+
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "BeegfsStorage",
+	}
+	m.tags = map[string]string{
+		"type":       "node",
+		"filesystem": "",
+	}
+	m.skipFS = make(map[string]struct{})
+	for _, fs := range m.config.ExcludeFilesystem {
+		m.skipFS[fs] = struct{}{}
+	}
+
+	// Beegfs file system statistics can only be queried by user root
+	user, err := user.Current()
+	if err != nil {
+		return fmt.Errorf("BeegfsStorageCollector.Init(): Failed to get current user: %v", err)
+	}
+	if user.Uid != "0" {
+		return fmt.Errorf("BeegfsStorageCollector.Init(): BeeGFS file system statistics can only be queried by user root")
+	}
+
+	// Check if beegfs-ctl is in executable search path
+	_, err = exec.LookPath(m.config.Beegfs)
+	if err != nil {
+		return fmt.Errorf("BeegfsStorageCollector.Init(): Failed to find beegfs-ctl binary '%s': %v", m.config.Beegfs, err)
+	}
+	m.init = true
+	return nil
+}
+
+func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	if !m.init {
+		return
+	}
+	//get mounpoint
+	buffer, _ := os.ReadFile(string("/proc/mounts"))
+	mounts := strings.Split(string(buffer), "\n")
+	var mountpoints []string
+	for _, line := range mounts {
+		if len(line) == 0 {
+			continue
+		}
+		f := strings.Fields(line)
+		if strings.Contains(f[0], "beegfs_ondemand") {
+			// Skip excluded filesystems
+			if _, skip := m.skipFS[f[1]]; skip {
+				continue
+			}
+			mountpoints = append(mountpoints, f[1])
+		}
+	}
+	if len(mountpoints) == 0 {
+		return
+	}
+	// collects stats for each BeeGFS on Demand FS
+	for _, mountpoint := range mountpoints {
+		m.tags["filesystem"] = mountpoint
+
+		// bwwgfs-ctl:
+		// --clientstats: Show client IO statistics.
+		// --nodetype=meta: The node type to query (meta, storage).
+		// --interval:
+		// --mount=/mnt/beeond/: Which mount point
+		//cmd := exec.Command(m.config.Beegfs, "/root/mc/test.txt")
+		mountoption := "--mount=" + mountpoint
+		cmd := exec.Command(m.config.Beegfs, "--clientstats",
+			"--nodetype=storage", mountoption, "--allstats")
+		cmd.Stdin = strings.NewReader("\n")
+		cmdStdout := new(bytes.Buffer)
+		cmdStderr := new(bytes.Buffer)
+		cmd.Stdout = cmdStdout
+		cmd.Stderr = cmdStderr
+		err := cmd.Run()
+		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)
+			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stderr: \"%s\"\n", string(data))
+			data, _ = io.ReadAll(cmdStdout)
+			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stdout: \"%s\"\n", string(data))
+			return
+		}
+		// Read I/O statistics
+		scanner := bufio.NewScanner(cmdStdout)
+
+		sumLine := regexp.MustCompile(`^Sum:\s+\d+\s+\[[a-zA-Z]+\]+`)
+		//Line := regexp.MustCompile(`^(.*)\s+(\d)+\s+\[([a-zA-Z]+)\]+`)
+		statsLine := regexp.MustCompile(`^(.*?)\s+?(\d.*?)$`)
+		singleSpacePattern := regexp.MustCompile(`\s+`)
+		removePattern := regexp.MustCompile(`[\[|\]]`)
+
+		for scanner.Scan() {
+			readLine := scanner.Text()
+			//fmt.Println(readLine)
+			// Jump few lines, we only want the I/O stats from nodes
+			if !sumLine.MatchString(readLine) {
+				continue
+			}
+
+			match := statsLine.FindStringSubmatch(readLine)
+			// nodeName = "Sum:" or would be nodes
+			// nodeName := match[1]
+			//Remove multiple whitespaces
+			dummy := removePattern.ReplaceAllString(match[2], " ")
+			metaStats := strings.TrimSpace(singleSpacePattern.ReplaceAllString(dummy, " "))
+			split := strings.Split(metaStats, " ")
+
+			// fill map with values
+			// split[i+1] = mdname
+			// split[i] = amount of operations
+			for i := 0; i <= len(split)-1; i += 2 {
+				if _, ok := m.matches[split[i+1]]; ok {
+					m.matches["beegfs_cstorage_"+split[i+1]] = split[i]
+					//m.matches[split[i+1]] = split[i]
+				} else {
+					f1, err := strconv.ParseFloat(m.matches["other"], 32)
+					if err != nil {
+						cclog.ComponentError(
+							m.name,
+							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
+						continue
+					}
+					f2, err := strconv.ParseFloat(split[i], 32)
+					if err != nil {
+						cclog.ComponentError(
+							m.name,
+							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
+						continue
+					}
+					m.matches["beegfs_cstorage_other"] = fmt.Sprintf("%f", f1+f2)
+				}
+			}
+
+			for key, data := range m.matches {
+				value, _ := strconv.ParseFloat(data, 32)
+				y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+				if err == nil {
+					output <- y
+				}
+			}
+		}
+	}
+}
+
+func (m *BeegfsStorageCollector) Close() {
+	m.init = false
+}

collectors/beegfsstorageMetric.md

@@ -0,0 +1,55 @@
+## `BeeGFS on Demand` collector
+This Collector is to collect BeeGFS on Demand (BeeOND) storage stats.
+
+```json
+  "beegfs_storage": {
+	"beegfs_path": "/usr/bin/beegfs-ctl",
+    "exclude_filesystem": [
+      "/mnt/ignore_me"
+    ],
+    "exclude_metrics": [     
+          "ack",
+		  "storInf",
+		  "unlnk"
+    ]
+  }
+```
+
+The `BeeGFS On Demand (BeeOND)` collector uses the `beegfs-ctl` command to read performance metrics for BeeGFS filesystems.
+
+The reported filesystems can be filtered with the `exclude_filesystem` option
+in the configuration.
+
+The path to the `beegfs-ctl` command can be configured with the `beegfs_path` option
+in the configuration.
+
+When using the `exclude_metrics` option, the excluded metrics are summed as `other`.
+
+Important: The metrics listed below, are similar to the naming of BeeGFS. The Collector prefixes these with `beegfs_cstorage_`(beegfs client meta).
+For example beegfs metric `open`-> `beegfs_cstorage_`
+
+Note: BeeGFS FS offers many Metadata Information. Probably it makes sense to exlcude most of them. Nevertheless, these excluded metrics will be summed as `beegfs_cstorage_other`. 
+
+Available Metrics:
+
+* "sum"
+* "ack"
+* "sChDrct" 
+* "getFSize"
+* "sAttr"
+* "statfs"
+* "trunc"
+* "close"
+* "fsync"
+* "ops-rd"
+* "MiB-rd/s" 
+* "ops-wr"
+* "MiB-wr/s" 
+* "endbg" 
+* "hrtbeat"
+* "remNode"
+* "storInf"
+* "unlnk"
+
+
+The collector adds a `filesystem` tag to all metrics

collectors/collectorManager.go

@@ -6,46 +6,53 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 // Map of all available metric collectors
 var AvailableCollectors = map[string]MetricCollector{
 
-	"likwid":           new(LikwidCollector),
-	"loadavg":          new(LoadavgCollector),
-	"memstat":          new(MemstatCollector),
-	"netstat":          new(NetstatCollector),
-	"ibstat":           new(InfinibandCollector),
-	"ibstat_perfquery": new(InfinibandPerfQueryCollector),
-	"lustrestat":       new(LustreCollector),
-	"cpustat":          new(CpustatCollector),
-	"topprocs":         new(TopProcsCollector),
-	"nvidia":           new(NvidiaCollector),
-	"customcmd":        new(CustomCmdCollector),
-	"iostat":           new(IOstatCollector),
-	"diskstat":         new(DiskstatCollector),
-	"tempstat":         new(TempCollector),
-	"ipmistat":         new(IpmiCollector),
-	"gpfs":             new(GpfsCollector),
-	"cpufreq":          new(CPUFreqCollector),
-	"cpufreq_cpuinfo":  new(CPUFreqCpuInfoCollector),
-	"nfs3stat":         new(Nfs3Collector),
-	"nfs4stat":         new(Nfs4Collector),
-	"numastats":        new(NUMAStatsCollector),
+	"likwid":          new(LikwidCollector),
+	"loadavg":         new(LoadavgCollector),
+	"memstat":         new(MemstatCollector),
+	"netstat":         new(NetstatCollector),
+	"ibstat":          new(InfinibandCollector),
+	"lustrestat":      new(LustreCollector),
+	"lustre_jobstat":  new(LustreJobstatCollector),
+	"cpustat":         new(CpustatCollector),
+	"topprocs":        new(TopProcsCollector),
+	"nvidia":          new(NvidiaCollector),
+	"customcmd":       new(CustomCmdCollector),
+	"iostat":          new(IOstatCollector),
+	"diskstat":        new(DiskstatCollector),
+	"tempstat":        new(TempCollector),
+	"ipmistat":        new(IpmiCollector),
+	"gpfs":            new(GpfsCollector),
+	"cpufreq":         new(CPUFreqCollector),
+	"cpufreq_cpuinfo": new(CPUFreqCpuInfoCollector),
+	"nfs3stat":        new(Nfs3Collector),
+	"nfs4stat":        new(Nfs4Collector),
+	"numastats":       new(NUMAStatsCollector),
+	"beegfs_meta":     new(BeegfsMetaCollector),
+	"beegfs_storage":  new(BeegfsStorageCollector),
+	"rocm_smi":        new(RocmSmiCollector),
+	"schedstat":       new(SchedstatCollector),
 }
 
 // Metric collector manager data structure
 type collectorManager struct {
-	collectors []MetricCollector          // List of metric collectors to use
-	output     chan lp.CCMetric           // Output channels
-	done       chan bool                  // channel to finish / stop metric collector manager
-	ticker     mct.MultiChanTicker        // periodically ticking once each interval
-	duration   time.Duration              // duration (for metrics that measure over a given duration)
-	wg         *sync.WaitGroup            // wait group for all goroutines in cc-metric-collector
-	config     map[string]json.RawMessage // json encoded config for collector manager
+	collectors   []MetricCollector          // List of metric collectors to read in parallel
+	serial       []MetricCollector          // List of metric collectors to read serially
+	output       chan lp.CCMetric           // Output channels
+	done         chan bool                  // channel to finish / stop metric collector manager
+	ticker       mct.MultiChanTicker        // periodically ticking once each interval
+	duration     time.Duration              // duration (for metrics that measure over a given duration)
+	wg           *sync.WaitGroup            // wait group for all goroutines in cc-metric-collector
+	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
@@ -65,6 +72,7 @@ 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
@@ -99,7 +107,11 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
 			continue
 		}
 		cclog.ComponentDebug("CollectorManager", "ADD COLLECTOR", collector.Name())
-		cm.collectors = append(cm.collectors, collector)
+		if collector.Parallel() {
+			cm.collectors = append(cm.collectors, collector)
+		} else {
+			cm.serial = append(cm.serial, collector)
+		}
 	}
 	return nil
 }
@@ -115,6 +127,10 @@ 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()
 			}
@@ -129,7 +145,26 @@ 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

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 //
@@ -48,6 +48,7 @@ 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",
@@ -57,7 +58,7 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 	const cpuInfoFile = "/proc/cpuinfo"
 	file, err := os.Open(cpuInfoFile)
 	if err != nil {
-		return fmt.Errorf("Failed to open file '%s': %v", cpuInfoFile, err)
+		return fmt.Errorf("failed to open file '%s': %v", cpuInfoFile, err)
 	}
 	defer file.Close()
 
@@ -106,14 +107,14 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 			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)
+				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)
+				return fmt.Errorf("unable to convert physicalPackageID '%s' to int64: %v", physicalPackageID, err)
 			}
 
 			// increase maximun socket / package ID, when required
@@ -150,7 +151,7 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 		t.numNonHT = numNonHT
 		t.numNonHT_int = numNonHT_int
 		t.tagSet = map[string]string{
-			"type":       "cpu",
+			"type":       "hwthread",
 			"type-id":    t.processor,
 			"package_id": t.physicalPackageID,
 		}

collectors/cpufreqCpuinfoMetric.md

@@ -4,7 +4,7 @@
   "cpufreq_cpuinfo": {}
 ```
 
-The `cpufreq_cpuinfo` collector reads the clock frequency from `/proc/cpuinfo` and outputs a handful **cpu** metrics.
+The `cpufreq_cpuinfo` collector reads the clock frequency from `/proc/cpuinfo` and outputs a handful **hwthread** metrics.
 
 Metrics:
 * `cpufreq`

collectors/cpufreqMetric.go

@@ -3,14 +3,14 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"golang.org/x/sys/unix"
 )
 
@@ -53,6 +53,7 @@ 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 {
@@ -62,7 +63,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	m.meta = map[string]string{
 		"source": m.name,
 		"group":  "CPU",
-		"unit":   "MHz",
+		"unit":   "Hz",
 	}
 
 	// Loop for all CPU directories
@@ -70,10 +71,10 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	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)
+		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)
+		return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
 	}
 
 	// Initialize CPU topology
@@ -82,38 +83,38 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 		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)
+			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)
+		line, err := os.ReadFile(physicalPackageIDFile)
 		if err != nil {
-			return fmt.Errorf("Unable to read physical package ID from file '%s': %v", physicalPackageIDFile, err)
+			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)
+			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)
+		line, err = os.ReadFile(coreIDFile)
 		if err != nil {
-			return fmt.Errorf("Unable to read core ID from file '%s': %v", coreIDFile, err)
+			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)
+			return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
 		}
 
 		// Check access to current frequency file
 		scalingCurFreqFile := filepath.Join(cpuDir, "cpufreq", "scaling_cur_freq")
 		err = unix.Access(scalingCurFreqFile, unix.R_OK)
 		if err != nil {
-			return fmt.Errorf("Unable to access file '%s': %v", scalingCurFreqFile, err)
+			return fmt.Errorf("unable to access file '%s': %v", scalingCurFreqFile, err)
 		}
 
 		t := &m.topology[processor_int]
@@ -161,7 +162,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 		t.numNonHT = numNonHT
 		t.numNonHT_int = numNonHT_int
 		t.tagSet = map[string]string{
-			"type":       "cpu",
+			"type":       "hwthread",
 			"type-id":    t.processor,
 			"package_id": t.physicalPackageID,
 		}
@@ -187,7 +188,7 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		}
 
 		// Read current frequency
-		line, err := ioutil.ReadFile(t.scalingCurFreqFile)
+		line, err := os.ReadFile(t.scalingCurFreqFile)
 		if err != nil {
 			cclog.ComponentError(
 				m.name,

collectors/cpufreqMetric.md

@@ -5,7 +5,7 @@
   }
 ```
 
-The `cpufreq` collector reads the clock frequency from `/sys/devices/system/cpu/cpu*/cpufreq` and outputs a handful **cpu** metrics.
+The `cpufreq` collector reads the clock frequency from `/sys/devices/system/cpu/cpu*/cpufreq` and outputs a handful **hwthread** metrics.
 
 Metrics:
 * `cpufreq`

collectors/cpustatMetric.go

@@ -9,8 +9,9 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	sysconf "github.com/tklauser/go-sysconf"
 )
 
 const CPUSTATFILE = `/proc/stat`
@@ -21,16 +22,18 @@ type CpustatCollectorConfig struct {
 
 type CpustatCollector struct {
 	metricCollector
-	config          CpustatCollectorConfig
-	matches         map[string]int
-	cputags         map[string]map[string]string
-	nodetags        map[string]string
-	num_cpus_metric lp.CCMetric
+	config        CpustatCollectorConfig
+	lastTimestamp time.Time // Store time stamp of last tick to derive values
+	matches       map[string]int
+	cputags       map[string]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 {
@@ -76,36 +79,48 @@ 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.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
+		if 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": "cpu", "type-id": fmt.Sprintf("%d", cpu)}
+			m.cputags[linefields[0]] = map[string]string{"type": "hwthread", "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) {
+func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
 	values := make(map[string]float64)
-	total := 0.0
+	clktck, _ := sysconf.Sysconf(sysconf.SC_CLK_TCK)
 	for match, index := range m.matches {
 		if len(match) > 0 {
 			x, err := strconv.ParseInt(linefields[index], 0, 64)
 			if err == nil {
-				values[match] = float64(x)
-				total += values[match]
+				vdiff := x - m.olddata[linefields[0]][match]
+				m.olddata[linefields[0]][match] = x // Store new value for next run
+				values[match] = float64(vdiff) / float64(tsdelta.Seconds()) / float64(clktck)
 			}
 		}
 	}
-	t := time.Now()
+
 	for name, value := range values {
-		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
 		}
@@ -117,6 +132,9 @@ 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())
@@ -128,9 +146,9 @@ 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)
+			m.parseStatLine(linefields, m.nodetags, output, now, tsdelta)
 		} else if strings.HasPrefix(linefields[0], "cpu") {
-			m.parseStatLine(linefields, m.cputags[linefields[0]], output)
+			m.parseStatLine(linefields, m.cputags[linefields[0]], output, now, tsdelta)
 			num_cpus++
 		}
 	}
@@ -139,11 +157,13 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		m.nodetags,
 		m.meta,
 		map[string]interface{}{"value": int(num_cpus)},
-		time.Now(),
+		now,
 	)
 	if err == nil {
 		output <- num_cpus_metric
 	}
+
+	m.lastTimestamp = now
 }
 
 func (m *CpustatCollector) Close() {

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/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 )
 
@@ -33,6 +33,7 @@ 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)
@@ -52,7 +53,7 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
 		}
 	}
 	for _, f := range m.config.Files {
-		_, err = ioutil.ReadFile(f)
+		_, err = os.ReadFile(f)
 		if err == nil {
 			m.files = append(m.files, f)
 		} else {
@@ -61,7 +62,7 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
 		}
 	}
 	if len(m.files) == 0 && len(m.commands) == 0 {
-		return errors.New("No metrics to collect")
+		return errors.New("no metrics to collect")
 	}
 	m.handler = influx.NewMetricHandler()
 	m.parser = influx.NewParser(m.handler)
@@ -105,7 +106,7 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 		}
 	}
 	for _, file := range m.files {
-		buffer, err := ioutil.ReadFile(file)
+		buffer, err := os.ReadFile(file)
 		if err != nil {
 			log.Print(err)
 			return

collectors/diskstatMetric.go

@@ -3,14 +3,13 @@ package collectors
 import (
 	"bufio"
 	"encoding/json"
-	"fmt"
 	"os"
 	"strings"
 	"syscall"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 //	"log"
@@ -30,6 +29,7 @@ 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 {
@@ -78,11 +78,17 @@ 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 {
-			fmt.Println(err.Error())
-			return
+			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)
@@ -97,9 +103,11 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric
 			y.AddMeta("unit", "GBytes")
 			output <- y
 		}
-		perc := (100 * (total - free)) / total
-		if perc > part_max_used {
-			part_max_used = perc
+		if total > 0 {
+			perc := (100 * (total - free)) / total
+			if perc > part_max_used {
+				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/ioutil"
+	"io"
 	"log"
 	"os/exec"
 	"os/user"
@@ -13,18 +13,28 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
+const DEFAULT_GPFS_CMD = "mmpmon"
+
+type GpfsCollectorLastState struct {
+	bytesRead    int64
+	bytesWritten int64
+}
+
 type GpfsCollector struct {
 	metricCollector
 	tags   map[string]string
 	config struct {
 		Mmpmon            string   `json:"mmpmon_path,omitempty"`
 		ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
+		SendBandwidths    bool     `json:"send_bandwidths"`
 	}
-	skipFS map[string]struct{}
+	skipFS        map[string]struct{}
+	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
+	lastState     map[string]GpfsCollectorLastState
 }
 
 func (m *GpfsCollector) Init(config json.RawMessage) error {
@@ -36,9 +46,10 @@ 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 = "/usr/lpp/mmfs/bin/mmpmon"
+	m.config.Mmpmon = DEFAULT_GPFS_CMD
 
 	// Read JSON configuration
 	if len(config) > 0 {
@@ -60,21 +71,23 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 	for _, fs := range m.config.ExcludeFilesystem {
 		m.skipFS[fs] = struct{}{}
 	}
+	m.lastState = make(map[string]GpfsCollectorLastState)
 
 	// GPFS / IBM Spectrum Scale file system statistics can only be queried by user root
 	user, err := user.Current()
 	if err != nil {
-		return fmt.Errorf("Failed to get current user: %v", err)
+		return fmt.Errorf("failed to get current user: %v", err)
 	}
 	if user.Uid != "0" {
 		return fmt.Errorf("GPFS file system statistics can only be queried by user root")
 	}
 
 	// Check if mmpmon is in executable search path
-	_, err = exec.LookPath(m.config.Mmpmon)
+	p, err := exec.LookPath(m.config.Mmpmon)
 	if err != nil {
-		return fmt.Errorf("Failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err)
+		return fmt.Errorf("failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err)
 	}
+	m.config.Mmpmon = p
 
 	m.init = true
 	return nil
@@ -86,6 +99,13 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 		return
 	}
 
+	// Current time stamp
+	now := time.Now()
+	// time difference to last time stamp
+	timeDiff := now.Sub(m.lastTimestamp).Seconds()
+	// Save current timestamp
+	m.lastTimestamp = now
+
 	// mmpmon:
 	// -p: generate output that can be parsed
 	// -s: suppress the prompt on input
@@ -98,8 +118,8 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	cmd.Stderr = cmdStderr
 	err := cmd.Run()
 	if err != nil {
-		dataStdErr, _ := ioutil.ReadAll(cmdStderr)
-		dataStdOut, _ := ioutil.ReadAll(cmdStdout)
+		dataStdErr, _ := io.ReadAll(cmdStderr)
+		dataStdOut, _ := io.ReadAll(cmdStdout)
 		cclog.ComponentError(
 			m.name,
 			fmt.Sprintf("Read(): Failed to execute command \"%s\": %v\n", cmd.String(), err),
@@ -144,8 +164,19 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 			continue
 		}
 
+		// Add filesystem tag
 		m.tags["filesystem"] = filesystem
 
+		// Create initial last state
+		if m.config.SendBandwidths {
+			if _, ok := m.lastState[filesystem]; !ok {
+				m.lastState[filesystem] = GpfsCollectorLastState{
+					bytesRead:    -1,
+					bytesWritten: -1,
+				}
+			}
+		}
+
 		// return code
 		rc, err := strconv.Atoi(key_value["_rc_"])
 		if err != nil {
@@ -188,6 +219,14 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 		if y, err := lp.New("gpfs_bytes_read", m.tags, m.meta, map[string]interface{}{"value": bytesRead}, timestamp); err == nil {
 			output <- y
 		}
+		if m.config.SendBandwidths {
+			if lastBytesRead := m.lastState[filesystem].bytesRead; lastBytesRead >= 0 {
+				bwRead := float64(bytesRead-lastBytesRead) / timeDiff
+				if y, err := lp.New("gpfs_bw_read", m.tags, m.meta, map[string]interface{}{"value": bwRead}, timestamp); err == nil {
+					output <- y
+				}
+			}
+		}
 
 		// bytes written
 		bytesWritten, err := strconv.ParseInt(key_value["_bw_"], 10, 64)
@@ -200,6 +239,21 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 		if y, err := lp.New("gpfs_bytes_written", m.tags, m.meta, map[string]interface{}{"value": bytesWritten}, timestamp); err == nil {
 			output <- y
 		}
+		if m.config.SendBandwidths {
+			if lastBytesWritten := m.lastState[filesystem].bytesRead; lastBytesWritten >= 0 {
+				bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff
+				if y, err := lp.New("gpfs_bw_write", m.tags, m.meta, map[string]interface{}{"value": bwWrite}, timestamp); err == nil {
+					output <- y
+				}
+			}
+		}
+
+		if m.config.SendBandwidths {
+			m.lastState[filesystem] = GpfsCollectorLastState{
+				bytesRead:    bytesRead,
+				bytesWritten: bytesWritten,
+			}
+		}
 
 		// number of opens
 		numOpens, err := strconv.ParseInt(key_value["_oc_"], 10, 64)

collectors/gpfsMetric.md

@@ -5,7 +5,8 @@
     "mmpmon_path": "/path/to/mmpmon",
     "exclude_filesystem": [
       "fs1"
-    ]
+    ],
+    "send_bandwidths" : true
   }
 ```
 
@@ -16,15 +17,18 @@ The reported filesystems can be filtered with the `exclude_filesystem` option
 in the configuration.
 
 The path to the `mmpmon` command can be configured with the `mmpmon_path` option
-in the configuration.
+in the configuration. If nothing is set, the collector searches in `$PATH` for `mmpmon`.
+
 
 Metrics:
-* `bytes_read`
+* `gpfs_bytes_read`
 * `gpfs_bytes_written`
 * `gpfs_num_opens`
 * `gpfs_num_closes`
 * `gpfs_num_reads`
 * `gpfs_num_readdirs`
 * `gpfs_num_inode_updates`
+* `gpfs_bw_read` (if `send_bandwidths == true`)
+* `gpfs_bw_write` (if `send_bandwidths == true`)
 
 The collector adds a `filesystem` tag to all metrics

collectors/infinibandMetric.go

@@ -2,11 +2,10 @@ package collectors
 
 import (
 	"fmt"
-	"io/ioutil"
 	"os"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"golang.org/x/sys/unix"
 
 	"encoding/json"
@@ -16,22 +15,32 @@ import (
 	"time"
 )
 
-const IB_BASEPATH = `/sys/class/infiniband/`
+const IB_BASEPATH = "/sys/class/infiniband/"
+
+type InfinibandCollectorMetric struct {
+	path  string
+	unit  string
+	scale int64
+}
 
 type InfinibandCollectorInfo struct {
-	LID              string            // IB local Identifier (LID)
-	device           string            // IB device
-	port             string            // IB device port
-	portCounterFiles map[string]string // mapping counter name -> sysfs file
-	tagSet           map[string]string // corresponding tag list
+	LID              string                               // IB local Identifier (LID)
+	device           string                               // IB device
+	port             string                               // IB device port
+	portCounterFiles map[string]InfinibandCollectorMetric // mapping counter name -> InfinibandCollectorMetric
+	tagSet           map[string]string                    // corresponding tag list
+	lastState        map[string]int64                     // State from last measurement
 }
 
 type InfinibandCollector struct {
 	metricCollector
 	config struct {
-		ExcludeDevices []string `json:"exclude_devices,omitempty"` // IB device to exclude e.g. mlx5_0
+		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
+		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
 }
 
 // Init initializes the Infiniband collector by walking through files below IB_BASEPATH
@@ -45,10 +54,16 @@ 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",
 	}
+
+	// Set default configuration,
+	m.config.SendAbsoluteValues = true
+	m.config.SendDerivedValues = false
+	// Read configuration file, allow overwriting default config
 	if len(config) > 0 {
 		err = json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -60,16 +75,16 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	globPattern := filepath.Join(IB_BASEPATH, "*", "ports", "*")
 	ibDirs, err := filepath.Glob(globPattern)
 	if err != nil {
-		return fmt.Errorf("Unable to glob files with pattern %s: %v", globPattern, err)
+		return fmt.Errorf("unable to glob files with pattern %s: %v", globPattern, err)
 	}
 	if ibDirs == nil {
-		return fmt.Errorf("Unable to find any directories with pattern %s", globPattern)
+		return fmt.Errorf("unable to find any directories with pattern %s", globPattern)
 	}
 
 	for _, path := range ibDirs {
 
 		// Skip, when no LID is assigned
-		line, err := ioutil.ReadFile(filepath.Join(path, "lid"))
+		line, err := os.ReadFile(filepath.Join(path, "lid"))
 		if err != nil {
 			continue
 		}
@@ -97,19 +112,25 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 
 		// Check access to counter files
 		countersDir := filepath.Join(path, "counters")
-		portCounterFiles := map[string]string{
-			"ib_recv":      filepath.Join(countersDir, "port_rcv_data"),
-			"ib_xmit":      filepath.Join(countersDir, "port_xmit_data"),
-			"ib_recv_pkts": filepath.Join(countersDir, "port_rcv_packets"),
-			"ib_xmit_pkts": filepath.Join(countersDir, "port_xmit_packets"),
+		portCounterFiles := map[string]InfinibandCollectorMetric{
+			"ib_recv":      {path: filepath.Join(countersDir, "port_rcv_data"), unit: "bytes", scale: 4},
+			"ib_xmit":      {path: filepath.Join(countersDir, "port_xmit_data"), unit: "bytes", scale: 4},
+			"ib_recv_pkts": {path: filepath.Join(countersDir, "port_rcv_packets"), unit: "packets", scale: 1},
+			"ib_xmit_pkts": {path: filepath.Join(countersDir, "port_xmit_packets"), unit: "packets", scale: 1},
 		}
-		for _, counterFile := range portCounterFiles {
-			err := unix.Access(counterFile, unix.R_OK)
+		for _, counter := range portCounterFiles {
+			err := unix.Access(counter.path, unix.R_OK)
 			if err != nil {
-				return fmt.Errorf("Unable to access %s: %v", counterFile, err)
+				return fmt.Errorf("unable to access %s: %v", counter.path, err)
 			}
 		}
 
+		// Initialize last state
+		lastState := make(map[string]int64)
+		for counter := range portCounterFiles {
+			lastState[counter] = -1
+		}
+
 		m.info = append(m.info,
 			&InfinibandCollectorInfo{
 				LID:              LID,
@@ -122,11 +143,12 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 					"port":   port,
 					"lid":    LID,
 				},
+				lastState: lastState,
 			})
 	}
 
 	if len(m.info) == 0 {
-		return fmt.Errorf("Found no IB devices")
+		return fmt.Errorf("found no IB devices")
 	}
 
 	m.init = true
@@ -141,17 +163,27 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 		return
 	}
 
+	// Current time stamp
 	now := time.Now()
+	// time difference to last time stamp
+	timeDiff := now.Sub(m.lastTimestamp).Seconds()
+	// Save current timestamp
+	m.lastTimestamp = now
+
 	for _, info := range m.info {
-		for counterName, counterFile := range info.portCounterFiles {
-			line, err := ioutil.ReadFile(counterFile)
+		for counterName, counterDef := range info.portCounterFiles {
+
+			// Read counter file
+			line, err := os.ReadFile(counterDef.path)
 			if err != nil {
 				cclog.ComponentError(
 					m.name,
-					fmt.Sprintf("Read(): Failed to read from file '%s': %v", counterFile, err))
+					fmt.Sprintf("Read(): Failed to read from file '%s': %v", counterDef.path, err))
 				continue
 			}
 			data := strings.TrimSpace(string(line))
+
+			// convert counter to int64
 			v, err := strconv.ParseInt(data, 10, 64)
 			if err != nil {
 				cclog.ComponentError(
@@ -159,8 +191,28 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterName, data, err))
 				continue
 			}
-			if y, err := lp.New(counterName, info.tagSet, m.meta, map[string]interface{}{"value": v}, now); err == nil {
-				output <- y
+			// Scale raw value
+			v *= counterDef.scale
+
+			// Send absolut values
+			if m.config.SendAbsoluteValues {
+				if y, err := lp.New(counterName, info.tagSet, m.meta, map[string]interface{}{"value": v}, now); err == nil {
+					y.AddMeta("unit", counterDef.unit)
+					output <- y
+				}
+			}
+
+			// Send derived values
+			if m.config.SendDerivedValues {
+				if info.lastState[counterName] >= 0 {
+					rate := float64((v - info.lastState[counterName])) / timeDiff
+					if y, err := lp.New(counterName+"_bw", info.tagSet, m.meta, map[string]interface{}{"value": rate}, now); err == nil {
+						y.AddMeta("unit", counterDef.unit+"/sec")
+						output <- y
+					}
+				}
+				// Save current state
+				info.lastState[counterName] = v
 			}
 		}
 

collectors/infinibandMetric.md

@@ -5,7 +5,9 @@
   "ibstat": {
     "exclude_devices": [
       "mlx4"
-    ]
+    ],
+    "send_abs_values": true,
+    "send_derived_values": true
   }
 ```
 
@@ -22,5 +24,9 @@ Metrics:
 * `ib_xmit`
 * `ib_recv_pkts`
 * `ib_xmit_pkts`
+* `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`)
+* `ib_xmit_pkts_bw` (if `send_derived_values == true`)
 
 The collector adds a `device` tag to all metrics

collectors/infinibandPerfQueryMetric.go

@@ -1,232 +0,0 @@
-package collectors
-
-import (
-	"fmt"
-	"io/ioutil"
-	"log"
-	"os/exec"
-
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-
-	//	"os"
-	"encoding/json"
-	"errors"
-	"path/filepath"
-	"strconv"
-	"strings"
-	"time"
-)
-
-const PERFQUERY = `/usr/sbin/perfquery`
-
-type InfinibandPerfQueryCollector struct {
-	metricCollector
-	tags   map[string]string
-	lids   map[string]map[string]string
-	config struct {
-		ExcludeDevices []string `json:"exclude_devices,omitempty"`
-		PerfQueryPath  string   `json:"perfquery_path"`
-	}
-}
-
-func (m *InfinibandPerfQueryCollector) Init(config json.RawMessage) error {
-	var err error
-	m.name = "InfinibandCollectorPerfQuery"
-	m.setup()
-	m.meta = map[string]string{"source": m.name, "group": "Network"}
-	m.tags = map[string]string{"type": "node"}
-	if len(config) > 0 {
-		err = json.Unmarshal(config, &m.config)
-		if err != nil {
-			return err
-		}
-	}
-	if len(m.config.PerfQueryPath) == 0 {
-		path, err := exec.LookPath("perfquery")
-		if err == nil {
-			m.config.PerfQueryPath = path
-		}
-	}
-	m.lids = make(map[string]map[string]string)
-	p := fmt.Sprintf("%s/*/ports/*/lid", string(IB_BASEPATH))
-	files, err := filepath.Glob(p)
-	if err != nil {
-		return err
-	}
-	for _, f := range files {
-		lid, err := ioutil.ReadFile(f)
-		if err == nil {
-			plist := strings.Split(strings.Replace(f, string(IB_BASEPATH), "", -1), "/")
-			skip := false
-			for _, d := range m.config.ExcludeDevices {
-				if d == plist[0] {
-					skip = true
-				}
-			}
-			if !skip {
-				m.lids[plist[0]] = make(map[string]string)
-				m.lids[plist[0]][plist[2]] = string(lid)
-			}
-		}
-	}
-
-	for _, ports := range m.lids {
-		for port, lid := range ports {
-			args := fmt.Sprintf("-r %s %s 0xf000", lid, port)
-			command := exec.Command(m.config.PerfQueryPath, args)
-			command.Wait()
-			_, err := command.Output()
-			if err != nil {
-				return fmt.Errorf("Failed to execute %s: %v", m.config.PerfQueryPath, err)
-			}
-		}
-	}
-
-	if len(m.lids) == 0 {
-		return errors.New("No usable IB devices")
-	}
-
-	m.init = true
-	return nil
-}
-
-func (m *InfinibandPerfQueryCollector) doPerfQuery(cmd string, dev string, lid string, port string, tags map[string]string, output chan lp.CCMetric) error {
-
-	args := fmt.Sprintf("-r %s %s 0xf000", lid, port)
-	command := exec.Command(cmd, args)
-	command.Wait()
-	stdout, err := command.Output()
-	if err != nil {
-		log.Print(err)
-		return err
-	}
-	ll := strings.Split(string(stdout), "\n")
-
-	for _, line := range ll {
-		if strings.HasPrefix(line, "PortRcvData") || strings.HasPrefix(line, "RcvData") {
-			lv := strings.Fields(line)
-			v, err := strconv.ParseFloat(lv[1], 64)
-			if err == nil {
-				y, err := lp.New("ib_recv", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-		if strings.HasPrefix(line, "PortXmitData") || strings.HasPrefix(line, "XmtData") {
-			lv := strings.Fields(line)
-			v, err := strconv.ParseFloat(lv[1], 64)
-			if err == nil {
-				y, err := lp.New("ib_xmit", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-		if strings.HasPrefix(line, "PortRcvPkts") || strings.HasPrefix(line, "RcvPkts") {
-			lv := strings.Fields(line)
-			v, err := strconv.ParseFloat(lv[1], 64)
-			if err == nil {
-				y, err := lp.New("ib_recv_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-		if strings.HasPrefix(line, "PortXmitPkts") || strings.HasPrefix(line, "XmtPkts") {
-			lv := strings.Fields(line)
-			v, err := strconv.ParseFloat(lv[1], 64)
-			if err == nil {
-				y, err := lp.New("ib_xmit_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-		if strings.HasPrefix(line, "PortRcvPkts") || strings.HasPrefix(line, "RcvPkts") {
-			lv := strings.Fields(line)
-			v, err := strconv.ParseFloat(lv[1], 64)
-			if err == nil {
-				y, err := lp.New("ib_recv_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-		if strings.HasPrefix(line, "PortXmitPkts") || strings.HasPrefix(line, "XmtPkts") {
-			lv := strings.Fields(line)
-			v, err := strconv.ParseFloat(lv[1], 64)
-			if err == nil {
-				y, err := lp.New("ib_xmit_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-	}
-	return nil
-}
-
-func (m *InfinibandPerfQueryCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-
-	if m.init {
-		for dev, ports := range m.lids {
-			for port, lid := range ports {
-				tags := map[string]string{
-					"type":   "node",
-					"device": dev,
-					"port":   port,
-					"lid":    lid}
-				path := fmt.Sprintf("%s/%s/ports/%s/counters/", string(IB_BASEPATH), dev, port)
-				buffer, err := ioutil.ReadFile(fmt.Sprintf("%s/port_rcv_data", path))
-				if err == nil {
-					data := strings.Replace(string(buffer), "\n", "", -1)
-					v, err := strconv.ParseFloat(data, 64)
-					if err == nil {
-						y, err := lp.New("ib_recv", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-						if err == nil {
-							output <- y
-						}
-					}
-				}
-				buffer, err = ioutil.ReadFile(fmt.Sprintf("%s/port_xmit_data", path))
-				if err == nil {
-					data := strings.Replace(string(buffer), "\n", "", -1)
-					v, err := strconv.ParseFloat(data, 64)
-					if err == nil {
-						y, err := lp.New("ib_xmit", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-						if err == nil {
-							output <- y
-						}
-					}
-				}
-				buffer, err = ioutil.ReadFile(fmt.Sprintf("%s/port_rcv_packets", path))
-				if err == nil {
-					data := strings.Replace(string(buffer), "\n", "", -1)
-					v, err := strconv.ParseFloat(data, 64)
-					if err == nil {
-						y, err := lp.New("ib_recv_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-						if err == nil {
-							output <- y
-						}
-					}
-				}
-				buffer, err = ioutil.ReadFile(fmt.Sprintf("%s/port_xmit_packets", path))
-				if err == nil {
-					data := strings.Replace(string(buffer), "\n", "", -1)
-					v, err := strconv.ParseFloat(data, 64)
-					if err == nil {
-						y, err := lp.New("ib_xmit_pkts", tags, m.meta, map[string]interface{}{"value": float64(v)}, time.Now())
-						if err == nil {
-							output <- y
-						}
-					}
-				}
-			}
-		}
-	}
-}
-
-func (m *InfinibandPerfQueryCollector) Close() {
-	m.init = false
-}

collectors/infinibandPerfQueryMetric.md

@@ -1,28 +0,0 @@
-
-## `ibstat_perfquery` collector
-
-```json
-  "ibstat_perfquery": {
-    "perfquery_path": "/path/to/perfquery",
-    "exclude_devices": [
-      "mlx4"
-    ]
-  }
-```
-
-The `ibstat_perfquery` collector includes all Infiniband devices that can be
-found below `/sys/class/infiniband/` and where any of the ports provides a
-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 calls the `perfquery` command. The path to the
-`perfquery` command can be configured with the `perfquery_path` option in the configuration
-
-Metrics:
-* `ib_recv`
-* `ib_xmit`
-* `ib_recv_pkts`
-* `ib_xmit_pkts`
-
-The collector adds a `device` tag to all metrics

collectors/iostatMetric.go

@@ -4,8 +4,8 @@ import (
 	"bufio"
 	"os"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 
 	//	"log"
 	"encoding/json"
@@ -37,6 +37,7 @@ 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

@@ -10,7 +10,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const IPMITOOL_PATH = `ipmitool`
@@ -34,6 +34,7 @@ type IpmiCollector struct {
 func (m *IpmiCollector) Init(config json.RawMessage) error {
 	m.name = "IpmiCollector"
 	m.setup()
+	m.parallel = true
 	m.meta = map[string]string{"source": m.name, "group": "IPMI"}
 	m.config.IpmitoolPath = string(IPMITOOL_PATH)
 	m.config.IpmisensorsPath = string(IPMISENSORS_PATH)
@@ -54,7 +55,7 @@ func (m *IpmiCollector) Init(config json.RawMessage) error {
 		m.ipmisensors = p
 	}
 	if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
-		return errors.New("No IPMI reader found")
+		return errors.New("no IPMI reader found")
 	}
 	m.init = true
 	return nil

collectors/likwidMetric.go

@@ -12,64 +12,24 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"io/ioutil"
 	"math"
 	"os"
-	"regexp"
+	"os/signal"
+	"sort"
 	"strconv"
 	"strings"
+	"sync"
+	"syscall"
 	"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"
 )
 
-type MetricScope string
-
-const (
-	METRIC_SCOPE_HWTHREAD = iota
-	METRIC_SCOPE_CORE
-	METRIC_SCOPE_LLC
-	METRIC_SCOPE_NUMA
-	METRIC_SCOPE_DIE
-	METRIC_SCOPE_SOCKET
-	METRIC_SCOPE_NODE
-)
-
-func (ms MetricScope) String() string {
-	return string(ms)
-}
-
-func (ms MetricScope) Likwid() string {
-	LikwidDomains := map[string]string{
-		"cpu":        "",
-		"core":       "",
-		"llc":        "C",
-		"numadomain": "M",
-		"die":        "D",
-		"socket":     "S",
-		"node":       "N",
-	}
-	return LikwidDomains[string(ms)]
-}
-
-func (ms MetricScope) Granularity() int {
-	for i, g := range GetAllMetricScopes() {
-		if ms == g {
-			return i
-		}
-	}
-	return -1
-}
-
-func GetAllMetricScopes() []MetricScope {
-	return []MetricScope{"cpu" /*, "core", "llc", "numadomain", "die",*/, "socket", "node"}
-}
-
 const (
 	LIKWID_LIB_NAME       = "liblikwid.so"
 	LIKWID_LIB_DL_FLAGS   = dl.RTLD_LAZY | dl.RTLD_GLOBAL
@@ -77,18 +37,26 @@ const (
 )
 
 type LikwidCollectorMetricConfig struct {
-	Name string `json:"name"` // Name of the metric
-	Calc string `json:"calc"` // Calculation for the metric using
-	//Aggr        string      `json:"aggregation"` // if scope unequal to LIKWID metric scope, the values are combined (sum, min, max, mean or avg, median)
-	Scope       MetricScope `json:"scope"` // scope for calculation. subscopes are aggregated using the 'aggregation' function
-	Publish     bool        `json:"publish"`
-	granulatity MetricScope
+	Name    string `json:"name"` // Name of the metric
+	Calc    string `json:"calc"` // Calculation for the metric using
+	Type    string `json:"type"` // Metric type (aka node, socket, cpu, ...)
+	Publish bool   `json:"publish"`
+	Unit    string `json:"unit"` // Unit of metric if any
 }
 
 type LikwidCollectorEventsetConfig struct {
-	Events      map[string]string `json:"events"`
-	granulatity map[string]MetricScope
-	Metrics     []LikwidCollectorMetricConfig `json:"metrics"`
+	Events  map[string]string             `json:"events"`
+	Metrics []LikwidCollectorMetricConfig `json:"metrics"`
+}
+
+type LikwidEventsetConfig struct {
+	internal int
+	gid      C.int
+	eorder   []*C.char
+	estr     *C.char
+	go_estr  string
+	results  map[int]map[string]interface{}
+	metrics  map[int]map[string]float64
 }
 
 type LikwidCollectorConfig struct {
@@ -98,28 +66,29 @@ type LikwidCollectorConfig struct {
 	InvalidToZero  bool                            `json:"invalid_to_zero,omitempty"`
 	AccessMode     string                          `json:"access_mode,omitempty"`
 	DaemonPath     string                          `json:"accessdaemon_path,omitempty"`
+	LibraryPath    string                          `json:"liblikwid_path,omitempty"`
 }
 
 type LikwidCollector struct {
 	metricCollector
-	cpulist       []C.int
-	cpu2tid       map[int]int
-	sock2tid      map[int]int
-	scopeRespTids map[MetricScope]map[int]int
-	metrics       map[C.int]map[string]int
-	groups        []C.int
-	config        LikwidCollectorConfig
-	results       map[int]map[int]map[string]interface{}
-	mresults      map[int]map[int]map[string]float64
-	gmresults     map[int]map[string]float64
-	basefreq      float64
-	running       bool
+	cpulist      []C.int
+	cpu2tid      map[int]int
+	sock2tid     map[int]int
+	metrics      map[C.int]map[string]int
+	groups       []C.int
+	config       LikwidCollectorConfig
+	gmresults    map[int]map[string]float64
+	basefreq     float64
+	running      bool
+	initialized  bool
+	likwidGroups map[C.int]LikwidEventsetConfig
+	lock         sync.Mutex
 }
 
 type LikwidMetric struct {
 	name      string
 	search    string
-	scope     MetricScope
+	scope     string
 	group_idx int
 }
 
@@ -131,152 +100,101 @@ func eventsToEventStr(events map[string]string) string {
 	return strings.Join(elist, ",")
 }
 
-func getGranularity(counter, event string) MetricScope {
-	if strings.HasPrefix(counter, "PMC") || strings.HasPrefix(counter, "FIXC") {
-		return "cpu"
-	} else if strings.Contains(counter, "BOX") || strings.Contains(counter, "DEV") {
-		return "socket"
-	} else if strings.HasPrefix(counter, "PWR") {
-		if event == "RAPL_CORE_ENERGY" {
-			return "cpu"
-		} else {
-			return "socket"
+func genLikwidEventSet(input LikwidCollectorEventsetConfig) LikwidEventsetConfig {
+	tmplist := make([]string, 0)
+	clist := make([]string, 0)
+	for k := range input.Events {
+		clist = append(clist, k)
+	}
+	sort.Strings(clist)
+	elist := make([]*C.char, 0)
+	for _, k := range clist {
+		v := input.Events[k]
+		tmplist = append(tmplist, fmt.Sprintf("%s:%s", v, k))
+		c_counter := C.CString(k)
+		elist = append(elist, c_counter)
+	}
+	estr := strings.Join(tmplist, ",")
+	res := make(map[int]map[string]interface{})
+	met := make(map[int]map[string]float64)
+	for _, i := range topo.CpuList() {
+		res[i] = make(map[string]interface{})
+		for k := range input.Events {
+			res[i][k] = 0.0
+		}
+		met[i] = make(map[string]float64)
+		for _, v := range input.Metrics {
+			res[i][v.Name] = 0.0
 		}
 	}
-	return "unknown"
+	return LikwidEventsetConfig{
+		gid:     -1,
+		eorder:  elist,
+		estr:    C.CString(estr),
+		go_estr: estr,
+		results: res,
+		metrics: met,
+	}
+}
+
+func testLikwidMetricFormula(formula string, params []string) bool {
+	myparams := make(map[string]interface{})
+	for _, p := range params {
+		myparams[p] = float64(1.0)
+	}
+	_, err := agg.EvalFloat64Condition(formula, myparams)
+	return err == nil
 }
 
 func getBaseFreq() float64 {
+	files := []string{
+		"/sys/devices/system/cpu/cpu0/cpufreq/bios_limit",
+		"/sys/devices/system/cpu/cpu0/cpufreq/base_frequency",
+	}
 	var freq float64 = math.NaN()
-	C.power_init(0)
-	info := C.get_powerInfo()
-	if float64(info.baseFrequency) != 0 {
-		freq = float64(info.baseFrequency) * 1e3
-	} else {
-		buffer, err := ioutil.ReadFile("/sys/devices/system/cpu/cpu0/cpufreq/bios_limit")
+	for _, f := range files {
+		buffer, err := os.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) * 1e3
+				freq = float64(x)
+				break
 			}
 		}
 	}
-	return freq
-}
-
-func (m *LikwidCollector) initGranularity() {
-	splitRegex := regexp.MustCompile("[+-/*()]")
-	for _, evset := range m.config.Eventsets {
-		evset.granulatity = make(map[string]MetricScope)
-		for counter, event := range evset.Events {
-			gran := getGranularity(counter, event)
-			if gran.Granularity() >= 0 {
-				evset.granulatity[counter] = gran
-			}
-		}
-		for i, metric := range evset.Metrics {
-			s := splitRegex.Split(metric.Calc, -1)
-			gran := MetricScope("cpu")
-			evset.Metrics[i].granulatity = gran
-			for _, x := range s {
-				if _, ok := evset.Events[x]; ok {
-					if evset.granulatity[x].Granularity() > gran.Granularity() {
-						gran = evset.granulatity[x]
-					}
-				}
-			}
-			evset.Metrics[i].granulatity = gran
-		}
-	}
-	for i, metric := range m.config.Metrics {
-		s := splitRegex.Split(metric.Calc, -1)
-		gran := MetricScope("cpu")
-		m.config.Metrics[i].granulatity = gran
-		for _, x := range s {
-			for _, evset := range m.config.Eventsets {
-				for _, m := range evset.Metrics {
-					if m.Name == x && m.granulatity.Granularity() > gran.Granularity() {
-						gran = m.granulatity
-					}
-				}
-			}
-		}
-		m.config.Metrics[i].granulatity = gran
-	}
-}
-
-type TopoResolveFunc func(cpuid int) int
-
-func (m *LikwidCollector) getResponsiblities() map[MetricScope]map[int]int {
-	get_cpus := func(scope MetricScope) map[int]int {
-		var slist []int
-		var cpu C.int
-		var input func(index int) string
-		switch scope {
-		case "node":
-			slist = []int{0}
-			input = func(index int) string { return "N:0" }
-		case "socket":
-			input = func(index int) string { return fmt.Sprintf("%s%d:0", scope.Likwid(), index) }
-			slist = topo.SocketList()
-		// case "numadomain":
-		// 	input = func(index int) string { return fmt.Sprintf("%s%d:0", scope.Likwid(), index) }
-		// 	slist = topo.NumaNodeList()
-		// 	cclog.Debug(scope, " ", input(0), " ", slist)
-		// case "die":
-		// 	input = func(index int) string { return fmt.Sprintf("%s%d:0", scope.Likwid(), index) }
-		// 	slist = topo.DieList()
-		// case "llc":
-		// 	input = fmt.Sprintf("%s%d:0", scope.Likwid(), s)
-		// 	slist = topo.LLCacheList()
-		case "cpu":
-			input = func(index int) string { return fmt.Sprintf("%d", index) }
-			slist = topo.CpuList()
-		case "hwthread":
-			input = func(index int) string { return fmt.Sprintf("%d", index) }
-			slist = topo.CpuList()
-		}
-		outmap := make(map[int]int)
-		for _, s := range slist {
-			t := C.CString(input(s))
-			clen := C.cpustr_to_cpulist(t, &cpu, 1)
-			if int(clen) == 1 {
-				outmap[s] = m.cpu2tid[int(cpu)]
-			} else {
-				cclog.Error(fmt.Sprintf("Cannot determine responsible CPU for %s", input(s)))
-				outmap[s] = -1
-			}
-			C.free(unsafe.Pointer(t))
-		}
-		return outmap
-	}
 
-	scopes := GetAllMetricScopes()
-	complete := make(map[MetricScope]map[int]int)
-	for _, s := range scopes {
-		complete[s] = get_cpus(s)
+	if math.IsNaN(freq) {
+		C.power_init(0)
+		info := C.get_powerInfo()
+		if float64(info.baseFrequency) != 0 {
+			freq = float64(info.baseFrequency)
+		}
+		C.power_finalize()
 	}
-	return complete
+	return freq * 1e3
 }
 
 func (m *LikwidCollector) Init(config json.RawMessage) error {
-	var ret C.int
 	m.name = "LikwidCollector"
+	m.parallel = false
+	m.initialized = false
+	m.running = false
 	m.config.AccessMode = LIKWID_DEF_ACCESSMODE
+	m.config.LibraryPath = LIKWID_LIB_NAME
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	lib := dl.New(LIKWID_LIB_NAME, LIKWID_LIB_DL_FLAGS)
+	lib := dl.New(m.config.LibraryPath, LIKWID_LIB_DL_FLAGS)
 	if lib == nil {
-		return fmt.Errorf("error instantiating DynamicLibrary for %s", LIKWID_LIB_NAME)
+		return fmt.Errorf("error instantiating DynamicLibrary for %s", m.config.LibraryPath)
 	}
 	err := lib.Open()
 	if err != nil {
-		return fmt.Errorf("error opening %s: %v", LIKWID_LIB_NAME, err)
+		return fmt.Errorf("error opening %s: %v", m.config.LibraryPath, err)
 	}
 
 	if m.config.ForceOverwrite {
@@ -285,202 +203,174 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 	}
 	m.setup()
 
-	m.meta = map[string]string{"source": m.name, "group": "PerfCounter"}
+	m.meta = map[string]string{"group": "PerfCounter"}
 	cclog.ComponentDebug(m.name, "Get cpulist and init maps and lists")
-	cpulist := topo.CpuList()
+	cpulist := topo.HwthreadList()
 	m.cpulist = make([]C.int, len(cpulist))
 	m.cpu2tid = make(map[int]int)
 	for i, c := range cpulist {
 		m.cpulist[i] = C.int(c)
 		m.cpu2tid[c] = i
-
 	}
-	m.results = make(map[int]map[int]map[string]interface{})
-	m.mresults = make(map[int]map[int]map[string]float64)
+
+	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)
-	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
-	}
-
-	// Determine which counter works at which level. PMC*: cpu, *BOX*: socket, ...
-	m.initGranularity()
-	// Generate map for MetricScope -> scope_id (like socket id) -> responsible id (offset in cpulist)
-	m.scopeRespTids = m.getResponsiblities()
-	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)
-	}
-
-	cclog.ComponentDebug(m.name, "initialize LIKWID perfmon module")
-	ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
-	if ret != 0 {
-		C.topology_finalize()
-		err := errors.New("failed to initialize LIKWID topology")
-		cclog.ComponentError(m.name, err.Error())
-		return err
+	for _, tid := range m.cpu2tid {
+		m.gmresults[tid] = make(map[string]float64)
 	}
 
 	// This is for the global metrics computation test
-	globalParams := make(map[string]interface{})
-	globalParams["time"] = float64(1.0)
-	globalParams["inverseClock"] = float64(1.0)
-	// While adding the events, we test the metrics whether they can be computed at all
-	for i, evset := range m.config.Eventsets {
-		estr := eventsToEventStr(evset.Events)
-		// Generate parameter list for the metric computing test
-		params := make(map[string]interface{})
-		params["time"] = float64(1.0)
-		params["inverseClock"] = float64(1.0)
-		for counter := range evset.Events {
-			params[counter] = float64(1.0)
-		}
-		for _, metric := range evset.Metrics {
-			// Try to evaluate the metric
-			_, err := agg.EvalFloat64Condition(metric.Calc, params)
-			if err != nil {
-				cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
-				continue
+	totalMetrics := 0
+	// Generate parameter list for the metric computing test
+	params := make([]string, 0)
+	params = append(params, "time", "inverseClock")
+	// Generate parameter list for the global metric computing test
+	globalParams := make([]string, 0)
+	globalParams = append(globalParams, "time", "inverseClock")
+	// We test the eventset metrics whether they can be computed at all
+	for _, evset := range m.config.Eventsets {
+		if len(evset.Events) > 0 {
+			params = params[:2]
+			for counter := range evset.Events {
+				params = append(params, counter)
 			}
-			// If the metric is not in the parameter list for the global metrics, add it
-			if _, ok := globalParams[metric.Name]; !ok {
-				globalParams[metric.Name] = float64(1.0)
-			}
-		}
-		// Now we add the list of events to likwid
-		cstr := C.CString(estr)
-		gid := C.perfmon_addEventSet(cstr)
-		if gid >= 0 {
-			m.groups = append(m.groups, gid)
-		}
-		C.free(unsafe.Pointer(cstr))
-		m.results[i] = make(map[int]map[string]interface{})
-		m.mresults[i] = make(map[int]map[string]float64)
-		for tid := range m.cpulist {
-			m.results[i][tid] = make(map[string]interface{})
-			m.mresults[i][tid] = make(map[string]float64)
-			if i == 0 {
-				m.gmresults[tid] = make(map[string]float64)
+			for _, metric := range evset.Metrics {
+				// Try to evaluate the metric
+				if testLikwidMetricFormula(metric.Calc, params) {
+					// Add the computable metric to the parameter list for the global metrics
+					globalParams = append(globalParams, metric.Name)
+					totalMetrics++
+				} else {
+					metric.Calc = ""
+				}
 			}
+		} else {
+			cclog.ComponentError(m.name, "Invalid Likwid eventset config, no events given")
+			continue
 		}
 	}
 	for _, metric := range m.config.Metrics {
 		// Try to evaluate the global metric
-		_, err := agg.EvalFloat64Condition(metric.Calc, globalParams)
-		if err != nil {
-			cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
-			continue
+		if !testLikwidMetricFormula(metric.Calc, globalParams) {
+			cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed")
+			metric.Calc = ""
+		} else {
+			totalMetrics++
 		}
 	}
 
 	// If no event set could be added, shut down LikwidCollector
-	if len(m.groups) == 0 {
-		C.perfmon_finalize()
-		C.topology_finalize()
-		err := errors.New("no LIKWID performance group initialized")
+	if totalMetrics == 0 {
+		err := errors.New("no LIKWID eventset or metric usable")
 		cclog.ComponentError(m.name, err.Error())
 		return err
 	}
-	m.basefreq = getBaseFreq()
-	cclog.ComponentDebug(m.name, "BaseFreq", m.basefreq)
 	m.init = true
 	return nil
 }
 
 // take a measurement for 'interval' seconds of event set index 'group'
-func (m *LikwidCollector) takeMeasurement(group int, interval time.Duration) error {
+func (m *LikwidCollector) takeMeasurement(evset LikwidEventsetConfig, interval time.Duration) (bool, error) {
 	var ret C.int
-	gid := m.groups[group]
-	ret = C.perfmon_setupCounters(gid)
-	if ret != 0 {
-		gctr := C.GoString(C.perfmon_getGroupName(gid))
-		err := fmt.Errorf("failed to setup performance group %d (%s)", gid, gctr)
-		return err
+	m.lock.Lock()
+	if m.initialized {
+		ret = C.perfmon_setupCounters(evset.gid)
+		if ret != 0 {
+			var err error = nil
+			var skip bool = false
+			if ret == -37 {
+				skip = true
+			} else {
+				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
+			}
+			m.lock.Unlock()
+			return skip, err
+		}
+		ret = C.perfmon_startCounters()
+		if ret != 0 {
+			var err error = nil
+			var skip bool = false
+			if ret == -37 {
+				skip = true
+			} else {
+				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
+			}
+			m.lock.Unlock()
+			return skip, err
+		}
+		m.running = true
+		time.Sleep(interval)
+		m.running = false
+		ret = C.perfmon_stopCounters()
+		if ret != 0 {
+			var err error = nil
+			var skip bool = false
+			if ret == -37 {
+				skip = true
+			} else {
+				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
+			}
+			m.lock.Unlock()
+			return skip, err
+		}
 	}
-	ret = C.perfmon_startCounters()
-	if ret != 0 {
-		gctr := C.GoString(C.perfmon_getGroupName(gid))
-		err := fmt.Errorf("failed to start performance group %d (%s)", gid, gctr)
-		return err
-	}
-	m.running = true
-	time.Sleep(interval)
-	m.running = false
-	ret = C.perfmon_stopCounters()
-	if ret != 0 {
-		gctr := C.GoString(C.perfmon_getGroupName(gid))
-		err := fmt.Errorf("failed to stop performance group %d (%s)", gid, gctr)
-		return err
-	}
-	return nil
+	m.lock.Unlock()
+	return false, nil
 }
 
 // Get all measurement results for an event set, derive the metric values out of the measurement results and send it
-func (m *LikwidCollector) calcEventsetMetrics(group int, interval time.Duration, output chan lp.CCMetric) error {
-	var eidx C.int
-	evset := m.config.Eventsets[group]
-	gid := m.groups[group]
+func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
 	invClock := float64(1.0 / m.basefreq)
 
 	// Go over events and get the results
-	for eidx = 0; int(eidx) < len(evset.Events); eidx++ {
-		ctr := C.perfmon_getCounterName(gid, eidx)
-		ev := C.perfmon_getEventName(gid, eidx)
-		gctr := C.GoString(ctr)
-		gev := C.GoString(ev)
-		// MetricScope for the counter (and if needed the event)
-		scope := getGranularity(gctr, gev)
-		// Get the map scope-id -> tids
-		// This way we read less counters like only the responsible hardware thread for a socket
-		scopemap := m.scopeRespTids[scope]
-		for _, tid := range scopemap {
-			if tid >= 0 {
-				m.results[group][tid]["time"] = interval.Seconds()
-				m.results[group][tid]["inverseClock"] = invClock
-				res := C.perfmon_getLastResult(gid, eidx, C.int(tid))
-				m.results[group][tid][gctr] = float64(res)
+	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
-	for _, metric := range evset.Metrics {
+	for _, metric := range m.config.Eventsets[evset.internal].Metrics {
 		// The metric scope is determined in the Init() function
 		// Get the map scope-id -> tids
-		scopemap := m.scopeRespTids[metric.Scope]
+		scopemap := m.cpu2tid
+		if metric.Type == "socket" {
+			scopemap = m.sock2tid
+		}
 		for domain, tid := range scopemap {
-			if tid >= 0 {
-				value, err := agg.EvalFloat64Condition(metric.Calc, m.results[group][tid])
+			if tid >= 0 && len(metric.Calc) > 0 {
+				value, err := agg.EvalFloat64Condition(metric.Calc, evset.results[tid])
 				if err != nil {
 					cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
-					continue
-				}
-				m.mresults[group][tid][metric.Name] = value
-				if m.config.InvalidToZero && math.IsNaN(value) {
 					value = 0.0
 				}
-				if m.config.InvalidToZero && math.IsInf(value, 0) {
+				if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {
 					value = 0.0
 				}
+				evset.metrics[tid][metric.Name] = value
 				// Now we have the result, send it with the proper tags
 				if !math.IsNaN(value) {
 					if metric.Publish {
-						tags := map[string]string{"type": metric.Scope.String()}
-						if metric.Scope != "node" {
-							tags["type-id"] = fmt.Sprintf("%d", domain)
-						}
 						fields := map[string]interface{}{"value": value}
-						y, err := lp.New(metric.Name, tags, m.meta, fields, time.Now())
+						y, err := lp.New(metric.Name, map[string]string{"type": metric.Type}, m.meta, fields, time.Now())
 						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
 						}
 					}
@@ -495,13 +385,16 @@ func (m *LikwidCollector) calcEventsetMetrics(group int, interval time.Duration,
 // Go over the global metrics, derive the value out of the event sets' metric values and send it
 func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan lp.CCMetric) error {
 	for _, metric := range m.config.Metrics {
-		scopemap := m.scopeRespTids[metric.Scope]
+		scopemap := m.cpu2tid
+		if metric.Type == "socket" {
+			scopemap = m.sock2tid
+		}
 		for domain, tid := range scopemap {
 			if tid >= 0 {
 				// Here we generate parameter list
 				params := make(map[string]interface{})
-				for j := range m.groups {
-					for mname, mres := range m.mresults[j][tid] {
+				for _, evset := range m.likwidGroups {
+					for mname, mres := range evset.metrics[tid] {
 						params[mname] = mres
 					}
 				}
@@ -509,25 +402,25 @@ func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan
 				value, err := agg.EvalFloat64Condition(metric.Calc, params)
 				if err != nil {
 					cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
-					continue
+					value = 0.0
+				}
+				if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {
+					value = 0.0
 				}
 				m.gmresults[tid][metric.Name] = value
-				if m.config.InvalidToZero && math.IsNaN(value) {
-					value = 0.0
-				}
-				if m.config.InvalidToZero && math.IsInf(value, 0) {
-					value = 0.0
-				}
 				// Now we have the result, send it with the proper tags
 				if !math.IsNaN(value) {
 					if metric.Publish {
-						tags := map[string]string{"type": metric.Scope.String()}
-						if metric.Scope != "node" {
-							tags["type-id"] = fmt.Sprintf("%d", domain)
-						}
+						tags := map[string]string{"type": metric.Type}
 						fields := map[string]interface{}{"value": value}
 						y, err := lp.New(metric.Name, tags, m.meta, fields, time.Now())
 						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
 						}
 					}
@@ -538,38 +431,163 @@ func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan
 	return nil
 }
 
+func (m *LikwidCollector) LateInit() error {
+	var ret C.int
+	if m.initialized {
+		return nil
+	}
+	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)
+	}
+	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
 	}
 
-	for i := range m.groups {
-		// measure event set 'i' for 'interval' seconds
-		err := m.takeMeasurement(i, interval)
+	if !m.initialized {
+		m.lock.Lock()
+		err = m.LateInit()
 		if err != nil {
-			cclog.ComponentError(m.name, err.Error())
+			m.lock.Unlock()
 			return
 		}
-		// read measurements and derive event set metrics
-		m.calcEventsetMetrics(i, interval, output)
+		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)
+		}
 	}
-	// use the event set metrics to derive the global metrics
-	m.calcGlobalMetrics(interval, output)
 }
 
 func (m *LikwidCollector) Close() {
 	if m.init {
-		cclog.ComponentDebug(m.name, "Closing ...")
 		m.init = false
-		if m.running {
-			cclog.ComponentDebug(m.name, "Stopping counters")
-			C.perfmon_stopCounters()
+		cclog.ComponentDebug(m.name, "Closing ...")
+		m.lock.Lock()
+		if m.initialized {
+			cclog.ComponentDebug(m.name, "Finalize LIKWID perfmon module")
+			C.perfmon_finalize()
+			m.initialized = false
 		}
-		cclog.ComponentDebug(m.name, "Finalize LIKWID perfmon module")
-		C.perfmon_finalize()
+		m.lock.Unlock()
 		cclog.ComponentDebug(m.name, "Finalize LIKWID topology module")
 		C.topology_finalize()
+
 		cclog.ComponentDebug(m.name, "Closing done")
 	}
 }

collectors/likwidMetric.md

@@ -3,29 +3,66 @@
 
 The `likwid` collector is probably the most complicated collector. The LIKWID library is included as static library with *direct* access mode. The *direct* access mode is suitable if the daemon is executed by a root user. The static library does not contain the performance groups, so all information needs to be provided in the configuration.
 
-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". Each metric has a name, the formula, a scope and a publish flag. 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`. The scope tells the Collector whether it is a metric for each hardware thread (`cpu`) or each CPU socket (`socket`). The last one is the publishing flag. It tells the collector whether a metric should be sent to the router.
-- The global metrics are metrics which require data from all 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. 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. **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.
+```json
+  "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",
+    "eventsets": [
+      {
+        "events" : {
+          "COUNTER0": "EVENT0",
+          "COUNTER1": "EVENT1",
+        },
+        "metrics" : [
+          {
+            "name": "sum_01",
+            "calc": "COUNTER0 + COUNTER1",
+            "publish": false,
+            "unit": "myunit",
+            "type": "hwthread"
+          }
+        ]
+      }
+    ]
+    "globalmetrics" : [
+      {
+        "name": "global_sum",
+        "calc": "sum_01",
+        "publish": true,
+        "unit": "myunit",
+        "type": "hwthread"
+      }
+    ]
+  }
+```
+
+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 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:
-- `access_mode` : Method to use for hardware performance monitoring (`direct` access as root user, `accessdaemon` for the daemon mode)
-- `accessdaemon_path`: Folder with the access daemon `likwid-accessD`, commonly `$LIKWID_INSTALL_LOC/sbin`
 - `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`.
+- `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`
 
 ### 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 collector provides the specification of a 'scope' for each metric.
+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.
 
-- `cpu` : One metric per CPU hardware thread with the tags `"type" : "cpu"` and `"type-id" : "$cpu_id"`
+- `hwthread` : One metric per CPU hardware thread with the tags `"type" : "hwthread"` and `"type-id" : "$hwthread_id"`
 - `socket` : One metric per CPU socket/package with the tags `"type" : "socket"` and `"type-id" : "$socket_id"`
 
-**Note:** You cannot specify `socket` scope for a metric that is measured at `cpu` scope, 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.
+**Note:** You cannot specify `socket` scope for a metric that is measured at `hwthread` scope, 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 scope `hwthread`
 - All counters names containing `BOX` have the scope `socket`
-- All `PWRx` counters have scope `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `cpu` scope
+- All `PWRx` counters have scope `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `hwthread` scope
 - All `DFCx` counters have scope `socket`
 
 ### Help with the configuration
@@ -47,6 +84,7 @@ $ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
 {
   "events": {
     "FIXC0": "INSTR_RETIRED_ANY",
+    "FIXC1": "CPU_CLK_UNHALTED_CORE",
     "..." : "..."
   },
   "metrics" : [
@@ -54,6 +92,7 @@ $ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
       "calc": "time",
       "name": "Runtime (RDTSC) [s]",
       "publish": true,
+      "unit": "seconds"
       "scope": "hwthread"
     },
     {
@@ -71,21 +110,28 @@ LIKWID checks the file `/var/run/likwid.lock` before performing any interfering
 
 Before (SLURM prolog, ...)
 ```
-$ chwon $JOBUSER /var/run/likwid.lock
+$ chown $JOBUSER /var/run/likwid.lock
 ```
 
 After (SLURM epilog, ...)
 ```
-$ chwon $CCUSER /var/run/likwid.lock
+$ 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).
+
+
 ### Example configuration
 
+#### AMD Zen3
 
 ```json
   "likwid": {
     "force_overwrite" : false,
-    "nan_to_zero" : false,
+    "invalid_to_zero" : false,
     "eventsets": [
       {
         "events": {
@@ -104,25 +150,28 @@ $ chwon $CCUSER /var/run/likwid.lock
           {
             "name": "ipc",
             "calc": "PMC0/PMC1",
-            "scope": "cpu",
+            "type": "hwthread",
             "publish": true
           },
           {
             "name": "flops_any",
             "calc": "0.000001*PMC2/time",
-            "scope": "cpu",
+            "unit": "MFlops/s",
+            "type": "hwthread",
             "publish": true
           },
           {
-            "name": "clock_mhz",
+            "name": "clock",
             "calc": "0.000001*(FIXC1/FIXC2)/inverseClock",
-            "scope": "cpu",
+            "type": "hwthread",
+            "unit": "MHz",
             "publish": true
           },
           {
             "name": "mem1",
             "calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
-            "scope": "socket",
+            "unit": "Mbyte/s",
+            "type": "socket",
             "publish": false
           }
         ]
@@ -140,19 +189,22 @@ $ chwon $CCUSER /var/run/likwid.lock
           {
             "name": "pwr_core",
             "calc": "PWR0/time",
-            "scope": "socket",
+            "unit": "Watt"
+            "type": "socket",
             "publish": true
           },
           {
             "name": "pwr_pkg",
             "calc": "PWR1/time",
-            "scope": "socket",
+            "type": "socket",
+            "unit": "Watt"
             "publish": true
           },
           {
             "name": "mem2",
             "calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
-            "scope": "socket",
+            "unit": "Mbyte/s",
+            "type": "socket",
             "publish": false
           }
         ]
@@ -162,7 +214,8 @@ $ chwon $CCUSER /var/run/likwid.lock
       {
         "name": "mem_bw",
         "calc": "mem1+mem2",
-        "scope": "socket",
+        "type": "socket",
+        "unit": "Mbyte/s",
         "publish": true
       }
     ]
@@ -171,7 +224,7 @@ $ chwon $CCUSER /var/run/likwid.lock
 
 ### How to get the eventsets and metrics from LIKWID
 
-The `likwid` collector reads hardware performance counters at a **cpu** 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 `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:
 ```
@@ -192,9 +245,10 @@ METRICS                          ->   "metrics": [
 IPC   PMC0/PMC1                  ->     {
                                  ->       "name" : "IPC",
                                  ->       "calc" : "PMC0/PMC1",
-                                 ->       "scope": "cpu",
+                                 ->       "scope": "hwthread",
                                  ->       "publish": true
                                  ->     }
                                  ->   ]
 ```
 
+The script `scripts/likwid_perfgroup_to_cc_config.py` might help you.

collectors/loadavgMetric.go

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

collectors/lustreJobstatMetric.go

@@ -0,0 +1,270 @@
+package collectors
+
+import (
+	"encoding/json"
+	"errors"
+	"os/exec"
+	"regexp"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+type LustreJobstatCollectorConfig struct {
+	LCtlCommand        string   `json:"lctl_command,omitempty"`
+	ExcludeMetrics     []string `json:"exclude_metrics,omitempty"`
+	Sudo               bool     `json:"use_sudo,omitempty"`
+	SendAbsoluteValues bool     `json:"send_abs_values,omitempty"`
+	SendDerivedValues  bool     `json:"send_derived_values,omitempty"`
+	SendDiffValues     bool     `json:"send_diff_values,omitempty"`
+	JobRegex           string   `json:"jobid_regex,omitempty"`
+}
+
+type LustreJobstatCollector struct {
+	metricCollector
+	tags          map[string]string
+	config        LustreJobstatCollectorConfig
+	lctl          string
+	sudoCmd       string
+	lastTimestamp time.Time                // Store time stamp of last tick to derive bandwidths
+	definitions   []LustreMetricDefinition // Combined list without excluded metrics
+	//stats             map[string]map[string]int64 // Data for last value per device and metric
+	lastMdtData       *map[string]map[string]LustreMetricData
+	lastObdfilterData *map[string]map[string]LustreMetricData
+	jobidRegex        *regexp.Regexp
+}
+
+var defaultJobidRegex = `^(?P<jobid>[\d\w\.]+)$`
+
+var LustreMetricJobstatsDefinition = []LustreMetricDefinition{
+	{
+		name:       "lustre_job_read_samples",
+		lineprefix: "read",
+		offsetname: "samples",
+		unit:       "requests",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_job_read_min_bytes",
+		lineprefix: "read_bytes",
+		offsetname: "min",
+		unit:       "bytes",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_job_read_max_bytes",
+		lineprefix: "read_bytes",
+		offsetname: "max",
+		unit:       "bytes",
+		calc:       "none",
+	},
+}
+
+func (m *LustreJobstatCollector) executeLustreCommand(option string) []string {
+	return executeLustreCommand(m.sudoCmd, m.lctl, LCTL_OPTION, option, m.config.Sudo)
+}
+
+func (m *LustreJobstatCollector) Init(config json.RawMessage) error {
+	var err error
+	m.name = "LustreJobstatCollector"
+	m.parallel = true
+	m.config.JobRegex = defaultJobidRegex
+	m.config.SendAbsoluteValues = true
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			return err
+		}
+	}
+	m.setup()
+	m.tags = map[string]string{"type": "jobid"}
+	m.meta = map[string]string{"source": m.name, "group": "Lustre", "scope": "job"}
+
+	// Lustre file system statistics can only be queried by user root
+	// or with password-less sudo
+	// if !m.config.Sudo {
+	// 	user, err := user.Current()
+	// 	if err != nil {
+	// 		cclog.ComponentError(m.name, "Failed to get current user:", err.Error())
+	// 		return err
+	// 	}
+	// 	if user.Uid != "0" {
+	// 		cclog.ComponentError(m.name, "Lustre file system statistics can only be queried by user root")
+	// 		return err
+	// 	}
+	// } else {
+	// 	p, err := exec.LookPath("sudo")
+	// 	if err != nil {
+	// 		cclog.ComponentError(m.name, "Cannot find 'sudo'")
+	// 		return err
+	// 	}
+	// 	m.sudoCmd = p
+	// }
+
+	p, err := exec.LookPath(m.config.LCtlCommand)
+	if err != nil {
+		p, err = exec.LookPath(LCTL_CMD)
+		if err != nil {
+			return err
+		}
+	}
+	m.lctl = p
+
+	m.definitions = make([]LustreMetricDefinition, 0)
+	if m.config.SendAbsoluteValues {
+		for _, def := range LustreMetricJobstatsDefinition {
+			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
+				m.definitions = append(m.definitions, def)
+			}
+		}
+	}
+
+	if len(m.definitions) == 0 {
+		return errors.New("no metrics to collect")
+	}
+
+	x := make(map[string]map[string]LustreMetricData)
+	m.lastMdtData = &x
+	x = make(map[string]map[string]LustreMetricData)
+	m.lastObdfilterData = &x
+
+	if len(m.config.JobRegex) > 0 {
+		jregex := strings.ReplaceAll(m.config.JobRegex, "%", "\\")
+		r, err := regexp.Compile(jregex)
+		if err == nil {
+			m.jobidRegex = r
+		} else {
+			cclog.ComponentError(m.name, "Cannot compile jobid regex")
+			return err
+		}
+	}
+
+	m.lastTimestamp = time.Now()
+	m.init = true
+	return nil
+}
+
+func (m *LustreJobstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	if !m.init {
+		return
+	}
+
+	getValue := func(data map[string]map[string]LustreMetricData, device string, jobid string, operation string, field string) int64 {
+		var value int64 = -1
+		if ddata, ok := data[device]; ok {
+			if jdata, ok := ddata[jobid]; ok {
+				if opdata, ok := jdata.op_data[operation]; ok {
+					if v, ok := opdata[field]; ok {
+						value = v
+					}
+				}
+			}
+		}
+		return value
+	}
+
+	jobIdToTags := func(jobregex *regexp.Regexp, job string) map[string]string {
+		tags := make(map[string]string)
+		groups := jobregex.SubexpNames()
+		for _, match := range jobregex.FindAllStringSubmatch(job, -1) {
+			for groupIdx, group := range match {
+				if len(groups[groupIdx]) > 0 {
+					tags[groups[groupIdx]] = group
+				}
+			}
+		}
+		return tags
+	}
+
+	generateMetric := func(definition LustreMetricDefinition, data map[string]map[string]LustreMetricData, last map[string]map[string]LustreMetricData, now time.Time) {
+		tdiff := now.Sub(m.lastTimestamp)
+		for dev, ddata := range data {
+			for jobid, jdata := range ddata {
+				jobtags := jobIdToTags(m.jobidRegex, jobid)
+				if _, ok := jobtags["jobid"]; !ok {
+					continue
+				}
+				cur := getValue(data, dev, jobid, definition.lineprefix, definition.offsetname)
+				old := getValue(last, dev, jobid, definition.lineprefix, definition.offsetname)
+				var x interface{} = -1
+				var valid = false
+				switch definition.calc {
+				case "none":
+					x = cur
+					valid = true
+				case "difference":
+					if len(last) > 0 {
+						if old >= 0 {
+							x = cur - old
+							valid = true
+						}
+					}
+				case "derivative":
+					if len(last) > 0 {
+						if old >= 0 {
+							x = float64(cur-old) / tdiff.Seconds()
+							valid = true
+						}
+					}
+				}
+				if valid {
+					y, err := lp.New(definition.name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
+					if err == nil {
+						y.AddTag("stype", "device")
+						y.AddTag("stype-id", dev)
+						if j, ok := jobtags["jobid"]; ok {
+							y.AddTag("type-id", j)
+						} else {
+							y.AddTag("type-id", jobid)
+						}
+						for k, v := range jobtags {
+							switch k {
+							case "jobid":
+							case "hostname":
+								y.AddTag("hostname", v)
+							default:
+								y.AddMeta(k, v)
+							}
+						}
+						if len(definition.unit) > 0 {
+							y.AddMeta("unit", definition.unit)
+						} else {
+							if unit, ok := jdata.op_units[definition.lineprefix]; ok {
+								y.AddMeta("unit", unit)
+							}
+						}
+						output <- y
+					}
+				}
+			}
+		}
+	}
+
+	now := time.Now()
+
+	mdt_lines := m.executeLustreCommand("mdt.*.job_stats")
+	if len(mdt_lines) > 0 {
+		mdt_data := readCommandOutput(mdt_lines)
+		for _, def := range m.definitions {
+			generateMetric(def, mdt_data, *m.lastMdtData, now)
+		}
+		m.lastMdtData = &mdt_data
+	}
+
+	obdfilter_lines := m.executeLustreCommand("obdfilter.*.job_stats")
+	if len(obdfilter_lines) > 0 {
+		obdfilter_data := readCommandOutput(obdfilter_lines)
+		for _, def := range m.definitions {
+			generateMetric(def, obdfilter_data, *m.lastObdfilterData, now)
+		}
+		m.lastObdfilterData = &obdfilter_data
+	}
+
+	m.lastTimestamp = now
+}
+
+func (m *LustreJobstatCollector) Close() {
+	m.init = false
+}

collectors/lustreJobstatMetric.md

@@ -0,0 +1,35 @@
+
+## `lustre_jobstat` collector
+
+**Note**: This collector is meant to run on the Lustre servers, **not** the clients
+
+The Lustre filesystem provides a feature (`job_stats`) to group processes on client side with an identifier string (like a compute job with its jobid) and retrieve the file system operation counts on the server side. Check the section [How to configure `job_stats`]() for more information.
+
+### Configuration
+
+```json
+  "lustre_jobstat_": {
+    "lctl_command": "/path/to/lctl",
+    "use_sudo": false,
+    "exclude_metrics": [
+      "setattr",
+      "getattr"
+    ],
+    "send_abs_values" : true,
+    
+    "jobid_regex" : "^(?P<jobid>[%d%w%.]+)$"
+  }
+```
+
+The `lustre_jobstat` collector uses the `lctl` application with the `get_param` option to get all `mdt.*.job_stats` and `obdfilter.*.job_stats` metrics. These metrics are only available for root users. If password-less sudo is configured, you can enable `sudo` in the configuration. In the `exclude_metrics` list, some metrics can be excluded to reduce network traffic and storage. With the `send_abs_values` flag, the collector sends absolute values for the configured metrics. The `jobid_regex` can be used to split the Lustre `job_stats` identifier into multiple parts. Since JSON cannot handle strings like `\d`, use `%` instead of `\`.
+
+Metrics:
+- `lustre_job_read_samples` (unit: `requests`)
+- `lustre_job_read_min_bytes` (unit: `bytes`)
+- `lustre_job_read_max_bytes` (unit: `bytes`)
+
+The collector adds the tags: `type=jobid,typeid=<jobid_from_regex>,stype=device,stype=<device_name_from_output>`.
+
+The collector adds the mega information: `unit=<unit>,scope=job`
+
+### How to configure `job_stats`

collectors/lustreMetric.go

@@ -10,42 +10,233 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
-const LUSTRE_SYSFS = `/sys/fs/lustre`
-const LCTL_CMD = `lctl`
-const LCTL_OPTION = `get_param`
-
 type LustreCollectorConfig struct {
-	LCtlCommand    string   `json:"lctl_command"`
-	ExcludeMetrics []string `json:"exclude_metrics"`
-	SendAllMetrics bool     `json:"send_all_metrics"`
-	Sudo           bool     `json:"use_sudo"`
+	LCtlCommand        string   `json:"lctl_command,omitempty"`
+	ExcludeMetrics     []string `json:"exclude_metrics,omitempty"`
+	Sudo               bool     `json:"use_sudo,omitempty"`
+	SendAbsoluteValues bool     `json:"send_abs_values,omitempty"`
+	SendDerivedValues  bool     `json:"send_derived_values,omitempty"`
+	SendDiffValues     bool     `json:"send_diff_values,omitempty"`
 }
 
 type LustreCollector struct {
 	metricCollector
-	tags    map[string]string
-	matches map[string]map[string]int
-	stats   map[string]map[string]int64
-	config  LustreCollectorConfig
-	lctl    string
-	sudoCmd string
+	tags          map[string]string
+	config        LustreCollectorConfig
+	lctl          string
+	sudoCmd       string
+	lastTimestamp time.Time                   // Store time stamp of last tick to derive bandwidths
+	definitions   []LustreMetricDefinition    // Combined list without excluded metrics
+	stats         map[string]map[string]int64 // Data for last value per device and metric
+}
+
+var LustreAbsMetrics = []LustreMetricDefinition{
+	{
+		name:       "lustre_read_requests",
+		lineprefix: "read_bytes",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "requests",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_write_requests",
+		lineprefix: "write_bytes",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "requests",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_read_bytes",
+		lineprefix: "read_bytes",
+		lineoffset: 6,
+		offsetname: "sum",
+		unit:       "bytes",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_write_bytes",
+		lineprefix: "write_bytes",
+		lineoffset: 6,
+		offsetname: "sum",
+		unit:       "bytes",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_open",
+		lineprefix: "open",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_close",
+		lineprefix: "close",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_setattr",
+		lineprefix: "setattr",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_getattr",
+		lineprefix: "getattr",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_statfs",
+		lineprefix: "statfs",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "none",
+	},
+	{
+		name:       "lustre_inode_permission",
+		lineprefix: "inode_permission",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "none",
+	},
+}
+
+var LustreDiffMetrics = []LustreMetricDefinition{
+	{
+		name:       "lustre_read_requests_diff",
+		lineprefix: "read_bytes",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "requests",
+		calc:       "difference",
+	},
+	{
+		name:       "lustre_write_requests_diff",
+		lineprefix: "write_bytes",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "requests",
+		calc:       "difference",
+	},
+	{
+		name:       "lustre_read_bytes_diff",
+		lineprefix: "read_bytes",
+		lineoffset: 6,
+		offsetname: "sum",
+		unit:       "bytes",
+		calc:       "difference",
+	},
+	{
+		name:       "lustre_write_bytes_diff",
+		lineprefix: "write_bytes",
+		lineoffset: 6,
+		offsetname: "sum",
+		unit:       "bytes",
+		calc:       "difference",
+	},
+	{
+		name:       "lustre_open_diff",
+		lineprefix: "open",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "difference",
+	},
+	{
+		name:       "lustre_close_diff",
+		lineprefix: "close",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "difference",
+	},
+	{
+		name:       "lustre_setattr_diff",
+		lineprefix: "setattr",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "difference",
+	},
+	{
+		name:       "lustre_getattr_diff",
+		lineprefix: "getattr",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "difference",
+	},
+	{
+		name:       "lustre_statfs_diff",
+		lineprefix: "statfs",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "difference",
+	},
+	{
+		name:       "lustre_inode_permission_diff",
+		lineprefix: "inode_permission",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "",
+		calc:       "difference",
+	},
+}
+
+var LustreDeriveMetrics = []LustreMetricDefinition{
+	{
+		name:       "lustre_read_requests_rate",
+		lineprefix: "read_bytes",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "requests/sec",
+		calc:       "derivative",
+	},
+	{
+		name:       "lustre_write_requests_rate",
+		lineprefix: "write_bytes",
+		lineoffset: 1,
+		offsetname: "samples",
+		unit:       "requests/sec",
+		calc:       "derivative",
+	},
+	{
+		name:       "lustre_read_bw",
+		lineprefix: "read_bytes",
+		lineoffset: 6,
+		offsetname: "sum",
+		unit:       "bytes/sec",
+		calc:       "derivative",
+	},
+	{
+		name:       "lustre_write_bw",
+		lineprefix: "write_bytes",
+		lineoffset: 6,
+		offsetname: "sum",
+		unit:       "bytes/sec",
+		calc:       "derivative",
+	},
 }
 
 func (m *LustreCollector) getDeviceDataCommand(device string) []string {
-	var command *exec.Cmd
-	statsfile := fmt.Sprintf("llite.%s.stats", device)
-	if m.config.Sudo {
-		command = exec.Command(m.sudoCmd, m.lctl, LCTL_OPTION, statsfile)
-	} else {
-		command = exec.Command(m.lctl, LCTL_OPTION, statsfile)
-	}
-	command.Wait()
-	stdout, _ := command.Output()
-	return strings.Split(string(stdout), "\n")
+	return executeLustreCommand(m.sudoCmd, m.lctl, LCTL_OPTION, fmt.Sprintf("llite.%s.stats", device), m.config.Sudo)
 }
 
 func (m *LustreCollector) getDevices() []string {
@@ -75,6 +266,16 @@ func (m *LustreCollector) getDevices() []string {
 	return devices
 }
 
+func getMetricData(lines []string, prefix string, offset int) (int64, error) {
+	for _, line := range lines {
+		if strings.HasPrefix(line, prefix) {
+			lf := strings.Fields(line)
+			return strconv.ParseInt(lf[offset], 0, 64)
+		}
+	}
+	return 0, errors.New("no such line in data")
+}
+
 // //Version reading the stats data of a device from sysfs
 // func (m *LustreCollector) getDeviceDataSysfs(device string) []string {
 // 	llitedir := filepath.Join(LUSTRE_SYSFS, "llite")
@@ -90,6 +291,7 @@ func (m *LustreCollector) getDevices() []string {
 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 {
@@ -98,43 +300,29 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
 	}
 	m.setup()
 	m.tags = map[string]string{"type": "node"}
-	m.meta = map[string]string{"source": m.name, "group": "Lustre"}
-	defmatches := map[string]map[string]int{
-		"read_bytes":       {"lustre_read_bytes": 6, "lustre_read_requests": 1},
-		"write_bytes":      {"lustre_write_bytes": 6, "lustre_write_requests": 1},
-		"open":             {"lustre_open": 1},
-		"close":            {"lustre_close": 1},
-		"setattr":          {"lustre_setattr": 1},
-		"getattr":          {"lustre_getattr": 1},
-		"statfs":           {"lustre_statfs": 1},
-		"inode_permission": {"lustre_inode_permission": 1}}
+	m.meta = map[string]string{"source": m.name, "group": "Lustre", "scope": "node"}
 
 	// Lustre file system statistics can only be queried by user root
-	user, err := user.Current()
-	if err != nil {
-		cclog.ComponentError(m.name, "Failed to get current user:", err.Error())
-		return err
-	}
-	if user.Uid != "0" {
-		cclog.ComponentError(m.name, "Lustre file system statistics can only be queried by user root")
-		return err
+	// or with password-less sudo
+	if !m.config.Sudo {
+		user, err := user.Current()
+		if err != nil {
+			cclog.ComponentError(m.name, "Failed to get current user:", err.Error())
+			return err
+		}
+		if user.Uid != "0" {
+			cclog.ComponentError(m.name, "Lustre file system statistics can only be queried by user root")
+			return err
+		}
+	} else {
+		p, err := exec.LookPath("sudo")
+		if err != nil {
+			cclog.ComponentError(m.name, "Cannot find 'sudo'")
+			return err
+		}
+		m.sudoCmd = p
 	}
 
-	m.matches = make(map[string]map[string]int)
-	for lineprefix, names := range defmatches {
-		for metricname, offset := range names {
-			_, skip := stringArrayContains(m.config.ExcludeMetrics, metricname)
-			if skip {
-				continue
-			}
-			if _, prefixExist := m.matches[lineprefix]; !prefixExist {
-				m.matches[lineprefix] = make(map[string]int)
-			}
-			if _, metricExist := m.matches[lineprefix][metricname]; !metricExist {
-				m.matches[lineprefix][metricname] = offset
-			}
-		}
-	}
 	p, err := exec.LookPath(m.config.LCtlCommand)
 	if err != nil {
 		p, err = exec.LookPath(LCTL_CMD)
@@ -143,26 +331,51 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
 		}
 	}
 	m.lctl = p
-	if m.config.Sudo {
-		p, err := exec.LookPath("sudo")
-		if err != nil {
-			m.sudoCmd = p
+
+	m.definitions = []LustreMetricDefinition{}
+	if m.config.SendAbsoluteValues {
+		for _, def := range LustreAbsMetrics {
+			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
+				m.definitions = append(m.definitions, def)
+			}
 		}
 	}
+	if m.config.SendDiffValues {
+		for _, def := range LustreDiffMetrics {
+			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
+				m.definitions = append(m.definitions, def)
+			}
+		}
+	}
+	if m.config.SendDerivedValues {
+		for _, def := range LustreDeriveMetrics {
+			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
+				m.definitions = append(m.definitions, def)
+			}
+		}
+	}
+	if len(m.definitions) == 0 {
+		return errors.New("no metrics to collect")
+	}
 
 	devices := m.getDevices()
 	if len(devices) == 0 {
-		return errors.New("no metrics to collect")
+		return errors.New("no Lustre devices found")
 	}
 	m.stats = make(map[string]map[string]int64)
 	for _, d := range devices {
 		m.stats[d] = make(map[string]int64)
-		for _, names := range m.matches {
-			for metricname := range names {
-				m.stats[d][metricname] = 0
+		data := m.getDeviceDataCommand(d)
+		for _, def := range m.definitions {
+			x, err := getMetricData(data, def.lineprefix, def.lineoffset)
+			if err == nil {
+				m.stats[d][def.name] = x
+			} else {
+				m.stats[d][def.name] = 0
 			}
 		}
 	}
+	m.lastTimestamp = time.Now()
 	m.init = true
 	return nil
 }
@@ -171,54 +384,49 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	if !m.init {
 		return
 	}
+	now := time.Now()
+	tdiff := now.Sub(m.lastTimestamp)
 	for device, devData := range m.stats {
-		stats := m.getDeviceDataCommand(device)
-		processed := []string{}
-
-		for _, line := range stats {
-			lf := strings.Fields(line)
-			if len(lf) > 1 {
-				if fields, ok := m.matches[lf[0]]; ok {
-					for name, idx := range fields {
-						x, err := strconv.ParseInt(lf[idx], 0, 64)
-						if err != nil {
-							continue
-						}
-						value := x - devData[name]
-						devData[name] = x
-						if value < 0 {
-							value = 0
-						}
-						y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-						if err == nil {
-							y.AddTag("device", device)
-							if strings.Contains(name, "byte") {
-								y.AddMeta("unit", "Byte")
-							}
-							output <- y
-							if m.config.SendAllMetrics {
-								processed = append(processed, name)
-							}
-						}
-					}
-				}
+		data := m.getDeviceDataCommand(device)
+		for _, def := range m.definitions {
+			var use_x int64
+			var err error
+			var y lp.CCMetric
+			x, err := getMetricData(data, def.lineprefix, def.lineoffset)
+			if err == nil {
+				use_x = x
+			} else {
+				use_x = devData[def.name]
 			}
-		}
-		if m.config.SendAllMetrics {
-			for name := range devData {
-				if _, done := stringArrayContains(processed, name); !done {
-					y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": 0}, time.Now())
-					if err == nil {
-						y.AddTag("device", device)
-						if strings.Contains(name, "byte") {
-							y.AddMeta("unit", "Byte")
-						}
-						output <- y
-					}
+			var value interface{}
+			switch def.calc {
+			case "none":
+				value = use_x
+				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+			case "difference":
+				value = use_x - devData[def.name]
+				if value.(int64) < 0 {
+					value = 0
 				}
+				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+			case "derivative":
+				value = float64(use_x-devData[def.name]) / tdiff.Seconds()
+				if value.(float64) < 0 {
+					value = 0
+				}
+				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			}
+			if err == nil {
+				y.AddTag("device", device)
+				if len(def.unit) > 0 {
+					y.AddMeta("unit", def.unit)
+				}
+				output <- y
+			}
+			devData[def.name] = use_x
 		}
 	}
+	m.lastTimestamp = now
 }
 
 func (m *LustreCollector) Close() {

collectors/lustreMetric.md

@@ -3,27 +3,44 @@
 
 ```json
   "lustrestat": {
-    "procfiles" : [
-      "/proc/fs/lustre/llite/lnec-XXXXXX/stats"
-    ],
+    "lctl_command": "/path/to/lctl",
     "exclude_metrics": [
       "setattr",
       "getattr"
-    ]
+    ],
+    "send_abs_values" : true,
+    "send_derived_values" : true,
+    "send_diff_values": true,
+    "use_sudo": false
   }
 ```
 
-The `lustrestat` collector reads from the procfs stat files for Lustre like `/proc/fs/lustre/llite/lnec-XXXXXX/stats`.
+The `lustrestat` collector uses the `lctl` application with the `get_param` option to get all `llite` metrics (Lustre client). The `llite` metrics are only available for root users. If password-less sudo is configured, you can enable `sudo` in the configuration.
 
 Metrics:
-* `read_bytes`
-* `read_requests`
-* `write_bytes`
-* `write_requests`
-* `open`
-* `close`
-* `getattr`
-* `setattr`
-* `statfs`
-* `inode_permission`
+* `lustre_read_bytes` (unit `bytes`)
+* `lustre_read_requests` (unit `requests`)
+* `lustre_write_bytes` (unit `bytes`)
+* `lustre_write_requests` (unit `requests`)
+* `lustre_open`
+* `lustre_close`
+* `lustre_getattr`
+* `lustre_setattr`
+* `lustre_statfs`
+* `lustre_inode_permission`
+* `lustre_read_bw` (if `send_derived_values == true`, unit `bytes/sec`)
+* `lustre_write_bw` (if `send_derived_values == true`, unit `bytes/sec`)
+* `lustre_read_requests_rate` (if `send_derived_values == true`, unit `requests/sec`)
+* `lustre_write_requests_rate` (if `send_derived_values == true`, unit `requests/sec`)
+* `lustre_read_bytes_diff` (if `send_diff_values == true`, unit `bytes`)
+* `lustre_read_requests_diff` (if `send_diff_values == true`, unit `requests`)
+* `lustre_write_bytes_diff` (if `send_diff_values == true`, unit `bytes`)
+* `lustre_write_requests_diff` (if `send_diff_values == true`, unit `requests`)
+* `lustre_open_diff` (if `send_diff_values == true`)
+* `lustre_close_diff` (if `send_diff_values == true`)
+* `lustre_getattr_diff` (if `send_diff_values == true`)
+* `lustre_setattr_diff` (if `send_diff_values == true`)
+* `lustre_statfs_diff` (if `send_diff_values == true`)
+* `lustre_inode_permission_diff` (if `send_diff_values == true`)
 
+This collector adds an `device` tag.

collectors/lustreMetricCommon.go

@@ -0,0 +1,190 @@
+package collectors
+
+import (
+	"fmt"
+	"os/exec"
+	"regexp"
+	"strconv"
+	"strings"
+)
+
+const LUSTRE_SYSFS = `/sys/fs/lustre`
+const LCTL_CMD = `lctl`
+const LCTL_OPTION = `get_param`
+
+type LustreMetricDefinition struct {
+	name       string
+	lineprefix string
+	lineoffset int
+	offsetname string
+	unit       string
+	calc       string
+}
+
+type LustreMetricData struct {
+	sample_time       int64
+	start_time        int64
+	elapsed_time      int64
+	op_data           map[string]map[string]int64
+	op_units          map[string]string
+	sample_time_unit  string
+	start_time_unit   string
+	elapsed_time_unit string
+}
+
+var devicePattern = regexp.MustCompile(`^[\w\d\-_]+\.([\w\d\-_]+)\.[\w\d\-_]+=$`)
+var jobPattern = regexp.MustCompile(`^-\s*job_id:\s*([\w\d\-_\.:]+)$`)
+var snapshotPattern = regexp.MustCompile(`^\s*snapshot_time\s*:\s*([\d\.]+)\s*([\w\d\-_\.]*)$`)
+var startPattern = regexp.MustCompile(`^\s*start_time\s*:\s*([\d\.]+)\s*([\w\d\-_\.]*)$`)
+var elapsedPattern = regexp.MustCompile(`^\s*elapsed_time\s*:\s*([\d\.]+)\s*([\w\d\-_\.]*)$`)
+var linePattern = regexp.MustCompile(`^\s*([\w\d\-_\.]+):\s*\{\s*samples:\s*([\d\.]+),\s*unit:\s*([\w\d\-_\.]+),\s*min:\s*([\d\.]+),\s*max:\s*([\d\.]+),\s*sum:\s*([\d\.]+),\s*sumsq:\s*([\d\.]+)\s*\}`)
+
+func executeLustreCommand(sudo, lctl, option, search string, use_sudo bool) []string {
+	var command *exec.Cmd
+	if use_sudo {
+		command = exec.Command(sudo, lctl, option, search)
+	} else {
+		command = exec.Command(lctl, option, search)
+	}
+	command.Wait()
+	stdout, _ := command.Output()
+	return strings.Split(string(stdout), "\n")
+}
+
+func splitTree(lines []string, splitRegex *regexp.Regexp) map[string][]string {
+	entries := make(map[string][]string)
+	ent_lines := make([]int, 0)
+	for i, l := range lines {
+		m := splitRegex.FindStringSubmatch(l)
+		if len(m) == 2 {
+			ent_lines = append(ent_lines, i)
+		}
+	}
+	if len(ent_lines) > 0 {
+		for i, idx := range ent_lines[:len(ent_lines)-1] {
+			m := splitRegex.FindStringSubmatch(lines[idx])
+			entries[m[1]] = lines[idx+1 : ent_lines[i+1]]
+		}
+		last := ent_lines[len(ent_lines)-1]
+		m := splitRegex.FindStringSubmatch(lines[last])
+		entries[m[1]] = lines[last:]
+	}
+	return entries
+}
+
+func readDevices(lines []string) map[string][]string {
+	return splitTree(lines, devicePattern)
+}
+
+func readJobs(lines []string) map[string][]string {
+	return splitTree(lines, jobPattern)
+}
+
+func readJobdata(lines []string) LustreMetricData {
+
+	jobdata := LustreMetricData{
+		op_data:           make(map[string]map[string]int64),
+		op_units:          make(map[string]string),
+		sample_time:       0,
+		sample_time_unit:  "nsec",
+		start_time:        0,
+		start_time_unit:   "nsec",
+		elapsed_time:      0,
+		elapsed_time_unit: "nsec",
+	}
+	parseTime := func(value, unit string) int64 {
+		var t int64 = 0
+		if len(unit) == 0 {
+			unit = "secs"
+		}
+		values := strings.Split(value, ".")
+		units := strings.Split(unit, ".")
+		if len(values) != len(units) {
+			fmt.Printf("Invalid time specification '%s' and '%s'\n", value, unit)
+		}
+		for i, v := range values {
+			if len(units) > i {
+				s, err := strconv.ParseInt(v, 10, 64)
+				if err == nil {
+					switch units[i] {
+					case "secs":
+						t += s * 1e9
+					case "msecs":
+						t += s * 1e6
+					case "usecs":
+						t += s * 1e3
+					case "nsecs":
+						t += s
+					}
+				}
+			}
+		}
+		return t
+	}
+	parseNumber := func(value string) int64 {
+		s, err := strconv.ParseInt(value, 10, 64)
+		if err == nil {
+			return s
+		}
+		return 0
+	}
+	for _, l := range lines {
+		if jobdata.sample_time == 0 {
+			m := snapshotPattern.FindStringSubmatch(l)
+			if len(m) == 3 {
+				if len(m[2]) > 0 {
+					jobdata.sample_time = parseTime(m[1], m[2])
+				} else {
+					jobdata.sample_time = parseTime(m[1], "secs")
+				}
+			}
+		}
+
+		if jobdata.start_time == 0 {
+			m := startPattern.FindStringSubmatch(l)
+			if len(m) == 3 {
+				if len(m[2]) > 0 {
+					jobdata.start_time = parseTime(m[1], m[2])
+				} else {
+					jobdata.start_time = parseTime(m[1], "secs")
+				}
+			}
+		}
+		if jobdata.elapsed_time == 0 {
+			m := elapsedPattern.FindStringSubmatch(l)
+			if len(m) == 3 {
+				if len(m[2]) > 0 {
+					jobdata.elapsed_time = parseTime(m[1], m[2])
+				} else {
+					jobdata.elapsed_time = parseTime(m[1], "secs")
+				}
+			}
+		}
+		m := linePattern.FindStringSubmatch(l)
+		if len(m) == 8 {
+			jobdata.op_units[m[1]] = m[3]
+			jobdata.op_data[m[1]] = map[string]int64{
+				"samples": parseNumber(m[2]),
+				"min":     parseNumber(m[4]),
+				"max":     parseNumber(m[5]),
+				"sum":     parseNumber(m[6]),
+				"sumsq":   parseNumber(m[7]),
+			}
+		}
+	}
+	return jobdata
+}
+
+func readCommandOutput(lines []string) map[string]map[string]LustreMetricData {
+	var data map[string]map[string]LustreMetricData = make(map[string]map[string]LustreMetricData)
+	devs := readDevices(lines)
+	for d, ddata := range devs {
+		data[d] = make(map[string]LustreMetricData)
+		jobs := readJobs(ddata)
+		for j, jdata := range jobs {
+			x := readJobdata(jdata)
+			data[d][j] = x
+		}
+	}
+	return data
+}

collectors/memstatMetric.go

@@ -12,8 +12,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const MEMSTATFILE = "/proc/meminfo"
@@ -32,15 +32,21 @@ type MemstatCollectorNode struct {
 
 type MemstatCollector struct {
 	metricCollector
-	stats     map[string]int64
-	tags      map[string]string
-	matches   map[string]string
-	config    MemstatCollectorConfig
-	nodefiles map[int]MemstatCollectorNode
+	stats       map[string]int64
+	tags        map[string]string
+	matches     map[string]string
+	config      MemstatCollectorConfig
+	nodefiles   map[int]MemstatCollectorNode
+	sendMemUsed bool
 }
 
-func getStats(filename string) map[string]float64 {
-	stats := make(map[string]float64)
+type MemstatStats struct {
+	value float64
+	unit  string
+}
+
+func getStats(filename string) map[string]MemstatStats {
+	stats := make(map[string]MemstatStats)
 	file, err := os.Open(filename)
 	if err != nil {
 		cclog.Error(err.Error())
@@ -54,12 +60,19 @@ func getStats(filename string) map[string]float64 {
 		if len(linefields) == 3 {
 			v, err := strconv.ParseFloat(linefields[1], 64)
 			if err == nil {
-				stats[strings.Trim(linefields[0], ":")] = v
+				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
+					value: v,
+					unit:  linefields[2],
+				}
 			}
 		} else if len(linefields) == 5 {
 			v, err := strconv.ParseFloat(linefields[3], 64)
 			if err == nil {
-				stats[strings.Trim(linefields[0], ":")] = v
+				cclog.ComponentDebug("getStats", strings.Trim(linefields[2], ":"), v, linefields[4])
+				stats[strings.Trim(linefields[2], ":")] = MemstatStats{
+					value: v,
+					unit:  linefields[4],
+				}
 			}
 		}
 	}
@@ -69,6 +82,7 @@ func getStats(filename string) map[string]float64 {
 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 {
@@ -77,7 +91,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 			return err
 		}
 	}
-	m.meta = map[string]string{"source": m.name, "group": "Memory", "unit": "kByte"}
+	m.meta = map[string]string{"source": m.name, "group": "Memory"}
 	m.stats = make(map[string]int64)
 	m.matches = make(map[string]string)
 	m.tags = map[string]string{"type": "node"}
@@ -99,6 +113,10 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 			m.matches[k] = v
 		}
 	}
+	m.sendMemUsed = false
+	if _, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_used"); !skip {
+		m.sendMemUsed = true
+	}
 	if len(m.matches) == 0 {
 		return errors.New("no metrics to collect")
 	}
@@ -146,29 +164,57 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		return
 	}
 
-	sendStats := func(stats map[string]float64, tags map[string]string) {
+	sendStats := func(stats map[string]MemstatStats, tags map[string]string) {
 		for match, name := range m.matches {
 			var value float64 = 0
+			var unit string = ""
 			if v, ok := stats[match]; ok {
-				value = v
+				value = v.value
+				if len(v.unit) > 0 {
+					unit = v.unit
+				}
 			}
+
 			y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			if err == nil {
+				if len(unit) > 0 {
+					y.AddMeta("unit", unit)
+				}
 				output <- y
 			}
 		}
-		if _, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_used"); !skip {
-			if freeVal, free := stats["MemFree"]; free {
-				if bufVal, buffers := stats["Buffers"]; buffers {
-					if cacheVal, cached := stats["Cached"]; cached {
-						memUsed := stats["MemTotal"] - (freeVal + bufVal + cacheVal)
-						y, err := lp.New("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
-						if err == nil {
-							output <- y
+		if m.sendMemUsed {
+			memUsed := 0.0
+			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
+							if len(cacheVal.unit) > 0 && len(unit) == 0 {
+								unit = cacheVal.unit
+							}
 						}
 					}
 				}
 			}
+			y, err := lp.New("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
+			if err == nil {
+				if len(unit) > 0 {
+					y.AddMeta("unit", unit)
+				}
+				output <- y
+			}
 		}
 	}
 

collectors/metricCollector.go

@@ -3,27 +3,25 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
-	"log"
-	"strconv"
-	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 type MetricCollector interface {
-	Name() string                                         // Name of the metric collector
-	Init(config json.RawMessage) error                    // Initialize metric collector
-	Initialized() bool                                    // Is metric collector initialized?
+	Name() string                      // Name of the metric collector
+	Init(config json.RawMessage) error // Initialize metric collector
+	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
-	init bool              // is metric collector initialized?
-	meta map[string]string // static meta data tags
+	name     string            // name of the metric
+	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
 }
 
 // Name returns the name of the metric collector
@@ -31,6 +29,11 @@ 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
@@ -65,58 +68,6 @@ 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) {
@@ -125,5 +76,5 @@ func RemoveFromStringList(s []string, r string) ([]string, error) {
 			return append(s[:i], s[i+1:]...), nil
 		}
 	}
-	return s, fmt.Errorf("No such string in list")
+	return s, fmt.Errorf("no such string in list")
 }

collectors/netstatMetric.go

@@ -9,42 +9,66 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
-const NETSTATFILE = `/proc/net/dev`
+const NETSTATFILE = "/proc/net/dev"
 
 type NetstatCollectorConfig struct {
-	IncludeDevices []string `json:"include_devices"`
+	IncludeDevices     []string `json:"include_devices"`
+	SendAbsoluteValues bool     `json:"send_abs_values"`
+	SendDerivedValues  bool     `json:"send_derived_values"`
 }
 
 type NetstatCollectorMetric struct {
-	index     int
-	lastValue float64
+	name       string
+	index      int
+	tags       map[string]string
+	meta       map[string]string
+	meta_rates map[string]string
+	lastValue  int64
 }
 
 type NetstatCollector struct {
 	metricCollector
 	config        NetstatCollectorConfig
-	matches       map[string]map[string]NetstatCollectorMetric
-	devtags       map[string]map[string]string
+	matches       map[string][]NetstatCollectorMetric
 	lastTimestamp time.Time
 }
 
 func (m *NetstatCollector) Init(config json.RawMessage) error {
 	m.name = "NetstatCollector"
+	m.parallel = true
 	m.setup()
 	m.lastTimestamp = time.Now()
-	m.meta = map[string]string{"source": m.name, "group": "Network"}
-	m.devtags = make(map[string]map[string]string)
-	nameIndexMap := map[string]int{
-		"net_bytes_in":  1,
-		"net_pkts_in":   2,
-		"net_bytes_out": 9,
-		"net_pkts_out":  10,
-	}
-	m.matches = make(map[string]map[string]NetstatCollectorMetric)
+
+	const (
+		fieldInterface = iota
+		fieldReceiveBytes
+		fieldReceivePackets
+		fieldReceiveErrs
+		fieldReceiveDrop
+		fieldReceiveFifo
+		fieldReceiveFrame
+		fieldReceiveCompressed
+		fieldReceiveMulticast
+		fieldTransmitBytes
+		fieldTransmitPackets
+		fieldTransmitErrs
+		fieldTransmitDrop
+		fieldTransmitFifo
+		fieldTransmitColls
+		fieldTransmitCarrier
+		fieldTransmitCompressed
+	)
+
+	m.matches = make(map[string][]NetstatCollectorMetric)
+
+	// Set default configuration,
+	m.config.SendAbsoluteValues = true
+	m.config.SendDerivedValues = false
+	// Read configuration file, allow overwriting default config
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -52,7 +76,9 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 			return err
 		}
 	}
-	file, err := os.Open(string(NETSTATFILE))
+
+	// Check access to net statistic file
+	file, err := os.Open(NETSTATFILE)
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return err
@@ -62,23 +88,65 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 	scanner := bufio.NewScanner(file)
 	for scanner.Scan() {
 		l := scanner.Text()
+
+		// Skip lines with no net device entry
 		if !strings.Contains(l, ":") {
 			continue
 		}
+
+		// Split line into fields
 		f := strings.Fields(l)
+
+		// Get net device entry
 		dev := strings.Trim(f[0], ": ")
+
+		// Check if device is a included device
 		if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
-			m.matches[dev] = make(map[string]NetstatCollectorMetric)
-			for name, idx := range nameIndexMap {
-				m.matches[dev][name] = NetstatCollectorMetric{
-					index:     idx,
-					lastValue: 0,
-				}
+			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"}
+			meta_unit_pkts_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "packets/sec"}
+
+			m.matches[dev] = []NetstatCollectorMetric{
+				{
+					name:       "net_bytes_in",
+					index:      fieldReceiveBytes,
+					lastValue:  -1,
+					tags:       tags,
+					meta:       meta_unit_byte,
+					meta_rates: meta_unit_byte_per_sec,
+				},
+				{
+					name:       "net_pkts_in",
+					index:      fieldReceivePackets,
+					lastValue:  -1,
+					tags:       tags,
+					meta:       meta_unit_pkts,
+					meta_rates: meta_unit_pkts_per_sec,
+				},
+				{
+					name:       "net_bytes_out",
+					index:      fieldTransmitBytes,
+					lastValue:  -1,
+					tags:       tags,
+					meta:       meta_unit_byte,
+					meta_rates: meta_unit_byte_per_sec,
+				},
+				{
+					name:       "net_pkts_out",
+					index:      fieldTransmitPackets,
+					lastValue:  -1,
+					tags:       tags,
+					meta:       meta_unit_pkts,
+					meta_rates: meta_unit_pkts_per_sec,
+				},
 			}
-			m.devtags[dev] = map[string]string{"device": dev, "type": "node"}
 		}
+
 	}
-	if len(m.devtags) == 0 {
+
+	if len(m.matches) == 0 {
 		return errors.New("no devices to collector metrics found")
 	}
 	m.init = true
@@ -89,50 +157,62 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	if !m.init {
 		return
 	}
+	// Current time stamp
 	now := time.Now()
+	// time difference to last time stamp
+	timeDiff := now.Sub(m.lastTimestamp).Seconds()
+	// Save current timestamp
+	m.lastTimestamp = now
+
 	file, err := os.Open(string(NETSTATFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return
 	}
 	defer file.Close()
-	tdiff := now.Sub(m.lastTimestamp)
 
 	scanner := bufio.NewScanner(file)
 	for scanner.Scan() {
 		l := scanner.Text()
+
+		// Skip lines with no net device entry
 		if !strings.Contains(l, ":") {
 			continue
 		}
+
+		// Split line into fields
 		f := strings.Fields(l)
+
+		// Get net device entry
 		dev := strings.Trim(f[0], ":")
 
+		// Check if device is a included device
 		if devmetrics, ok := m.matches[dev]; ok {
-			for name, data := range devmetrics {
-				v, err := strconv.ParseFloat(f[data.index], 64)
-				if err == nil {
-					vdiff := v - data.lastValue
-					value := vdiff / tdiff.Seconds()
-					if data.lastValue == 0 {
-						value = 0
-					}
-					data.lastValue = v
-					y, err := lp.New(name, m.devtags[dev], m.meta, map[string]interface{}{"value": value}, now)
-					if err == nil {
-						switch {
-						case strings.Contains(name, "byte"):
-							y.AddMeta("unit", "bytes/sec")
-						case strings.Contains(name, "pkt"):
-							y.AddMeta("unit", "packets/sec")
-						}
+			for i := range devmetrics {
+				metric := &devmetrics[i]
+
+				// Read value
+				v, err := strconv.ParseInt(f[metric.index], 10, 64)
+				if err != nil {
+					continue
+				}
+				if m.config.SendAbsoluteValues {
+					if y, err := lp.New(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
 						output <- y
 					}
-					devmetrics[name] = data
+				}
+				if m.config.SendDerivedValues {
+					if metric.lastValue >= 0 {
+						rate := float64(v-metric.lastValue) / timeDiff
+						if y, err := lp.New(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]interface{}{"value": rate}, now); err == nil {
+							output <- y
+						}
+					}
+					metric.lastValue = v
 				}
 			}
 		}
 	}
-	m.lastTimestamp = time.Now()
 }
 
 func (m *NetstatCollector) Close() {

collectors/netstatMetric.md

@@ -5,17 +5,23 @@
   "netstat": {
     "include_devices": [
       "eth0"
-    ]
+    ],
+    "send_abs_values" : true,
+    "send_derived_values" : true
   }
 ```
 
 The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. With the `include_devices` list you can specify which network devices should be measured. **Note**: Most other collectors use an _exclude_ list instead of an include list.
 
 Metrics:
-* `net_bytes_in` (`unit=bytes/sec`)
-* `net_bytes_out` (`unit=bytes/sec`)
-* `net_pkts_in` (`unit=packets/sec`)
-* `net_pkts_out` (`unit=packets/sec`)
+* `net_bytes_in` (`unit=bytes`)
+* `net_bytes_out` (`unit=bytes`)
+* `net_pkts_in` (`unit=packets`)
+* `net_pkts_out` (`unit=packets`)
+* `net_bytes_in_bw` (`unit=bytes/sec` if `send_derived_values == true`)
+* `net_bytes_out_bw` (`unit=bytes/sec` if `send_derived_values == true`)
+* `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 `device`.
 

collectors/nfsMetric.go

@@ -11,7 +11,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // First part contains the code for the general NfsCollector.
@@ -36,7 +36,7 @@ type nfsCollector struct {
 }
 
 func (m *nfsCollector) initStats() error {
-	cmd := exec.Command(m.config.Nfsstats, `-l`)
+	cmd := exec.Command(m.config.Nfsstats, `-l`, `--all`)
 	cmd.Wait()
 	buffer, err := cmd.Output()
 	if err == nil {
@@ -52,7 +52,7 @@ func (m *nfsCollector) initStats() error {
 					if err == nil {
 						x := m.data[name]
 						x.current = value
-						x.last = 0
+						x.last = value
 						m.data[name] = x
 					}
 				}
@@ -63,7 +63,7 @@ func (m *nfsCollector) initStats() error {
 }
 
 func (m *nfsCollector) updateStats() error {
-	cmd := exec.Command(m.config.Nfsstats, `-l`)
+	cmd := exec.Command(m.config.Nfsstats, `-l`, `--all`)
 	cmd.Wait()
 	buffer, err := cmd.Output()
 	if err == nil {
@@ -114,6 +114,7 @@ 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/numastatsMetric.go

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 //
@@ -54,6 +54,7 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
 	}
 
 	m.name = "NUMAStatsCollector"
+	m.parallel = true
 	m.setup()
 	m.meta = map[string]string{
 		"source": m.name,

collectors/nvidiaMetric.md

@@ -3,38 +3,74 @@
 
 ```json
   "nvidia": {
-    "exclude_devices" : [
-      "0","1"
+    "exclude_devices": [
+      "0","1", "0000000:ff:01.0"
     ],
     "exclude_metrics": [
-      "nv_fb_memory",
+      "nv_fb_mem_used",
       "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_mem_total`
-* `nv_fb_memory`
+* `nv_fb_mem_total`
+* `nv_fb_mem_used`
+* `nv_bar1_mem_total`
+* `nv_bar1_mem_used`
 * `nv_temp`
 * `nv_fan`
 * `nv_ecc_mode`
 * `nv_perf_state`
-* `nv_power_usage_report`
-* `nv_graphics_clock_report`
-* `nv_sm_clock_report`
-* `nv_mem_clock_report`
+* `nv_power_usage`
+* `nv_graphics_clock`
+* `nv_sm_clock`
+* `nv_mem_clock`
+* `nv_video_clock`
 * `nv_max_graphics_clock`
 * `nv_max_sm_clock`
 * `nv_max_mem_clock`
-* `nv_ecc_db_error`
-* `nv_ecc_sb_error`
-* `nv_power_man_limit`
+* `nv_max_video_clock`
+* `nv_ecc_uncorrected_error`
+* `nv_ecc_corrected_error`
+* `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`
 
-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>`
-
+Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`. 

collectors/rocmsmiMetric.go

@@ -0,0 +1,319 @@
+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

@@ -0,0 +1,47 @@
+
+## `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/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	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
@@ -35,6 +35,10 @@ 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 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": "SAMPLE"}
@@ -42,7 +46,12 @@ func (m *SampleCollector) Init(config json.RawMessage) error {
 	// 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)
+	// 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{"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/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	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

collectors/schedstatMetric.go

@@ -0,0 +1,154 @@
+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

@@ -0,0 +1,11 @@
+
+## `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/tempMetric.go

@@ -3,14 +3,14 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html
@@ -50,6 +50,7 @@ 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)
@@ -70,10 +71,10 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 	globPattern := filepath.Join("/sys/class/hwmon", "*", "temp*_input")
 	inputFiles, err := filepath.Glob(globPattern)
 	if err != nil {
-		return fmt.Errorf("Unable to glob files with pattern '%s': %v", globPattern, err)
+		return fmt.Errorf("unable to glob files with pattern '%s': %v", globPattern, err)
 	}
 	if inputFiles == nil {
-		return fmt.Errorf("Unable to find any files with pattern '%s'", globPattern)
+		return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
 	}
 
 	// Get sensor name for each temperature sensor file
@@ -82,14 +83,14 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 
 		// sensor name
 		nameFile := filepath.Join(filepath.Dir(file), "name")
-		name, err := ioutil.ReadFile(nameFile)
+		name, err := os.ReadFile(nameFile)
 		if err == nil {
 			sensor.name = strings.TrimSpace(string(name))
 		}
 
 		// sensor label
 		labelFile := strings.TrimSuffix(file, "_input") + "_label"
-		label, err := ioutil.ReadFile(labelFile)
+		label, err := os.ReadFile(labelFile)
 		if err == nil {
 			sensor.label = strings.TrimSpace(string(label))
 		}
@@ -116,6 +117,10 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		}
 
 		// Sensor file
+		_, err = os.ReadFile(file)
+		if err != nil {
+			continue
+		}
 		sensor.file = file
 
 		// Sensor tags
@@ -134,7 +139,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		// max temperature
 		if m.config.ReportMaxTemp {
 			maxTempFile := strings.TrimSuffix(file, "_input") + "_max"
-			if buffer, err := ioutil.ReadFile(maxTempFile); err == nil {
+			if buffer, err := os.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
@@ -145,7 +150,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		// critical temperature
 		if m.config.ReportCriticalTemp {
 			criticalTempFile := strings.TrimSuffix(file, "_input") + "_crit"
-			if buffer, err := ioutil.ReadFile(criticalTempFile); err == nil {
+			if buffer, err := os.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
@@ -158,7 +163,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 
 	// Empty sensors map
 	if len(m.sensors) == 0 {
-		return fmt.Errorf("No temperature sensors found")
+		return fmt.Errorf("no temperature sensors found")
 	}
 
 	// Finished initialization
@@ -170,7 +175,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 	for _, sensor := range m.sensors {
 		// Read sensor file
-		buffer, err := ioutil.ReadFile(sensor.file)
+		buffer, err := os.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/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const MAX_NUM_PROCS = 10
@@ -28,6 +28,7 @@ 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 {
@@ -39,14 +40,14 @@ func (m *TopProcsCollector) Init(config json.RawMessage) error {
 		m.config.Num_procs = int(DEFAULT_NUM_PROCS)
 	}
 	if m.config.Num_procs <= 0 || m.config.Num_procs > MAX_NUM_PROCS {
-		return errors.New(fmt.Sprintf("num_procs option must be set in 'topprocs' config (range: 1-%d)", MAX_NUM_PROCS))
+		return fmt.Errorf("num_procs option must be set in 'topprocs' config (range: 1-%d)", MAX_NUM_PROCS)
 	}
 	m.setup()
 	command := exec.Command("ps", "-Ao", "comm", "--sort=-pcpu")
 	command.Wait()
 	_, err = command.Output()
 	if err != nil {
-		return errors.New("Failed to execute command")
+		return errors.New("failed to execute command")
 	}
 	m.init = true
 	return nil

config.json

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

docs/building.md

@@ -0,0 +1,60 @@
+# 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
+```
+
+## 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_

docs/configuration.md

@@ -0,0 +1,189 @@
+# Configuring the CC metric collector
+
+The configuration of the CC metric collector consists of five configuration files: one global file and four component related files.
+
+## Global configuration
+
+The global file contains the paths to the other four files and some global options. 
+
+```json
+{
+  "sinks": "sinks.json",
+  "collectors" : "collectors.json",
+  "receivers" : "receivers.json",
+  "router" : "router.json",
+  "interval": 10,
+  "duration": 1
+}
+```
+
+Be aware that the paths are relative to the execution folder of the cc-metric-collector binary, so it is recommended to use absolute paths.
+
+## Component configuration
+
+The others are mainly list of of subcomponents: the collectors, the receivers, the router and the sinks. Their role is best shown in a picture:
+
+```mermaid
+flowchart LR
+
+  subgraph col ["Collectors"]
+  direction TB
+  cpustat["cpustat"]
+  memstat["memstat"]
+  tempstat["tempstat"]
+  misc["..."]
+  end
+  
+  subgraph Receivers ["Receivers"]
+  direction TB
+  nats["NATS"]
+  httprecv["HTTP"]
+  miscrecv[...]
+  end
+
+  subgraph calc["Aggregator"]
+  direction LR
+  cache["Cache"]
+  agg["Calculator"]
+  end
+
+  subgraph sinks ["Sinks"]
+  direction RL
+  influx["InfluxDB"]
+  ganglia["Ganglia"]
+  logger["Logfile"]
+  miscsink["..."]
+  end
+
+  cpustat --> CollectorManager["CollectorManager"]
+  memstat --> CollectorManager
+  tempstat --> CollectorManager
+  misc --> CollectorManager
+
+  nats  --> ReceiverManager["ReceiverManager"]
+  httprecv --> ReceiverManager
+  miscrecv --> ReceiverManager
+
+  CollectorManager --> newrouter["Router"]
+  ReceiverManager -.-> newrouter
+  calc -.-> newrouter
+  newrouter --> SinkManager["SinkManager"]
+  newrouter -.-> calc
+
+  SinkManager --> influx
+  SinkManager --> ganglia
+  SinkManager --> logger
+  SinkManager --> miscsink
+
+
+```
+
+There are four parts:
+- The collectors read data from files, execute commands and call dynamically loaded library function and send it to the router
+- The router can process metrics by cacheing and evaluating functions and conditions on them
+- The sinks send the metrics to storage backends
+- The receivers can be used to receive metrics from other collectors and forward them to the router. They can be used to create a tree-like structure of collectors.
+
+(A maybe better differentiation between collectors and receivers is that the collectors are called periodically while the receivers have their own logic and submit metrics at any time)
+
+
+### Collectors configuration file
+
+The collectors configuration file tells which metrics should be queried from the system. The metric gathering is logically grouped in so called 'Collectors'. So there are Collectors to read CPU, memory or filesystem statistics. The collectors configuration file is a list of these collectors with collector-specific configurations:
+
+```json
+{
+  "cpustat" : {},
+  "diskstat": {
+    "exclude_metrics": [
+      "disk_total"
+    ]
+  }
+}
+```
+
+The first one is the CPU statistics collector without any collector-specific setting. The second one enables disk mount statistics but excludes the metric `disk_total`.
+
+All names and possible collector-specific configuration options can be found [here](../collectors/README.md).
+
+Some collectors might dynamically load shared libraries. In order to enable these collectors, make sure that the shared library path is part of the `LD_LIBRARY_PATH` environment variable.
+
+### Sinks configuration file
+
+The sinks define the output/sending of metrics. The metrics can be forwarded to multiple sinks, even to sinks of the same type. The sinks configuration file is a list of these sinks, each with an individual name.
+
+```json
+{
+  "myinflux" : {
+    "type" : "influxasync",
+    "host": "localhost",
+    "port": "8086",
+    "organization" : "testorga",
+    "database" : "testbucket",
+    "password" : "<my secret JWT>"
+  },
+  "companyinflux" : {
+    "type" : "influxasync",
+    "host": "companyhost",
+    "port": "8086",
+    "organization" : "company",
+    "database" : "main",
+    "password" : "<company's secret JWT>"
+  }
+}
+```
+
+The above example configuration file defines two sink, both ot type `influxasync`. They are differentiated internally by the names: `myinflux` and `companyinflux`.
+
+All types and possible sink-specific configuration options can be found [here](../sinks/README.md).
+
+Some sinks might dynamically load shared libraries. In order to enable these sinks, make sure that the shared library path is part of the `LD_LIBRARY_PATH` environment variable.
+
+### Router configuration file
+
+The collectors and the sinks are connected through the router. The router forwards the metrics to the sinks but enables some data processing. A common example is to tag all passing metrics like adding `cluster=mycluster`. But also aggregations like "take the average of all 'ipc' metrics" (ipc -> Instructions Per Cycle). Since the configurations of these aggregations can be quite complicated, we refer to the router's [README](../internal/metricRouter/README.md).
+
+A simple router configuration file to start with looks like this:
+
+```json
+{
+    "add_tags" : [
+        {
+            "key" : "cluster",
+            "value" : "mycluster",
+            "if" : "*"
+        }
+    ],
+    "interval_timestamp" : false,
+    "num_cache_intervals" : 0
+}
+```
+
+With the `add_tags` section, we tell to attach the `cluster=mycluster` tag to each (`*` metric). The `interval_timestamp` tell the router to not touch the timestamp of metrics. It is possible to send all metrics within an interval with a common time stamp to avoid later alignment issues. The `num_cache_intervals` diables the cache completely. The cache is only required if you want to do complex metric aggregations.
+
+All configuration options can be found [here](../internal/metricRouter/README.md).
+
+### Receivers configuration file
+
+The receivers are a special feature of the CC Metric Collector to enable simpler integration into exising setups. While collectors query data from the local system, the receivers commonly get data from other systems through some network technology like HTTP or NATS. The idea is keep the current setup but send it to a CC Metric Collector which forwards it to the the destination system (if a sink exists for it). For most setups, the receivers are not required and an the receiver config file should contain only an empty JSON map (`{}`). 
+
+```json
+{
+  "nats_rack0": {
+    "type": "nats",
+    "address" : "nats-server.example.org",
+    "port" : "4222",
+    "subject" : "rack0",
+  },
+  "nats_rack1": {
+    "type": "nats",
+    "address" : "nats-server.example.org",
+    "port" : "4222",
+    "subject" : "rack1",
+  }
+}
+```
+
+This example configuration creates two receivers with the names `nats_rack0` and `nats_rack1`. While one subscribes to metrics published with the `rack0` subject, the other one subscribes to the `rack0` subject. The NATS server is the same as it manages all subjects in a subnet. (As example, the router could add tags `rack=0` and `rack=1` respectively to the received metrics.)
+
+All types and possible receiver-specific configuration options can be found [here](../receivers/README.md).

docs/introduction.md

@@ -0,0 +1,23 @@
+# 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

@@ -1,19 +1,40 @@
 module github.com/ClusterCockpit/cc-metric-collector
 
-go 1.16
+go 1.18
 
 require (
-	github.com/NVIDIA/go-nvml v0.11.1-0
-	github.com/influxdata/influxdb-client-go/v2 v2.7.0
+	github.com/ClusterCockpit/cc-units v0.3.0
+	github.com/ClusterCockpit/go-rocm-smi v0.3.0
+	github.com/NVIDIA/go-nvml v0.11.6-0
+	github.com/PaesslerAG/gval v1.2.0
+	github.com/gorilla/mux v1.8.0
+	github.com/influxdata/influxdb-client-go/v2 v2.9.1
 	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
-	github.com/nats-io/nats.go v1.13.1-0.20211122170419-d7c1d78a50fc
-	golang.org/x/sys v0.0.0-20220114195835-da31bd327af9
-	gopkg.in/Knetic/govaluate.v2 v2.3.0
+	github.com/nats-io/nats.go v1.16.0
+	github.com/prometheus/client_golang v1.12.2
+	github.com/stmcginnis/gofish v0.13.0
+	github.com/tklauser/go-sysconf v0.3.10
+	golang.org/x/sys v0.0.0-20220712014510-0a85c31ab51e
 )
 
 require (
-	github.com/PaesslerAG/gval v1.1.2
+	github.com/beorn7/perks v1.0.1 // indirect
+	github.com/cespare/xxhash/v2 v2.1.2 // indirect
+	github.com/deepmap/oapi-codegen v1.11.0 // indirect
 	github.com/golang/protobuf v1.5.2 // indirect
-	github.com/nats-io/nats-server/v2 v2.7.0 // indirect
-	google.golang.org/protobuf v1.27.1 // indirect
+	github.com/google/uuid v1.3.0 // indirect
+	github.com/matttproud/golang_protobuf_extensions v1.0.1 // indirect
+	github.com/nats-io/nats-server/v2 v2.8.4 // indirect
+	github.com/nats-io/nkeys v0.3.0 // indirect
+	github.com/nats-io/nuid v1.0.1 // indirect
+	github.com/pkg/errors v0.9.1 // indirect
+	github.com/prometheus/client_model v0.2.0 // indirect
+	github.com/prometheus/common v0.37.0 // indirect
+	github.com/prometheus/procfs v0.7.3 // indirect
+	github.com/shopspring/decimal v1.3.1 // indirect
+	github.com/tklauser/numcpus v0.4.0 // indirect
+	golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d // indirect
+	golang.org/x/net v0.0.0-20220708220712-1185a9018129 // indirect
+	google.golang.org/protobuf v1.28.0 // indirect
+	gopkg.in/yaml.v2 v2.4.0 // indirect
 )

go.sum

@@ -1,145 +1,624 @@
-github.com/NVIDIA/go-nvml v0.11.1-0 h1:XHSz3zZKC4NCP2ja1rI7++DXFhA+uDhdYa3MykCTGHY=
-github.com/NVIDIA/go-nvml v0.11.1-0/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
-github.com/PaesslerAG/gval v1.1.2 h1:EROKxV4/fAKWb0Qoj7NOxmHZA7gcpjOV9XgiRZMRCUU=
-github.com/PaesslerAG/gval v1.1.2/go.mod h1:Fa8gfkCmUsELXgayr8sfL/sw+VzCVoa03dcOcR/if2w=
+cloud.google.com/go v0.26.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
+cloud.google.com/go v0.34.0/go.mod h1:aQUYkXzVsufM+DwF1aE+0xfcU+56JwCaLick0ClmMTw=
+cloud.google.com/go v0.38.0/go.mod h1:990N+gfupTy94rShfmMCWGDn0LpTmnzTp2qbd1dvSRU=
+cloud.google.com/go v0.44.1/go.mod h1:iSa0KzasP4Uvy3f1mN/7PiObzGgflwredwwASm/v6AU=
+cloud.google.com/go v0.44.2/go.mod h1:60680Gw3Yr4ikxnPRS/oxxkBccT6SA1yMk63TGekxKY=
+cloud.google.com/go v0.45.1/go.mod h1:RpBamKRgapWJb87xiFSdk4g1CME7QZg3uwTez+TSTjc=
+cloud.google.com/go v0.46.3/go.mod h1:a6bKKbmY7er1mI7TEI4lsAkts/mkhTSZK8w33B4RAg0=
+cloud.google.com/go v0.50.0/go.mod h1:r9sluTvynVuxRIOHXQEHMFffphuXHOMZMycpNR5e6To=
+cloud.google.com/go v0.52.0/go.mod h1:pXajvRH/6o3+F9jDHZWQ5PbGhn+o8w9qiu/CffaVdO4=
+cloud.google.com/go v0.53.0/go.mod h1:fp/UouUEsRkN6ryDKNW/Upv/JBKnv6WDthjR6+vze6M=
+cloud.google.com/go v0.54.0/go.mod h1:1rq2OEkV3YMf6n/9ZvGWI3GWw0VoqH/1x2nd8Is/bPc=
+cloud.google.com/go v0.56.0/go.mod h1:jr7tqZxxKOVYizybht9+26Z/gUq7tiRzu+ACVAMbKVk=
+cloud.google.com/go v0.57.0/go.mod h1:oXiQ6Rzq3RAkkY7N6t3TcE6jE+CIBBbA36lwQ1JyzZs=
+cloud.google.com/go v0.62.0/go.mod h1:jmCYTdRCQuc1PHIIJ/maLInMho30T/Y0M4hTdTShOYc=
+cloud.google.com/go v0.65.0/go.mod h1:O5N8zS7uWy9vkA9vayVHs65eM1ubvY4h553ofrNHObY=
+cloud.google.com/go/bigquery v1.0.1/go.mod h1:i/xbL2UlR5RvWAURpBYZTtm/cXjCha9lbfbpx4poX+o=
+cloud.google.com/go/bigquery v1.3.0/go.mod h1:PjpwJnslEMmckchkHFfq+HTD2DmtT67aNFKH1/VBDHE=
+cloud.google.com/go/bigquery v1.4.0/go.mod h1:S8dzgnTigyfTmLBfrtrhyYhwRxG72rYxvftPBK2Dvzc=
+cloud.google.com/go/bigquery v1.5.0/go.mod h1:snEHRnqQbz117VIFhE8bmtwIDY80NLUZUMb4Nv6dBIg=
+cloud.google.com/go/bigquery v1.7.0/go.mod h1://okPTzCYNXSlb24MZs83e2Do+h+VXtc4gLoIoXIAPc=
+cloud.google.com/go/bigquery v1.8.0/go.mod h1:J5hqkt3O0uAFnINi6JXValWIb1v0goeZM77hZzJN/fQ=
+cloud.google.com/go/datastore v1.0.0/go.mod h1:LXYbyblFSglQ5pkeyhO+Qmw7ukd3C+pD7TKLgZqpHYE=
+cloud.google.com/go/datastore v1.1.0/go.mod h1:umbIZjpQpHh4hmRpGhH4tLFup+FVzqBi1b3c64qFpCk=
+cloud.google.com/go/pubsub v1.0.1/go.mod h1:R0Gpsv3s54REJCy4fxDixWD93lHJMoZTyQ2kNxGRt3I=
+cloud.google.com/go/pubsub v1.1.0/go.mod h1:EwwdRX2sKPjnvnqCa270oGRyludottCI76h+R3AArQw=
+cloud.google.com/go/pubsub v1.2.0/go.mod h1:jhfEVHT8odbXTkndysNHCcx0awwzvfOlguIAii9o8iA=
+cloud.google.com/go/pubsub v1.3.1/go.mod h1:i+ucay31+CNRpDW4Lu78I4xXG+O1r/MAHgjpRVR+TSU=
+cloud.google.com/go/storage v1.0.0/go.mod h1:IhtSnM/ZTZV8YYJWCY8RULGVqBDmpoyjwiyrjsg+URw=
+cloud.google.com/go/storage v1.5.0/go.mod h1:tpKbwo567HUNpVclU5sGELwQWBDZ8gh0ZeosJ0Rtdos=
+cloud.google.com/go/storage v1.6.0/go.mod h1:N7U0C8pVQ/+NIKOBQyamJIeKQKkZ+mxpohlUTyfDhBk=
+cloud.google.com/go/storage v1.8.0/go.mod h1:Wv1Oy7z6Yz3DshWRJFhqM/UCfaWIRTdp0RXyy7KQOVs=
+cloud.google.com/go/storage v1.10.0/go.mod h1:FLPqc6j+Ki4BU591ie1oL6qBQGu2Bl/tZ9ullr3+Kg0=
+dmitri.shuralyov.com/gpu/mtl v0.0.0-20190408044501-666a987793e9/go.mod h1:H6x//7gZCb22OMCxBHrMx7a5I7Hp++hsVxbQ4BYO7hU=
+github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
+github.com/BurntSushi/xgb v0.0.0-20160522181843-27f122750802/go.mod h1:IVnqGOEym/WlBOVXweHU+Q+/VP0lqqI8lqeDx9IjBqo=
+github.com/ClusterCockpit/cc-units v0.3.0 h1:JEKgEyvN4GABheKIReW2siDXgpYf2zf4STXV2ip418Y=
+github.com/ClusterCockpit/cc-units v0.3.0/go.mod h1:3S3PAhAayS3pbgcT4q9Vn9VJw22Op51X0YimtG77zBw=
+github.com/ClusterCockpit/go-rocm-smi v0.3.0 h1:1qZnSpG7/NyLtc7AjqnUL9Jb8xtqG1nMVgp69rJfaR8=
+github.com/ClusterCockpit/go-rocm-smi v0.3.0/go.mod h1:+I3UMeX3OlizXDf1WpGD43W4KGZZGVSGmny6rTeOnWA=
+github.com/NVIDIA/go-nvml v0.11.6-0 h1:tugQzmaX84Y/6+03wZ/MAgcpfSKDkvkAWeuxFNLHmxY=
+github.com/NVIDIA/go-nvml v0.11.6-0/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
+github.com/PaesslerAG/gval v1.2.0 h1:DA7PsxmtzlUU4bYxV35MKp9KDDVWcrJJRhlaCohMhsM=
+github.com/PaesslerAG/gval v1.2.0/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/alecthomas/template v0.0.0-20160405071501-a0175ee3bccc/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
+github.com/alecthomas/template v0.0.0-20190718012654-fb15b899a751/go.mod h1:LOuyumcjzFXgccqObfd/Ljyb9UuFJ6TxHnclSeseNhc=
+github.com/alecthomas/units v0.0.0-20151022065526-2efee857e7cf/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
+github.com/alecthomas/units v0.0.0-20190717042225-c3de453c63f4/go.mod h1:ybxpYRFXyAe+OPACYpWeL0wqObRcbAqCMya13uyzqw0=
+github.com/alecthomas/units v0.0.0-20190924025748-f65c72e2690d/go.mod h1:rBZYJk541a8SKzHPHnH3zbiI+7dagKZ0cgpgrD7Fyho=
+github.com/beorn7/perks v0.0.0-20180321164747-3a771d992973/go.mod h1:Dwedo/Wpr24TaqPxmxbtue+5NUziq4I4S80YR8gNf3Q=
+github.com/beorn7/perks v1.0.0/go.mod h1:KWe93zE9D1o94FZ5RNwFwVgaQK1VOXiVxmqh+CedLV8=
+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/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
+github.com/cespare/xxhash/v2 v2.1.1/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/cespare/xxhash/v2 v2.1.2 h1:YRXhKfTDauu4ajMg1TPgFO5jnlC2HCbmLXMcTG5cbYE=
+github.com/cespare/xxhash/v2 v2.1.2/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/chzyer/logex v1.1.10/go.mod h1:+Ywpsq7O8HXn0nuIou7OrIPyXbp3wmkHB+jjWRnGsAI=
+github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5PlCu98SY8svDHJxuZscDgtXS6KTTbou5AhLI=
+github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU=
+github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDkc90ppPyw=
+github.com/cncf/udpa/go v0.0.0-20191209042840-269d4d468f6f/go.mod h1:M8M6+tZqaGXZJjfX53e64911xZQV5JYwmTeXPW+k8Sc=
+github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/cyberdelia/templates v0.0.0-20141128023046-ca7fffd4298c/go.mod h1:GyV+0YP4qX0UQ7r2MoYZ+AvYDp12OF5yg4q8rGnyNh4=
 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/deepmap/oapi-codegen v1.8.2 h1:SegyeYGcdi0jLLrpbCMoJxnUUn8GBXHsvr4rbzjuhfU=
-github.com/deepmap/oapi-codegen v1.8.2/go.mod h1:YLgSKSDv/bZQB7N4ws6luhozi3cEdRktEqrX88CvjIw=
-github.com/dgrijalva/jwt-go v3.2.0+incompatible/go.mod h1:E3ru+11k8xSBh+hMPgOLZmtrrCbhqsmaPHjLKYnJCaQ=
-github.com/getkin/kin-openapi v0.61.0/go.mod h1:7Yn5whZr5kJi6t+kShccXS8ae1APpYTW6yheSwk8Yi4=
+github.com/decred/dcrd/crypto/blake256 v1.0.0/go.mod h1:sQl2p6Y26YV+ZOcSTP6thNdn47hh8kt6rqSlvmrXFAc=
+github.com/decred/dcrd/dcrec/secp256k1/v4 v4.0.0-20210816181553-5444fa50b93d/go.mod h1:tmAIfUFEirG/Y8jhZ9M+h36obRZAk/1fcSpXwAVlfqE=
+github.com/decred/dcrd/dcrec/secp256k1/v4 v4.0.1/go.mod h1:hyedUtir6IdtD/7lIxGeCxkaw7y45JueMRL4DIyJDKs=
+github.com/deepmap/oapi-codegen v1.11.0 h1:f/X2NdIkaBKsSdpeuwLnY/vDI0AtPUrmB5LMgc7YD+A=
+github.com/deepmap/oapi-codegen v1.11.0/go.mod h1:k+ujhoQGxmQYBZBbxhOZNZf4j08qv5mC+OH+fFTnKxM=
+github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
+github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
+github.com/envoyproxy/go-control-plane v0.9.4/go.mod h1:6rpuAdCZL397s3pYoYcLgu1mIlRU8Am5FuJP05cCM98=
+github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
+github.com/getkin/kin-openapi v0.94.0/go.mod h1:LWZfzOd7PRy8GJ1dJ6mCU6tNdSfOwRac1BUPam4aw6Q=
 github.com/ghodss/yaml v1.0.0/go.mod h1:4dBDuWmgqj2HViK6kFavaiC9ZROes6MMH2rRYeMEF04=
-github.com/go-chi/chi/v5 v5.0.0/go.mod h1:BBug9lr0cqtdAhsu6R4AAdvufI0/XBzAQSsUqJpoZOs=
+github.com/gin-contrib/sse v0.1.0/go.mod h1:RHrZQHXnP2xjPF+u1gW/2HnVO7nvIa9PG3Gm+fLHvGI=
+github.com/gin-gonic/gin v1.7.7/go.mod h1:axIBovoeJpVj8S3BwE0uPMTeReE4+AfFtqpqaZ1qq1U=
+github.com/go-chi/chi/v5 v5.0.7/go.mod h1:DslCQbL2OYiznFReuXYUmQ2hGd1aDpCnlMNITLSKoi8=
+github.com/go-gl/glfw v0.0.0-20190409004039-e6da0acd62b1/go.mod h1:vR7hzQXu2zJy9AVAgeJqvqgH9Q5CA+iKCZ2gyEVpxRU=
+github.com/go-gl/glfw/v3.3/glfw v0.0.0-20191125211704-12ad95a8df72/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
+github.com/go-gl/glfw/v3.3/glfw v0.0.0-20200222043503-6f7a984d4dc4/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
+github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
+github.com/go-kit/kit v0.9.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
+github.com/go-kit/log v0.1.0/go.mod h1:zbhenjAZHb184qTLMA9ZjW7ThYL0H2mk7Q6pNt4vbaY=
+github.com/go-kit/log v0.2.0/go.mod h1:NwTd00d/i8cPZ3xOwwiv2PO5MOcx78fFErGNcVmBjv0=
+github.com/go-logfmt/logfmt v0.3.0/go.mod h1:Qt1PoO58o5twSAckw1HlFXLmHsOX5/0LbT9GBnD5lWE=
+github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V4qmtdjCk=
+github.com/go-logfmt/logfmt v0.5.0/go.mod h1:wCYkCAKZfumFQihp8CzCvQ3paCTfi41vtzG1KdI/P7A=
+github.com/go-logfmt/logfmt v0.5.1/go.mod h1:WYhtIu8zTZfxdn5+rREduYbwxfcBr/Vr6KEVveWlfTs=
 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/go-openapi/swag v0.21.1/go.mod h1:QYRuS/SOXUCsnplDa677K7+DxSOj6IPNl/eQntq43wQ=
+github.com/go-playground/assert/v2 v2.0.1/go.mod h1:VDjEfimB/XKnb+ZQfWdccd7VUvScMdVu0Titje2rxJ4=
+github.com/go-playground/locales v0.13.0/go.mod h1:taPMhCMXrRLJO55olJkUXHZBHCxTMfnGwq/HNwmWNS8=
+github.com/go-playground/locales v0.14.0/go.mod h1:sawfccIbzZTqEDETgFXqTho0QybSa7l++s0DH+LDiLs=
+github.com/go-playground/universal-translator v0.17.0/go.mod h1:UkSxE5sNxxRwHyU+Scu5vgOQjsIJAF8j9muTVoKLVtA=
+github.com/go-playground/universal-translator v0.18.0/go.mod h1:UvRDBj+xPUEGrFYl+lu/H90nyDXpg0fqeB/AQUGNTVA=
+github.com/go-playground/validator/v10 v10.4.1/go.mod h1:nlOn6nFhuKACm19sB/8EGNn9GlaMV7XkbRSipzJ0Ii4=
+github.com/go-playground/validator/v10 v10.11.0/go.mod h1:i+3WkQ1FvaUjjxh1kSvIA4dMGDBiPU55YFDl0WbKdWU=
+github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
+github.com/goccy/go-json v0.9.7/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
+github.com/gogo/protobuf v1.1.1/go.mod h1:r8qH/GZQm5c6nD/R0oafs1akxWv10x8SbQlK7atdtwQ=
+github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzqecmYZeUEB8OUGHkxJ+I=
+github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
+github.com/golang/groupcache v0.0.0-20190702054246-869f871628b6/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
+github.com/golang/groupcache v0.0.0-20191227052852-215e87163ea7/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
+github.com/golang/groupcache v0.0.0-20200121045136-8c9f03a8e57e/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
+github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
+github.com/golang/mock v1.2.0/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
+github.com/golang/mock v1.3.1/go.mod h1:sBzyDLLjw3U8JLTeZvSv8jJB+tU5PVekmnlKIyFUx0Y=
+github.com/golang/mock v1.4.0/go.mod h1:UOMv5ysSaYNkG+OFQykRIcU/QvvxJf3p21QfJ2Bt3cw=
+github.com/golang/mock v1.4.1/go.mod h1:UOMv5ysSaYNkG+OFQykRIcU/QvvxJf3p21QfJ2Bt3cw=
+github.com/golang/mock v1.4.3/go.mod h1:UOMv5ysSaYNkG+OFQykRIcU/QvvxJf3p21QfJ2Bt3cw=
+github.com/golang/mock v1.4.4/go.mod h1:l3mdAwkq5BuhzHwde/uurv3sEJeZMXNpwsxVWU71h+4=
+github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.3.1/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.3.2/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.3.3/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
+github.com/golang/protobuf v1.3.4/go.mod h1:vzj43D7+SQXF/4pzW/hwtAqwc6iTitCiVSaWz5lYuqw=
+github.com/golang/protobuf v1.3.5/go.mod h1:6O5/vntMXwX2lRkT1hjjk0nAC1IDOTvTlVgjlRvqsdk=
 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 v1.4.1/go.mod h1:U8fpvMrcmy5pZrNK1lt4xCsGvpyWQ/VVv6QDs8UjoX8=
 github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
+github.com/golang/protobuf v1.4.3/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/btree v0.0.0-20180813153112-4030bb1f1f0c/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
+github.com/google/btree v1.0.0/go.mod h1:lNA+9X1NB3Zf8V7Ke586lFgjr2dZNuvo3lPJSGZ5JPQ=
+github.com/google/go-cmp v0.2.0/go.mod h1:oXzfMopK8JAjlY9xF4vHSVASa0yLyX7SntLO5aqRK0M=
 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 v0.4.1/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.1/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.4/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.5 h1:Khx7svrCpmxxtHBq5j2mp/xVjsi8hQMfNLvJFAlrGgU=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
+github.com/google/martian v2.1.0+incompatible/go.mod h1:9I4somxYTbIHy5NJKHRl3wXiIaQGbYVAs8BPL6v8lEs=
+github.com/google/martian/v3 v3.0.0/go.mod h1:y5Zk1BBys9G+gd6Jrk0W3cC1+ELVxBWuIGO+w/tUAp0=
+github.com/google/pprof v0.0.0-20181206194817-3ea8567a2e57/go.mod h1:zfwlbNMJ+OItoe0UupaVj+oy1omPYYDuagoSzA8v9mc=
+github.com/google/pprof v0.0.0-20190515194954-54271f7e092f/go.mod h1:zfwlbNMJ+OItoe0UupaVj+oy1omPYYDuagoSzA8v9mc=
+github.com/google/pprof v0.0.0-20191218002539-d4f498aebedc/go.mod h1:ZgVRPoUq/hfqzAqh7sHMqb3I9Rq5C59dIz2SbBwJ4eM=
+github.com/google/pprof v0.0.0-20200212024743-f11f1df84d12/go.mod h1:ZgVRPoUq/hfqzAqh7sHMqb3I9Rq5C59dIz2SbBwJ4eM=
+github.com/google/pprof v0.0.0-20200229191704-1ebb73c60ed3/go.mod h1:ZgVRPoUq/hfqzAqh7sHMqb3I9Rq5C59dIz2SbBwJ4eM=
+github.com/google/pprof v0.0.0-20200430221834-fc25d7d30c6d/go.mod h1:ZgVRPoUq/hfqzAqh7sHMqb3I9Rq5C59dIz2SbBwJ4eM=
+github.com/google/pprof v0.0.0-20200708004538-1a94d8640e99/go.mod h1:ZgVRPoUq/hfqzAqh7sHMqb3I9Rq5C59dIz2SbBwJ4eM=
+github.com/google/renameio v0.1.0/go.mod h1:KWCgfxg9yswjAJkECMjeO8J8rahYeXnNhOm40UhjYkI=
+github.com/google/uuid v1.3.0 h1:t6JiXgmwXMjEs8VusXIJk2BXHsn+wx8BZdTaoZ5fu7I=
+github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/googleapis/gax-go/v2 v2.0.4/go.mod h1:0Wqv26UfaUD9n4G6kQubkQ+KchISgw+vpHVxEJEs9eg=
+github.com/googleapis/gax-go/v2 v2.0.5/go.mod h1:DWXyrwAJ9X0FpwwEdw+IPEYBICEFu5mhpdKc/us6bOk=
+github.com/gorilla/mux v1.8.0 h1:i40aqfkR1h2SlN9hojwV5ZA91wcXFOvkdNIeFDP5koI=
 github.com/gorilla/mux v1.8.0/go.mod h1:DVbg23sWSpFRCP0SfiEN6jmj59UnW/n46BH5rLB71So=
-github.com/influxdata/influxdb-client-go/v2 v2.7.0 h1:QgP5mlBE9sGnzplpnf96pr+p7uqlIlL4W2GAP3n+XZg=
-github.com/influxdata/influxdb-client-go/v2 v2.7.0/go.mod h1:Y/0W1+TZir7ypoQZYd2IrnVOKB3Tq6oegAQeSVN/+EU=
-github.com/influxdata/line-protocol v0.0.0-20200327222509-2487e7298839/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
+github.com/hashicorp/golang-lru v0.5.0/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
+github.com/hashicorp/golang-lru v0.5.1/go.mod h1:/m3WP610KZHVQ1SGc6re/UDhFvYD7pJ4Ao+sR/qLZy8=
+github.com/ianlancetaylor/demangle v0.0.0-20181102032728-5e5cf60278f6/go.mod h1:aSSvb/t6k1mPoxDqO4vJh6VOCGPwU4O0C2/Eqndh1Sc=
+github.com/influxdata/influxdb-client-go/v2 v2.9.1 h1:5kbH226fmmiV0MMTs7a8L7/ECCKdJWBi1QZNNv4/TkI=
+github.com/influxdata/influxdb-client-go/v2 v2.9.1/go.mod h1:x7Jo5UHHl+w8wu8UnGiNobDDHygojXwJX4mx7rXGKMk=
 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/klauspost/compress v1.13.4 h1:0zhec2I8zGnjWcKyLl6i3gPqKANCCn5e9xmviEEeX6s=
-github.com/klauspost/compress v1.13.4/go.mod h1:8dP1Hq4DHOhN9w426knH3Rhby4rFm6D8eO+e+Dq5Gzg=
-github.com/kr/pretty v0.1.0 h1:L/CwN0zerZDmRFUapSPitk6f+Q3+0za1rQkzVuMiMFI=
+github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
+github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX5e0EB2j4=
+github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
+github.com/json-iterator/go v1.1.9/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
+github.com/json-iterator/go v1.1.10/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
+github.com/json-iterator/go v1.1.11/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
+github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
+github.com/jstemmer/go-junit-report v0.0.0-20190106144839-af01ea7f8024/go.mod h1:6v2b51hI/fHJwM22ozAgKL4VKDeJcHhJFhtBdhmNjmU=
+github.com/jstemmer/go-junit-report v0.9.1/go.mod h1:Brl9GWCQeLvo8nXZwPNNblvFj/XSXhF0NWZEnDohbsk=
+github.com/julienschmidt/httprouter v1.2.0/go.mod h1:SYymIcj16QtmaHHD7aYtjjsJG7VTCxuUUipMqKk8s4w=
+github.com/julienschmidt/httprouter v1.3.0/go.mod h1:JR6WtHb+2LUe8TCKY3cZOxFyyO8IZAc4RVcycCCAKdM=
+github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
+github.com/klauspost/compress v1.14.4 h1:eijASRJcobkVtSt81Olfh7JX43osYLwy5krOJo6YEu4=
+github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
+github.com/konsorten/go-windows-terminal-sequences v1.0.3/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
+github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
+github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
+github.com/kr/pretty v0.3.0 h1:WgNl7dwNpEZ6jJ9k1snq4pZsg7DOEN8hP9Xw0Tsjwk0=
+github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
 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/labstack/echo/v4 v4.2.1/go.mod h1:AA49e0DZ8kk5jTOOCKNuPR6oTnBS0dYiM4FW1e6jwpg=
-github.com/labstack/gommon v0.3.0/go.mod h1:MULnywXg0yavhxWKc+lOruYdAhDwPK9wf0OL7NoOu+k=
+github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
+github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/labstack/echo/v4 v4.7.2/go.mod h1:xkCDAdFCIf8jsFQ5NnbK7oqaF/yU1A1X20Ltm0OvSks=
+github.com/labstack/gommon v0.3.1/go.mod h1:uW6kP17uPlLJsD3ijUYn3/M5bAxtlZhMI6m3MFxTMTM=
+github.com/leodido/go-urn v1.2.0/go.mod h1:+8+nEpDfqqsY+g338gtMEUOtuK+4dEMhiQEgxpxOKII=
+github.com/leodido/go-urn v1.2.1/go.mod h1:zt4jvISO2HfUBqxjfIshjdMTYS56ZS/qv49ictyFfxY=
+github.com/lestrrat-go/backoff/v2 v2.0.8/go.mod h1:rHP/q/r9aT27n24JQLa7JhSQZCKBBOiM/uP402WwN8Y=
+github.com/lestrrat-go/blackmagic v1.0.0/go.mod h1:TNgH//0vYSs8VXDCfkZLgIrVTTXQELZffUV0tz3MtdQ=
+github.com/lestrrat-go/blackmagic v1.0.1/go.mod h1:UrEqBzIR2U6CnzVyUtfM6oZNMt/7O7Vohk2J0OGSAtU=
+github.com/lestrrat-go/httpcc v1.0.1/go.mod h1:qiltp3Mt56+55GPVCbTdM9MlqhvzyuL6W/NMDA8vA5E=
+github.com/lestrrat-go/iter v1.0.1/go.mod h1:zIdgO1mRKhn8l9vrZJZz9TUMMFbQbLeTsbqPDrJ/OJc=
+github.com/lestrrat-go/iter v1.0.2/go.mod h1:Momfcq3AnRlRjI5b5O8/G5/BvpzrhoFTZcn06fEOPt4=
+github.com/lestrrat-go/jwx v1.2.24/go.mod h1:zoNuZymNl5lgdcu6P7K6ie2QRll5HVfF4xwxBBK1NxY=
+github.com/lestrrat-go/option v1.0.0/go.mod h1:5ZHFbivi4xwXxhxY9XHDe2FHo6/Z7WWmtT7T5nBBp3I=
 github.com/mailru/easyjson v0.0.0-20190614124828-94de47d64c63/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
 github.com/mailru/easyjson v0.0.0-20190626092158-b2ccc519800e/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
-github.com/matryer/moq v0.0.0-20190312154309-6cfb0558e1bd/go.mod h1:9ELz6aaclSIGnZBoaSLZ3NAl1VTufbOrXBPvtcy6WiQ=
-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/mailru/easyjson v0.7.6/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
+github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
+github.com/matryer/moq v0.2.7/go.mod h1:kITsx543GOENm48TUAQyJ9+SAvFSr7iGQXPoth/VUBk=
+github.com/mattn/go-colorable v0.1.11/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=
+github.com/mattn/go-colorable v0.1.12/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=
 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/mattn/go-isatty v0.0.14/go.mod h1:7GGIvUiUoEMVVmxf/4nioHXj79iQHKdU27kJ6hsGG94=
+github.com/matttproud/golang_protobuf_extensions v1.0.1 h1:4hp9jkHxhMHkqkrB3Ix0jegS5sx/RkqARlsWZ6pIwiU=
+github.com/matttproud/golang_protobuf_extensions v1.0.1/go.mod h1:D8He9yQNgCq6Z5Ld7szi9bcBfOoFv/3dc6xSMkL2PC0=
+github.com/minio/highwayhash v1.0.2 h1:Aak5U0nElisjDCfPSG79Tgzkn2gl66NxOMspRrKnA/g=
+github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
+github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
+github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
+github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
+github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
+github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
+github.com/nats-io/jwt/v2 v2.2.1-0.20220330180145-442af02fd36a h1:lem6QCvxR0Y28gth9P+wV2K/zYUUAkJ+55U8cpS0p5I=
+github.com/nats-io/nats-server/v2 v2.8.4 h1:0jQzze1T9mECg8YZEl8+WYUXb9JKluJfCBriPUtluB4=
+github.com/nats-io/nats-server/v2 v2.8.4/go.mod h1:8zZa+Al3WsESfmgSs98Fi06dRWLH5Bnq90m5bKD/eT4=
+github.com/nats-io/nats.go v1.16.0 h1:zvLE7fGBQYW6MWaFaRdsgm9qT39PJDQoju+DS8KsO1g=
+github.com/nats-io/nats.go v1.16.0/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/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
+github.com/pkg/errors v0.8.0/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/prometheus/client_golang v0.9.1/go.mod h1:7SWBe2y4D6OKWSNQJUaRYU/AaXPKyh/dDVn+NZz0KFw=
+github.com/prometheus/client_golang v1.0.0/go.mod h1:db9x61etRT2tGnBNRi70OPL5FsnadC4Ky3P0J6CfImo=
+github.com/prometheus/client_golang v1.7.1/go.mod h1:PY5Wy2awLA44sXw4AOSfFBetzPP4j5+D6mVACh+pe2M=
+github.com/prometheus/client_golang v1.11.0/go.mod h1:Z6t4BnS23TR94PD6BsDNk8yVqroYurpAkEiz0P2BEV0=
+github.com/prometheus/client_golang v1.12.1/go.mod h1:3Z9XVyYiZYEO+YQWt3RD2R3jrbd179Rt297l4aS6nDY=
+github.com/prometheus/client_golang v1.12.2 h1:51L9cDoUHVrXx4zWYlcLQIZ+d+VXHgqnYKkIuq4g/34=
+github.com/prometheus/client_golang v1.12.2/go.mod h1:3Z9XVyYiZYEO+YQWt3RD2R3jrbd179Rt297l4aS6nDY=
+github.com/prometheus/client_model v0.0.0-20180712105110-5c3871d89910/go.mod h1:MbSGuTsp3dbXC40dX6PRTWyKYBIrTGTE9sqQNg2J8bo=
+github.com/prometheus/client_model v0.0.0-20190129233127-fd36f4220a90/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
+github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
+github.com/prometheus/client_model v0.2.0 h1:uq5h0d+GuxiXLJLNABMgp2qUWDPiLvgCzz2dUR+/W/M=
+github.com/prometheus/client_model v0.2.0/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
+github.com/prometheus/common v0.4.1/go.mod h1:TNfzLD0ON7rHzMJeJkieUDPYmFC7Snx/y86RQel1bk4=
+github.com/prometheus/common v0.10.0/go.mod h1:Tlit/dnDKsSWFlCLTWaA1cyBgKHSMdTB80sz/V91rCo=
+github.com/prometheus/common v0.26.0/go.mod h1:M7rCNAaPfAosfx8veZJCuw84e35h3Cfd9VFqTh1DIvc=
+github.com/prometheus/common v0.32.1/go.mod h1:vu+V0TpY+O6vW9J44gczi3Ap/oXXR10b+M/gUGO4Hls=
+github.com/prometheus/common v0.37.0 h1:ccBbHCgIiT9uSoFY0vX8H3zsNR5eLt17/RQLUvn8pXE=
+github.com/prometheus/common v0.37.0/go.mod h1:phzohg0JFMnBEFGxTDbfu3QyL5GI8gTQJFhYO5B3mfA=
+github.com/prometheus/procfs v0.0.0-20181005140218-185b4288413d/go.mod h1:c3At6R/oaqEKCNdg8wHV1ftS6bRYblBhIjjI8uT2IGk=
+github.com/prometheus/procfs v0.0.2/go.mod h1:TjEm7ze935MbeOT/UhFTIMYKhuLP4wbCsTZCD3I8kEA=
+github.com/prometheus/procfs v0.1.3/go.mod h1:lV6e/gmhEcM9IjHGsFOCxxuZ+z1YqCvr4OA4YeYWdaU=
+github.com/prometheus/procfs v0.6.0/go.mod h1:cz+aTbrPOrUb4q7XlbU9ygM+/jj0fzG6c1xBZuNvfVA=
+github.com/prometheus/procfs v0.7.3 h1:4jVXhlkAyzOScmCkXBTOLRLTz8EeU+eyjrwB/EPq0VU=
+github.com/prometheus/procfs v0.7.3/go.mod h1:cz+aTbrPOrUb4q7XlbU9ygM+/jj0fzG6c1xBZuNvfVA=
+github.com/rogpeppe/go-internal v1.3.0/go.mod h1:M8bDsm7K2OlrFYOpmOWEs/qY81heoFRclV5y23lUDJ4=
+github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
+github.com/rogpeppe/go-internal v1.8.0 h1:FCbCCtXNOY3UtUuHUYaghJg4y7Fd14rXifAYUAtL9R8=
+github.com/rogpeppe/go-internal v1.8.0/go.mod h1:WmiCO8CzOY8rg0OYDC4/i/2WRWAB6poM+XZ2dLUbcbE=
+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/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
+github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
+github.com/sirupsen/logrus v1.6.0/go.mod h1:7uNnSEd1DgxDLC74fIahvMZmmYsHGZGEOFrfsX/uA88=
+github.com/stmcginnis/gofish v0.13.0 h1:qq6q3yNt9vw7ZuJxiw87hq9+BdPLsuRQBwl+XoZSz60=
+github.com/stmcginnis/gofish v0.13.0/go.mod h1:BLDSFTp8pDlf/xDbLZa+F7f7eW0E/CHCboggsu8CznI=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/objx v0.1.1/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
-github.com/stretchr/testify v1.5.1 h1:nOGnQDM7FYENwehXlg/kFVnos3rEvtKTjRvOWSzb6H4=
 github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
+github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.7.1 h1:5TQK59W5E3v0r2duFAb7P95B6hEeOyEnHRa8MjYSMTY=
+github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/tklauser/go-sysconf v0.3.10 h1:IJ1AZGZRWbY8T5Vfk04D9WOA5WSejdflXxP03OUqALw=
+github.com/tklauser/go-sysconf v0.3.10/go.mod h1:C8XykCvCb+Gn0oNCWPIlcb0RuglQTYaQ2hGm7jmxEFk=
+github.com/tklauser/numcpus v0.4.0 h1:E53Dm1HjH1/R2/aoCtXtPgzmElmn51aOkhCFSuZq//o=
+github.com/tklauser/numcpus v0.4.0/go.mod h1:1+UI3pD8NW14VMwdgJNJ1ESk2UnwhAnz5hMwiKKqXCQ=
+github.com/ugorji/go v1.1.7/go.mod h1:kZn38zHttfInRq0xu/PH0az30d+z6vm202qpg1oXVMw=
+github.com/ugorji/go v1.2.7/go.mod h1:nF9osbDWLy6bDVv/Rtoh6QgnvNDpmCalQV5urGCCS6M=
+github.com/ugorji/go/codec v1.1.7/go.mod h1:Ax+UKWsSmolVDwsd+7N3ZtXu+yMGCf907BLYF3GoBXY=
+github.com/ugorji/go/codec v1.2.7/go.mod h1:WGN1fab3R1fzQlVQTkfxVtIBhWDRqOviHU95kRgeqEY=
 github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
-github.com/valyala/fasttemplate v1.0.1/go.mod h1:UQGH1tvbgY+Nz5t2n7tXsz52dQxojPUpymEIMZ47gx8=
 github.com/valyala/fasttemplate v1.2.1/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
+github.com/yuin/goldmark v1.1.25/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
+github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
+github.com/yuin/goldmark v1.1.32/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
+github.com/yuin/goldmark v1.4.1/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
+go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
+go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
+go.opencensus.io v0.22.2/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
+go.opencensus.io v0.22.3/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
+go.opencensus.io v0.22.4/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
+golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
-golang.org/x/crypto v0.0.0-20200820211705-5c72a883971a/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
-golang.org/x/crypto v0.0.0-20201221181555-eec23a3978ad/go.mod h1:jdWPYTVW3xRLrWPugEBEK3UY2ZEsg3UU495nc5E+M+I=
 golang.org/x/crypto v0.0.0-20210314154223-e6e6c4f2bb5b/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
-golang.org/x/crypto v0.0.0-20220112180741-5e0467b6c7ce h1:Roh6XWxHFKrPgC/EQhVubSAGQ6Ozk6IdxHSzt1mR0EI=
-golang.org/x/crypto v0.0.0-20220112180741-5e0467b6c7ce/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
+golang.org/x/crypto v0.0.0-20210817164053-32db794688a5/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/crypto v0.0.0-20211215153901-e495a2d5b3d3/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
+golang.org/x/crypto v0.0.0-20220427172511-eb4f295cb31f/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
+golang.org/x/crypto v0.0.0-20220513210258-46612604a0f9/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
+golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d h1:sK3txAijHtOK88l68nt020reeT1ZdKLIYetKl95FzVY=
+golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
+golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
+golang.org/x/exp v0.0.0-20190306152737-a1d7652674e8/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
+golang.org/x/exp v0.0.0-20190510132918-efd6b22b2522/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8=
+golang.org/x/exp v0.0.0-20190829153037-c13cbed26979/go.mod h1:86+5VVa7VpoJ4kLfm080zCjGlMRFzhUhsZKEZO7MGek=
+golang.org/x/exp v0.0.0-20191030013958-a1ab85dbe136/go.mod h1:JXzH8nQsPlswgeRAPE3MuO9GYsAcnJvJ4vnMwN/5qkY=
+golang.org/x/exp v0.0.0-20191129062945-2f5052295587/go.mod h1:2RIsYlXP63K8oxa1u096TMicItID8zy7Y6sNkU49FU4=
+golang.org/x/exp v0.0.0-20191227195350-da58074b4299/go.mod h1:2RIsYlXP63K8oxa1u096TMicItID8zy7Y6sNkU49FU4=
+golang.org/x/exp v0.0.0-20200119233911-0405dc783f0a/go.mod h1:2RIsYlXP63K8oxa1u096TMicItID8zy7Y6sNkU49FU4=
+golang.org/x/exp v0.0.0-20200207192155-f17229e696bd/go.mod h1:J/WKrq2StrnmMY6+EHIKF9dgMWnmCNThgcyBT1FY9mM=
+golang.org/x/exp v0.0.0-20200224162631-6cc2880d07d6/go.mod h1:3jZMyOhIsHpP37uCMkUooju7aAi5cS1Q23tOzKc+0MU=
+golang.org/x/image v0.0.0-20190227222117-0694c2d4d067/go.mod h1:kZ7UVZpmo3dzQBMxlp+ypCbDeSB+sBbTgSJuh5dn5js=
+golang.org/x/image v0.0.0-20190802002840-cff245a6509b/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
+golang.org/x/lint v0.0.0-20181026193005-c67002cb31c3/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
+golang.org/x/lint v0.0.0-20190227174305-5b3e6a55c961/go.mod h1:wehouNa3lNwaWXcvxsM5YxQ5yQlVC4a0KAMCusXpPoU=
+golang.org/x/lint v0.0.0-20190301231843-5614ed5bae6f/go.mod h1:UVdnD1Gm6xHRNCYTkRU2/jEulfH38KcIWyp/GAMgvoE=
+golang.org/x/lint v0.0.0-20190313153728-d0100b6bd8b3/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
+golang.org/x/lint v0.0.0-20190409202823-959b441ac422/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
+golang.org/x/lint v0.0.0-20190909230951-414d861bb4ac/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
+golang.org/x/lint v0.0.0-20190930215403-16217165b5de/go.mod h1:6SW0HCj/g11FgYtHlgUYUwCkIfeOF89ocIRzGO/8vkc=
+golang.org/x/lint v0.0.0-20191125180803-fdd1cda4f05f/go.mod h1:5qLYkcX4OjUUV8bRuDixDT3tpyyb+LUpUlRWLxfhWrs=
+golang.org/x/lint v0.0.0-20200130185559-910be7a94367/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
+golang.org/x/lint v0.0.0-20200302205851-738671d3881b/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
+golang.org/x/mobile v0.0.0-20190312151609-d3739f865fa6/go.mod h1:z+o9i4GpDbdi3rU15maQ/Ox0txvL9dWGYEHz965HBQE=
+golang.org/x/mobile v0.0.0-20190719004257-d2bd2a29d028/go.mod h1:E/iHnbuqvinMTCcRqshq8CkpyQDoeVncDDYHnLhea+o=
+golang.org/x/mod v0.0.0-20190513183733-4bf6d317e70e/go.mod h1:mXi4GBBbnImb6dmsKGUJ2LatrhH/nqhxcFungHvyanc=
+golang.org/x/mod v0.1.0/go.mod h1:0QHyrYULN0/3qlju5TqG8bIK38QM8yzMo5ekMj3DlcY=
+golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
+golang.org/x/mod v0.1.1-0.20191107180719-034126e5016b/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
+golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
+golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
+golang.org/x/mod v0.6.0-dev.0.20220106191415-9b9b3d81d5e3/go.mod h1:3p9vT2HGsQu2K1YbXdKPJLVgG5VJdoTa1poYQBtP1AY=
+golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190108225652-1e06a53dbb7e/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190213061140-3a22650c66bd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
+golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190501004415-9ce7a6920f09/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190503192946-f4e77d36d62c/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
+golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks=
+golang.org/x/net v0.0.0-20190613194153-d28f0bde5980/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20190628185345-da137c7871d7/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20190724013045-ca1201d0de80/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20191209160850-c0dbc17a3553/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20200114155413-6afb5195e5aa/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20200202094626-16171245cfb2/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20200222125558-5a598a2470a0/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20200301022130-244492dfa37a/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20200324143707-d3edc9973b7e/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
+golang.org/x/net v0.0.0-20200501053045-e0ff5e5a1de5/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
+golang.org/x/net v0.0.0-20200506145744-7e3656a0809f/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
+golang.org/x/net v0.0.0-20200513185701-a91f0712d120/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
+golang.org/x/net v0.0.0-20200520182314-0ba52f642ac2/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
+golang.org/x/net v0.0.0-20200625001655-4c5254603344/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
+golang.org/x/net v0.0.0-20200707034311-ab3426394381/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
 golang.org/x/net v0.0.0-20200822124328-c89045814202/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA=
-golang.org/x/net v0.0.0-20210119194325-5f4716e94777/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
-golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2 h1:CIJ76btIcR3eFI5EgSo6k1qKw9KJexJuRLI9G7Hp5wE=
+golang.org/x/net v0.0.0-20210525063256-abc453219eb5/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/net v0.0.0-20211015210444-4f30a5c0130f/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/net v0.0.0-20220127200216-cd36cc0744dd/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk=
+golang.org/x/net v0.0.0-20220225172249-27dd8689420f/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk=
+golang.org/x/net v0.0.0-20220513224357-95641704303c/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk=
+golang.org/x/net v0.0.0-20220708220712-1185a9018129 h1:vucSRfWwTsoXro7P+3Cjlr6flUMtzCwzlvkxEQtHHB0=
+golang.org/x/net v0.0.0-20220708220712-1185a9018129/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
+golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
+golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
+golang.org/x/oauth2 v0.0.0-20191202225959-858c2ad4c8b6/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
+golang.org/x/oauth2 v0.0.0-20200107190931-bf48bf16ab8d/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw=
+golang.org/x/oauth2 v0.0.0-20210514164344-f6687ab2804c/go.mod h1:KelEdhl1UZF7XfJ4dDtk6s++YSgaE7mD/BuKKDLBl4A=
+golang.org/x/oauth2 v0.0.0-20220223155221-ee480838109b/go.mod h1:DAh4E804XQdzx2j+YRIaUnCqCV2RuMz24cGBJ5QYIrc=
+golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20181221193216-37e7f081c4d4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20190227155943-e225da77a7e6/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 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/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20200317015054-43a5402ce75a/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20200625203802-6e8e738ad208/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20201207232520-09787c993a3a/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
+golang.org/x/sys v0.0.0-20181116152217-5ac8a444bdc5/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 v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 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 v0.0.0-20190422165155-953cdadca894/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190502145724-3ef323f4f1fd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190507160741-ecd444e8653b/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190606165138-5da285871e9c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190624142023-c5567b49c5d0/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190726091711-fc99dfbffb4e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20191001151750-bb3f8db39f24/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20191204072324-ce4227a45e2e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20191228213918-04cbcbbfeed8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200106162015-b016eb3dc98e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200113162924-86b910548bc1/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200122134326-e047566fdf82/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200202164722-d101bd2416d5/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200212091648-12a6c2dcc1e4/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200223170610-d5e6a3e2c0ae/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200302150141-5c8b2ff67527/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 v0.0.0-20200331124033-c3d80250170d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200501052902-10377860bb8e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200511232937-7e40ca221e25/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200515095857-1151b9dac4a9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200523222454-059865788121/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200615200032-f1bc736245b1/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200625212154-ddb9806d33ae/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200803210538-64077c9b5642/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 v0.0.0-20210603081109-ebe580a85c40/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 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 v0.0.0-20210630005230-0f9fa26af87c/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20210806184541-e5e7981a1069/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20210927094055-39ccf1dd6fa6/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20211019181941-9d821ace8654/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20211103235746-7861aae1554b/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20211216021012-1d35b9e2eb4e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 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/sys v0.0.0-20220128215802-99c3d69c2c27/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220513210249-45d2b4557a2a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220712014510-0a85c31ab51e h1:NHvCuwuS43lGnYhten69ZWqi2QOj/CiDNcKbVqwVoew=
+golang.org/x/sys v0.0.0-20220712014510-0a85c31ab51e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
+golang.org/x/text v0.0.0-20170915032832-14c0d48ead0c/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.3.1-0.20180807135948-17ff2d5776d2/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
+golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 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/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/time v0.0.0-20181108054448-85acf8d2951c/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
+golang.org/x/time v0.0.0-20190308202827-9d24e82272b4/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
+golang.org/x/time v0.0.0-20191024005414-555d28b269f0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 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/time v0.0.0-20220411224347-583f2d630306 h1:+gHMid33q6pen7kv9xvT+JRinntgeXO2AeZVd0AWD3w=
+golang.org/x/time v0.0.0-20220411224347-583f2d630306/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190114222345-bf090417da8b/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
+golang.org/x/tools v0.0.0-20190226205152-f727befe758c/go.mod h1:9Yl7xja0Znq3iFh3HoIrodX9oNMXvdceNzlUR8zjMvY=
+golang.org/x/tools v0.0.0-20190311212946-11955173bddd/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+golang.org/x/tools v0.0.0-20190312151545-0bb0c0a6e846/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+golang.org/x/tools v0.0.0-20190312170243-e65039ee4138/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
+golang.org/x/tools v0.0.0-20190425150028-36563e24a262/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
+golang.org/x/tools v0.0.0-20190506145303-2d16b83fe98c/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
+golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
+golang.org/x/tools v0.0.0-20190606124116-d0a3d012864b/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
+golang.org/x/tools v0.0.0-20190621195816-6e04913cbbac/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
+golang.org/x/tools v0.0.0-20190628153133-6cdbf07be9d0/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
+golang.org/x/tools v0.0.0-20190816200558-6889da9d5479/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20190911174233-4f2ddba30aff/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191012152004-8de300cfc20a/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191113191852-77e3bb0ad9e7/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191115202509-3a792d9c32b2/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191125144606-a911d9008d1f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191130070609-6e064ea0cf2d/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191216173652-a0e659d51361/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20191227053925-7b8e75db28f4/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200117161641-43d50277825c/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200122220014-bf1340f18c4a/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200204074204-1cc6d1ef6c74/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200207183749-b753a1ba74fa/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200212150539-ea181f53ac56/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200224181240-023911ca70b2/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200227222343-706bc42d1f0d/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200304193943-95d2e580d8eb/go.mod h1:o4KQGtdN14AW+yjsvvwRTJJuXz8XRtIHtEnmAXLyFUw=
+golang.org/x/tools v0.0.0-20200312045724-11d5b4c81c7d/go.mod h1:o4KQGtdN14AW+yjsvvwRTJJuXz8XRtIHtEnmAXLyFUw=
+golang.org/x/tools v0.0.0-20200331025713-a30bf2db82d4/go.mod h1:Sl4aGygMT6LrqrWclx+PTx3U+LnKx/seiNR+3G19Ar8=
+golang.org/x/tools v0.0.0-20200501065659-ab2804fb9c9d/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
+golang.org/x/tools v0.0.0-20200512131952-2bc93b1c0c88/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
+golang.org/x/tools v0.0.0-20200515010526-7d3b6ebf133d/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
+golang.org/x/tools v0.0.0-20200618134242-20370b0cb4b2/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
+golang.org/x/tools v0.0.0-20200729194436-6467de6f59a7/go.mod h1:njjCfa9FT2d7l9Bc6FUM5FLjQPp3cFF28FI3qnDFljA=
+golang.org/x/tools v0.0.0-20200804011535-6c149bb5ef0d/go.mod h1:njjCfa9FT2d7l9Bc6FUM5FLjQPp3cFF28FI3qnDFljA=
+golang.org/x/tools v0.0.0-20200825202427-b303f430e36d/go.mod h1:njjCfa9FT2d7l9Bc6FUM5FLjQPp3cFF28FI3qnDFljA=
+golang.org/x/tools v0.1.10/go.mod h1:Uh6Zz+xoGYZom868N8YTex3t7RhtHDBrE8Gzo9bV56E=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20220411194840-2f41105eb62f h1:GGU+dLjvlC3qDwqYgL6UgRmHXhOOgns0bZu2Ty5mm6U=
+golang.org/x/xerrors v0.0.0-20220411194840-2f41105eb62f/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+google.golang.org/api v0.4.0/go.mod h1:8k5glujaEP+g9n7WNsDg8QP6cUVNI86fCNMcbazEtwE=
+google.golang.org/api v0.7.0/go.mod h1:WtwebWUNSVBH/HAw79HIFXZNqEvBhG+Ra+ax0hx3E3M=
+google.golang.org/api v0.8.0/go.mod h1:o4eAsZoiT+ibD93RtjEohWalFOjRDx6CVaqeizhEnKg=
+google.golang.org/api v0.9.0/go.mod h1:o4eAsZoiT+ibD93RtjEohWalFOjRDx6CVaqeizhEnKg=
+google.golang.org/api v0.13.0/go.mod h1:iLdEw5Ide6rF15KTC1Kkl0iskquN2gFfn9o9XIsbkAI=
+google.golang.org/api v0.14.0/go.mod h1:iLdEw5Ide6rF15KTC1Kkl0iskquN2gFfn9o9XIsbkAI=
+google.golang.org/api v0.15.0/go.mod h1:iLdEw5Ide6rF15KTC1Kkl0iskquN2gFfn9o9XIsbkAI=
+google.golang.org/api v0.17.0/go.mod h1:BwFmGc8tA3vsd7r/7kR8DY7iEEGSU04BFxCo5jP/sfE=
+google.golang.org/api v0.18.0/go.mod h1:BwFmGc8tA3vsd7r/7kR8DY7iEEGSU04BFxCo5jP/sfE=
+google.golang.org/api v0.19.0/go.mod h1:BwFmGc8tA3vsd7r/7kR8DY7iEEGSU04BFxCo5jP/sfE=
+google.golang.org/api v0.20.0/go.mod h1:BwFmGc8tA3vsd7r/7kR8DY7iEEGSU04BFxCo5jP/sfE=
+google.golang.org/api v0.22.0/go.mod h1:BwFmGc8tA3vsd7r/7kR8DY7iEEGSU04BFxCo5jP/sfE=
+google.golang.org/api v0.24.0/go.mod h1:lIXQywCXRcnZPGlsd8NbLnOjtAoL6em04bJ9+z0MncE=
+google.golang.org/api v0.28.0/go.mod h1:lIXQywCXRcnZPGlsd8NbLnOjtAoL6em04bJ9+z0MncE=
+google.golang.org/api v0.29.0/go.mod h1:Lcubydp8VUV7KeIHD9z2Bys/sm/vGKnG1UHuDBSrHWM=
+google.golang.org/api v0.30.0/go.mod h1:QGmEvQ87FHZNiUVJkT14jQNYJ4ZJjdRF23ZXz5138Fc=
+google.golang.org/appengine v1.1.0/go.mod h1:EbEs0AVv82hx2wNQdGPgUI5lhzA/G0D9YwlJXL52JkM=
+google.golang.org/appengine v1.4.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
+google.golang.org/appengine v1.5.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7/EB5XEv4=
+google.golang.org/appengine v1.6.1/go.mod h1:i06prIuMbXzDqacNJfV5OdTW448YApPu5ww/cMBSeb0=
+google.golang.org/appengine v1.6.5/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
+google.golang.org/appengine v1.6.6/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
+google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
+google.golang.org/genproto v0.0.0-20190307195333-5fe7a883aa19/go.mod h1:VzzqZJRnGkLBvHegQrXjBqPurQTc5/KpmUdxsrq26oE=
+google.golang.org/genproto v0.0.0-20190418145605-e7d98fc518a7/go.mod h1:VzzqZJRnGkLBvHegQrXjBqPurQTc5/KpmUdxsrq26oE=
+google.golang.org/genproto v0.0.0-20190425155659-357c62f0e4bb/go.mod h1:VzzqZJRnGkLBvHegQrXjBqPurQTc5/KpmUdxsrq26oE=
+google.golang.org/genproto v0.0.0-20190502173448-54afdca5d873/go.mod h1:VzzqZJRnGkLBvHegQrXjBqPurQTc5/KpmUdxsrq26oE=
+google.golang.org/genproto v0.0.0-20190801165951-fa694d86fc64/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
+google.golang.org/genproto v0.0.0-20190819201941-24fa4b261c55/go.mod h1:DMBHOl98Agz4BDEuKkezgsaosCRResVns1a3J2ZsMNc=
+google.golang.org/genproto v0.0.0-20190911173649-1774047e7e51/go.mod h1:IbNlFCBrqXvoKpeg0TB2l7cyZUmoaFKYIwrEpbDKLA8=
+google.golang.org/genproto v0.0.0-20191108220845-16a3f7862a1a/go.mod h1:n3cpQtvxv34hfy77yVDNjmbRyujviMdxYliBSkLhpCc=
+google.golang.org/genproto v0.0.0-20191115194625-c23dd37a84c9/go.mod h1:n3cpQtvxv34hfy77yVDNjmbRyujviMdxYliBSkLhpCc=
+google.golang.org/genproto v0.0.0-20191216164720-4f79533eabd1/go.mod h1:n3cpQtvxv34hfy77yVDNjmbRyujviMdxYliBSkLhpCc=
+google.golang.org/genproto v0.0.0-20191230161307-f3c370f40bfb/go.mod h1:n3cpQtvxv34hfy77yVDNjmbRyujviMdxYliBSkLhpCc=
+google.golang.org/genproto v0.0.0-20200115191322-ca5a22157cba/go.mod h1:n3cpQtvxv34hfy77yVDNjmbRyujviMdxYliBSkLhpCc=
+google.golang.org/genproto v0.0.0-20200122232147-0452cf42e150/go.mod h1:n3cpQtvxv34hfy77yVDNjmbRyujviMdxYliBSkLhpCc=
+google.golang.org/genproto v0.0.0-20200204135345-fa8e72b47b90/go.mod h1:GmwEX6Z4W5gMy59cAlVYjN9JhxgbQH6Gn+gFDQe2lzA=
+google.golang.org/genproto v0.0.0-20200212174721-66ed5ce911ce/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
+google.golang.org/genproto v0.0.0-20200224152610-e50cd9704f63/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
+google.golang.org/genproto v0.0.0-20200228133532-8c2c7df3a383/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
+google.golang.org/genproto v0.0.0-20200305110556-506484158171/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
+google.golang.org/genproto v0.0.0-20200312145019-da6875a35672/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
+google.golang.org/genproto v0.0.0-20200331122359-1ee6d9798940/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
+google.golang.org/genproto v0.0.0-20200430143042-b979b6f78d84/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
+google.golang.org/genproto v0.0.0-20200511104702-f5ebc3bea380/go.mod h1:55QSHmfGQM9UVYDPBsyGGes0y52j32PQ3BqQfXhyH3c=
+google.golang.org/genproto v0.0.0-20200515170657-fc4c6c6a6587/go.mod h1:YsZOwe1myG/8QRHRsmBRE1LrgQY60beZKjly0O1fX9U=
+google.golang.org/genproto v0.0.0-20200526211855-cb27e3aa2013/go.mod h1:NbSheEEYHJ7i3ixzK3sjbqSGDJWnxyFXZblF3eUsNvo=
+google.golang.org/genproto v0.0.0-20200618031413-b414f8b61790/go.mod h1:jDfRM7FcilCzHH/e9qn6dsT145K34l5v+OpcnNgKAAA=
+google.golang.org/genproto v0.0.0-20200729003335-053ba62fc06f/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
+google.golang.org/genproto v0.0.0-20200804131852-c06518451d9c/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
+google.golang.org/genproto v0.0.0-20200825200019-8632dd797987/go.mod h1:FWY/as6DDZQgahTzZj3fqbO1CbirC29ZNUFHwi0/+no=
+google.golang.org/grpc v1.19.0/go.mod h1:mqu4LbDTu4XGKhr4mRzUsmM4RtVoemTSY81AxZiDr8c=
+google.golang.org/grpc v1.20.1/go.mod h1:10oTOabMzJvdu6/UiuZezV6QK5dSlG84ov/aaiqXj38=
+google.golang.org/grpc v1.21.1/go.mod h1:oYelfM1adQP15Ek0mdvEgi9Df8B9CZIaU1084ijfRaM=
+google.golang.org/grpc v1.23.0/go.mod h1:Y5yQAOtifL1yxbo5wqy6BxZv8vAUGQwXBOALyacEbxg=
+google.golang.org/grpc v1.25.1/go.mod h1:c3i+UQWmh7LiEpx4sFZnkU36qjEYZ0imhYfXVyQciAY=
+google.golang.org/grpc v1.26.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
+google.golang.org/grpc v1.27.0/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
+google.golang.org/grpc v1.27.1/go.mod h1:qbnxyOmOxrQa7FizSgH+ReBfzJrCY1pSN7KXBS8abTk=
+google.golang.org/grpc v1.28.0/go.mod h1:rpkK4SK4GF4Ach/+MFLZUBavHOvF2JJB5uozKKal+60=
+google.golang.org/grpc v1.29.1/go.mod h1:itym6AZVZYACWQqET3MqgPpjcuV5QH3BxFS3IjizoKk=
+google.golang.org/grpc v1.30.0/go.mod h1:N36X2cJ7JwdamYAgDz+s+rVMFjt3numwzf/HckM8pak=
+google.golang.org/grpc v1.31.0/go.mod h1:N36X2cJ7JwdamYAgDz+s+rVMFjt3numwzf/HckM8pak=
 google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
 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 v1.22.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
 google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.23.1-0.20200526195155-81db48ad09cc/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.24.0/go.mod h1:r/3tXBNzIEhYS9I1OUVjXDlt8tc493IdKGjtUeSXeh4=
+google.golang.org/protobuf v1.25.0/go.mod h1:9JNX74DMeImyA3h4bdi1ymwjUzf21/xIlbajtzgsN7c=
 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=
+google.golang.org/protobuf v1.28.0 h1:w43yiav+6bVFTBQFZX0r7ipe9JQ1QsbMgHwbBziscLw=
+google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
-gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127 h1:qIbj1fsPNlZgppZ+VLlY7N33q108Sa+fhmuc+sWQYwY=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20190902080502-41f04d3bba15/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
+gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
+gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
+gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
-gopkg.in/yaml.v2 v2.3.0 h1:clyUAQHOM3G0M3f5vQj7LuJrETvjVot3Z5el9nffUtU=
+gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.2.5/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
+gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b h1:h8qDotaEPuJATrMmW04NCwg7v22aHH28wwpauUhK9Oo=
+gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
+honnef.co/go/tools v0.0.0-20190106161140-3f1c8253044a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
+honnef.co/go/tools v0.0.0-20190418001031-e561f6794a2a/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
+honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
+honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt0JzvZhAg=
+honnef.co/go/tools v0.0.1-2020.1.3/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
+honnef.co/go/tools v0.0.1-2020.1.4/go.mod h1:X/FiERA/W4tHapMX5mGpAtMSVEeEUOyHaw9vFzvIQ3k=
+rsc.io/binaryregexp v0.2.0/go.mod h1:qTv7/COck+e2FymRvadv62gMdZztPaShugOCi3I+8D8=
+rsc.io/quote/v3 v3.1.0/go.mod h1:yEA65RcK8LyAZtP9Kv3t0HmxON59tX3rD+tICJqUlj0=
+rsc.io/sampler v1.3.0/go.mod h1:T1hPZKmBbMNahiBKFy5HrXp6adAjACjK9JXDnKaTXpA=

internal/ccMetric/README.md

@@ -1,32 +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            // 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/metricAggregator/metricAggregator.go

@@ -9,10 +9,10 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 
 	"github.com/PaesslerAG/gval"
 )

internal/metricAggregator/metricAggregatorFunctions.go

@@ -8,8 +8,8 @@ import (
 	"sort"
 	"strings"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 )
 
 /*
@@ -246,7 +246,7 @@ func matchfunc(args ...interface{}) (interface{}, error) {
 func getCpuCoreFunc(args ...interface{}) (interface{}, error) {
 	switch cpuid := args[0].(type) {
 	case int:
-		return topo.GetCpuCore(cpuid), nil
+		return topo.GetHwthreadCore(cpuid), nil
 	}
 	return -1, errors.New("function 'getCpuCore' accepts only an 'int' cpuid")
 }
@@ -255,7 +255,7 @@ func getCpuCoreFunc(args ...interface{}) (interface{}, error) {
 func getCpuSocketFunc(args ...interface{}) (interface{}, error) {
 	switch cpuid := args[0].(type) {
 	case int:
-		return topo.GetCpuSocket(cpuid), nil
+		return topo.GetHwthreadSocket(cpuid), nil
 	}
 	return -1, errors.New("function 'getCpuCore' accepts only an 'int' cpuid")
 }
@@ -264,7 +264,7 @@ func getCpuSocketFunc(args ...interface{}) (interface{}, error) {
 func getCpuNumaDomainFunc(args ...interface{}) (interface{}, error) {
 	switch cpuid := args[0].(type) {
 	case int:
-		return topo.GetCpuNumaDomain(cpuid), nil
+		return topo.GetHwthreadNumaDomain(cpuid), nil
 	}
 	return -1, errors.New("function 'getCpuNuma' accepts only an 'int' cpuid")
 }
@@ -273,7 +273,7 @@ func getCpuNumaDomainFunc(args ...interface{}) (interface{}, error) {
 func getCpuDieFunc(args ...interface{}) (interface{}, error) {
 	switch cpuid := args[0].(type) {
 	case int:
-		return topo.GetCpuDie(cpuid), nil
+		return topo.GetHwthreadDie(cpuid), nil
 	}
 	return -1, errors.New("function 'getCpuDie' accepts only an 'int' cpuid")
 }
@@ -336,7 +336,7 @@ func getCpuListOfDieFunc(args ...interface{}) (interface{}, error) {
 
 // wrapper function to get a list of all cpuids of the node
 func getCpuListOfNode(args ...interface{}) (interface{}, error) {
-	return topo.CpuList(), nil
+	return topo.HwthreadList(), nil
 }
 
 // helper function to get the cpuid list for a CCMetric type tag set (type and type-id)
@@ -348,14 +348,14 @@ func getCpuListOfType(args ...interface{}) (interface{}, error) {
 	case string:
 		switch typ {
 		case "node":
-			return topo.CpuList(), nil
+			return topo.HwthreadList(), nil
 		case "socket":
 			return getCpuListOfSocketFunc(args[1])
 		case "numadomain":
 			return getCpuListOfNumaDomainFunc(args[1])
 		case "core":
 			return getCpuListOfCoreFunc(args[1])
-		case "cpu":
+		case "hwthread":
 			var cpu int
 
 			switch id := args[1].(type) {

internal/metricRouter/README.md

@@ -8,6 +8,8 @@ The CCMetric router sits in between the collectors and the sinks and can be used
 {
     "num_cache_intervals" : 1,
     "interval_timestamp" : true,
+    "hostname_tag" : "hostname",
+    "max_forward" : 50,
     "add_tags" : [
         {
             "key" : "cluster",
@@ -50,11 +52,30 @@ 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"
     }
 }
 ```
 
 There are three main options `add_tags`, `delete_tags` and `interval_timestamp`. `add_tags` and `delete_tags` are lists consisting of dicts with `key`, `value` and `if`. The `value` can be omitted in the `delete_tags` part as it only uses the `key` for removal. The `interval_timestamp` setting means that a unique timestamp is applied to all metrics traversing the router during an interval.
+
+# Processing order in the router
+
+- Add the `hostname_tag` tag (if sent by collectors or cache)
+- If `interval_timestamp == true`, change time of metrics
+- Check if metric should be dropped (`drop_metrics` and `drop_metrics_if`)
+- Add tags from `add_tags`
+- Delete tags from `del_tags`
+- Rename metric based on `rename_metrics` and store old name as `oldname` in meta information
+- Add tags from `add_tags` (if you used the new name in the `if` condition)
+- Delete tags from `del_tags` (if you used the new name in the `if` condition)
+- Send to sinks
+- Move to cache (if `num_cache_intervals > 0`)
+
 # The `interval_timestamp` option
 
 The collectors' `Read()` functions are not called simultaneously and therefore the metrics gathered in an interval can have different timestamps. If you want to avoid that and have a common timestamp (the beginning of the interval), set this option to `true` and the MetricRouter sets the time.
@@ -65,6 +86,14 @@ If the MetricRouter should buffer metrics of intervals in a MetricCache, this op
 
 A `num_cache_intervals > 0` is required to use the `interval_aggregates` option.
 
+# The `hostname_tag` option
+
+By default, the router tags metrics with the hostname for all locally created metrics. The default tag name is `hostname`, but it can be changed if your organization wants anything else
+
+# The `max_forward` option
+
+Every time the router receives a metric through any of the channels, it tries to directly read up to `max_forward` metrics from the same channel. This was done as the router thread would go to sleep and wake up with every arriving metric. The default are `50` metrics at once and `max_forward` needs to greater than `1`.
+
 # The `rename_metrics` option
 
 In the ClusterCockpit world we specified a set of standard metrics. Since some collectors determine the metric names based on files, execuables and libraries, they might change from system to system (or installation to installtion, OS to OS, ...). In order to get the common names, you can rename incoming metrics before sending them to the sink. If the metric name matches the `oldname`, it is changed to `newname`
@@ -168,6 +197,14 @@ 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
 
@@ -215,3 +252,22 @@ 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/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
-	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 metricCachePeriod struct {

internal/metricRouter/metricRouter.go

@@ -7,11 +7,12 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
-	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
@@ -25,6 +26,7 @@ type metricRouterTagConfig struct {
 
 // Metric router configuration
 type metricRouterConfig struct {
+	HostnameTagName   string                               `json:"hostname_tag"`        // Key name used when adding the hostname to a metric (default 'hostname')
 	AddTags           []metricRouterTagConfig              `json:"add_tags"`            // List of tags that are added when the condition is met
 	DelTags           []metricRouterTagConfig              `json:"delete_tags"`         // List of tags that are removed when the condition is met
 	IntervalAgg       []agg.MetricAggregatorIntervalConfig `json:"interval_aggregates"` // List of aggregation function processed at the end of an interval
@@ -33,6 +35,9 @@ type metricRouterConfig struct {
 	RenameMetrics     map[string]string                    `json:"rename_metrics"`      // Map to rename metric name from key to value
 	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
 }
 
@@ -46,7 +51,6 @@ type metricRouter struct {
 	done        chan bool           // channel to finish / stop metric router
 	wg          *sync.WaitGroup     // wait group for all goroutines in cc-metric-collector
 	timestamp   time.Time           // timestamp periodically updated by ticker each interval
-	timerdone   chan bool           // channel to finish / stop timestamp updater
 	ticker      mct.MultiChanTicker // periodically ticking once each interval
 	config      metricRouterConfig  // json encoded config for metric router
 	cache       MetricCache         // pointer to MetricCache
@@ -76,7 +80,8 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 	r.cache_input = make(chan lp.CCMetric)
 	r.wg = wg
 	r.ticker = ticker
-	r.maxForward = ROUTER_MAX_FORWARD
+	r.config.MaxForward = ROUTER_MAX_FORWARD
+	r.config.HostnameTagName = "hostname"
 
 	// Set hostname
 	hostname, err := os.Hostname()
@@ -100,6 +105,10 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 		cclog.ComponentError("MetricRouter", err.Error())
 		return err
 	}
+	r.maxForward = 1
+	if r.config.MaxForward > r.maxForward {
+		r.maxForward = r.config.MaxForward
+	}
 	if r.config.NumCacheIntervals > 0 {
 		r.cache, err = NewCache(r.cache_input, r.ticker, &r.cachewg, r.config.NumCacheIntervals)
 		if err != nil {
@@ -117,29 +126,6 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 	return nil
 }
 
-// StartTimer starts a timer which updates timestamp periodically
-func (r *metricRouter) StartTimer() {
-	m := make(chan time.Time)
-	r.ticker.AddChannel(m)
-	r.timerdone = make(chan bool)
-
-	r.wg.Add(1)
-	go func() {
-		defer r.wg.Done()
-		for {
-			select {
-			case <-r.timerdone:
-				close(r.timerdone)
-				cclog.ComponentDebug("MetricRouter", "TIMER DONE")
-				return
-			case t := <-m:
-				r.timestamp = t
-			}
-		}
-	}()
-	cclog.ComponentDebug("MetricRouter", "TIMER START")
-}
-
 func getParamMap(point lp.CCMetric) map[string]interface{} {
 	params := make(map[string]interface{})
 	params["metric"] = point
@@ -224,12 +210,45 @@ 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
 	r.timestamp = time.Now()
+	timeChan := make(chan time.Time)
 	if r.config.IntervalStamp {
-		r.StartTimer()
+		r.ticker.AddChannel(timeChan)
 	}
 
 	// Router manager is done
@@ -244,11 +263,15 @@ func (r *metricRouter) Start() {
 		cclog.ComponentDebug("MetricRouter", "FORWARD", point)
 		r.DoAddTags(point)
 		r.DoDelTags(point)
-		if new, ok := r.config.RenameMetrics[point.Name()]; ok {
+		name := point.Name()
+		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.DoDelTags(point)
+
+		r.prepareUnit(point)
 
 		for _, o := range r.outputs {
 			o <- point
@@ -258,7 +281,9 @@ func (r *metricRouter) Start() {
 	// Foward message received from collector channel
 	coll_forward := func(p lp.CCMetric) {
 		// receive from metric collector
-		p.AddTag("hostname", r.hostname)
+		if !p.HasTag(r.config.HostnameTagName) {
+			p.AddTag(r.config.HostnameTagName, r.hostname)
+		}
 		if r.config.IntervalStamp {
 			p.SetTime(r.timestamp)
 		}
@@ -287,7 +312,9 @@ func (r *metricRouter) Start() {
 	cache_forward := func(p lp.CCMetric) {
 		// receive from metric collector
 		if !r.dropMetric(p) {
-			p.AddTag("hostname", r.hostname)
+			if !p.HasTag(r.config.HostnameTagName) {
+				p.AddTag(r.config.HostnameTagName, r.hostname)
+			}
 			forward(p)
 		}
 	}
@@ -307,21 +334,25 @@ func (r *metricRouter) Start() {
 				done()
 				return
 
+			case timestamp := <-timeChan:
+				r.timestamp = timestamp
+				cclog.ComponentDebug("MetricRouter", "Update timestamp", r.timestamp.UnixNano())
+
 			case p := <-r.coll_input:
 				coll_forward(p)
-				for i := 0; len(r.coll_input) > 0 && i < r.maxForward; i++ {
+				for i := 0; len(r.coll_input) > 0 && i < (r.maxForward-1); i++ {
 					coll_forward(<-r.coll_input)
 				}
 
 			case p := <-r.recv_input:
 				recv_forward(p)
-				for i := 0; len(r.recv_input) > 0 && i < r.maxForward; i++ {
+				for i := 0; len(r.recv_input) > 0 && i < (r.maxForward-1); i++ {
 					recv_forward(<-r.recv_input)
 				}
 
 			case p := <-r.cache_input:
 				cache_forward(p)
-				for i := 0; len(r.cache_input) > 0 && i < r.maxForward; i++ {
+				for i := 0; len(r.cache_input) > 0 && i < (r.maxForward-1); i++ {
 					cache_forward(<-r.cache_input)
 				}
 			}
@@ -352,14 +383,6 @@ func (r *metricRouter) Close() {
 	// wait for close of channel r.done
 	<-r.done
 
-	// stop timer
-	if r.config.IntervalStamp {
-		cclog.ComponentDebug("MetricRouter", "TIMER CLOSE")
-		r.timerdone <- true
-		// wait for close of channel r.timerdone
-		<-r.timerdone
-	}
-
 	// stop metric cache
 	if r.config.NumCacheIntervals > 0 {
 		cclog.ComponentDebug("MetricRouter", "CACHE CLOSE")

pkg/ccMetric/README.md

@@ -0,0 +1,57 @@
+# 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/ccMetric/ccMetric.go

@@ -24,8 +24,8 @@ type ccMetric struct {
 
 // ccMetric access functions
 type CCMetric interface {
-	ToPoint(metaAsTags bool) *write.Point  // Generate influxDB point for data type ccMetric
-	ToLineProtocol(metaAsTags bool) string // Generate influxDB line protocol for data type ccMetric
+	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
 
 	Name() string        // Get metric name
 	SetName(name string) // Set metric name
@@ -50,6 +50,7 @@ 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
@@ -61,25 +62,18 @@ func (m *ccMetric) String() string {
 }
 
 // ToLineProtocol generates influxDB line protocol for data type ccMetric
-func (m *ccMetric) ToPoint(metaAsTags bool) (p *write.Point) {
-
-	if !metaAsTags {
-		p = influxdb2.NewPoint(m.name, m.tags, m.fields, m.tm)
-	} else {
-		tags := make(map[string]string, len(m.tags)+len(m.meta))
-		for key, value := range m.tags {
-			tags[key] = value
+func (m *ccMetric) ToPoint(metaAsTags map[string]bool) (p *write.Point) {
+	p = influxdb2.NewPoint(m.name, m.tags, m.fields, m.tm)
+	for key, ok1 := range metaAsTags {
+		if val, ok2 := m.GetMeta(key); ok1 && ok2 {
+			p.AddTag(key, val)
 		}
-		for key, value := range m.meta {
-			tags[key] = value
-		}
-		p = influxdb2.NewPoint(m.name, tags, m.fields, m.tm)
 	}
-	return
+	return p
 }
 
 // ToLineProtocol generates influxDB line protocol for data type ccMetric
-func (m *ccMetric) ToLineProtocol(metaAsTags bool) string {
+func (m *ccMetric) ToLineProtocol(metaAsTags map[string]bool) string {
 
 	return write.PointToLineProtocol(
 		m.ToPoint(metaAsTags),
@@ -224,23 +218,26 @@ func New(
 }
 
 // FromMetric copies the metric <other>
-func FromMetric(other ccMetric) CCMetric {
+func FromMetric(other CCMetric) CCMetric {
+	otags := other.Tags()
+	ometa := other.Meta()
+	ofields := other.Fields()
 	m := &ccMetric{
 		name:   other.Name(),
-		tags:   make(map[string]string, len(other.tags)),
-		meta:   make(map[string]string, len(other.meta)),
-		fields: make(map[string]interface{}, len(other.fields)),
+		tags:   make(map[string]string, len(otags)),
+		meta:   make(map[string]string, len(ometa)),
+		fields: make(map[string]interface{}, len(ofields)),
 		tm:     other.Time(),
 	}
 
 	// deep copy tags, meta data tags and fields
-	for key, value := range other.tags {
+	for key, value := range otags {
 		m.tags[key] = value
 	}
-	for key, value := range other.meta {
+	for key, value := range ometa {
 		m.meta[key] = value
 	}
-	for key, value := range other.fields {
+	for key, value := range ofields {
 		m.fields[key] = value
 	}
 	return m

pkg/ccTopology/ccTopology.go

@@ -10,7 +10,7 @@ import (
 	"strconv"
 	"strings"
 
-	cclogger "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclogger "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 )
 
 const SYSFS_NUMABASE = `/sys/devices/system/node`
@@ -29,6 +29,7 @@ func intArrayContains(array []int, str int) (int, bool) {
 	return -1, false
 }
 
+// Used internally for sysfs file reads
 func fileToInt(path string) int {
 	buffer, err := ioutil.ReadFile(path)
 	if err != nil {
@@ -47,6 +48,7 @@ func fileToInt(path string) int {
 	return int(id)
 }
 
+// Get list of CPU socket IDs
 func SocketList() []int {
 	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
 	if err != nil {
@@ -54,7 +56,7 @@ func SocketList() []int {
 		return nil
 	}
 	ll := strings.Split(string(buffer), "\n")
-	var packs []int
+	packs := make([]int, 0)
 	for _, line := range ll {
 		if strings.HasPrefix(line, "physical id") {
 			lv := strings.Fields(line)
@@ -72,7 +74,8 @@ func SocketList() []int {
 	return packs
 }
 
-func CpuList() []int {
+// Get list of hardware thread IDs in the order of listing in /proc/cpuinfo
+func HwthreadList() []int {
 	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
 	if err != nil {
 		log.Print(err)
@@ -97,6 +100,13 @@ func CpuList() []int {
 	return cpulist
 }
 
+// Get list of hardware thread IDs in the order of listing in /proc/cpuinfo
+// Deprecated! Use HwthreadList()
+func CpuList() []int {
+	return HwthreadList()
+}
+
+// Get list of CPU core IDs in the order of listing in /proc/cpuinfo
 func CoreList() []int {
 	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
 	if err != nil {
@@ -122,6 +132,7 @@ func CoreList() []int {
 	return corelist
 }
 
+// Get list of NUMA node IDs
 func NumaNodeList() []int {
 	numaList := make([]int, 0)
 	globPath := filepath.Join(string(SYSFS_NUMABASE), "node*")
@@ -156,8 +167,9 @@ func NumaNodeList() []int {
 	return numaList
 }
 
+// Get list of CPU die IDs
 func DieList() []int {
-	cpulist := CpuList()
+	cpulist := HwthreadList()
 	dielist := make([]int, 0)
 	for _, c := range cpulist {
 		diepath := filepath.Join(string(SYSFS_CPUBASE), fmt.Sprintf("cpu%d", c), "topology/die_id")
@@ -169,10 +181,33 @@ func DieList() []int {
 			}
 		}
 	}
-	return dielist
+	if len(dielist) > 0 {
+		return dielist
+	}
+	return SocketList()
 }
 
-type CpuEntry struct {
+// Get 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{}
+}
+
+// Structure holding all information about a hardware thread
+type HwthreadEntry struct {
 	Cpuid      int
 	SMT        int
 	Core       int
@@ -181,25 +216,25 @@ type CpuEntry struct {
 	Die        int
 }
 
-func CpuData() []CpuEntry {
+func CpuData() []HwthreadEntry {
 
-	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)
-	}
+	// 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))
 	}
@@ -257,11 +292,11 @@ func CpuData() []CpuEntry {
 		return 0
 	}
 
-	clist := make([]CpuEntry, 0)
-	for _, c := range CpuList() {
-		clist = append(clist, CpuEntry{Cpuid: c})
+	clist := make([]HwthreadEntry, 0)
+	for _, c := range HwthreadList() {
+		clist = append(clist, HwthreadEntry{Cpuid: c})
 	}
-	for _, centry := range clist {
+	for i, centry := range clist {
 		centry.Socket = -1
 		centry.Numadomain = -1
 		centry.Die = -1
@@ -289,10 +324,13 @@ func CpuData() []CpuEntry {
 		// Lookup NUMA domain id
 		centry.Numadomain = getNumaDomain(base)
 
+		// Update values in output list
+		clist[i] = centry
 	}
 	return clist
 }
 
+// Structure holding basic information about a CPU
 type CpuInformation struct {
 	NumHWthreads   int
 	SMTWidth       int
@@ -302,6 +340,7 @@ type CpuInformation struct {
 	NumNumaDomains int
 }
 
+// Get basic information about the CPU
 func CpuInfo() CpuInformation {
 	var c CpuInformation
 
@@ -337,7 +376,8 @@ func CpuInfo() CpuInformation {
 	return c
 }
 
-func GetCpuSocket(cpuid int) int {
+// Get the CPU socket ID for a given hardware thread ID
+func GetHwthreadSocket(cpuid int) int {
 	cdata := CpuData()
 	for _, d := range cdata {
 		if d.Cpuid == cpuid {
@@ -347,7 +387,8 @@ func GetCpuSocket(cpuid int) int {
 	return -1
 }
 
-func GetCpuNumaDomain(cpuid int) int {
+// Get the NUMA node ID for a given hardware thread ID
+func GetHwthreadNumaDomain(cpuid int) int {
 	cdata := CpuData()
 	for _, d := range cdata {
 		if d.Cpuid == cpuid {
@@ -357,7 +398,8 @@ func GetCpuNumaDomain(cpuid int) int {
 	return -1
 }
 
-func GetCpuDie(cpuid int) int {
+// Get the CPU die ID for a given hardware thread ID
+func GetHwthreadDie(cpuid int) int {
 	cdata := CpuData()
 	for _, d := range cdata {
 		if d.Cpuid == cpuid {
@@ -367,7 +409,8 @@ func GetCpuDie(cpuid int) int {
 	return -1
 }
 
-func GetCpuCore(cpuid int) int {
+// Get the CPU core ID for a given hardware thread ID
+func GetHwthreadCore(cpuid int) int {
 	cdata := CpuData()
 	for _, d := range cdata {
 		if d.Cpuid == cpuid {
@@ -377,7 +420,8 @@ func GetCpuCore(cpuid int) int {
 	return -1
 }
 
-func GetSocketCpus(socket int) []int {
+// Get the all hardware thread ID associated with a CPU socket
+func GetSocketHwthreads(socket int) []int {
 	all := CpuData()
 	cpulist := make([]int, 0)
 	for _, d := range all {
@@ -388,7 +432,8 @@ func GetSocketCpus(socket int) []int {
 	return cpulist
 }
 
-func GetNumaDomainCpus(domain int) []int {
+// Get the all hardware thread ID associated with a NUMA node
+func GetNumaDomainHwthreads(domain int) []int {
 	all := CpuData()
 	cpulist := make([]int, 0)
 	for _, d := range all {
@@ -399,7 +444,8 @@ func GetNumaDomainCpus(domain int) []int {
 	return cpulist
 }
 
-func GetDieCpus(die int) []int {
+// Get the all hardware thread ID associated with a CPU die
+func GetDieHwthreads(die int) []int {
 	all := CpuData()
 	cpulist := make([]int, 0)
 	for _, d := range all {
@@ -410,7 +456,8 @@ func GetDieCpus(die int) []int {
 	return cpulist
 }
 
-func GetCoreCpus(core int) []int {
+// Get the all hardware thread ID associated with a CPU core
+func GetCoreHwthreads(core int) []int {
 	all := CpuData()
 	cpulist := make([]int, 0)
 	for _, d := range all {

pkg/multiChanTicker/multiChanTicker.go

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

receivers.json

@@ -4,5 +4,22 @@
         "address": "nats://my-url",
         "port" : "4222",
         "database": "testcluster"
+    },
+    "redfish_recv": {
+        "type": "redfish",
+        "client_config": [
+            {
+                "hostname": "my-host-1",
+                "username": "username-1",
+                "password": "password-1",
+                "endpoint": "https://my-endpoint-1"
+            },
+            {
+                "hostname": "my-host-2",
+                "username": "username-2",
+                "password": "password-2",
+                "endpoint": "https://my-endpoint-2"
+            }
+        ]
     }
 }

receivers/README.md

@@ -21,6 +21,7 @@ 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
 
 # Contributing own receivers
 A receiver contains a few functions and is derived from the type `Receiver` (in `metricReceiver.go`):

receivers/httpReceiver.go

@@ -0,0 +1,118 @@
+package receivers
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+	"sync"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	"github.com/gorilla/mux"
+	influx "github.com/influxdata/line-protocol"
+)
+
+const HTTP_RECEIVER_PORT = "8080"
+
+type HttpReceiverConfig struct {
+	Type string `json:"type"`
+	Addr string `json:"address"`
+	Port string `json:"port"`
+	Path string `json:"path"`
+}
+
+type HttpReceiver struct {
+	receiver
+	handler *influx.MetricHandler
+	parser  *influx.Parser
+	meta    map[string]string
+	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)
+	r.config.Port = HTTP_RECEIVER_PORT
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &r.config)
+		if err != nil {
+			cclog.ComponentError(r.name, "Error reading config:", err.Error())
+			return err
+		}
+	}
+	if len(r.config.Port) == 0 {
+		return errors.New("not all configuration variables set required by HttpReceiver")
+	}
+	r.meta = map[string]string{"source": r.name}
+	p := r.config.Path
+	if !strings.HasPrefix(p, "/") {
+		p = "/" + p
+	}
+	uri := fmt.Sprintf("%s:%s%s", r.config.Addr, r.config.Port, p)
+	cclog.ComponentDebug(r.name, "INIT", uri)
+	r.handler = influx.NewMetricHandler()
+	r.parser = influx.NewParser(r.handler)
+	r.parser.SetTimeFunc(DefaultTime)
+
+	r.router = mux.NewRouter()
+	r.router.Path(p).HandlerFunc(r.ServerHttp)
+	r.server = &http.Server{Addr: uri, Handler: r.router}
+	return nil
+}
+
+func (r *HttpReceiver) Start() {
+	cclog.ComponentDebug(r.name, "START")
+	r.wg.Add(1)
+	go func() {
+		err := r.server.ListenAndServe()
+		if err != nil && err.Error() != "http: Server closed" {
+			cclog.ComponentError(r.name, err.Error())
+		}
+		r.wg.Done()
+	}()
+}
+
+func (r *HttpReceiver) ServerHttp(w http.ResponseWriter, req *http.Request) {
+	if req.Method != http.MethodPost {
+		http.Error(w, "Method Not Allowed", http.StatusMethodNotAllowed)
+		return
+	}
+
+	body, err := io.ReadAll(req.Body)
+	if err != nil {
+		http.Error(w, err.Error(), http.StatusInternalServerError)
+		return
+	}
+	metrics, err := r.parser.Parse(body)
+	if err != nil {
+		http.Error(w, err.Error(), http.StatusBadRequest)
+	}
+
+	for _, m := range metrics {
+		y := lp.FromInfluxMetric(m)
+		for k, v := range r.meta {
+			y.AddMeta(k, v)
+		}
+		if r.sink != nil {
+			r.sink <- y
+		}
+	}
+
+	w.WriteHeader(http.StatusOK)
+}
+
+func (r *HttpReceiver) Close() {
+	r.server.Shutdown(context.Background())
+}
+
+func NewHttpReceiver(name string, config json.RawMessage) (Receiver, error) {
+	r := new(HttpReceiver)
+	err := r.Init(name, config)
+	return r, err
+}

receivers/httpReceiver.md

@@ -0,0 +1,23 @@
+## `http` receiver
+
+The `http` receiver can be used receive metrics through HTTP POST requests.
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "http",
+    "address" : "",
+    "port" : "8080",
+    "path" : "/write"
+  }
+}
+```
+
+- `type`: makes the receiver a `http` receiver
+- `address`: Listen address
+- `port`: Listen port
+- `path`: URL path for the write endpoint
+
+The HTTP endpoint listens to `http://<address>:<port>/<path>`

receivers/metricReceiver.go

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

receivers/natsReceiver.go

@@ -6,8 +6,8 @@ import (
 	"fmt"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 	nats "github.com/nats-io/nats.go"
 )

receivers/prometheusReceiver.go

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

receivers/receiveManager.go

@@ -5,19 +5,18 @@ import (
 	"os"
 	"sync"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
-	"nats": NewNatsReceiver,
+	"nats":    NewNatsReceiver,
+	"redfish": NewRedfishReceiver,
 }
 
 type receiveManager struct {
 	inputs []Receiver
 	output chan lp.CCMetric
-	done   chan bool
-	wg     *sync.WaitGroup
 	config []json.RawMessage
 }
 
@@ -33,8 +32,6 @@ func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) er
 	// Initialize struct fields
 	rm.inputs = make([]Receiver, 0)
 	rm.output = nil
-	rm.done = make(chan bool)
-	rm.wg = wg
 	rm.config = make([]json.RawMessage, 0)
 
 	configFile, err := os.Open(receiverConfigFile)
@@ -58,7 +55,7 @@ func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) er
 }
 
 func (rm *receiveManager) Start() {
-	rm.wg.Add(1)
+	cclog.ComponentDebug("ReceiveManager", "START")
 
 	for _, r := range rm.inputs {
 		cclog.ComponentDebug("ReceiveManager", "START", r.Name())
@@ -97,16 +94,19 @@ func (rm *receiveManager) AddOutput(output chan lp.CCMetric) {
 }
 
 func (rm *receiveManager) Close() {
+	cclog.ComponentDebug("ReceiveManager", "CLOSE")
+
+	// Close all receivers
 	for _, r := range rm.inputs {
 		cclog.ComponentDebug("ReceiveManager", "CLOSE", r.Name())
 		r.Close()
 	}
-	rm.wg.Done()
-	cclog.ComponentDebug("ReceiveManager", "CLOSE")
+
+	cclog.ComponentDebug("ReceiveManager", "DONE")
 }
 
 func New(wg *sync.WaitGroup, receiverConfigFile string) (ReceiveManager, error) {
-	r := &receiveManager{}
+	r := new(receiveManager)
 	err := r.Init(wg, receiverConfigFile)
 	if err != nil {
 		return nil, err

receivers/redfishReceiver.go

@@ -0,0 +1,822 @@
+package receivers
+
+import (
+	"crypto/tls"
+	"encoding/json"
+	"fmt"
+	"net/http"
+	"strconv"
+	"strings"
+	"sync"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+
+	// See: https://pkg.go.dev/github.com/stmcginnis/gofish
+	"github.com/stmcginnis/gofish"
+	"github.com/stmcginnis/gofish/common"
+	"github.com/stmcginnis/gofish/redfish"
+)
+
+type RedfishReceiverClientConfig struct {
+
+	// Hostname the redfish service belongs to
+	Hostname string
+
+	// is metric excluded globally or per client
+	isExcluded map[string](bool)
+
+	doPowerMetric      bool
+	doProcessorMetrics bool
+	doThermalMetrics   bool
+
+	skipProcessorMetricsURL map[string]bool
+
+	gofish gofish.ClientConfig
+}
+
+// RedfishReceiver configuration:
+type RedfishReceiver struct {
+	receiver
+
+	config struct {
+		fanout      int
+		Interval    time.Duration
+		HttpTimeout time.Duration
+
+		// Client config for each redfish service
+		ClientConfigs []RedfishReceiverClientConfig
+	}
+
+	done chan bool      // channel to finish / stop redfish receiver
+	wg   sync.WaitGroup // wait group for redfish receiver
+}
+
+// readThermalMetrics reads thermal metrics from a redfish device
+func (r *RedfishReceiver) readThermalMetrics(
+	clientConfig *RedfishReceiverClientConfig,
+	chassis *redfish.Chassis) error {
+
+	// Get thermal information for each chassis
+	thermal, err := chassis.Thermal()
+	if err != nil {
+		return fmt.Errorf("readMetrics: chassis.Thermal() failed: %v", err)
+	}
+
+	// Skip empty thermal information
+	if thermal == nil {
+		return nil
+	}
+
+	timestamp := time.Now()
+
+	for _, temperature := range thermal.Temperatures {
+
+		// Skip, when temperature metric is excluded
+		if clientConfig.isExcluded["temperature"] {
+			break
+		}
+
+		// Skip all temperatures which are not in enabled state
+		if temperature.Status.State != "" && temperature.Status.State != common.EnabledState {
+			continue
+		}
+
+		tags := map[string]string{
+			"hostname": clientConfig.Hostname,
+			"type":     "node",
+			// ChassisType shall indicate the physical form factor for the type of chassis
+			"chassis_typ": string(chassis.ChassisType),
+			// Chassis name
+			"chassis_name": chassis.Name,
+			// ID uniquely identifies the resource
+			"temperature_id": temperature.ID,
+			// MemberID shall uniquely identify the member within the collection. For
+			// services supporting Redfish v1.6 or higher, this value shall be the
+			// zero-based array index.
+			"temperature_member_id": temperature.MemberID,
+			// PhysicalContext shall be a description of the affected device or region
+			// within the chassis to which this temperature measurement applies
+			"temperature_physical_context": string(temperature.PhysicalContext),
+			// Name
+			"temperature_name": temperature.Name,
+		}
+
+		// Delete empty tags
+		for key, value := range tags {
+			if value == "" {
+				delete(tags, key)
+			}
+		}
+
+		// Set meta data tags
+		meta := map[string]string{
+			"source": r.name,
+			"group":  "Temperature",
+			"unit":   "degC",
+		}
+
+		// ReadingCelsius shall be the current value of the temperature sensor's reading.
+		value := temperature.ReadingCelsius
+
+		y, err := lp.New("temperature", tags, meta,
+			map[string]interface{}{
+				"value": value,
+			},
+			timestamp)
+		if err == nil {
+			r.sink <- y
+		}
+	}
+
+	for _, fan := range thermal.Fans {
+		// Skip, when fan_speed metric is excluded
+		if clientConfig.isExcluded["fan_speed"] {
+			break
+		}
+
+		// Skip all fans which are not in enabled state
+		if fan.Status.State != common.EnabledState {
+			continue
+		}
+
+		tags := map[string]string{
+			"hostname": clientConfig.Hostname,
+			"type":     "node",
+			// ChassisType shall indicate the physical form factor for the type of chassis
+			"chassis_typ": string(chassis.ChassisType),
+			// Chassis name
+			"chassis_name": chassis.Name,
+			// ID uniquely identifies the resource
+			"fan_id": fan.ID,
+			// MemberID shall uniquely identify the member within the collection. For
+			// services supporting Redfish v1.6 or higher, this value shall be the
+			// zero-based array index.
+			"fan_member_id": fan.MemberID,
+			// PhysicalContext shall be a description of the affected device or region
+			// within the chassis to which this fan is associated
+			"fan_physical_context": string(fan.PhysicalContext),
+			// Name
+			"fan_name": fan.Name,
+		}
+
+		// Delete empty tags
+		for key, value := range tags {
+			if value == "" {
+				delete(tags, key)
+			}
+		}
+
+		// Set meta data tags
+		meta := map[string]string{
+			"source": r.name,
+			"group":  "FanSpeed",
+			"unit":   string(fan.ReadingUnits),
+		}
+
+		// Reading shall be the current value of the fan sensor's reading
+		value := fan.Reading
+
+		y, err := lp.New("fan_speed", tags, meta,
+			map[string]interface{}{
+				"value": value,
+			},
+			timestamp)
+		if err == nil {
+			r.sink <- y
+		}
+	}
+
+	return nil
+}
+
+// readPowerMetrics reads power metrics from a redfish device
+func (r *RedfishReceiver) readPowerMetrics(
+	clientConfig *RedfishReceiverClientConfig,
+	chassis *redfish.Chassis) error {
+
+	// Get power information for each chassis
+	power, err := chassis.Power()
+	if err != nil {
+		return fmt.Errorf("readMetrics: chassis.Power() failed: %v", err)
+	}
+
+	// Skip empty power information
+	if power == nil {
+		return nil
+	}
+
+	timestamp := time.Now()
+
+	// Read min, max and average consumed watts for each power control
+	for _, pc := range power.PowerControl {
+
+		// Skip all power controls which are not in enabled state
+		if pc.Status.State != "" && pc.Status.State != common.EnabledState {
+			continue
+		}
+
+		// Map of collected metrics
+		metrics := make(map[string]float32)
+
+		// PowerConsumedWatts shall represent the actual power being consumed (in
+		// Watts) by the chassis
+		if !clientConfig.isExcluded["consumed_watts"] {
+			metrics["consumed_watts"] = pc.PowerConsumedWatts
+		}
+		// AverageConsumedWatts shall represent the
+		// average power level that occurred averaged over the last IntervalInMin
+		// minutes.
+		if !clientConfig.isExcluded["average_consumed_watts"] {
+			metrics["average_consumed_watts"] = pc.PowerMetrics.AverageConsumedWatts
+		}
+		// MinConsumedWatts shall represent the
+		// minimum power level in watts that occurred within the last
+		// IntervalInMin minutes.
+		if !clientConfig.isExcluded["min_consumed_watts"] {
+			metrics["min_consumed_watts"] = pc.PowerMetrics.MinConsumedWatts
+		}
+		// MaxConsumedWatts shall represent the
+		// maximum power level in watts that occurred within the last
+		// IntervalInMin minutes
+		if !clientConfig.isExcluded["max_consumed_watts"] {
+			metrics["max_consumed_watts"] = pc.PowerMetrics.MaxConsumedWatts
+		}
+		// IntervalInMin shall represent the time interval (or window), in minutes,
+		// in which the PowerMetrics properties are measured over.
+		// Should be an integer, but some Dell implementations return as a float
+		intervalInMin :=
+			strconv.FormatFloat(
+				float64(pc.PowerMetrics.IntervalInMin), 'f', -1, 32)
+
+		// Set tags
+		tags := map[string]string{
+			"hostname": clientConfig.Hostname,
+			"type":     "node",
+			// ChassisType shall indicate the physical form factor for the type of chassis
+			"chassis_typ": string(chassis.ChassisType),
+			// Chassis name
+			"chassis_name": chassis.Name,
+			// ID uniquely identifies the resource
+			"power_control_id": pc.ID,
+			// MemberID shall uniquely identify the member within the collection. For
+			// services supporting Redfish v1.6 or higher, this value shall be the
+			// zero-based array index.
+			"power_control_member_id": pc.MemberID,
+			// PhysicalContext shall be a description of the affected device(s) or region
+			// within the chassis to which this power control applies.
+			"power_control_physical_context": string(pc.PhysicalContext),
+			// Name
+			"power_control_name": pc.Name,
+		}
+
+		// Delete empty tags
+		for key, value := range tags {
+			if value == "" {
+				delete(tags, key)
+			}
+		}
+
+		// Set meta data tags
+		meta := map[string]string{
+			"source":              r.name,
+			"group":               "Energy",
+			"interval_in_minutes": intervalInMin,
+			"unit":                "watts",
+		}
+
+		// Delete empty meta data tags
+		for key, value := range meta {
+			if value == "" {
+				delete(meta, key)
+			}
+		}
+
+		for name, value := range metrics {
+
+			y, err := lp.New(name, tags, meta,
+				map[string]interface{}{
+					"value": value,
+				},
+				timestamp)
+			if err == nil {
+				r.sink <- y
+			}
+		}
+	}
+
+	return nil
+}
+
+// readProcessorMetrics reads processor metrics from a redfish device
+// See: https://redfish.dmtf.org/schemas/v1/ProcessorMetrics.json
+func (r *RedfishReceiver) readProcessorMetrics(
+	clientConfig *RedfishReceiverClientConfig,
+	processor *redfish.Processor) error {
+
+	timestamp := time.Now()
+
+	// URL to processor metrics
+	URL := processor.ODataID + "/ProcessorMetrics"
+
+	// Skip previously detected non existing URLs
+	if clientConfig.skipProcessorMetricsURL[URL] {
+		return nil
+	}
+
+	resp, err := processor.Client.Get(URL)
+	if err != nil {
+		// Skip non existing URLs
+		if statusCode := err.(*common.Error).HTTPReturnedStatusCode; statusCode == http.StatusNotFound {
+			clientConfig.skipProcessorMetricsURL[URL] = true
+			return nil
+		}
+
+		return fmt.Errorf("processor.Client.Get(%v) failed: %+w", URL, err)
+	}
+
+	var processorMetrics struct {
+		common.Entity
+		ODataType   string `json:"@odata.type"`
+		ODataEtag   string `json:"@odata.etag"`
+		Description string `json:"Description"`
+		// This property shall contain the power, in watts, that the processor has consumed.
+		ConsumedPowerWatt float32 `json:"ConsumedPowerWatt"`
+		// This property shall contain the temperature, in Celsius, of the processor.
+		TemperatureCelsius float32 `json:"TemperatureCelsius"`
+	}
+	err = json.NewDecoder(resp.Body).Decode(&processorMetrics)
+	if err != nil {
+		return fmt.Errorf("unable to decode JSON for processor metrics: %+w", err)
+	}
+	processorMetrics.SetClient(processor.Client)
+
+	// Set tags
+	tags := map[string]string{
+		"hostname": clientConfig.Hostname,
+		"type":     "socket",
+		// ProcessorType shall contain the string which identifies the type of processor contained in this Socket
+		"processor_typ": string(processor.ProcessorType),
+		// Processor name
+		"processor_name": processor.Name,
+		// ID uniquely identifies the resource
+		"processor_id": processor.ID,
+	}
+
+	// Delete empty tags
+	for key, value := range tags {
+		if value == "" {
+			delete(tags, key)
+		}
+	}
+
+	// Set meta data tags
+	metaPower := map[string]string{
+		"source": r.name,
+		"group":  "Energy",
+		"unit":   "watts",
+	}
+
+	namePower := "consumed_power"
+
+	if !clientConfig.isExcluded[namePower] {
+		y, err := lp.New(namePower, tags, metaPower,
+			map[string]interface{}{
+				"value": processorMetrics.ConsumedPowerWatt,
+			},
+			timestamp)
+		if err == nil {
+			r.sink <- y
+		}
+	}
+	// Set meta data tags
+	metaThermal := map[string]string{
+		"source": r.name,
+		"group":  "Temperature",
+		"unit":   "degC",
+	}
+
+	nameThermal := "temperature"
+
+	if !clientConfig.isExcluded[nameThermal] {
+		y, err := lp.New(nameThermal, tags, metaThermal,
+			map[string]interface{}{
+				"value": processorMetrics.TemperatureCelsius,
+			},
+			timestamp)
+		if err == nil {
+			r.sink <- y
+		}
+	}
+	return nil
+}
+
+// readMetrics reads redfish thermal, power and processor metrics from the redfish device
+// configured in clientConfig
+func (r *RedfishReceiver) readMetrics(clientConfig *RedfishReceiverClientConfig) error {
+
+	// Connect to redfish service
+	c, err := gofish.Connect(clientConfig.gofish)
+	if err != nil {
+		return fmt.Errorf(
+			"readMetrics: gofish.Connect({Username: %v, Endpoint: %v, BasicAuth: %v, HttpTimeout: %v, HttpInsecure: %v}) failed: %v",
+			clientConfig.gofish.Username,
+			clientConfig.gofish.Endpoint,
+			clientConfig.gofish.BasicAuth,
+			clientConfig.gofish.HTTPClient.Timeout,
+			clientConfig.gofish.HTTPClient.Transport.(*http.Transport).TLSClientConfig.InsecureSkipVerify,
+			err)
+	}
+	defer c.Logout()
+
+	// Create a session, when required
+	if _, err = c.GetSession(); err != nil {
+		c, err = c.CloneWithSession()
+		if err != nil {
+			return fmt.Errorf("readMetrics: Failed to create a session: %+w", err)
+		}
+	}
+
+	// Get all chassis managed by this service
+	isChassisListRequired :=
+		clientConfig.doThermalMetrics ||
+			clientConfig.doPowerMetric
+	var chassisList []*redfish.Chassis
+	if isChassisListRequired {
+		chassisList, err = c.Service.Chassis()
+		if err != nil {
+			return fmt.Errorf("readMetrics: c.Service.Chassis() failed: %v", err)
+		}
+	}
+
+	// Get all computer systems managed by this service
+	isComputerSystemListRequired := clientConfig.doProcessorMetrics
+	var computerSystemList []*redfish.ComputerSystem
+	if isComputerSystemListRequired {
+		computerSystemList, err = c.Service.Systems()
+		if err != nil {
+			return fmt.Errorf("readMetrics: c.Service.Systems() failed: %v", err)
+		}
+	}
+
+	// read thermal metrics
+	if clientConfig.doThermalMetrics {
+		for _, chassis := range chassisList {
+			err := r.readThermalMetrics(clientConfig, chassis)
+			if err != nil {
+				return err
+			}
+		}
+	}
+
+	// read power metrics
+	if clientConfig.doPowerMetric {
+		for _, chassis := range chassisList {
+			err = r.readPowerMetrics(clientConfig, chassis)
+			if err != nil {
+				return err
+			}
+		}
+	}
+
+	// read processor metrics
+	if clientConfig.doProcessorMetrics {
+		// loop for all computer systems
+		for _, system := range computerSystemList {
+
+			// loop for all processors
+			processors, err := system.Processors()
+			if err != nil {
+				return fmt.Errorf("readMetrics: system.Processors() failed: %v", err)
+			}
+			for _, processor := range processors {
+				err := r.readProcessorMetrics(clientConfig, processor)
+				if err != nil {
+					return err
+				}
+			}
+		}
+	}
+
+	return nil
+}
+
+// doReadMetrics reads metrics from all configure redfish devices.
+// To compensate latencies of the Redfish devices a fanout is used.
+func (r *RedfishReceiver) doReadMetric() {
+
+	// Create wait group and input channel for workers
+	var workerWaitGroup sync.WaitGroup
+	workerInput := make(chan *RedfishReceiverClientConfig, r.config.fanout)
+
+	// Create worker go routines
+	for i := 0; i < r.config.fanout; i++ {
+		// Increment worker wait group counter
+		workerWaitGroup.Add(1)
+		go func() {
+			// Decrement worker wait group counter
+			defer workerWaitGroup.Done()
+
+			// Read power metrics for each client config
+			for clientConfig := range workerInput {
+				err := r.readMetrics(clientConfig)
+				if err != nil {
+					cclog.ComponentError(r.name, err)
+				}
+			}
+		}()
+	}
+
+	// Distribute client configs to workers
+	for i := range r.config.ClientConfigs {
+
+		// Check done channel status
+		select {
+		case workerInput <- &r.config.ClientConfigs[i]:
+		case <-r.done:
+			// process done event
+			// Stop workers, clear channel and wait for all workers to finish
+			close(workerInput)
+			for range workerInput {
+			}
+			workerWaitGroup.Wait()
+			return
+		}
+	}
+
+	// Stop workers and wait for all workers to finish
+	close(workerInput)
+	workerWaitGroup.Wait()
+}
+
+// Start starts the redfish receiver
+func (r *RedfishReceiver) Start() {
+	cclog.ComponentDebug(r.name, "START")
+
+	// Start redfish 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 closes the redfish receiver
+func (r *RedfishReceiver) Close() {
+	cclog.ComponentDebug(r.name, "CLOSE")
+
+	// Send the signal and wait
+	close(r.done)
+	r.wg.Wait()
+
+	cclog.ComponentDebug(r.name, "DONE")
+}
+
+// NewRedfishReceiver creates a new instance of the redfish receiver
+// Initialize the receiver by giving it a name and reading in the config JSON
+func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
+	r := new(RedfishReceiver)
+
+	// Config options from config file
+	configJSON := struct {
+		Type string `json:"type"`
+
+		// Maximum number of simultaneous redfish connections (default: 64)
+		Fanout int `json:"fanout,omitempty"`
+		// How often the redfish power metrics should be read and send to the sink (default: 30 s)
+		IntervalString string `json:"interval,omitempty"`
+
+		// Control whether a client verifies the server's certificate
+		// (default: true == do not verify server's certificate)
+		HttpInsecure bool `json:"http_insecure,omitempty"`
+		// Time limit for requests made by this HTTP client (default: 10 s)
+		HttpTimeoutString string `json:"http_timeout,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 redfish service
+
+		// Globally disable collection of power, processor or thermal metrics
+		DisablePowerMetrics     bool `json:"disable_power_metrics"`
+		DisableProcessorMetrics bool `json:"disable_processor_metrics"`
+		DisableThermalMetrics   bool `json:"disable_thermal_metrics"`
+
+		// Globally excluded metrics
+		ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+
+		ClientConfigs []struct {
+			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 redfish service
+
+			// Per client disable collection of power,processor or thermal metrics
+			DisablePowerMetrics     bool `json:"disable_power_metrics"`
+			DisableProcessorMetrics bool `json:"disable_processor_metrics"`
+			DisableThermalMetrics   bool `json:"disable_thermal_metrics"`
+
+			// Per client excluded metrics
+			ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+		} `json:"client_config"`
+	}{
+		// Set defaults values
+		// Allow overwriting these defaults by reading config JSON
+		Fanout:            64,
+		IntervalString:    "30s",
+		HttpTimeoutString: "10s",
+		HttpInsecure:      true,
+	}
+
+	// Set name
+	r.name = fmt.Sprintf("RedfishReceiver(%s)", name)
+
+	// Create done channel
+	r.done = make(chan bool)
+
+	// Read the redfish receiver specific JSON config
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &configJSON)
+		if 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
+	}
+
+	// HTTP timeout duration
+	r.config.HttpTimeout, err = time.ParseDuration(configJSON.HttpTimeoutString)
+	if err != nil {
+		err := fmt.Errorf(
+			"Failed to parse duration string http_timeout='%s': %w",
+			configJSON.HttpTimeoutString,
+			err,
+		)
+		cclog.Error(r.name, err)
+		return nil, err
+	}
+
+	// Create new http client
+	customTransport := http.DefaultTransport.(*http.Transport).Clone()
+	customTransport.TLSClientConfig = &tls.Config{
+		InsecureSkipVerify: configJSON.HttpInsecure,
+	}
+	httpClient := &http.Client{
+		Timeout:   r.config.HttpTimeout,
+		Transport: customTransport,
+	}
+
+	// Initialize client configurations
+	r.config.ClientConfigs = make([]RedfishReceiverClientConfig, 0)
+
+	// Create client config from JSON config
+	for i := range configJSON.ClientConfigs {
+
+		clientConfigJSON := &configJSON.ClientConfigs[i]
+
+		var endpoint_pattern string
+		if clientConfigJSON.Endpoint != nil {
+			endpoint_pattern = *clientConfigJSON.Endpoint
+		} else if configJSON.Endpoint != nil {
+			endpoint_pattern = *configJSON.Endpoint
+		} else {
+			err := fmt.Errorf("client config number %v requires endpoint", i)
+			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
+		}
+
+		// Which metrics should be collected
+		doPowerMetric :=
+			!(configJSON.DisablePowerMetrics ||
+				clientConfigJSON.DisablePowerMetrics)
+		doProcessorMetrics :=
+			!(configJSON.DisableProcessorMetrics ||
+				clientConfigJSON.DisableProcessorMetrics)
+		doThermalMetrics :=
+			!(configJSON.DisableThermalMetrics ||
+				clientConfigJSON.DisableThermalMetrics)
+
+		// 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
+		}
+
+		for _, host := range clientConfigJSON.HostList {
+
+			// Endpoint of the redfish service
+			endpoint := strings.Replace(endpoint_pattern, "%h", host, -1)
+
+			r.config.ClientConfigs = append(
+				r.config.ClientConfigs,
+				RedfishReceiverClientConfig{
+					Hostname:                host,
+					isExcluded:              isExcluded,
+					doPowerMetric:           doPowerMetric,
+					doProcessorMetrics:      doProcessorMetrics,
+					doThermalMetrics:        doThermalMetrics,
+					skipProcessorMetricsURL: make(map[string]bool),
+					gofish: gofish.ClientConfig{
+						Username:   username,
+						Password:   password,
+						Endpoint:   endpoint,
+						HTTPClient: httpClient,
+					},
+				})
+		}
+
+	}
+
+	// Compute parallel fanout to use
+	numClients := len(r.config.ClientConfigs)
+	r.config.fanout = configJSON.Fanout
+	if numClients < r.config.fanout {
+		r.config.fanout = numClients
+	}
+
+	if numClients == 0 {
+		err := fmt.Errorf("at least one client config is required")
+		cclog.ComponentError(r.name, err)
+		return nil, err
+	}
+
+	// Check for duplicate client configurations
+	isDuplicate := make(map[string]bool)
+	for i := range r.config.ClientConfigs {
+		host := r.config.ClientConfigs[i].Hostname
+		if isDuplicate[host] {
+			err := fmt.Errorf("Found duplicate client config for host %s", host)
+			cclog.ComponentError(r.name, err)
+			return nil, err
+		}
+		isDuplicate[host] = true
+	}
+
+	// Give some basic info about redfish receiver status
+	cclog.ComponentInfo(r.name, "Monitoring", numClients, "clients")
+	cclog.ComponentInfo(r.name, "Monitoring interval:", r.config.Interval)
+	cclog.ComponentInfo(r.name, "Monitoring parallel fanout:", r.config.fanout)
+
+	return r, nil
+}

receivers/redfishReceiver.md

@@ -0,0 +1,54 @@
+## 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": "<user A>",
+        "password": "<password A>",
+        "endpoint": "https://%h-bmc",
+        "exclude_metrics": [ "min_consumed_watts" ],
+        "client_config": [
+            {
+                "host_list": [ "<host 1>", "<host 2>" ]
+            },
+            {
+                "host_list": [ "<host 3>", "<host 4>" ]
+                "disable_power_metrics": true
+            },
+            {
+                "host_list": [ "<host 5>" ],
+                "username": "<user B>",
+                "password": "<password B>",
+                "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/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 )
 
 // SampleReceiver configuration: receiver type, listen address, port
@@ -36,16 +36,26 @@ func (r *SampleReceiver) Start() {
 
 	// or use own go routine but always make sure it exits
 	// as soon as it gets the signal of the r.done channel
+	//
+	// r.done = make(chan bool)
 	// r.wg.Add(1)
 	// go func() {
-	// 	for {
-	// 		select {
-	// 		case <-r.done:
-	// 			r.wg.Done()
-	// 			return
-	// 		}
-	// 	}
-	// 	r.wg.Done()
+	//      defer r.wg.Done()
+	//
+	//      // Create ticker
+	//      ticker := time.NewTicker(30 * time.Second)
+	//      defer ticker.Stop()
+	//
+	//      for {
+	//          readMetric()
+	//          select {
+	//          case <-ticker.C:
+	//              // process ticker event -> continue
+	//              continue
+	//          case <-r.done:
+	//              return
+	//          }
+	//      }
 	// }()
 }
 

scripts/cc-metric-collector.config

@@ -6,7 +6,7 @@ CC_HOME=/tmp
 
 LOG_DIR=/var/log
 
-DATA_DIR=/var/lib/grafana
+DATA_DIR=/var/lib/cc-metric-collector
 
 MAX_OPEN_FILES=10000
 
@@ -15,3 +15,9 @@ 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.control

@@ -0,0 +1,12 @@
+Package: cc-metric-collector
+Version: {VERSION}
+Installed-Size: {INSTALLED_SIZE}
+Architecture: {ARCH}
+Maintainer: thomas.gruber@fau.de
+Depends: libc6 (>= 2.2.1)
+Build-Depends: debhelper-compat (= 13), git, golang-go
+Description: Metric collection daemon from the ClusterCockpit suite
+Homepage: https://github.com/ClusterCockpit/cc-metric-collector
+Source: cc-metric-collector
+Rules-Requires-Root: no
+

scripts/cc-metric-collector.deb.rules

@@ -0,0 +1,16 @@
+
+#!/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

@@ -19,7 +19,7 @@
 PATH=/bin:/usr/bin:/sbin:/usr/sbin
 NAME=cc-metric-collector
 DESC="ClusterCockpit metric collector"
-DEFAULT=/etc/default/${NAME}.json
+DEFAULT=/etc/default/${NAME}
 
 CC_USER=clustercockpit
 CC_GROUP=clustercockpit
@@ -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 -- $DAEMON_OPTS
+	start-stop-daemon --start -b --chdir "$WORK_DIR" --user "$CC_USER" -c "$CC_USER" --pidfile "$PID_FILE" --exec $DAEMON -- $CC_OPTS
 	return=$?
 	if [ $return -eq 0 ]
 	then

scripts/cc-metric-collector.spec

@@ -8,8 +8,8 @@ Source0:        %{name}-%{version}.tar.gz
 
 BuildRequires:  go-toolset
 BuildRequires:  systemd-rpm-macros
-# for internal LIKWID installation
-BuildRequires:  wget perl-Data-Dumper
+# for header downloads
+BuildRequires:  wget
 
 Provides:       %{name} = %{version}
 
@@ -53,7 +53,7 @@ install -Dpm 0644 scripts/%{name}.sysusers %{buildroot}%{_sysusersdir}/%{name}.c
 %files
 # Binary
 %attr(-,clustercockpit,clustercockpit) %{_sbindir}/%{name}
-# Configuration
+# Config
 %dir %{_sysconfdir}/%{name}
 %attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/%{name}.json
 %attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/collectors.json
@@ -61,9 +61,9 @@ install -Dpm 0644 scripts/%{name}.sysusers %{buildroot}%{_sysusersdir}/%{name}.c
 %attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/receivers.json
 %attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/router.json
 # Systemd
-%{_sysusersdir}/%{name}.conf
 %{_unitdir}/%{name}.service
 %{_sysconfdir}/default/%{name}
+%{_sysusersdir}/%{name}.conf
 
 %changelog
 * Thu Mar 03 2022 Thomas Gruber - 0.3

scripts/likwid_perfgroup_to_cc_config.py

@@ -39,7 +39,7 @@ def group_to_json(groupfile):
             llist = re.split("\s+", line)
             calc = llist[-1]
             metric = " ".join(llist[:-1])
-            scope = "cpu"
+            scope = "hwthread"
             if "BOX" in calc:
                 scope = "socket"
             if "PWR" in calc:

sinks.json

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

sinks/gangliaCommon.go

@@ -4,7 +4,7 @@ import (
 	"fmt"
 	"strings"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 func GangliaMetricName(point lp.CCMetric) string {
@@ -148,10 +148,14 @@ type GangliaMetricConfig struct {
 	Unit  string
 	Group string
 	Value string
+	Name  string
 }
 
 func GetCommonGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
 	mname := GangliaMetricRename(point.Name())
+	if oldname, ok := point.GetMeta("oldname"); ok {
+		mname = GangliaMetricRename(oldname)
+	}
 	for _, group := range CommonGangliaMetrics {
 		for _, metric := range group.Metrics {
 			if metric.Name == mname {
@@ -187,6 +191,7 @@ func GetCommonGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
 					Tmax:  metric.Tmax,
 					Unit:  metric.Unit,
 					Value: valueStr,
+					Name:  GangliaMetricRename(mname),
 				}
 			}
 		}
@@ -198,10 +203,15 @@ func GetCommonGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
 		Tmax:  0,
 		Unit:  "",
 		Value: "",
+		Name:  "",
 	}
 }
 
 func GetGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
+	mname := GangliaMetricRename(point.Name())
+	if oldname, ok := point.GetMeta("oldname"); ok {
+		mname = GangliaMetricRename(oldname)
+	}
 	group := ""
 	if g, ok := point.GetMeta("group"); ok {
 		group = g
@@ -254,5 +264,6 @@ func GetGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
 		Tmax:  DEFAULT_GANGLIA_METRIC_TMAX,
 		Unit:  unit,
 		Value: valueStr,
+		Name:  GangliaMetricRename(mname),
 	}
 }

sinks/gangliaSink.go

@@ -9,8 +9,8 @@ import (
 	//	"time"
 	"os/exec"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const GMETRIC_EXEC = `gmetric`
@@ -39,16 +39,13 @@ func (s *GangliaSink) Write(point lp.CCMetric) error {
 	//var tagsstr []string
 	var argstr []string
 
-	// Get metric name
-	metricname := GangliaMetricRename(point.Name())
-
 	// Get metric config (type, value, ... in suitable format)
 	conf := GetCommonGangliaConfig(point)
 	if len(conf.Type) == 0 {
 		conf = GetGangliaConfig(point)
 	}
 	if len(conf.Type) == 0 {
-		return fmt.Errorf("metric %s has no 'value' field", metricname)
+		return fmt.Errorf("metric %q (Ganglia name %q) has no 'value' field", point.Name(), conf.Name)
 	}
 
 	if s.config.AddGangliaGroup {
@@ -70,7 +67,7 @@ func (s *GangliaSink) Write(point lp.CCMetric) error {
 	if s.config.AddTypeToName {
 		argstr = append(argstr, fmt.Sprintf("--name=%s", GangliaMetricName(point)))
 	} else {
-		argstr = append(argstr, fmt.Sprintf("--name=%s", metricname))
+		argstr = append(argstr, fmt.Sprintf("--name=%s", conf.Name))
 	}
 	argstr = append(argstr, fmt.Sprintf("--slope=%s", conf.Slope))
 	argstr = append(argstr, fmt.Sprintf("--value=%s", conf.Value))

sinks/httpSink.go

@@ -9,8 +9,8 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 )
 
@@ -19,9 +19,9 @@ type HttpSinkConfig struct {
 	URL             string `json:"url,omitempty"`
 	JWT             string `json:"jwt,omitempty"`
 	Timeout         string `json:"timeout,omitempty"`
-	MaxIdleConns    int    `json:"max_idle_connections,omitempty"`
 	IdleConnTimeout string `json:"idle_connection_timeout,omitempty"`
 	FlushDelay      string `json:"flush_delay,omitempty"`
+	MaxRetries      int    `json:"max_retries,omitempty"`
 }
 
 type HttpSink struct {
@@ -32,80 +32,87 @@ type HttpSink struct {
 	buffer          *bytes.Buffer
 	flushTimer      *time.Timer
 	config          HttpSinkConfig
-	maxIdleConns    int
 	idleConnTimeout time.Duration
 	timeout         time.Duration
 	flushDelay      time.Duration
 }
 
 func (s *HttpSink) Write(m lp.CCMetric) error {
-	if s.buffer.Len() == 0 && s.flushDelay != 0 {
-		// This is the first write since the last flush, start the flushTimer!
-		if s.flushTimer != nil && s.flushTimer.Stop() {
-			cclog.ComponentDebug("HttpSink", "unexpected: the flushTimer was already running?")
-		}
-
-		// Run a batched flush for all lines that have arrived in the last second
-		s.flushTimer = time.AfterFunc(s.flushDelay, func() {
-			if err := s.Flush(); err != nil {
-				cclog.ComponentError("HttpSink", "flush failed:", err.Error())
-			}
-		})
-	}
-
-	p := m.ToPoint(s.config.MetaAsTags)
-
+	p := m.ToPoint(s.meta_as_tags)
 	s.lock.Lock()
+	firstWriteOfBatch := s.buffer.Len() == 0
 	_, err := s.encoder.Encode(p)
-	s.lock.Unlock() // defer does not work here as Flush() takes the lock as well
-
+	s.lock.Unlock()
 	if err != nil {
+		cclog.ComponentError(s.name, "encoding failed:", err.Error())
 		return err
 	}
 
-	// Flush synchronously if "flush_delay" is zero
 	if s.flushDelay == 0 {
 		return s.Flush()
 	}
 
-	return err
+	if firstWriteOfBatch {
+		if s.flushTimer == nil {
+			s.flushTimer = time.AfterFunc(s.flushDelay, func() {
+				if err := s.Flush(); err != nil {
+					cclog.ComponentError(s.name, "flush failed:", err.Error())
+				}
+			})
+		} else {
+			s.flushTimer.Reset(s.flushDelay)
+		}
+	}
+
+	return nil
 }
 
 func (s *HttpSink) Flush() error {
-	// buffer is read by client.Do, prevent concurrent modifications
+	// Own lock for as short as possible: the time it takes to copy the buffer.
 	s.lock.Lock()
-	defer s.lock.Unlock()
-
-	// Do not flush empty buffer
-	if s.buffer.Len() == 0 {
+	buf := make([]byte, s.buffer.Len())
+	copy(buf, s.buffer.Bytes())
+	s.buffer.Reset()
+	s.lock.Unlock()
+	if len(buf) == 0 {
 		return nil
 	}
 
-	// Create new request to send buffer
-	req, err := http.NewRequest(http.MethodPost, s.config.URL, s.buffer)
-	if err != nil {
-		return err
+	var res *http.Response
+	for i := 0; i < s.config.MaxRetries; i++ {
+		// Create new request to send buffer
+		req, err := http.NewRequest(http.MethodPost, s.config.URL, bytes.NewReader(buf))
+		if err != nil {
+			cclog.ComponentError(s.name, "failed to create request:", err.Error())
+			return err
+		}
+
+		// Set authorization header
+		if len(s.config.JWT) != 0 {
+			req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", s.config.JWT))
+		}
+
+		// Do request
+		res, err = s.client.Do(req)
+		if err != nil {
+			cclog.ComponentError(s.name, "transport/tcp error:", err.Error())
+			// Wait between retries
+			time.Sleep(time.Duration(i+1) * (time.Second / 2))
+			continue
+		}
+
+		break
 	}
 
-	// Set authorization header
-	if len(s.config.JWT) != 0 {
-		req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", s.config.JWT))
-	}
-
-	// Send
-	res, err := s.client.Do(req)
-
-	// Clear buffer
-	s.buffer.Reset()
-
-	// Handle transport/tcp errors
-	if err != nil {
-		return err
+	if res == nil {
+		return errors.New("flush failed due to repeated errors")
 	}
 
 	// Handle application errors
 	if res.StatusCode != http.StatusOK {
-		return errors.New(res.Status)
+		err := errors.New(res.Status)
+		cclog.ComponentError(s.name, "application error:", err.Error())
+		return err
 	}
 
 	return nil
@@ -114,7 +121,7 @@ func (s *HttpSink) Flush() error {
 func (s *HttpSink) Close() {
 	s.flushTimer.Stop()
 	if err := s.Flush(); err != nil {
-		cclog.ComponentError("HttpSink", "flush failed:", err.Error())
+		cclog.ComponentError(s.name, "flush failed:", err.Error())
 	}
 	s.client.CloseIdleConnections()
 }
@@ -123,10 +130,10 @@ func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
 	s := new(HttpSink)
 	// Set default values
 	s.name = fmt.Sprintf("HttpSink(%s)", name)
-	s.config.MaxIdleConns = 10
-	s.config.IdleConnTimeout = "5s"
+	s.config.IdleConnTimeout = "120s" // should be larger than the measurement interval.
 	s.config.Timeout = "5s"
-	s.config.FlushDelay = "1s"
+	s.config.FlushDelay = "5s"
+	s.config.MaxRetries = 3
 
 	// Read config
 	if len(config) > 0 {
@@ -138,9 +145,6 @@ func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
 	if len(s.config.URL) == 0 {
 		return nil, errors.New("`url` config option is required for HTTP sink")
 	}
-	if s.config.MaxIdleConns > 0 {
-		s.maxIdleConns = s.config.MaxIdleConns
-	}
 	if len(s.config.IdleConnTimeout) > 0 {
 		t, err := time.ParseDuration(s.config.IdleConnTimeout)
 		if err == nil {
@@ -159,8 +163,13 @@ func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
 			s.flushDelay = t
 		}
 	}
+	// Create lookup map to use meta infos as tags in the output metric
+	s.meta_as_tags = make(map[string]bool)
+	for _, k := range s.config.MetaAsTags {
+		s.meta_as_tags[k] = true
+	}
 	tr := &http.Transport{
-		MaxIdleConns:    s.maxIdleConns,
+		MaxIdleConns:    1, // We will only ever talk to one host.
 		IdleConnTimeout: s.idleConnTimeout,
 	}
 	s.client = &http.Client{Transport: tr, Timeout: s.timeout}

sinks/influxAsyncSink.go

@@ -6,11 +6,14 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"strings"
+	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
 	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
+	influxdb2ApiHttp "github.com/influxdata/influxdb-client-go/v2/api/http"
 )
 
 type InfluxAsyncSinkConfig struct {
@@ -22,19 +25,28 @@ type InfluxAsyncSinkConfig struct {
 	Password     string `json:"password,omitempty"`
 	Organization string `json:"organization,omitempty"`
 	SSL          bool   `json:"ssl,omitempty"`
-	RetentionPol string `json:"retention_policy,omitempty"`
 	// Maximum number of points sent to server in single request. Default 5000
 	BatchSize uint `json:"batch_size,omitempty"`
 	// Interval, in ms, in which is buffer flushed if it has not been already written (by reaching batch size) . Default 1000ms
-	FlushInterval uint `json:"flush_interval,omitempty"`
+	FlushInterval         uint   `json:"flush_interval,omitempty"`
+	InfluxRetryInterval   string `json:"retry_interval,omitempty"`
+	InfluxExponentialBase uint   `json:"retry_exponential_base,omitempty"`
+	InfluxMaxRetries      uint   `json:"max_retries,omitempty"`
+	InfluxMaxRetryTime    string `json:"max_retry_time,omitempty"`
+	CustomFlushInterval   string `json:"custom_flush_interval,omitempty"`
+	MaxRetryAttempts      uint   `json:"max_retry_attempts,omitempty"`
 }
 
 type InfluxAsyncSink struct {
 	sink
-	client   influxdb2.Client
-	writeApi influxdb2Api.WriteAPI
-	errors   <-chan error
-	config   InfluxAsyncSinkConfig
+	client              influxdb2.Client
+	writeApi            influxdb2Api.WriteAPI
+	errors              <-chan error
+	config              InfluxAsyncSinkConfig
+	influxRetryInterval uint
+	influxMaxRetryTime  uint
+	customFlushInterval time.Duration
+	flushTimer          *time.Timer
 }
 
 func (s *InfluxAsyncSink) connect() error {
@@ -53,16 +65,35 @@ func (s *InfluxAsyncSink) connect() error {
 	cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
 	clientOptions := influxdb2.DefaultOptions()
 	if s.config.BatchSize != 0 {
+		cclog.ComponentDebug(s.name, "Batch size", s.config.BatchSize)
 		clientOptions.SetBatchSize(s.config.BatchSize)
 	}
 	if s.config.FlushInterval != 0 {
+		cclog.ComponentDebug(s.name, "Flush interval", s.config.FlushInterval)
 		clientOptions.SetFlushInterval(s.config.FlushInterval)
 	}
+	if s.influxRetryInterval != 0 {
+		cclog.ComponentDebug(s.name, "MaxRetryInterval", s.influxRetryInterval)
+		clientOptions.SetMaxRetryInterval(s.influxRetryInterval)
+	}
+	if s.influxMaxRetryTime != 0 {
+		cclog.ComponentDebug(s.name, "MaxRetryTime", s.influxMaxRetryTime)
+		clientOptions.SetMaxRetryTime(s.influxMaxRetryTime)
+	}
+	if s.config.InfluxExponentialBase != 0 {
+		cclog.ComponentDebug(s.name, "Exponential Base", s.config.InfluxExponentialBase)
+		clientOptions.SetExponentialBase(s.config.InfluxExponentialBase)
+	}
+	if s.config.InfluxMaxRetries != 0 {
+		cclog.ComponentDebug(s.name, "Max Retries", s.config.InfluxMaxRetries)
+		clientOptions.SetMaxRetries(s.config.InfluxMaxRetries)
+	}
 	clientOptions.SetTLSConfig(
 		&tls.Config{
 			InsecureSkipVerify: true,
 		},
-	)
+	).SetPrecision(time.Second)
+
 	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
 	s.writeApi = s.client.WriteAPI(s.config.Organization, s.config.Database)
 	ok, err := s.client.Ping(context.Background())
@@ -72,18 +103,35 @@ func (s *InfluxAsyncSink) connect() error {
 	if !ok {
 		return fmt.Errorf("connection to %s not healthy", uri)
 	}
+	s.writeApi.SetWriteFailedCallback(func(batch string, err influxdb2ApiHttp.Error, retryAttempts uint) bool {
+		mlist := strings.Split(batch, "\n")
+		cclog.ComponentError(s.name, fmt.Sprintf("Failed to write batch with %d metrics %d times (max: %d): %s", len(mlist), retryAttempts, s.config.MaxRetryAttempts, err.Error()))
+		return retryAttempts <= s.config.MaxRetryAttempts
+	})
 	return nil
 }
 
 func (s *InfluxAsyncSink) Write(m lp.CCMetric) error {
+	if s.customFlushInterval != 0 && s.flushTimer == nil {
+		// Run a batched flush for all lines that have arrived in the defined interval
+		s.flushTimer = time.AfterFunc(s.customFlushInterval, func() {
+			if err := s.Flush(); err != nil {
+				cclog.ComponentError(s.name, "flush failed:", err.Error())
+			}
+		})
+	}
 	s.writeApi.WritePoint(
-		m.ToPoint(s.config.MetaAsTags),
+		m.ToPoint(s.meta_as_tags),
 	)
 	return nil
 }
 
 func (s *InfluxAsyncSink) Flush() error {
+	cclog.ComponentDebug(s.name, "Flushing")
 	s.writeApi.Flush()
+	if s.customFlushInterval != 0 && s.flushTimer != nil {
+		s.flushTimer = nil
+	}
 	return nil
 }
 
@@ -98,7 +146,38 @@ func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
 	s.name = fmt.Sprintf("InfluxSink(%s)", name)
 
 	// Set default for maximum number of points sent to server in single request.
-	s.config.BatchSize = 100
+	s.config.BatchSize = 0
+	s.influxRetryInterval = 0
+	//s.config.InfluxRetryInterval = "1s"
+	s.influxMaxRetryTime = 0
+	//s.config.InfluxMaxRetryTime = "168h"
+	s.config.InfluxMaxRetries = 0
+	s.config.InfluxExponentialBase = 0
+	s.config.FlushInterval = 0
+	s.config.CustomFlushInterval = ""
+	s.customFlushInterval = time.Duration(0)
+	s.config.MaxRetryAttempts = 1
+
+	// Default retry intervals (in seconds)
+	// 1 2
+	// 2 4
+	// 4 8
+	// 8 16
+	// 16 32
+	// 32 64
+	// 64 128
+	// 128 256
+	// 256 512
+	// 512 1024
+	// 1024 2048
+	// 2048 4096
+	// 4096 8192
+	// 8192 16384
+	// 16384 32768
+	// 32768 65536
+	// 65536 131072
+	// 131072 262144
+	// 262144 524288
 
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &s.config)
@@ -106,12 +185,41 @@ func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
 			return nil, err
 		}
 	}
-	if len(s.config.Host) == 0 ||
-		len(s.config.Port) == 0 ||
-		len(s.config.Database) == 0 ||
-		len(s.config.Organization) == 0 ||
-		len(s.config.Password) == 0 {
-		return nil, errors.New("not all configuration variables set required by InfluxAsyncSink")
+	if len(s.config.Port) == 0 {
+		return nil, errors.New("Missing port configuration required by InfluxSink")
+	}
+	if len(s.config.Database) == 0 {
+		return nil, errors.New("Missing database configuration required by InfluxSink")
+	}
+	if len(s.config.Organization) == 0 {
+		return nil, errors.New("Missing organization configuration required by InfluxSink")
+	}
+	if len(s.config.Password) == 0 {
+		return nil, errors.New("Missing password configuration required by InfluxSink")
+	}
+	// Create lookup map to use meta infos as tags in the output metric
+	s.meta_as_tags = make(map[string]bool)
+	for _, k := range s.config.MetaAsTags {
+		s.meta_as_tags[k] = true
+	}
+
+	toUint := func(duration string, def uint) uint {
+		t, err := time.ParseDuration(duration)
+		if err == nil {
+			return uint(t.Milliseconds())
+		}
+		return def
+	}
+	s.influxRetryInterval = toUint(s.config.InfluxRetryInterval, s.influxRetryInterval)
+	s.influxMaxRetryTime = toUint(s.config.InfluxMaxRetryTime, s.influxMaxRetryTime)
+
+	// Use a own timer for calling Flush()
+	if len(s.config.CustomFlushInterval) > 0 {
+		t, err := time.ParseDuration(s.config.CustomFlushInterval)
+		if err != nil {
+			return nil, fmt.Errorf("invalid duration in 'custom_flush_interval': %v", err)
+		}
+		s.customFlushInterval = t
 	}
 
 	// Connect to InfluxDB server

sinks/influxAsyncSink.md

@@ -18,6 +18,10 @@ The `influxasync` sink uses the official [InfluxDB golang client](https://pkg.go
     "organization": "myorg",
     "ssl": true,
     "batch_size": 200,
+    "retry_interval" : "1s",
+    "retry_exponential_base" : 2,
+    "max_retries": 20,
+    "max_retry_time" : "168h"
   }
 }
 ```
@@ -31,4 +35,10 @@ The `influxasync` sink uses the official [InfluxDB golang client](https://pkg.go
 - `password`: Password for basic authentification
 - `organization`: Organization in the InfluxDB
 - `ssl`: Use SSL connection
-- `batch_size`: batch up metrics internally, default 100
+- `batch_size`: batch up metrics internally, default 100
+- `retry_interval`: Base retry interval for failed write requests, default 1s
+- `retry_exponential_base`: The retry interval is exponentially increased with this base, default 2
+- `max_retries`: Maximal number of retry attempts
+- `max_retry_time`: Maximal time to retry failed writes, default 168h (one week)
+
+For information about the calculation of the retry interval settings, see [offical influxdb-client-go documentation](https://github.com/influxdata/influxdb-client-go#handling-of-failed-async-writes)

sinks/influxSink.go

@@ -6,54 +6,92 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
+	"sync"
+	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
 	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
+	"github.com/influxdata/influxdb-client-go/v2/api/write"
 )
 
-type InfluxSinkConfig struct {
-	defaultSinkConfig
-	Host         string `json:"host,omitempty"`
-	Port         string `json:"port,omitempty"`
-	Database     string `json:"database,omitempty"`
-	User         string `json:"user,omitempty"`
-	Password     string `json:"password,omitempty"`
-	Organization string `json:"organization,omitempty"`
-	SSL          bool   `json:"ssl,omitempty"`
-	RetentionPol string `json:"retention_policy,omitempty"`
-}
-
 type InfluxSink struct {
 	sink
 	client   influxdb2.Client
 	writeApi influxdb2Api.WriteAPIBlocking
-	config   InfluxSinkConfig
+	config   struct {
+		defaultSinkConfig
+		Host         string `json:"host,omitempty"`
+		Port         string `json:"port,omitempty"`
+		Database     string `json:"database,omitempty"`
+		User         string `json:"user,omitempty"`
+		Password     string `json:"password,omitempty"`
+		Organization string `json:"organization,omitempty"`
+		SSL          bool   `json:"ssl,omitempty"`
+		// Maximum number of points sent to server in single request.
+		// Default: 1000
+		BatchSize int `json:"batch_size,omitempty"`
+		// Time interval for delayed sending of metrics.
+		// If the buffers are already filled before the end of this interval,
+		// the metrics are sent without further delay.
+		// Default: 1s
+		FlushInterval string `json:"flush_delay,omitempty"`
+		// Number of metrics that are dropped when buffer is full
+		// Default: 100
+		DropRate int `json:"drop_rate,omitempty"`
+	}
+	batch           []*write.Point
+	flushTimer      *time.Timer
+	flushDelay      time.Duration
+	batchMutex      sync.Mutex // Flush() runs in another goroutine, so this lock has to protect the buffer
+	flushTimerMutex sync.Mutex // Ensure only one flush timer is running
 }
 
+// connect connects to the InfluxDB server
 func (s *InfluxSink) connect() error {
-	var auth string
+
+	// URI options:
+	// * http://host:port
+	// * https://host:port
 	var uri string
 	if s.config.SSL {
 		uri = fmt.Sprintf("https://%s:%s", s.config.Host, s.config.Port)
 	} else {
 		uri = fmt.Sprintf("http://%s:%s", s.config.Host, s.config.Port)
 	}
+
+	// Authentication options:
+	// * token
+	// * username:password
+	var auth string
 	if len(s.config.User) == 0 {
 		auth = s.config.Password
 	} else {
 		auth = fmt.Sprintf("%s:%s", s.config.User, s.config.Password)
 	}
-	cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
+	cclog.ComponentDebug(s.name,
+		"Using URI='"+uri+"'",
+		"Org='"+s.config.Organization+"'",
+		"Bucket='"+s.config.Database+"'")
+
+	// Set influxDB client options
 	clientOptions := influxdb2.DefaultOptions()
+
+	// Do not check InfluxDB certificate
 	clientOptions.SetTLSConfig(
 		&tls.Config{
 			InsecureSkipVerify: true,
 		},
 	)
+
+	clientOptions.SetPrecision(time.Second)
+
+	// Create new writeAPI
 	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
 	s.writeApi = s.client.WriteAPIBlocking(s.config.Organization, s.config.Database)
+
+	// Check InfluxDB server accessibility
 	ok, err := s.client.Ping(context.Background())
 	if err != nil {
 		return err
@@ -65,43 +103,163 @@ func (s *InfluxSink) connect() error {
 }
 
 func (s *InfluxSink) Write(m lp.CCMetric) error {
-	err :=
-		s.writeApi.WritePoint(
-			context.Background(),
-			m.ToPoint(s.config.MetaAsTags),
-		)
-	return err
+
+	if s.flushDelay != 0 && s.flushTimerMutex.TryLock() {
+		// Run a batched flush for all metrics that arrived in the last flush delay interval
+		cclog.ComponentDebug(s.name, "Starting new flush timer")
+		s.flushTimer = time.AfterFunc(
+			s.flushDelay,
+			func() {
+				defer s.flushTimerMutex.Unlock()
+				cclog.ComponentDebug(s.name, "Starting flush in flush timer")
+				if err := s.Flush(); err != nil {
+					cclog.ComponentError(s.name, "Flush timer: flush failed:", err)
+				}
+			})
+	}
+
+	// Lock access to batch slice
+	s.batchMutex.Lock()
+
+	// batch slice full, dropping oldest metric(s)
+	// e.g. when previous flushes failed and batch slice was not cleared
+	if len(s.batch) == s.config.BatchSize {
+		newSize := s.config.BatchSize - s.config.DropRate
+
+		for i := 0; i < newSize; i++ {
+			s.batch[i] = s.batch[i+s.config.DropRate]
+		}
+		for i := newSize; i < s.config.BatchSize; i++ {
+			s.batch[i] = nil
+		}
+		s.batch = s.batch[:newSize]
+		cclog.ComponentError(s.name, "Batch slice full, dropping", s.config.DropRate, "oldest metric(s)")
+	}
+
+	// Append metric to batch slice
+	p := m.ToPoint(s.meta_as_tags)
+	s.batch = append(s.batch, p)
+
+	// Flush synchronously if "flush_delay" is zero
+	// or
+	// Flush if batch size is reached
+	if s.flushDelay == 0 ||
+		len(s.batch) == s.config.BatchSize {
+		// Unlock access to batch slice
+		s.batchMutex.Unlock()
+		return s.Flush()
+	}
+
+	// Unlock access to batch slice
+	s.batchMutex.Unlock()
+	return nil
 }
 
+// Flush sends all metrics buffered in batch slice to InfluxDB server
 func (s *InfluxSink) Flush() error {
+	cclog.ComponentDebug(s.name, "Flushing")
+
+	// Lock access to batch slice
+	s.batchMutex.Lock()
+	defer s.batchMutex.Unlock()
+
+	// Nothing to do, batch slice is empty
+	if len(s.batch) == 0 {
+		return nil
+	}
+
+	// Send metrics from batch slice
+	err := s.writeApi.WritePoint(context.Background(), s.batch...)
+	if err != nil {
+		cclog.ComponentError(s.name, "Flush(): Flush of", len(s.batch), "metrics failed:", err)
+		return err
+	}
+
+	// Clear batch slice
+	for i := range s.batch {
+		s.batch[i] = nil
+	}
+	s.batch = s.batch[:0]
+
 	return nil
 }
 
 func (s *InfluxSink) Close() {
 	cclog.ComponentDebug(s.name, "Closing InfluxDB connection")
+	s.flushTimer.Stop()
+	s.Flush()
+	if err := s.Flush(); err != nil {
+		cclog.ComponentError(s.name, "Close(): Flush failed:", err)
+	}
 	s.client.Close()
 }
 
+// NewInfluxSink create a new InfluxDB sink
 func NewInfluxSink(name string, config json.RawMessage) (Sink, error) {
 	s := new(InfluxSink)
 	s.name = fmt.Sprintf("InfluxSink(%s)", name)
+
+	// Set config default values
+	s.config.BatchSize = 1000
+	s.config.FlushInterval = "1s"
+	s.config.DropRate = 100
+
+	// Read config
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &s.config)
 		if err != nil {
-			return nil, err
+			return s, err
 		}
 	}
-	if len(s.config.Host) == 0 ||
-		len(s.config.Port) == 0 ||
-		len(s.config.Database) == 0 ||
-		len(s.config.Organization) == 0 ||
-		len(s.config.Password) == 0 {
-		return nil, errors.New("not all configuration variables set required by InfluxSink")
+
+	if len(s.config.Host) == 0 {
+		return s, errors.New("Missing host configuration required by InfluxSink")
 	}
+	if len(s.config.Port) == 0 {
+		return s, errors.New("Missing port configuration required by InfluxSink")
+	}
+	if len(s.config.Database) == 0 {
+		return s, errors.New("Missing database configuration required by InfluxSink")
+	}
+	if len(s.config.Organization) == 0 {
+		return s, errors.New("Missing organization configuration required by InfluxSink")
+	}
+	if len(s.config.Password) == 0 {
+		return s, errors.New("Missing password configuration required by InfluxSink")
+	}
+
+	// Create lookup map to use meta infos as tags in the output metric
+	s.meta_as_tags = make(map[string]bool)
+	for _, k := range s.config.MetaAsTags {
+		s.meta_as_tags[k] = true
+	}
+
+	// Configure flush delay duration
+	if len(s.config.FlushInterval) > 0 {
+		t, err := time.ParseDuration(s.config.FlushInterval)
+		if err == nil {
+			s.flushDelay = t
+		}
+	}
+
+	if !(s.config.BatchSize > 0) {
+		return s, fmt.Errorf("batch_size=%d in InfluxDB config must be > 0", s.config.BatchSize)
+	}
+	if !(s.config.DropRate > 0) {
+		return s, fmt.Errorf("drop_rate=%d in InfluxDB config must be > 0", s.config.DropRate)
+	}
+	if !(s.config.BatchSize > s.config.DropRate) {
+		return s, fmt.Errorf(
+			"batch_size=%d must be greater then drop_rate=%d in InfluxDB config",
+			s.config.BatchSize, s.config.DropRate)
+	}
+
+	// allocate batch slice
+	s.batch = make([]*write.Point, 0, s.config.BatchSize)
 
 	// Connect to InfluxDB server
 	if err := s.connect(); err != nil {
-		return nil, fmt.Errorf("unable to connect: %v", err)
+		return s, fmt.Errorf("unable to connect: %v", err)
 	}
 	return s, nil
 }

sinks/influxSink.md

@@ -17,6 +17,8 @@ The `influxdb` sink uses the official [InfluxDB golang client](https://pkg.go.de
     "password" : "examplepw",
     "organization": "myorg",
     "ssl": true,
+    "flush_delay" : "1s",
+    "batch_size" : 100
   }
 }
 ```
@@ -29,4 +31,7 @@ The `influxdb` sink uses the official [InfluxDB golang client](https://pkg.go.de
 - `user`: Username for basic authentification
 - `password`: Password for basic authentification
 - `organization`: Organization in the InfluxDB
-- `ssl`: Use SSL connection
+- `ssl`: Use SSL connection
+- `flush_delay`: Group metrics coming in to a single batch
+- `batch_size`: Maximal batch size
+

sinks/libgangliaSink.go

@@ -71,8 +71,8 @@ import (
 	"fmt"
 	"unsafe"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"github.com/NVIDIA/go-nvml/pkg/dl"
 )
 
@@ -124,24 +124,21 @@ func (s *LibgangliaSink) Write(point lp.CCMetric) error {
 		return s.cstrCache[key]
 	}
 
-	// Get metric name
-	metricname := GangliaMetricRename(point.Name())
-
 	conf := GetCommonGangliaConfig(point)
 	if len(conf.Type) == 0 {
 		conf = GetGangliaConfig(point)
 	}
 	if len(conf.Type) == 0 {
-		return fmt.Errorf("metric %s has no 'value' field", metricname)
+		return fmt.Errorf("metric %q (Ganglia name %q) has no 'value' field", point.Name(), conf.Name)
 	}
 
 	if s.config.AddTypeToName {
-		metricname = GangliaMetricName(point)
+		conf.Name = GangliaMetricName(point)
 	}
 
 	c_value = C.CString(conf.Value)
 	c_type = lookup(conf.Type)
-	c_name = lookup(metricname)
+	c_name = lookup(conf.Name)
 
 	// Add unit
 	unit := ""