Numastats: Read in config and send abs values by default. Fixes #146

* Add energy metrics from NVML to Nvidia NVML collector

* Add energy metrics to Nvidia collector README

.github/ci-config.json

@@ -1,8 +1,10 @@
 {
-  "sinks": ".github/ci-sinks.json",
-  "collectors" : ".github/ci-collectors.json",
-  "receivers" : ".github/ci-receivers.json",
-  "router" : ".github/ci-router.json",
-  "interval": "5s",
-  "duration": "1s"
+  "sinks-file": ".github/ci-sinks.json",
+  "collectors-file" : ".github/ci-collectors.json",
+  "receivers-file" : ".github/ci-receivers.json",
+  "router-file" : ".github/ci-router.json",
+  "main" : {
+    "interval": "5s",
+    "duration": "1s"
+  }
 }

.github/workflows/Release.yml

@@ -8,16 +8,17 @@ on:
  push:
   tags:
   - '**'
+ workflow_dispatch:
 
 jobs:
 
   #
-  # Build on AlmaLinux 8.5 using go-toolset
+  # Build on AlmaLinux 8 using go-toolset
   #
-  AlmaLinux-RPM-build:
+  AlmaLinux8-RPM-build:
     runs-on: ubuntu-latest
     # See: https://hub.docker.com/_/almalinux
-    container: almalinux:8.5
+    container: almalinux:8
     # The job outputs link to the outputs of the 'rpmrename' step
     # Only job outputs can be used in child jobs
     outputs:
@@ -27,64 +28,154 @@ jobs:
 
     # Use dnf to install development packages
     - name: Install development packages
-      run: dnf --assumeyes group install "Development Tools" "RPM Development Tools"
+      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
+      uses: actions/checkout@v4
       with:
         submodules: recursive
         fetch-depth: 0
 
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
+    # - name: Setup Golang
+    #   uses: actions/setup-go@v5
+    #   with:
+    #     go-version: 'stable'
+    - name: Setup Golang
       run: |
-        dnf --assumeyes install 'dnf-command(builddep)'
-        dnf --assumeyes install which
-        dnf --assumeyes builddep scripts/cc-metric-collector.spec
+          dnf --assumeyes --disableplugin=subscription-manager install \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/go-toolset-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-bin-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-src-1.22.9-1.module_el8.10.0+3938+8c723e16.noarch.rpm
 
     - name: RPM build MetricCollector
       id: rpmbuild
-      run: make RPM
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make RPM
 
-    # AlmaLinux 8.5 is a derivate of RedHat Enterprise Linux 8 (UBI8),
+    # AlmaLinux 8 is a derivate of RedHat Enterprise Linux 8 (UBI8),
     # so the created RPM both contain the substring 'el8' in the RPM file names
-    # This step replaces the substring 'el8' to 'alma85'. It uses the move operation
-    # because it is unclear whether the default AlmaLinux 8.5 container contains the 
+    # This step replaces the substring 'el8' to 'alma8'. It uses the move operation
+    # because it is unclear whether the default AlmaLinux 8 container contains the
     # 'rename' command. This way we also get the new names for output.
-    - name: Rename RPMs (s/el8/alma85/)
+    - name: Rename RPMs (s/el8/alma8/)
       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}
+        NEW_RPM="${OLD_RPM/el8/alma8}"
+        NEW_SRPM=${OLD_SRPM/el8/alma8}
         mv "${OLD_RPM}" "${NEW_RPM}"
         mv "${OLD_SRPM}" "${NEW_SRPM}"
-        echo "::set-output name=SRPM::${NEW_SRPM}"
-        echo "::set-output name=RPM::${NEW_RPM}"
+        echo "SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT
+        echo "RPM=${NEW_RPM}" >> $GITHUB_OUTPUT
 
     # See: https://github.com/actions/upload-artifact
     - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
-        name: cc-metric-collector RPM for AlmaLinux 8.5
+        name: cc-metric-collector RPM for AlmaLinux 8
         path: ${{ steps.rpmrename.outputs.RPM }}
+        overwrite: true
     - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
-        name: cc-metric-collector SRPM for AlmaLinux 8.5
+        name: cc-metric-collector SRPM for AlmaLinux 8
         path: ${{ steps.rpmrename.outputs.SRPM }}
+        overwrite: true
+
+  #
+  # Build on AlmaLinux 9 using go-toolset
+  #
+  AlmaLinux9-RPM-build:
+    runs-on: ubuntu-latest
+    # See: https://hub.docker.com/_/almalinux
+    container: almalinux:9
+    # 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@v4
+      with:
+        submodules: recursive
+        fetch-depth: 0
+
+    # - name: Setup Golang
+    #   uses: actions/setup-go@v5
+    #   with:
+    #     go-version: 'stable'
+    - name: Setup Golang
+      run: |
+          dnf --assumeyes --disableplugin=subscription-manager install \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/go-toolset-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-bin-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-src-1.22.7-2.el9_5.noarch.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-race-1.22.7-2.el9_5.x86_64.rpm
+
+    - name: RPM build MetricCollector
+      id: rpmbuild
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make RPM
+
+    # AlmaLinux 9 is a derivate of RedHat Enterprise Linux 8 (UBI8),
+    # so the created RPM both contain the substring 'el9' in the RPM file names
+    # This step replaces the substring 'el8' to 'alma8'. It uses the move operation
+    # because it is unclear whether the default AlmaLinux 8 container contains the
+    # 'rename' command. This way we also get the new names for output.
+    - name: Rename RPMs (s/el9/alma9/)
+      id: rpmrename
+      run: |
+        OLD_RPM="${{steps.rpmbuild.outputs.RPM}}"
+        OLD_SRPM="${{steps.rpmbuild.outputs.SRPM}}"
+        NEW_RPM="${OLD_RPM/el9/alma9}"
+        NEW_SRPM=${OLD_SRPM/el9/alma9}
+        mv "${OLD_RPM}" "${NEW_RPM}"
+        mv "${OLD_SRPM}" "${NEW_SRPM}"
+        echo "SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT
+        echo "RPM=${NEW_RPM}" >> $GITHUB_OUTPUT
+
+    # See: https://github.com/actions/upload-artifact
+    - name: Save RPM as artifact
+      uses: actions/upload-artifact@v4
+      with:
+        name: cc-metric-collector RPM for AlmaLinux 9
+        path: ${{ steps.rpmrename.outputs.RPM }}
+        overwrite: true
+    - name: Save SRPM as artifact
+      uses: actions/upload-artifact@v4
+      with:
+        name: cc-metric-collector SRPM for AlmaLinux 9
+        path: ${{ steps.rpmrename.outputs.SRPM }}
+        overwrite: true
 
   #
   # 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
+    # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c35984d70cc534b3a3784e?container-tabs=gti
+    container: registry.access.redhat.com/ubi8/ubi:8.8-1032.1692772289
     # The job outputs link to the outputs of the 'rpmbuild' step
     outputs:
       rpm : ${{steps.rpmbuild.outputs.RPM}}
@@ -93,36 +184,210 @@ jobs:
 
     # Use dnf to install development packages
     - name: Install development packages
-      run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros rpm-build-libs rpm-libs gcc make python38 git
+      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
+      uses: actions/checkout@v4
       with:
         submodules: recursive
         fetch-depth: 0
 
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: dnf --assumeyes --disableplugin=subscription-manager builddep scripts/cc-metric-collector.spec
+    # - name: Setup Golang
+    #   uses: actions/setup-go@v5
+    #   with:
+    #     go-version: 'stable'
+    - name: Setup Golang
+      run: |
+          dnf --assumeyes --disableplugin=subscription-manager install \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/go-toolset-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-bin-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-src-1.22.9-1.module_el8.10.0+3938+8c723e16.noarch.rpm
 
     - name: RPM build MetricCollector
       id: rpmbuild
-      run: make RPM
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make RPM
 
     # See: https://github.com/actions/upload-artifact
     - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: cc-metric-collector RPM for UBI 8
         path: ${{ steps.rpmbuild.outputs.RPM }}
+        overwrite: true
     - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v2
+      uses: actions/upload-artifact@v4
       with:
         name: cc-metric-collector SRPM for UBI 8
         path: ${{ steps.rpmbuild.outputs.SRPM }}
+        overwrite: true
+
+  #
+  # Build on UBI 9 using go-toolset
+  #
+  UBI-9-RPM-build:
+    runs-on: ubuntu-latest
+    # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
+    container: redhat/ubi9
+    # The job outputs link to the outputs of the 'rpmbuild' step
+    # 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 gcc make python39 git wget openssl-devel diffutils delve 
+
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        submodules: recursive
+        fetch-depth: 0
+
+    # See: https://github.com/marketplace/actions/setup-go-environment
+    # - name: Setup Golang
+    #   uses: actions/setup-go@v5
+    #   with:
+    #     go-version: 'stable'
+    - name: Setup Golang
+      run: |
+          dnf --assumeyes --disableplugin=subscription-manager install \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/go-toolset-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-bin-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-src-1.22.7-2.el9_5.noarch.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-race-1.22.7-2.el9_5.x86_64.rpm
+
+    - name: RPM build MetricCollector
+      id: rpmbuild
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make RPM
+
+    # See: https://github.com/actions/upload-artifact
+    - name: Save RPM as artifact
+      uses: actions/upload-artifact@v4
+      with:
+        name: cc-metric-collector RPM for UBI 9
+        path: ${{ steps.rpmbuild.outputs.RPM }}
+        overwrite: true
+    - name: Save SRPM as artifact
+      uses: actions/upload-artifact@v4
+      with:
+        name: cc-metric-collector SRPM for UBI 9
+        path: ${{ steps.rpmbuild.outputs.SRPM }}
+        overwrite: true
+
+  #
+  # Build on Ubuntu 22.04 using official go package
+  #
+  Ubuntu-jammy-build:
+    runs-on: ubuntu-latest
+    container: ubuntu:22.04
+    # The job outputs link to the outputs of the 'debrename' step
+    # Only job outputs can be used in child jobs
+    outputs:
+      deb : ${{steps.debrename.outputs.DEB}}
+    steps:
+    # Use apt to install development packages
+    - name: Install development packages
+      run: |
+          apt update && apt --assume-yes upgrade
+          apt --assume-yes install build-essential sed git wget bash
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        submodules: recursive
+        fetch-depth: 0
+
+    - name: Setup Golang
+      uses: actions/setup-go@v5
+      with:
+        go-version: 'stable'
+
+    - name: DEB build MetricCollector
+      id: dpkg-build
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make DEB
+    - name: Rename DEB (add '_ubuntu22.04')
+      id: debrename
+      run: |
+        OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev)
+        NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu22.04.deb"
+        mv "${{steps.dpkg-build.outputs.DEB}}" "${NEW_DEB_FILE}"
+        echo "DEB=${NEW_DEB_FILE}" >> $GITHUB_OUTPUT
+    # See: https://github.com/actions/upload-artifact
+    - name: Save DEB as artifact
+      uses: actions/upload-artifact@v4
+      with:
+        name: cc-metric-collector DEB for Ubuntu 22.04
+        path: ${{ steps.debrename.outputs.DEB }}
+        overwrite: true
+
+ #
+  # Build on Ubuntu 24.04 using official go package
+  #
+  Ubuntu-noblenumbat-build:
+    runs-on: ubuntu-latest
+    container: ubuntu:24.04
+    # The job outputs link to the outputs of the 'debrename' step
+    # Only job outputs can be used in child jobs
+    outputs:
+      deb : ${{steps.debrename.outputs.DEB}}
+    steps:
+    # Use apt to install development packages
+    - name: Install development packages
+      run: |
+          apt update && apt --assume-yes upgrade
+          apt --assume-yes install build-essential sed git wget bash
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        submodules: recursive
+        fetch-depth: 0
+
+    - name: Setup Golang
+      uses: actions/setup-go@v5
+      with:
+        go-version: 'stable'
+
+    - name: DEB build MetricCollector
+      id: dpkg-build
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make DEB
+    - name: Rename DEB (add '_ubuntu24.04')
+      id: debrename
+      run: |
+        OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev)
+        NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu24.04.deb"
+        mv "${{steps.dpkg-build.outputs.DEB}}" "${NEW_DEB_FILE}"
+        echo "DEB=${NEW_DEB_FILE}" >> $GITHUB_OUTPUT
+    # See: https://github.com/actions/upload-artifact
+    - name: Save DEB as artifact
+      uses: actions/upload-artifact@v4
+      with:
+        name: cc-metric-collector DEB for Ubuntu 24.04
+        path: ${{ steps.debrename.outputs.DEB }}
+        overwrite: true
+
 
   #
   # Create release with fresh RPMs
@@ -130,28 +395,56 @@ jobs:
   Release:
     runs-on: ubuntu-latest
     # We need the RPMs, so add dependency
-    needs: [AlmaLinux-RPM-build, UBI-8-RPM-build]
+    needs: [AlmaLinux8-RPM-build, AlmaLinux9-RPM-build, UBI-8-RPM-build, UBI-9-RPM-build, Ubuntu-jammy-build, Ubuntu-noblenumbat-build]
 
     steps:
     # See: https://github.com/actions/download-artifact
-    - name: Download AlmaLinux 8.5 RPM
-      uses: actions/download-artifact@v2
+    - name: Download AlmaLinux 8 RPM
+      uses: actions/download-artifact@v4
       with:
-        name: cc-metric-collector RPM for AlmaLinux 8.5
-    - name: Download AlmaLinux 8.5 SRPM
-      uses: actions/download-artifact@v2
+        name: cc-metric-collector RPM for AlmaLinux 8
+    - name: Download AlmaLinux 8 SRPM
+      uses: actions/download-artifact@v4
       with:
-        name: cc-metric-collector SRPM for AlmaLinux 8.5
-    
+        name: cc-metric-collector SRPM for AlmaLinux 8
+
+    - name: Download AlmaLinux 9 RPM
+      uses: actions/download-artifact@v4
+      with:
+        name: cc-metric-collector RPM for AlmaLinux 9
+    - name: Download AlmaLinux 9 SRPM
+      uses: actions/download-artifact@v4
+      with:
+        name: cc-metric-collector SRPM for AlmaLinux 9
+
     - name: Download UBI 8 RPM
-      uses: actions/download-artifact@v2
+      uses: actions/download-artifact@v4
       with:
         name: cc-metric-collector RPM for UBI 8
     - name: Download UBI 8 SRPM
-      uses: actions/download-artifact@v2
+      uses: actions/download-artifact@v4
       with:
         name: cc-metric-collector SRPM for UBI 8
 
+    - name: Download UBI 9 RPM
+      uses: actions/download-artifact@v4
+      with:
+        name: cc-metric-collector RPM for UBI 9
+    - name: Download UBI 9 SRPM
+      uses: actions/download-artifact@v4
+      with:
+        name: cc-metric-collector SRPM for UBI 9
+
+    - name: Download Ubuntu 22.04 DEB
+      uses: actions/download-artifact@v4
+      with:
+        name: cc-metric-collector DEB for Ubuntu 22.04
+
+    - name: Download Ubuntu 24.04 DEB
+      uses: actions/download-artifact@v4
+      with:
+        name: cc-metric-collector DEB for Ubuntu 24.04
+
     # 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.
@@ -161,27 +454,51 @@ jobs:
     - 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}}")
+        ALMA_8_RPM=$(basename "${{ needs.AlmaLinux8-RPM-build.outputs.rpm}}")
+        ALMA_8_SRPM=$(basename "${{ needs.AlmaLinux8-RPM-build.outputs.srpm}}")
+        ALMA_9_RPM=$(basename "${{ needs.AlmaLinux9-RPM-build.outputs.rpm}}")
+        ALMA_9_SRPM=$(basename "${{ needs.AlmaLinux9-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}}")
-        echo "ALMA_85_RPM::${ALMA_85_RPM}"
-        echo "ALMA_85_SRPM::${ALMA_85_SRPM}"
+        UBI_9_RPM=$(basename "${{ needs.UBI-9-RPM-build.outputs.rpm}}")
+        UBI_9_SRPM=$(basename "${{ needs.UBI-9-RPM-build.outputs.srpm}}")
+        U_2204_DEB=$(basename "${{ needs.Ubuntu-jammy-build.outputs.deb}}")
+        U_2404_DEB=$(basename "${{ needs.Ubuntu-noblenumbat-build.outputs.deb}}")
+        echo "ALMA_8_RPM::${ALMA_8_RPM}"
+        echo "ALMA_8_SRPM::${ALMA_8_SRPM}"
+        echo "ALMA_9_RPM::${ALMA_9_RPM}"
+        echo "ALMA_9_SRPM::${ALMA_9_SRPM}"
         echo "UBI_8_RPM::${UBI_8_RPM}"
         echo "UBI_8_SRPM::${UBI_8_SRPM}"
-        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 "UBI_9_RPM::${UBI_9_RPM}"
+        echo "UBI_9_SRPM::${UBI_9_SRPM}"
+        echo "U_2204_DEB::${U_2204_DEB}"
+        echo "U_2404_DEB::${U_2404_DEB}"
+        echo "ALMA_8_RPM=${ALMA_8_RPM}" >> $GITHUB_OUTPUT
+        echo "ALMA_8_SRPM=${ALMA_8_SRPM}" >> $GITHUB_OUTPUT
+        echo "ALMA_9_RPM=${ALMA_9_RPM}" >> $GITHUB_OUTPUT
+        echo "ALMA_9_SRPM=${ALMA_9_SRPM}" >> $GITHUB_OUTPUT
+        echo "UBI_8_RPM=${UBI_8_RPM}" >> $GITHUB_OUTPUT
+        echo "UBI_8_SRPM=${UBI_8_SRPM}" >> $GITHUB_OUTPUT
+        echo "UBI_9_RPM=${UBI_9_RPM}" >> $GITHUB_OUTPUT
+        echo "UBI_9_SRPM=${UBI_9_SRPM}" >> $GITHUB_OUTPUT
+        echo "U_2204_DEB=${U_2204_DEB}" >> $GITHUB_OUTPUT
+        echo "U_2404_DEB=${U_2404_DEB}" >> $GITHUB_OUTPUT
 
     # See: https://github.com/softprops/action-gh-release
     - name: Release
-      uses: softprops/action-gh-release@v1
+      uses: softprops/action-gh-release@v2
       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.ALMA_8_RPM }}
+         ${{ steps.files.outputs.ALMA_8_SRPM }}
+         ${{ steps.files.outputs.ALMA_9_RPM }}
+         ${{ steps.files.outputs.ALMA_9_SRPM }}
          ${{ steps.files.outputs.UBI_8_RPM }}
          ${{ steps.files.outputs.UBI_8_SRPM }}
+         ${{ steps.files.outputs.UBI_9_RPM }}
+         ${{ steps.files.outputs.UBI_9_SRPM }}
+         ${{ steps.files.outputs.U_2204_DEB }}
+         ${{ steps.files.outputs.U_2404_DEB }}

.github/workflows/runonce.yml

@@ -4,28 +4,32 @@
 name: Run Test
 
 # Run on event push
-on: push
+on:
+  push:
+  workflow_dispatch:
 
 jobs:
+
   #
-  # Job build-1-18
-  # Build on latest Ubuntu using golang version 1.18
+  # Job build-latest
+  # Build on latest Ubuntu using latest golang version
   #
-  build-1-18:
+  build-latest:
     runs-on: ubuntu-latest
     steps:
     # See: https://github.com/marketplace/actions/checkout
     # Checkout git repository and submodules
     - name: Checkout
-      uses: actions/checkout@v2
+      uses: actions/checkout@v4
       with:
         submodules: recursive
 
     # See: https://github.com/marketplace/actions/setup-go-environment
     - name: Setup Golang
-      uses: actions/setup-go@v3
+      uses: actions/setup-go@v5
       with:
-        go-version: '1.18.2'
+        go-version: '1.21'
+        check-latest: true
 
     - name: Build MetricCollector
       run: make
@@ -34,53 +38,246 @@ jobs:
       run: ./cc-metric-collector --once --config .github/ci-config.json
 
   #
-  # Job build-1-17
-  # Build on latest Ubuntu using golang version 1.17 
+  # Build on AlmaLinux 8
   #
-  build-1-17:
+  AlmaLinux8-RPM-build:
     runs-on: ubuntu-latest
+    # See: https://hub.docker.com/_/almalinux
+    container: almalinux:8
+    # The job outputs link to the outputs of the 'rpmrename' step
+    # Only job outputs can be used in child jobs
     steps:
-    # See: https://github.com/marketplace/actions/checkout
+
+    # 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
+      uses: actions/checkout@v4
       with:
         submodules: recursive
+        fetch-depth: 0
 
     # See: https://github.com/marketplace/actions/setup-go-environment
+    # - name: Setup Golang
+    #   uses: actions/setup-go@v5
+    #   with:
+    #     go-version: 'stable'
     - name: Setup Golang
-      uses: actions/setup-go@v3
-      with:
-        go-version: '1.17.7'
+      run: |
+          dnf --assumeyes --disableplugin=subscription-manager install \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/go-toolset-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-bin-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-src-1.22.9-1.module_el8.10.0+3938+8c723e16.noarch.rpm
 
-    - name: Build MetricCollector
-      run: make
-
-    - name: Run MetricCollector once
-      run: ./cc-metric-collector --once --config .github/ci-config.json
+    - name: RPM build MetricCollector
+      id: rpmbuild
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make RPM
 
   #
-  # Job build-1-16
-  # Build on latest Ubuntu using golang version 1.16
+  # Build on AlmaLinux 9
   #
-  build-1-16:
+  AlmaLinux9-RPM-build:
     runs-on: ubuntu-latest
+    # See: https://hub.docker.com/_/almalinux
+    container: almalinux:9
+    # The job outputs link to the outputs of the 'rpmrename' step
+    # Only job outputs can be used in child jobs
     steps:
-    # See: https://github.com/marketplace/actions/checkout
+
+    # 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
+      uses: actions/checkout@v4
       with:
         submodules: recursive
+        fetch-depth: 0
 
     # See: https://github.com/marketplace/actions/setup-go-environment
+    # - name: Setup Golang
+    #   uses: actions/setup-go@v5
+    #   with:
+    #     go-version: 'stable'
     - name: Setup Golang
-      uses: actions/setup-go@v3
+      run: |
+          dnf --assumeyes --disableplugin=subscription-manager install \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/go-toolset-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-bin-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-src-1.22.7-2.el9_5.noarch.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-race-1.22.7-2.el9_5.x86_64.rpm
+
+    - name: RPM build MetricCollector
+      id: rpmbuild
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make RPM
+
+
+  #
+  # Build on UBI 8 using go-toolset
+  #
+  UBI-8-RPM-build:
+    runs-on: ubuntu-latest
+    # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
+    container: redhat/ubi8
+    # The job outputs link to the outputs of the 'rpmbuild' step
+    steps:
+
+    # Use dnf to install development packages
+    - name: Install development packages
+      run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros rpm-build-libs rpm-libs gcc make python38 git wget openssl-devel diffutils delve which
+
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v4
       with:
-        go-version: '1.16.7' # The version AlmaLinux 8.5 uses
+        submodules: recursive
+        fetch-depth: 0
 
-    - name: Build MetricCollector
-      run: make
+    # See: https://github.com/marketplace/actions/setup-go-environment
+    # - name: Setup Golang
+    #   uses: actions/setup-go@v5
+    #   with:
+    #     go-version: 'stable'
+    - name: Setup Golang
+      run: |
+          dnf --assumeyes --disableplugin=subscription-manager install \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/go-toolset-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-bin-1.22.9-1.module_el8.10.0+3938+8c723e16.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/8/AppStream/x86_64/os/Packages/golang-src-1.22.9-1.module_el8.10.0+3938+8c723e16.noarch.rpm
 
-    - name: Run MetricCollector once
-      run: ./cc-metric-collector --once --config .github/ci-config.json
+    - name: RPM build MetricCollector
+      id: rpmbuild
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make RPM
+
+  #
+  # Build on UBI 9 using go-toolset
+  #
+  UBI-9-RPM-build:
+    runs-on: ubuntu-latest
+    # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
+    container: redhat/ubi9
+    # The job outputs link to the outputs of the 'rpmbuild' step
+    steps:
+
+    # Use dnf to install development packages
+    - name: Install development packages
+      run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros gcc make python39 git wget openssl-devel diffutils delve
+
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        submodules: recursive
+        fetch-depth: 0
+
+    # See: https://github.com/marketplace/actions/setup-go-environment
+    # - name: Setup Golang
+    #   uses: actions/setup-go@v5
+    #   with:
+    #     go-version: 'stable'
+    - name: Setup Golang
+      run: |
+          dnf --assumeyes --disableplugin=subscription-manager install \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/go-toolset-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-bin-1.22.7-2.el9_5.x86_64.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-src-1.22.7-2.el9_5.noarch.rpm \
+              https://repo.almalinux.org/almalinux/9/AppStream/x86_64/os/Packages/golang-race-1.22.7-2.el9_5.x86_64.rpm
+
+    - name: RPM build MetricCollector
+      id: rpmbuild
+      run: |
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
+          make RPM
+
+  #
+  # Build on Ubuntu 22.04 using official go package
+  #
+  Ubuntu-jammy-build:
+    runs-on: ubuntu-latest
+    container: ubuntu:22.04
+
+    steps:
+    # Use apt to install development packages
+    - name: Install development packages
+      run: |
+          apt update && apt --assume-yes upgrade
+          apt --assume-yes install build-essential sed git wget bash
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        submodules: recursive
+        fetch-depth: 0
+    # Use official golang package
+    # See: https://github.com/marketplace/actions/setup-go-environment
+    - name: Setup Golang
+      uses: actions/setup-go@v5
+      with:
+        go-version: 'stable'
+
+    - name: DEB build MetricCollector
+      id: dpkg-build
+      run: |
+          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
+          make DEB
+
+  #
+  # Build on Ubuntu 24.04 using official go package
+  #
+  Ubuntu-noblenumbat-build:
+    runs-on: ubuntu-latest
+    container: ubuntu:24.04
+
+    steps:
+    # Use apt to install development packages
+    - name: Install development packages
+      run: |
+          apt update && apt --assume-yes upgrade
+          apt --assume-yes install build-essential sed git wget bash
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        submodules: recursive
+        fetch-depth: 0
+    # Use official golang package
+    # See: https://github.com/marketplace/actions/setup-go-environment
+    - name: Setup Golang
+      uses: actions/setup-go@v5
+      with:
+        go-version: 'stable'
+
+    - name: DEB build MetricCollector
+      id: dpkg-build
+      run: |
+          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
+          make DEB

.zenodo.json

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

Makefile

@@ -22,14 +22,7 @@ GOBIN = $(shell which go)
 .PHONY: all
 all: $(APP)
 
-$(APP): $(GOSRC)
-	if [ "$(shell $(GOBIN) version | cut -d' ' -f 3 | cut -d '.' -f1-2)" = "go1.16" ]; then \
-		echo "1.16"; \
-		cp go.mod.1.16 go.mod; \
-	else \
-		echo "1.17+"; \
-		cp go.mod.1.17+ go.mod; \
-	fi
+$(APP): $(GOSRC) go.mod
 	make -C collectors
 	$(GOBIN) get
 	$(GOBIN) build -o $(APP) $(GOSRC_APP)
@@ -91,7 +84,7 @@ RPM: scripts/cc-metric-collector.spec
 	@COMMITISH="HEAD"
 	@VERS=$$(git describe --tags $${COMMITISH})
 	@VERS=$${VERS#v}
-	@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
+	@VERS=$$(echo $${VERS} | sed -e s+'-'+'_'+g)
 	@eval $$(rpmspec --query --queryformat "NAME='%{name}' VERSION='%{version}' RELEASE='%{release}' NVR='%{NVR}' NVRA='%{NVRA}'" --define="VERS $${VERS}" "$${SPECFILE}")
 	@PREFIX="$${NAME}-$${VERSION}"
 	@FORMAT="tar.gz"
@@ -103,10 +96,8 @@ RPM: scripts/cc-metric-collector.spec
 	@if [[ "$${GITHUB_ACTIONS}" == true ]]; then
 	@     RPMFILE="$${RPMDIR}/$${ARCH}/$${NVRA}.rpm"
 	@     SRPMFILE="$${SRPMDIR}/$${NVR}.src.rpm"
-	@     echo "RPM: $${RPMFILE}"
-	@     echo "SRPM: $${SRPMFILE}"
-	@     echo "::set-output name=SRPM::$${SRPMFILE}"
-	@     echo "::set-output name=RPM::$${RPMFILE}"
+	@     echo "SRPM=$${SRPMFILE}" >> $${GITHUB_OUTPUT}
+	@     echo "RPM=$${RPMFILE}" >> $${GITHUB_OUTPUT}
 	@fi
 
 .PHONY: DEB
@@ -115,21 +106,24 @@ DEB: scripts/cc-metric-collector.deb.control $(APP)
 	@WORKSPACE=$${PWD}/.dpkgbuild
 	@DEBIANDIR=$${WORKSPACE}/debian
 	@DEBIANBINDIR=$${WORKSPACE}/DEBIAN
-	@mkdir --parents --verbose $$WORKSPACE $$DEBIANBINDIR
+	@mkdir --parents --verbose $${WORKSPACE} $${DEBIANBINDIR}
 	#@mkdir --parents --verbose $$DEBIANDIR
 	@CONTROLFILE="$${BASEDIR}/scripts/cc-metric-collector.deb.control"
 	@COMMITISH="HEAD"
 	@VERS=$$(git describe --tags --abbrev=0 $${COMMITISH})
+	@if [ -z "$${VERS}" ]; then VERS=${GITHUB_REF_NAME}; fi
 	@VERS=$${VERS#v}
-	@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
 	@ARCH=$$(uname -m)
-	@ARCH=$$(echo $$ARCH | sed -e s+'_'+'-'+g)
+	@ARCH=$$(echo $${ARCH} | sed -e s+'_'+'-'+g)
+	@if [ "$${ARCH}" = "x86-64" ]; then ARCH=amd64; fi
 	@PREFIX="$${NAME}-$${VERSION}_$${ARCH}"
-	@SIZE_BYTES=$$(du -bcs --exclude=.dpkgbuild "$$WORKSPACE"/ | awk '{print $$1}' | head -1 | sed -e 's/^0\+//')
-	@SIZE="$$(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
+	@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} > $${DEBIANBINDIR}/control
 	@make PREFIX=$${WORKSPACE} install
 	@DEB_FILE="cc-metric-collector_$${VERS}_$${ARCH}.deb"
-	@dpkg-deb -b $${WORKSPACE} "$$DEB_FILE"
+	@dpkg-deb -b $${WORKSPACE} "$${DEB_FILE}"
+	@if [ "$${GITHUB_ACTIONS}" = "true" ]; then
+	@     echo "DEB=$${DEB_FILE}" >> $${GITHUB_OUTPUT}
+	@fi
 	@rm -r "$${WORKSPACE}"

README.md

@@ -1,5 +1,17 @@
+<!--
+---
+title: cc-metric-collector
+description: Metric collecting node agent
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/_index.md
+---
+-->
+
 # 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](https://clustercockpit.org/docs/overview/).
 
 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).
 
@@ -7,10 +19,14 @@ There is a single timer loop that triggers all collectors serially, collects the
 
 The receiver runs as a go routine side-by-side with the timer loop and asynchronously forwards received metrics to the sink.
 
+
+[![DOI](https://zenodo.org/badge/DOI/10.5281/zenodo.7438287.svg)](https://doi.org/10.5281/zenodo.7438287)
+
+
 # Configuration
 
 Configuration is implemented using a single json document that is distributed over network and may be persisted as file.
-Supported metrics are documented [here](https://github.com/ClusterCockpit/cc-specifications/blob/master/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.
 
@@ -20,19 +36,19 @@ 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)
 
+* [`collectors`](./collectors/README.md)
+* [`sinks`](https://github.com/ClusterCockpit/cc-lib/blob/main/sinks/README.md)
+* [`receivers`](https://github.com/ClusterCockpit/cc-lib/blob/main/receivers/README.md)
+* [`router`](./internal/metricRouter/README.md)
 
 # Installation
 
@@ -43,6 +59,7 @@ $ go get (requires at least golang 1.16)
 $ make
 ```
 
+For more information, see [here](./docs/building.md).
 
 # Running
 
@@ -56,6 +73,7 @@ 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 +111,12 @@ 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

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package main
 
 import (
@@ -7,39 +14,24 @@ import (
 	"os/signal"
 	"syscall"
 
+	"github.com/ClusterCockpit/cc-lib/receivers"
+	"github.com/ClusterCockpit/cc-lib/sinks"
 	"github.com/ClusterCockpit/cc-metric-collector/collectors"
-	"github.com/ClusterCockpit/cc-metric-collector/receivers"
-	"github.com/ClusterCockpit/cc-metric-collector/sinks"
 
 	//	"strings"
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	ccconf "github.com/ClusterCockpit/cc-lib/ccConfig"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 	mr "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
-	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
+	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 type CentralConfigFile struct {
-	Interval            string `json:"interval"`
-	Duration            string `json:"duration"`
-	CollectorConfigFile string `json:"collectors"`
-	RouterConfigFile    string `json:"router"`
-	SinkConfigFile      string `json:"sinks"`
-	ReceiverConfigFile  string `json:"receivers,omitempty"`
-}
-
-func LoadCentralConfiguration(file string, config *CentralConfigFile) error {
-	configFile, err := os.Open(file)
-	if err != nil {
-		cclog.Error(err.Error())
-		return err
-	}
-	defer configFile.Close()
-	jsonParser := json.NewDecoder(configFile)
-	err = jsonParser.Decode(config)
-	return err
+	Interval string `json:"interval"`
+	Duration string `json:"duration"`
 }
 
 type RuntimeConfig struct {
@@ -54,7 +46,7 @@ type RuntimeConfig struct {
 	ReceiveManager  receivers.ReceiveManager
 	MultiChanTicker mct.MultiChanTicker
 
-	Channels []chan lp.CCMetric
+	Channels []chan lp.CCMessage
 	Sync     sync.WaitGroup
 }
 
@@ -87,7 +79,7 @@ func ReadCli() map[string]string {
 	cfg := flag.String("config", "./config.json", "Path to configuration file")
 	logfile := flag.String("log", "stderr", "Path for logfile")
 	once := flag.Bool("once", false, "Run all collectors only once")
-	debug := flag.Bool("debug", false, "Activate debug output")
+	loglevel := flag.String("loglevel", "info", "Set log level")
 	flag.Parse()
 	m = make(map[string]string)
 	m["configfile"] = *cfg
@@ -97,12 +89,7 @@ func ReadCli() map[string]string {
 	} else {
 		m["once"] = "false"
 	}
-	if *debug {
-		m["debug"] = "true"
-		cclog.SetDebug()
-	} else {
-		m["debug"] = "false"
-	}
+	m["loglevel"] = *loglevel
 	return m
 }
 
@@ -167,8 +154,15 @@ func mainFunc() int {
 		CliArgs:        ReadCli(),
 	}
 
+	// Set loglevel based on command line input.
+	cclog.Init(rcfg.CliArgs["loglevel"], false)
+
+	// Init ccConfig with configuration file
+	ccconf.Init(rcfg.CliArgs["configfile"])
+
 	// Load and check configuration
-	err = LoadCentralConfiguration(rcfg.CliArgs["configfile"], &rcfg.ConfigFile)
+	main := ccconf.GetPackageConfig("main")
+	err = json.Unmarshal(main, &rcfg.ConfigFile)
 	if err != nil {
 		cclog.Error("Error reading configuration file ", rcfg.CliArgs["configfile"], ": ", err.Error())
 		return 1
@@ -204,70 +198,74 @@ func mainFunc() int {
 		return 1
 	}
 
-	if len(rcfg.ConfigFile.RouterConfigFile) == 0 {
+	routerConf := ccconf.GetPackageConfig("router")
+	if len(routerConf) == 0 {
 		cclog.Error("Metric router configuration file must be set")
 		return 1
 	}
 
-	if len(rcfg.ConfigFile.SinkConfigFile) == 0 {
+	sinkConf := ccconf.GetPackageConfig("sinks")
+	if len(sinkConf) == 0 {
 		cclog.Error("Sink configuration file must be set")
 		return 1
 	}
 
-	if len(rcfg.ConfigFile.CollectorConfigFile) == 0 {
+	collectorConf := ccconf.GetPackageConfig("collectors")
+	if len(collectorConf) == 0 {
 		cclog.Error("Metric collector configuration file must be set")
 		return 1
 	}
 
 	// Set log file
-	if logfile := rcfg.CliArgs["logfile"]; logfile != "stderr" {
-		cclog.SetOutput(logfile)
-	}
+	// if logfile := rcfg.CliArgs["logfile"]; logfile != "stderr" {
+	// 	cclog.SetOutput(logfile)
+	// }
 
 	// Creat new multi channel ticker
 	rcfg.MultiChanTicker = mct.NewTicker(rcfg.Interval)
 
 	// Create new metric router
-	rcfg.MetricRouter, err = mr.New(rcfg.MultiChanTicker, &rcfg.Sync, rcfg.ConfigFile.RouterConfigFile)
+	rcfg.MetricRouter, err = mr.New(rcfg.MultiChanTicker, &rcfg.Sync, routerConf)
 	if err != nil {
 		cclog.Error(err.Error())
 		return 1
 	}
 
 	// Create new sink
-	rcfg.SinkManager, err = sinks.New(&rcfg.Sync, rcfg.ConfigFile.SinkConfigFile)
+	rcfg.SinkManager, err = sinks.New(&rcfg.Sync, sinkConf)
 	if err != nil {
 		cclog.Error(err.Error())
 		return 1
 	}
 
 	// Connect metric router to sink manager
-	RouterToSinksChannel := make(chan lp.CCMetric, 200)
+	RouterToSinksChannel := make(chan lp.CCMessage, 200)
 	rcfg.SinkManager.AddInput(RouterToSinksChannel)
 	rcfg.MetricRouter.AddOutput(RouterToSinksChannel)
 
 	// Create new collector manager
-	rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, &rcfg.Sync, rcfg.ConfigFile.CollectorConfigFile)
+	rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, &rcfg.Sync, collectorConf)
 	if err != nil {
 		cclog.Error(err.Error())
 		return 1
 	}
 
 	// Connect collector manager to metric router
-	CollectToRouterChannel := make(chan lp.CCMetric, 200)
+	CollectToRouterChannel := make(chan lp.CCMessage, 200)
 	rcfg.CollectManager.AddOutput(CollectToRouterChannel)
 	rcfg.MetricRouter.AddCollectorInput(CollectToRouterChannel)
 
 	// Create new receive manager
-	if len(rcfg.ConfigFile.ReceiverConfigFile) > 0 {
-		rcfg.ReceiveManager, err = receivers.New(&rcfg.Sync, rcfg.ConfigFile.ReceiverConfigFile)
+	receiveConf := ccconf.GetPackageConfig("receivers")
+	if len(receiveConf) > 0 {
+		rcfg.ReceiveManager, err = receivers.New(&rcfg.Sync, receiveConf)
 		if err != nil {
 			cclog.Error(err.Error())
 			return 1
 		}
 
 		// Connect receive manager to metric router
-		ReceiveToRouterChannel := make(chan lp.CCMetric, 200)
+		ReceiveToRouterChannel := make(chan lp.CCMessage, 200)
 		rcfg.ReceiveManager.AddOutput(ReceiveToRouterChannel)
 		rcfg.MetricRouter.AddReceiverInput(ReceiveToRouterChannel)
 		use_recv = true

collectors.json

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

collectors/Makefile

@@ -1,31 +1,33 @@
 # LIKWID version
-LIKWID_VERSION = 5.2.1
-LIKWID_INSTALLED_FOLDER=$(shell dirname $(shell which likwid-topology 2>/dev/null) 2>/dev/null)
+LIKWID_VERSION := 5.4.1
+LIKWID_INSTALLED_FOLDER := $(shell dirname $$(which likwid-topology 2>/dev/null) 2>/dev/null)
 
-LIKWID_FOLDER="$(shell pwd)/likwid"
+LIKWID_FOLDER := $(CURDIR)/likwid
 
-all: $(LIKWID_FOLDER)/likwid.h
+all: likwid
 
 .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 $${BUILD_FOLDER}; \
+.PHONY: likwid
+likwid:
+	if [ -n "$(LIKWID_INSTALLED_FOLDER)" ]; then
+	    # Using likwid include files from system installation
+	    INCLUDE_DIR="$(LIKWID_INSTALLED_FOLDER)/../include"
+	    mkdir --parents --verbose "$(LIKWID_FOLDER)"
+	    cp "$${INCLUDE_DIR}"/*.h "$(LIKWID_FOLDER)"
+	else
+	    # Using likwid include files from downloaded tar archive
+	    if [ -d "$(LIKWID_FOLDER)" ]; then
+	        rm --recursive "$(LIKWID_FOLDER)"
+	    fi
+	    BUILD_FOLDER="$${PWD}/likwidbuild"
+	    mkdir --parents --verbose  "$${BUILD_FOLDER}"
+	    wget --output-document=- http://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz |
+	        tar --directory="$${BUILD_FOLDER}" --extract --gz
+		install -D --verbose --preserve-timestamps --mode=0644 --target-directory="$(LIKWID_FOLDER)" "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/likwid*.h
+	    rm --recursive "$${BUILD_FOLDER}"
 	fi
 
 
+.PHONY: clean
 clean:
 	rm -rf likwid
-
-.PHONY: clean

collectors/README.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: Metric Collectors
+description: Metric collectors for cc-metric-collector
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/_index.md
+---
+-->
+
 # CCMetric collectors
 
 This folder contains the collectors for the cc-metric-collector.
@@ -23,7 +34,6 @@ In contrast to the configuration files for sinks and receivers, the collectors c
 * [`loadavg`](./loadavgMetric.md)
 * [`netstat`](./netstatMetric.md)
 * [`ibstat`](./infinibandMetric.md)
-* [`ibstat_perfquery`](./infinibandPerfQueryMetric.md)
 * [`tempstat`](./tempMetric.md)
 * [`lustrestat`](./lustreMetric.md)
 * [`likwid`](./likwidMetric.md)
@@ -33,9 +43,11 @@ In contrast to the configuration files for sinks and receivers, the collectors c
 * [`topprocs`](./topprocsMetric.md)
 * [`nfs3stat`](./nfs3Metric.md)
 * [`nfs4stat`](./nfs4Metric.md)
+* [`nfsiostat`](./nfsiostatMetric.md)
 * [`cpufreq`](./cpufreqMetric.md)
 * [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
-* [`numastat`](./numastatMetric.md)
+* [`schedstat`](./schedstatMetric.md)
+* [`numastats`](./numastatsMetric.md)
 * [`gpfs`](./gpfsMetric.md)
 * [`beegfs_meta`](./beegfsmetaMetric.md)
 * [`beegfs_storage`](./beegfsstorageMetric.md)
@@ -51,7 +63,7 @@ A collector reads data from any source, parses it to metrics and submits these m
 * `Name() string`: Return the name of the collector
 * `Init(config json.RawMessage) error`: Initializes the collector using the given collector-specific config in JSON. Check if needed files/commands exists, ...
 * `Initialized() bool`: Check if a collector is successfully initialized
-* `Read(duration time.Duration, output chan ccMetric.CCMetric)`: Read, parse and submit data to the `output` channel as [`CCMetric`](../internal/ccMetric/README.md). If the collector has to measure anything for some duration, use the provided function argument `duration`. 
+* `Read(duration time.Duration, output chan ccMessage.CCMessage)`: Read, parse and submit data to the `output` channel as [`CCMessage`](https://github.com/ClusterCockpit/cc-lib/blob/main/ccMessage/README.md). If the collector has to measure anything for some duration, use the provided function argument `duration`.
 * `Close()`: Closes down the collector.
 
 It is recommanded to call `setup()` in the `Init()` function.

collectors/beegfsmetaMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -5,7 +12,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"os"
 	"os/exec"
 	"os/user"
@@ -14,8 +21,8 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
@@ -110,12 +117,12 @@ func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
 	//get mounpoint
-	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
+	buffer, _ := os.ReadFile(string("/proc/mounts"))
 	mounts := strings.Split(string(buffer), "\n")
 	var mountpoints []string
 	for _, line := range mounts {
@@ -157,9 +164,9 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetr
 		if err != nil {
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
-			data, _ := ioutil.ReadAll(cmdStderr)
+			data, _ := io.ReadAll(cmdStderr)
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = ioutil.ReadAll(cmdStdout)
+			data, _ = io.ReadAll(cmdStdout)
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stdout: \"%s\"\n", string(data))
 			return
 		}
@@ -216,7 +223,7 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetr
 
 			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())
+				y, err := lp.NewMessage(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 				if err == nil {
 					output <- y
 				}

collectors/beegfsmetaMetric.md

@@ -1,5 +1,17 @@
+<!--
+---
+title: BeeGFS metadata metric collector
+description: Collect metadata clientstats for `BeeGFS on Demand`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/beegfsmeta.md
+---
+-->
+
+
 ## `BeeGFS on Demand` collector
-This Collector is to collect BeeGFS on Demand (BeeOND) metadata clientstats.
+This Collector is to collect `BeeGFS on Demand` (BeeOND) metadata clientstats.
 
 ```json
   "beegfs_meta": {
@@ -72,4 +84,4 @@ Available Metrics:
 * setXA
 * mirror
 
-The collector adds a `filesystem` tag to all metrics
+The collector adds a `filesystem` tag to all metrics

collectors/beegfsstorageMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -5,7 +12,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"os"
 	"os/exec"
 	"os/user"
@@ -14,8 +21,8 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 // Struct for the collector-specific JSON config
@@ -103,12 +110,12 @@ func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
 	//get mounpoint
-	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
+	buffer, _ := os.ReadFile(string("/proc/mounts"))
 	mounts := strings.Split(string(buffer), "\n")
 	var mountpoints []string
 	for _, line := range mounts {
@@ -149,9 +156,9 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
 		if err != nil {
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
-			data, _ := ioutil.ReadAll(cmdStderr)
+			data, _ := io.ReadAll(cmdStderr)
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = ioutil.ReadAll(cmdStdout)
+			data, _ = io.ReadAll(cmdStdout)
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stdout: \"%s\"\n", string(data))
 			return
 		}
@@ -208,7 +215,7 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
 
 			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())
+				y, err := lp.NewMessage(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 				if err == nil {
 					output <- y
 				}

collectors/beegfsstorageMetric.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: "BeeGFS on Demand metric collector"
+description: Collect performance metrics for BeeGFS filesystems
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/beegfsstorage.md
+---
+-->
+
 ## `BeeGFS on Demand` collector
 This Collector is to collect BeeGFS on Demand (BeeOND) storage stats.
 
@@ -52,4 +63,4 @@ Available Metrics:
 * "unlnk"
 
 
-The collector adds a `filesystem` tag to all metrics
+The collector adds a `filesystem` tag to all metrics

collectors/collectorManager.go

@@ -1,14 +1,20 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
 	"encoding/json"
-	"os"
 	"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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 // Map of all available metric collectors
@@ -36,14 +42,18 @@ var AvailableCollectors = map[string]MetricCollector{
 	"numastats":       new(NUMAStatsCollector),
 	"beegfs_meta":     new(BeegfsMetaCollector),
 	"beegfs_storage":  new(BeegfsStorageCollector),
+	"rapl":            new(RAPLCollector),
 	"rocm_smi":        new(RocmSmiCollector),
+	"self":            new(SelfCollector),
+	"schedstat":       new(SchedstatCollector),
+	"nfsiostat":       new(NfsIOStatCollector),
 }
 
 // Metric collector manager data structure
 type collectorManager struct {
 	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
+	output       chan lp.CCMessage          // 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)
@@ -55,8 +65,8 @@ type collectorManager struct {
 
 // Metric collector manager access functions
 type CollectorManager interface {
-	Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error
-	AddOutput(output chan lp.CCMetric)
+	Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) error
+	AddOutput(output chan lp.CCMessage)
 	Start()
 	Close()
 }
@@ -68,7 +78,7 @@ type CollectorManager interface {
 // * ticker (from variable ticker)
 // * configuration (read from config file in variable collectConfigFile)
 // Initialization is done for all configured collectors
-func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error {
+func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) error {
 	cm.collectors = make([]MetricCollector, 0)
 	cm.serial = make([]MetricCollector, 0)
 	cm.output = nil
@@ -77,15 +87,7 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
 	cm.ticker = ticker
 	cm.duration = duration
 
-	// Read collector config file
-	configFile, err := os.Open(collectConfigFile)
-	if err != nil {
-		cclog.Error(err.Error())
-		return err
-	}
-	defer configFile.Close()
-	jsonParser := json.NewDecoder(configFile)
-	err = jsonParser.Decode(&cm.config)
+	err := json.Unmarshal(collectConfig, &cm.config)
 	if err != nil {
 		cclog.Error(err.Error())
 		return err
@@ -183,7 +185,7 @@ func (cm *collectorManager) Start() {
 }
 
 // AddOutput adds the output channel to the metric collector manager
-func (cm *collectorManager) AddOutput(output chan lp.CCMetric) {
+func (cm *collectorManager) AddOutput(output chan lp.CCMessage) {
 	cm.output = output
 }
 
@@ -196,9 +198,9 @@ func (cm *collectorManager) Close() {
 }
 
 // New creates a new initialized metric collector manager
-func New(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) (CollectorManager, error) {
+func New(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) (CollectorManager, error) {
 	cm := new(collectorManager)
-	err := cm.Init(ticker, duration, wg, collectConfigFile)
+	err := cm.Init(ticker, duration, wg, collectConfig)
 	if err != nil {
 		return nil, err
 	}

collectors/cpufreqCpuinfoMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -10,33 +17,22 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
-//
 // CPUFreqCollector
 // a metric collector to measure the current frequency of the CPUs
 // as obtained from /proc/cpuinfo
 // Only measure on the first hyperthread
-//
 type CPUFreqCpuInfoCollectorTopology struct {
-	processor               string // logical processor number (continuous, starting at 0)
-	coreID                  string // socket local core ID
-	coreID_int              int64
-	physicalPackageID       string // socket / package ID
-	physicalPackageID_int   int64
-	numPhysicalPackages     string // number of  sockets / packages
-	numPhysicalPackages_int int64
-	isHT                    bool
-	numNonHT                string // number of non hyperthreading processors
-	numNonHT_int            int64
-	tagSet                  map[string]string
+	isHT   bool
+	tagSet map[string]string
 }
 
 type CPUFreqCpuInfoCollector struct {
 	metricCollector
-	topology []*CPUFreqCpuInfoCollectorTopology
+	topology []CPUFreqCpuInfoCollectorTopology
 }
 
 func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
@@ -65,11 +61,9 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 	// Collect topology information from file cpuinfo
 	foundFreq := false
 	processor := ""
-	var numNonHT_int int64 = 0
 	coreID := ""
 	physicalPackageID := ""
-	var maxPhysicalPackageID int64 = 0
-	m.topology = make([]*CPUFreqCpuInfoCollectorTopology, 0)
+	m.topology = make([]CPUFreqCpuInfoCollectorTopology, 0)
 	coreSeenBefore := make(map[string]bool)
 
 	// Read cpuinfo file, line by line
@@ -98,41 +92,22 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 			len(coreID) > 0 &&
 			len(physicalPackageID) > 0 {
 
-			topology := new(CPUFreqCpuInfoCollectorTopology)
-
-			// Processor
-			topology.processor = processor
-
-			// Core ID
-			topology.coreID = coreID
-			topology.coreID_int, err = strconv.ParseInt(coreID, 10, 64)
-			if err != nil {
-				return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
-			}
-
-			// Physical package ID
-			topology.physicalPackageID = physicalPackageID
-			topology.physicalPackageID_int, err = strconv.ParseInt(physicalPackageID, 10, 64)
-			if err != nil {
-				return fmt.Errorf("unable to convert physicalPackageID '%s' to int64: %v", physicalPackageID, err)
-			}
-
-			// increase maximun socket / package ID, when required
-			if topology.physicalPackageID_int > maxPhysicalPackageID {
-				maxPhysicalPackageID = topology.physicalPackageID_int
-			}
-
-			// is hyperthread?
 			globalID := physicalPackageID + ":" + coreID
-			topology.isHT = coreSeenBefore[globalID]
-			coreSeenBefore[globalID] = true
-			if !topology.isHT {
-				// increase number on non hyper thread cores
-				numNonHT_int++
-			}
 
 			// store collected topology information
-			m.topology = append(m.topology, topology)
+			m.topology = append(m.topology,
+				CPUFreqCpuInfoCollectorTopology{
+					isHT: coreSeenBefore[globalID],
+					tagSet: map[string]string{
+						"type":       "hwthread",
+						"type-id":    processor,
+						"package_id": physicalPackageID,
+					},
+				},
+			)
+
+			// mark core as seen before
+			coreSeenBefore[globalID] = true
 
 			// reset topology information
 			foundFreq = false
@@ -142,26 +117,16 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 		}
 	}
 
-	numPhysicalPackageID_int := maxPhysicalPackageID + 1
-	numPhysicalPackageID := fmt.Sprint(numPhysicalPackageID_int)
-	numNonHT := fmt.Sprint(numNonHT_int)
-	for _, t := range m.topology {
-		t.numPhysicalPackages = numPhysicalPackageID
-		t.numPhysicalPackages_int = numPhysicalPackageID_int
-		t.numNonHT = numNonHT
-		t.numNonHT_int = numNonHT_int
-		t.tagSet = map[string]string{
-			"type":       "hwthread",
-			"type-id":    t.processor,
-			"package_id": t.physicalPackageID,
-		}
+	// Check if at least one CPU with frequency information was detected
+	if len(m.topology) == 0 {
+		return fmt.Errorf("no CPU frequency info found in %s", cpuInfoFile)
 	}
 
 	m.init = true
 	return nil
 }
 
-func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	// Check if already initialized
 	if !m.init {
 		return
@@ -196,7 +161,7 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
 							fmt.Sprintf("Read(): Failed to convert cpu MHz '%s' to float64: %v", lineSplit[1], err))
 						return
 					}
-					if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil {
+					if y, err := lp.NewMessage("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil {
 						output <- y
 					}
 				}

collectors/cpufreqCpuinfoMetric.md

@@ -1,5 +1,16 @@
+<!--
+---
+title: CPU frequency metric collector through cpuinfo
+description: Collect the CPU frequency from `/proc/cpuinfo`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/cpufreq_cpuinfo.md
+---
+-->
 
 ## `cpufreq_cpuinfo` collector
+
 ```json
   "cpufreq_cpuinfo": {}
 ```
@@ -7,4 +18,5 @@
 The `cpufreq_cpuinfo` collector reads the clock frequency from `/proc/cpuinfo` and outputs a handful **hwthread** metrics.
 
 Metrics:
+
 * `cpufreq`

collectors/cpufreqMetric.go

@@ -1,42 +1,38 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	"github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 	"golang.org/x/sys/unix"
 )
 
 type CPUFreqCollectorTopology struct {
-	processor               string // logical processor number (continuous, starting at 0)
-	coreID                  string // socket local core ID
-	coreID_int              int64
-	physicalPackageID       string // socket / package ID
-	physicalPackageID_int   int64
-	numPhysicalPackages     string // number of  sockets / packages
-	numPhysicalPackages_int int64
-	isHT                    bool
-	numNonHT                string // number of non hyperthreading processors
-	numNonHT_int            int64
-	scalingCurFreqFile      string
-	tagSet                  map[string]string
+	scalingCurFreqFile string
+	tagSet             map[string]string
 }
 
-//
 // CPUFreqCollector
 // a metric collector to measure the current frequency of the CPUs
 // as obtained from the hardware (in KHz)
-// Only measure on the first hyper thread
+// Only measure on the first hyper-thread
 //
 // See: https://www.kernel.org/doc/html/latest/admin-guide/pm/cpufreq.html
-//
 type CPUFreqCollector struct {
 	metricCollector
 	topology []CPUFreqCollectorTopology
@@ -63,116 +59,46 @@ 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
-	baseDir := "/sys/devices/system/cpu"
-	globPattern := filepath.Join(baseDir, "cpu[0-9]*")
-	cpuDirs, err := filepath.Glob(globPattern)
-	if err != nil {
-		return fmt.Errorf("unable to glob files with pattern '%s': %v", globPattern, err)
-	}
-	if cpuDirs == nil {
-		return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
-	}
+	m.topology = make([]CPUFreqCollectorTopology, 0)
+	for _, c := range ccTopology.CpuData() {
 
-	// Initialize CPU topology
-	m.topology = make([]CPUFreqCollectorTopology, len(cpuDirs))
-	for _, cpuDir := range cpuDirs {
-		processor := strings.TrimPrefix(cpuDir, "/sys/devices/system/cpu/cpu")
-		processor_int, err := strconv.ParseInt(processor, 10, 64)
-		if err != nil {
-			return fmt.Errorf("unable to convert cpuID '%s' to int64: %v", processor, err)
-		}
-
-		// Read package ID
-		physicalPackageIDFile := filepath.Join(cpuDir, "topology", "physical_package_id")
-		line, err := ioutil.ReadFile(physicalPackageIDFile)
-		if err != nil {
-			return fmt.Errorf("unable to read physical package ID from file '%s': %v", physicalPackageIDFile, err)
-		}
-		physicalPackageID := strings.TrimSpace(string(line))
-		physicalPackageID_int, err := strconv.ParseInt(physicalPackageID, 10, 64)
-		if err != nil {
-			return fmt.Errorf("unable to convert packageID '%s' to int64: %v", physicalPackageID, err)
-		}
-
-		// Read core ID
-		coreIDFile := filepath.Join(cpuDir, "topology", "core_id")
-		line, err = ioutil.ReadFile(coreIDFile)
-		if err != nil {
-			return fmt.Errorf("unable to read core ID from file '%s': %v", coreIDFile, err)
-		}
-		coreID := strings.TrimSpace(string(line))
-		coreID_int, err := strconv.ParseInt(coreID, 10, 64)
-		if err != nil {
-			return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
+		// Skip hyper threading CPUs
+		if c.CpuID != c.CoreCPUsList[0] {
+			continue
 		}
 
 		// Check access to current frequency file
-		scalingCurFreqFile := filepath.Join(cpuDir, "cpufreq", "scaling_cur_freq")
-		err = unix.Access(scalingCurFreqFile, unix.R_OK)
+		scalingCurFreqFile := filepath.Join("/sys/devices/system/cpu", fmt.Sprintf("cpu%d", c.CpuID), "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)
 		}
 
-		t := &m.topology[processor_int]
-		t.processor = processor
-		t.physicalPackageID = physicalPackageID
-		t.physicalPackageID_int = physicalPackageID_int
-		t.coreID = coreID
-		t.coreID_int = coreID_int
-		t.scalingCurFreqFile = scalingCurFreqFile
-	}
-
-	// is processor a hyperthread?
-	coreSeenBefore := make(map[string]bool)
-	for i := range m.topology {
-		t := &m.topology[i]
-
-		globalID := t.physicalPackageID + ":" + t.coreID
-		t.isHT = coreSeenBefore[globalID]
-		coreSeenBefore[globalID] = true
-	}
-
-	// number of non hyper thread cores and packages / sockets
-	var numNonHT_int int64 = 0
-	var maxPhysicalPackageID int64 = 0
-	for i := range m.topology {
-		t := &m.topology[i]
-
-		// Update maxPackageID
-		if t.physicalPackageID_int > maxPhysicalPackageID {
-			maxPhysicalPackageID = t.physicalPackageID_int
-		}
-
-		if !t.isHT {
-			numNonHT_int++
-		}
-	}
-
-	numPhysicalPackageID_int := maxPhysicalPackageID + 1
-	numPhysicalPackageID := fmt.Sprint(numPhysicalPackageID_int)
-	numNonHT := fmt.Sprint(numNonHT_int)
-	for i := range m.topology {
-		t := &m.topology[i]
-		t.numPhysicalPackages = numPhysicalPackageID
-		t.numPhysicalPackages_int = numPhysicalPackageID_int
-		t.numNonHT = numNonHT
-		t.numNonHT_int = numNonHT_int
-		t.tagSet = map[string]string{
-			"type":       "hwthread",
-			"type-id":    t.processor,
-			"package_id": t.physicalPackageID,
-		}
+		m.topology = append(m.topology,
+			CPUFreqCollectorTopology{
+				tagSet: map[string]string{
+					"type":       "hwthread",
+					"type-id":    fmt.Sprint(c.CpuID),
+					"package_id": fmt.Sprint(c.Socket),
+				},
+				scalingCurFreqFile: scalingCurFreqFile,
+			},
+		)
 	}
 
+	// Initialized
+	cclog.ComponentDebug(
+		m.name,
+		"initialized",
+		len(m.topology), "non-hyper-threading CPUs")
 	m.init = true
 	return nil
 }
 
-func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	// Check if already initialized
 	if !m.init {
 		return
@@ -182,13 +108,8 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	for i := range m.topology {
 		t := &m.topology[i]
 
-		// skip hyperthreads
-		if t.isHT {
-			continue
-		}
-
 		// Read current frequency
-		line, err := ioutil.ReadFile(t.scalingCurFreqFile)
+		line, err := os.ReadFile(t.scalingCurFreqFile)
 		if err != nil {
 			cclog.ComponentError(
 				m.name,
@@ -203,7 +124,7 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric)
 			continue
 		}
 
-		if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil {
+		if y, err := lp.NewMessage("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil {
 			output <- y
 		}
 	}

collectors/cpufreqMetric.md

@@ -1,4 +1,16 @@
+<!--
+---
+title: CPU frequency metric collector through sysfs
+description: Collect the CPU frequency metrics from `/sys/.../cpu/.../cpufreq`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/cpufreq.md
+---
+-->
+
 ## `cpufreq_cpuinfo` collector
+
 ```json
   "cpufreq": {
     "exclude_metrics": []
@@ -8,4 +20,5 @@
 The `cpufreq` collector reads the clock frequency from `/sys/devices/system/cpu/cpu*/cpufreq` and outputs a handful **hwthread** metrics.
 
 Metrics:
-* `cpufreq`
+
+* `cpufreq`

collectors/cpustatMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -9,8 +16,9 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	sysconf "github.com/tklauser/go-sysconf"
 )
 
 const CPUSTATFILE = `/proc/stat`
@@ -21,17 +29,19 @@ type CpustatCollectorConfig struct {
 
 type CpustatCollector struct {
 	metricCollector
-	config   CpustatCollectorConfig
-	matches  map[string]int
-	cputags  map[string]map[string]string
-	nodetags map[string]string
+	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.meta = map[string]string{"source": m.name, "group": "CPU"}
 	m.nodetags = map[string]string{"type": "node"}
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
@@ -76,47 +86,73 @@ 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": "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.CCMessage, 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()
+
+	sum := float64(0)
 	for name, value := range values {
-		y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": (value * 100.0) / total}, t)
+		sum += value
+		y, err := lp.NewMessage(name, tags, m.meta, map[string]interface{}{"value": value * 100}, now)
 		if err == nil {
+			y.AddTag("unit", "Percent")
+			output <- y
+		}
+	}
+	if v, ok := values["cpu_idle"]; ok {
+		sum -= v
+		y, err := lp.NewMessage("cpu_used", tags, m.meta, map[string]interface{}{"value": sum * 100}, now)
+		if err == nil {
+			y.AddTag("unit", "Percent")
 			output <- y
 		}
 	}
 }
 
-func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		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())
@@ -128,22 +164,24 @@ 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++
 		}
 	}
 
-	num_cpus_metric, err := lp.New("num_cpus",
+	num_cpus_metric, err := lp.NewMessage("num_cpus",
 		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/cpustatMetric.md

@@ -1,5 +1,17 @@
+<!--
+---
+title: CPU usage metric collector
+description: Collect CPU metrics from `/proc/stat`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/cpustat.md
+---
+-->
+
 
 ## `cpustat` collector
+
 ```json
   "cpustat": {
     "exclude_metrics": [
@@ -8,16 +20,19 @@
   }
 ```
 
-The `cpustat` collector reads data from `/proc/stats` and outputs a handful **node** and **hwthread** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
+The `cpustat` collector reads data from `/proc/stat` and outputs a handful **node** and **hwthread** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
 
 Metrics:
-* `cpu_user`
-* `cpu_nice`
-* `cpu_system`
-* `cpu_idle`
-* `cpu_iowait`
-* `cpu_irq`
-* `cpu_softirq`
-* `cpu_steal`
-* `cpu_guest`
-* `cpu_guest_nice`
+
+* `cpu_user` with `unit=Percent`
+* `cpu_nice` with `unit=Percent`
+* `cpu_system` with `unit=Percent`
+* `cpu_idle` with `unit=Percent`
+* `cpu_iowait` with `unit=Percent`
+* `cpu_irq` with `unit=Percent`
+* `cpu_softirq` with `unit=Percent`
+* `cpu_steal` with `unit=Percent`
+* `cpu_guest` with `unit=Percent`
+* `cpu_guest_nice` with `unit=Percent`
+* `cpu_used` = `cpu_* - cpu_idle` with `unit=Percent`
+* `num_cpus`

collectors/customCmdMetric.go

@@ -1,15 +1,22 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 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-lib/ccMessage"
 	influx "github.com/influxdata/line-protocol"
 )
 
@@ -48,12 +55,12 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
 		command := exec.Command(cmdfields[0], strings.Join(cmdfields[1:], " "))
 		command.Wait()
 		_, err = command.Output()
-		if err != nil {
+		if err == nil {
 			m.commands = append(m.commands, c)
 		}
 	}
 	for _, f := range m.config.Files {
-		_, err = ioutil.ReadFile(f)
+		_, err = os.ReadFile(f)
 		if err == nil {
 			m.files = append(m.files, f)
 		} else {
@@ -75,7 +82,7 @@ var DefaultTime = func() time.Time {
 	return time.Unix(42, 0)
 }
 
-func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
@@ -99,14 +106,11 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 				continue
 			}
 
-			y := lp.FromInfluxMetric(c)
-			if err == nil {
-				output <- y
-			}
+			output <- lp.FromInfluxMetric(c)
 		}
 	}
 	for _, file := range m.files {
-		buffer, err := ioutil.ReadFile(file)
+		buffer, err := os.ReadFile(file)
 		if err != nil {
 			log.Print(err)
 			return
@@ -121,10 +125,7 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 			if skip {
 				continue
 			}
-			y := lp.FromInfluxMetric(f)
-			if err == nil {
-				output <- y
-			}
+			output <- lp.FromInfluxMetric(f)
 		}
 	}
 }

collectors/customCmdMetric.md

@@ -1,3 +1,13 @@
+<!--
+---
+title: CustomCommand metric collector
+description: Collect messages from custom command or files
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/customcmd.md
+---
+-->
 
 ## `customcmd` collector
 

collectors/diskstatMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -8,23 +15,21 @@ import (
 	"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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
-//	"log"
-
 const MOUNTFILE = `/proc/self/mounts`
 
 type DiskstatCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+	ExcludeMounts  []string `json:"exclude_mounts,omitempty"`
 }
 
 type DiskstatCollector struct {
 	metricCollector
-	//matches map[string]int
-	config IOstatCollectorConfig
-	//devices map[string]IOstatCollectorEntry
+	config         DiskstatCollectorConfig
+	allowedMetrics map[string]bool
 }
 
 func (m *DiskstatCollector) Init(config json.RawMessage) error {
@@ -33,12 +38,21 @@ func (m *DiskstatCollector) Init(config json.RawMessage) error {
 	m.meta = map[string]string{"source": m.name, "group": "Disk"}
 	m.setup()
 	if len(config) > 0 {
-		err := json.Unmarshal(config, &m.config)
-		if err != nil {
+		if err := json.Unmarshal(config, &m.config); err != nil {
 			return err
 		}
 	}
-	file, err := os.Open(string(MOUNTFILE))
+	m.allowedMetrics = map[string]bool{
+		"disk_total":    true,
+		"disk_free":     true,
+		"part_max_used": true,
+	}
+	for _, excl := range m.config.ExcludeMetrics {
+		if _, ok := m.allowedMetrics[excl]; ok {
+			m.allowedMetrics[excl] = false
+		}
+	}
+	file, err := os.Open(MOUNTFILE)
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return err
@@ -48,12 +62,12 @@ func (m *DiskstatCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
 
-	file, err := os.Open(string(MOUNTFILE))
+	file, err := os.Open(MOUNTFILE)
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return
@@ -62,6 +76,7 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric
 
 	part_max_used := uint64(0)
 	scanner := bufio.NewScanner(file)
+mountLoop:
 	for scanner.Scan() {
 		line := scanner.Text()
 		if len(line) == 0 {
@@ -77,13 +92,17 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric
 		if strings.Contains(linefields[1], "boot") {
 			continue
 		}
-		path := strings.Replace(linefields[1], `\040`, " ", -1)
-		stat := syscall.Statfs_t{
-			Blocks: 0,
-			Bsize:  0,
-			Bfree:  0,
+
+		mountPath := strings.Replace(linefields[1], `\040`, " ", -1)
+
+		for _, excl := range m.config.ExcludeMounts {
+			if strings.Contains(mountPath, excl) {
+				continue mountLoop
+			}
 		}
-		err := syscall.Statfs(path, &stat)
+
+		stat := syscall.Statfs_t{}
+		err := syscall.Statfs(mountPath, &stat)
 		if err != nil {
 			continue
 		}
@@ -92,16 +111,20 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric
 		}
 		tags := map[string]string{"type": "node", "device": linefields[0]}
 		total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)
-		y, err := lp.New("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now())
-		if err == nil {
-			y.AddMeta("unit", "GBytes")
-			output <- y
+		if m.allowedMetrics["disk_total"] {
+			y, err := lp.NewMessage("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now())
+			if err == nil {
+				y.AddMeta("unit", "GBytes")
+				output <- y
+			}
 		}
 		free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000000000)
-		y, err = lp.New("disk_free", tags, m.meta, map[string]interface{}{"value": free}, time.Now())
-		if err == nil {
-			y.AddMeta("unit", "GBytes")
-			output <- y
+		if m.allowedMetrics["disk_free"] {
+			y, err := lp.NewMessage("disk_free", tags, m.meta, map[string]interface{}{"value": free}, time.Now())
+			if err == nil {
+				y.AddMeta("unit", "GBytes")
+				output <- y
+			}
 		}
 		if total > 0 {
 			perc := (100 * (total - free)) / total
@@ -110,10 +133,12 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric
 			}
 		}
 	}
-	y, err := lp.New("part_max_used", map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": int(part_max_used)}, time.Now())
-	if err == nil {
-		y.AddMeta("unit", "percent")
-		output <- y
+	if m.allowedMetrics["part_max_used"] {
+		y, err := lp.NewMessage("part_max_used", map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": int(part_max_used)}, time.Now())
+		if err == nil {
+			y.AddMeta("unit", "percent")
+			output <- y
+		}
 	}
 }
 

collectors/diskstatMetric.md

@@ -1,3 +1,13 @@
+<!--
+---
+title: Disk usage statistics metric collector
+description: Collect metrics for various filesystems from `/proc/self/mounts`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/diskstat.md
+---
+-->
 
 ## `diskstat` collector
 
@@ -6,10 +16,13 @@
     "exclude_metrics": [
       "disk_total"
     ],
+    "exclude_mounts": [
+      "slurm-tmpfs"
+    ]
   }
 ```
 
-The `diskstat` collector reads data from `/proc/self/mounts` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
+The `diskstat` collector reads data from `/proc/self/mounts` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink. Additionally, any mount point containing one of the strings specified in `exclude_mounts` will be skipped during metric collection.
 
 Metrics per device (with `device` tag):
 * `disk_total` (unit `GBytes`)

collectors/gpfsMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -5,7 +12,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"log"
 	"os/exec"
 	"os/user"
@@ -13,8 +20,8 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 const DEFAULT_GPFS_CMD = "mmpmon"
@@ -31,6 +38,7 @@ type GpfsCollector struct {
 		Mmpmon            string   `json:"mmpmon_path,omitempty"`
 		ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
 		SendBandwidths    bool     `json:"send_bandwidths"`
+		SendTotalValues   bool     `json:"send_total_values"`
 	}
 	skipFS        map[string]struct{}
 	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
@@ -93,7 +101,7 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	// Check if already initialized
 	if !m.init {
 		return
@@ -118,8 +126,8 @@ 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),
@@ -216,13 +224,33 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert bytes read '%s' to int64: %v", key_value["_br_"], err))
 			continue
 		}
-		if y, err := lp.New("gpfs_bytes_read", m.tags, m.meta, map[string]interface{}{"value": bytesRead}, timestamp); err == nil {
+		if y, err :=
+			lp.NewMessage(
+				"gpfs_bytes_read",
+				m.tags,
+				m.meta,
+				map[string]interface{}{
+					"value": bytesRead,
+				},
+				timestamp,
+			); err == nil {
+			y.AddMeta("unit", "bytes")
 			output <- y
 		}
 		if m.config.SendBandwidths {
 			if lastBytesRead := m.lastState[filesystem].bytesRead; lastBytesRead >= 0 {
 				bwRead := float64(bytesRead-lastBytesRead) / timeDiff
-				if y, err := lp.New("gpfs_bw_read", m.tags, m.meta, map[string]interface{}{"value": bwRead}, timestamp); err == nil {
+				if y, err :=
+					lp.NewMessage(
+						"gpfs_bw_read",
+						m.tags,
+						m.meta,
+						map[string]interface{}{
+							"value": bwRead,
+						},
+						timestamp,
+					); err == nil {
+					y.AddMeta("unit", "bytes/sec")
 					output <- y
 				}
 			}
@@ -236,13 +264,33 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert bytes written '%s' to int64: %v", key_value["_bw_"], err))
 			continue
 		}
-		if y, err := lp.New("gpfs_bytes_written", m.tags, m.meta, map[string]interface{}{"value": bytesWritten}, timestamp); err == nil {
+		if y, err :=
+			lp.NewMessage(
+				"gpfs_bytes_written",
+				m.tags,
+				m.meta,
+				map[string]interface{}{
+					"value": bytesWritten,
+				},
+				timestamp,
+			); err == nil {
+			y.AddMeta("unit", "bytes")
 			output <- y
 		}
 		if m.config.SendBandwidths {
 			if lastBytesWritten := m.lastState[filesystem].bytesRead; lastBytesWritten >= 0 {
 				bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff
-				if y, err := lp.New("gpfs_bw_write", m.tags, m.meta, map[string]interface{}{"value": bwWrite}, timestamp); err == nil {
+				if y, err :=
+					lp.NewMessage(
+						"gpfs_bw_write",
+						m.tags,
+						m.meta,
+						map[string]interface{}{
+							"value": bwWrite,
+						},
+						timestamp,
+					); err == nil {
+					y.AddMeta("unit", "bytes/sec")
 					output <- y
 				}
 			}
@@ -263,7 +311,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert number of opens '%s' to int64: %v", key_value["_oc_"], err))
 			continue
 		}
-		if y, err := lp.New("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil {
+		if y, err := lp.NewMessage("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -275,7 +323,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert number of closes: '%s' to int64: %v", key_value["_cc_"], err))
 			continue
 		}
-		if y, err := lp.New("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil {
+		if y, err := lp.NewMessage("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -287,7 +335,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert number of reads: '%s' to int64: %v", key_value["_rdc_"], err))
 			continue
 		}
-		if y, err := lp.New("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil {
+		if y, err := lp.NewMessage("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -299,7 +347,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert number of writes: '%s' to int64: %v", key_value["_wc_"], err))
 			continue
 		}
-		if y, err := lp.New("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil {
+		if y, err := lp.NewMessage("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -311,7 +359,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert number of read directories: '%s' to int64: %v", key_value["_dir_"], err))
 			continue
 		}
-		if y, err := lp.New("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil {
+		if y, err := lp.NewMessage("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -323,9 +371,50 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 				fmt.Sprintf("Read(): Failed to convert number of inode updates: '%s' to int: %v", key_value["_iu_"], err))
 			continue
 		}
-		if y, err := lp.New("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
+		if y, err := lp.NewMessage("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
 			output <- y
 		}
+
+		// Total values
+		if m.config.SendTotalValues {
+			bytesTotal := bytesRead + bytesWritten
+			if y, err :=
+				lp.NewMessage("gpfs_bytes_total",
+					m.tags,
+					m.meta,
+					map[string]interface{}{
+						"value": bytesTotal,
+					},
+					timestamp,
+				); err == nil {
+				y.AddMeta("unit", "bytes")
+				output <- y
+			}
+			iops := numReads + numWrites
+			if y, err :=
+				lp.NewMessage("gpfs_iops",
+					m.tags,
+					m.meta,
+					map[string]interface{}{
+						"value": iops,
+					},
+					timestamp,
+				); err == nil {
+				output <- y
+			}
+			metaops := numInodeUpdates + numCloses + numOpens + numReaddirs
+			if y, err :=
+				lp.NewMessage("gpfs_metaops",
+					m.tags,
+					m.meta,
+					map[string]interface{}{
+						"value": metaops,
+					},
+					timestamp,
+				); err == nil {
+				output <- y
+			}
+		}
 	}
 }
 

collectors/gpfsMetric.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: GPFS collector
+description: Collect infos about GPFS filesystems
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/gpfs.md
+---
+-->
+
 ## `gpfs` collector
 
 ```json
@@ -6,7 +17,8 @@
     "exclude_filesystem": [
       "fs1"
     ],
-    "send_bandwidths" : true
+    "send_bandwidths": true,
+    "send_total_values": true
   }
 ```
 
@@ -26,8 +38,12 @@ Metrics:
 * `gpfs_num_opens`
 * `gpfs_num_closes`
 * `gpfs_num_reads`
+* `gpfs_num_writes`
 * `gpfs_num_readdirs`
 * `gpfs_num_inode_updates`
+* `gpfs_bytes_total = gpfs_bytes_read + gpfs_bytes_written` (if `send_total_values == true`)
+* `gpfs_iops = gpfs_num_reads + gpfs_num_writes` (if `send_total_values == true`)
+* `gpfs_metaops = gpfs_num_inode_updates + gpfs_num_closes + gpfs_num_opens + gpfs_num_readdirs` (if `send_total_values == true`)
 * `gpfs_bw_read` (if `send_bandwidths == true`)
 * `gpfs_bw_write` (if `send_bandwidths == true`)
 

collectors/infinibandMetric.go

@@ -1,12 +1,18 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 	"golang.org/x/sys/unix"
 
 	"encoding/json"
@@ -19,17 +25,22 @@ import (
 const IB_BASEPATH = "/sys/class/infiniband/"
 
 type InfinibandCollectorMetric struct {
-	path string
-	unit string
+	name             string
+	path             string
+	unit             string
+	scale            int64
+	addToIBTotal     bool
+	addToIBTotalPkgs bool
+	currentState     int64
+	lastState        int64
 }
 
 type InfinibandCollectorInfo struct {
-	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
+	LID              string                      // IB local Identifier (LID)
+	device           string                      // IB device
+	port             string                      // IB device port
+	portCounterFiles []InfinibandCollectorMetric // mapping counter name -> InfinibandCollectorMetric
+	tagSet           map[string]string           // corresponding tag list
 }
 
 type InfinibandCollector struct {
@@ -37,9 +48,10 @@ type InfinibandCollector struct {
 	config struct {
 		ExcludeDevices     []string `json:"exclude_devices,omitempty"` // IB device to exclude e.g. mlx5_0
 		SendAbsoluteValues bool     `json:"send_abs_values"`           // Send absolut values as read from sys filesystem
+		SendTotalValues    bool     `json:"send_total_values"`         // Send computed total values
 		SendDerivedValues  bool     `json:"send_derived_values"`       // Send derived values e.g. rates
 	}
-	info          []*InfinibandCollectorInfo
+	info          []InfinibandCollectorInfo
 	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
 }
 
@@ -84,7 +96,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	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
 		}
@@ -112,11 +124,39 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 
 		// Check access to counter files
 		countersDir := filepath.Join(path, "counters")
-		portCounterFiles := map[string]InfinibandCollectorMetric{
-			"ib_recv":      {path: filepath.Join(countersDir, "port_rcv_data"), unit: "bytes"},
-			"ib_xmit":      {path: filepath.Join(countersDir, "port_xmit_data"), unit: "bytes"},
-			"ib_recv_pkts": {path: filepath.Join(countersDir, "port_rcv_packets"), unit: "packets"},
-			"ib_xmit_pkts": {path: filepath.Join(countersDir, "port_xmit_packets"), unit: "packets"},
+		portCounterFiles := []InfinibandCollectorMetric{
+			{
+				name:         "ib_recv",
+				path:         filepath.Join(countersDir, "port_rcv_data"),
+				unit:         "bytes",
+				scale:        4,
+				addToIBTotal: true,
+				lastState:    -1,
+			},
+			{
+				name:         "ib_xmit",
+				path:         filepath.Join(countersDir, "port_xmit_data"),
+				unit:         "bytes",
+				scale:        4,
+				addToIBTotal: true,
+				lastState:    -1,
+			},
+			{
+				name:             "ib_recv_pkts",
+				path:             filepath.Join(countersDir, "port_rcv_packets"),
+				unit:             "packets",
+				scale:            1,
+				addToIBTotalPkgs: true,
+				lastState:        -1,
+			},
+			{
+				name:             "ib_xmit_pkts",
+				path:             filepath.Join(countersDir, "port_xmit_packets"),
+				unit:             "packets",
+				scale:            1,
+				addToIBTotalPkgs: true,
+				lastState:        -1,
+			},
 		}
 		for _, counter := range portCounterFiles {
 			err := unix.Access(counter.path, unix.R_OK)
@@ -125,14 +165,8 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 			}
 		}
 
-		// Initialize last state
-		lastState := make(map[string]int64)
-		for counter := range portCounterFiles {
-			lastState[counter] = -1
-		}
-
 		m.info = append(m.info,
-			&InfinibandCollectorInfo{
+			InfinibandCollectorInfo{
 				LID:              LID,
 				device:           device,
 				port:             port,
@@ -143,7 +177,6 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 					"port":   port,
 					"lid":    LID,
 				},
-				lastState: lastState,
 			})
 	}
 
@@ -156,7 +189,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 }
 
 // Read reads Infiniband counter files below IB_BASEPATH
-func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 
 	// Check if already initialized
 	if !m.init {
@@ -170,11 +203,15 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 	// Save current timestamp
 	m.lastTimestamp = now
 
-	for _, info := range m.info {
-		for counterName, counterDef := range info.portCounterFiles {
+	for i := range m.info {
+		info := &m.info[i]
+
+		var ib_total, ib_total_pkts int64
+		for i := range info.portCounterFiles {
+			counterDef := &info.portCounterFiles[i]
 
 			// Read counter file
-			line, err := ioutil.ReadFile(counterDef.path)
+			line, err := os.ReadFile(counterDef.path)
 			if err != nil {
 				cclog.ComponentError(
 					m.name,
@@ -188,13 +225,26 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 			if err != nil {
 				cclog.ComponentError(
 					m.name,
-					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterName, data, err))
+					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterDef.name, data, err))
 				continue
 			}
+			// Scale raw value
+			v *= counterDef.scale
+
+			// Save current state
+			counterDef.currentState = v
 
 			// Send absolut values
 			if m.config.SendAbsoluteValues {
-				if y, err := lp.New(counterName, info.tagSet, m.meta, map[string]interface{}{"value": v}, now); err == nil {
+				if y, err :=
+					lp.NewMessage(
+						counterDef.name,
+						info.tagSet,
+						m.meta,
+						map[string]interface{}{
+							"value": counterDef.currentState,
+						},
+						now); err == nil {
 					y.AddMeta("unit", counterDef.unit)
 					output <- y
 				}
@@ -202,18 +252,64 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 
 			// 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 {
+				if counterDef.lastState >= 0 {
+					rate := float64((counterDef.currentState - counterDef.lastState)) / timeDiff
+					if y, err :=
+						lp.NewMessage(
+							counterDef.name+"_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
+				counterDef.lastState = counterDef.currentState
+			}
+
+			// Sum up total values
+			if m.config.SendTotalValues {
+				switch {
+				case counterDef.addToIBTotal:
+					ib_total += counterDef.currentState
+				case counterDef.addToIBTotalPkgs:
+					ib_total_pkts += counterDef.currentState
+				}
 			}
 		}
 
+		// Send total values
+		if m.config.SendTotalValues {
+			if y, err :=
+				lp.NewMessage(
+					"ib_total",
+					info.tagSet,
+					m.meta,
+					map[string]interface{}{
+						"value": ib_total,
+					},
+					now); err == nil {
+				y.AddMeta("unit", "bytes")
+				output <- y
+			}
+
+			if y, err :=
+				lp.NewMessage(
+					"ib_total_pkts",
+					info.tagSet,
+					m.meta,
+					map[string]interface{}{
+						"value": ib_total_pkts,
+					},
+					now); err == nil {
+				y.AddMeta("unit", "packets")
+				output <- y
+			}
+		}
 	}
 }
 

collectors/infinibandMetric.md

@@ -1,3 +1,13 @@
+<!--
+---
+title: InfiniBand Metric collector
+description: Collect metrics for InfiniBand devices
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/infiniband.md
+---
+-->
 
 ## `ibstat` collector
 
@@ -17,13 +27,16 @@ LID file (`/sys/class/infiniband/<dev>/ports/<port>/lid`)
 
 The devices can be filtered with the `exclude_devices` option in the configuration.
 
-For each found LID the collector reads data through the sysfs files below `/sys/class/infiniband/<device>`.
+For each found LID the collector reads data through the sysfs files below `/sys/class/infiniband/<device>`. (See: <https://www.kernel.org/doc/Documentation/ABI/stable/sysfs-class-infiniband>)
 
 Metrics:
+
 * `ib_recv`
 * `ib_xmit`
 * `ib_recv_pkts`
 * `ib_xmit_pkts`
+* `ib_total = ib_recv + ib_xmit` (if `send_total_values == true`)
+* `ib_total_pkts = ib_recv_pkts + ib_xmit_pkts` (if `send_total_values == true`)
 * `ib_recv_bw` (if `send_derived_values == true`)
 * `ib_xmit_bw` (if `send_derived_values == true`)
 * `ib_recv_pkts_bw` (if `send_derived_values == true`)

collectors/iostatMetric.go

@@ -1,25 +1,32 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
 	"bufio"
-	"os"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-
-	//	"log"
 	"encoding/json"
 	"errors"
+	"os"
 	"strconv"
 	"strings"
 	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
+// Konstante für den Pfad zu /proc/diskstats
 const IOSTATFILE = `/proc/diskstats`
-const IOSTAT_SYSFSPATH = `/sys/block`
 
 type IOstatCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+	// Neues Feld zum Ausschließen von Devices per JSON-Konfiguration
+	ExcludeDevices []string `json:"exclude_devices,omitempty"`
 }
 
 type IOstatCollectorEntry struct {
@@ -76,7 +83,7 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
 	if len(m.matches) == 0 {
 		return errors.New("no metrics to collect")
 	}
-	file, err := os.Open(string(IOSTATFILE))
+	file, err := os.Open(IOSTATFILE)
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return err
@@ -87,17 +94,24 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
 	for scanner.Scan() {
 		line := scanner.Text()
 		linefields := strings.Fields(line)
+		if len(linefields) < 3 {
+			continue
+		}
 		device := linefields[2]
+
 		if strings.Contains(device, "loop") {
 			continue
 		}
+		if _, skip := stringArrayContains(m.config.ExcludeDevices, device); skip {
+			continue
+		}
 		values := make(map[string]int64)
 		for m := range m.matches {
 			values[m] = 0
 		}
 		m.devices[device] = IOstatCollectorEntry{
 			tags: map[string]string{
-				"device": linefields[2],
+				"device": device,
 				"type":   "node",
 			},
 			lastValues: values,
@@ -107,12 +121,12 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
 	return err
 }
 
-func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
 
-	file, err := os.Open(string(IOSTATFILE))
+	file, err := os.Open(IOSTATFILE)
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return
@@ -126,10 +140,16 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 			continue
 		}
 		linefields := strings.Fields(line)
+		if len(linefields) < 3 {
+			continue
+		}
 		device := linefields[2]
 		if strings.Contains(device, "loop") {
 			continue
 		}
+		if _, skip := stringArrayContains(m.config.ExcludeDevices, device); skip {
+			continue
+		}
 		if _, ok := m.devices[device]; !ok {
 			continue
 		}
@@ -139,7 +159,7 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 				x, err := strconv.ParseInt(linefields[idx], 0, 64)
 				if err == nil {
 					diff := x - entry.lastValues[name]
-					y, err := lp.New(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now())
+					y, err := lp.NewMessage(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now())
 					if err == nil {
 						output <- y
 					}

collectors/iostatMetric.md

@@ -1,15 +1,30 @@
+<!--
+---
+title: IOStat Metric collector
+description: Collect metrics from `/proc/diskstats`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/iostat.md
+---
+-->
 
 ## `iostat` collector
 
 ```json
   "iostat": {
     "exclude_metrics": [
-      "read_ms"
+      "io_read_ms"
     ],
+    "exclude_devices": [
+      "nvme0n1p1",
+      "nvme0n1p2",
+      "md127"
+    ]
   }
 ```
 
-The `iostat` collector reads data from `/proc/diskstats` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
+The `iostat` collector reads data from `/proc/diskstats` and outputs a handful **node** metrics. If a metric or device is not required, it can be excluded from forwarding it to the sink.
 
 Metrics:
 * `io_reads`

collectors/ipmiMetric.go

@@ -1,86 +1,123 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
+	"bufio"
+	"bytes"
 	"encoding/json"
 	"errors"
+	"fmt"
+	"io"
 	"log"
-	"os"
 	"os/exec"
 	"strconv"
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
-const IPMITOOL_PATH = `ipmitool`
 const IPMISENSORS_PATH = `ipmi-sensors`
 
-type IpmiCollectorConfig struct {
-	ExcludeDevices  []string `json:"exclude_devices"`
-	IpmitoolPath    string   `json:"ipmitool_path"`
-	IpmisensorsPath string   `json:"ipmisensors_path"`
-}
-
 type IpmiCollector struct {
 	metricCollector
-	//tags        map[string]string
-	//matches     map[string]string
-	config      IpmiCollectorConfig
+	config struct {
+		ExcludeDevices  []string `json:"exclude_devices"`
+		IpmitoolPath    string   `json:"ipmitool_path"`
+		IpmisensorsPath string   `json:"ipmisensors_path"`
+	}
 	ipmitool    string
 	ipmisensors string
 }
 
 func (m *IpmiCollector) Init(config json.RawMessage) error {
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+
 	m.name = "IpmiCollector"
 	m.setup()
 	m.parallel = true
-	m.meta = map[string]string{"source": m.name, "group": "IPMI"}
-	m.config.IpmitoolPath = string(IPMITOOL_PATH)
-	m.config.IpmisensorsPath = string(IPMISENSORS_PATH)
-	m.ipmitool = ""
-	m.ipmisensors = ""
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "IPMI",
+	}
+	// default path to IPMI tools
+	m.config.IpmitoolPath = "ipmitool"
+	m.config.IpmisensorsPath = "ipmi-sensors"
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
+	// Check if executables ipmitool or ipmisensors are found
 	p, err := exec.LookPath(m.config.IpmitoolPath)
 	if err == nil {
-		m.ipmitool = p
+		command := exec.Command(p)
+		err := command.Run()
+		if err != nil {
+			cclog.ComponentError(m.name, fmt.Sprintf("Failed to execute %s: %v", p, err.Error()))
+			m.ipmitool = ""
+		} else {
+			m.ipmitool = p
+		}
 	}
 	p, err = exec.LookPath(m.config.IpmisensorsPath)
 	if err == nil {
-		m.ipmisensors = p
+		command := exec.Command(p)
+		err := command.Run()
+		if err != nil {
+			cclog.ComponentError(m.name, fmt.Sprintf("Failed to execute %s: %v", p, err.Error()))
+			m.ipmisensors = ""
+		} else {
+			m.ipmisensors = p
+		}
 	}
 	if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
-		return errors.New("no IPMI reader found")
+		return errors.New("no usable IPMI reader found")
 	}
+
 	m.init = true
 	return nil
 }
 
-func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
+func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
+
+	// Setup ipmitool command
 	command := exec.Command(cmd, "sensor")
-	command.Wait()
-	stdout, err := command.Output()
-	if err != nil {
-		log.Print(err)
+	stdout, _ := command.StdoutPipe()
+	errBuf := new(bytes.Buffer)
+	command.Stderr = errBuf
+
+	// start command
+	if err := command.Start(); err != nil {
+		cclog.ComponentError(
+			m.name,
+			fmt.Sprintf("readIpmiTool(): Failed to start command \"%s\": %v", command.String(), err),
+		)
 		return
 	}
 
-	ll := strings.Split(string(stdout), "\n")
-
-	for _, line := range ll {
-		lv := strings.Split(line, "|")
+	// Read command output
+	scanner := bufio.NewScanner(stdout)
+	for scanner.Scan() {
+		lv := strings.Split(scanner.Text(), "|")
 		if len(lv) < 3 {
 			continue
 		}
-		v, err := strconv.ParseFloat(strings.Trim(lv[1], " "), 64)
+		v, err := strconv.ParseFloat(strings.TrimSpace(lv[1]), 64)
 		if err == nil {
-			name := strings.ToLower(strings.Replace(strings.Trim(lv[0], " "), " ", "_", -1))
-			unit := strings.Trim(lv[2], " ")
+			name := strings.ToLower(strings.Replace(strings.TrimSpace(lv[0]), " ", "_", -1))
+			unit := strings.TrimSpace(lv[2])
 			if unit == "Volts" {
 				unit = "Volts"
 			} else if unit == "degrees C" {
@@ -91,16 +128,27 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
 				unit = "Watts"
 			}
 
-			y, err := lp.New(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
+			y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", unit)
 				output <- y
 			}
 		}
 	}
+
+	// Wait for command end
+	if err := command.Wait(); err != nil {
+		errMsg, _ := io.ReadAll(errBuf)
+		cclog.ComponentError(
+			m.name,
+			fmt.Sprintf("readIpmiTool(): Failed to wait for the end of command \"%s\": %v\n", command.String(), err),
+		)
+		cclog.ComponentError(m.name, fmt.Sprintf("readIpmiTool(): command stderr: \"%s\"\n", strings.TrimSpace(string(errMsg))))
+		return
+	}
 }
 
-func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
+func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) {
 
 	command := exec.Command(cmd, "--comma-separated-output", "--sdr-cache-recreate")
 	command.Wait()
@@ -118,7 +166,7 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
 			v, err := strconv.ParseFloat(lv[3], 64)
 			if err == nil {
 				name := strings.ToLower(strings.Replace(lv[1], " ", "_", -1))
-				y, err := lp.New(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
+				y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
 				if err == nil {
 					if len(lv) > 4 {
 						y.AddMeta("unit", lv[4])
@@ -130,17 +178,17 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
 	}
 }
 
-func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+
+	// Check if already initialized
+	if !m.init {
+		return
+	}
+
 	if len(m.config.IpmitoolPath) > 0 {
-		_, err := os.Stat(m.config.IpmitoolPath)
-		if err == nil {
-			m.readIpmiTool(m.config.IpmitoolPath, output)
-		}
+		m.readIpmiTool(m.config.IpmitoolPath, output)
 	} else if len(m.config.IpmisensorsPath) > 0 {
-		_, err := os.Stat(m.config.IpmisensorsPath)
-		if err == nil {
-			m.readIpmiSensors(m.config.IpmisensorsPath, output)
-		}
+		m.readIpmiSensors(m.config.IpmisensorsPath, output)
 	}
 }
 

collectors/ipmiMetric.md

@@ -1,3 +1,13 @@
+<!--
+---
+title: IPMI Metric collector
+description: Collect metrics using ipmitool or ipmi-sensors
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/ipmi.md
+---
+-->
 
 ## `ipmistat` collector
 
@@ -8,9 +18,6 @@
   }
 ```
 
-The `ipmistat` collector reads data from `ipmitool` (`ipmitool sensor`) or `ipmi-sensors` (`ipmi-sensors --sdr-cache-recreate --comma-separated-output`). 
+The `ipmistat` collector reads data from `ipmitool` (`ipmitool sensor`) or `ipmi-sensors` (`ipmi-sensors --sdr-cache-recreate --comma-separated-output`).
 
 The metrics depend on the output of the underlying tools but contain temperature, power and energy metrics.
-
-
-

collectors/likwidMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 /*
@@ -12,10 +19,10 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"io/ioutil"
 	"math"
 	"os"
 	"os/signal"
+	"os/user"
 	"sort"
 	"strconv"
 	"strings"
@@ -24,25 +31,31 @@ import (
 	"time"
 	"unsafe"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
+	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 	"github.com/NVIDIA/go-nvml/pkg/dl"
+	"github.com/fsnotify/fsnotify"
+	"golang.design/x/thread"
 )
 
 const (
 	LIKWID_LIB_NAME       = "liblikwid.so"
 	LIKWID_LIB_DL_FLAGS   = dl.RTLD_LAZY | dl.RTLD_GLOBAL
 	LIKWID_DEF_ACCESSMODE = "direct"
+	LIKWID_DEF_LOCKFILE   = "/var/run/likwid.lock"
 )
 
 type LikwidCollectorMetricConfig struct {
-	Name    string `json:"name"` // Name of the metric
-	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
+	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, hwthread, ...)
+	Publish            bool   `json:"publish"`
+	SendCoreTotalVal   bool   `json:"send_core_total_values,omitempty"`
+	SendSocketTotalVal bool   `json:"send_socket_total_values,omitempty"`
+	SendNodeTotalVal   bool   `json:"send_node_total_values,omitempty"`
+	Unit               string `json:"unit"` // Unit of metric if any
 }
 
 type LikwidCollectorEventsetConfig struct {
@@ -56,7 +69,7 @@ type LikwidEventsetConfig struct {
 	eorder   []*C.char
 	estr     *C.char
 	go_estr  string
-	results  map[int]map[string]interface{}
+	results  map[int]map[string]float64
 	metrics  map[int]map[string]float64
 }
 
@@ -68,22 +81,28 @@ type LikwidCollectorConfig struct {
 	AccessMode     string                          `json:"access_mode,omitempty"`
 	DaemonPath     string                          `json:"accessdaemon_path,omitempty"`
 	LibraryPath    string                          `json:"liblikwid_path,omitempty"`
+	LockfilePath   string                          `json:"lockfile_path,omitempty"`
 }
 
 type LikwidCollector struct {
 	metricCollector
-	cpulist      []C.int
-	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
+	cpulist       []C.int
+	cpu2tid       map[int]int
+	sock2tid      map[int]int
+	tid2core      map[int]int
+	tid2socket    map[int]int
+	metrics       map[C.int]map[string]int
+	groups        []C.int
+	config        LikwidCollectorConfig
+	basefreq      float64
+	running       bool
+	initialized   bool
+	needs_reinit  bool
+	myuid         int
+	lock_err_once bool
+	likwidGroups  map[C.int]LikwidEventsetConfig
+	lock          sync.Mutex
+	measureThread thread.Thread
 }
 
 type LikwidMetric struct {
@@ -93,6 +112,18 @@ type LikwidMetric struct {
 	group_idx int
 }
 
+func checkMetricType(t string) bool {
+	valid := map[string]bool{
+		"node":         true,
+		"socket":       true,
+		"hwthread":     true,
+		"core":         true,
+		"memoryDomain": true,
+	}
+	_, ok := valid[t]
+	return ok
+}
+
 func eventsToEventStr(events map[string]string) string {
 	elist := make([]string, 0)
 	for k, v := range events {
@@ -116,10 +147,10 @@ func genLikwidEventSet(input LikwidCollectorEventsetConfig) LikwidEventsetConfig
 		elist = append(elist, c_counter)
 	}
 	estr := strings.Join(tmplist, ",")
-	res := make(map[int]map[string]interface{})
+	res := make(map[int]map[string]float64)
 	met := make(map[int]map[string]float64)
 	for _, i := range topo.CpuList() {
-		res[i] = make(map[string]interface{})
+		res[i] = make(map[string]float64)
 		for k := range input.Events {
 			res[i][k] = 0.0
 		}
@@ -139,7 +170,7 @@ func genLikwidEventSet(input LikwidCollectorEventsetConfig) LikwidEventsetConfig
 }
 
 func testLikwidMetricFormula(formula string, params []string) bool {
-	myparams := make(map[string]interface{})
+	myparams := make(map[string]float64)
 	for _, p := range params {
 		myparams[p] = float64(1.0)
 	}
@@ -154,34 +185,34 @@ func getBaseFreq() float64 {
 	}
 	var freq float64 = math.NaN()
 	for _, f := range files {
-		buffer, err := ioutil.ReadFile(f)
+		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) * 1e6
+				freq = float64(x)
+				break
 			}
 		}
 	}
 
 	if math.IsNaN(freq) {
-		C.power_init(0)
-		info := C.get_powerInfo()
-		if float64(info.baseFrequency) != 0 {
-			freq = float64(info.baseFrequency) * 1e6
-		}
-		C.power_finalize()
+		C.timer_init()
+		freq = float64(C.timer_getCycleClock()) / 1e3
 	}
-	return freq
+	return freq * 1e3
 }
 
 func (m *LikwidCollector) Init(config json.RawMessage) error {
 	m.name = "LikwidCollector"
 	m.parallel = false
 	m.initialized = false
+	m.needs_reinit = true
 	m.running = false
+	m.myuid = os.Getuid()
 	m.config.AccessMode = LIKWID_DEF_ACCESSMODE
 	m.config.LibraryPath = LIKWID_LIB_NAME
+	m.config.LockfilePath = LIKWID_DEF_LOCKFILE
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -215,13 +246,6 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 
 	m.likwidGroups = make(map[C.int]LikwidEventsetConfig)
 
-	// m.results = make(map[int]map[int]map[string]interface{})
-	// m.mresults = make(map[int]map[int]map[string]float64)
-	m.gmresults = make(map[int]map[string]float64)
-	for _, tid := range m.cpu2tid {
-		m.gmresults[tid] = make(map[string]float64)
-	}
-
 	// This is for the global metrics computation test
 	totalMetrics := 0
 	// Generate parameter list for the metric computing test
@@ -239,12 +263,16 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 			}
 			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
+				cclog.ComponentDebug(m.name, "Checking", metric.Name)
+				if !checkMetricType(metric.Type) {
+					cclog.ComponentError(m.name, "Metric", metric.Name, "uses invalid type", metric.Type)
+					metric.Calc = ""
+				} else if !testLikwidMetricFormula(metric.Calc, params) {
+					cclog.ComponentError(m.name, "Metric", metric.Name, "cannot be calculated with given counters")
+					metric.Calc = ""
+				} else {
 					globalParams = append(globalParams, metric.Name)
 					totalMetrics++
-				} else {
-					metric.Calc = ""
 				}
 			}
 		} else {
@@ -254,8 +282,14 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 	}
 	for _, metric := range m.config.Metrics {
 		// Try to evaluate the global metric
-		if !testLikwidMetricFormula(metric.Calc, globalParams) {
-			cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed")
+		if !checkMetricType(metric.Type) {
+			cclog.ComponentError(m.name, "Metric", metric.Name, "uses invalid type", metric.Type)
+			metric.Calc = ""
+		} else if !testLikwidMetricFormula(metric.Calc, globalParams) {
+			cclog.ComponentError(m.name, "Metric", metric.Name, "cannot be calculated with given counters")
+			metric.Calc = ""
+		} else if !checkMetricType(metric.Type) {
+			cclog.ComponentError(m.name, "Metric", metric.Name, "has invalid type")
 			metric.Calc = ""
 		} else {
 			totalMetrics++
@@ -268,78 +302,275 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 		cclog.ComponentError(m.name, err.Error())
 		return err
 	}
+
+	ret := C.topology_init()
+	if ret != 0 {
+		err := errors.New("failed to initialize topology module")
+		cclog.ComponentError(m.name, err.Error())
+		return err
+	}
+	m.measureThread = thread.New()
+	switch m.config.AccessMode {
+	case "direct":
+		C.HPMmode(0)
+	case "accessdaemon":
+		if len(m.config.DaemonPath) > 0 {
+			p := os.Getenv("PATH")
+			os.Setenv("PATH", m.config.DaemonPath+":"+p)
+		}
+		C.HPMmode(1)
+		retCode := C.HPMinit()
+		if retCode != 0 {
+			err := fmt.Errorf("C.HPMinit() failed with return code %v", retCode)
+			cclog.ComponentError(m.name, err.Error())
+		}
+		for _, c := range m.cpulist {
+			m.measureThread.Call(
+				func() {
+					retCode := C.HPMaddThread(c)
+					if retCode != 0 {
+						err := fmt.Errorf("C.HPMaddThread(%v) failed with return code %v", c, retCode)
+						cclog.ComponentError(m.name, err.Error())
+					}
+				})
+		}
+	}
+	m.sock2tid = make(map[int]int)
+	tmp := make([]C.int, 1)
+	for _, sid := range topo.SocketList() {
+		cstr := C.CString(fmt.Sprintf("S%d:0", sid))
+		ret = C.cpustr_to_cpulist(cstr, &tmp[0], 1)
+		if ret > 0 {
+			m.sock2tid[sid] = m.cpu2tid[int(tmp[0])]
+		}
+		C.free(unsafe.Pointer(cstr))
+	}
+
+	cpuData := topo.CpuData()
+	m.tid2core = make(map[int]int, len(cpuData))
+	m.tid2socket = make(map[int]int, len(cpuData))
+	for i := range cpuData {
+		c := &cpuData[i]
+		// Hardware thread ID to core ID mapping
+		if len(c.CoreCPUsList) > 0 {
+			m.tid2core[c.CpuID] = c.CoreCPUsList[0]
+		} else {
+			m.tid2core[c.CpuID] = c.CpuID
+		}
+		// Hardware thead ID to socket ID mapping
+		m.tid2socket[c.CpuID] = c.Socket
+	}
+
+	m.basefreq = getBaseFreq()
 	m.init = true
 	return nil
 }
 
 // take a measurement for 'interval' seconds of event set index 'group'
-func (m *LikwidCollector) takeMeasurement(evset LikwidEventsetConfig, interval time.Duration) (bool, error) {
+func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig, interval time.Duration) (bool, error) {
 	var ret C.int
-	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)
+	var gid C.int = -1
+	sigchan := make(chan os.Signal, 1)
+
+	// Watch changes for the lock file ()
+	watcher, err := fsnotify.NewWatcher()
+	if err != nil {
+		cclog.ComponentError(m.name, err.Error())
+		return true, err
+	}
+	defer watcher.Close()
+	if len(m.config.LockfilePath) > 0 {
+		// Check if the lock file exists
+		info, err := os.Stat(m.config.LockfilePath)
+		if os.IsNotExist(err) {
+			// Create the lock file if it does not exist
+			file, createErr := os.Create(m.config.LockfilePath)
+			if createErr != nil {
+				return true, fmt.Errorf("failed to create lock file: %v", createErr)
 			}
-			m.lock.Unlock()
-			return skip, err
+			file.Close()
+			info, err = os.Stat(m.config.LockfilePath) // Recheck the file after creation
 		}
-		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
+		if err != nil {
+			return true, 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
+		// Check file ownership
+		uid := info.Sys().(*syscall.Stat_t).Uid
+		if uid != uint32(m.myuid) {
+			usr, err := user.LookupId(fmt.Sprint(uid))
+			if err == nil {
+				err = fmt.Errorf("access to performance counters locked by %s", usr.Username)
 			} else {
-				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
+				err = fmt.Errorf("access to performance counters locked by %d", uid)
 			}
-			m.lock.Unlock()
-			return skip, err
+			// delete error if we already returned the error once.
+			if !m.lock_err_once {
+				m.lock_err_once = true
+			} else {
+				err = nil
+			}
+			return true, err
+		}
+		// reset lock_err_once
+		m.lock_err_once = false
+
+		// Add the lock file to the watcher
+		err = watcher.Add(m.config.LockfilePath)
+		if err != nil {
+			cclog.ComponentError(m.name, err.Error())
 		}
 	}
-	m.lock.Unlock()
-	return false, nil
-}
+	m.lock.Lock()
+	defer m.lock.Unlock()
 
-// Get all measurement results for an event set, derive the metric values out of the measurement results and send it
-func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
-	invClock := float64(1.0 / m.basefreq)
+	// Initialize the performance monitoring feature by creating basic data structures
+	select {
+	case e := <-watcher.Events:
+		ret = -1
+		if e.Op != fsnotify.Chmod {
+			ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
+		}
+	default:
+		ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
+	}
+	if ret != 0 {
+		return true, fmt.Errorf("failed to initialize library, error %d", ret)
+	}
+	signal.Notify(sigchan, os.Interrupt)
+	signal.Notify(sigchan, syscall.SIGCHLD)
 
-	// Go over events and get the results
+	// Add an event string to LIKWID
+	select {
+	case <-sigchan:
+		gid = -1
+	case e := <-watcher.Events:
+		gid = -1
+		if e.Op != fsnotify.Chmod {
+			gid = C.perfmon_addEventSet(evset.estr)
+		}
+	default:
+		gid = C.perfmon_addEventSet(evset.estr)
+	}
+	if gid < 0 {
+		return true, fmt.Errorf("failed to add events %s, id %d, error %d", evset.go_estr, evidx, gid)
+	}
+
+	// Setup all performance monitoring counters of an eventSet
+	select {
+	case <-sigchan:
+		ret = -1
+	case e := <-watcher.Events:
+		if e.Op != fsnotify.Chmod {
+			ret = C.perfmon_setupCounters(gid)
+		}
+	default:
+		ret = C.perfmon_setupCounters(gid)
+	}
+	if ret != 0 {
+		return true, fmt.Errorf("failed to setup events '%s', error %d", evset.go_estr, ret)
+	}
+
+	// Start counters
+	select {
+	case <-sigchan:
+		ret = -1
+	case e := <-watcher.Events:
+		if e.Op != fsnotify.Chmod {
+			ret = C.perfmon_startCounters()
+		}
+	default:
+		ret = C.perfmon_startCounters()
+	}
+	if ret != 0 {
+		return true, fmt.Errorf("failed to start events '%s', error %d", evset.go_estr, ret)
+	}
+	select {
+	case <-sigchan:
+		ret = -1
+	case e := <-watcher.Events:
+		if e.Op != fsnotify.Chmod {
+			ret = C.perfmon_readCounters()
+		}
+	default:
+		ret = C.perfmon_readCounters()
+	}
+	if ret != 0 {
+		return true, fmt.Errorf("failed to read events '%s', error %d", evset.go_estr, ret)
+	}
+
+	// Wait
+	time.Sleep(interval)
+
+	// Read counters
+	select {
+	case <-sigchan:
+		ret = -1
+	case e := <-watcher.Events:
+		if e.Op != fsnotify.Chmod {
+			ret = C.perfmon_readCounters()
+		}
+	default:
+		ret = C.perfmon_readCounters()
+	}
+	if ret != 0 {
+		return true, fmt.Errorf("failed to read events '%s', error %d", evset.go_estr, ret)
+	}
+
+	// Store counters
 	for eidx, counter := range evset.eorder {
 		gctr := C.GoString(counter)
 		for _, tid := range m.cpu2tid {
-			res := C.perfmon_getLastResult(evset.gid, C.int(eidx), C.int(tid))
+			res := C.perfmon_getLastResult(gid, C.int(eidx), C.int(tid))
 			fres := float64(res)
 			if m.config.InvalidToZero && (math.IsNaN(fres) || math.IsInf(fres, 0)) {
 				fres = 0.0
 			}
 			evset.results[tid][gctr] = fres
-			evset.results[tid]["time"] = interval.Seconds()
-			evset.results[tid]["inverseClock"] = invClock
 		}
 	}
 
+	// Store time in seconds the event group was measured the last time
+	for _, tid := range m.cpu2tid {
+		evset.results[tid]["time"] = float64(C.perfmon_getLastTimeOfGroup(gid))
+	}
+
+	// Stop counters
+	select {
+	case <-sigchan:
+		ret = -1
+	case e := <-watcher.Events:
+		if e.Op != fsnotify.Chmod {
+			ret = C.perfmon_stopCounters()
+		}
+	default:
+		ret = C.perfmon_stopCounters()
+	}
+	if ret != 0 {
+		return true, fmt.Errorf("failed to stop events '%s', error %d", evset.go_estr, ret)
+	}
+
+	// Deallocates all internal data that is used during performance monitoring
+	signal.Stop(sigchan)
+	select {
+	case e := <-watcher.Events:
+		if e.Op != fsnotify.Chmod {
+			C.perfmon_finalize()
+		}
+	default:
+		C.perfmon_finalize()
+	}
+	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(evset LikwidEventsetConfig, interval time.Duration, output chan lp.CCMessage) error {
+	invClock := float64(1.0 / m.basefreq)
+
+	for _, tid := range m.cpu2tid {
+		evset.results[tid]["inverseClock"] = invClock
+		evset.results[tid]["gotime"] = interval.Seconds()
+	}
+
 	// Go over the event set metrics, derive the value out of the event:counter values and send it
 	for _, metric := range m.config.Eventsets[evset.internal].Metrics {
 		// The metric scope is determined in the Init() function
@@ -348,6 +579,9 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
 		if metric.Type == "socket" {
 			scopemap = m.sock2tid
 		}
+		// Send all metrics with same time stamp
+		// This function does only computiation, counter measurement is done before
+		now := time.Now()
 		for domain, tid := range scopemap {
 			if tid >= 0 && len(metric.Calc) > 0 {
 				value, err := agg.EvalFloat64Condition(metric.Calc, evset.results[tid])
@@ -360,31 +594,151 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
 				}
 				evset.metrics[tid][metric.Name] = value
 				// Now we have the result, send it with the proper tags
-				if !math.IsNaN(value) {
-					if metric.Publish {
-						fields := map[string]interface{}{"value": value}
-						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
+				if !math.IsNaN(value) && metric.Publish {
+					fields := map[string]interface{}{"value": value}
+					y, err :=
+						lp.NewMessage(
+							metric.Name,
+							map[string]string{
+								"type": metric.Type,
+							},
+							m.meta,
+							fields,
+							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
 					}
 				}
 			}
 		}
+
+		// Send per core aggregated values
+		if metric.SendCoreTotalVal {
+			totalCoreValues := make(map[int]float64)
+			for _, tid := range scopemap {
+				if tid >= 0 && len(metric.Calc) > 0 {
+					coreID := m.tid2core[tid]
+					value := evset.metrics[tid][metric.Name]
+					if !math.IsNaN(value) && metric.Publish {
+						totalCoreValues[coreID] += value
+					}
+				}
+			}
+
+			for coreID, value := range totalCoreValues {
+				y, err :=
+					lp.NewMessage(
+						metric.Name,
+						map[string]string{
+							"type":    "core",
+							"type-id": fmt.Sprintf("%d", coreID),
+						},
+						m.meta,
+						map[string]interface{}{
+							"value": value,
+						},
+						now,
+					)
+				if err != nil {
+					continue
+				}
+				if len(metric.Unit) > 0 {
+					y.AddMeta("unit", metric.Unit)
+				}
+				output <- y
+			}
+		}
+
+		// Send per socket aggregated values
+		if metric.SendSocketTotalVal {
+			totalSocketValues := make(map[int]float64)
+			for _, tid := range scopemap {
+				if tid >= 0 && len(metric.Calc) > 0 {
+					socketID := m.tid2socket[tid]
+					value := evset.metrics[tid][metric.Name]
+					if !math.IsNaN(value) && metric.Publish {
+						totalSocketValues[socketID] += value
+					}
+				}
+			}
+
+			for socketID, value := range totalSocketValues {
+				y, err :=
+					lp.NewMessage(
+						metric.Name,
+						map[string]string{
+							"type":    "socket",
+							"type-id": fmt.Sprintf("%d", socketID),
+						},
+						m.meta,
+						map[string]interface{}{
+							"value": value,
+						},
+						now,
+					)
+				if err != nil {
+					continue
+				}
+				if len(metric.Unit) > 0 {
+					y.AddMeta("unit", metric.Unit)
+				}
+				output <- y
+			}
+		}
+
+		// Send per node aggregated value
+		if metric.SendNodeTotalVal {
+			var totalNodeValue float64 = 0.0
+			for _, tid := range scopemap {
+				if tid >= 0 && len(metric.Calc) > 0 {
+					value := evset.metrics[tid][metric.Name]
+					if !math.IsNaN(value) && metric.Publish {
+						totalNodeValue += value
+					}
+				}
+			}
+
+			y, err :=
+				lp.NewMessage(
+					metric.Name,
+					map[string]string{
+						"type": "node",
+					},
+					m.meta,
+					map[string]interface{}{
+						"value": totalNodeValue,
+					},
+					now,
+				)
+			if err != nil {
+				continue
+			}
+			if len(metric.Unit) > 0 {
+				y.AddMeta("unit", metric.Unit)
+			}
+			output <- y
+		}
 	}
 
 	return nil
 }
 
 // Go over the global metrics, derive the value out of the event sets' metric values and send it
-func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan lp.CCMetric) error {
+func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, interval time.Duration, output chan lp.CCMessage) error {
+	// Send all metrics with same time stamp
+	// This function does only computiation, counter measurement is done before
+	now := time.Now()
+
 	for _, metric := range m.config.Metrics {
+		// The metric scope is determined in the Init() function
+		// Get the map scope-id -> tids
 		scopemap := m.cpu2tid
 		if metric.Type == "socket" {
 			scopemap = m.sock2tid
@@ -392,12 +746,13 @@ func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan
 		for domain, tid := range scopemap {
 			if tid >= 0 {
 				// Here we generate parameter list
-				params := make(map[string]interface{})
-				for _, evset := range m.likwidGroups {
+				params := make(map[string]float64)
+				for _, evset := range groups {
 					for mname, mres := range evset.metrics[tid] {
 						params[mname] = mres
 					}
 				}
+				params["gotime"] = interval.Seconds()
 				// Evaluate the metric
 				value, err := agg.EvalFloat64Condition(metric.Calc, params)
 				if err != nil {
@@ -407,13 +762,21 @@ func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan
 				if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {
 					value = 0.0
 				}
-				m.gmresults[tid][metric.Name] = value
 				// Now we have the result, send it with the proper tags
 				if !math.IsNaN(value) {
 					if metric.Publish {
-						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())
+						y, err :=
+							lp.NewMessage(
+								metric.Name,
+								map[string]string{
+									"type": metric.Type,
+								},
+								m.meta,
+								map[string]interface{}{
+									"value": value,
+								},
+								now,
+							)
 						if err == nil {
 							if metric.Type != "node" {
 								y.AddTag("type-id", fmt.Sprintf("%d", domain))
@@ -431,163 +794,52 @@ 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
-	}
+func (m *LikwidCollector) ReadThread(interval time.Duration, output chan lp.CCMessage) {
+	var err error = nil
+	groups := make([]LikwidEventsetConfig, 0)
 
-	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
-				}
+	for evidx, evset := range m.config.Eventsets {
+		e := genLikwidEventSet(evset)
+		e.internal = evidx
+		skip := false
+		if !skip {
+			// measure event set 'i' for 'interval' seconds
+			skip, err = m.takeMeasurement(evidx, e, interval)
+			if err != nil {
+				cclog.ComponentError(m.name, err.Error())
+				return
 			}
-			if skip {
-				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 !skip {
+			// read measurements and derive event set metrics
+			m.calcEventsetMetrics(e, interval, output)
+			groups = append(groups, e)
+		}
 	}
-
-	// 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
+	if len(groups) > 0 {
+		// calculate global metrics
+		m.calcGlobalMetrics(groups, interval, output)
 	}
-	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
+func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
-
-	if !m.initialized {
-		m.lock.Lock()
-		err = m.LateInit()
-		if err != nil {
-			m.lock.Unlock()
-			return
-		}
-		m.initialized = true
-		m.lock.Unlock()
-	}
-
-	if m.initialized && !skip {
-		for _, evset := range m.likwidGroups {
-			if !skip {
-				// measure event set 'i' for 'interval' seconds
-				skip, err = m.takeMeasurement(evset, interval)
-				if err != nil {
-					cclog.ComponentError(m.name, err.Error())
-					return
-				}
-			}
-
-			if !skip {
-				// read measurements and derive event set metrics
-				m.calcEventsetMetrics(evset, interval, output)
-			}
-		}
-		if !skip {
-			// use the event set metrics to derive the global metrics
-			m.calcGlobalMetrics(interval, output)
-		}
-	}
+	m.measureThread.Call(func() {
+		m.ReadThread(interval, output)
+	})
 }
 
 func (m *LikwidCollector) Close() {
 	if m.init {
 		m.init = false
-		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
-		}
+		m.measureThread.Terminate()
+		m.initialized = false
 		m.lock.Unlock()
-		cclog.ComponentDebug(m.name, "Finalize LIKWID topology module")
 		C.topology_finalize()
-
-		cclog.ComponentDebug(m.name, "Closing done")
 	}
 }

collectors/likwidMetric.md

@@ -1,3 +1,13 @@
+<!--
+---
+title: LIKWID collector
+description: Collect hardware performance events and metrics using LIKWID
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/likwid.md
+---
+-->
 
 ## `likwid` collector
 
@@ -7,11 +17,15 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
   "likwid": {
     "force_overwrite" : false,
     "invalid_to_zero" : false,
+    "liblikwid_path" : "/path/to/liblikwid.so",
+    "accessdaemon_path" : "/folder/that/contains/likwid-accessD",
+    "access_mode" : "direct or accessdaemon or perf_event",
+    "lockfile_path" : "/var/run/likwid.lock",
     "eventsets": [
       {
         "events" : {
           "COUNTER0": "EVENT0",
-          "COUNTER1": "EVENT1",
+          "COUNTER1": "EVENT1"
         },
         "metrics" : [
           {
@@ -23,7 +37,7 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
           }
         ]
       }
-    ]
+    ],
     "globalmetrics" : [
       {
         "name": "global_sum",
@@ -37,34 +51,39 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
 ```
 
 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.
+- The `globalmetrics` are metrics which require data from multiple event set measurements to be derived. The inputs are the metrics in the event sets. Similar to the metrics in the event sets, the global metrics are defined by a name, a formula, a type and a publish flag. See event set metrics for details. The only difference is that there is no access to the raw event measurements anymore but only to the metrics. Also `time` and `inverseClock` cannot be used anymore. So, the idea is to derive a metric in the `eventsets` section and reuse it in the `globalmetrics` part. If you need a metric only for deriving the global metrics, disable forwarding of the event set metrics (`"publish": false`). **Be aware** that the combination might be misleading because the "behavior" of a metric changes over time and the multiple measurements might count different computing phases. Similar to the metrics in the eventset, you can specify a metric unit with the `unit` field.
 
 Additional options:
+
 - `force_overwrite`: Same as setting `LIKWID_FORCE=1`. In case counters are already in-use, LIKWID overwrites their configuration to do its measurements
 - `invalid_to_zero`: In some cases, the calculations result in `NaN` or `Inf`. With this option, all `NaN` and `Inf` values are replaces with `0.0`. See below in [seperate section](./likwidMetric.md#invalid_to_zero-option)
 - `access_mode`: Specify LIKWID access mode: `direct` for direct register access as root user or `accessdaemon`. The access mode `perf_event` is current untested.
 - `accessdaemon_path`: Folder of the accessDaemon `likwid-accessD` (like `/usr/local/sbin`)
 - `liblikwid_path`: Location of `liblikwid.so` including file name like `/usr/local/lib/liblikwid.so`
+- `lockfile_path`: Location of LIKWID's lock file if multiple tools should access the hardware counters. Default `/var/run/likwid.lock`
 
-### Available metric scopes
+### Available metric types
 
 Hardware performance counters are scattered all over the system nowadays. A counter coveres a specific part of the system. While there are hardware thread specific counter for CPU cycles, instructions and so on, some others are specific for a whole CPU socket/package. To address that, the LikwidCollector provides the specification of a `type` for each metric.
 
 - `hwthread` : One metric per CPU hardware thread with the tags `"type" : "hwthread"` and `"type-id" : "$hwthread_id"`
 - `socket` : One metric per CPU socket/package with the tags `"type" : "socket"` and `"type-id" : "$socket_id"`
 
-**Note:** You cannot specify `socket` scope for a metric that is measured at `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.
+**Note:** You cannot specify `socket` type for a metric that is measured at `hwthread` type, so some kind of expert knowledge or lookup work in the [Likwid Wiki](https://github.com/RRZE-HPC/likwid/wiki) is required. Get the type of each counter from the *Architecture* pages and as soon as one counter in a metric is socket-specific, the whole metric is socket-specific.
 
 As a guideline:
-- 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 `hwthread` scope
-- All `DFCx` counters have scope `socket`
+
+- All counters `FIXCx`, `PMCy` and `TMAz` have the type `hwthread`
+- All counters names containing `BOX` have the type `socket`
+- All `PWRx` counters have type `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `hwthread` type
+- All `DFCx` counters have type `socket`
 
 ### Help with the configuration
 
 The configuration for the `likwid` collector is quite complicated. Most users don't use LIKWID with the event:counter notation but rely on the performance groups defined by the LIKWID team for each architecture. In order to help with the `likwid` collector configuration, we included a script `scripts/likwid_perfgroup_to_cc_config.py` that creates the configuration of an `eventset` from a performance group (using a LIKWID installation in `$PATH`):
+
 ```
 $ likwid-perfctr -i
 [...]
@@ -90,7 +109,7 @@ $ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
       "name": "Runtime (RDTSC) [s]",
       "publish": true,
       "unit": "seconds"
-      "scope": "hwthread"
+      "type": "hwthread"
     },
     {
       "..." : "..."
@@ -106,20 +125,31 @@ You can copy this JSON and add it to the `eventsets` list. If you specify multip
 LIKWID checks the file `/var/run/likwid.lock` before performing any interfering operations. Who is allowed to access the counters is determined by the owner of the file. If it does not exist, it is created for the current user. So, if you want to temporarly allow counter access to a user (e.g. in a job):
 
 Before (SLURM prolog, ...)
-```
-$ chown $JOBUSER /var/run/likwid.lock
+
+```bash
+chown $JOBUSER /var/run/likwid.lock
 ```
 
 After (SLURM epilog, ...)
-```
-$ chown $CCUSER /var/run/likwid.lock
+
+```bash
+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).
 
+### `lockfile_path` option
+LIKWID can be configured with a lock file with which the access to the performance monitoring registers can be disabled (only the owner of the lock file is allowed to access the registers). When the `lockfile_path` option is set, the collector subscribes to changes to this file to stop monitoring if the owner of the lock file changes. This feature is useful when users should be able to perform own hardware performance counter measurements through LIKWID or any other tool.
+
+### `send_*_total values` option
+
+- `send_core_total_values`: Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per CPU core.
+- `send_socket_total_values` Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per CPU socket.
+- `send_node_total_values` Metrics, which are usually collected on a per hardware thread basis, are additionally summed up per node.
 
 ### Example configuration
 
@@ -224,6 +254,7 @@ One might think this does not happen often but often used metrics in the world o
 The `likwid` collector reads hardware performance counters at a **hwthread** and **socket** level. The configuration looks quite complicated but it is basically copy&paste from [LIKWID's performance groups](https://github.com/RRZE-HPC/likwid/tree/master/groups). The collector made multiple iterations and tried to use the performance groups but it lacked flexibility. The current way of configuration provides most flexibility.
 
 The logic is as following: There are multiple eventsets, each consisting of a list of counters+events and a list of metrics. If you compare a common performance group with the example setting above, there is not much difference:
+
 ```
 EVENTSET                         ->   "events": {
 FIXC1 ACTUAL_CPU_CLOCK           ->     "FIXC1": "ACTUAL_CPU_CLOCK",
@@ -242,7 +273,7 @@ METRICS                          ->   "metrics": [
 IPC   PMC0/PMC1                  ->     {
                                  ->       "name" : "IPC",
                                  ->       "calc" : "PMC0/PMC1",
-                                 ->       "scope": "hwthread",
+                                 ->       "type": "hwthread",
                                  ->       "publish": true
                                  ->     }
                                  ->   ]

collectors/loadavgMetric.go

@@ -1,25 +1,30 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
-//
 // LoadavgCollector collects:
 // * load average of last 1, 5 & 15 minutes
 // * number of processes currently runnable
 // * total number of processes in system
 //
 // See: https://www.kernel.org/doc/html/latest/filesystems/proc.html
-//
 const LOADAVGFILE = "/proc/loadavg"
 
 type LoadavgCollector struct {
@@ -68,17 +73,15 @@ func (m *LoadavgCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
-	buffer, err := ioutil.ReadFile(LOADAVGFILE)
+	buffer, err := os.ReadFile(LOADAVGFILE)
 	if err != nil {
-		if err != nil {
-			cclog.ComponentError(
-				m.name,
-				fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err))
-		}
+		cclog.ComponentError(
+			m.name,
+			fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err))
 		return
 	}
 	now := time.Now()
@@ -96,7 +99,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		if m.load_skips[i] {
 			continue
 		}
-		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
+		y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
 		if err == nil {
 			output <- y
 		}
@@ -115,7 +118,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		if m.proc_skips[i] {
 			continue
 		}
-		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
+		y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
 		if err == nil {
 			output <- y
 		}

collectors/loadavgMetric.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: Load average metric collector
+description: Collect metrics from `/proc/loadavg`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/loadavg.md
+---
+-->
+
 
 ## `loadavg` collector
 

collectors/lustreMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -10,8 +17,8 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 const LUSTRE_SYSFS = `/sys/fs/lustre`
@@ -101,7 +108,7 @@ func getMetricData(lines []string, prefix string, offset int) (int64, error) {
 // 	llitedir := filepath.Join(LUSTRE_SYSFS, "llite")
 // 	devdir := filepath.Join(llitedir, device)
 // 	statsfile := filepath.Join(devdir, "stats")
-// 	buffer, err := ioutil.ReadFile(statsfile)
+// 	buffer, err := os.ReadFile(statsfile)
 // 	if err != nil {
 // 		return make([]string, 0)
 // 	}
@@ -377,7 +384,7 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
@@ -388,7 +395,7 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		for _, def := range m.definitions {
 			var use_x int64
 			var err error
-			var y lp.CCMetric
+			var y lp.CCMessage
 			x, err := getMetricData(data, def.lineprefix, def.lineoffset)
 			if err == nil {
 				use_x = x
@@ -399,19 +406,19 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric)
 			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())
+				y, err = lp.NewMessage(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())
+				y, err = lp.NewMessage(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())
+				y, err = lp.NewMessage(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			}
 			if err == nil {
 				y.AddTag("device", device)

collectors/lustreMetric.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: Lustre filesystem metric collector
+description: Collect metrics for Lustre filesystems
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/lustre.md
+---
+-->
+
 
 ## `lustrestat` collector
 
@@ -43,4 +54,4 @@ Metrics:
 * `lustre_statfs_diff` (if `send_diff_values == true`)
 * `lustre_inode_permission_diff` (if `send_diff_values == true`)
 
-This collector adds an `device` tag.
+This collector adds an `device` tag.

collectors/memstatMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -12,8 +19,8 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 const MEMSTATFILE = "/proc/meminfo"
@@ -68,7 +75,8 @@ func getStats(filename string) map[string]MemstatStats {
 		} else if len(linefields) == 5 {
 			v, err := strconv.ParseFloat(linefields[3], 64)
 			if err == nil {
-				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
+				cclog.ComponentDebug("getStats", strings.Trim(linefields[2], ":"), v, linefields[4])
+				stats[strings.Trim(linefields[2], ":")] = MemstatStats{
 					value: v,
 					unit:  linefields[4],
 				}
@@ -158,9 +166,8 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 	return err
 }
 
-func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
-		cclog.ComponentPrint(m.name, "Here")
 		return
 	}
 
@@ -175,7 +182,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 				}
 			}
 
-			y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+			y, err := lp.NewMessage(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			if err == nil {
 				if len(unit) > 0 {
 					y.AddMeta("unit", unit)
@@ -188,23 +195,27 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 			unit := ""
 			if totalVal, total := stats["MemTotal"]; total {
 				if freeVal, free := stats["MemFree"]; free {
+					memUsed = totalVal.value - freeVal.value
+					if len(totalVal.unit) > 0 {
+						unit = totalVal.unit
+					} else if len(freeVal.unit) > 0 {
+						unit = freeVal.unit
+					}
 					if bufVal, buffers := stats["Buffers"]; buffers {
+						memUsed -= bufVal.value
+						if len(bufVal.unit) > 0 && len(unit) == 0 {
+							unit = bufVal.unit
+						}
 						if cacheVal, cached := stats["Cached"]; cached {
-							memUsed = totalVal.value - (freeVal.value + bufVal.value + cacheVal.value)
-							if len(totalVal.unit) > 0 {
-								unit = totalVal.unit
-							} else if len(freeVal.unit) > 0 {
-								unit = freeVal.unit
-							} else if len(bufVal.unit) > 0 {
-								unit = bufVal.unit
-							} else if len(cacheVal.unit) > 0 {
+							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())
+			y, err := lp.NewMessage("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
 			if err == nil {
 				if len(unit) > 0 {
 					y.AddMeta("unit", unit)

collectors/memstatMetric.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: Memory statistics metric collector
+description: Collect metrics from `/proc/meminfo`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/memstat.md
+---
+-->
+
 
 ## `memstat` collector
 

collectors/metricCollector.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -5,7 +12,7 @@ import (
 	"fmt"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 type MetricCollector interface {
@@ -13,8 +20,8 @@ type MetricCollector interface {
 	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
+	Read(duration time.Duration, output chan lp.CCMessage) // Read metrics from metric collector
+	Close()                                                // Close / finish metric collector
 }
 
 type metricCollector struct {

collectors/netstatMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -9,16 +16,17 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 const NETSTATFILE = "/proc/net/dev"
 
 type NetstatCollectorConfig struct {
-	IncludeDevices     []string `json:"include_devices"`
-	SendAbsoluteValues bool     `json:"send_abs_values"`
-	SendDerivedValues  bool     `json:"send_derived_values"`
+	IncludeDevices     []string            `json:"include_devices"`
+	SendAbsoluteValues bool                `json:"send_abs_values"`
+	SendDerivedValues  bool                `json:"send_derived_values"`
+	InterfaceAliases   map[string][]string `json:"interface_aliases,omitempty"`
 }
 
 type NetstatCollectorMetric struct {
@@ -32,9 +40,26 @@ type NetstatCollectorMetric struct {
 
 type NetstatCollector struct {
 	metricCollector
-	config        NetstatCollectorConfig
-	matches       map[string][]NetstatCollectorMetric
-	lastTimestamp time.Time
+	config           NetstatCollectorConfig
+	aliasToCanonical map[string]string
+	matches          map[string][]NetstatCollectorMetric
+	lastTimestamp    time.Time
+}
+
+func (m *NetstatCollector) buildAliasMapping() {
+	m.aliasToCanonical = make(map[string]string)
+	for canon, aliases := range m.config.InterfaceAliases {
+		for _, alias := range aliases {
+			m.aliasToCanonical[alias] = canon
+		}
+	}
+}
+
+func getCanonicalName(raw string, aliasToCanonical map[string]string) string {
+	if canon, ok := aliasToCanonical[raw]; ok {
+		return canon
+	}
+	return raw
 }
 
 func (m *NetstatCollector) Init(config json.RawMessage) error {
@@ -77,6 +102,8 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 		}
 	}
 
+	m.buildAliasMapping()
+
 	// Check access to net statistic file
 	file, err := os.Open(NETSTATFILE)
 	if err != nil {
@@ -97,18 +124,20 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 		// Split line into fields
 		f := strings.Fields(l)
 
-		// Get net device entry
-		dev := strings.Trim(f[0], ": ")
+		// Get raw and canonical names
+		raw := strings.Trim(f[0], ": ")
+		canonical := getCanonicalName(raw, m.aliasToCanonical)
 
 		// Check if device is a included device
-		if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
-			tags := map[string]string{"device": dev, "type": "node"}
+		if _, ok := stringArrayContains(m.config.IncludeDevices, canonical); ok {
+			// Tag will contain original device name (raw).
+			tags := map[string]string{"stype": "network", "stype-id": raw, "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{
+			m.matches[canonical] = []NetstatCollectorMetric{
 				{
 					name:       "net_bytes_in",
 					index:      fieldReceiveBytes,
@@ -143,7 +172,6 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 				},
 			}
 		}
-
 	}
 
 	if len(m.matches) == 0 {
@@ -153,7 +181,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
@@ -164,7 +192,7 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	// Save current timestamp
 	m.lastTimestamp = now
 
-	file, err := os.Open(string(NETSTATFILE))
+	file, err := os.Open(NETSTATFILE)
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return
@@ -183,11 +211,12 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		// Split line into fields
 		f := strings.Fields(l)
 
-		// Get net device entry
-		dev := strings.Trim(f[0], ":")
+		// Get raw and canonical names
+		raw := strings.Trim(f[0], ":")
+		canonical := getCanonicalName(raw, m.aliasToCanonical)
 
 		// Check if device is a included device
-		if devmetrics, ok := m.matches[dev]; ok {
+		if devmetrics, ok := m.matches[canonical]; ok {
 			for i := range devmetrics {
 				metric := &devmetrics[i]
 
@@ -197,14 +226,14 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 					continue
 				}
 				if m.config.SendAbsoluteValues {
-					if y, err := lp.New(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
+					if y, err := lp.NewMessage(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
 						output <- y
 					}
 				}
 				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 {
+						if y, err := lp.NewMessage(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]interface{}{"value": rate}, now); err == nil {
 							output <- y
 						}
 					}

collectors/netstatMetric.md

@@ -1,17 +1,32 @@
+<!--
+---
+title: Network device metric collector
+description: Collect metrics for network devices through procfs
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/netstat.md
+---
+-->
 
 ## `netstat` collector
 
 ```json
   "netstat": {
     "include_devices": [
-      "eth0"
+      "eth0",
+      "eno1"
     ],
-    "send_abs_values" : true,
-    "send_derived_values" : true
+    "send_abs_values": true,
+    "send_derived_values": true,
+    "interface_aliases": {
+      "eno1": ["eno1np0", "eno1_alt"],
+      "eth0": ["eth0_alias"]
+    }
   }
 ```
 
-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.
+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. Optionally, you can define an interface_aliases mapping. For each canonical device (as listed in include_devices), you may provide an array of aliases that may be reported by the system. When an alias is detected, it is preferred for matching, while the output tag stype-id always shows the actual system-reported name.
 
 Metrics:
 * `net_bytes_in` (`unit=bytes`)
@@ -23,5 +38,4 @@ Metrics:
 * `net_pkts_in_bw` (`unit=packets/sec` if `send_derived_values == true`)
 * `net_pkts_out_bw` (`unit=packets/sec` if `send_derived_values == true`)
 
-The device name is added as tag `device`.
-
+The device name is added as tag `stype=network,stype-id=<device>`.

collectors/nfs3Metric.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: NFS network filesystem (v3) metric collector
+description: Collect metrics for NFS network filesystems in version 3
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/nfs3.md
+---
+-->
+
 
 ## `nfs3stat` collector
 

collectors/nfs4Metric.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: NFS network filesystem (v4) metric collector
+description: Collect metrics for NFS network filesystems in version 4
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/nfs4.md
+---
+-->
+
 
 ## `nfs4stat` collector
 

collectors/nfsMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -11,7 +18,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 // First part contains the code for the general NfsCollector.
@@ -118,7 +125,7 @@ func (m *nfsCollector) MainInit(config json.RawMessage) error {
 	return nil
 }
 
-func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
@@ -140,7 +147,7 @@ func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 			continue
 		}
 		value := data.current - data.last
-		y, err := lp.New(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+		y, err := lp.NewMessage(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
 		if err == nil {
 			y.AddMeta("version", m.version)
 			output <- y

collectors/nfsiostatMetric.go

@@ -0,0 +1,189 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
+package collectors
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"regexp"
+	"strconv"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+)
+
+// These are the fields we read from the JSON configuration
+type NfsIOStatCollectorConfig struct {
+	ExcludeMetrics          []string `json:"exclude_metrics,omitempty"`
+	ExcludeFilesystem       []string `json:"exclude_filesystem,omitempty"`
+	UseServerAddressAsSType bool     `json:"use_server_as_stype,omitempty"`
+	SendAbsoluteValues      bool     `json:"send_abs_values"`
+	SendDerivedValues       bool     `json:"send_derived_values"`
+}
+
+// This contains all variables we need during execution and the variables
+// defined by metricCollector (name, init, ...)
+type NfsIOStatCollector struct {
+	metricCollector
+	config        NfsIOStatCollectorConfig    // the configuration structure
+	meta          map[string]string           // default meta information
+	tags          map[string]string           // default tags
+	data          map[string]map[string]int64 // data storage for difference calculation
+	key           string                      // which device info should be used as subtype ID? 'server' or 'mntpoint'
+	lastTimestamp time.Time
+}
+
+var deviceRegex = regexp.MustCompile(`device (?P<server>[^ ]+) mounted on (?P<mntpoint>[^ ]+) with fstype nfs(?P<version>\d*) statvers=[\d\.]+`)
+var bytesRegex = regexp.MustCompile(`\s+bytes:\s+(?P<nread>[^ ]+) (?P<nwrite>[^ ]+) (?P<dread>[^ ]+) (?P<dwrite>[^ ]+) (?P<nfsread>[^ ]+) (?P<nfswrite>[^ ]+) (?P<pageread>[^ ]+) (?P<pagewrite>[^ ]+)`)
+
+func resolve_regex_fields(s string, regex *regexp.Regexp) map[string]string {
+	fields := make(map[string]string)
+	groups := regex.SubexpNames()
+	for _, match := range regex.FindAllStringSubmatch(s, -1) {
+		for groupIdx, group := range match {
+			if len(groups[groupIdx]) > 0 {
+				fields[groups[groupIdx]] = group
+			}
+		}
+	}
+	return fields
+}
+
+func (m *NfsIOStatCollector) readNfsiostats() map[string]map[string]int64 {
+	data := make(map[string]map[string]int64)
+	filename := "/proc/self/mountstats"
+	stats, err := os.ReadFile(filename)
+	if err != nil {
+		return data
+	}
+
+	lines := strings.Split(string(stats), "\n")
+	var current map[string]string = nil
+	for _, l := range lines {
+		// Is this a device line with mount point, remote target and NFS version?
+		dev := resolve_regex_fields(l, deviceRegex)
+		if len(dev) > 0 {
+			if _, ok := stringArrayContains(m.config.ExcludeFilesystem, dev[m.key]); !ok {
+				current = dev
+				if len(current["version"]) == 0 {
+					current["version"] = "3"
+				}
+			}
+		}
+
+		if len(current) > 0 {
+			// Byte line parsing (if found the device for it)
+			bytes := resolve_regex_fields(l, bytesRegex)
+			if len(bytes) > 0 {
+				data[current[m.key]] = make(map[string]int64)
+				for name, sval := range bytes {
+					if _, ok := stringArrayContains(m.config.ExcludeMetrics, name); !ok {
+						val, err := strconv.ParseInt(sval, 10, 64)
+						if err == nil {
+							data[current[m.key]][name] = val
+						}
+					}
+				}
+				current = nil
+			}
+		}
+	}
+	return data
+}
+
+func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
+	var err error = nil
+	m.name = "NfsIOStatCollector"
+	m.setup()
+	m.parallel = true
+	m.meta = map[string]string{"source": m.name, "group": "NFS", "unit": "bytes"}
+	m.tags = map[string]string{"type": "node"}
+	m.config.UseServerAddressAsSType = false
+	// Set default configuration
+	m.config.SendAbsoluteValues = true
+	m.config.SendDerivedValues = false
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			cclog.ComponentError(m.name, "Error reading config:", err.Error())
+			return err
+		}
+	}
+	m.key = "mntpoint"
+	if m.config.UseServerAddressAsSType {
+		m.key = "server"
+	}
+	m.data = m.readNfsiostats()
+	m.lastTimestamp = time.Now()
+	m.init = true
+	return err
+}
+
+func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+	now := time.Now()
+	timeDiff := now.Sub(m.lastTimestamp).Seconds()
+	m.lastTimestamp = now
+
+	// Get the current values for all mountpoints
+	newdata := m.readNfsiostats()
+
+	for mntpoint, values := range newdata {
+		// Was the mount point already present in the last iteration
+		if old, ok := m.data[mntpoint]; ok {
+			for name, newVal := range values {
+				if m.config.SendAbsoluteValues {
+					msg, err := lp.NewMessage(fmt.Sprintf("nfsio_%s", name), m.tags, m.meta, map[string]interface{}{"value": newVal}, now)
+					if err == nil {
+						msg.AddTag("stype", "filesystem")
+						msg.AddTag("stype-id", mntpoint)
+						output <- msg
+					}
+				}
+				if m.config.SendDerivedValues {
+					rate := float64(newVal-old[name]) / timeDiff
+					msg, err := lp.NewMessage(fmt.Sprintf("nfsio_%s_bw", name), m.tags, m.meta, map[string]interface{}{"value": rate}, now)
+					if err == nil {
+						if strings.HasPrefix(name, "page") {
+							msg.AddMeta("unit", "4K_pages/s")
+						} else {
+							msg.AddMeta("unit", "bytes/sec")
+						}
+						msg.AddTag("stype", "filesystem")
+						msg.AddTag("stype-id", mntpoint)
+						output <- msg
+					}
+				}
+				old[name] = newVal
+			}
+		} else {
+			// First time we see this mount point, store all values
+			m.data[mntpoint] = values
+		}
+	}
+	// Reset entries that do not exist anymore
+	for mntpoint := range m.data {
+		found := false
+		for new := range newdata {
+			if new == mntpoint {
+				found = true
+				break
+			}
+		}
+		if !found {
+			delete(m.data, mntpoint)
+		}
+	}
+}
+
+func (m *NfsIOStatCollector) Close() {
+	// Unset flag
+	m.init = false
+}

collectors/nfsiostatMetric.md

@@ -0,0 +1,45 @@
+<!--
+---
+title: NFS network filesystem metrics from procfs
+description: Collect NFS network filesystem metrics for mounts from `/proc/self/mountstats`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/nfsio.md
+---
+-->
+
+## `nfsiostat` collector
+
+```json
+  "nfsiostat": {
+    "exclude_metrics": [
+      "oread", "pageread"
+    ],
+    "exclude_filesystems": [
+      "/mnt"
+    ],
+    "use_server_as_stype": false,
+    "send_abs_values": false,
+    "send_derived_values": true
+  }
+```
+
+The `nfsiostat` collector reads data from `/proc/self/mountstats` and outputs a handful **node** metrics for each NFS filesystem. If a metric or filesystem is not required, it can be excluded from forwarding it to the sink. **Note:** When excluding metrics, you must provide the base metric name (e.g. pageread) without the nfsio_ prefix. This exclusion applies to both absolute and derived values.
+
+Metrics:
+* `nfsio_nread`: Bytes transferred by normal `read()` calls
+* `nfsio_nwrite`: Bytes transferred by normal `write()` calls
+* `nfsio_oread`: Bytes transferred by `read()` calls with `O_DIRECT`
+* `nfsio_owrite`: Bytes transferred by `write()` calls with `O_DIRECT`
+* `nfsio_pageread`: Pages transferred by `read()` calls
+* `nfsio_pagewrite`: Pages transferred by `write()` calls
+* `nfsio_nfsread`: Bytes transferred for reading from the server
+* `nfsio_nfswrite`: Pages transferred by writing to the server
+
+For each of these, if derived values are enabled, an additional metric is sent with the `_bw` suffix, which represents the rate:
+
+  * For normal byte metrics: `unit=bytes/sec`
+  * For page metrics: `unit=4K_pages/s`
+
+The `nfsiostat` collector adds the mountpoint to the tags as `stype=filesystem,stype-id=<mountpoint>`. If the server address should be used instead of the mountpoint, use the `use_server_as_stype` config setting.

collectors/numastatsMetric.go

@@ -10,41 +10,58 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
-//
-// Numa policy hit/miss statistics
+type NUMAStatsCollectorConfig struct {
+	SendAbsoluteValues bool `json:"send_abs_values"`
+	SendDerivedValues  bool `json:"send_derived_values"`
+}
+
+// Non-Uniform Memory Access (NUMA) policy hit/miss statistics
 //
 // numa_hit:
-//   A process wanted to allocate memory from this node, and succeeded.
+//
+//	A process wanted to allocate memory from this node, and succeeded.
+//
 // numa_miss:
-//   A process wanted to allocate memory from another node,
-//   but ended up with memory from this node.
+//
+//	A process wanted to allocate memory from another node,
+//	but ended up with memory from this node.
+//
 // numa_foreign:
-//   A process wanted to allocate on this node,
-//   but ended up with memory from another node.
+//
+//	A process wanted to allocate on this node,
+//	but ended up with memory from another node.
+//
 // local_node:
-//   A process ran on this node's CPU,
-//   and got memory from this node.
+//
+//	A process ran on this node's CPU,
+//	and got memory from this node.
+//
 // other_node:
-//   A process ran on a different node's CPU
-//   and got memory from this node.
+//
+//	A process ran on a different node's CPU
+//	and got memory from this node.
+//
 // interleave_hit:
-//   Interleaving wanted to allocate from this node
-//   and succeeded.
+//
+//	Interleaving wanted to allocate from this node
+//	and succeeded.
 //
 // See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
-//
 type NUMAStatsCollectorTopolgy struct {
-	file   string
-	tagSet map[string]string
+	file           string
+	tagSet         map[string]string
+	previousValues map[string]int64
 }
 
 type NUMAStatsCollector struct {
 	metricCollector
-	topology []NUMAStatsCollectorTopolgy
+	topology      []NUMAStatsCollectorTopolgy
+	config        NUMAStatsCollectorConfig
+	lastTimestamp time.Time
 }
 
 func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
@@ -61,6 +78,14 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
 		"group":  "NUMA",
 	}
 
+	m.config.SendAbsoluteValues = true
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &m.config)
+		if err != nil {
+			return fmt.Errorf("unable to unmarshal numastat configuration: %s", err.Error())
+		}
+	}
+
 	// Loop for all NUMA node directories
 	base := "/sys/devices/system/node/node"
 	globPattern := base + "[0-9]*"
@@ -77,37 +102,44 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
 		file := filepath.Join(dir, "numastat")
 		m.topology = append(m.topology,
 			NUMAStatsCollectorTopolgy{
-				file:   file,
-				tagSet: map[string]string{"memoryDomain": node},
+				file:           file,
+				tagSet:         map[string]string{"memoryDomain": node},
+				previousValues: make(map[string]int64),
 			})
 	}
 
+	// Initialized
+	cclog.ComponentDebug(m.name, "initialized", len(m.topology), "NUMA domains")
 	m.init = true
 	return nil
 }
 
-func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
 
+	now := time.Now()
+	timeDiff := now.Sub(m.lastTimestamp).Seconds()
+	m.lastTimestamp = now
+
 	for i := range m.topology {
 		// Loop for all NUMA domains
 		t := &m.topology[i]
 
-		now := time.Now()
 		file, err := os.Open(t.file)
 		if err != nil {
 			cclog.ComponentError(
 				m.name,
 				fmt.Sprintf("Read(): Failed to open file '%s': %v", t.file, err))
-			return
+			continue
 		}
 		scanner := bufio.NewScanner(file)
 
 		// Read line by line
 		for scanner.Scan() {
-			split := strings.Fields(scanner.Text())
+			line := scanner.Text()
+			split := strings.Fields(line)
 			if len(split) != 2 {
 				continue
 			}
@@ -119,18 +151,38 @@ func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMetri
 					fmt.Sprintf("Read(): Failed to convert %s='%s' to int64: %v", key, split[1], err))
 				continue
 			}
-			y, err := lp.New(
-				"numastats_"+key,
-				t.tagSet,
-				m.meta,
-				map[string]interface{}{"value": value},
-				now,
-			)
-			if err == nil {
-				output <- y
+
+			if m.config.SendAbsoluteValues {
+				msg, err := lp.NewMetric(
+					"numastats_"+key,
+					t.tagSet,
+					m.meta,
+					value,
+					now,
+				)
+				if err == nil {
+					output <- msg
+				}
+			}
+
+			if m.config.SendDerivedValues {
+				prev, ok := t.previousValues[key]
+				if ok {
+					rate := float64(value-prev) / timeDiff
+					msg, err := lp.NewMetric(
+						"numastats_"+key+"_rate",
+						t.tagSet,
+						m.meta,
+						rate,
+						now,
+					)
+					if err == nil {
+						output <- msg
+					}
+				}
+				t.previousValues[key] = value
 			}
 		}
-
 		file.Close()
 	}
 }

collectors/numastatsMetric.md

@@ -1,15 +1,36 @@
+<!--
+---
+title: NUMAStat collector
+description: Collect infos about NUMA domains
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/numastat.md
+---
+-->
 
 ## `numastat` collector
+
 ```json
-  "numastat": {}
+  "numastats": {
+    "send_abs_values" : true,
+    "send_derived_values" : true
+}
 ```
 
-The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
+The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: <https://www.kernel.org/doc/html/latest/admin-guide/numastat.html>
 
 Metrics:
+
 * `numastats_numa_hit`: A process wanted to allocate memory from this node, and succeeded.
 * `numastats_numa_miss`: A process wanted to allocate memory from another node, but ended up with memory from this node.
 * `numastats_numa_foreign`: A process wanted to allocate on this node, but ended up with memory from another node.
 * `numastats_local_node`: A process ran on this node's CPU, and got memory from this node.
 * `numastats_other_node`: A process ran on a different node's CPU, and got memory from this node.
-* `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded.
+* `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded.
+* `numastats_numa_hit_rate` (if `send_derived_values == true`): Derived rate value per second.
+* `numastats_numa_miss_rate` (if `send_derived_values == true`): Derived rate value per second.
+* `numastats_numa_foreign_rate` (if `send_derived_values == true`): Derived rate value per second.
+* `numastats_local_node_rate` (if `send_derived_values == true`): Derived rate value per second.
+* `numastats_other_node_rate` (if `send_derived_values == true`): Derived rate value per second.
+* `numastats_interleave_hit_rate` (if `send_derived_values == true`): Derived rate value per second.

collectors/nvidiaMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -8,8 +15,8 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 	"github.com/NVIDIA/go-nvml/pkg/nvml"
 )
 
@@ -27,10 +34,12 @@ type NvidiaCollectorConfig struct {
 }
 
 type NvidiaCollectorDevice struct {
-	device         nvml.Device
-	excludeMetrics map[string]bool
-	tags           map[string]string
-	meta           map[string]string
+	device              nvml.Device
+	excludeMetrics      map[string]bool
+	tags                map[string]string
+	meta                map[string]string
+	lastEnergyReading   uint64
+	lastEnergyTimestamp time.Time
 }
 
 type NvidiaCollector struct {
@@ -71,6 +80,14 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
 
 	// Initialize NVIDIA Management Library (NVML)
 	ret := nvml.Init()
+
+	// Error: NVML library not found
+	// (nvml.ErrorString can not be used in this case)
+	if ret == nvml.ERROR_LIBRARY_NOT_FOUND {
+		err = fmt.Errorf("NVML library not found")
+		cclog.ComponentError(m.name, err.Error())
+		return err
+	}
 	if ret != nvml.SUCCESS {
 		err = errors.New(nvml.ErrorString(ret))
 		cclog.ComponentError(m.name, "Unable to initialize NVML", err.Error())
@@ -141,6 +158,8 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
 
 		// Add device handle
 		g.device = device
+		g.lastEnergyReading = 0
+		g.lastEnergyTimestamp = time.Now()
 
 		// Add tags
 		g.tags = map[string]string{
@@ -198,7 +217,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readMemoryInfo(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_fb_mem_total"] || !device.excludeMetrics["nv_fb_mem_used"] || !device.excludeMetrics["nv_fb_mem_reserved"] {
 		var total uint64
 		var used uint64
@@ -214,7 +233,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 
 		if !device.excludeMetrics["nv_fb_mem_total"] {
 			t := float64(total) / (1024 * 1024)
-			y, err := lp.New("nv_fb_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_fb_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -223,7 +242,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 
 		if !device.excludeMetrics["nv_fb_mem_used"] {
 			f := float64(used) / (1024 * 1024)
-			y, err := lp.New("nv_fb_mem_used", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
+			y, err := lp.NewMessage("nv_fb_mem_used", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -232,7 +251,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 
 		if v2 && !device.excludeMetrics["nv_fb_mem_reserved"] {
 			r := float64(reserved) / (1024 * 1024)
-			y, err := lp.New("nv_fb_mem_reserved", device.tags, device.meta, map[string]interface{}{"value": r}, time.Now())
+			y, err := lp.NewMessage("nv_fb_mem_reserved", device.tags, device.meta, map[string]interface{}{"value": r}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -242,7 +261,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	return nil
 }
 
-func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readBarMemoryInfo(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_bar1_mem_total"] || !device.excludeMetrics["nv_bar1_mem_used"] {
 		meminfo, ret := nvml.DeviceGetBAR1MemoryInfo(device.device)
 		if ret != nvml.SUCCESS {
@@ -251,7 +270,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) er
 		}
 		if !device.excludeMetrics["nv_bar1_mem_total"] {
 			t := float64(meminfo.Bar1Total) / (1024 * 1024)
-			y, err := lp.New("nv_bar1_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_bar1_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -259,7 +278,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) er
 		}
 		if !device.excludeMetrics["nv_bar1_mem_used"] {
 			t := float64(meminfo.Bar1Used) / (1024 * 1024)
-			y, err := lp.New("nv_bar1_mem_used", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_bar1_mem_used", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -269,7 +288,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) er
 	return nil
 }
 
-func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readUtilization(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
 	if ret != nvml.SUCCESS {
 		err := errors.New(nvml.ErrorString(ret))
@@ -293,14 +312,14 @@ func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) erro
 		util, ret := nvml.DeviceGetUtilizationRates(device.device)
 		if ret == nvml.SUCCESS {
 			if !device.excludeMetrics["nv_util"] {
-				y, err := lp.New("nv_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Gpu)}, time.Now())
+				y, err := lp.NewMessage("nv_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Gpu)}, time.Now())
 				if err == nil {
 					y.AddMeta("unit", "%")
 					output <- y
 				}
 			}
 			if !device.excludeMetrics["nv_mem_util"] {
-				y, err := lp.New("nv_mem_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Memory)}, time.Now())
+				y, err := lp.NewMessage("nv_mem_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Memory)}, time.Now())
 				if err == nil {
 					y.AddMeta("unit", "%")
 					output <- y
@@ -311,7 +330,7 @@ func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) erro
 	return nil
 }
 
-func readTemp(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readTemp(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_temp"] {
 		// Retrieves the current temperature readings for the device, in degrees C.
 		//
@@ -320,7 +339,7 @@ func readTemp(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 		// * NVML_TEMPERATURE_COUNT
 		temp, ret := nvml.DeviceGetTemperature(device.device, nvml.TEMPERATURE_GPU)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_temp", device.tags, device.meta, map[string]interface{}{"value": float64(temp)}, time.Now())
+			y, err := lp.NewMessage("nv_temp", device.tags, device.meta, map[string]interface{}{"value": float64(temp)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "degC")
 				output <- y
@@ -330,7 +349,7 @@ func readTemp(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	return nil
 }
 
-func readFan(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readFan(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_fan"] {
 		// Retrieves the intended operating speed of the device's fan.
 		//
@@ -343,7 +362,7 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 		// This value may exceed 100% in certain cases.
 		fan, ret := nvml.DeviceGetFanSpeed(device.device)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
+			y, err := lp.NewMessage("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "%")
 				output <- y
@@ -353,14 +372,14 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	return nil
 }
 
-// func readFans(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+// func readFans(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 // 	if !device.excludeMetrics["nv_fan"] {
 // 		numFans, ret := nvml.DeviceGetNumFans(device.device)
 // 		if ret == nvml.SUCCESS {
 // 			for i := 0; i < numFans; i++ {
 // 				fan, ret := nvml.DeviceGetFanSpeed_v2(device.device, i)
 // 				if ret == nvml.SUCCESS {
-// 					y, err := lp.New("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
+// 					y, err := lp.NewMessage("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
 // 					if err == nil {
 // 						y.AddMeta("unit", "%")
 // 						y.AddTag("stype", "fan")
@@ -374,7 +393,7 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 // 	return nil
 // }
 
-func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readEccMode(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_ecc_mode"] {
 		// Retrieves the current and pending ECC modes for the device.
 		//
@@ -385,21 +404,21 @@ func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 		// The "pending" ECC mode refers to the target mode following the next reboot.
 		_, ecc_pend, ret := nvml.DeviceGetEccMode(device.device)
 		if ret == nvml.SUCCESS {
-			var y lp.CCMetric
+			var y lp.CCMessage
 			var err error
 			switch ecc_pend {
 			case nvml.FEATURE_DISABLED:
-				y, err = lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "OFF"}, time.Now())
+				y, err = lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "OFF"}, time.Now())
 			case nvml.FEATURE_ENABLED:
-				y, err = lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "ON"}, time.Now())
+				y, err = lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "ON"}, time.Now())
 			default:
-				y, err = lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "UNKNOWN"}, time.Now())
+				y, err = lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "UNKNOWN"}, time.Now())
 			}
 			if err == nil {
 				output <- y
 			}
 		} else if ret == nvml.ERROR_NOT_SUPPORTED {
-			y, err := lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "N/A"}, time.Now())
+			y, err := lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "N/A"}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -408,7 +427,7 @@ func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	return nil
 }
 
-func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readPerfState(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_perf_state"] {
 		// Retrieves the current performance state for the device.
 		//
@@ -419,7 +438,7 @@ func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 		// 32: Unknown performance state.
 		pState, ret := nvml.DeviceGetPerformanceState(device.device)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_perf_state", device.tags, device.meta, map[string]interface{}{"value": fmt.Sprintf("P%d", int(pState))}, time.Now())
+			y, err := lp.NewMessage("nv_perf_state", device.tags, device.meta, map[string]interface{}{"value": fmt.Sprintf("P%d", int(pState))}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -428,13 +447,16 @@ func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	return nil
 }
 
-func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readPowerUsage(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_power_usage"] {
 		// Retrieves power usage for this GPU in milliwatts and its associated circuitry (e.g. memory)
 		//
 		// On Fermi and Kepler GPUs the reading is accurate to within +/- 5% of current power draw.
+		// On Ampere (except GA100) or newer GPUs, the API returns power averaged over 1 sec interval.
+		// On GA100 and older architectures, instantaneous power is returned.
 		//
-		// It is only available if power management mode is supported
+		// It is only available if power management mode is supported.
+
 		mode, ret := nvml.DeviceGetPowerManagementMode(device.device)
 		if ret != nvml.SUCCESS {
 			return nil
@@ -442,7 +464,7 @@ func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 		if mode == nvml.FEATURE_ENABLED {
 			power, ret := nvml.DeviceGetPowerUsage(device.device)
 			if ret == nvml.SUCCESS {
-				y, err := lp.New("nv_power_usage", device.tags, device.meta, map[string]interface{}{"value": float64(power) / 1000}, time.Now())
+				y, err := lp.NewMessage("nv_power_usage", device.tags, device.meta, map[string]interface{}{"value": float64(power) / 1000}, time.Now())
 				if err == nil {
 					y.AddMeta("unit", "watts")
 					output <- y
@@ -453,7 +475,54 @@ func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	return nil
 }
 
-func readClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readEnergyConsumption(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
+	// Retrieves total energy consumption for this GPU in millijoules (mJ) since the driver was last reloaded
+
+	// For Volta or newer fully supported devices.
+	if (!device.excludeMetrics["nv_energy"]) && (!device.excludeMetrics["nv_energy_abs"]) && (!device.excludeMetrics["nv_average_power"]) {
+		now := time.Now()
+		mode, ret := nvml.DeviceGetPowerManagementMode(device.device)
+		if ret != nvml.SUCCESS {
+			return nil
+		}
+		if mode == nvml.FEATURE_ENABLED {
+			energy, ret := nvml.DeviceGetTotalEnergyConsumption(device.device)
+			if ret == nvml.SUCCESS {
+				if device.lastEnergyReading != 0 {
+					if !device.excludeMetrics["nv_energy"] {
+						y, err := lp.NewMetric("nv_energy", device.tags, device.meta, (energy-device.lastEnergyReading)/1000, now)
+						if err == nil {
+							y.AddMeta("unit", "Joules")
+							output <- y
+						}
+					}
+					if !device.excludeMetrics["nv_average_power"] {
+
+						energyDiff := (energy - device.lastEnergyReading) / 1000
+						timeDiff := now.Sub(device.lastEnergyTimestamp)
+						y, err := lp.NewMetric("nv_average_power", device.tags, device.meta, energyDiff/uint64(timeDiff.Seconds()), now)
+						if err == nil {
+							y.AddMeta("unit", "watts")
+							output <- y
+						}
+					}
+				}
+				if !device.excludeMetrics["nv_energy_abs"] {
+					y, err := lp.NewMetric("nv_energy_abs", device.tags, device.meta, energy/1000, now)
+					if err == nil {
+						y.AddMeta("unit", "Joules")
+						output <- y
+					}
+				}
+				device.lastEnergyReading = energy
+				device.lastEnergyTimestamp = time.Now()
+			}
+		}
+	}
+	return nil
+}
+
+func readClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	// Retrieves the current clock speeds for the device.
 	//
 	// Available clock information:
@@ -463,7 +532,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_graphics_clock"] {
 		graphicsClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_GRAPHICS)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(graphicsClock)}, time.Now())
+			y, err := lp.NewMessage("nv_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(graphicsClock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -474,7 +543,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_sm_clock"] {
 		smCock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(smCock)}, time.Now())
+			y, err := lp.NewMessage("nv_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(smCock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -485,7 +554,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_mem_clock"] {
 		memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
+			y, err := lp.NewMessage("nv_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -495,7 +564,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_video_clock"] {
 		memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
+			y, err := lp.NewMessage("nv_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -505,7 +574,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	return nil
 }
 
-func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readMaxClocks(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	// Retrieves the maximum clock speeds for the device.
 	//
 	// Available clock information:
@@ -520,7 +589,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	if !device.excludeMetrics["nv_max_graphics_clock"] {
 		max_gclk, ret := nvml.DeviceGetMaxClockInfo(device.device, nvml.CLOCK_GRAPHICS)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_max_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(max_gclk)}, time.Now())
+			y, err := lp.NewMessage("nv_max_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(max_gclk)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -531,7 +600,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	if !device.excludeMetrics["nv_max_sm_clock"] {
 		maxSmClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_max_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxSmClock)}, time.Now())
+			y, err := lp.NewMessage("nv_max_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxSmClock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -542,7 +611,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	if !device.excludeMetrics["nv_max_mem_clock"] {
 		maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_max_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
+			y, err := lp.NewMessage("nv_max_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -553,7 +622,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	if !device.excludeMetrics["nv_max_video_clock"] {
 		maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_max_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
+			y, err := lp.NewMessage("nv_max_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -563,7 +632,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	return nil
 }
 
-func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readEccErrors(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_ecc_uncorrected_error"] {
 		// Retrieves the total ECC error counts for the device.
 		//
@@ -576,7 +645,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 		// i.e. the total set of errors across the entire device.
 		ecc_db, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_UNCORRECTED, nvml.AGGREGATE_ECC)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_ecc_uncorrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_db)}, time.Now())
+			y, err := lp.NewMessage("nv_ecc_uncorrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_db)}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -585,7 +654,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	if !device.excludeMetrics["nv_ecc_corrected_error"] {
 		ecc_sb, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_CORRECTED, nvml.AGGREGATE_ECC)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_ecc_corrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_sb)}, time.Now())
+			y, err := lp.NewMessage("nv_ecc_corrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_sb)}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -594,7 +663,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	return nil
 }
 
-func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readPowerLimit(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_power_max_limit"] {
 		// Retrieves the power management limit associated with this device.
 		//
@@ -604,7 +673,7 @@ func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 		// If the card's total power draw reaches this limit the power management algorithm kicks in.
 		pwr_limit, ret := nvml.DeviceGetPowerManagementLimit(device.device)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_power_max_limit", device.tags, device.meta, map[string]interface{}{"value": float64(pwr_limit) / 1000}, time.Now())
+			y, err := lp.NewMessage("nv_power_max_limit", device.tags, device.meta, map[string]interface{}{"value": float64(pwr_limit) / 1000}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "watts")
 				output <- y
@@ -614,7 +683,7 @@ func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMetric) error
 	return nil
 }
 
-func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readEncUtilization(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
 	if ret != nvml.SUCCESS {
 		err := errors.New(nvml.ErrorString(ret))
@@ -631,7 +700,7 @@ func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		// Note: On MIG-enabled GPUs, querying encoder utilization is not currently supported.
 		enc_util, _, ret := nvml.DeviceGetEncoderUtilization(device.device)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_encoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(enc_util)}, time.Now())
+			y, err := lp.NewMessage("nv_encoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(enc_util)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "%")
 				output <- y
@@ -641,7 +710,7 @@ func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 	return nil
 }
 
-func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readDecUtilization(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
 	if ret != nvml.SUCCESS {
 		err := errors.New(nvml.ErrorString(ret))
@@ -658,7 +727,7 @@ func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		// Note: On MIG-enabled GPUs, querying encoder utilization is not currently supported.
 		dec_util, _, ret := nvml.DeviceGetDecoderUtilization(device.device)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_decoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(dec_util)}, time.Now())
+			y, err := lp.NewMessage("nv_decoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(dec_util)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "%")
 				output <- y
@@ -668,7 +737,7 @@ func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 	return nil
 }
 
-func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readRemappedRows(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_remapped_rows_corrected"] ||
 		!device.excludeMetrics["nv_remapped_rows_uncorrected"] ||
 		!device.excludeMetrics["nv_remapped_rows_pending"] ||
@@ -685,13 +754,13 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMetric) err
 		corrected, uncorrected, pending, failure, ret := nvml.DeviceGetRemappedRows(device.device)
 		if ret == nvml.SUCCESS {
 			if !device.excludeMetrics["nv_remapped_rows_corrected"] {
-				y, err := lp.New("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(corrected)}, time.Now())
+				y, err := lp.NewMessage("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(corrected)}, time.Now())
 				if err == nil {
 					output <- y
 				}
 			}
 			if !device.excludeMetrics["nv_remapped_rows_uncorrected"] {
-				y, err := lp.New("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(uncorrected)}, time.Now())
+				y, err := lp.NewMessage("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(uncorrected)}, time.Now())
 				if err == nil {
 					output <- y
 				}
@@ -701,7 +770,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMetric) err
 				if pending {
 					p = 1
 				}
-				y, err := lp.New("nv_remapped_rows_pending", device.tags, device.meta, map[string]interface{}{"value": p}, time.Now())
+				y, err := lp.NewMessage("nv_remapped_rows_pending", device.tags, device.meta, map[string]interface{}{"value": p}, time.Now())
 				if err == nil {
 					output <- y
 				}
@@ -711,7 +780,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMetric) err
 				if failure {
 					f = 1
 				}
-				y, err := lp.New("nv_remapped_rows_failure", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
+				y, err := lp.NewMessage("nv_remapped_rows_failure", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
 				if err == nil {
 					output <- y
 				}
@@ -721,7 +790,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMetric) err
 	return nil
 }
 
-func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readProcessCounts(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_compute_processes"] {
 		// Get information about processes with a compute context on a device
 		//
@@ -745,7 +814,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMetric) er
 		//        Querying per-instance information using MIG device handles is not supported if the device is in vGPU Host virtualization mode.
 		procList, ret := nvml.DeviceGetComputeRunningProcesses(device.device)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
+			y, err := lp.NewMessage("nv_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -774,7 +843,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMetric) er
 		//       Querying per-instance information using MIG device handles is not supported if the device is in vGPU Host virtualization mode.
 		procList, ret := nvml.DeviceGetGraphicsRunningProcesses(device.device)
 		if ret == nvml.SUCCESS {
-			y, err := lp.New("nv_graphics_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
+			y, err := lp.NewMessage("nv_graphics_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -804,7 +873,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMetric) er
 	// 	//       Querying per-instance information using MIG device handles is not supported if the device is in vGPU Host virtualization mode.
 	// 	procList, ret := nvml.DeviceGetMPSComputeRunningProcesses(device.device)
 	// 	if ret == nvml.SUCCESS {
-	// 		y, err := lp.New("nv_mps_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
+	// 		y, err := lp.NewMessage("nv_mps_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
 	// 		if err == nil {
 	// 			output <- y
 	// 		}
@@ -813,7 +882,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMetric) er
 	return nil
 }
 
-func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readViolationStats(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	var violTime nvml.ViolationTime
 	var ret nvml.Return
 
@@ -832,7 +901,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_POWER)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.New("nv_violation_power", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_violation_power", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -844,7 +913,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_THERMAL)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.New("nv_violation_thermal", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_violation_thermal", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -856,7 +925,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_SYNC_BOOST)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.New("nv_violation_sync_boost", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_violation_sync_boost", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -868,7 +937,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_BOARD_LIMIT)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.New("nv_violation_board_limit", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_violation_board_limit", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -880,7 +949,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_LOW_UTILIZATION)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.New("nv_violation_low_util", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_violation_low_util", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -892,7 +961,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_RELIABILITY)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.New("nv_violation_reliability", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_violation_reliability", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -904,7 +973,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_TOTAL_APP_CLOCKS)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.New("nv_violation_below_app_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_violation_below_app_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -916,7 +985,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_TOTAL_BASE_CLOCKS)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.New("nv_violation_below_base_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.NewMessage("nv_violation_below_base_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -927,12 +996,18 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) e
 	return nil
 }
 
-func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
+func readNVLinkStats(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	// Retrieves the specified error counter value
 	// Please refer to \a nvmlNvLinkErrorCounter_t for error counters that are available
 	//
 	// For Pascal &tm; or newer fully supported devices.
 
+	var aggregate_crc_errors uint64 = 0
+	var aggregate_ecc_errors uint64 = 0
+	var aggregate_replay_errors uint64 = 0
+	var aggregate_recovery_errors uint64 = 0
+	var aggregate_crc_flit_errors uint64 = 0
+
 	for i := 0; i < nvml.NVLINK_MAX_LINKS; i++ {
 		state, ret := nvml.DeviceGetNvLinkState(device.device, i)
 		if ret == nvml.SUCCESS {
@@ -940,8 +1015,9 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMetric) erro
 				if !device.excludeMetrics["nv_nvlink_crc_errors"] {
 					// Data link receive data CRC error counter
 					count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_CRC_DATA)
+					aggregate_crc_errors = aggregate_crc_errors + count
 					if ret == nvml.SUCCESS {
-						y, err := lp.New("nv_nvlink_crc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.NewMessage("nv_nvlink_crc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
 						if err == nil {
 							y.AddTag("stype", "nvlink")
 							y.AddTag("stype-id", fmt.Sprintf("%d", i))
@@ -952,8 +1028,9 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMetric) erro
 				if !device.excludeMetrics["nv_nvlink_ecc_errors"] {
 					// Data link receive data ECC error counter
 					count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_ECC_DATA)
+					aggregate_ecc_errors = aggregate_ecc_errors + count
 					if ret == nvml.SUCCESS {
-						y, err := lp.New("nv_nvlink_ecc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.NewMessage("nv_nvlink_ecc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
 						if err == nil {
 							y.AddTag("stype", "nvlink")
 							y.AddTag("stype-id", fmt.Sprintf("%d", i))
@@ -964,8 +1041,9 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMetric) erro
 				if !device.excludeMetrics["nv_nvlink_replay_errors"] {
 					// Data link transmit replay error counter
 					count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_REPLAY)
+					aggregate_replay_errors = aggregate_replay_errors + count
 					if ret == nvml.SUCCESS {
-						y, err := lp.New("nv_nvlink_replay_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.NewMessage("nv_nvlink_replay_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
 						if err == nil {
 							y.AddTag("stype", "nvlink")
 							y.AddTag("stype-id", fmt.Sprintf("%d", i))
@@ -976,8 +1054,9 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMetric) erro
 				if !device.excludeMetrics["nv_nvlink_recovery_errors"] {
 					// Data link transmit recovery error counter
 					count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_RECOVERY)
+					aggregate_recovery_errors = aggregate_recovery_errors + count
 					if ret == nvml.SUCCESS {
-						y, err := lp.New("nv_nvlink_recovery_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.NewMessage("nv_nvlink_recovery_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
 						if err == nil {
 							y.AddTag("stype", "nvlink")
 							y.AddTag("stype-id", fmt.Sprintf("%d", i))
@@ -988,8 +1067,9 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMetric) erro
 				if !device.excludeMetrics["nv_nvlink_crc_flit_errors"] {
 					// Data link receive flow control digit CRC error counter
 					count, ret := nvml.DeviceGetNvLinkErrorCounter(device.device, i, nvml.NVLINK_ERROR_DL_CRC_FLIT)
+					aggregate_crc_flit_errors = aggregate_crc_flit_errors + count
 					if ret == nvml.SUCCESS {
-						y, err := lp.New("nv_nvlink_crc_flit_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.NewMessage("nv_nvlink_crc_flit_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
 						if err == nil {
 							y.AddTag("stype", "nvlink")
 							y.AddTag("stype-id", fmt.Sprintf("%d", i))
@@ -1000,16 +1080,58 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMetric) erro
 			}
 		}
 	}
+
+	// Export aggegated values
+	if !device.excludeMetrics["nv_nvlink_crc_errors"] {
+		// Data link receive data CRC error counter
+		y, err := lp.NewMessage("nv_nvlink_crc_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_crc_errors}, time.Now())
+		if err == nil {
+			y.AddTag("stype", "nvlink")
+			output <- y
+		}
+	}
+	if !device.excludeMetrics["nv_nvlink_ecc_errors"] {
+		// Data link receive data ECC error counter
+		y, err := lp.NewMessage("nv_nvlink_ecc_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_ecc_errors}, time.Now())
+		if err == nil {
+			y.AddTag("stype", "nvlink")
+			output <- y
+		}
+	}
+	if !device.excludeMetrics["nv_nvlink_replay_errors"] {
+		// Data link transmit replay error counter
+		y, err := lp.NewMessage("nv_nvlink_replay_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_replay_errors}, time.Now())
+		if err == nil {
+			y.AddTag("stype", "nvlink")
+			output <- y
+		}
+	}
+	if !device.excludeMetrics["nv_nvlink_recovery_errors"] {
+		// Data link transmit recovery error counter
+		y, err := lp.NewMessage("nv_nvlink_recovery_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_recovery_errors}, time.Now())
+		if err == nil {
+			y.AddTag("stype", "nvlink")
+			output <- y
+		}
+	}
+	if !device.excludeMetrics["nv_nvlink_crc_flit_errors"] {
+		// Data link receive flow control digit CRC error counter
+		y, err := lp.NewMessage("nv_nvlink_crc_flit_errors_sum", device.tags, device.meta, map[string]interface{}{"value": aggregate_crc_flit_errors}, time.Now())
+		if err == nil {
+			y.AddTag("stype", "nvlink")
+			output <- y
+		}
+	}
 	return nil
 }
 
-func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	var err error
 	if !m.init {
 		return
 	}
 
-	readAll := func(device NvidiaCollectorDevice, output chan lp.CCMetric) {
+	readAll := func(device *NvidiaCollectorDevice, output chan lp.CCMessage) {
 		name, ret := nvml.DeviceGetName(device.device)
 		if ret != nvml.SUCCESS {
 			name = "NoName"
@@ -1049,6 +1171,11 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMetric)
 			cclog.ComponentDebug(m.name, "readPowerUsage for device", name, "failed")
 		}
 
+		err = readEnergyConsumption(device, output)
+		if err != nil {
+			cclog.ComponentDebug(m.name, "readEnergyConsumption for device", name, "failed")
+		}
+
 		err = readClocks(device, output)
 		if err != nil {
 			cclog.ComponentDebug(m.name, "readClocks for device", name, "failed")
@@ -1108,7 +1235,7 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	// Actual read loop over all attached Nvidia GPUs
 	for i := 0; i < m.num_gpus; i++ {
 
-		readAll(m.gpus[i], output)
+		readAll(&m.gpus[i], output)
 
 		// Iterate over all MIG devices if any
 		if m.config.ProcessMigDevices {
@@ -1182,7 +1309,7 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMetric)
 					}
 				}
 
-				readAll(migDevice, output)
+				readAll(&migDevice, output)
 			}
 		}
 	}

collectors/nvidiaMetric.md

@@ -1,3 +1,13 @@
+<!--
+---
+title: "Nvidia NVML metric collector"
+description: Collect metrics for Nvidia GPUs using the NVML
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/nvidia.md
+---
+-->
 
 ## `nvidia` collector
 
@@ -72,5 +82,8 @@ Metrics:
 * `nv_nvlink_ecc_errors`
 * `nv_nvlink_replay_errors`
 * `nv_nvlink_recovery_errors`
+* `nv_energy`
+* `nv_energy_abs`
+* `nv_average_power`
 
-Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`. 
+Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`. 

collectors/raplMetric.go

@@ -0,0 +1,269 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
+package collectors
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+)
+
+// running average power limit (RAPL) monitoring attributes for a zone
+type RAPLZoneInfo struct {
+	// tags describing the RAPL zone:
+	// * zone_name, subzone_name: e.g. psys, dram, core, uncore, package-0
+	// * zone_id: e.g. 0:1 (zone 0 sub zone 1)
+	tags            map[string]string
+	energyFilepath  string    // path to a file containing the zones current energy counter in micro joules
+	energy          int64     // current reading of the energy counter in micro joules
+	energyTimestamp time.Time // timestamp when energy counter was read
+	maxEnergyRange  int64     // Range of the above energy counter in micro-joules
+}
+
+type RAPLCollector struct {
+	metricCollector
+	config struct {
+		// Exclude IDs for RAPL zones, e.g.
+		// * 0 for zone 0
+		// * 0:1 for zone 0 subzone 1
+		ExcludeByID []string `json:"exclude_device_by_id,omitempty"`
+		// Exclude names for RAPL zones, e.g. psys, dram, core, uncore, package-0
+		ExcludeByName []string `json:"exclude_device_by_name,omitempty"`
+	}
+	RAPLZoneInfo []RAPLZoneInfo
+	meta         map[string]string // default meta information
+}
+
+// Init initializes the running average power limit (RAPL) collector
+func (m *RAPLCollector) Init(config json.RawMessage) error {
+
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+
+	var err error = nil
+	m.name = "RAPLCollector"
+	m.setup()
+	m.parallel = true
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "energy",
+		"unit":   "Watt",
+	}
+
+	// Read in the JSON configuration
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			cclog.ComponentError(m.name, "Error reading config:", err.Error())
+			return err
+		}
+	}
+
+	// Configure excluded RAPL zones
+	isIDExcluded := make(map[string]bool)
+	if m.config.ExcludeByID != nil {
+		for _, ID := range m.config.ExcludeByID {
+			isIDExcluded[ID] = true
+		}
+	}
+	isNameExcluded := make(map[string]bool)
+	if m.config.ExcludeByName != nil {
+		for _, name := range m.config.ExcludeByName {
+			isNameExcluded[name] = true
+		}
+	}
+
+	// readZoneInfo reads RAPL monitoring attributes for a zone given by zonePath
+	// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
+	readZoneInfo := func(zonePath string) (z struct {
+		name            string    // zones name e.g. psys, dram, core, uncore, package-0
+		energyFilepath  string    // path to a file containing the zones current energy counter in micro joules
+		energy          int64     // current reading of the energy counter in micro joules
+		energyTimestamp time.Time // timestamp when energy counter was read
+		maxEnergyRange  int64     // Range of the above energy counter in micro-joules
+		ok              bool      // Are all information available?
+	}) {
+		// zones name e.g. psys, dram, core, uncore, package-0
+		foundName := false
+		if v, err :=
+			os.ReadFile(
+				filepath.Join(zonePath, "name")); err == nil {
+			foundName = true
+			z.name = strings.TrimSpace(string(v))
+		}
+
+		// path to a file containing the zones current energy counter in micro joules
+		z.energyFilepath = filepath.Join(zonePath, "energy_uj")
+
+		// current reading of the energy counter in micro joules
+		foundEnergy := false
+		if v, err := os.ReadFile(z.energyFilepath); err == nil {
+			// timestamp when energy counter was read
+			z.energyTimestamp = time.Now()
+			if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
+				foundEnergy = true
+				z.energy = i
+			}
+		}
+
+		// Range of the above energy counter in micro-joules
+		foundMaxEnergyRange := false
+		if v, err :=
+			os.ReadFile(
+				filepath.Join(zonePath, "max_energy_range_uj")); err == nil {
+			if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
+				foundMaxEnergyRange = true
+				z.maxEnergyRange = i
+			}
+		}
+
+		// Are all information available?
+		z.ok = foundName && foundEnergy && foundMaxEnergyRange
+
+		return
+	}
+
+	powerCapPrefix := "/sys/devices/virtual/powercap"
+	controlType := "intel-rapl"
+	controlTypePath := filepath.Join(powerCapPrefix, controlType)
+
+	// Find all RAPL zones
+	zonePrefix := filepath.Join(controlTypePath, controlType+":")
+	zonesPath, err := filepath.Glob(zonePrefix + "*")
+	if err != nil || zonesPath == nil {
+		return fmt.Errorf("unable to find any zones under %s", controlTypePath)
+	}
+
+	for _, zonePath := range zonesPath {
+		zoneID := strings.TrimPrefix(zonePath, zonePrefix)
+		z := readZoneInfo(zonePath)
+		if z.ok &&
+			!isIDExcluded[zoneID] &&
+			!isNameExcluded[z.name] {
+
+			// Add RAPL monitoring attributes for a zone
+			m.RAPLZoneInfo =
+				append(
+					m.RAPLZoneInfo,
+					RAPLZoneInfo{
+						tags: map[string]string{
+							"id":        zoneID,
+							"zone_name": z.name,
+						},
+						energyFilepath:  z.energyFilepath,
+						energy:          z.energy,
+						energyTimestamp: z.energyTimestamp,
+						maxEnergyRange:  z.maxEnergyRange,
+					})
+		}
+
+		// find all sub zones for the given zone
+		subZonePrefix := filepath.Join(zonePath, controlType+":"+zoneID+":")
+		subZonesPath, err := filepath.Glob(subZonePrefix + "*")
+		if err != nil || subZonesPath == nil {
+			continue
+		}
+
+		for _, subZonePath := range subZonesPath {
+			subZoneID := strings.TrimPrefix(subZonePath, subZonePrefix)
+			sz := readZoneInfo(subZonePath)
+			if len(zoneID) > 0 && len(z.name) > 0 &&
+				sz.ok &&
+				!isIDExcluded[zoneID+":"+subZoneID] &&
+				!isNameExcluded[sz.name] {
+				m.RAPLZoneInfo =
+					append(
+						m.RAPLZoneInfo,
+						RAPLZoneInfo{
+							tags: map[string]string{
+								"id":            zoneID + ":" + subZoneID,
+								"zone_name":     z.name,
+								"sub_zone_name": sz.name,
+							},
+							energyFilepath:  sz.energyFilepath,
+							energy:          sz.energy,
+							energyTimestamp: sz.energyTimestamp,
+							maxEnergyRange:  sz.maxEnergyRange,
+						})
+			}
+		}
+	}
+
+	if m.RAPLZoneInfo == nil {
+		return fmt.Errorf("no running average power limit (RAPL) device found in %s", controlTypePath)
+
+	}
+
+	// Initialized
+	cclog.ComponentDebug(
+		m.name,
+		"initialized",
+		len(m.RAPLZoneInfo),
+		"zones with running average power limit (RAPL) monitoring attributes")
+	m.init = true
+
+	return err
+}
+
+// Read reads running average power limit (RAPL) monitoring attributes for all initialized zones
+// See: https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes
+func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+
+	for i := range m.RAPLZoneInfo {
+		p := &m.RAPLZoneInfo[i]
+
+		// Read current value of the energy counter in micro joules
+		if v, err := os.ReadFile(p.energyFilepath); err == nil {
+			energyTimestamp := time.Now()
+			if i, err := strconv.ParseInt(strings.TrimSpace(string(v)), 10, 64); err == nil {
+				energy := i
+
+				// Compute average power (Δ energy / Δ time)
+				energyDiff := energy - p.energy
+				if energyDiff < 0 {
+					// Handle overflow:
+					// ( p.maxEnergyRange - p.energy ) + energy
+					// = p.maxEnergyRange + ( energy - p.energy )
+					// = p.maxEnergyRange + diffEnergy
+					energyDiff += p.maxEnergyRange
+				}
+				timeDiff := energyTimestamp.Sub(p.energyTimestamp)
+				averagePower := float64(energyDiff) / float64(timeDiff.Microseconds())
+
+				y, err := lp.NewMessage(
+					"rapl_average_power",
+					p.tags,
+					m.meta,
+					map[string]interface{}{"value": averagePower},
+					energyTimestamp)
+				if err == nil {
+					output <- y
+				}
+
+				// Save current energy counter state
+				p.energy = energy
+				p.energyTimestamp = energyTimestamp
+			}
+		}
+	}
+}
+
+// Close closes running average power limit (RAPL) metric collector
+func (m *RAPLCollector) Close() {
+	// Unset flag
+	m.init = false
+}

collectors/raplMetric.md

@@ -0,0 +1,26 @@
+<!--
+---
+title: RAPL metric collector
+description: Collect energy data through the RAPL sysfs interface
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/rapl.md
+---
+-->
+
+## `rapl` collector
+
+This collector reads running average power limit (RAPL) monitoring attributes to compute average power consumption metrics. See <https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes>.
+
+The Likwid metric collector provides similar functionality.
+
+```json
+  "rapl": {
+    "exclude_device_by_id": ["0:1", "0:2"],
+    "exclude_device_by_name": ["psys"]
+  }
+```
+
+Metrics:
+* `rapl_average_power`: average power consumption in Watt. The average is computed over the entire runtime from the last measurement to the current measurement

collectors/rocmsmiMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -6,8 +13,8 @@ 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 	"github.com/ClusterCockpit/go-rocm-smi/pkg/rocm_smi"
 )
 
@@ -66,14 +73,14 @@ func (m *RocmSmiCollector) Init(config json.RawMessage) error {
 
 	ret := rocm_smi.Init()
 	if ret != rocm_smi.STATUS_SUCCESS {
-		err = errors.New("Failed to initialize ROCm SMI library")
+		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")
+		err = errors.New("failed to get number of GPUs from ROCm SMI library")
 		cclog.ComponentError(m.name, err.Error())
 		return err
 	}
@@ -98,14 +105,14 @@ func (m *RocmSmiCollector) Init(config json.RawMessage) error {
 		}
 		device, ret := rocm_smi.DeviceGetHandleByIndex(i)
 		if ret != rocm_smi.STATUS_SUCCESS {
-			err = fmt.Errorf("Failed to get handle for GPU %d", i)
+			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)
+			err = fmt.Errorf("failed to get PCI information for GPU %d", i)
 			cclog.ComponentError(m.name, err.Error())
 			return err
 		}
@@ -162,7 +169,7 @@ func (m *RocmSmiCollector) Init(config json.RawMessage) error {
 
 // 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) {
+func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	// Create a sample metric
 	timestamp := time.Now()
 
@@ -175,119 +182,119 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMetric)
 
 		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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("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)
+			y, err := lp.NewMessage("rocm_d1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
@@ -295,7 +302,7 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		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)
+				y, err := lp.NewMessage("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))

collectors/rocmsmiMetric.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: "ROCm SMI metric collector"
+description: Collect metrics for AMD GPUs using the SMI library
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/rocmsmi.md
+---
+-->
+
 
 ## `rocm_smi` collector
 

collectors/sampleMetric.go

@@ -1,11 +1,18 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 // These are the fields we read from the JSON configuration
@@ -17,9 +24,9 @@ type SampleCollectorConfig struct {
 // defined by metricCollector (name, init, ...)
 type SampleCollector struct {
 	metricCollector
-	config SampleTimerCollectorConfig // the configuration structure
-	meta   map[string]string          // default meta information
-	tags   map[string]string          // default tags
+	config SampleCollectorConfig // the configuration structure
+	meta   map[string]string     // default meta information
+	tags   map[string]string     // default tags
 }
 
 // Functions to implement MetricCollector interface
@@ -32,18 +39,18 @@ type SampleCollector struct {
 func (m *SampleCollector) 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 = "InternalCollector"
+	m.name = "SampleCollector"
 	// 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
+	// or it should be run serially, mostly for collectors actually doing measurements
 	// because they should not measure the execution of the other collectors
 	m.parallel = true
 	// Define meta information sent with each metric
 	// (Can also be dynamic or this is the basic set with extension through AddMeta())
 	m.meta = map[string]string{"source": m.name, "group": "SAMPLE"}
 	// Define tags sent with each metric
-	// The 'type' tag is always needed, it defines the granulatity of the metric
+	// The 'type' tag is always needed, it defines the granularity of the metric
 	// node -> whole system
 	// socket -> CPU socket (requires socket ID as 'type-id' tag)
 	// die -> CPU die (requires CPU die ID as 'type-id' tag)
@@ -74,7 +81,7 @@ func (m *SampleCollector) Init(config json.RawMessage) error {
 
 // Read collects all metrics belonging to the sample collector
 // and sends them through the output channel to the collector manager
-func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	// Create a sample metric
 	timestamp := time.Now()
 
@@ -85,7 +92,7 @@ func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	// stop := readState()
 	// value = (stop - start) / interval.Seconds()
 
-	y, err := lp.New("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+	y, err := lp.NewMessage("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
 	if err == nil {
 		// Send it to output channel
 		output <- y

collectors/sampleTimerMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -5,8 +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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 // These are the fields we read from the JSON configuration
@@ -25,7 +32,7 @@ type SampleTimerCollector struct {
 	config   SampleTimerCollectorConfig // the configuration structure
 	interval time.Duration              // the interval parsed from configuration
 	ticker   *time.Ticker               // own timer
-	output   chan lp.CCMetric           // own internal output channel
+	output   chan lp.CCMessage          // own internal output channel
 }
 
 func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
@@ -38,7 +45,7 @@ func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
 	// (Can also be dynamic or this is the basic set with extension through AddMeta())
 	m.meta = map[string]string{"source": m.name, "group": "SAMPLE"}
 	// Define tags sent with each metric
-	// The 'type' tag is always needed, it defines the granulatity of the metric
+	// The 'type' tag is always needed, it defines the granularity of the metric
 	// node -> whole system
 	// socket -> CPU socket (requires socket ID as 'type-id' tag)
 	// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
@@ -60,7 +67,7 @@ func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
 
 	// Storage for output channel
 	m.output = nil
-	// Mangement channel for the timer function.
+	// Management channel for the timer function.
 	m.done = make(chan bool)
 	// Create the own ticker
 	m.ticker = time.NewTicker(m.interval)
@@ -94,20 +101,20 @@ func (m *SampleTimerCollector) ReadMetrics(timestamp time.Time) {
 
 	value := 1.0
 
-	// If you want to measure something for a specific amout of time, use interval
+	// If you want to measure something for a specific amount of time, use interval
 	// start := readState()
 	// time.Sleep(interval)
 	// stop := readState()
 	// value = (stop - start) / interval.Seconds()
 
-	y, err := lp.New("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+	y, err := lp.NewMessage("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
 	if err == nil && m.output != nil {
 		// Send it to output channel if we have a valid channel
 		m.output <- y
 	}
 }
 
-func (m *SampleTimerCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *SampleTimerCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	// Capture output channel
 	m.output = output
 }

collectors/schedstatMetric.go

@@ -0,0 +1,161 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
+package collectors
+
+import (
+	"bufio"
+	"encoding/json"
+	"fmt"
+	"math"
+	"os"
+	"strconv"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+)
+
+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.CCMessage, 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.NewMessage("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.CCMessage) {
+	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 +1,21 @@
+<!--
+---
+title: SchedStat Metric collector
+description: Collect metrics from `/proc/schedstat`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/schedstat.md
+---
+-->
+
+## `schedstat` collector
+```json
+  "schedstat": {
+  }
+```
+
+The `schedstat` collector reads data from /proc/schedstat and calculates a load value, separated by hwthread. This might be useful to detect bad cpu pinning on shared nodes etc. 
+
+Metric:
+* `cpu_load_core`

collectors/selfMetric.go

@@ -0,0 +1,151 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
+package collectors
+
+import (
+	"encoding/json"
+	"runtime"
+	"syscall"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+)
+
+type SelfCollectorConfig struct {
+	MemStats   bool `json:"read_mem_stats"`
+	GoRoutines bool `json:"read_goroutines"`
+	CgoCalls   bool `json:"read_cgo_calls"`
+	Rusage     bool `json:"read_rusage"`
+}
+
+type SelfCollector struct {
+	metricCollector
+	config SelfCollectorConfig // the configuration structure
+	meta   map[string]string   // default meta information
+	tags   map[string]string   // default tags
+}
+
+func (m *SelfCollector) Init(config json.RawMessage) error {
+	var err error = nil
+	m.name = "SelfCollector"
+	m.setup()
+	m.parallel = true
+	m.meta = map[string]string{"source": m.name, "group": "Self"}
+	m.tags = map[string]string{"type": "node"}
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			cclog.ComponentError(m.name, "Error reading config:", err.Error())
+			return err
+		}
+	}
+	m.init = true
+	return err
+}
+
+func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+	timestamp := time.Now()
+
+	if m.config.MemStats {
+		var memstats runtime.MemStats
+		runtime.ReadMemStats(&memstats)
+
+		y, err := lp.NewMessage("total_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.TotalAlloc}, timestamp)
+		if err == nil {
+			y.AddMeta("unit", "Bytes")
+			output <- y
+		}
+		y, err = lp.NewMessage("heap_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapAlloc}, timestamp)
+		if err == nil {
+			y.AddMeta("unit", "Bytes")
+			output <- y
+		}
+		y, err = lp.NewMessage("heap_sys", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapSys}, timestamp)
+		if err == nil {
+			y.AddMeta("unit", "Bytes")
+			output <- y
+		}
+		y, err = lp.NewMessage("heap_idle", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapIdle}, timestamp)
+		if err == nil {
+			y.AddMeta("unit", "Bytes")
+			output <- y
+		}
+		y, err = lp.NewMessage("heap_inuse", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapInuse}, timestamp)
+		if err == nil {
+			y.AddMeta("unit", "Bytes")
+			output <- y
+		}
+		y, err = lp.NewMessage("heap_released", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapReleased}, timestamp)
+		if err == nil {
+			y.AddMeta("unit", "Bytes")
+			output <- y
+		}
+		y, err = lp.NewMessage("heap_objects", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapObjects}, timestamp)
+		if err == nil {
+			output <- y
+		}
+	}
+	if m.config.GoRoutines {
+		y, err := lp.NewMessage("num_goroutines", m.tags, m.meta, map[string]interface{}{"value": runtime.NumGoroutine()}, timestamp)
+		if err == nil {
+			output <- y
+		}
+	}
+	if m.config.CgoCalls {
+		y, err := lp.NewMessage("num_cgo_calls", m.tags, m.meta, map[string]interface{}{"value": runtime.NumCgoCall()}, timestamp)
+		if err == nil {
+			output <- y
+		}
+	}
+	if m.config.Rusage {
+		var rusage syscall.Rusage
+		err := syscall.Getrusage(syscall.RUSAGE_SELF, &rusage)
+		if err == nil {
+			sec, nsec := rusage.Utime.Unix()
+			t := float64(sec) + (float64(nsec) * 1e-9)
+			y, err := lp.NewMessage("rusage_user_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
+			if err == nil {
+				y.AddMeta("unit", "seconds")
+				output <- y
+			}
+			sec, nsec = rusage.Stime.Unix()
+			t = float64(sec) + (float64(nsec) * 1e-9)
+			y, err = lp.NewMessage("rusage_system_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
+			if err == nil {
+				y.AddMeta("unit", "seconds")
+				output <- y
+			}
+			y, err = lp.NewMessage("rusage_vol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nvcsw}, timestamp)
+			if err == nil {
+				output <- y
+			}
+			y, err = lp.NewMessage("rusage_invol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nivcsw}, timestamp)
+			if err == nil {
+				output <- y
+			}
+			y, err = lp.NewMessage("rusage_signals", m.tags, m.meta, map[string]interface{}{"value": rusage.Nsignals}, timestamp)
+			if err == nil {
+				output <- y
+			}
+			y, err = lp.NewMessage("rusage_major_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Majflt}, timestamp)
+			if err == nil {
+				output <- y
+			}
+			y, err = lp.NewMessage("rusage_minor_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Minflt}, timestamp)
+			if err == nil {
+				output <- y
+			}
+		}
+
+	}
+}
+
+func (m *SelfCollector) Close() {
+	m.init = false
+}

collectors/selfMetric.md

@@ -0,0 +1,45 @@
+<!--
+---
+title: Self-monitoring metric collector
+description: Collect metrics from the execution of cc-metric-collector itself
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/self.md
+---
+-->
+
+## `self` collector
+
+```json
+  "self": {
+    "read_mem_stats" : true,
+    "read_goroutines" : true,
+    "read_cgo_calls" : true,
+    "read_rusage" : true
+  }
+```
+
+The `self` collector reads the data from the `runtime` and `syscall` packages, so monitors the execution of the cc-metric-collector itself.
+
+Metrics:
+* If `read_mem_stats == true`:
+  * `total_alloc`: The metric reports cumulative bytes allocated for heap objects.
+  * `heap_alloc`: The metric reports bytes of allocated heap objects.
+  * `heap_sys`: The metric reports bytes of heap memory obtained from the OS.
+  * `heap_idle`: The metric reports bytes in idle (unused) spans.
+  * `heap_inuse`: The metric reports bytes in in-use spans.
+  * `heap_released`: The metric reports bytes of physical memory returned to the OS.
+  * `heap_objects`: The metric reports the number of allocated heap objects.
+* If `read_goroutines == true`:
+  * `num_goroutines`: The metric reports the number of goroutines that currently exist.
+* If `read_cgo_calls == true`:
+  * `num_cgo_calls`: The metric reports the number of cgo calls made by the current process.
+* If `read_rusage == true`:
+  * `rusage_user_time`: The metric reports the amount of time that this process has been scheduled in user mode.
+  * `rusage_system_time`: The metric reports the amount of time that this process has been scheduled in kernel mode.
+  * `rusage_vol_ctx_switch`: The metric reports the amount of voluntary context switches.
+  * `rusage_invol_ctx_switch`: The metric reports the amount of involuntary context switches.
+  * `rusage_signals`: The metric reports the number of signals received.
+  * `rusage_major_pgfaults`: The metric reports the number of major faults the process has made which have required loading a memory page from disk.
+  * `rusage_minor_pgfaults`: The metric reports the number of minor faults the process has made which have not required loading a memory page from disk.

collectors/tempMetric.go

@@ -1,16 +1,23 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 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-lib/ccLogger"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 // See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html
@@ -83,14 +90,14 @@ 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))
 		}
@@ -117,7 +124,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		}
 
 		// Sensor file
-		_, err = ioutil.ReadFile(file)
+		_, err = os.ReadFile(file)
 		if err != nil {
 			continue
 		}
@@ -139,7 +146,7 @@ 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
@@ -150,7 +157,7 @@ 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
@@ -171,11 +178,11 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 
 	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,
@@ -190,7 +197,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 			continue
 		}
 		x /= 1000
-		y, err := lp.New(
+		y, err := lp.NewMessage(
 			sensor.metricName,
 			sensor.tags,
 			m.meta,
@@ -203,7 +210,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 		// max temperature
 		if m.config.ReportMaxTemp && sensor.maxTemp != 0 {
-			y, err := lp.New(
+			y, err := lp.NewMessage(
 				sensor.maxTempName,
 				sensor.tags,
 				m.meta,
@@ -217,7 +224,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 		// critical temperature
 		if m.config.ReportCriticalTemp && sensor.critTemp != 0 {
-			y, err := lp.New(
+			y, err := lp.NewMessage(
 				sensor.critTempName,
 				sensor.tags,
 				m.meta,

collectors/tempMetric.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: Temperature metric collector
+description: Collect thermal metrics from `/sys/class/hwmon/*`
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/temp.md
+---
+-->
+
 
 ## `tempstat` collector
 

collectors/topprocsMetric.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package collectors
 
 import (
@@ -9,7 +16,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 )
 
 const MAX_NUM_PROCS = 10
@@ -53,7 +60,7 @@ func (m *TopProcsCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	if !m.init {
 		return
 	}
@@ -68,7 +75,7 @@ func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMetric
 	lines := strings.Split(string(stdout), "\n")
 	for i := 1; i < m.config.Num_procs+1; i++ {
 		name := fmt.Sprintf("topproc%d", i)
-		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": string(lines[i])}, time.Now())
+		y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": string(lines[i])}, time.Now())
 		if err == nil {
 			output <- y
 		}

collectors/topprocsMetric.md

@@ -1,3 +1,15 @@
+<!--
+---
+title: TopProcs collector
+description: Collect infos about most CPU-consuming processes
+categories: [cc-metric-collector]
+tags: ['Admin']
+weight: 2
+hugo_path: docs/reference/cc-metric-collector/collectors/topprocs.md
+---
+-->
+
+
 
 ## `topprocs` collector
 

config.json

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

docs/building.md

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

docs/configuration.md

@@ -12,8 +12,8 @@ The global file contains the paths to the other four files and some global optio
   "collectors" : "collectors.json",
   "receivers" : "receivers.json",
   "router" : "router.json",
-  "interval": 10,
-  "duration": 1
+  "interval": "10s",
+  "duration": "1s"
 }
 ```
 

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

@@ -1,35 +1,48 @@
 module github.com/ClusterCockpit/cc-metric-collector
 
-go 1.17
+go 1.23.4
+
+toolchain go1.23.7
 
 require (
-	github.com/ClusterCockpit/cc-units v0.0.0-20220318130935-92a0c6442220
-	github.com/NVIDIA/go-nvml v0.11.6-0
-	github.com/PaesslerAG/gval v1.1.2
-	github.com/gorilla/mux v1.8.0
-	github.com/influxdata/influxdb-client-go/v2 v2.8.1
+	github.com/ClusterCockpit/cc-lib v0.1.1
+	github.com/ClusterCockpit/go-rocm-smi v0.3.0
+	github.com/NVIDIA/go-nvml v0.12.0-2
+	github.com/PaesslerAG/gval v1.2.2
+	github.com/fsnotify/fsnotify v1.7.0
+	github.com/gorilla/mux v1.8.1
+	github.com/influxdata/influxdb-client-go/v2 v2.14.0
 	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
-	github.com/nats-io/nats.go v1.14.0
-	github.com/prometheus/client_golang v1.12.1
-	github.com/stmcginnis/gofish v0.13.0
-	golang.org/x/sys v0.0.0-20220412211240-33da011f77ad
+	github.com/influxdata/line-protocol/v2 v2.2.1
+	github.com/nats-io/nats.go v1.39.0
+	github.com/prometheus/client_golang v1.20.5
+	github.com/stmcginnis/gofish v0.15.0
+	github.com/tklauser/go-sysconf v0.3.13
+	golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
+	golang.org/x/exp v0.0.0-20250215185904-eff6e970281f
+	golang.org/x/sys v0.30.0
 )
 
 require (
+	github.com/ClusterCockpit/cc-backend v1.4.2 // indirect
+	github.com/ClusterCockpit/cc-units v0.4.0 // indirect
+	github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
-	github.com/cespare/xxhash/v2 v2.1.2 // indirect
-	github.com/deepmap/oapi-codegen v1.8.2 // indirect
-	github.com/golang/protobuf v1.5.2 // indirect
-	github.com/matttproud/golang_protobuf_extensions v1.0.1 // indirect
-	github.com/nats-io/nats-server/v2 v2.8.0 // indirect
-	github.com/nats-io/nkeys v0.3.0 // indirect
+	github.com/cespare/xxhash/v2 v2.3.0 // indirect
+	github.com/expr-lang/expr v1.17.0 // indirect
+	github.com/google/uuid v1.6.0 // indirect
+	github.com/klauspost/compress v1.17.9 // indirect
+	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
+	github.com/nats-io/nkeys v0.4.9 // 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 v0.32.1 // indirect
-	github.com/prometheus/procfs v0.7.3 // indirect
-	golang.org/x/crypto v0.0.0-20220112180741-5e0467b6c7ce // indirect
-	golang.org/x/net v0.0.0-20211112202133-69e39bad7dc2 // indirect
-	google.golang.org/protobuf v1.26.0 // indirect
-	gopkg.in/yaml.v2 v2.4.0 // indirect
+	github.com/oapi-codegen/runtime v1.1.1 // indirect
+	github.com/prometheus/client_model v0.6.1 // indirect
+	github.com/prometheus/common v0.55.0 // indirect
+	github.com/prometheus/procfs v0.15.1 // indirect
+	github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 // indirect
+	github.com/shopspring/decimal v1.3.1 // indirect
+	github.com/tklauser/numcpus v0.7.0 // indirect
+	golang.org/x/crypto v0.35.0 // indirect
+	golang.org/x/net v0.36.0 // indirect
+	google.golang.org/protobuf v1.35.2 // indirect
 )

go.mod.1.16

@@ -1,16 +0,0 @@
-module github.com/ClusterCockpit/cc-metric-collector
-
-go 1.16
-
-require (
-	github.com/NVIDIA/go-nvml v0.11.6-0
-	github.com/PaesslerAG/gval v1.1.2
-	github.com/gorilla/mux v1.8.0
-	github.com/influxdata/influxdb-client-go/v2 v2.7.0
-	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
-	github.com/nats-io/nats-server/v2 v2.8.0 // indirect
-	github.com/nats-io/nats.go v1.14.0
-	github.com/prometheus/client_golang v1.12.1
-	github.com/stmcginnis/gofish v0.13.0
-	golang.org/x/sys v0.0.0-20220412211240-33da011f77ad
-)

go.mod.1.17+

@@ -1,16 +0,0 @@
-module github.com/ClusterCockpit/cc-metric-collector
-
-go 1.17
-
-require (
-	github.com/NVIDIA/go-nvml v0.11.6-0
-	github.com/PaesslerAG/gval v1.1.2
-	github.com/gorilla/mux v1.8.0
-	github.com/influxdata/influxdb-client-go/v2 v2.8.1
-	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
-	github.com/nats-io/nats-server/v2 v2.8.0 // indirect
-	github.com/nats-io/nats.go v1.14.0
-	github.com/prometheus/client_golang v1.12.1
-	github.com/stmcginnis/gofish v0.13.0
-	golang.org/x/sys v0.0.0-20220412211240-33da011f77ad
-)

go.sum

@@ -1,145 +1,139 @@
-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=
+github.com/ClusterCockpit/cc-backend v1.4.2 h1:kTOzqkh9N0564N9nqQThnSs7TAfg8RLgvSm00e5HtIc=
+github.com/ClusterCockpit/cc-backend v1.4.2/go.mod h1:g8TNHXe4AXej26snu2//jO3mUF980elT93iV/k11O/c=
+github.com/ClusterCockpit/cc-lib v0.1.0-beta.1 h1:dz9j0g2cod8+SMDjuoIY6ISpiHHeekhX6yQaeiwiwJw=
+github.com/ClusterCockpit/cc-lib v0.1.0-beta.1/go.mod h1:kXMskla1i5ZSfXW0vVRIHgGeXMU5zu2PzYOYnUaOr80=
+github.com/ClusterCockpit/cc-lib v0.1.1 h1:AXZWYUzgTaE/WdxLNSWPR7FJoA5WlzvYZxw4gIw3gNw=
+github.com/ClusterCockpit/cc-lib v0.1.1/go.mod h1:SHKcWW/+kN+pcofAtHJFxvmx1FV0VIJuQv5PuT0HDcc=
+github.com/ClusterCockpit/cc-units v0.4.0 h1:zP5DOu99GmErW0tCDf0gcLrlWt42RQ9dpoONEOh4cI0=
+github.com/ClusterCockpit/cc-units v0.4.0/go.mod h1:3S3PAhAayS3pbgcT4q9Vn9VJw22Op51X0YimtG77zBw=
+github.com/ClusterCockpit/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/go.mod h1:hy7HYeQy335x6nEss0Ne3PYqleRa6Ct+VKD9RQ4nyFs=
+github.com/NVIDIA/go-nvml v0.12.0-2 h1:Sg239yy7jmopu/cuvYauoMj9fOpcGMngxVxxS1EBXeY=
+github.com/NVIDIA/go-nvml v0.12.0-2/go.mod h1:7ruy85eOM73muOc/I37euONSwEyFqZsv5ED9AogD4G0=
+github.com/PaesslerAG/gval v1.2.2 h1:Y7iBzhgE09IGTt5QgGQ2IdaYYYOU134YGHBThD+wm9E=
+github.com/PaesslerAG/gval v1.2.2/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac=
+github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI=
 github.com/PaesslerAG/jsonpath v0.1.0/go.mod h1:4BzmtoM/PI8fPO4aQGIusjGxGir2BzcV0grWtFzq1Y8=
-github.com/cyberdelia/templates v0.0.0-20141128023046-ca7fffd4298c/go.mod h1:GyV+0YP4qX0UQ7r2MoYZ+AvYDp12OF5yg4q8rGnyNh4=
+github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk=
+github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ=
+github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP2+08jFMw88y4klk=
+github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
+github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
+github.com/bmatcuk/doublestar v1.1.1/go.mod h1:UD6OnuiIn0yFxxA2le/rnRU1G4RaI4UvFv1sNto9p6w=
+github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
+github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/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/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/go-openapi/jsonpointer v0.19.5/go.mod h1:Pl9vOtqEWErmShwVjC8pYs9cog34VGT37dQOVbmoatg=
-github.com/go-openapi/swag v0.19.5/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
-github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
-github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA=
-github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs=
-github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
-github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
-github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
-github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
-github.com/golang/protobuf v1.5.2 h1:ROPKBNFfQgOUMifHyP+KYbvpjbdoFNs+aK7DXlji0Tw=
-github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
-github.com/golang/snappy v0.0.3/go.mod h1:/XxbfmMg8lxefKM7IXC3fBNl/7bRcc72aCRzEWrmP2Q=
-github.com/golangci/lint-1 v0.0.0-20181222135242-d2cdd8c08219/go.mod h1:/X8TswGSh1pIozq4ZwCfxS0WA5JGXguxk94ar/4c87Y=
-github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
-github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
-github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/expr-lang/expr v1.16.9 h1:WUAzmR0JNI9JCiF0/ewwHB1gmcGw5wW7nWt8gc6PpCI=
+github.com/expr-lang/expr v1.16.9/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
+github.com/expr-lang/expr v1.17.0 h1:+vpszOyzKLQXC9VF+wA8cVA0tlA984/Wabc/1hF9Whg=
+github.com/expr-lang/expr v1.17.0/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
+github.com/frankban/quicktest v1.11.0/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
+github.com/frankban/quicktest v1.11.2/go.mod h1:K+q6oSqb0W0Ininfk863uOk1lMy69l/P6txr3mVT54s=
+github.com/frankban/quicktest v1.13.0 h1:yNZif1OkDfNoDfb9zZa9aXIpejNR4F23Wely0c+Qdqk=
+github.com/frankban/quicktest v1.13.0/go.mod h1:qLE0fzW0VuyUAJgPU19zByoIr0HtCHN/r/VLSOOIySU=
+github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
+github.com/fsnotify/fsnotify v1.7.0/go.mod h1:40Bi/Hjc2AVfZrqy+aj+yEI+/bRxZnMJyTJwOpGvigM=
+github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/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/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
+github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
+github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
+github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
+github.com/gorilla/mux v1.8.1 h1:TuBL49tXwgrFYWhqrNgrUNEY92u81SPhu7sTdzQEiWY=
+github.com/gorilla/mux v1.8.1/go.mod h1:AKf9I4AEqPTmMytcMc0KkNouC66V3BtZ4qD5fmWSiMQ=
+github.com/influxdata/influxdb-client-go/v2 v2.14.0 h1:AjbBfJuq+QoaXNcrova8smSjwJdUHnwvfjMF71M1iI4=
+github.com/influxdata/influxdb-client-go/v2 v2.14.0/go.mod h1:Ahpm3QXKMJslpXl3IftVLVezreAUtBOTZssDrjZEFHI=
 github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf h1:7JTmneyiNEwVBOHSjoMxiWAqB992atOeepeFYegn5RU=
 github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
-github.com/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/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
+github.com/influxdata/line-protocol-corpus v0.0.0-20210519164801-ca6fa5da0184/go.mod h1:03nmhxzZ7Xk2pdG+lmMd7mHDfeVOYFyhOgwO61qWU98=
+github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937 h1:MHJNQ+p99hFATQm6ORoLmpUCF7ovjwEFshs/NHzAbig=
+github.com/influxdata/line-protocol-corpus v0.0.0-20210922080147-aa28ccfb8937/go.mod h1:BKR9c0uHSmRgM/se9JhFHtTT7JTO67X23MtKMHtZcpo=
+github.com/influxdata/line-protocol/v2 v2.0.0-20210312151457-c52fdecb625a/go.mod h1:6+9Xt5Sq1rWx+glMgxhcg2c0DUaehK+5TDcPZ76GypY=
+github.com/influxdata/line-protocol/v2 v2.1.0/go.mod h1:QKw43hdUBg3GTk2iC3iyCxksNj7PX9aUSeYOYE/ceHY=
+github.com/influxdata/line-protocol/v2 v2.2.1 h1:EAPkqJ9Km4uAxtMRgUubJyqAr6zgWM0dznKMLRauQRE=
+github.com/influxdata/line-protocol/v2 v2.2.1/go.mod h1:DmB3Cnh+3oxmG6LOBIxce4oaL4CPj3OmMPgvauXh+tM=
+github.com/juju/gnuflag v0.0.0-20171113085948-2ce1bb71843d/go.mod h1:2PavIy+JPciBPrBUjwbNvtwB6RQlve+hkpll6QSNmOE=
+github.com/klauspost/compress v1.17.9 h1:6KIumPrER1LHsvBVuDa0r5xaG0Es51mhhB9BQB2qeMA=
+github.com/klauspost/compress v1.17.9/go.mod h1:Di0epgTjJY877eYKx5yC51cX2A2Vl2ibi7bDH9ttBbw=
+github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
+github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
+github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
-github.com/kr/text v0.1.0 h1:45sCR5RtlFHMR4UwH9sdQ5TC8v0qDQCHnXt+kaKSTVE=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
-github.com/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/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/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Kysco4FUpU=
-github.com/minio/highwayhash v1.0.1 h1:dZ6IIu8Z14VlC0VpfKofAhCy74wu/Qb5gcn52yWoz/0=
-github.com/minio/highwayhash v1.0.1/go.mod h1:BQskDq+xkJ12lmlUUi7U0M5Swg3EWR+dLTk+kldvVxY=
-github.com/nats-io/jwt/v2 v2.2.1-0.20220113022732-58e87895b296 h1:vU9tpM3apjYlLLeY23zRWJ9Zktr5jp+mloR942LEOpY=
-github.com/nats-io/jwt/v2 v2.2.1-0.20220113022732-58e87895b296/go.mod h1:0tqz9Hlu6bCBFLWAASKhE5vUA4c24L9KPUUgvwumE/k=
-github.com/nats-io/nats-server/v2 v2.7.0 h1:UpqcAM93FI7AHlCyI2FD5QcV3QuHNCauQF2LBVU0238=
-github.com/nats-io/nats-server/v2 v2.7.0/go.mod h1:cjxtMhZsZovK1XS2iiapCduR8HuqB/YpFamL0qntIcw=
-github.com/nats-io/nats.go v1.13.1-0.20211122170419-d7c1d78a50fc h1:SHr4MUUZJ/fAC0uSm2OzWOJYsHpapmR86mpw7q1qPXU=
-github.com/nats-io/nats.go v1.13.1-0.20211122170419-d7c1d78a50fc/go.mod h1:BPko4oXsySz4aSWeFgOHLZs3G4Jq4ZAyE6/zMCxRT6w=
-github.com/nats-io/nkeys v0.3.0 h1:cgM5tL53EvYRU+2YLXIK0G2mJtK12Ft9oeooSZMA2G8=
-github.com/nats-io/nkeys v0.3.0/go.mod h1:gvUNGjVcM2IPr5rCsRsC6Wb3Hr2CQAm08dsxtV6A5y4=
+github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
+github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
+github.com/kylelemons/godebug v1.1.0 h1:RPNrshWIDI6G2gRW9EHilWtl7Z6Sb1BR0xunSBf0SNc=
+github.com/kylelemons/godebug v1.1.0/go.mod h1:9/0rRGxNHcop5bhtWyNeEfOS8JIWk580+fNqagV/RAw=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
+github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
+github.com/nats-io/nats.go v1.39.0 h1:2/yg2JQjiYYKLwDuBzV0FbB2sIV+eFNkEevlRi4n9lI=
+github.com/nats-io/nats.go v1.39.0/go.mod h1:MgRb8oOdigA6cYpEPhXJuRVH6UE/V4jblJ2jQ27IXYM=
+github.com/nats-io/nkeys v0.4.9 h1:qe9Faq2Gxwi6RZnZMXfmGMZkg3afLLOtrU+gDZJ35b0=
+github.com/nats-io/nkeys v0.4.9/go.mod h1:jcMqs+FLG+W5YO36OX6wFIFcmpdAns+w1Wm6D3I/evE=
 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/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/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
+github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmtpMYro=
+github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg=
 github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
+github.com/prometheus/client_golang v1.20.5 h1:cxppBPuYhUnsO6yo/aoRol4L7q7UFfdm+bR9r+8l63Y=
+github.com/prometheus/client_golang v1.20.5/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE=
+github.com/prometheus/client_model v0.6.1 h1:ZKSh/rekM+n3CeS952MLRAdFwIKqeY8b62p8ais2e9E=
+github.com/prometheus/client_model v0.6.1/go.mod h1:OrxVMOVHjw3lKMa8+x6HeMGkHMQyHDk9E3jmP2AmGiY=
+github.com/prometheus/common v0.55.0 h1:KEi6DK7lXW/m7Ig5i47x0vRzuBsHuvJdi5ee6Y3G1dc=
+github.com/prometheus/common v0.55.0/go.mod h1:2SECS4xJG1kd8XF9IcM1gMX6510RAEL65zxzNImwdc8=
+github.com/prometheus/procfs v0.15.1 h1:YagwOFzUgYfKKHX6Dr+sHT7km/hxC76UB0learggepc=
+github.com/prometheus/procfs v0.15.1/go.mod h1:fB45yRUv8NstnjriLhBQLuOUt+WW4BsoGhij/e3PBqk=
+github.com/rogpeppe/go-internal v1.10.0 h1:TMyTOH3F/DB16zRVcYyreMH6GnZZrwQVAoYjRBZyWFQ=
+github.com/rogpeppe/go-internal v1.10.0/go.mod h1:UQnix2H7Ngw/k4C5ijL5+65zddjncjaFoBhdsK/akog=
+github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 h1:lZUw3E0/J3roVtGQ+SCrUrg3ON6NgVqpn3+iol9aGu4=
+github.com/santhosh-tekuri/jsonschema/v5 v5.3.1/go.mod h1:uToXkOrWAZ6/Oc07xWQrPOhJotwFIyu2bBVN41fcDUY=
+github.com/shopspring/decimal v1.3.1 h1:2Usl1nmF/WZucqkFZhnfFYxxxu8LG21F6nPQBE5gKV8=
+github.com/shopspring/decimal v1.3.1/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
+github.com/spkg/bom v0.0.0-20160624110644-59b7046e48ad/go.mod h1:qLr4V1qq6nMqFKkMo8ZTx3f+BZEkzsRUY10Xsm2mwU0=
+github.com/stmcginnis/gofish v0.15.0 h1:8TG41+lvJk/0Nf8CIIYErxbMlQUy80W0JFRZP3Ld82A=
+github.com/stmcginnis/gofish v0.15.0/go.mod h1:BLDSFTp8pDlf/xDbLZa+F7f7eW0E/CHCboggsu8CznI=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
+github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
-github.com/stretchr/testify v1.4.0/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/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=
-golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
-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/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
-golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
-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 v0.0.0-20211112202133-69e39bad7dc2/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
-golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sys v0.0.0-20190130150945-aca44879d564/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
-golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20190813064441-fde4db37ae7a/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200116001909-b77594299b42/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200223170610-d5e6a3e2c0ae/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200826173525-f9321e4c35a6/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220111092808-5a964db01320/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220114195835-da31bd327af9 h1:XfKQ4OlFl8okEOr5UvAqFRVj8pY/4yfcXrddB8qAbU0=
-golang.org/x/sys v0.0.0-20220114195835-da31bd327af9/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
-golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
-golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
-golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.3.5/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/time v0.0.0-20201208040808-7e3f01d25324/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.0.0-20210220033141-f8bda1e9f3ba/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/time v0.0.0-20211116232009-f0f3c7e86c11 h1:GZokNIeuVkl3aZHJchRrr13WCsols02MLUcz1U9is6M=
-golang.org/x/time v0.0.0-20211116232009-f0f3c7e86c11/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
-golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
-golang.org/x/tools v0.0.0-20191125144606-a911d9008d1f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
-golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
+github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
+github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
+github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
+github.com/tklauser/go-sysconf v0.3.13 h1:GBUpcahXSpR2xN01jhkNAbTLRk2Yzgggk8IM08lq3r4=
+github.com/tklauser/go-sysconf v0.3.13/go.mod h1:zwleP4Q4OehZHGn4CYZDipCgg9usW5IJePewFCGVEa0=
+github.com/tklauser/numcpus v0.7.0 h1:yjuerZP127QG9m5Zh/mSO4wqurYil27tHrqwRoRjpr4=
+github.com/tklauser/numcpus v0.7.0/go.mod h1:bb6dMVcj8A42tSE7i32fsIUCbQNllK5iDguyOZRUzAY=
+golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1 h1:P7S/GeHBAFEZIYp0ePPs2kHXoazz8q2KsyxHyQVGCJg=
+golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1/go.mod h1:9CWpnTUmlQkfdpdutA1nNf4iE5lAVt3QZOu0Z6hahBE=
+golang.org/x/crypto v0.31.0 h1:ihbySMvVjLAeSH1IbfcRTkD/iNscyz8rGzjF/E5hV6U=
+golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
+golang.org/x/crypto v0.35.0 h1:b15kiHdrGCHrP6LvwaQ3c03kgNhhiMgvlhxHQhmg2Xs=
+golang.org/x/crypto v0.35.0/go.mod h1:dy7dXNW32cAb/6/PRuTNsix8T+vJAqvuIy5Bli/x0YQ=
+golang.org/x/exp v0.0.0-20250215185904-eff6e970281f h1:oFMYAjX0867ZD2jcNiLBrI9BdpmEkvPyi5YrBGXbamg=
+golang.org/x/exp v0.0.0-20250215185904-eff6e970281f/go.mod h1:BHOTPb3L19zxehTsLoJXVaTktb06DFgmdW6Wb9s8jqk=
+golang.org/x/net v0.31.0 h1:68CPQngjLL0r2AlUKiSxtQFKvzRVbnzLwMUn5SzcLHo=
+golang.org/x/net v0.31.0/go.mod h1:P4fl1q7dY2hnZFxEk4pPSkDHF+QqjitcnDjUQyMM+pM=
+golang.org/x/net v0.36.0 h1:vWF2fRbw4qslQsQzgFqZff+BItCvGFQqKzKIzx1rmoA=
+golang.org/x/net v0.36.0/go.mod h1:bFmbeoIPfrw4sMHNhb4J9f6+tPziuGjq7Jk/38fxi1I=
+golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.28.0 h1:Fksou7UEQUWlKvIdsqzJmUmCX3cZuD2+P3XyyzwMhlA=
+golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.30.0 h1:QjkSwP/36a20jFYWkSue1YwXzLmsV5Gfq7Eiy72C1uc=
+golang.org/x/sys v0.30.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-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 v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
-google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
-google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
-google.golang.org/protobuf v1.27.1 h1:SnqbnDw1V7RiZcXPx5MEeqPv2s79L9i7BJUlG/+RurQ=
-google.golang.org/protobuf v1.27.1/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
-gopkg.in/Knetic/govaluate.v2 v2.3.0 h1:naJVc9CZlWA8rC8f5mvECJD7jreTrn7FvGXjBthkHJQ=
-gopkg.in/Knetic/govaluate.v2 v2.3.0/go.mod h1:NW0gr10J8s7aNghEg6uhdxiEaBvc0+8VgJjVViHUKp4=
+google.golang.org/protobuf v1.35.2 h1:8Ar7bF+apOIoThw1EdZl0p1oWvMqTHmpA2fRTyZO8io=
+google.golang.org/protobuf v1.35.2/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
 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/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
-gopkg.in/yaml.v2 v2.3.0 h1:clyUAQHOM3G0M3f5vQj7LuJrETvjVot3Z5el9nffUtU=
-gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.0-20200615113413-eeeca48fe776/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
+gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

internal/ccLogger/cclogger.go

@@ -1,113 +0,0 @@
-package cclogger
-
-import (
-	"fmt"
-	"log"
-	"os"
-	"runtime"
-)
-
-var (
-	globalDebug             = false
-	stdout                  = os.Stdout
-	stderr                  = os.Stderr
-	debugLog    *log.Logger = nil
-	infoLog     *log.Logger = nil
-	errorLog    *log.Logger = nil
-	warnLog     *log.Logger = nil
-	defaultLog  *log.Logger = nil
-)
-
-func initLogger() {
-	if debugLog == nil {
-		debugLog = log.New(stderr, "DEBUG ", log.LstdFlags)
-	}
-	if infoLog == nil {
-		infoLog = log.New(stdout, "INFO ", log.LstdFlags)
-	}
-	if errorLog == nil {
-		errorLog = log.New(stderr, "ERROR ", log.LstdFlags)
-	}
-	if warnLog == nil {
-		warnLog = log.New(stderr, "WARN ", log.LstdFlags)
-	}
-	if defaultLog == nil {
-		defaultLog = log.New(stdout, "", log.LstdFlags)
-	}
-}
-
-func Print(e ...interface{}) {
-	initLogger()
-	defaultLog.Print(e...)
-}
-
-func ComponentPrint(component string, e ...interface{}) {
-	initLogger()
-	defaultLog.Print(fmt.Sprintf("[%s] ", component), e)
-}
-
-func Info(e ...interface{}) {
-	initLogger()
-	infoLog.Print(e...)
-}
-
-func ComponentInfo(component string, e ...interface{}) {
-	initLogger()
-	infoLog.Print(fmt.Sprintf("[%s] ", component), e)
-}
-
-func Debug(e ...interface{}) {
-	initLogger()
-	if globalDebug {
-		debugLog.Print(e...)
-	}
-}
-
-func ComponentDebug(component string, e ...interface{}) {
-	initLogger()
-	if globalDebug && debugLog != nil {
-		//CCComponentPrint(debugLog, component,  e)
-		debugLog.Print(fmt.Sprintf("[%s] ", component), e)
-	}
-}
-
-func Error(e ...interface{}) {
-	initLogger()
-	_, fn, line, _ := runtime.Caller(1)
-	errorLog.Print(fmt.Sprintf("[%s:%d] ", fn, line), e)
-}
-
-func ComponentError(component string, e ...interface{}) {
-	initLogger()
-	_, fn, line, _ := runtime.Caller(1)
-	errorLog.Print(fmt.Sprintf("[%s|%s:%d] ", component, fn, line), e)
-}
-
-func SetDebug() {
-	globalDebug = true
-	initLogger()
-}
-
-func SetOutput(filename string) {
-	if filename == "stderr" {
-		if stderr != os.Stderr && stderr != os.Stdout {
-			stderr.Close()
-		}
-		stderr = os.Stderr
-	} else if filename == "stdout" {
-		if stderr != os.Stderr && stderr != os.Stdout {
-			stderr.Close()
-		}
-		stderr = os.Stdout
-	} else {
-		file, err := os.OpenFile(filename, os.O_APPEND|os.O_CREATE|os.O_WRONLY, 0600)
-		if err == nil {
-			defer file.Close()
-			stderr = file
-		}
-	}
-	debugLog = nil
-	errorLog = nil
-	warnLog = nil
-	initLogger()
-}

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/ccMetric/ccMetric.go

@@ -1,364 +0,0 @@
-package ccmetric
-
-import (
-	"fmt"
-	"time"
-
-	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
-	write "github.com/influxdata/influxdb-client-go/v2/api/write"
-	lp "github.com/influxdata/line-protocol" // MIT license
-)
-
-// Most functions are derived from github.com/influxdata/line-protocol/metric.go
-// The metric type is extended with an extra meta information list re-using the Tag
-// type.
-//
-// See: https://docs.influxdata.com/influxdb/latest/reference/syntax/line-protocol/
-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
-}
-
-// ccMetric access functions
-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
-
-	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
-}
-
-// String implements the stringer interface for data type ccMetric
-func (m *ccMetric) String() string {
-	return fmt.Sprintf(
-		"Name: %s, Tags: %+v, Meta: %+v, fields: %+v, Timestamp: %d",
-		m.name, m.tags, m.meta, m.fields, m.tm.UnixNano(),
-	)
-}
-
-// ToLineProtocol generates influxDB line protocol for data type ccMetric
-func (m *ccMetric) ToPoint(metaAsTags map[string]bool) (p *write.Point) {
-	p = influxdb2.NewPoint(m.name, m.tags, m.fields, m.tm)
-	for key, ok1 := range metaAsTags {
-		if val, ok2 := m.GetMeta(key); ok1 && ok2 {
-			p.AddTag(key, val)
-		}
-	}
-	return p
-}
-
-// ToLineProtocol generates influxDB line protocol for data type ccMetric
-func (m *ccMetric) ToLineProtocol(metaAsTags map[string]bool) string {
-
-	return write.PointToLineProtocol(
-		m.ToPoint(metaAsTags),
-		time.Nanosecond,
-	)
-}
-
-// Name returns the measurement name
-func (m *ccMetric) Name() string {
-	return m.name
-}
-
-// SetName sets the measurement name
-func (m *ccMetric) SetName(name string) {
-	m.name = name
-}
-
-// Time returns timestamp
-func (m *ccMetric) Time() time.Time {
-	return m.tm
-}
-
-// SetTime sets the timestamp
-func (m *ccMetric) SetTime(t time.Time) {
-	m.tm = t
-}
-
-// Tags returns the the list of tags as key-value-mapping
-func (m *ccMetric) Tags() map[string]string {
-	return m.tags
-}
-
-// AddTag adds a tag (consisting of key and value) to the map of tags
-func (m *ccMetric) AddTag(key, value string) {
-	m.tags[key] = value
-}
-
-// GetTag returns the tag with tag's key equal to <key>
-func (m *ccMetric) GetTag(key string) (string, bool) {
-	value, ok := m.tags[key]
-	return value, ok
-}
-
-// HasTag checks if a tag with key equal to <key> is present in the list of tags
-func (m *ccMetric) HasTag(key string) bool {
-	_, ok := m.tags[key]
-	return ok
-}
-
-// RemoveTag removes the tag with tag's key equal to <key>
-func (m *ccMetric) RemoveTag(key string) {
-	delete(m.tags, key)
-}
-
-// Meta returns the meta data tags as key-value mapping
-func (m *ccMetric) Meta() map[string]string {
-	return m.meta
-}
-
-// AddMeta adds a meta data tag (consisting of key and value) to the map of meta data tags
-func (m *ccMetric) AddMeta(key, value string) {
-	m.meta[key] = value
-}
-
-// GetMeta returns the meta data tag with meta data's key equal to <key>
-func (m *ccMetric) GetMeta(key string) (string, bool) {
-	value, ok := m.meta[key]
-	return value, ok
-}
-
-// HasMeta checks if a meta data tag with meta data's key equal to <key> is present in the map of meta data tags
-func (m *ccMetric) HasMeta(key string) bool {
-	_, ok := m.meta[key]
-	return ok
-}
-
-// RemoveMeta removes the meta data tag with tag's key equal to <key>
-func (m *ccMetric) RemoveMeta(key string) {
-	delete(m.meta, key)
-}
-
-// Fields returns the list of fields as key-value-mapping
-func (m *ccMetric) Fields() map[string]interface{} {
-	return m.fields
-}
-
-// AddField adds a field (consisting of key and value) to the map of fields
-func (m *ccMetric) AddField(key string, value interface{}) {
-	m.fields[key] = value
-}
-
-// GetField returns the field with field's key equal to <key>
-func (m *ccMetric) GetField(key string) (interface{}, bool) {
-	v, ok := m.fields[key]
-	return v, ok
-}
-
-// HasField checks if a field with field's key equal to <key> is present in the map of fields
-func (m *ccMetric) HasField(key string) bool {
-	_, ok := m.fields[key]
-	return ok
-}
-
-// RemoveField removes the field with field's key equal to <key>
-// from the map of fields
-func (m *ccMetric) RemoveField(key string) {
-	delete(m.fields, key)
-}
-
-// New creates a new measurement point
-func New(
-	name string,
-	tags map[string]string,
-	meta map[string]string,
-	fields map[string]interface{},
-	tm time.Time,
-) (CCMetric, error) {
-	m := &ccMetric{
-		name:   name,
-		tags:   make(map[string]string, len(tags)),
-		meta:   make(map[string]string, len(meta)),
-		fields: make(map[string]interface{}, len(fields)),
-		tm:     tm,
-	}
-
-	// deep copy tags, meta data tags and fields
-	for k, v := range tags {
-		m.tags[k] = v
-	}
-	for k, v := range meta {
-		m.meta[k] = v
-	}
-	for k, v := range fields {
-		v := convertField(v)
-		if v == nil {
-			continue
-		}
-		m.fields[k] = v
-	}
-
-	return m, nil
-}
-
-// FromMetric copies the metric <other>
-func FromMetric(other ccMetric) CCMetric {
-	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)),
-		tm:     other.Time(),
-	}
-
-	// deep copy tags, meta data tags and fields
-	for key, value := range other.tags {
-		m.tags[key] = value
-	}
-	for key, value := range other.meta {
-		m.meta[key] = value
-	}
-	for key, value := range other.fields {
-		m.fields[key] = value
-	}
-	return m
-}
-
-// FromInfluxMetric copies the influxDB line protocol metric <other>
-func FromInfluxMetric(other lp.Metric) CCMetric {
-	m := &ccMetric{
-		name:   other.Name(),
-		tags:   make(map[string]string),
-		meta:   make(map[string]string),
-		fields: make(map[string]interface{}),
-		tm:     other.Time(),
-	}
-
-	// deep copy tags and fields
-	for _, otherTag := range other.TagList() {
-		m.tags[otherTag.Key] = otherTag.Value
-	}
-	for _, otherField := range other.FieldList() {
-		m.fields[otherField.Key] = otherField.Value
-	}
-	return m
-}
-
-// convertField converts data types of fields by the following schemata:
-//                         *float32, *float64,                      float32, float64 -> float64
-//  *int,  *int8,  *int16,   *int32,   *int64,  int,  int8,  int16,   int32,   int64 ->   int64
-// *uint, *uint8, *uint16,  *uint32,  *uint64, uint, uint8, uint16,  uint32,  uint64 ->  uint64
-// *[]byte, *string,                           []byte, string                        -> string
-// *bool,                                      bool                                  -> bool
-func convertField(v interface{}) interface{} {
-	switch v := v.(type) {
-	case float64:
-		return v
-	case int64:
-		return v
-	case string:
-		return v
-	case bool:
-		return v
-	case int:
-		return int64(v)
-	case uint:
-		return uint64(v)
-	case uint64:
-		return uint64(v)
-	case []byte:
-		return string(v)
-	case int32:
-		return int64(v)
-	case int16:
-		return int64(v)
-	case int8:
-		return int64(v)
-	case uint32:
-		return uint64(v)
-	case uint16:
-		return uint64(v)
-	case uint8:
-		return uint64(v)
-	case float32:
-		return float64(v)
-	case *float64:
-		if v != nil {
-			return *v
-		}
-	case *int64:
-		if v != nil {
-			return *v
-		}
-	case *string:
-		if v != nil {
-			return *v
-		}
-	case *bool:
-		if v != nil {
-			return *v
-		}
-	case *int:
-		if v != nil {
-			return int64(*v)
-		}
-	case *uint:
-		if v != nil {
-			return uint64(*v)
-		}
-	case *uint64:
-		if v != nil {
-			return uint64(*v)
-		}
-	case *[]byte:
-		if v != nil {
-			return string(*v)
-		}
-	case *int32:
-		if v != nil {
-			return int64(*v)
-		}
-	case *int16:
-		if v != nil {
-			return int64(*v)
-		}
-	case *int8:
-		if v != nil {
-			return int64(*v)
-		}
-	case *uint32:
-		if v != nil {
-			return uint64(*v)
-		}
-	case *uint16:
-		if v != nil {
-			return uint64(*v)
-		}
-	case *uint8:
-		if v != nil {
-			return uint64(*v)
-		}
-	case *float32:
-		if v != nil {
-			return float64(*v)
-		}
-	default:
-		return nil
-	}
-	return nil
-}

internal/ccTopology/ccTopology.go

@@ -1,469 +0,0 @@
-package ccTopology
-
-import (
-	"fmt"
-	"io/ioutil"
-	"log"
-	"os"
-	"path/filepath"
-	"regexp"
-	"strconv"
-	"strings"
-
-	cclogger "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-)
-
-const SYSFS_NUMABASE = `/sys/devices/system/node`
-const SYSFS_CPUBASE = `/sys/devices/system/cpu`
-const PROCFS_CPUINFO = `/proc/cpuinfo`
-
-// intArrayContains scans an array of ints if the value str is present in the array
-// If the specified value is found, the corresponding array index is returned.
-// The bool value is used to signal success or failure
-func intArrayContains(array []int, str int) (int, bool) {
-	for i, a := range array {
-		if a == str {
-			return i, true
-		}
-	}
-	return -1, false
-}
-
-// Used internally for sysfs file reads
-func fileToInt(path string) int {
-	buffer, err := ioutil.ReadFile(path)
-	if err != nil {
-		log.Print(err)
-		cclogger.ComponentError("ccTopology", "Reading", path, ":", err.Error())
-		return -1
-	}
-	sbuffer := strings.Replace(string(buffer), "\n", "", -1)
-	var id int64
-	//_, err = fmt.Scanf("%d", sbuffer, &id)
-	id, err = strconv.ParseInt(sbuffer, 10, 32)
-	if err != nil {
-		cclogger.ComponentError("ccTopology", "Parsing", path, ":", sbuffer, err.Error())
-		return -1
-	}
-	return int(id)
-}
-
-// Get list of CPU socket IDs
-func SocketList() []int {
-	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
-	if err != nil {
-		log.Print(err)
-		return nil
-	}
-	ll := strings.Split(string(buffer), "\n")
-	packs := make([]int, 0)
-	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
-}
-
-// 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)
-		return nil
-	}
-	ll := strings.Split(string(buffer), "\n")
-	cpulist := make([]int, 0)
-	for _, line := range ll {
-		if strings.HasPrefix(line, "processor") {
-			lv := strings.Fields(line)
-			id, err := strconv.ParseInt(lv[2], 10, 32)
-			if err != nil {
-				log.Print(err)
-				return cpulist
-			}
-			_, found := intArrayContains(cpulist, int(id))
-			if !found {
-				cpulist = append(cpulist, int(id))
-			}
-		}
-	}
-	return cpulist
-}
-
-// 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 {
-		log.Print(err)
-		return nil
-	}
-	ll := strings.Split(string(buffer), "\n")
-	corelist := make([]int, 0)
-	for _, line := range ll {
-		if strings.HasPrefix(line, "core id") {
-			lv := strings.Fields(line)
-			id, err := strconv.ParseInt(lv[3], 10, 32)
-			if err != nil {
-				log.Print(err)
-				return corelist
-			}
-			_, found := intArrayContains(corelist, int(id))
-			if !found {
-				corelist = append(corelist, int(id))
-			}
-		}
-	}
-	return corelist
-}
-
-// Get list of NUMA node IDs
-func NumaNodeList() []int {
-	numaList := make([]int, 0)
-	globPath := filepath.Join(string(SYSFS_NUMABASE), "node*")
-	regexPath := filepath.Join(string(SYSFS_NUMABASE), "node(\\d+)")
-	regex := regexp.MustCompile(regexPath)
-	files, err := filepath.Glob(globPath)
-	if err != nil {
-		cclogger.ComponentError("CCTopology", "NumaNodeList", err.Error())
-	}
-	for _, f := range files {
-		if !regex.MatchString(f) {
-			continue
-		}
-		finfo, err := os.Lstat(f)
-		if err != nil {
-			continue
-		}
-		if !finfo.IsDir() {
-			continue
-		}
-		matches := regex.FindStringSubmatch(f)
-		if len(matches) == 2 {
-			id, err := strconv.Atoi(matches[1])
-			if err == nil {
-				if _, found := intArrayContains(numaList, id); !found {
-					numaList = append(numaList, id)
-				}
-			}
-		}
-
-	}
-	return numaList
-}
-
-// Get list of CPU die IDs
-func DieList() []int {
-	cpulist := HwthreadList()
-	dielist := make([]int, 0)
-	for _, c := range cpulist {
-		diepath := filepath.Join(string(SYSFS_CPUBASE), fmt.Sprintf("cpu%d", c), "topology/die_id")
-		dieid := fileToInt(diepath)
-		if dieid > 0 {
-			_, found := intArrayContains(dielist, int(dieid))
-			if !found {
-				dielist = append(dielist, int(dieid))
-			}
-		}
-	}
-	if len(dielist) > 0 {
-		return dielist
-	}
-	return SocketList()
-}
-
-// 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
-	Socket     int
-	Numadomain int
-	Die        int
-}
-
-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)
-	// }
-	getCore := func(basepath string) int {
-		return fileToInt(fmt.Sprintf("%s/core_id", basepath))
-	}
-
-	getSocket := func(basepath string) int {
-		return fileToInt(fmt.Sprintf("%s/physical_package_id", basepath))
-	}
-
-	getDie := func(basepath string) int {
-		return fileToInt(fmt.Sprintf("%s/die_id", basepath))
-	}
-
-	getSMT := func(cpuid int, basepath string) int {
-		buffer, err := ioutil.ReadFile(fmt.Sprintf("%s/thread_siblings_list", basepath))
-		if err != nil {
-			cclogger.ComponentError("CCTopology", "CpuData:getSMT", err.Error())
-		}
-		threadlist := make([]int, 0)
-		sbuffer := strings.Replace(string(buffer), "\n", "", -1)
-		for _, x := range strings.Split(sbuffer, ",") {
-			id, err := strconv.ParseInt(x, 10, 32)
-			if err != nil {
-				cclogger.ComponentError("CCTopology", "CpuData:getSMT", err.Error())
-			}
-			threadlist = append(threadlist, int(id))
-		}
-		for i, x := range threadlist {
-			if x == cpuid {
-				return i
-			}
-		}
-		return 1
-	}
-
-	getNumaDomain := func(basepath string) int {
-		globPath := filepath.Join(basepath, "node*")
-		regexPath := filepath.Join(basepath, "node(\\d+)")
-		regex := regexp.MustCompile(regexPath)
-		files, err := filepath.Glob(globPath)
-		if err != nil {
-			cclogger.ComponentError("CCTopology", "CpuData:getNumaDomain", err.Error())
-		}
-		for _, f := range files {
-			finfo, err := os.Lstat(f)
-			if err == nil && finfo.IsDir() {
-				matches := regex.FindStringSubmatch(f)
-				if len(matches) == 2 {
-					id, err := strconv.Atoi(matches[1])
-					if err == nil {
-						return id
-					}
-				}
-			}
-		}
-		return 0
-	}
-
-	clist := make([]HwthreadEntry, 0)
-	for _, c := range HwthreadList() {
-		clist = append(clist, HwthreadEntry{Cpuid: c})
-	}
-	for i, centry := range clist {
-		centry.Socket = -1
-		centry.Numadomain = -1
-		centry.Die = -1
-		centry.Core = -1
-		// Set base directory for topology lookup
-		cpustr := fmt.Sprintf("cpu%d", centry.Cpuid)
-		base := filepath.Join("/sys/devices/system/cpu", cpustr)
-		topoBase := filepath.Join(base, "topology")
-
-		// Lookup CPU core id
-		centry.Core = getCore(topoBase)
-
-		// Lookup CPU socket id
-		centry.Socket = getSocket(topoBase)
-
-		// Lookup CPU die id
-		centry.Die = getDie(topoBase)
-		if centry.Die < 0 {
-			centry.Die = centry.Socket
-		}
-
-		// Lookup SMT thread id
-		centry.SMT = getSMT(centry.Cpuid, topoBase)
-
-		// Lookup NUMA domain id
-		centry.Numadomain = getNumaDomain(base)
-
-		// Update values in output list
-		clist[i] = centry
-	}
-	return clist
-}
-
-// Structure holding basic information about a CPU
-type CpuInformation struct {
-	NumHWthreads   int
-	SMTWidth       int
-	NumSockets     int
-	NumDies        int
-	NumCores       int
-	NumNumaDomains int
-}
-
-// Get basic information about the CPU
-func CpuInfo() CpuInformation {
-	var c CpuInformation
-
-	smtList := make([]int, 0)
-	numaList := make([]int, 0)
-	dieList := make([]int, 0)
-	socketList := make([]int, 0)
-	coreList := make([]int, 0)
-	cdata := CpuData()
-	for _, d := range cdata {
-		if _, ok := intArrayContains(smtList, d.SMT); !ok {
-			smtList = append(smtList, d.SMT)
-		}
-		if _, ok := intArrayContains(numaList, d.Numadomain); !ok {
-			numaList = append(numaList, d.Numadomain)
-		}
-		if _, ok := intArrayContains(dieList, d.Die); !ok {
-			dieList = append(dieList, d.Die)
-		}
-		if _, ok := intArrayContains(socketList, d.Socket); !ok {
-			socketList = append(socketList, d.Socket)
-		}
-		if _, ok := intArrayContains(coreList, d.Core); !ok {
-			coreList = append(coreList, d.Core)
-		}
-	}
-	c.NumNumaDomains = len(numaList)
-	c.SMTWidth = len(smtList)
-	c.NumDies = len(dieList)
-	c.NumCores = len(coreList)
-	c.NumSockets = len(socketList)
-	c.NumHWthreads = len(cdata)
-	return c
-}
-
-// 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 {
-			return d.Socket
-		}
-	}
-	return -1
-}
-
-// 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 {
-			return d.Numadomain
-		}
-	}
-	return -1
-}
-
-// 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 {
-			return d.Die
-		}
-	}
-	return -1
-}
-
-// 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 {
-			return d.Core
-		}
-	}
-	return -1
-}
-
-// 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 {
-		if d.Socket == socket {
-			cpulist = append(cpulist, d.Cpuid)
-		}
-	}
-	return cpulist
-}
-
-// 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 {
-		if d.Numadomain == domain {
-			cpulist = append(cpulist, d.Cpuid)
-		}
-	}
-	return cpulist
-}
-
-// 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 {
-		if d.Die == die {
-			cpulist = append(cpulist, d.Cpuid)
-		}
-	}
-	return cpulist
-}
-
-// 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 {
-		if d.Core == core {
-			cpulist = append(cpulist, d.Cpuid)
-		}
-	}
-	return cpulist
-}

internal/metricAggregator/README.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: Metric Aggregator
+description: Subsystem for evaluating expressions on metrics (deprecated)
+categories: [cc-metric-collector]
+tags: ['Developer']
+weight: 1
+hugo_path: docs/reference/cc-metric-collector/internal/metricaggregator/_index.md
+---
+-->
+
 # The MetricAggregator
 
 In some cases, further combination of metrics or raw values is required. For that strings like `foo + 1` with runtime dependent `foo` need to be evaluated. The MetricAggregator relies on the [`gval`](https://github.com/PaesslerAG/gval) Golang package to perform all expression evaluation. The `gval` package provides the basic arithmetic operations but the MetricAggregator defines additional ones.
@@ -35,4 +46,4 @@ The MetricAggregator provides these functions additional to the `Full` language
 ## Limitations
 
 - Since the metrics are written in JSON files which do not allow `""` without proper escaping inside of JSON strings, you have to use `''` for strings.
-- Since `\` is interpreted by JSON as escape character, it cannot be used in metrics. But it is required to write regular expressions. So instead of `/`, use `%` and the MetricAggregator replaces them after reading the JSON file.
+- Since `\` is interpreted by JSON as escape character, it cannot be used in metrics. But it is required to write regular expressions. So instead of `/`, use `%` and the MetricAggregator replaces them after reading the JSON file.

internal/metricAggregator/metricAggregator.go

@@ -1,3 +1,10 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package metricAggregator
 
 import (
@@ -9,10 +16,10 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 
 	"github.com/PaesslerAG/gval"
 )
@@ -31,14 +38,14 @@ type metricAggregator struct {
 	functions []*MetricAggregatorIntervalConfig
 	constants map[string]interface{}
 	language  gval.Language
-	output    chan lp.CCMetric
+	output    chan lp.CCMessage
 }
 
 type MetricAggregator interface {
 	AddAggregation(name, function, condition string, tags, meta map[string]string) error
 	DeleteAggregation(name string) error
-	Init(output chan lp.CCMetric) error
-	Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMetric)
+	Init(output chan lp.CCMessage) error
+	Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMessage)
 }
 
 var metricCacheLanguage = gval.NewLanguage(
@@ -74,7 +81,7 @@ var evaluables = struct {
 	mapping: make(map[string]gval.Evaluable),
 }
 
-func (c *metricAggregator) Init(output chan lp.CCMetric) error {
+func (c *metricAggregator) Init(output chan lp.CCMessage) error {
 	c.output = output
 	c.functions = make([]*MetricAggregatorIntervalConfig, 0)
 	c.constants = make(map[string]interface{})
@@ -112,7 +119,7 @@ func (c *metricAggregator) Init(output chan lp.CCMetric) error {
 	return nil
 }
 
-func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMetric) {
+func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMessage) {
 	vars := make(map[string]interface{})
 	for k, v := range c.constants {
 		vars[k] = v
@@ -121,8 +128,13 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 	vars["endtime"] = endtime
 	for _, f := range c.functions {
 		cclog.ComponentDebug("MetricCache", "COLLECT", f.Name, "COND", f.Condition)
-		values := make([]float64, 0)
-		matches := make([]lp.CCMetric, 0)
+		var valuesFloat64 []float64
+		var valuesFloat32 []float32
+		var valuesInt []int
+		var valuesInt32 []int32
+		var valuesInt64 []int64
+		var valuesBool []bool
+		matches := make([]lp.CCMessage, 0)
 		for _, m := range metrics {
 			vars["metric"] = m
 			//value, err := gval.Evaluate(f.Condition, vars, c.language)
@@ -136,17 +148,17 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 				if valid {
 					switch x := v.(type) {
 					case float64:
-						values = append(values, x)
+						valuesFloat64 = append(valuesFloat64, x)
 					case float32:
+						valuesFloat32 = append(valuesFloat32, x)
 					case int:
+						valuesInt = append(valuesInt, x)
+					case int32:
+						valuesInt32 = append(valuesInt32, x)
 					case int64:
-						values = append(values, float64(x))
+						valuesInt64 = append(valuesInt64, x)
 					case bool:
-						if x {
-							values = append(values, float64(1.0))
-						} else {
-							values = append(values, float64(0.0))
-						}
+						valuesBool = append(valuesBool, x)
 					default:
 						cclog.ComponentError("MetricCache", "COLLECT ADD VALUE", v, "FAILED")
 					}
@@ -155,17 +167,63 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 			}
 		}
 		delete(vars, "metric")
-		cclog.ComponentDebug("MetricCache", "EVALUATE", f.Name, "METRICS", len(values), "CALC", f.Function)
-		vars["values"] = values
+
+		// Check, that only values of one type were collected
+		countValueTypes := 0
+		if len(valuesFloat64) > 0 {
+			countValueTypes += 1
+		}
+		if len(valuesFloat32) > 0 {
+			countValueTypes += 1
+		}
+		if len(valuesInt) > 0 {
+			countValueTypes += 1
+		}
+		if len(valuesInt32) > 0 {
+			countValueTypes += 1
+		}
+		if len(valuesInt64) > 0 {
+			countValueTypes += 1
+		}
+		if len(valuesBool) > 0 {
+			countValueTypes += 1
+		}
+		if countValueTypes > 1 {
+			cclog.ComponentError("MetricCache", "Collected values of different types")
+		}
+
+		var len_values int
+		switch {
+		case len(valuesFloat64) > 0:
+			vars["values"] = valuesFloat64
+			len_values = len(valuesFloat64)
+		case len(valuesFloat32) > 0:
+			vars["values"] = valuesFloat32
+			len_values = len(valuesFloat32)
+		case len(valuesInt) > 0:
+			vars["values"] = valuesInt
+			len_values = len(valuesInt)
+		case len(valuesInt32) > 0:
+			vars["values"] = valuesInt32
+			len_values = len(valuesInt32)
+		case len(valuesInt64) > 0:
+			vars["values"] = valuesInt64
+			len_values = len(valuesInt64)
+		case len(valuesBool) > 0:
+			vars["values"] = valuesBool
+			len_values = len(valuesBool)
+		}
+		cclog.ComponentDebug("MetricCache", "EVALUATE", f.Name, "METRICS", len_values, "CALC", f.Function)
+
 		vars["metrics"] = matches
-		if len(values) > 0 {
+		if len_values > 0 {
 			value, err := gval.Evaluate(f.Function, vars, c.language)
 			if err != nil {
-				cclog.ComponentError("MetricCache", "EVALUATE", f.Name, "METRICS", len(values), "CALC", f.Function, ":", err.Error())
+				cclog.ComponentError("MetricCache", "EVALUATE", f.Name, "METRICS", len_values, "CALC", f.Function, ":", err.Error())
 				break
 			}
 
-			copy_tags := func(tags map[string]string, metrics []lp.CCMetric) map[string]string {
+			copy_tags := func(tags map[string]string, metrics []lp.CCMessage) map[string]string {
 				out := make(map[string]string)
 				for key, value := range tags {
 					switch value {
@@ -182,7 +240,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 				}
 				return out
 			}
-			copy_meta := func(meta map[string]string, metrics []lp.CCMetric) map[string]string {
+			copy_meta := func(meta map[string]string, metrics []lp.CCMessage) map[string]string {
 				out := make(map[string]string)
 				for key, value := range meta {
 					switch value {
@@ -202,18 +260,18 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 			tags := copy_tags(f.Tags, matches)
 			meta := copy_meta(f.Meta, matches)
 
-			var m lp.CCMetric
+			var m lp.CCMessage
 			switch t := value.(type) {
 			case float64:
-				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			case float32:
-				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			case int:
-				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			case int64:
-				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			case string:
-				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			default:
 				cclog.ComponentError("MetricCache", "Gval returned invalid type", t, "skipping metric", f.Name)
 			}
@@ -316,7 +374,7 @@ func EvalBoolCondition(condition string, params map[string]interface{}) (bool, e
 	return value, err
 }
 
-func EvalFloat64Condition(condition string, params map[string]interface{}) (float64, error) {
+func EvalFloat64Condition(condition string, params map[string]float64) (float64, error) {
 	evaluables.mutex.Lock()
 	evaluable, ok := evaluables.mapping[condition]
 	evaluables.mutex.Unlock()
@@ -338,7 +396,7 @@ func EvalFloat64Condition(condition string, params map[string]interface{}) (floa
 	return value, err
 }
 
-func NewAggregator(output chan lp.CCMetric) (MetricAggregator, error) {
+func NewAggregator(output chan lp.CCMessage) (MetricAggregator, error) {
 	a := new(metricAggregator)
 	err := a.Init(output)
 	if err != nil {

internal/metricAggregator/metricAggregatorFunctions.go

@@ -1,164 +1,176 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package metricAggregator
 
 import (
 	"errors"
 	"fmt"
-	"math"
 	"regexp"
-	"sort"
 	"strings"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
+	"golang.org/x/exp/slices"
+
+	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 )
 
 /*
  * Arithmetic functions on value arrays
  */
 
-// Sum up values
-func sumfunc(args ...interface{}) (interface{}, error) {
-	s := 0.0
-	values, ok := args[0].([]float64)
-	if ok {
-		cclog.ComponentDebug("MetricCache", "SUM FUNC START")
-		for _, x := range values {
-			s += x
-		}
-		cclog.ComponentDebug("MetricCache", "SUM FUNC END", s)
-	} else {
-		cclog.ComponentDebug("MetricCache", "SUM FUNC CAST FAILED")
+func sumAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
+	if len(values) == 0 {
+		return 0.0, errors.New("sum function requires at least one argument")
 	}
-	return s, nil
+	var sum T
+	for _, value := range values {
+		sum += value
+	}
+	return sum, nil
 }
 
-// Get the minimum value
-func minfunc(args ...interface{}) (interface{}, error) {
-	var err error = nil
-	switch values := args[0].(type) {
+// Sum up values
+func sumfunc(args interface{}) (interface{}, error) {
+
+	var err error
+	switch values := args.(type) {
 	case []float64:
-		var s float64 = math.MaxFloat64
-		for _, x := range values {
-			if x < s {
-				s = x
-			}
-		}
-		return s, nil
+		return sumAnyType(values)
 	case []float32:
-		var s float32 = math.MaxFloat32
-		for _, x := range values {
-			if x < s {
-				s = x
-			}
-		}
-		return s, nil
+		return sumAnyType(values)
 	case []int:
-		var s int = int(math.MaxInt32)
-		for _, x := range values {
-			if x < s {
-				s = x
-			}
-		}
-		return s, nil
+		return sumAnyType(values)
 	case []int64:
-		var s int64 = math.MaxInt64
-		for _, x := range values {
-			if x < s {
-				s = x
-			}
-		}
-		return s, nil
+		return sumAnyType(values)
 	case []int32:
-		var s int32 = math.MaxInt32
-		for _, x := range values {
-			if x < s {
-				s = x
-			}
-		}
-		return s, nil
+		return sumAnyType(values)
 	default:
-		err = errors.New("function 'min' only on list of values (float64, float32, int, int32, int64)")
+		err = errors.New("function 'sum' only on list of values (float64, float32, int, int32, int64)")
 	}
 
 	return 0.0, err
 }
 
-// Get the average or mean value
-func avgfunc(args ...interface{}) (interface{}, error) {
-	switch values := args[0].(type) {
-	case []float64:
-		var s float64 = 0
-		for _, x := range values {
-			s += x
-		}
-		return s / float64(len(values)), nil
-	case []float32:
-		var s float32 = 0
-		for _, x := range values {
-			s += x
-		}
-		return s / float32(len(values)), nil
-	case []int:
-		var s int = 0
-		for _, x := range values {
-			s += x
-		}
-		return s / len(values), nil
-	case []int64:
-		var s int64 = 0
-		for _, x := range values {
-			s += x
-		}
-		return s / int64(len(values)), nil
+func minAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
+	if len(values) == 0 {
+		return 0.0, errors.New("min function requires at least one argument")
 	}
-	return 0.0, nil
+	return slices.Min(values), nil
+}
+
+// Get the minimum value
+func minfunc(args interface{}) (interface{}, error) {
+	switch values := args.(type) {
+	case []float64:
+		return minAnyType(values)
+	case []float32:
+		return minAnyType(values)
+	case []int:
+		return minAnyType(values)
+	case []int64:
+		return minAnyType(values)
+	case []int32:
+		return minAnyType(values)
+	default:
+		return 0.0, errors.New("function 'min' only on list of values (float64, float32, int, int32, int64)")
+	}
+}
+
+func avgAnyType[T float64 | float32 | int | int32 | int64](values []T) (float64, error) {
+	if len(values) == 0 {
+		return 0.0, errors.New("average function requires at least one argument")
+	}
+	sum, err := sumAnyType[T](values)
+	return float64(sum) / float64(len(values)), err
+}
+
+// Get the average or mean value
+func avgfunc(args interface{}) (interface{}, error) {
+	switch values := args.(type) {
+	case []float64:
+		return avgAnyType(values)
+	case []float32:
+		return avgAnyType(values)
+	case []int:
+		return avgAnyType(values)
+	case []int64:
+		return avgAnyType(values)
+	case []int32:
+		return avgAnyType(values)
+	default:
+		return 0.0, errors.New("function 'average' only on list of values (float64, float32, int, int32, int64)")
+	}
+}
+
+func maxAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
+	if len(values) == 0 {
+		return 0.0, errors.New("max function requires at least one argument")
+	}
+	return slices.Max(values), nil
 }
 
 // Get the maximum value
-func maxfunc(args ...interface{}) (interface{}, error) {
-	s := 0.0
-	values, ok := args[0].([]float64)
-	if ok {
-		for _, x := range values {
-			if x > s {
-				s = x
-			}
-		}
+func maxfunc(args interface{}) (interface{}, error) {
+	switch values := args.(type) {
+	case []float64:
+		return maxAnyType(values)
+	case []float32:
+		return maxAnyType(values)
+	case []int:
+		return maxAnyType(values)
+	case []int64:
+		return maxAnyType(values)
+	case []int32:
+		return maxAnyType(values)
+	default:
+		return 0.0, errors.New("function 'max' only on list of values (float64, float32, int, int32, int64)")
 	}
-	return s, nil
+}
+
+func medianAnyType[T float64 | float32 | int | int32 | int64](values []T) (T, error) {
+	if len(values) == 0 {
+		return 0.0, errors.New("median function requires at least one argument")
+	}
+	slices.Sort(values)
+	var median T
+	if midPoint := len(values) % 2; midPoint == 0 {
+		median = (values[midPoint-1] + values[midPoint]) / 2
+	} else {
+		median = values[midPoint]
+	}
+	return median, nil
 }
 
 // Get the median value
-func medianfunc(args ...interface{}) (interface{}, error) {
-	switch values := args[0].(type) {
+func medianfunc(args interface{}) (interface{}, error) {
+	switch values := args.(type) {
 	case []float64:
-		sort.Float64s(values)
-		return values[len(values)/2], nil
-	// case []float32:
-	// 	sort.Float64s(values)
-	// 	return values[len(values)/2], nil
+		return medianAnyType(values)
+	case []float32:
+		return medianAnyType(values)
 	case []int:
-		sort.Ints(values)
-		return values[len(values)/2], nil
-
-		// case []int64:
-		// 	sort.Ints(values)
-		// 	return values[len(values)/2], nil
-		// case []int32:
-		// 	sort.Ints(values)
-		// 	return values[len(values)/2], nil
+		return medianAnyType(values)
+	case []int64:
+		return medianAnyType(values)
+	case []int32:
+		return medianAnyType(values)
+	default:
+		return 0.0, errors.New("function 'median' only on list of values (float64, float32, int, int32, int64)")
 	}
-	return 0.0, errors.New("function 'median()' only on lists of type float64 and int")
 }
 
 /*
  * Get number of values in list. Returns always an int
  */
 
-func lenfunc(args ...interface{}) (interface{}, error) {
+func lenfunc(args interface{}) (interface{}, error) {
 	var err error = nil
 	var length int = 0
-	switch values := args[0].(type) {
+	switch values := args.(type) {
 	case []float64:
 		length = len(values)
 	case []float32:
@@ -243,8 +255,8 @@ func matchfunc(args ...interface{}) (interface{}, error) {
  */
 
 // for a given cpuid, it returns the core id
-func getCpuCoreFunc(args ...interface{}) (interface{}, error) {
-	switch cpuid := args[0].(type) {
+func getCpuCoreFunc(args interface{}) (interface{}, error) {
+	switch cpuid := args.(type) {
 	case int:
 		return topo.GetHwthreadCore(cpuid), nil
 	}
@@ -252,8 +264,8 @@ func getCpuCoreFunc(args ...interface{}) (interface{}, error) {
 }
 
 // for a given cpuid, it returns the socket id
-func getCpuSocketFunc(args ...interface{}) (interface{}, error) {
-	switch cpuid := args[0].(type) {
+func getCpuSocketFunc(args interface{}) (interface{}, error) {
+	switch cpuid := args.(type) {
 	case int:
 		return topo.GetHwthreadSocket(cpuid), nil
 	}
@@ -261,8 +273,8 @@ func getCpuSocketFunc(args ...interface{}) (interface{}, error) {
 }
 
 // for a given cpuid, it returns the id of the NUMA node
-func getCpuNumaDomainFunc(args ...interface{}) (interface{}, error) {
-	switch cpuid := args[0].(type) {
+func getCpuNumaDomainFunc(args interface{}) (interface{}, error) {
+	switch cpuid := args.(type) {
 	case int:
 		return topo.GetHwthreadNumaDomain(cpuid), nil
 	}
@@ -270,8 +282,8 @@ func getCpuNumaDomainFunc(args ...interface{}) (interface{}, error) {
 }
 
 // for a given cpuid, it returns the id of the CPU die
-func getCpuDieFunc(args ...interface{}) (interface{}, error) {
-	switch cpuid := args[0].(type) {
+func getCpuDieFunc(args interface{}) (interface{}, error) {
+	switch cpuid := args.(type) {
 	case int:
 		return topo.GetHwthreadDie(cpuid), nil
 	}
@@ -279,13 +291,13 @@ func getCpuDieFunc(args ...interface{}) (interface{}, error) {
 }
 
 // for a given core id, it returns the list of cpuids
-func getCpuListOfCoreFunc(args ...interface{}) (interface{}, error) {
+func getCpuListOfCoreFunc(args interface{}) (interface{}, error) {
 	cpulist := make([]int, 0)
-	switch in := args[0].(type) {
+	switch in := args.(type) {
 	case int:
 		for _, c := range topo.CpuData() {
 			if c.Core == in {
-				cpulist = append(cpulist, c.Cpuid)
+				cpulist = append(cpulist, c.CpuID)
 			}
 		}
 	}
@@ -293,13 +305,13 @@ func getCpuListOfCoreFunc(args ...interface{}) (interface{}, error) {
 }
 
 // for a given socket id, it returns the list of cpuids
-func getCpuListOfSocketFunc(args ...interface{}) (interface{}, error) {
+func getCpuListOfSocketFunc(args interface{}) (interface{}, error) {
 	cpulist := make([]int, 0)
-	switch in := args[0].(type) {
+	switch in := args.(type) {
 	case int:
 		for _, c := range topo.CpuData() {
 			if c.Socket == in {
-				cpulist = append(cpulist, c.Cpuid)
+				cpulist = append(cpulist, c.CpuID)
 			}
 		}
 	}
@@ -307,13 +319,13 @@ func getCpuListOfSocketFunc(args ...interface{}) (interface{}, error) {
 }
 
 // for a given id of a NUMA domain, it returns the list of cpuids
-func getCpuListOfNumaDomainFunc(args ...interface{}) (interface{}, error) {
+func getCpuListOfNumaDomainFunc(args interface{}) (interface{}, error) {
 	cpulist := make([]int, 0)
-	switch in := args[0].(type) {
+	switch in := args.(type) {
 	case int:
 		for _, c := range topo.CpuData() {
-			if c.Numadomain == in {
-				cpulist = append(cpulist, c.Cpuid)
+			if c.NumaDomain == in {
+				cpulist = append(cpulist, c.CpuID)
 			}
 		}
 	}
@@ -321,13 +333,13 @@ func getCpuListOfNumaDomainFunc(args ...interface{}) (interface{}, error) {
 }
 
 // for a given CPU die id, it returns the list of cpuids
-func getCpuListOfDieFunc(args ...interface{}) (interface{}, error) {
+func getCpuListOfDieFunc(args interface{}) (interface{}, error) {
 	cpulist := make([]int, 0)
-	switch in := args[0].(type) {
+	switch in := args.(type) {
 	case int:
 		for _, c := range topo.CpuData() {
 			if c.Die == in {
-				cpulist = append(cpulist, c.Cpuid)
+				cpulist = append(cpulist, c.CpuID)
 			}
 		}
 	}
@@ -335,7 +347,7 @@ func getCpuListOfDieFunc(args ...interface{}) (interface{}, error) {
 }
 
 // wrapper function to get a list of all cpuids of the node
-func getCpuListOfNode(args ...interface{}) (interface{}, error) {
+func getCpuListOfNode() (interface{}, error) {
 	return topo.HwthreadList(), nil
 }
 

internal/metricRouter/README.md

@@ -1,15 +1,32 @@
+<!--
+---
+title: Message Router
+description: Routing component inside cc-metric-collector
+categories: [cc-metric-collector]
+tags: ['Developer']
+weight: 1
+hugo_path: docs/reference/cc-metric-collector/internal/metricrouter/_index.md
+---
+-->
+
 # CC Metric Router
 
-The CCMetric router sits in between the collectors and the sinks and can be used to add and remove tags to/from traversing [CCMetrics](../ccMetric/README.md).
+The CCMetric router sits in between the collectors and the sinks and can be used to add and remove tags to/from traversing [CCMessages](https://pkg.go.dev/github.com/ClusterCockpit/cc-lib/ccMessage).
+
 
 # Configuration
 
+**Note**: Use the [message processor configuration](https://github.com/ClusterCockpit/cc-lib/blob/main/messageProcessor/README.md) with option `process_messages`.
+
 ```json
 {
     "num_cache_intervals" : 1,
     "interval_timestamp" : true,
     "hostname_tag" : "hostname",
     "max_forward" : 50,
+    "process_messages": {
+      "see": "pkg/messageProcessor/README.md"
+    },
     "add_tags" : [
         {
             "key" : "cluster",
@@ -63,6 +80,8 @@ The CCMetric router sits in between the collectors and the sinks and can be used
 
 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.
 
+**Note**: Use the [message processor configuration](https://github.com/ClusterCockpit/cc-lib/blob/main/messageProcessor/README.md) (option `process_messages`) instead of `add_tags`, `delete_tags`, `drop_metrics`, `drop_metrics_if`, `rename_metrics`, `normalize_units` and `change_unit_prefix`. These options are deprecated and will be removed in future versions. Until then, they are added to the message processor.
+
 # Processing order in the router
 
 - Add the `hostname_tag` tag (if sent by collectors or cache)
@@ -96,6 +115,8 @@ Every time the router receives a metric through any of the channels, it tries to
 
 # The `rename_metrics` option
 
+__deprecated__
+
 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`
 
 ```json
@@ -107,6 +128,8 @@ In the ClusterCockpit world we specified a set of standard metrics. Since some c
 
 # Conditional manipulation of tags (`add_tags` and `del_tags`)
 
+__deprecated__
+
 Common config format:
 ```json
 {
@@ -118,6 +141,8 @@ Common config format:
 
 ## The `del_tags` option
 
+__deprecated__
+
 The collectors are free to add whatever `key=value` pair to the metric tags (although the usage of tags should be minimized). If you want to delete a tag afterwards, you can do that. When the `if` condition matches on a metric, the `key` is removed from the metric's tags.
 
 If you want to remove a tag for all metrics, use the condition wildcard `*`. The `value` field can be omitted in the `del_tags` case.
@@ -129,6 +154,8 @@ Never delete tags:
 
 ## The `add_tags` option
 
+__deprecated__
+
 In some cases, metrics should be tagged or an existing tag changed based on some condition. This can be done in the `add_tags` section. When the `if` condition evaluates to `true`, the tag `key` is added or gets changed to the new `value`.
 
 If the CCMetric name is equal to `temp_package_id_0`, it adds an additional tag `test=testing` to the metric.
@@ -170,6 +197,8 @@ In some cases, you want to drop a metric and don't get it forwarded to the sinks
 
 ## The `drop_metrics` section
 
+__deprecated__
+
 The argument is a list of metric names. No futher checks are performed, only a comparison of the metric name
 
 ```json
@@ -185,6 +214,8 @@ The example drops all metrics with the name `drop_metric_1` and `drop_metric_2`.
 
 ## The `drop_metrics_if` section
 
+__deprecated__
+
 This option takes a list of evaluable conditions and performs them one after the other on **all** metrics incoming from the collectors and the metric cache (aka `interval_aggregates`).
 
 ```json
@@ -200,15 +231,22 @@ The first line is comparable with the example in `drop_metrics`, it drops all me
 # Manipulating the metric units
 
 ## The `normalize_units` option
+
+__deprecated__
+
+
 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 [cc-units](https://github.com/ClusterCockpit/cc-lib/ccUnits) 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.
+
+__deprecated__
+
+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-lib/ccUnits). 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
 
-**Note:** `interval_aggregates` works only if `num_cache_intervals` > 0
+**Note:** `interval_aggregates` works only if `num_cache_intervals` > 0 and is **experimental**
 
 In some cases, you need to derive new metrics based on the metrics arriving during an interval. This can be done in the `interval_aggregates` section. The logic is similar to the other metric manipulation and filtering options. A cache stores all metrics that arrive during an interval. At the beginning of the *next* interval, the list of metrics is submitted to the MetricAggregator. It derives new metrics and submits them back to the MetricRouter, so they are sent in the next interval but have the timestamp of the previous interval beginning.
 
@@ -236,7 +274,7 @@ The above configuration, collects all metric values for metrics evaluating `if`
 If you are not interested in the input metrics `sub_metric_%d+` at all, you can add the same condition used here to the `drop_metrics_if` section to drop them.
 
 Use cases for `interval_aggregates`:
-- Combine multiple metrics of the a collector to a new one like the [MemstatCollector](../../collectors/memstatMetric.md) does it for `mem_used`)):
+- Combine multiple metrics of the a collector to a new one like the [MemstatCollector](../../collectors/memstatMetric.md) does it for `mem_used`:
 ```json
   {
     "name" : "mem_used",

internal/metricRouter/metricCache.go

@@ -1,14 +1,21 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package metricRouter
 
 import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 	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"
 )
 
 type metricCachePeriod struct {
@@ -16,7 +23,7 @@ type metricCachePeriod struct {
 	stopstamp   time.Time
 	numMetrics  int
 	sizeMetrics int
-	metrics     []lp.CCMetric
+	metrics     []lp.CCMessage
 }
 
 // Metric cache data structure
@@ -29,21 +36,21 @@ type metricCache struct {
 	ticker     mct.MultiChanTicker
 	tickchan   chan time.Time
 	done       chan bool
-	output     chan lp.CCMetric
+	output     chan lp.CCMessage
 	aggEngine  agg.MetricAggregator
 }
 
 type MetricCache interface {
-	Init(output chan lp.CCMetric, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error
+	Init(output chan lp.CCMessage, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error
 	Start()
-	Add(metric lp.CCMetric)
-	GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric)
+	Add(metric lp.CCMessage)
+	GetPeriod(index int) (time.Time, time.Time, []lp.CCMessage)
 	AddAggregation(name, function, condition string, tags, meta map[string]string) error
 	DeleteAggregation(name string) error
 	Close()
 }
 
-func (c *metricCache) Init(output chan lp.CCMetric, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error {
+func (c *metricCache) Init(output chan lp.CCMessage, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error {
 	var err error = nil
 	c.done = make(chan bool)
 	c.wg = wg
@@ -55,7 +62,7 @@ func (c *metricCache) Init(output chan lp.CCMetric, ticker mct.MultiChanTicker,
 		p := new(metricCachePeriod)
 		p.numMetrics = 0
 		p.sizeMetrics = 0
-		p.metrics = make([]lp.CCMetric, 0)
+		p.metrics = make([]lp.CCMessage, 0)
 		c.intervals = append(c.intervals, p)
 	}
 
@@ -124,7 +131,7 @@ func (c *metricCache) Start() {
 // Add a metric to the cache. The interval is defined by the global timer (rotate() in Start())
 // The intervals list is used as round-robin buffer and the metric list grows dynamically and
 // to avoid reallocations
-func (c *metricCache) Add(metric lp.CCMetric) {
+func (c *metricCache) Add(metric lp.CCMessage) {
 	if c.curPeriod >= 0 && c.curPeriod < c.numPeriods {
 		c.lock.Lock()
 		p := c.intervals[c.curPeriod]
@@ -153,10 +160,10 @@ func (c *metricCache) DeleteAggregation(name string) error {
 // Get all metrics of a interval. The index is the difference to the current interval, so index=0
 // is the current one, index=1 the last interval and so on. Returns and empty array if a wrong index
 // is given (negative index, index larger than configured number of total intervals, ...)
-func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric) {
+func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMessage) {
 	var start time.Time = time.Now()
 	var stop time.Time = time.Now()
-	var metrics []lp.CCMetric
+	var metrics []lp.CCMessage
 	if index >= 0 && index < c.numPeriods {
 		pindex := c.curPeriod - index
 		if pindex < 0 {
@@ -168,10 +175,10 @@ func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric)
 			metrics = c.intervals[pindex].metrics
 			//return c.intervals[pindex].startstamp, c.intervals[pindex].stopstamp, c.intervals[pindex].metrics
 		} else {
-			metrics = make([]lp.CCMetric, 0)
+			metrics = make([]lp.CCMessage, 0)
 		}
 	} else {
-		metrics = make([]lp.CCMetric, 0)
+		metrics = make([]lp.CCMessage, 0)
 	}
 	return start, stop, metrics
 }
@@ -182,7 +189,7 @@ func (c *metricCache) Close() {
 	c.done <- true
 }
 
-func NewCache(output chan lp.CCMetric, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) (MetricCache, error) {
+func NewCache(output chan lp.CCMessage, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) (MetricCache, error) {
 	c := new(metricCache)
 	err := c.Init(output, ticker, wg, numPeriods)
 	if err != nil {

internal/metricRouter/metricRouter.go

@@ -1,18 +1,26 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package metricRouter
 
 import (
 	"encoding/json"
+	"fmt"
 	"os"
 	"strings"
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	mp "github.com/ClusterCockpit/cc-lib/messageProcessor"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
-	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
-	units "github.com/ClusterCockpit/cc-units"
+	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 const ROUTER_MAX_FORWARD = 50
@@ -38,16 +46,17 @@ type metricRouterConfig struct {
 	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
+	// dropMetrics       map[string]bool                      // Internal map for O(1) lookup
+	MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
 }
 
 // Metric router data structure
 type metricRouter struct {
 	hostname    string              // Hostname used in tags
-	coll_input  chan lp.CCMetric    // Input channel from CollectorManager
-	recv_input  chan lp.CCMetric    // Input channel from ReceiveManager
-	cache_input chan lp.CCMetric    // Input channel from MetricCache
-	outputs     []chan lp.CCMetric  // List of all output channels
+	coll_input  chan lp.CCMessage   // Input channel from CollectorManager
+	recv_input  chan lp.CCMessage   // Input channel from ReceiveManager
+	cache_input chan lp.CCMessage   // Input channel from MetricCache
+	outputs     []chan lp.CCMessage // List of all output channels
 	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
@@ -56,14 +65,15 @@ type metricRouter struct {
 	cache       MetricCache         // pointer to MetricCache
 	cachewg     sync.WaitGroup      // wait group for MetricCache
 	maxForward  int                 // number of metrics to forward maximally in one iteration
+	mp          mp.MessageProcessor
 }
 
 // MetricRouter access functions
 type MetricRouter interface {
-	Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) error
-	AddCollectorInput(input chan lp.CCMetric)
-	AddReceiverInput(input chan lp.CCMetric)
-	AddOutput(output chan lp.CCMetric)
+	Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfig json.RawMessage) error
+	AddCollectorInput(input chan lp.CCMessage)
+	AddReceiverInput(input chan lp.CCMessage)
+	AddOutput(output chan lp.CCMessage)
 	Start()
 	Close()
 }
@@ -74,10 +84,10 @@ type MetricRouter interface {
 // * wait group synchronization (from variable wg)
 // * ticker (from variable ticker)
 // * configuration (read from config file in variable routerConfigFile)
-func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) error {
-	r.outputs = make([]chan lp.CCMetric, 0)
+func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfig json.RawMessage) error {
+	r.outputs = make([]chan lp.CCMessage, 0)
 	r.done = make(chan bool)
-	r.cache_input = make(chan lp.CCMetric)
+	r.cache_input = make(chan lp.CCMessage)
 	r.wg = wg
 	r.ticker = ticker
 	r.config.MaxForward = ROUTER_MAX_FORWARD
@@ -92,15 +102,7 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 	// Drop domain part of host name
 	r.hostname = strings.SplitN(hostname, `.`, 2)[0]
 
-	// Read metric router config file
-	configFile, err := os.Open(routerConfigFile)
-	if err != nil {
-		cclog.ComponentError("MetricRouter", err.Error())
-		return err
-	}
-	defer configFile.Close()
-	jsonParser := json.NewDecoder(configFile)
-	err = jsonParser.Decode(&r.config)
+	err = json.Unmarshal(routerConfig, &r.config)
 	if err != nil {
 		cclog.ComponentError("MetricRouter", err.Error())
 		return err
@@ -119,14 +121,56 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 			r.cache.AddAggregation(agg.Name, agg.Function, agg.Condition, agg.Tags, agg.Meta)
 		}
 	}
-	r.config.dropMetrics = make(map[string]bool)
-	for _, mname := range r.config.DropMetrics {
-		r.config.dropMetrics[mname] = true
+	p, err := mp.NewMessageProcessor()
+	if err != nil {
+		return fmt.Errorf("initialization of message processor failed: %v", err.Error())
 	}
+	r.mp = p
+
+	if len(r.config.MessageProcessor) > 0 {
+		err = r.mp.FromConfigJSON(r.config.MessageProcessor)
+		if err != nil {
+			return fmt.Errorf("failed parsing JSON for message processor: %v", err.Error())
+		}
+	}
+	for _, mname := range r.config.DropMetrics {
+		r.mp.AddDropMessagesByName(mname)
+	}
+	for _, cond := range r.config.DropMetricsIf {
+		r.mp.AddDropMessagesByCondition(cond)
+	}
+	for _, data := range r.config.AddTags {
+		cond := data.Condition
+		if cond == "*" {
+			cond = "true"
+		}
+		r.mp.AddAddTagsByCondition(cond, data.Key, data.Value)
+	}
+	for _, data := range r.config.DelTags {
+		cond := data.Condition
+		if cond == "*" {
+			cond = "true"
+		}
+		r.mp.AddDeleteTagsByCondition(cond, data.Key, data.Value)
+	}
+	for oldname, newname := range r.config.RenameMetrics {
+		r.mp.AddRenameMetricByName(oldname, newname)
+	}
+	for metricName, prefix := range r.config.ChangeUnitPrefix {
+		r.mp.AddChangeUnitPrefix(fmt.Sprintf("name == '%s'", metricName), prefix)
+	}
+	r.mp.SetNormalizeUnits(r.config.NormalizeUnits)
+
+	r.mp.AddAddTagsByCondition("true", r.config.HostnameTagName, r.hostname)
+
+	// r.config.dropMetrics = make(map[string]bool)
+	// for _, mname := range r.config.DropMetrics {
+	// 	r.config.dropMetrics[mname] = true
+	// }
 	return nil
 }
 
-func getParamMap(point lp.CCMetric) map[string]interface{} {
+func getParamMap(point lp.CCMessage) map[string]interface{} {
 	params := make(map[string]interface{})
 	params["metric"] = point
 	params["name"] = point.Name()
@@ -144,7 +188,7 @@ func getParamMap(point lp.CCMetric) map[string]interface{} {
 }
 
 // DoAddTags adds a tag when condition is fullfiled
-func (r *metricRouter) DoAddTags(point lp.CCMetric) {
+func (r *metricRouter) DoAddTags(point lp.CCMessage) {
 	var conditionMatches bool
 	for _, m := range r.config.AddTags {
 		if m.Condition == "*" {
@@ -166,81 +210,81 @@ func (r *metricRouter) DoAddTags(point lp.CCMetric) {
 }
 
 // DoDelTags removes a tag when condition is fullfiled
-func (r *metricRouter) DoDelTags(point lp.CCMetric) {
-	var conditionMatches bool
-	for _, m := range r.config.DelTags {
-		if m.Condition == "*" {
-			// Condition is always matched
-			conditionMatches = true
-		} else {
-			// Evaluate condition
-			var err error
-			conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point))
-			if err != nil {
-				cclog.ComponentError("MetricRouter", err.Error())
-				conditionMatches = false
-			}
-		}
-		if conditionMatches {
-			point.RemoveTag(m.Key)
-		}
-	}
-}
+// func (r *metricRouter) DoDelTags(point lp.CCMessage) {
+// 	var conditionMatches bool
+// 	for _, m := range r.config.DelTags {
+// 		if m.Condition == "*" {
+// 			// Condition is always matched
+// 			conditionMatches = true
+// 		} else {
+// 			// Evaluate condition
+// 			var err error
+// 			conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point))
+// 			if err != nil {
+// 				cclog.ComponentError("MetricRouter", err.Error())
+// 				conditionMatches = false
+// 			}
+// 		}
+// 		if conditionMatches {
+// 			point.RemoveTag(m.Key)
+// 		}
+// 	}
+// }
 
 // Conditional test whether a metric should be dropped
-func (r *metricRouter) dropMetric(point lp.CCMetric) bool {
-	// Simple drop check
-	if conditionMatches, ok := r.config.dropMetrics[point.Name()]; ok {
-		return conditionMatches
-	}
+// func (r *metricRouter) dropMetric(point lp.CCMessage) bool {
+// 	// Simple drop check
+// 	if conditionMatches, ok := r.config.dropMetrics[point.Name()]; ok {
+// 		return conditionMatches
+// 	}
 
-	// Checking the dropping conditions
-	for _, m := range r.config.DropMetricsIf {
-		conditionMatches, err := agg.EvalBoolCondition(m, getParamMap(point))
-		if err != nil {
-			cclog.ComponentError("MetricRouter", err.Error())
-			conditionMatches = false
-		}
-		if conditionMatches {
-			return conditionMatches
-		}
-	}
+// 	// Checking the dropping conditions
+// 	for _, m := range r.config.DropMetricsIf {
+// 		conditionMatches, err := agg.EvalBoolCondition(m, getParamMap(point))
+// 		if err != nil {
+// 			cclog.ComponentError("MetricRouter", err.Error())
+// 			conditionMatches = false
+// 		}
+// 		if conditionMatches {
+// 			return conditionMatches
+// 		}
+// 	}
 
-	// No dropping condition met
-	return false
-}
+// 	// No dropping condition met
+// 	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 {
+// func (r *metricRouter) prepareUnit(point lp.CCMessage) 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)
+// 		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())
-					}
-				}
-			}
+// 		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
-}
+// 	return true
+// }
 
 // Start starts the metric router
 func (r *metricRouter) Start() {
@@ -259,59 +303,75 @@ func (r *metricRouter) Start() {
 
 	// Forward takes a received metric, adds or deletes tags
 	// and forwards it to the output channels
-	forward := func(point lp.CCMetric) {
-		cclog.ComponentDebug("MetricRouter", "FORWARD", point)
-		r.DoAddTags(point)
-		r.DoDelTags(point)
-		name := point.Name()
-		if new, ok := r.config.RenameMetrics[name]; ok {
-			point.SetName(new)
-			point.AddMeta("oldname", name)
-			r.DoAddTags(point)
-			r.DoDelTags(point)
-		}
+	// forward := func(point lp.CCMessage) {
+	// 	cclog.ComponentDebug("MetricRouter", "FORWARD", point)
+	// 	r.DoAddTags(point)
+	// 	r.DoDelTags(point)
+	// 	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.prepareUnit(point)
+	// 	r.prepareUnit(point)
 
-		for _, o := range r.outputs {
-			o <- point
-		}
-	}
+	// 	for _, o := range r.outputs {
+	// 		o <- point
+	// 	}
+	// }
 
 	// Foward message received from collector channel
-	coll_forward := func(p lp.CCMetric) {
+	coll_forward := func(p lp.CCMessage) {
 		// receive from metric collector
-		p.AddTag(r.config.HostnameTagName, r.hostname)
+		//p.AddTag(r.config.HostnameTagName, r.hostname)
 		if r.config.IntervalStamp {
 			p.SetTime(r.timestamp)
 		}
-		if !r.dropMetric(p) {
-			forward(p)
+		m, err := r.mp.ProcessMessage(p)
+		if err == nil && m != nil {
+			for _, o := range r.outputs {
+				o <- m
+			}
 		}
+		// if !r.dropMetric(p) {
+		// 	for _, o := range r.outputs {
+		// 		o <- point
+		// 	}
+		// }
 		// even if the metric is dropped, it is stored in the cache for
 		// aggregations
 		if r.config.NumCacheIntervals > 0 {
-			r.cache.Add(p)
+			r.cache.Add(m)
 		}
 	}
 
 	// Forward message received from receivers channel
-	recv_forward := func(p lp.CCMetric) {
+	recv_forward := func(p lp.CCMessage) {
 		// receive from receive manager
 		if r.config.IntervalStamp {
 			p.SetTime(r.timestamp)
 		}
-		if !r.dropMetric(p) {
-			forward(p)
+		m, err := r.mp.ProcessMessage(p)
+		if err == nil && m != nil {
+			for _, o := range r.outputs {
+				o <- m
+			}
 		}
+		// if !r.dropMetric(p) {
+		// 	forward(p)
+		// }
 	}
 
 	// Forward message received from cache channel
-	cache_forward := func(p lp.CCMetric) {
+	cache_forward := func(p lp.CCMessage) {
 		// receive from metric collector
-		if !r.dropMetric(p) {
-			p.AddTag(r.config.HostnameTagName, r.hostname)
-			forward(p)
+		m, err := r.mp.ProcessMessage(p)
+		if err == nil && m != nil {
+			for _, o := range r.outputs {
+				o <- m
+			}
 		}
 	}
 
@@ -358,17 +418,17 @@ func (r *metricRouter) Start() {
 }
 
 // AddCollectorInput adds a channel between metric collector and metric router
-func (r *metricRouter) AddCollectorInput(input chan lp.CCMetric) {
+func (r *metricRouter) AddCollectorInput(input chan lp.CCMessage) {
 	r.coll_input = input
 }
 
 // AddReceiverInput adds a channel between metric receiver and metric router
-func (r *metricRouter) AddReceiverInput(input chan lp.CCMetric) {
+func (r *metricRouter) AddReceiverInput(input chan lp.CCMessage) {
 	r.recv_input = input
 }
 
 // AddOutput adds a output channel to the metric router
-func (r *metricRouter) AddOutput(output chan lp.CCMetric) {
+func (r *metricRouter) AddOutput(output chan lp.CCMessage) {
 	r.outputs = append(r.outputs, output)
 }
 
@@ -388,9 +448,9 @@ func (r *metricRouter) Close() {
 }
 
 // New creates a new initialized metric router
-func New(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) (MetricRouter, error) {
+func New(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfig json.RawMessage) (MetricRouter, error) {
 	r := new(metricRouter)
-	err := r.Init(ticker, wg, routerConfigFile)
+	err := r.Init(ticker, wg, routerConfig)
 	if err != nil {
 		return nil, err
 	}

pkg/ccTopology/ccTopology.go

@@ -0,0 +1,470 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
+package ccTopology
+
+import (
+	"fmt"
+	"log"
+	"os"
+	"path/filepath"
+	"regexp"
+	"strconv"
+	"strings"
+
+	cclogger "github.com/ClusterCockpit/cc-lib/ccLogger"
+	"golang.org/x/exp/slices"
+)
+
+const SYSFS_CPUBASE = `/sys/devices/system/cpu`
+
+// Structure holding all information about a hardware thread
+// See https://www.kernel.org/doc/Documentation/ABI/stable/sysfs-devices-system-cpu
+type HwthreadEntry struct {
+	// for each CPUx:
+	CpuID        int   // CPU / hardware thread ID
+	SMT          int   // Simultaneous Multithreading ID
+	CoreCPUsList []int // CPUs within the same core
+	Core         int   // Socket local core ID
+	Socket       int   // Sockets (physical) ID
+	Die          int   // Die ID
+	NumaDomain   int   // NUMA Domain
+}
+
+var cache struct {
+	HwthreadList   []int // List of CPU hardware threads
+	SMTList        []int // List of symmetric hyper threading IDs
+	CoreList       []int // List of CPU core IDs
+	SocketList     []int // List of CPU sockets (physical) IDs
+	DieList        []int // List of CPU Die IDs
+	NumaDomainList []int // List of NUMA Domains
+
+	CpuData []HwthreadEntry
+}
+
+// fileToInt reads an integer value from a sysfs file
+// In case of an error -1 is returned
+func fileToInt(path string) int {
+	buffer, err := os.ReadFile(path)
+	if err != nil {
+		log.Print(err)
+		cclogger.ComponentError("ccTopology", "fileToInt", "Reading", path, ":", err.Error())
+		return -1
+	}
+	stringBuffer := strings.TrimSpace(string(buffer))
+	id, err := strconv.Atoi(stringBuffer)
+	if err != nil {
+		cclogger.ComponentError("ccTopology", "fileToInt", "Parsing", path, ":", stringBuffer, err.Error())
+		return -1
+	}
+	return id
+}
+
+// fileToList reads a list from a sysfs file
+// A list consists of value ranges separated by colon
+// A range can be a single value or a range of values given by a startValue-endValue
+// In case of an error nil is returned
+func fileToList(path string) []int {
+	// Read list
+	buffer, err := os.ReadFile(path)
+	if err != nil {
+		log.Print(err)
+		cclogger.ComponentError("ccTopology", "fileToList", "Reading", path, ":", err.Error())
+		return nil
+	}
+
+	// Create list
+	list := make([]int, 0)
+	stringBuffer := strings.TrimSpace(string(buffer))
+	for _, valueRangeString := range strings.Split(stringBuffer, ",") {
+		valueRange := strings.Split(valueRangeString, "-")
+		switch len(valueRange) {
+		case 1:
+			singleValue, err := strconv.Atoi(valueRange[0])
+			if err != nil {
+				cclogger.ComponentError("CCTopology", "fileToList", "Parsing", valueRange[0], ":", err.Error())
+				return nil
+			}
+			list = append(list, singleValue)
+		case 2:
+			startValue, err := strconv.Atoi(valueRange[0])
+			if err != nil {
+				cclogger.ComponentError("CCTopology", "fileToList", "Parsing", valueRange[0], ":", err.Error())
+				return nil
+			}
+			endValue, err := strconv.Atoi(valueRange[1])
+			if err != nil {
+				cclogger.ComponentError("CCTopology", "fileToList", "Parsing", valueRange[1], ":", err.Error())
+				return nil
+			}
+			for value := startValue; value <= endValue; value++ {
+				list = append(list, value)
+			}
+		}
+	}
+
+	return list
+}
+
+// init initializes the cache structure
+func init() {
+
+	getHWThreads :=
+		func() []int {
+			globPath := filepath.Join(SYSFS_CPUBASE, "cpu[0-9]*")
+			regexPath := filepath.Join(SYSFS_CPUBASE, "cpu([[:digit:]]+)")
+			regex := regexp.MustCompile(regexPath)
+
+			// File globbing for hardware threads
+			files, err := filepath.Glob(globPath)
+			if err != nil {
+				cclogger.ComponentError("CCTopology", "init:getHWThreads", err.Error())
+				return nil
+			}
+
+			hwThreadIDs := make([]int, len(files))
+			for i, file := range files {
+				// Extract hardware thread ID
+				matches := regex.FindStringSubmatch(file)
+				if len(matches) != 2 {
+					cclogger.ComponentError("CCTopology", "init:getHWThreads: Failed to extract hardware thread ID from ", file)
+					return nil
+				}
+
+				// Convert hardware thread ID to int
+				id, err := strconv.Atoi(matches[1])
+				if err != nil {
+					cclogger.ComponentError("CCTopology", "init:getHWThreads: Failed to convert to int hardware thread ID ", matches[1])
+					return nil
+				}
+
+				hwThreadIDs[i] = id
+			}
+
+			// Sort hardware thread IDs
+			slices.Sort(hwThreadIDs)
+			return hwThreadIDs
+		}
+
+	getNumaDomain :=
+		func(basePath string) int {
+			globPath := filepath.Join(basePath, "node*")
+			regexPath := filepath.Join(basePath, "node([[:digit:]]+)")
+			regex := regexp.MustCompile(regexPath)
+
+			// File globbing for NUMA node
+			files, err := filepath.Glob(globPath)
+			if err != nil {
+				cclogger.ComponentError("CCTopology", "init:getNumaDomain", err.Error())
+				return -1
+			}
+
+			// Check, that exactly one NUMA domain was found
+			if len(files) != 1 {
+				cclogger.ComponentError("CCTopology", "init:getNumaDomain", "Number of NUMA domains != 1: ", len(files))
+				return -1
+			}
+
+			// Extract NUMA node ID
+			matches := regex.FindStringSubmatch(files[0])
+			if len(matches) != 2 {
+				cclogger.ComponentError("CCTopology", "init:getNumaDomain", "Failed to extract NUMA node ID from: ", files[0])
+				return -1
+			}
+
+			id, err := strconv.Atoi(matches[1])
+			if err != nil {
+				cclogger.ComponentError("CCTopology", "init:getNumaDomain", "Failed to parse NUMA node ID from: ", matches[1])
+				return -1
+			}
+
+			return id
+		}
+
+	cache.HwthreadList = getHWThreads()
+	cache.CoreList = make([]int, len(cache.HwthreadList))
+	cache.SocketList = make([]int, len(cache.HwthreadList))
+	cache.DieList = make([]int, len(cache.HwthreadList))
+	cache.SMTList = make([]int, len(cache.HwthreadList))
+	cache.NumaDomainList = make([]int, len(cache.HwthreadList))
+	cache.CpuData = make([]HwthreadEntry, len(cache.HwthreadList))
+	for i, c := range cache.HwthreadList {
+		// Set cpuBase directory for topology lookup
+		cpuBase := filepath.Join(SYSFS_CPUBASE, fmt.Sprintf("cpu%d", c))
+		topoBase := filepath.Join(cpuBase, "topology")
+
+		// Lookup Core ID
+		cache.CoreList[i] = fileToInt(filepath.Join(topoBase, "core_id"))
+
+		// Lookup socket / physical package ID
+		cache.SocketList[i] = fileToInt(filepath.Join(topoBase, "physical_package_id"))
+
+		// Lookup CPU die id
+		cache.DieList[i] = fileToInt(filepath.Join(topoBase, "die_id"))
+		if cache.DieList[i] < 0 {
+			cache.DieList[i] = cache.SocketList[i]
+		}
+
+		// Lookup List of CPUs within the same core
+		coreCPUsList := fileToList(filepath.Join(topoBase, "core_cpus_list"))
+
+		// Find index of CPU ID in List of CPUs within the same core
+		// if not found return -1
+		cache.SMTList[i] = slices.Index(coreCPUsList, c)
+
+		// Lookup NUMA domain id
+		cache.NumaDomainList[i] = getNumaDomain(cpuBase)
+
+		cache.CpuData[i] =
+			HwthreadEntry{
+				CpuID:        cache.HwthreadList[i],
+				SMT:          cache.SMTList[i],
+				CoreCPUsList: coreCPUsList,
+				Socket:       cache.SocketList[i],
+				NumaDomain:   cache.NumaDomainList[i],
+				Die:          cache.DieList[i],
+				Core:         cache.CoreList[i],
+			}
+	}
+
+	slices.Sort(cache.HwthreadList)
+	cache.HwthreadList = slices.Compact(cache.HwthreadList)
+
+	slices.Sort(cache.SMTList)
+	cache.SMTList = slices.Compact(cache.SMTList)
+
+	slices.Sort(cache.CoreList)
+	cache.CoreList = slices.Compact(cache.CoreList)
+
+	slices.Sort(cache.SocketList)
+	cache.SocketList = slices.Compact(cache.SocketList)
+
+	slices.Sort(cache.DieList)
+	cache.DieList = slices.Compact(cache.DieList)
+
+	slices.Sort(cache.NumaDomainList)
+	cache.NumaDomainList = slices.Compact(cache.NumaDomainList)
+}
+
+// SocketList gets the list of CPU socket IDs
+func SocketList() []int {
+	return slices.Clone(cache.SocketList)
+}
+
+// HwthreadList gets the list of hardware thread IDs in the order of listing in /proc/cpuinfo
+func HwthreadList() []int {
+	return slices.Clone(cache.HwthreadList)
+}
+
+// Get list of hardware thread IDs in the order of listing in /proc/cpuinfo
+// Deprecated! Use HwthreadList()
+func CpuList() []int {
+	return HwthreadList()
+}
+
+// CoreList gets the list of CPU core IDs in the order of listing in /proc/cpuinfo
+func CoreList() []int {
+	return slices.Clone(cache.CoreList)
+}
+
+// Get list of NUMA node IDs
+func NumaNodeList() []int {
+	return slices.Clone(cache.NumaDomainList)
+}
+
+// DieList gets the list of CPU die IDs
+func DieList() []int {
+	if len(cache.DieList) > 0 {
+		return slices.Clone(cache.DieList)
+	}
+	return SocketList()
+}
+
+// GetTypeList gets the list of specified type using the naming format inside ClusterCockpit
+func GetTypeList(topology_type string) []int {
+	switch topology_type {
+	case "node":
+		return []int{0}
+	case "socket":
+		return SocketList()
+	case "die":
+		return DieList()
+	case "memoryDomain":
+		return NumaNodeList()
+	case "core":
+		return CoreList()
+	case "hwthread":
+		return HwthreadList()
+	}
+	return []int{}
+}
+
+func GetTypeId(hwt HwthreadEntry, topology_type string) (int, error) {
+	var err error = nil
+	switch topology_type {
+	case "node":
+		return 0, err
+	case "socket":
+		return hwt.Socket, err
+	case "die":
+		return hwt.Die, err
+	case "memoryDomain":
+		return hwt.NumaDomain, err
+	case "core":
+		return hwt.Core, err
+	case "hwthread":
+		return hwt.CpuID, err
+	}
+	return -1, fmt.Errorf("unknown topology type '%s'", topology_type)
+}
+
+// CpuData returns CPU data for each hardware thread
+func CpuData() []HwthreadEntry {
+	// return a deep copy to protect cache data
+	c := slices.Clone(cache.CpuData)
+	for i := range c {
+		c[i].CoreCPUsList = slices.Clone(cache.CpuData[i].CoreCPUsList)
+	}
+	return c
+}
+
+// Structure holding basic information about a CPU
+type CpuInformation struct {
+	NumHWthreads   int
+	SMTWidth       int
+	NumSockets     int
+	NumDies        int
+	NumCores       int
+	NumNumaDomains int
+}
+
+// CpuInformation reports basic information about the CPU
+func CpuInfo() CpuInformation {
+	return CpuInformation{
+		NumNumaDomains: len(cache.NumaDomainList),
+		SMTWidth:       len(cache.SMTList),
+		NumDies:        len(cache.DieList),
+		NumCores:       len(cache.CoreList),
+		NumSockets:     len(cache.SocketList),
+		NumHWthreads:   len(cache.HwthreadList),
+	}
+}
+
+// GetHwthreadSocket gets the CPU socket ID for a given hardware thread ID
+// In case hardware thread ID is not found -1 is returned
+func GetHwthreadSocket(cpuID int) int {
+	for i := range cache.CpuData {
+		d := &cache.CpuData[i]
+		if d.CpuID == cpuID {
+			return d.Socket
+		}
+	}
+	return -1
+}
+
+// GetHwthreadNumaDomain gets the NUMA domain ID for a given hardware thread ID
+// In case hardware thread ID is not found -1 is returned
+func GetHwthreadNumaDomain(cpuID int) int {
+	for i := range cache.CpuData {
+		d := &cache.CpuData[i]
+		if d.CpuID == cpuID {
+			return d.NumaDomain
+		}
+	}
+	return -1
+}
+
+// GetHwthreadDie gets the CPU die ID for a given hardware thread ID
+// In case hardware thread ID is not found -1 is returned
+func GetHwthreadDie(cpuID int) int {
+	for i := range cache.CpuData {
+		d := &cache.CpuData[i]
+		if d.CpuID == cpuID {
+			return d.Die
+		}
+	}
+	return -1
+}
+
+// GetHwthreadCore gets the CPU core ID for a given hardware thread ID
+// In case hardware thread ID is not found -1 is returned
+func GetHwthreadCore(cpuID int) int {
+	for i := range cache.CpuData {
+		d := &cache.CpuData[i]
+		if d.CpuID == cpuID {
+			return d.Core
+		}
+	}
+	return -1
+}
+
+// GetSocketHwthreads gets all hardware thread IDs associated with a CPU socket
+func GetSocketHwthreads(socket int) []int {
+	cpuList := make([]int, 0)
+	for i := range cache.CpuData {
+		d := &cache.CpuData[i]
+		if d.Socket == socket {
+			cpuList = append(cpuList, d.CpuID)
+		}
+	}
+	return cpuList
+}
+
+// GetNumaDomainHwthreads gets the all hardware thread IDs associated with a NUMA domain
+func GetNumaDomainHwthreads(numaDomain int) []int {
+	cpuList := make([]int, 0)
+	for i := range cache.CpuData {
+		d := &cache.CpuData[i]
+		if d.NumaDomain == numaDomain {
+			cpuList = append(cpuList, d.CpuID)
+		}
+	}
+	return cpuList
+}
+
+// GetDieHwthreads gets all hardware thread IDs associated with a CPU die
+func GetDieHwthreads(die int) []int {
+	cpuList := make([]int, 0)
+	for i := range cache.CpuData {
+		d := &cache.CpuData[i]
+		if d.Die == die {
+			cpuList = append(cpuList, d.CpuID)
+		}
+	}
+	return cpuList
+}
+
+// GetCoreHwthreads get all hardware thread IDs associated with a CPU core
+func GetCoreHwthreads(core int) []int {
+	cpuList := make([]int, 0)
+	for i := range cache.CpuData {
+		d := &cache.CpuData[i]
+		if d.Core == core {
+			cpuList = append(cpuList, d.CpuID)
+		}
+	}
+	return cpuList
+}
+
+// GetTypeList gets the list of specified type using the naming format inside ClusterCockpit
+func GetTypeHwthreads(topology_type string, id int) []int {
+	switch topology_type {
+	case "node":
+		return HwthreadList()
+	case "socket":
+		return GetSocketHwthreads(id)
+	case "die":
+		return GetDieHwthreads(id)
+	case "memoryDomain":
+		return GetNumaDomainHwthreads(id)
+	case "core":
+		return GetCoreHwthreads(id)
+	case "hwthread":
+		return []int{id}
+	}
+	return []int{}
+}

pkg/multiChanTicker/README.md

@@ -1,3 +1,14 @@
+<!--
+---
+title: Multi-channel Ticker
+description: Timer ticker that sends out the tick to multiple channels
+categories: [cc-metric-collector]
+tags: ['Developer']
+weight: 1
+hugo_path: docs/reference/cc-metric-collector/pkg/multichanticker/_index.md
+---
+-->
+
 # MultiChanTicker
 
 The idea of this ticker is to multiply the output channels. The original Golang `time.Ticker` provides only a single output channel, so the signal can only be received by a single other class. This ticker allows to add multiple channels which get all notified about the time tick.

pkg/multiChanTicker/multiChanTicker.go

@@ -1,9 +1,16 @@
+// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
+// All rights reserved. This file is part of cc-lib.
+// Use of this source code is governed by a MIT-style
+// license that can be found in the LICENSE file.
+// additional authors:
+// Holger Obermaier (NHR@KIT)
+
 package multiChanTicker
 
 import (
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
 )
 
 type multiChanTicker struct {

receivers.json

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

receivers/README.md

@@ -1,29 +0,0 @@
-# CCMetric receivers
-
-This folder contains the ReceiveManager and receiver implementations for the cc-metric-collector.
-
-# Configuration
-
-The configuration file for the receivers is a list of configurations. The `type` field in each specifies which receiver to initialize.
-
-```json
-{
-  "myreceivername" : {
-    "type": "receiver-type",
-    <receiver-specific configuration>
-  }
-}
-```
-
-This allows to specify
-
-## Available receivers
-
-- [`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`):
-
-For an example, check the [sample receiver](./sampleReceiver.go)

receivers/httpReceiver.go

@@ -1,118 +0,0 @@
-package receivers
-
-import (
-	"context"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"io/ioutil"
-	"net/http"
-	"strings"
-	"sync"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/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 := ioutil.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

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

@@ -1,40 +0,0 @@
-package receivers
-
-import (
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-)
-
-type defaultReceiverConfig struct {
-	Type string `json:"type"`
-}
-
-// Receiver configuration: Listen address, port
-type ReceiverConfig struct {
-	Addr         string `json:"address"`
-	Port         string `json:"port"`
-	Database     string `json:"database"`
-	Organization string `json:"organization,omitempty"`
-	Type         string `json:"type"`
-}
-
-type receiver struct {
-	name string
-	sink chan lp.CCMetric
-}
-
-type Receiver interface {
-	Start()
-	Close()                        // Close / finish metric receiver
-	Name() string                  // Name of the metric receiver
-	SetSink(sink chan lp.CCMetric) // Set sink channel
-}
-
-// Name returns the name of the metric receiver
-func (r *receiver) Name() string {
-	return r.name
-}
-
-// SetSink set the sink channel
-func (r *receiver) SetSink(sink chan lp.CCMetric) {
-	r.sink = sink
-}

receivers/natsReceiver.go

@@ -1,92 +0,0 @@
-package receivers
-
-import (
-	"encoding/json"
-	"errors"
-	"fmt"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	influx "github.com/influxdata/line-protocol"
-	nats "github.com/nats-io/nats.go"
-)
-
-type NatsReceiverConfig struct {
-	Type    string `json:"type"`
-	Addr    string `json:"address"`
-	Port    string `json:"port"`
-	Subject string `json:"subject"`
-}
-
-type NatsReceiver struct {
-	receiver
-	nc      *nats.Conn
-	handler *influx.MetricHandler
-	parser  *influx.Parser
-	meta    map[string]string
-	config  NatsReceiverConfig
-}
-
-var DefaultTime = func() time.Time {
-	return time.Unix(42, 0)
-}
-
-func (r *NatsReceiver) Start() {
-	cclog.ComponentDebug(r.name, "START")
-	r.nc.Subscribe(r.config.Subject, r._NatsReceive)
-}
-
-func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
-	metrics, err := r.parser.Parse(m.Data)
-	if err == nil {
-		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
-			}
-		}
-	}
-}
-
-func (r *NatsReceiver) Close() {
-	if r.nc != nil {
-		cclog.ComponentDebug(r.name, "CLOSE")
-		r.nc.Close()
-	}
-}
-
-func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
-	r := new(NatsReceiver)
-	r.name = fmt.Sprintf("NatsReceiver(%s)", name)
-	r.config.Addr = nats.DefaultURL
-	r.config.Port = "4222"
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &r.config)
-		if err != nil {
-			cclog.ComponentError(r.name, "Error reading config:", err.Error())
-			return nil, err
-		}
-	}
-	if len(r.config.Addr) == 0 ||
-		len(r.config.Port) == 0 ||
-		len(r.config.Subject) == 0 {
-		return nil, errors.New("not all configuration variables set required by NatsReceiver")
-	}
-	r.meta = map[string]string{"source": r.name}
-	uri := fmt.Sprintf("%s:%s", r.config.Addr, r.config.Port)
-	cclog.ComponentDebug(r.name, "NewNatsReceiver", uri, "Subject", r.config.Subject)
-	if nc, err := nats.Connect(uri); err == nil {
-		r.nc = nc
-	} else {
-		r.nc = nil
-		return nil, err
-	}
-	r.handler = influx.NewMetricHandler()
-	r.parser = influx.NewParser(r.handler)
-	r.parser.SetTimeFunc(DefaultTime)
-	return r, nil
-}

receivers/natsReceiver.md

@@ -1,21 +0,0 @@
-## `nats` receiver
-
-The `nats` receiver can be used receive metrics from the NATS network. The `nats` receiver subscribes to the topic `database` and listens on `address` and `port` for metrics in the InfluxDB line protocol.
-
-### Configuration structure
-
-```json
-{
-  "<name>": {
-    "type": "nats",
-    "address" : "nats-server.example.org",
-    "port" : "4222",
-    "subject" : "subject"
-  }
-}
-```
-
-- `type`: makes the receiver a `nats` receiver
-- `address`: Address of the NATS control server
-- `port`: Port of the NATS control server
-- `subject`: Subscribes to this subject and receive metrics

receivers/prometheusReceiver.go

@@ -1,122 +0,0 @@
-package receivers
-
-import (
-	"bufio"
-	"encoding/json"
-	"errors"
-	"fmt"
-	"log"
-	"net/http"
-	"strconv"
-	"strings"
-	"sync"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-)
-
-type PrometheusReceiverConfig struct {
-	defaultReceiverConfig
-	Addr     string `json:"address"`
-	Port     string `json:"port"`
-	Path     string `json:"path"`
-	Interval string `json:"interval"`
-	SSL      bool   `json:"ssl"`
-}
-
-type PrometheusReceiver struct {
-	receiver
-	meta     map[string]string
-	config   PrometheusReceiverConfig
-	interval time.Duration
-	done     chan bool
-	wg       sync.WaitGroup
-	ticker   *time.Ticker
-	uri      string
-}
-
-func (r *PrometheusReceiver) Start() {
-	cclog.ComponentDebug(r.name, "START", r.uri)
-	r.wg.Add(1)
-
-	r.ticker = time.NewTicker(r.interval)
-	go func() {
-		for {
-			select {
-			case <-r.done:
-				r.wg.Done()
-				return
-			case t := <-r.ticker.C:
-				resp, err := http.Get(r.uri)
-				if err != nil {
-					log.Fatal(err)
-				}
-				defer resp.Body.Close()
-
-				scanner := bufio.NewScanner(resp.Body)
-				for scanner.Scan() {
-					line := scanner.Text()
-					if strings.HasPrefix(line, "#") {
-						continue
-					}
-					lineSplit := strings.Fields(line)
-					// separate metric name from tags (labels in Prometheus)
-					tags := map[string]string{}
-					name := lineSplit[0]
-					if sindex := strings.Index(name, "{"); sindex >= 0 {
-						eindex := strings.Index(name, "}")
-						for _, kv := range strings.Split(name[sindex+1:eindex], ",") {
-							eq := strings.Index(kv, "=")
-							tags[kv[0:eq]] = strings.Trim(kv[eq+1:], "\"")
-						}
-						name = lineSplit[0][0:sindex]
-					}
-					value, err := strconv.ParseFloat(lineSplit[1], 64)
-					if err == nil {
-						y, err := lp.New(name, tags, r.meta, map[string]interface{}{"value": value}, t)
-						if err == nil {
-							r.sink <- y
-						}
-					}
-				}
-			}
-		}
-	}()
-}
-
-func (r *PrometheusReceiver) Close() {
-	cclog.ComponentDebug(r.name, "CLOSE")
-	r.done <- true
-	r.wg.Wait()
-}
-
-func NewPrometheusReceiver(name string, config json.RawMessage) (Receiver, error) {
-	r := new(PrometheusReceiver)
-	r.name = fmt.Sprintf("PrometheusReceiver(%s)", name)
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &r.config)
-		if err != nil {
-			cclog.ComponentError(r.name, "Error reading config:", err.Error())
-			return nil, err
-		}
-	}
-	if len(r.config.Addr) == 0 ||
-		len(r.config.Port) == 0 ||
-		len(r.config.Interval) == 0 {
-		return nil, errors.New("not all configuration variables set required by PrometheusReceiver (address and port)")
-	}
-	if len(r.config.Interval) > 0 {
-		t, err := time.ParseDuration(r.config.Interval)
-		if err == nil {
-			r.interval = t
-		}
-	}
-	r.meta = map[string]string{"source": r.name}
-	proto := "http"
-	if r.config.SSL {
-		proto = "https"
-	}
-	r.uri = fmt.Sprintf("%s://%s:%s/%s", proto, r.config.Addr, r.config.Port, r.config.Path)
-	return r, nil
-}

receivers/prometheusReceiver.md

@@ -1,27 +0,0 @@
-## `prometheus` receiver
-
-The `prometheus` receiver can be used to scrape the metrics of a single `prometheus` client. It does **not** use any official Golang library but making simple HTTP get requests and parse the response.
-
-### Configuration structure
-
-```json
-{
-  "<name>": {
-    "type": "prometheus",
-    "address" : "testpromhost",
-    "port" : "12345",
-    "path" : "/prometheus",
-    "interval": "5s",
-    "ssl" : true,
-  }
-}
-```
-
-- `type`: makes the receiver a `prometheus` receiver
-- `address`: Hostname or IP of the Prometheus agent
-- `port`: Port of Prometheus agent
-- `path`: Path to the Prometheus endpoint
-- `interval`: Scrape the Prometheus endpoint in this interval (default '5s')
-- `ssl`: Use SSL or not
-
-The receiver requests data from `http(s)://<address>:<port>/<path>`.

receivers/receiveManager.go

@@ -1,115 +0,0 @@
-package receivers
-
-import (
-	"encoding/json"
-	"os"
-	"sync"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-)
-
-var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
-	"nats":    NewNatsReceiver,
-	"redfish": NewRedfishReceiver,
-}
-
-type receiveManager struct {
-	inputs []Receiver
-	output chan lp.CCMetric
-	config []json.RawMessage
-}
-
-type ReceiveManager interface {
-	Init(wg *sync.WaitGroup, receiverConfigFile string) error
-	AddInput(name string, rawConfig json.RawMessage) error
-	AddOutput(output chan lp.CCMetric)
-	Start()
-	Close()
-}
-
-func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) error {
-	// Initialize struct fields
-	rm.inputs = make([]Receiver, 0)
-	rm.output = nil
-	rm.config = make([]json.RawMessage, 0)
-
-	configFile, err := os.Open(receiverConfigFile)
-	if err != nil {
-		cclog.ComponentError("ReceiveManager", err.Error())
-		return err
-	}
-	defer configFile.Close()
-	jsonParser := json.NewDecoder(configFile)
-	var rawConfigs map[string]json.RawMessage
-	err = jsonParser.Decode(&rawConfigs)
-	if err != nil {
-		cclog.ComponentError("ReceiveManager", err.Error())
-		return err
-	}
-	for name, raw := range rawConfigs {
-		rm.AddInput(name, raw)
-	}
-
-	return nil
-}
-
-func (rm *receiveManager) Start() {
-	cclog.ComponentDebug("ReceiveManager", "START")
-
-	for _, r := range rm.inputs {
-		cclog.ComponentDebug("ReceiveManager", "START", r.Name())
-		r.Start()
-	}
-	cclog.ComponentDebug("ReceiveManager", "STARTED")
-}
-
-func (rm *receiveManager) AddInput(name string, rawConfig json.RawMessage) error {
-	var config defaultReceiverConfig
-	err := json.Unmarshal(rawConfig, &config)
-	if err != nil {
-		cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "JSON config error:", err.Error())
-		return err
-	}
-	if _, found := AvailableReceivers[config.Type]; !found {
-		cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "unknown receiver:", err.Error())
-		return err
-	}
-	r, err := AvailableReceivers[config.Type](name, rawConfig)
-	if err != nil {
-		cclog.ComponentError("ReceiveManager", "SKIP", name, "initialization failed:", err.Error())
-		return err
-	}
-	rm.inputs = append(rm.inputs, r)
-	rm.config = append(rm.config, rawConfig)
-	cclog.ComponentDebug("ReceiveManager", "ADD RECEIVER", r.Name())
-	return nil
-}
-
-func (rm *receiveManager) AddOutput(output chan lp.CCMetric) {
-	rm.output = output
-	for _, r := range rm.inputs {
-		r.SetSink(rm.output)
-	}
-}
-
-func (rm *receiveManager) Close() {
-	cclog.ComponentDebug("ReceiveManager", "CLOSE")
-
-	// Close all receivers
-	for _, r := range rm.inputs {
-		cclog.ComponentDebug("ReceiveManager", "CLOSE", r.Name())
-		r.Close()
-	}
-
-	cclog.ComponentDebug("ReceiveManager", "DONE")
-}
-
-func New(wg *sync.WaitGroup, receiverConfigFile string) (ReceiveManager, error) {
-	r := new(receiveManager)
-	err := r.Init(wg, receiverConfigFile)
-	if err != nil {
-		return nil, err
-	}
-	return r, err
-}

receivers/redfishReceiver.go

@@ -1,324 +0,0 @@
-package receivers
-
-import (
-	"encoding/json"
-	"fmt"
-	"strconv"
-	"sync"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-
-	// See: https://pkg.go.dev/github.com/stmcginnis/gofish
-	"github.com/stmcginnis/gofish"
-)
-
-// RedfishReceiver configuration:
-type RedfishReceiver struct {
-	receiver
-	config struct {
-		Type     string `json:"type"`
-		Fanout   int    `json:"fanout,omitempty"`   // Default fanout: 64
-		Interval int    `json:"interval,omitempty"` // Default interval: 30s
-
-		// Client config for each redfish service
-		ClientConfigs []struct {
-			Hostname       *string  `json:"hostname"`
-			Username       *string  `json:"username"`
-			Password       *string  `json:"password"`
-			Endpoint       *string  `json:"endpoint"`
-			Insecure       *bool    `json:"insecure,omitempty"`
-			ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-			gofish         gofish.ClientConfig
-		} `json:"client_config"`
-	}
-
-	done chan bool      // channel to finish / stop redfish receiver
-	wg   sync.WaitGroup // wait group for redfish receiver
-}
-
-// Start starts the redfish receiver
-func (r *RedfishReceiver) Start() {
-	cclog.ComponentDebug(r.name, "START")
-
-	// readPowerMetric reads readfish power metric from the endpoint configured in conf
-	readPowerMetric := func(clientConfigIndex int) error {
-
-		clientConfig := &r.config.ClientConfigs[clientConfigIndex]
-
-		// Connect to redfish service
-		c, err := gofish.Connect(clientConfig.gofish)
-		if err != nil {
-			c := struct {
-				Username  string
-				Endpoint  string
-				BasicAuth bool
-				Insecure  bool
-			}{
-				Username:  clientConfig.gofish.Username,
-				Endpoint:  clientConfig.gofish.Endpoint,
-				BasicAuth: clientConfig.gofish.BasicAuth,
-				Insecure:  clientConfig.gofish.Insecure,
-			}
-			return fmt.Errorf("readPowerMetric: gofish.Connect(%+v) failed: %v", c, err)
-		}
-		defer c.Logout()
-
-		// Get all chassis managed by this service
-		chassis_list, err := c.Service.Chassis()
-		if err != nil {
-			return fmt.Errorf("readPowerMetric: c.Service.Chassis() failed: %v", err)
-		}
-
-		for _, chassis := range chassis_list {
-			timestamp := time.Now()
-
-			// Get power information for each chassis
-			power, err := chassis.Power()
-			if err != nil {
-				return fmt.Errorf("readPowerMetric: chassis.Power() failed: %v", err)
-			}
-			if power == nil {
-				continue
-			}
-
-			// Read min, max and average consumed watts for each power control
-			for _, pc := range power.PowerControl {
-
-				// Map of collected metrics
-				metrics := map[string]float32{
-					// PowerConsumedWatts shall represent the actual power being consumed (in
-					// Watts) by the chassis
-					"consumed_watts": pc.PowerConsumedWatts,
-					// AverageConsumedWatts shall represent the
-					// average power level that occurred averaged over the last IntervalInMin
-					// minutes.
-					"average_consumed_watts": pc.PowerMetrics.AverageConsumedWatts,
-					// MinConsumedWatts shall represent the
-					// minimum power level in watts that occurred within the last
-					// IntervalInMin minutes.
-					"min_consumed_watts": pc.PowerMetrics.MinConsumedWatts,
-					// MaxConsumedWatts shall represent the
-					// maximum power level in watts that occurred within the last
-					// IntervalInMin minutes
-					"max_consumed_watts": pc.PowerMetrics.MaxConsumedWatts,
-				}
-				intervalInMin := strconv.FormatFloat(float64(pc.PowerMetrics.IntervalInMin), 'f', -1, 32)
-
-				// Metrics to exclude
-				for _, key := range clientConfig.ExcludeMetrics {
-					delete(metrics, key)
-				}
-
-				// Set tags
-				tags := map[string]string{
-					"hostname": *clientConfig.Hostname,
-					"type":     "node",
-					// ID uniquely identifies the resource
-					"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.
-					"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.
-					"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
-	}
-
-	// doReadPowerMetric read power metrics for all configure redfish services.
-	// To compensate latencies of the Redfish services a fanout is used.
-	doReadPowerMetric := func() {
-
-		// Compute fanout to use
-		realFanout := r.config.Fanout
-		if len(r.config.ClientConfigs) < realFanout {
-			realFanout = len(r.config.ClientConfigs)
-		}
-
-		// Create wait group and input channel for workers
-		var workerWaitGroup sync.WaitGroup
-		workerInput := make(chan int, realFanout)
-
-		// Create worker go routines
-		for i := 0; i < realFanout; 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 clientConfigIndex := range workerInput {
-					err := readPowerMetric(clientConfigIndex)
-					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 <- 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 redfish receiver
-	r.wg.Add(1)
-	go func() {
-		defer r.wg.Done()
-
-		// Create ticker
-		ticker := time.NewTicker(time.Duration(r.config.Interval) * time.Second)
-		defer ticker.Stop()
-
-		for {
-			doReadPowerMetric()
-
-			select {
-			case <-ticker.C:
-				// process ticker event -> continue
-				continue
-			case <-r.done:
-				// process done event
-				return
-			}
-		}
-	}()
-
-	cclog.ComponentDebug(r.name, "STARTED")
-}
-
-// Close 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")
-}
-
-// New function to create a new instance of the 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)
-
-	// Set name
-	r.name = fmt.Sprintf("RedfishReceiver(%s)", name)
-
-	// Create done channel
-	r.done = make(chan bool)
-
-	// Set defaults in r.config
-	// Allow overwriting these defaults by reading config JSON
-	r.config.Fanout = 64
-	r.config.Interval = 30
-
-	// Read the redfish receiver specific JSON config
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &r.config)
-		if err != nil {
-			cclog.ComponentError(r.name, "Error reading config:", err.Error())
-			return nil, err
-		}
-	}
-
-	// Create gofish client config
-	for i := range r.config.ClientConfigs {
-		clientConfig := &r.config.ClientConfigs[i]
-		gofishConfig := &clientConfig.gofish
-
-		if clientConfig.Hostname == nil {
-			err := fmt.Errorf("client config number %v requires hostname", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-
-		if clientConfig.Endpoint == nil {
-			err := fmt.Errorf("client config number %v requires endpoint", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		gofishConfig.Endpoint = *clientConfig.Endpoint
-
-		if clientConfig.Username == nil {
-			err := fmt.Errorf("client config number %v requires username", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		gofishConfig.Username = *clientConfig.Username
-
-		if clientConfig.Password == nil {
-			err := fmt.Errorf("client config number %v requires password", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		gofishConfig.Password = *clientConfig.Password
-
-		gofishConfig.Insecure = true
-		if clientConfig.Insecure != nil {
-			gofishConfig.Insecure = *clientConfig.Insecure
-		}
-	}
-
-	return r, nil
-}

receivers/sampleReceiver.go

@@ -1,101 +0,0 @@
-package receivers
-
-import (
-	"encoding/json"
-	"fmt"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-)
-
-// SampleReceiver configuration: receiver type, listen address, port
-type SampleReceiverConfig struct {
-	Type string `json:"type"`
-	Addr string `json:"address"`
-	Port string `json:"port"`
-}
-
-type SampleReceiver struct {
-	receiver
-	config SampleReceiverConfig
-
-	// Storage for static information
-	meta map[string]string
-	// Use in case of own go routine
-	// done chan bool
-	// wg   sync.WaitGroup
-}
-
-// Implement functions required for Receiver interface
-// Start(), Close()
-// See: metricReceiver.go
-
-func (r *SampleReceiver) Start() {
-	cclog.ComponentDebug(r.name, "START")
-
-	// Start server process like http.ListenAndServe()
-
-	// 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() {
-	//      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
-	//          }
-	//      }
-	// }()
-}
-
-// Close receiver: close network connection, close files, close libraries, ...
-func (r *SampleReceiver) Close() {
-	cclog.ComponentDebug(r.name, "CLOSE")
-
-	// Close server like http.Shutdown()
-
-	// in case of own go routine, send the signal and wait
-	// r.done <- true
-	// r.wg.Wait()
-}
-
-// New function to create a new instance of the receiver
-// Initialize the receiver by giving it a name and reading in the config JSON
-func NewSampleReceiver(name string, config json.RawMessage) (Receiver, error) {
-	r := new(SampleReceiver)
-
-	// Set name of SampleReceiver
-	// The name should be chosen in such a way that different instances of SampleReceiver can be distinguished
-	r.name = fmt.Sprintf("SampleReceiver(%s)", name)
-
-	// Set static information
-	r.meta = map[string]string{"source": r.name}
-
-	// Set defaults in r.config
-	// Allow overwriting these defaults by reading config JSON
-
-	// Read the sample receiver specific JSON config
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &r.config)
-		if err != nil {
-			cclog.ComponentError(r.name, "Error reading config:", err.Error())
-			return nil, err
-		}
-	}
-
-	// Check that all required fields in the configuration are set
-	// Use 'if len(r.config.Option) > 0' for strings
-
-	return r, nil
-}