Add documentation of the internal structure of the LikwidCollector to its documentation

.github/ci-config.json

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

.github/workflows/Release.yml

@@ -15,7 +15,7 @@ jobs:
   #
   # Build on AlmaLinux 8 using go-toolset
   #
-  AlmaLinux8-RPM-build:
+  AlmaLinux-RPM-build:
     runs-on: ubuntu-latest
     # See: https://hub.docker.com/_/almalinux
     container: almalinux:8
@@ -41,17 +41,14 @@ jobs:
         submodules: recursive
         fetch-depth: 0
 
-    # - name: Setup Golang
-    #   uses: actions/setup-go@v5
-    #   with:
-    #     go-version: 'stable'
-    - name: Setup Golang
+    # Use dnf to install build dependencies
+    - name: Install build dependencies
       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
+          dnf --assumeyes install \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm
 
     - name: RPM build MetricCollector
       id: rpmbuild
@@ -73,101 +70,20 @@ jobs:
         NEW_SRPM=${OLD_SRPM/el8/alma8}
         mv "${OLD_RPM}" "${NEW_RPM}"
         mv "${OLD_SRPM}" "${NEW_SRPM}"
-        echo "SRPM=${NEW_SRPM}" >> $GITHUB_OUTPUT
-        echo "RPM=${NEW_RPM}" >> $GITHUB_OUTPUT
+        echo "::set-output name=SRPM::${NEW_SRPM}"
+        echo "::set-output name=RPM::${NEW_RPM}"
 
     # See: https://github.com/actions/upload-artifact
     - name: Save RPM as artifact
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
         name: cc-metric-collector RPM for AlmaLinux 8
         path: ${{ steps.rpmrename.outputs.RPM }}
-        overwrite: true
     - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       with:
         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
@@ -195,17 +111,14 @@ jobs:
         submodules: recursive
         fetch-depth: 0
 
-    # - name: Setup Golang
-    #   uses: actions/setup-go@v5
-    #   with:
-    #     go-version: 'stable'
-    - name: Setup Golang
+    # Use dnf to install build dependencies
+    - name: Install build dependencies
       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
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm
 
     - name: RPM build MetricCollector
       id: rpmbuild
@@ -215,78 +128,15 @@ jobs:
 
     # See: https://github.com/actions/upload-artifact
     - name: Save RPM as artifact
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       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@v4
+      uses: actions/upload-artifact@v2
       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
@@ -312,15 +162,17 @@ jobs:
       with:
         submodules: recursive
         fetch-depth: 0
-
-    - name: Setup Golang
-      uses: actions/setup-go@v5
-      with:
-        go-version: 'stable'
-
+    # Use official golang package
+    - name: Install Golang
+      run: |
+          wget -q https://go.dev/dl/go1.21.1.linux-amd64.tar.gz --output-document=- | \
+          tar --directory=/usr/local --extract --gzip
+          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
+          go version
     - name: DEB build MetricCollector
       id: dpkg-build
       run: |
+          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
           git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
           make DEB
     - name: Rename DEB (add '_ubuntu22.04')
@@ -329,65 +181,13 @@ jobs:
         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}" >> $GITHUB_OUTPUT
+        echo "::set-output name=DEB::${NEW_DEB_FILE}"
     # See: https://github.com/actions/upload-artifact
     - name: Save DEB as artifact
-      uses: actions/upload-artifact@v4
+      uses: actions/upload-artifact@v2
       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
@@ -395,56 +195,33 @@ jobs:
   Release:
     runs-on: ubuntu-latest
     # We need the RPMs, so add dependency
-    needs: [AlmaLinux8-RPM-build, AlmaLinux9-RPM-build, UBI-8-RPM-build, UBI-9-RPM-build, Ubuntu-jammy-build, Ubuntu-noblenumbat-build]
+    needs: [AlmaLinux-RPM-build, UBI-8-RPM-build, Ubuntu-focal-build]
 
     steps:
     # See: https://github.com/actions/download-artifact
     - name: Download AlmaLinux 8 RPM
-      uses: actions/download-artifact@v4
+      uses: actions/download-artifact@v2
       with:
         name: cc-metric-collector RPM for AlmaLinux 8
     - name: Download AlmaLinux 8 SRPM
-      uses: actions/download-artifact@v4
+      uses: actions/download-artifact@v2
       with:
         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@v4
+      uses: actions/download-artifact@v2
       with:
         name: cc-metric-collector RPM for UBI 8
     - name: Download UBI 8 SRPM
-      uses: actions/download-artifact@v4
+      uses: actions/download-artifact@v2
       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
+      uses: actions/download-artifact@v2
       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.
@@ -454,51 +231,31 @@ jobs:
     - name: Set RPM variables
       id: files
       run: |
-        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}}")
+        ALMA_8_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
+        ALMA_8_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
         UBI_8_RPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.rpm}}")
         UBI_8_SRPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.srpm}}")
-        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}}")
+        U_2004_DEB=$(basename "${{ needs.Ubuntu-focal-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 "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}" >> $GITHUB_OUTPUT
+        echo "U_2004_DEB::${U_2004_DEB}"
+        echo "::set-output name=ALMA_8_RPM::${ALMA_8_RPM}"
+        echo "::set-output name=ALMA_8_SRPM::${ALMA_8_SRPM}"
+        echo "::set-output name=UBI_8_RPM::${UBI_8_RPM}"
+        echo "::set-output name=UBI_8_SRPM::${UBI_8_SRPM}"
+        echo "::set-output name=U_2004_DEB::${U_2004_DEB}"
 
     # See: https://github.com/softprops/action-gh-release
     - name: Release
-      uses: softprops/action-gh-release@v2
+      uses: softprops/action-gh-release@v1
       if: startsWith(github.ref, 'refs/tags/')
       with:
         name: cc-metric-collector-${{github.ref_name}}
         files: |
          ${{ steps.files.outputs.ALMA_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 }}
+         ${{ steps.files.outputs.U_2004_DEB }}

.github/workflows/runonce.yml

@@ -11,10 +11,10 @@ on:
 jobs:
 
   #
-  # Job build-latest
-  # Build on latest Ubuntu using latest golang version
+  # Job build-1-21
+  # Build on latest Ubuntu using golang version 1.21
   #
-  build-latest:
+  build-1-21:
     runs-on: ubuntu-latest
     steps:
     # See: https://github.com/marketplace/actions/checkout
@@ -26,10 +26,9 @@ jobs:
 
     # See: https://github.com/marketplace/actions/setup-go-environment
     - name: Setup Golang
-      uses: actions/setup-go@v5
+      uses: actions/setup-go@v4
       with:
         go-version: '1.21'
-        check-latest: true
 
     - name: Build MetricCollector
       run: make
@@ -38,9 +37,35 @@ jobs:
       run: ./cc-metric-collector --once --config .github/ci-config.json
 
   #
-  # Build on AlmaLinux 8
+  # Job build-1-22
+  # Build on latest Ubuntu using golang version 1.22
   #
-  AlmaLinux8-RPM-build:
+  build-1-22:
+    runs-on: ubuntu-latest
+    steps:
+    # See: https://github.com/marketplace/actions/checkout
+    # Checkout git repository and submodules
+    - name: Checkout
+      uses: actions/checkout@v4
+      with:
+        submodules: recursive
+
+    # See: https://github.com/marketplace/actions/setup-go-environment
+    - name: Setup Golang
+      uses: actions/setup-go@v4
+      with:
+        go-version: '1.22'
+
+    - name: Build MetricCollector
+      run: make
+
+    - name: Run MetricCollector once
+      run: ./cc-metric-collector --once --config .github/ci-config.json
+
+  #
+  # Build on AlmaLinux 8 using go-toolset
+  #
+  AlmaLinux-RPM-build:
     runs-on: ubuntu-latest
     # See: https://hub.docker.com/_/almalinux
     container: almalinux:8
@@ -63,18 +88,14 @@ jobs:
         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
+    # Use dnf to install build dependencies
+    - name: Install build dependencies
       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
+          dnf --assumeyes install \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm
 
     - name: RPM build MetricCollector
       id: rpmbuild
@@ -82,60 +103,13 @@ jobs:
           git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
           make RPM
 
-  #
-  # Build on AlmaLinux 9
-  #
-  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:
-
-    # 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
-
-    # 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 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
+    container: registry.access.redhat.com/ubi8/ubi:8.8-1032.1692772289
     # The job outputs link to the outputs of the 'rpmbuild' step
     steps:
 
@@ -152,61 +126,14 @@ jobs:
         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
+    # Use dnf to install build dependencies
+    - name: Install build dependencies
       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: |
-          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
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-bin-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/golang-src-1.21.7-1.module_el8+960+4060efbe.noarch.rpm \
+              http://mirror.centos.org/centos/8-stream/AppStream/x86_64/os/Packages/go-toolset-1.21.7-1.module_el8+960+4060efbe.x86_64.rpm
 
     - name: RPM build MetricCollector
       id: rpmbuild
@@ -236,48 +163,15 @@ jobs:
         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:$PATH
-          make DEB
-
-  #
-  # Build on Ubuntu 24.04 using official go package
-  #
-  Ubuntu-noblenumbat-build:
-    runs-on: ubuntu-latest
-    container: ubuntu:24.04
-
-    steps:
-    # Use apt to install development packages
-    - name: Install development packages
-      run: |
-          apt update && apt --assume-yes upgrade
-          apt --assume-yes install build-essential sed git wget bash
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v4
-      with:
-        submodules: recursive
-        fetch-depth: 0
-    # Use official golang package
-    # See: https://github.com/marketplace/actions/setup-go-environment
-    - name: Setup Golang
-      uses: actions/setup-go@v5
-      with:
-        go-version: 'stable'
-
+    - name: Install Golang
+      run: |
+          wget -q https://go.dev/dl/go1.21.1.linux-amd64.tar.gz --output-document=- | \
+          tar --directory=/usr/local --extract --gzip
+          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
+          go version
     - name: DEB build MetricCollector
       id: dpkg-build
       run: |
           export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
+          git config --global --add safe.directory /__w/cc-metric-collector/cc-metric-collector
           make DEB

cc-metric-collector.go

@@ -7,24 +7,39 @@ 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"
 
-	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"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 type CentralConfigFile struct {
-	Interval string `json:"interval"`
-	Duration string `json:"duration"`
+	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
 }
 
 type RuntimeConfig struct {
@@ -39,7 +54,7 @@ type RuntimeConfig struct {
 	ReceiveManager  receivers.ReceiveManager
 	MultiChanTicker mct.MultiChanTicker
 
-	Channels []chan lp.CCMessage
+	Channels []chan lp.CCMetric
 	Sync     sync.WaitGroup
 }
 
@@ -72,7 +87,7 @@ 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")
-	loglevel := flag.String("loglevel", "info", "Set log level")
+	debug := flag.Bool("debug", false, "Activate debug output")
 	flag.Parse()
 	m = make(map[string]string)
 	m["configfile"] = *cfg
@@ -82,7 +97,12 @@ func ReadCli() map[string]string {
 	} else {
 		m["once"] = "false"
 	}
-	m["loglevel"] = *loglevel
+	if *debug {
+		m["debug"] = "true"
+		cclog.SetDebug()
+	} else {
+		m["debug"] = "false"
+	}
 	return m
 }
 
@@ -147,15 +167,8 @@ 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
-	main := ccconf.GetPackageConfig("main")
-	err = json.Unmarshal(main, &rcfg.ConfigFile)
+	err = LoadCentralConfiguration(rcfg.CliArgs["configfile"], &rcfg.ConfigFile)
 	if err != nil {
 		cclog.Error("Error reading configuration file ", rcfg.CliArgs["configfile"], ": ", err.Error())
 		return 1
@@ -191,74 +204,70 @@ func mainFunc() int {
 		return 1
 	}
 
-	routerConf := ccconf.GetPackageConfig("router")
-	if len(routerConf) == 0 {
+	if len(rcfg.ConfigFile.RouterConfigFile) == 0 {
 		cclog.Error("Metric router configuration file must be set")
 		return 1
 	}
 
-	sinkConf := ccconf.GetPackageConfig("sinks")
-	if len(sinkConf) == 0 {
+	if len(rcfg.ConfigFile.SinkConfigFile) == 0 {
 		cclog.Error("Sink configuration file must be set")
 		return 1
 	}
 
-	collectorConf := ccconf.GetPackageConfig("collectors")
-	if len(collectorConf) == 0 {
+	if len(rcfg.ConfigFile.CollectorConfigFile) == 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, routerConf)
+	rcfg.MetricRouter, err = mr.New(rcfg.MultiChanTicker, &rcfg.Sync, rcfg.ConfigFile.RouterConfigFile)
 	if err != nil {
 		cclog.Error(err.Error())
 		return 1
 	}
 
 	// Create new sink
-	rcfg.SinkManager, err = sinks.New(&rcfg.Sync, sinkConf)
+	rcfg.SinkManager, err = sinks.New(&rcfg.Sync, rcfg.ConfigFile.SinkConfigFile)
 	if err != nil {
 		cclog.Error(err.Error())
 		return 1
 	}
 
 	// Connect metric router to sink manager
-	RouterToSinksChannel := make(chan lp.CCMessage, 200)
+	RouterToSinksChannel := make(chan lp.CCMetric, 200)
 	rcfg.SinkManager.AddInput(RouterToSinksChannel)
 	rcfg.MetricRouter.AddOutput(RouterToSinksChannel)
 
 	// Create new collector manager
-	rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, &rcfg.Sync, collectorConf)
+	rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, &rcfg.Sync, rcfg.ConfigFile.CollectorConfigFile)
 	if err != nil {
 		cclog.Error(err.Error())
 		return 1
 	}
 
 	// Connect collector manager to metric router
-	CollectToRouterChannel := make(chan lp.CCMessage, 200)
+	CollectToRouterChannel := make(chan lp.CCMetric, 200)
 	rcfg.CollectManager.AddOutput(CollectToRouterChannel)
 	rcfg.MetricRouter.AddCollectorInput(CollectToRouterChannel)
 
 	// Create new receive manager
-	receiveConf := ccconf.GetPackageConfig("receivers")
-	if len(receiveConf) > 0 {
-		rcfg.ReceiveManager, err = receivers.New(&rcfg.Sync, receiveConf)
+	if len(rcfg.ConfigFile.ReceiverConfigFile) > 0 {
+		rcfg.ReceiveManager, err = receivers.New(&rcfg.Sync, rcfg.ConfigFile.ReceiverConfigFile)
 		if err != nil {
 			cclog.Error(err.Error())
 			return 1
 		}
 
 		// Connect receive manager to metric router
-		ReceiveToRouterChannel := make(chan lp.CCMessage, 200)
+		ReceiveToRouterChannel := make(chan lp.CCMetric, 200)
 		rcfg.ReceiveManager.AddOutput(ReceiveToRouterChannel)
 		rcfg.MetricRouter.AddReceiverInput(ReceiveToRouterChannel)
 		use_recv = true

collectors/Makefile

@@ -1,5 +1,5 @@
 # LIKWID version
-LIKWID_VERSION := 5.4.1
+LIKWID_VERSION := 5.2.2
 LIKWID_INSTALLED_FOLDER := $(shell dirname $$(which likwid-topology 2>/dev/null) 2>/dev/null)
 
 LIKWID_FOLDER := $(CURDIR)/likwid
@@ -23,7 +23,7 @@ likwid:
 	    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)" "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/likwid*.h
+		install -D --verbose --preserve-timestamps --mode=0644 --target-directory="$(LIKWID_FOLDER)" "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/likwid*.h "$${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes"/bstrlib.h
 	    rm --recursive "$${BUILD_FOLDER}"
 	fi
 

collectors/beegfsmetaMetric.go

@@ -14,8 +14,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
@@ -110,7 +110,7 @@ func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
@@ -216,7 +216,7 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMess
 
 			for key, data := range m.matches {
 				value, _ := strconv.ParseFloat(data, 32)
-				y, err := lp.NewMessage(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+				y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 				if err == nil {
 					output <- y
 				}

collectors/beegfsstorageMetric.go

@@ -14,8 +14,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // Struct for the collector-specific JSON config
@@ -103,7 +103,7 @@ func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
@@ -208,7 +208,7 @@ 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.NewMessage(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+				y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 				if err == nil {
 					output <- y
 				}

collectors/collectorManager.go

@@ -2,11 +2,12 @@ package collectors
 
 import (
 	"encoding/json"
+	"os"
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
@@ -46,7 +47,7 @@ var AvailableCollectors = map[string]MetricCollector{
 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.CCMessage          // Output channels
+	output       chan lp.CCMetric           // Output channels
 	done         chan bool                  // channel to finish / stop metric collector manager
 	ticker       mct.MultiChanTicker        // periodically ticking once each interval
 	duration     time.Duration              // duration (for metrics that measure over a given duration)
@@ -58,8 +59,8 @@ type collectorManager struct {
 
 // Metric collector manager access functions
 type CollectorManager interface {
-	Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) error
-	AddOutput(output chan lp.CCMessage)
+	Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error
+	AddOutput(output chan lp.CCMetric)
 	Start()
 	Close()
 }
@@ -71,7 +72,7 @@ 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, collectConfig json.RawMessage) error {
+func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error {
 	cm.collectors = make([]MetricCollector, 0)
 	cm.serial = make([]MetricCollector, 0)
 	cm.output = nil
@@ -80,7 +81,15 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
 	cm.ticker = ticker
 	cm.duration = duration
 
-	err := json.Unmarshal(collectConfig, &cm.config)
+	// 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)
 	if err != nil {
 		cclog.Error(err.Error())
 		return err
@@ -178,7 +187,7 @@ func (cm *collectorManager) Start() {
 }
 
 // AddOutput adds the output channel to the metric collector manager
-func (cm *collectorManager) AddOutput(output chan lp.CCMessage) {
+func (cm *collectorManager) AddOutput(output chan lp.CCMetric) {
 	cm.output = output
 }
 
@@ -191,9 +200,9 @@ func (cm *collectorManager) Close() {
 }
 
 // New creates a new initialized metric collector manager
-func New(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) (CollectorManager, error) {
+func New(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) (CollectorManager, error) {
 	cm := new(collectorManager)
-	err := cm.Init(ticker, duration, wg, collectConfig)
+	err := cm.Init(ticker, duration, wg, collectConfigFile)
 	if err != nil {
 		return nil, err
 	}

collectors/cpufreqCpuinfoMetric.go

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // CPUFreqCollector
@@ -112,14 +112,14 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 
 	// 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)
+		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.CCMessage) {
+func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	// Check if already initialized
 	if !m.init {
 		return
@@ -154,7 +154,7 @@ 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.NewMessage("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil {
+					if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil {
 						output <- y
 					}
 				}

collectors/cpufreqMetric.go

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 	"golang.org/x/sys/unix"
 )
@@ -91,7 +91,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	// Check if already initialized
 	if !m.init {
 		return
@@ -117,7 +117,7 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMessage
 			continue
 		}
 
-		if y, err := lp.NewMessage("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil {
+		if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil {
 			output <- y
 		}
 	}

collectors/cpustatMetric.go

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	sysconf "github.com/tklauser/go-sysconf"
 )
 
@@ -34,7 +34,7 @@ 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"}
+	m.meta = map[string]string{"source": m.name, "group": "CPU", "unit": "Percent"}
 	m.nodetags = map[string]string{"type": "node"}
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
@@ -105,7 +105,7 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMessage, now time.Time, tsdelta time.Duration) {
+func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
 	values := make(map[string]float64)
 	clktck, _ := sysconf.Sysconf(sysconf.SC_CLK_TCK)
 	for match, index := range m.matches {
@@ -122,23 +122,21 @@ func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]st
 	sum := float64(0)
 	for name, value := range values {
 		sum += value
-		y, err := lp.NewMessage(name, tags, m.meta, map[string]interface{}{"value": value * 100}, now)
+		y, err := lp.New(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)
+		y, err := lp.New("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.CCMessage) {
+func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
@@ -164,7 +162,7 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMessage
 		}
 	}
 
-	num_cpus_metric, err := lp.NewMessage("num_cpus",
+	num_cpus_metric, err := lp.New("num_cpus",
 		m.nodetags,
 		m.meta,
 		map[string]interface{}{"value": int(num_cpus)},

collectors/cpustatMetric.md

@@ -13,15 +13,14 @@ The `cpustat` collector reads data from `/proc/stat` and outputs a handful **nod
 
 Metrics:
 
-* `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`
+* `cpu_user`
+* `cpu_nice`
+* `cpu_system`
+* `cpu_idle`
+* `cpu_iowait`
+* `cpu_irq`
+* `cpu_softirq`
+* `cpu_steal`
+* `cpu_guest`
+* `cpu_guest_nice`
+* `cpu_used` = `cpu_* - cpu_idle`

collectors/customCmdMetric.go

@@ -9,7 +9,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 )
 
@@ -75,7 +75,7 @@ var DefaultTime = func() time.Time {
 	return time.Unix(42, 0)
 }
 
-func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}

collectors/diskstatMetric.go

@@ -8,21 +8,23 @@ import (
 	"syscall"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
+//	"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
-	config         DiskstatCollectorConfig
-	allowedMetrics map[string]bool
+	//matches map[string]int
+	config IOstatCollectorConfig
+	//devices map[string]IOstatCollectorEntry
 }
 
 func (m *DiskstatCollector) Init(config json.RawMessage) error {
@@ -31,21 +33,12 @@ func (m *DiskstatCollector) Init(config json.RawMessage) error {
 	m.meta = map[string]string{"source": m.name, "group": "Disk"}
 	m.setup()
 	if len(config) > 0 {
-		if err := json.Unmarshal(config, &m.config); err != nil {
+		err := json.Unmarshal(config, &m.config)
+		if err != nil {
 			return err
 		}
 	}
-	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)
+	file, err := os.Open(string(MOUNTFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return err
@@ -55,12 +48,12 @@ func (m *DiskstatCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
 
-	file, err := os.Open(MOUNTFILE)
+	file, err := os.Open(string(MOUNTFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return
@@ -69,7 +62,6 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessag
 
 	part_max_used := uint64(0)
 	scanner := bufio.NewScanner(file)
-mountLoop:
 	for scanner.Scan() {
 		line := scanner.Text()
 		if len(line) == 0 {
@@ -85,17 +77,13 @@ mountLoop:
 		if strings.Contains(linefields[1], "boot") {
 			continue
 		}
-
-		mountPath := strings.Replace(linefields[1], `\040`, " ", -1)
-
-		for _, excl := range m.config.ExcludeMounts {
-			if strings.Contains(mountPath, excl) {
-				continue mountLoop
-			}
+		path := strings.Replace(linefields[1], `\040`, " ", -1)
+		stat := syscall.Statfs_t{
+			Blocks: 0,
+			Bsize:  0,
+			Bfree:  0,
 		}
-
-		stat := syscall.Statfs_t{}
-		err := syscall.Statfs(mountPath, &stat)
+		err := syscall.Statfs(path, &stat)
 		if err != nil {
 			continue
 		}
@@ -104,20 +92,16 @@ mountLoop:
 		}
 		tags := map[string]string{"type": "node", "device": linefields[0]}
 		total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)
-		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
-			}
+		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
 		}
 		free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000000000)
-		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
-			}
+		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 total > 0 {
 			perc := (100 * (total - free)) / total
@@ -126,12 +110,10 @@ mountLoop:
 			}
 		}
 	}
-	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
-		}
+	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
 	}
 }
 

collectors/diskstatMetric.md

@@ -6,13 +6,10 @@
     "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. Additionally, any mount point containing one of the strings specified in `exclude_mounts` will be skipped during metric collection.
+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.
 
 Metrics per device (with `device` tag):
 * `disk_total` (unit `GBytes`)

collectors/gpfsMetric.go

@@ -13,8 +13,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const DEFAULT_GPFS_CMD = "mmpmon"
@@ -94,7 +94,7 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	// Check if already initialized
 	if !m.init {
 		return
@@ -218,7 +218,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			continue
 		}
 		if y, err :=
-			lp.NewMessage(
+			lp.New(
 				"gpfs_bytes_read",
 				m.tags,
 				m.meta,
@@ -234,7 +234,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			if lastBytesRead := m.lastState[filesystem].bytesRead; lastBytesRead >= 0 {
 				bwRead := float64(bytesRead-lastBytesRead) / timeDiff
 				if y, err :=
-					lp.NewMessage(
+					lp.New(
 						"gpfs_bw_read",
 						m.tags,
 						m.meta,
@@ -258,7 +258,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			continue
 		}
 		if y, err :=
-			lp.NewMessage(
+			lp.New(
 				"gpfs_bytes_written",
 				m.tags,
 				m.meta,
@@ -274,7 +274,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			if lastBytesWritten := m.lastState[filesystem].bytesRead; lastBytesWritten >= 0 {
 				bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff
 				if y, err :=
-					lp.NewMessage(
+					lp.New(
 						"gpfs_bw_write",
 						m.tags,
 						m.meta,
@@ -304,7 +304,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				fmt.Sprintf("Read(): Failed to convert number of opens '%s' to int64: %v", key_value["_oc_"], err))
 			continue
 		}
-		if y, err := lp.NewMessage("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil {
+		if y, err := lp.New("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -316,7 +316,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				fmt.Sprintf("Read(): Failed to convert number of closes: '%s' to int64: %v", key_value["_cc_"], err))
 			continue
 		}
-		if y, err := lp.NewMessage("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil {
+		if y, err := lp.New("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -328,7 +328,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				fmt.Sprintf("Read(): Failed to convert number of reads: '%s' to int64: %v", key_value["_rdc_"], err))
 			continue
 		}
-		if y, err := lp.NewMessage("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil {
+		if y, err := lp.New("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -340,7 +340,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				fmt.Sprintf("Read(): Failed to convert number of writes: '%s' to int64: %v", key_value["_wc_"], err))
 			continue
 		}
-		if y, err := lp.NewMessage("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil {
+		if y, err := lp.New("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -352,7 +352,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				fmt.Sprintf("Read(): Failed to convert number of read directories: '%s' to int64: %v", key_value["_dir_"], err))
 			continue
 		}
-		if y, err := lp.NewMessage("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil {
+		if y, err := lp.New("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -364,7 +364,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				fmt.Sprintf("Read(): Failed to convert number of inode updates: '%s' to int: %v", key_value["_iu_"], err))
 			continue
 		}
-		if y, err := lp.NewMessage("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
+		if y, err := lp.New("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
 			output <- y
 		}
 
@@ -372,7 +372,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 		if m.config.SendTotalValues {
 			bytesTotal := bytesRead + bytesWritten
 			if y, err :=
-				lp.NewMessage("gpfs_bytes_total",
+				lp.New("gpfs_bytes_total",
 					m.tags,
 					m.meta,
 					map[string]interface{}{
@@ -385,7 +385,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			}
 			iops := numReads + numWrites
 			if y, err :=
-				lp.NewMessage("gpfs_iops",
+				lp.New("gpfs_iops",
 					m.tags,
 					m.meta,
 					map[string]interface{}{
@@ -397,7 +397,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			}
 			metaops := numInodeUpdates + numCloses + numOpens + numReaddirs
 			if y, err :=
-				lp.NewMessage("gpfs_metaops",
+				lp.New("gpfs_metaops",
 					m.tags,
 					m.meta,
 					map[string]interface{}{

collectors/infinibandMetric.go

@@ -4,8 +4,8 @@ import (
 	"fmt"
 	"os"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"golang.org/x/sys/unix"
 
 	"encoding/json"
@@ -182,7 +182,7 @@ 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.CCMessage) {
+func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 	// Check if already initialized
 	if !m.init {
@@ -230,7 +230,7 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
 			// Send absolut values
 			if m.config.SendAbsoluteValues {
 				if y, err :=
-					lp.NewMessage(
+					lp.New(
 						counterDef.name,
 						info.tagSet,
 						m.meta,
@@ -248,7 +248,7 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
 				if counterDef.lastState >= 0 {
 					rate := float64((counterDef.currentState - counterDef.lastState)) / timeDiff
 					if y, err :=
-						lp.NewMessage(
+						lp.New(
 							counterDef.name+"_bw",
 							info.tagSet,
 							m.meta,
@@ -278,7 +278,7 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
 		// Send total values
 		if m.config.SendTotalValues {
 			if y, err :=
-				lp.NewMessage(
+				lp.New(
 					"ib_total",
 					info.tagSet,
 					m.meta,
@@ -291,7 +291,7 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
 			}
 
 			if y, err :=
-				lp.NewMessage(
+				lp.New(
 					"ib_total_pkts",
 					info.tagSet,
 					m.meta,

collectors/iostatMetric.go

@@ -2,24 +2,24 @@ package collectors
 
 import (
 	"bufio"
+	"os"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/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 +76,7 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
 	if len(m.matches) == 0 {
 		return errors.New("no metrics to collect")
 	}
-	file, err := os.Open(IOSTATFILE)
+	file, err := os.Open(string(IOSTATFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return err
@@ -87,24 +87,17 @@ 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": device,
+				"device": linefields[2],
 				"type":   "node",
 			},
 			lastValues: values,
@@ -114,12 +107,12 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
 	return err
 }
 
-func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
 
-	file, err := os.Open(IOSTATFILE)
+	file, err := os.Open(string(IOSTATFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return
@@ -133,16 +126,10 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
 			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
 		}
@@ -152,7 +139,7 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
 				x, err := strconv.ParseInt(linefields[idx], 0, 64)
 				if err == nil {
 					diff := x - entry.lastValues[name]
-					y, err := lp.NewMessage(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now())
+					y, err := lp.New(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now())
 					if err == nil {
 						output <- y
 					}

collectors/iostatMetric.md

@@ -4,17 +4,12 @@
 ```json
   "iostat": {
     "exclude_metrics": [
-      "io_read_ms"
+      "read_ms"
     ],
-    "exclude_devices": [
-      "nvme0n1p1",
-      "nvme0n1p2",
-      "md127"
-    ]
   }
 ```
 
-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.
+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.
 
 Metrics:
 * `io_reads`

collectors/ipmiMetric.go

@@ -12,9 +12,8 @@ import (
 	"strconv"
 	"strings"
 	"time"
-
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const IPMISENSORS_PATH = `ipmi-sensors`
@@ -55,35 +54,20 @@ func (m *IpmiCollector) Init(config json.RawMessage) error {
 	// Check if executables ipmitool or ipmisensors are found
 	p, err := exec.LookPath(m.config.IpmitoolPath)
 	if err == nil {
-		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
-		}
+		m.ipmitool = p
 	}
 	p, err = exec.LookPath(m.config.IpmisensorsPath)
 	if err == nil {
-		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
-		}
+		m.ipmisensors = p
 	}
 	if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
-		return errors.New("no usable IPMI reader found")
+		return errors.New("no IPMI reader found")
 	}
-
 	m.init = true
 	return nil
 }
 
-func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
+func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMetric) {
 
 	// Setup ipmitool command
 	command := exec.Command(cmd, "sensor")
@@ -121,7 +105,7 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
 				unit = "Watts"
 			}
 
-			y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
+			y, err := lp.New(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", unit)
 				output <- y
@@ -135,13 +119,13 @@ func (m *IpmiCollector) readIpmiTool(cmd string, output chan lp.CCMessage) {
 		cclog.ComponentError(
 			m.name,
 			fmt.Sprintf("readIpmiTool(): Failed to wait for the end of command \"%s\": %v\n", command.String(), err),
+			fmt.Sprintf("readIpmiTool(): command stderr: \"%s\"\n", string(errMsg)),
 		)
-		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.CCMessage) {
+func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMetric) {
 
 	command := exec.Command(cmd, "--comma-separated-output", "--sdr-cache-recreate")
 	command.Wait()
@@ -159,7 +143,7 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) {
 			v, err := strconv.ParseFloat(lv[3], 64)
 			if err == nil {
 				name := strings.ToLower(strings.Replace(lv[1], " ", "_", -1))
-				y, err := lp.NewMessage(name, map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": v}, time.Now())
+				y, err := lp.New(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])
@@ -171,7 +155,7 @@ func (m *IpmiCollector) readIpmiSensors(cmd string, output chan lp.CCMessage) {
 	}
 }
 
-func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *IpmiCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 	// Check if already initialized
 	if !m.init {

collectors/likwidMetric.go

@@ -24,9 +24,9 @@ import (
 	"time"
 	"unsafe"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 	"github.com/NVIDIA/go-nvml/pkg/dl"
 	"github.com/fsnotify/fsnotify"
@@ -43,7 +43,7 @@ const (
 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, hwthread, ...)
+	Type               string `json:"type"` // Metric type (aka node, socket, cpu, ...)
 	Publish            bool   `json:"publish"`
 	SendCoreTotalVal   bool   `json:"send_core_total_values,omitempty"`
 	SendSocketTotalVal bool   `json:"send_socket_total_values,omitempty"`
@@ -91,8 +91,6 @@ type LikwidCollector struct {
 	running       bool
 	initialized   bool
 	needs_reinit  bool
-	myuid         int
-	lock_err_once bool
 	likwidGroups  map[C.int]LikwidEventsetConfig
 	lock          sync.Mutex
 	measureThread thread.Thread
@@ -206,7 +204,6 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 	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
@@ -377,41 +374,27 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
 	}
 	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)
+		if _, err := os.Stat(m.config.LockfilePath); os.IsNotExist(err) {
+			file, err := os.Create(m.config.LockfilePath)
+			if err != nil {
+				cclog.ComponentError(m.name, "Cannot create lockfile", m.config.LockfilePath, ":", err.Error())
+				return true, err
 			}
 			file.Close()
-			info, err = os.Stat(m.config.LockfilePath) // Recheck the file after creation
 		}
+		info, err := os.Stat(m.config.LockfilePath)
 		if err != nil {
 			return true, err
 		}
-		// Check file ownership
 		uid := info.Sys().(*syscall.Stat_t).Uid
-		if uid != uint32(m.myuid) {
+		if uid != uint32(os.Getuid()) {
 			usr, err := user.LookupId(fmt.Sprint(uid))
 			if err == nil {
-				err = fmt.Errorf("access to performance counters locked by %s", usr.Username)
+				return true, fmt.Errorf("access to performance counters locked by %s", usr.Username)
 			} else {
-				err = fmt.Errorf("access to performance counters locked by %d", uid)
+				return true, fmt.Errorf("access to performance counters locked by %d", uid)
 			}
-			// 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())
@@ -449,7 +432,9 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
 		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)
+		return true, fmt.Errorf("failed to add events %s, error %d", evset.go_estr, gid)
+	} else {
+		evset.gid = gid
 	}
 
 	// Setup all performance monitoring counters of an eventSet
@@ -560,12 +545,11 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
 }
 
 // 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 {
+func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
 	invClock := float64(1.0 / m.basefreq)
 
 	for _, tid := range m.cpu2tid {
 		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
@@ -594,7 +578,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
 				if !math.IsNaN(value) && metric.Publish {
 					fields := map[string]interface{}{"value": value}
 					y, err :=
-						lp.NewMessage(
+						lp.New(
 							metric.Name,
 							map[string]string{
 								"type": metric.Type,
@@ -631,7 +615,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
 
 			for coreID, value := range totalCoreValues {
 				y, err :=
-					lp.NewMessage(
+					lp.New(
 						metric.Name,
 						map[string]string{
 							"type":    "core",
@@ -668,7 +652,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
 
 			for socketID, value := range totalSocketValues {
 				y, err :=
-					lp.NewMessage(
+					lp.New(
 						metric.Name,
 						map[string]string{
 							"type":    "socket",
@@ -703,7 +687,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
 			}
 
 			y, err :=
-				lp.NewMessage(
+				lp.New(
 					metric.Name,
 					map[string]string{
 						"type": "node",
@@ -728,7 +712,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
 }
 
 // Go over the global metrics, derive the value out of the event sets' metric values and send it
-func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, interval time.Duration, output chan lp.CCMessage) error {
+func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
 	// Send all metrics with same time stamp
 	// This function does only computiation, counter measurement is done before
 	now := time.Now()
@@ -749,7 +733,6 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
 						params[mname] = mres
 					}
 				}
-				params["gotime"] = interval.Seconds()
 				// Evaluate the metric
 				value, err := agg.EvalFloat64Condition(metric.Calc, params)
 				if err != nil {
@@ -763,7 +746,7 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
 				if !math.IsNaN(value) {
 					if metric.Publish {
 						y, err :=
-							lp.NewMessage(
+							lp.New(
 								metric.Name,
 								map[string]string{
 									"type": metric.Type,
@@ -791,7 +774,7 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
 	return nil
 }
 
-func (m *LikwidCollector) ReadThread(interval time.Duration, output chan lp.CCMessage) {
+func (m *LikwidCollector) ReadThread(interval time.Duration, output chan lp.CCMetric) {
 	var err error = nil
 	groups := make([]LikwidEventsetConfig, 0)
 
@@ -811,17 +794,15 @@ func (m *LikwidCollector) ReadThread(interval time.Duration, output chan lp.CCMe
 		if !skip {
 			// read measurements and derive event set metrics
 			m.calcEventsetMetrics(e, interval, output)
-			groups = append(groups, e)
 		}
+		groups = append(groups, e)
 	}
-	if len(groups) > 0 {
-		// calculate global metrics
-		m.calcGlobalMetrics(groups, interval, output)
-	}
+	// calculate global metrics
+	m.calcGlobalMetrics(groups, interval, output)
 }
 
 // main read function taking multiple measurement rounds, each 'interval' seconds long
-func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}

collectors/likwidMetric.md

@@ -15,7 +15,7 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
       {
         "events" : {
           "COUNTER0": "EVENT0",
-          "COUNTER1": "EVENT1"
+          "COUNTER1": "EVENT1",
         },
         "metrics" : [
           {
@@ -27,7 +27,7 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
           }
         ]
       }
-    ],
+    ]
     "globalmetrics" : [
       {
         "name": "global_sum",
@@ -132,9 +132,6 @@ In some cases LIKWID returns `0.0` for some events that are further used in proc
 
 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.
@@ -270,3 +267,45 @@ IPC   PMC0/PMC1                  ->     {
 ```
 
 The script `scripts/likwid_perfgroup_to_cc_config.py` might help you.
+
+### Internal structure
+
+This section describes the internal structure of the `likwid` collector. 
+
+#### At initialization
+
+After setting the defaults, the configuration is read.
+
+Based on the configuration, the library is searched using `dlopen` to see whether it makes sense to proceed.
+
+Next, the user-given metrics are tested to ensure they can be evaluated. For this, it creates a list of all user-given events/counters with the value `1.0` which is provided to the metric evaluator. The same is done for the global metrics by using the metric names with value `1.0`. If the evaluator does not fail, the metric can be evaluated and the collector initialization can proceed.
+
+A separate thread is started to do the measurement. This is not done using a common goroutine but a real application thread with full control. This is required because LIKWID's access system tracks the processes of the using application and the PID should not change between measurements because that would require teardown and reopening of the access system.
+
+With the separate thread, the access system is initialized by setting the user-given access mode and adding all hardware threads.
+
+LIKWID measures per hardware thread in general but only some HW threads read the counters available only e.g. per CPU socket (often memory traffic). For this, the collector gets the system topology through LIKWID and creates different mappings like 'hwthread to list offset' and others. With this, the hardware threads responsible for a topological entity can be determined because those read the counters of the per CPU socket units. These mappings are later used in the measurement phase.
+
+In the end, we read the base CPU frequency of the system. It may be used in the metric evaluation.
+
+#### Measurements
+
+The reading of events is done by the separate application thread.
+
+It traverses over all configured event sets, creates valid LIKWID eventstrings out of them and pass them to take a measurement. This could be done only once but when the LIKWID lock changes, LIKWID has to be completely reopened to provide access again. With this reopening, the already added event sets are gone.
+
+LIKWID has it's own locking mechanism using a lock file. But not the content of the file is of interest but the owner. In order to track changes of the file, a `fsnotify` watcher is installed on the file. If the file does not exist, it is created and consequently is owned by the same user as `cc-metric-collector`. The LikwidCollector has to watch the file on it's own because LIKWID does not provide proper error handling for this.
+
+Each call to the LIKWID library for loading the event set, setting up the counting facilities as well as starting and stopping of the counters is wrapped into lockfile checks to ensure no state change happens. If the file owner changed, the LikwidCollector cannot access the counters anymore, so no further operation can be done and measurment stops.
+
+Although start/stop would be sufficient, the LikwidCollector performs start, read, wait, read, `getLastResult`, stop. Reason might be "historic" but is not 100% clear anymore. The author failed to document ;)
+
+#### Metric evaluation
+
+After each meaurement, the metrics of the event set are directly evaluated. It updates the counter->result mapping with the new measurements, calls the evaluator and generates the `CCMetric` with the user-given settings if it should be published. Each metric name to result calculation is stored for the global metric evaluation, which is done as a final step.
+
+#### Shutdown
+
+Since each measurment involves a complete initialize to finalize cycle of the LIKWID library, only the topology module needs to be closed.
+
+Moreover, the separate application thread is stopped.

collectors/loadavgMetric.go

@@ -8,16 +8,18 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
+//
 // 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 {
@@ -66,15 +68,17 @@ func (m *LoadavgCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
 	buffer, err := os.ReadFile(LOADAVGFILE)
 	if err != nil {
-		cclog.ComponentError(
-			m.name,
-			fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err))
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err))
+		}
 		return
 	}
 	now := time.Now()
@@ -92,7 +96,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage
 		if m.load_skips[i] {
 			continue
 		}
-		y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
+		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
 		if err == nil {
 			output <- y
 		}
@@ -111,7 +115,7 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage
 		if m.proc_skips[i] {
 			continue
 		}
-		y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
+		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
 		if err == nil {
 			output <- y
 		}

collectors/lustreMetric.go

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const LUSTRE_SYSFS = `/sys/fs/lustre`
@@ -377,7 +377,7 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
@@ -388,7 +388,7 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMessage)
 		for _, def := range m.definitions {
 			var use_x int64
 			var err error
-			var y lp.CCMessage
+			var y lp.CCMetric
 			x, err := getMetricData(data, def.lineprefix, def.lineoffset)
 			if err == nil {
 				use_x = x
@@ -399,19 +399,19 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMessage)
 			switch def.calc {
 			case "none":
 				value = use_x
-				y, err = lp.NewMessage(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			case "difference":
 				value = use_x - devData[def.name]
 				if value.(int64) < 0 {
 					value = 0
 				}
-				y, err = lp.NewMessage(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			case "derivative":
 				value = float64(use_x-devData[def.name]) / tdiff.Seconds()
 				if value.(float64) < 0 {
 					value = 0
 				}
-				y, err = lp.NewMessage(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			}
 			if err == nil {
 				y.AddTag("device", device)

collectors/memstatMetric.go

@@ -12,8 +12,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const MEMSTATFILE = "/proc/meminfo"
@@ -159,7 +159,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 	return err
 }
 
-func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
@@ -175,7 +175,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMessage
 				}
 			}
 
-			y, err := lp.NewMessage(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+			y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			if err == nil {
 				if len(unit) > 0 {
 					y.AddMeta("unit", unit)
@@ -208,7 +208,7 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMessage
 					}
 				}
 			}
-			y, err := lp.NewMessage("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
+			y, err := lp.New("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
 			if err == nil {
 				if len(unit) > 0 {
 					y.AddMeta("unit", unit)

collectors/metricCollector.go

@@ -5,7 +5,7 @@ import (
 	"fmt"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 type MetricCollector interface {
@@ -13,8 +13,8 @@ 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.CCMessage) // Read metrics from metric collector
-	Close()                                                // Close / finish metric collector
+	Read(duration time.Duration, output chan lp.CCMetric) // Read metrics from metric collector
+	Close()                                               // Close / finish metric collector
 }
 
 type metricCollector struct {

collectors/netstatMetric.go

@@ -9,17 +9,16 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 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"`
-	InterfaceAliases   map[string][]string `json:"interface_aliases,omitempty"`
+	IncludeDevices     []string `json:"include_devices"`
+	SendAbsoluteValues bool     `json:"send_abs_values"`
+	SendDerivedValues  bool     `json:"send_derived_values"`
 }
 
 type NetstatCollectorMetric struct {
@@ -33,26 +32,9 @@ type NetstatCollectorMetric struct {
 
 type NetstatCollector struct {
 	metricCollector
-	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
+	config        NetstatCollectorConfig
+	matches       map[string][]NetstatCollectorMetric
+	lastTimestamp time.Time
 }
 
 func (m *NetstatCollector) Init(config json.RawMessage) error {
@@ -95,8 +77,6 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 		}
 	}
 
-	m.buildAliasMapping()
-
 	// Check access to net statistic file
 	file, err := os.Open(NETSTATFILE)
 	if err != nil {
@@ -117,20 +97,18 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 		// Split line into fields
 		f := strings.Fields(l)
 
-		// Get raw and canonical names
-		raw := strings.Trim(f[0], ": ")
-		canonical := getCanonicalName(raw, m.aliasToCanonical)
+		// Get net device entry
+		dev := strings.Trim(f[0], ": ")
 
 		// Check if device is a included device
-		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"}
+		if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
+			tags := map[string]string{"stype": "network", "stype-id": dev, "type": "node"}
 			meta_unit_byte := map[string]string{"source": m.name, "group": "Network", "unit": "bytes"}
 			meta_unit_byte_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "bytes/sec"}
 			meta_unit_pkts := map[string]string{"source": m.name, "group": "Network", "unit": "packets"}
 			meta_unit_pkts_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "packets/sec"}
 
-			m.matches[canonical] = []NetstatCollectorMetric{
+			m.matches[dev] = []NetstatCollectorMetric{
 				{
 					name:       "net_bytes_in",
 					index:      fieldReceiveBytes,
@@ -165,6 +143,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 				},
 			}
 		}
+
 	}
 
 	if len(m.matches) == 0 {
@@ -174,7 +153,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
@@ -185,7 +164,7 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
 	// Save current timestamp
 	m.lastTimestamp = now
 
-	file, err := os.Open(NETSTATFILE)
+	file, err := os.Open(string(NETSTATFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return
@@ -204,12 +183,11 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
 		// Split line into fields
 		f := strings.Fields(l)
 
-		// Get raw and canonical names
-		raw := strings.Trim(f[0], ":")
-		canonical := getCanonicalName(raw, m.aliasToCanonical)
+		// Get net device entry
+		dev := strings.Trim(f[0], ":")
 
 		// Check if device is a included device
-		if devmetrics, ok := m.matches[canonical]; ok {
+		if devmetrics, ok := m.matches[dev]; ok {
 			for i := range devmetrics {
 				metric := &devmetrics[i]
 
@@ -219,14 +197,14 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
 					continue
 				}
 				if m.config.SendAbsoluteValues {
-					if y, err := lp.NewMessage(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
+					if y, err := lp.New(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.NewMessage(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]interface{}{"value": rate}, now); err == nil {
+						if y, err := lp.New(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]interface{}{"value": rate}, now); err == nil {
 							output <- y
 						}
 					}

collectors/netstatMetric.md

@@ -4,19 +4,14 @@
 ```json
   "netstat": {
     "include_devices": [
-      "eth0",
-      "eno1"
+      "eth0"
     ],
-    "send_abs_values": true,
-    "send_derived_values": true,
-    "interface_aliases": {
-      "eno1": ["eno1np0", "eno1_alt"],
-      "eth0": ["eth0_alias"]
-    }
+    "send_abs_values" : true,
+    "send_derived_values" : true
   }
 ```
 
-The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. With the `include_devices` list you can specify which network devices should be measured. **Note**: Most other collectors use an _exclude_ list instead of an include list. 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.
+The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. With the `include_devices` list you can specify which network devices should be measured. **Note**: Most other collectors use an _exclude_ list instead of an include list.
 
 Metrics:
 * `net_bytes_in` (`unit=bytes`)
@@ -28,4 +23,5 @@ Metrics:
 * `net_pkts_in_bw` (`unit=packets/sec` if `send_derived_values == true`)
 * `net_pkts_out_bw` (`unit=packets/sec` if `send_derived_values == true`)
 
-The device name is added as tag `stype=network,stype-id=<device>`.
+The device name is added as tag `stype=network,stype-id=<device>`.
+

collectors/nfsMetric.go

@@ -11,7 +11,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // First part contains the code for the general NfsCollector.
@@ -118,7 +118,7 @@ func (m *nfsCollector) MainInit(config json.RawMessage) error {
 	return nil
 }
 
-func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
@@ -140,7 +140,7 @@ func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			continue
 		}
 		value := data.current - data.last
-		y, err := lp.NewMessage(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+		y, err := lp.New(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

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // These are the fields we read from the JSON configuration
@@ -18,20 +18,17 @@ 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
+	config NfsIOStatCollectorConfig    // the configuration structure
+	meta   map[string]string           // default meta information
+	tags   map[string]string           // default tags
+	data   map[string]map[string]int64 // data storage for difference calculation
+	key    string                      // which device info should be used as subtype ID? 'server' or 'mntpoint', see NfsIOStatCollectorConfig.UseServerAddressAsSType
 }
 
 var deviceRegex = regexp.MustCompile(`device (?P<server>[^ ]+) mounted on (?P<mntpoint>[^ ]+) with fstype nfs(?P<version>\d*) statvers=[\d\.]+`)
@@ -84,6 +81,7 @@ func (m *NfsIOStatCollector) readNfsiostats() map[string]map[string]int64 {
 							data[current[m.key]][name] = val
 						}
 					}
+
 				}
 				current = nil
 			}
@@ -100,9 +98,6 @@ func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
 	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 {
@@ -115,15 +110,12 @@ func (m *NfsIOStatCollector) Init(config json.RawMessage) error {
 		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
+func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	timestamp := time.Now()
 
 	// Get the current values for all mountpoints
 	newdata := m.readNfsiostats()
@@ -131,30 +123,21 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
 	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
+			// Calculate the difference of old and new values
+			for i := range values {
+				x := values[i] - old[i]
+				y, err := lp.New(fmt.Sprintf("nfsio_%s", i), m.tags, m.meta, map[string]interface{}{"value": x}, timestamp)
+				if err == nil {
+					if strings.HasPrefix(i, "page") {
+						y.AddMeta("unit", "4K_Pages")
 					}
+					y.AddTag("stype", "filesystem")
+					y.AddTag("stype-id", mntpoint)
+					// Send it to output channel
+					output <- y
 				}
-				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
+				// Update old to the new value for the next iteration
+				old[i] = values[i]
 			}
 		} else {
 			// First time we see this mount point, store all values
@@ -171,9 +154,10 @@ func (m *NfsIOStatCollector) Read(interval time.Duration, output chan lp.CCMessa
 			}
 		}
 		if !found {
-			delete(m.data, mntpoint)
+			m.data[mntpoint] = nil
 		}
 	}
+
 }
 
 func (m *NfsIOStatCollector) Close() {

collectors/nfsiostatMetric.md

@@ -3,18 +3,16 @@
 ```json
   "nfsiostat": {
     "exclude_metrics": [
-      "oread", "pageread"
+      "nfsio_oread"
     ],
-    "exclude_filesystems": [
-      "/mnt"
+    "exclude_filesystems" : [
+        "/mnt",
     ],
-    "use_server_as_stype": false,
-    "send_abs_values": false,
-    "send_derived_values": true
+    "use_server_as_stype": false
   }
 ```
 
-The `nfsiostat` collector reads data from `/proc/self/mountstats` and outputs a handful **node** metrics for each NFS filesystem. If a metric or filesystem is not required, it can be excluded from forwarding it to the sink. **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.
+The `nfsiostat` collector reads data from `/proc/self/mountstats` and outputs a handful **node** metrics for each NFS filesystem. If a metric or filesystem is not required, it can be excluded from forwarding it to the sink.
 
 Metrics:
 * `nfsio_nread`: Bytes transferred by normal `read()` calls
@@ -26,9 +24,4 @@ Metrics:
 * `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.
+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

@@ -10,15 +10,10 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
-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:
@@ -52,16 +47,13 @@ type NUMAStatsCollectorConfig struct {
 //
 // See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
 type NUMAStatsCollectorTopolgy struct {
-	file           string
-	tagSet         map[string]string
-	previousValues map[string]int64
+	file   string
+	tagSet map[string]string
 }
 
 type NUMAStatsCollector struct {
 	metricCollector
-	topology      []NUMAStatsCollectorTopolgy
-	config        NUMAStatsCollectorConfig
-	lastTimestamp time.Time
+	topology []NUMAStatsCollectorTopolgy
 }
 
 func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
@@ -94,9 +86,8 @@ 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},
-				previousValues: make(map[string]int64),
+				file:   file,
+				tagSet: map[string]string{"memoryDomain": node},
 			})
 	}
 
@@ -106,32 +97,28 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	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))
-			continue
+			return
 		}
 		scanner := bufio.NewScanner(file)
 
 		// Read line by line
 		for scanner.Scan() {
-			line := scanner.Text()
-			split := strings.Fields(line)
+			split := strings.Fields(scanner.Text())
 			if len(split) != 2 {
 				continue
 			}
@@ -143,38 +130,18 @@ func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMessa
 					fmt.Sprintf("Read(): Failed to convert %s='%s' to int64: %v", key, split[1], err))
 				continue
 			}
-
-			if m.config.SendAbsoluteValues {
-				msg, err := lp.NewMessage(
-					"numastats_"+key,
-					t.tagSet,
-					m.meta,
-					map[string]interface{}{"value": 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.NewMessage(
-						"numastats_"+key+"_rate",
-						t.tagSet,
-						m.meta,
-						map[string]interface{}{"value": rate},
-						now,
-					)
-					if err == nil {
-						output <- msg
-					}
-				}
-				t.previousValues[key] = value
+			y, err := lp.New(
+				"numastats_"+key,
+				t.tagSet,
+				m.meta,
+				map[string]interface{}{"value": value},
+				now,
+			)
+			if err == nil {
+				output <- y
 			}
 		}
+
 		file.Close()
 	}
 }

collectors/numastatsMetric.md

@@ -2,10 +2,7 @@
 ## `numastat` collector
 
 ```json
-  "numastats": {
-    "send_abs_values" : true,
-    "send_derived_values" : true
-}
+  "numastats": {}
 ```
 
 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>
@@ -18,9 +15,3 @@ Metrics:
 * `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_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

@@ -8,8 +8,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"github.com/NVIDIA/go-nvml/pkg/nvml"
 )
 
@@ -206,7 +206,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) 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
@@ -222,7 +222,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
 
 		if !device.excludeMetrics["nv_fb_mem_total"] {
 			t := float64(total) / (1024 * 1024)
-			y, err := lp.NewMessage("nv_fb_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("nv_fb_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -231,7 +231,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
 
 		if !device.excludeMetrics["nv_fb_mem_used"] {
 			f := float64(used) / (1024 * 1024)
-			y, err := lp.NewMessage("nv_fb_mem_used", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
+			y, err := lp.New("nv_fb_mem_used", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -240,7 +240,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
 
 		if v2 && !device.excludeMetrics["nv_fb_mem_reserved"] {
 			r := float64(reserved) / (1024 * 1024)
-			y, err := lp.NewMessage("nv_fb_mem_reserved", device.tags, device.meta, map[string]interface{}{"value": r}, time.Now())
+			y, err := lp.New("nv_fb_mem_reserved", device.tags, device.meta, map[string]interface{}{"value": r}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -250,7 +250,7 @@ func readMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
 	return nil
 }
 
-func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_bar1_mem_total"] || !device.excludeMetrics["nv_bar1_mem_used"] {
 		meminfo, ret := nvml.DeviceGetBAR1MemoryInfo(device.device)
 		if ret != nvml.SUCCESS {
@@ -259,7 +259,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) e
 		}
 		if !device.excludeMetrics["nv_bar1_mem_total"] {
 			t := float64(meminfo.Bar1Total) / (1024 * 1024)
-			y, err := lp.NewMessage("nv_bar1_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("nv_bar1_mem_total", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -267,7 +267,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) e
 		}
 		if !device.excludeMetrics["nv_bar1_mem_used"] {
 			t := float64(meminfo.Bar1Used) / (1024 * 1024)
-			y, err := lp.NewMessage("nv_bar1_mem_used", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("nv_bar1_mem_used", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MByte")
 				output <- y
@@ -277,7 +277,7 @@ func readBarMemoryInfo(device NvidiaCollectorDevice, output chan lp.CCMessage) e
 	return nil
 }
 
-func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
 	if ret != nvml.SUCCESS {
 		err := errors.New(nvml.ErrorString(ret))
@@ -301,14 +301,14 @@ func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) err
 		util, ret := nvml.DeviceGetUtilizationRates(device.device)
 		if ret == nvml.SUCCESS {
 			if !device.excludeMetrics["nv_util"] {
-				y, err := lp.NewMessage("nv_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Gpu)}, time.Now())
+				y, err := lp.New("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.NewMessage("nv_mem_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Memory)}, time.Now())
+				y, err := lp.New("nv_mem_util", device.tags, device.meta, map[string]interface{}{"value": float64(util.Memory)}, time.Now())
 				if err == nil {
 					y.AddMeta("unit", "%")
 					output <- y
@@ -319,7 +319,7 @@ func readUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) err
 	return nil
 }
 
-func readTemp(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readTemp(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_temp"] {
 		// Retrieves the current temperature readings for the device, in degrees C.
 		//
@@ -328,7 +328,7 @@ func readTemp(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 		// * NVML_TEMPERATURE_COUNT
 		temp, ret := nvml.DeviceGetTemperature(device.device, nvml.TEMPERATURE_GPU)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_temp", device.tags, device.meta, map[string]interface{}{"value": float64(temp)}, time.Now())
+			y, err := lp.New("nv_temp", device.tags, device.meta, map[string]interface{}{"value": float64(temp)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "degC")
 				output <- y
@@ -338,7 +338,7 @@ func readTemp(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	return nil
 }
 
-func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readFan(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_fan"] {
 		// Retrieves the intended operating speed of the device's fan.
 		//
@@ -351,7 +351,7 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 		// This value may exceed 100% in certain cases.
 		fan, ret := nvml.DeviceGetFanSpeed(device.device)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
+			y, err := lp.New("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "%")
 				output <- y
@@ -361,14 +361,14 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	return nil
 }
 
-// func readFans(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+// func readFans(device NvidiaCollectorDevice, output chan lp.CCMetric) 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.NewMessage("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
+// 					y, err := lp.New("nv_fan", device.tags, device.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
 // 					if err == nil {
 // 						y.AddMeta("unit", "%")
 // 						y.AddTag("stype", "fan")
@@ -382,7 +382,7 @@ func readFan(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 // 	return nil
 // }
 
-func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_ecc_mode"] {
 		// Retrieves the current and pending ECC modes for the device.
 		//
@@ -393,21 +393,21 @@ func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMessage) 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.CCMessage
+			var y lp.CCMetric
 			var err error
 			switch ecc_pend {
 			case nvml.FEATURE_DISABLED:
-				y, err = lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "OFF"}, time.Now())
+				y, err = lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "OFF"}, time.Now())
 			case nvml.FEATURE_ENABLED:
-				y, err = lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "ON"}, time.Now())
+				y, err = lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "ON"}, time.Now())
 			default:
-				y, err = lp.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "UNKNOWN"}, time.Now())
+				y, err = lp.New("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.NewMessage("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "N/A"}, time.Now())
+			y, err := lp.New("nv_ecc_mode", device.tags, device.meta, map[string]interface{}{"value": "N/A"}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -416,7 +416,7 @@ func readEccMode(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	return nil
 }
 
-func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_perf_state"] {
 		// Retrieves the current performance state for the device.
 		//
@@ -427,7 +427,7 @@ func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMessage) error
 		// 32: Unknown performance state.
 		pState, ret := nvml.DeviceGetPerformanceState(device.device)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_perf_state", device.tags, device.meta, map[string]interface{}{"value": fmt.Sprintf("P%d", int(pState))}, time.Now())
+			y, err := lp.New("nv_perf_state", device.tags, device.meta, map[string]interface{}{"value": fmt.Sprintf("P%d", int(pState))}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -436,7 +436,7 @@ func readPerfState(device NvidiaCollectorDevice, output chan lp.CCMessage) error
 	return nil
 }
 
-func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_power_usage"] {
 		// Retrieves power usage for this GPU in milliwatts and its associated circuitry (e.g. memory)
 		//
@@ -450,7 +450,7 @@ func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
 		if mode == nvml.FEATURE_ENABLED {
 			power, ret := nvml.DeviceGetPowerUsage(device.device)
 			if ret == nvml.SUCCESS {
-				y, err := lp.NewMessage("nv_power_usage", device.tags, device.meta, map[string]interface{}{"value": float64(power) / 1000}, time.Now())
+				y, err := lp.New("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
@@ -461,7 +461,7 @@ func readPowerUsage(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
 	return nil
 }
 
-func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	// Retrieves the current clock speeds for the device.
 	//
 	// Available clock information:
@@ -471,7 +471,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_graphics_clock"] {
 		graphicsClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_GRAPHICS)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(graphicsClock)}, time.Now())
+			y, err := lp.New("nv_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(graphicsClock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -482,7 +482,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_sm_clock"] {
 		smCock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(smCock)}, time.Now())
+			y, err := lp.New("nv_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(smCock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -493,7 +493,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_mem_clock"] {
 		memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
+			y, err := lp.New("nv_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -503,7 +503,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	if !device.excludeMetrics["nv_video_clock"] {
 		memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
+			y, err := lp.New("nv_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "MHz")
 				output <- y
@@ -513,7 +513,7 @@ func readClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
 	return nil
 }
 
-func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	// Retrieves the maximum clock speeds for the device.
 	//
 	// Available clock information:
@@ -528,7 +528,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) 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.NewMessage("nv_max_graphics_clock", device.tags, device.meta, map[string]interface{}{"value": float64(max_gclk)}, time.Now())
+			y, err := lp.New("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
@@ -539,7 +539,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
 	if !device.excludeMetrics["nv_max_sm_clock"] {
 		maxSmClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_max_sm_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxSmClock)}, time.Now())
+			y, err := lp.New("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
@@ -550,7 +550,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
 	if !device.excludeMetrics["nv_max_mem_clock"] {
 		maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_max_mem_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
+			y, err := lp.New("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
@@ -561,7 +561,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
 	if !device.excludeMetrics["nv_max_video_clock"] {
 		maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_VIDEO)
 		if ret == nvml.SUCCESS {
-			y, err := lp.NewMessage("nv_max_video_clock", device.tags, device.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
+			y, err := lp.New("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
@@ -571,7 +571,7 @@ func readMaxClocks(device NvidiaCollectorDevice, output chan lp.CCMessage) error
 	return nil
 }
 
-func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_ecc_uncorrected_error"] {
 		// Retrieves the total ECC error counts for the device.
 		//
@@ -584,7 +584,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) 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.NewMessage("nv_ecc_uncorrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_db)}, time.Now())
+			y, err := lp.New("nv_ecc_uncorrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_db)}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -593,7 +593,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) 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.NewMessage("nv_ecc_corrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_sb)}, time.Now())
+			y, err := lp.New("nv_ecc_corrected_error", device.tags, device.meta, map[string]interface{}{"value": float64(ecc_sb)}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -602,7 +602,7 @@ func readEccErrors(device NvidiaCollectorDevice, output chan lp.CCMessage) error
 	return nil
 }
 
-func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_power_max_limit"] {
 		// Retrieves the power management limit associated with this device.
 		//
@@ -612,7 +612,7 @@ func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
 		// 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.NewMessage("nv_power_max_limit", device.tags, device.meta, map[string]interface{}{"value": float64(pwr_limit) / 1000}, time.Now())
+			y, err := lp.New("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
@@ -622,7 +622,7 @@ func readPowerLimit(device NvidiaCollectorDevice, output chan lp.CCMessage) erro
 	return nil
 }
 
-func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
 	if ret != nvml.SUCCESS {
 		err := errors.New(nvml.ErrorString(ret))
@@ -639,7 +639,7 @@ func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		// 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.NewMessage("nv_encoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(enc_util)}, time.Now())
+			y, err := lp.New("nv_encoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(enc_util)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "%")
 				output <- y
@@ -649,7 +649,7 @@ func readEncUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
 	return nil
 }
 
-func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	isMig, ret := nvml.DeviceIsMigDeviceHandle(device.device)
 	if ret != nvml.SUCCESS {
 		err := errors.New(nvml.ErrorString(ret))
@@ -666,7 +666,7 @@ func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		// 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.NewMessage("nv_decoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(dec_util)}, time.Now())
+			y, err := lp.New("nv_decoder_util", device.tags, device.meta, map[string]interface{}{"value": float64(dec_util)}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "%")
 				output <- y
@@ -676,7 +676,7 @@ func readDecUtilization(device NvidiaCollectorDevice, output chan lp.CCMessage)
 	return nil
 }
 
-func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_remapped_rows_corrected"] ||
 		!device.excludeMetrics["nv_remapped_rows_uncorrected"] ||
 		!device.excludeMetrics["nv_remapped_rows_pending"] ||
@@ -693,13 +693,13 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
 		corrected, uncorrected, pending, failure, ret := nvml.DeviceGetRemappedRows(device.device)
 		if ret == nvml.SUCCESS {
 			if !device.excludeMetrics["nv_remapped_rows_corrected"] {
-				y, err := lp.NewMessage("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(corrected)}, time.Now())
+				y, err := lp.New("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.NewMessage("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(uncorrected)}, time.Now())
+				y, err := lp.New("nv_remapped_rows_corrected", device.tags, device.meta, map[string]interface{}{"value": float64(uncorrected)}, time.Now())
 				if err == nil {
 					output <- y
 				}
@@ -709,7 +709,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
 				if pending {
 					p = 1
 				}
-				y, err := lp.NewMessage("nv_remapped_rows_pending", device.tags, device.meta, map[string]interface{}{"value": p}, time.Now())
+				y, err := lp.New("nv_remapped_rows_pending", device.tags, device.meta, map[string]interface{}{"value": p}, time.Now())
 				if err == nil {
 					output <- y
 				}
@@ -719,7 +719,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
 				if failure {
 					f = 1
 				}
-				y, err := lp.NewMessage("nv_remapped_rows_failure", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
+				y, err := lp.New("nv_remapped_rows_failure", device.tags, device.meta, map[string]interface{}{"value": f}, time.Now())
 				if err == nil {
 					output <- y
 				}
@@ -729,7 +729,7 @@ func readRemappedRows(device NvidiaCollectorDevice, output chan lp.CCMessage) er
 	return nil
 }
 
-func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	if !device.excludeMetrics["nv_compute_processes"] {
 		// Get information about processes with a compute context on a device
 		//
@@ -753,7 +753,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) e
 		//        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.NewMessage("nv_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
+			y, err := lp.New("nv_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -782,7 +782,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) e
 		//       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.NewMessage("nv_graphics_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
+			y, err := lp.New("nv_graphics_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
 			if err == nil {
 				output <- y
 			}
@@ -812,7 +812,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) e
 	// 	//       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.NewMessage("nv_mps_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
+	// 		y, err := lp.New("nv_mps_compute_processes", device.tags, device.meta, map[string]interface{}{"value": len(procList)}, time.Now())
 	// 		if err == nil {
 	// 			output <- y
 	// 		}
@@ -821,7 +821,7 @@ func readProcessCounts(device NvidiaCollectorDevice, output chan lp.CCMessage) e
 	return nil
 }
 
-func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMetric) error {
 	var violTime nvml.ViolationTime
 	var ret nvml.Return
 
@@ -840,7 +840,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_POWER)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.NewMessage("nv_violation_power", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("nv_violation_power", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -852,7 +852,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_THERMAL)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.NewMessage("nv_violation_thermal", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("nv_violation_thermal", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -864,7 +864,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_SYNC_BOOST)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.NewMessage("nv_violation_sync_boost", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("nv_violation_sync_boost", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -876,7 +876,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_BOARD_LIMIT)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.NewMessage("nv_violation_board_limit", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("nv_violation_board_limit", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -888,7 +888,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_LOW_UTILIZATION)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.NewMessage("nv_violation_low_util", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("nv_violation_low_util", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -900,7 +900,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		violTime, ret = nvml.DeviceGetViolationStatus(device.device, nvml.PERF_POLICY_RELIABILITY)
 		if ret == nvml.SUCCESS {
 			t := float64(violTime.ViolationTime) * 1e-9
-			y, err := lp.NewMessage("nv_violation_reliability", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("nv_violation_reliability", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
 			if err == nil {
 				y.AddMeta("unit", "sec")
 				output <- y
@@ -912,7 +912,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		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.NewMessage("nv_violation_below_app_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("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
@@ -924,7 +924,7 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
 		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.NewMessage("nv_violation_below_base_clock", device.tags, device.meta, map[string]interface{}{"value": t}, time.Now())
+			y, err := lp.New("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
@@ -935,18 +935,12 @@ func readViolationStats(device NvidiaCollectorDevice, output chan lp.CCMessage)
 	return nil
 }
 
-func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) error {
+func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMetric) 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 {
@@ -954,9 +948,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
 				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.NewMessage("nv_nvlink_crc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.New("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))
@@ -967,9 +960,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
 				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.NewMessage("nv_nvlink_ecc_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.New("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))
@@ -980,9 +972,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
 				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.NewMessage("nv_nvlink_replay_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.New("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))
@@ -993,9 +984,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
 				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.NewMessage("nv_nvlink_recovery_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.New("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))
@@ -1006,9 +996,8 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
 				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.NewMessage("nv_nvlink_crc_flit_errors", device.tags, device.meta, map[string]interface{}{"value": count}, time.Now())
+						y, err := lp.New("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))
@@ -1019,58 +1008,16 @@ func readNVLinkStats(device NvidiaCollectorDevice, output chan lp.CCMessage) err
 			}
 		}
 	}
-
-	// 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.CCMessage) {
+func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	var err error
 	if !m.init {
 		return
 	}
 
-	readAll := func(device NvidiaCollectorDevice, output chan lp.CCMessage) {
+	readAll := func(device NvidiaCollectorDevice, output chan lp.CCMetric) {
 		name, ret := nvml.DeviceGetName(device.device)
 		if ret != nvml.SUCCESS {
 			name = "NoName"

collectors/raplMetric.go

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // running average power limit (RAPL) monitoring attributes for a zone
@@ -214,7 +214,7 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
 
 // 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) {
+func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 	for i := range m.RAPLZoneInfo {
 		p := &m.RAPLZoneInfo[i]
@@ -237,7 +237,7 @@ func (m *RAPLCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 				timeDiff := energyTimestamp.Sub(p.energyTimestamp)
 				averagePower := float64(energyDiff) / float64(timeDiff.Microseconds())
 
-				y, err := lp.NewMessage(
+				y, err := lp.New(
 					"rapl_average_power",
 					p.tags,
 					m.meta,

collectors/raplMetric.md

@@ -1,9 +1,11 @@
-## `rapl` collector
+# Running average power limit (RAPL) metric collector
 
 This collector reads running average power limit (RAPL) monitoring attributes to compute average power consumption metrics. See <https://www.kernel.org/doc/html/latest/power/powercap/powercap.html#monitoring-attributes>.
 
 The Likwid metric collector provides similar functionality.
 
+## Configuration
+
 ```json
   "rapl": {
     "exclude_device_by_id": ["0:1", "0:2"],
@@ -11,5 +13,6 @@ The Likwid metric collector provides similar functionality.
   }
 ```
 
-Metrics:
+## 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

@@ -6,8 +6,8 @@ import (
 	"fmt"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"github.com/ClusterCockpit/go-rocm-smi/pkg/rocm_smi"
 )
 
@@ -162,7 +162,7 @@ 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.CCMessage) {
+func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	// Create a sample metric
 	timestamp := time.Now()
 
@@ -175,119 +175,119 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage
 
 		if !dev.excludeMetrics["rocm_gfx_util"] {
 			value := metrics.Average_gfx_activity
-			y, err := lp.NewMessage("rocm_gfx_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_gfx_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_umc_util"] {
 			value := metrics.Average_umc_activity
-			y, err := lp.NewMessage("rocm_umc_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_umc_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_mm_util"] {
 			value := metrics.Average_mm_activity
-			y, err := lp.NewMessage("rocm_mm_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_mm_util", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_avg_power"] {
 			value := metrics.Average_socket_power
-			y, err := lp.NewMessage("rocm_avg_power", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_avg_power", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_mem"] {
 			value := metrics.Temperature_mem
-			y, err := lp.NewMessage("rocm_temp_mem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_temp_mem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_hotspot"] {
 			value := metrics.Temperature_hotspot
-			y, err := lp.NewMessage("rocm_temp_hotspot", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_temp_hotspot", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_edge"] {
 			value := metrics.Temperature_edge
-			y, err := lp.NewMessage("rocm_temp_edge", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_temp_edge", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_vrgfx"] {
 			value := metrics.Temperature_vrgfx
-			y, err := lp.NewMessage("rocm_temp_vrgfx", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_temp_vrgfx", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_vrsoc"] {
 			value := metrics.Temperature_vrsoc
-			y, err := lp.NewMessage("rocm_temp_vrsoc", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_temp_vrsoc", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_temp_vrmem"] {
 			value := metrics.Temperature_vrmem
-			y, err := lp.NewMessage("rocm_temp_vrmem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_temp_vrmem", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_gfx_clock"] {
 			value := metrics.Average_gfxclk_frequency
-			y, err := lp.NewMessage("rocm_gfx_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_gfx_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_soc_clock"] {
 			value := metrics.Average_socclk_frequency
-			y, err := lp.NewMessage("rocm_soc_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_soc_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_u_clock"] {
 			value := metrics.Average_uclk_frequency
-			y, err := lp.NewMessage("rocm_u_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_u_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_v0_clock"] {
 			value := metrics.Average_vclk0_frequency
-			y, err := lp.NewMessage("rocm_v0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_v0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_v1_clock"] {
 			value := metrics.Average_vclk1_frequency
-			y, err := lp.NewMessage("rocm_v1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_v1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_d0_clock"] {
 			value := metrics.Average_dclk0_frequency
-			y, err := lp.NewMessage("rocm_d0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_d0_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
 		}
 		if !dev.excludeMetrics["rocm_d1_clock"] {
 			value := metrics.Average_dclk1_frequency
-			y, err := lp.NewMessage("rocm_d1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+			y, err := lp.New("rocm_d1_clock", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 			if err == nil {
 				output <- y
 			}
@@ -295,7 +295,7 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage
 		if !dev.excludeMetrics["rocm_temp_hbm"] {
 			for i := 0; i < rocm_smi.NUM_HBM_INSTANCES; i++ {
 				value := metrics.Temperature_hbm[i]
-				y, err := lp.NewMessage("rocm_temp_hbm", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
+				y, err := lp.New("rocm_temp_hbm", dev.tags, dev.meta, map[string]interface{}{"value": value}, timestamp)
 				if err == nil {
 					y.AddTag("stype", "device")
 					y.AddTag("stype-id", fmt.Sprintf("%d", i))

collectors/sampleMetric.go

@@ -4,8 +4,8 @@ import (
 	"encoding/json"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // These are the fields we read from the JSON configuration
@@ -32,7 +32,7 @@ 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 = "SampleCollector"
+	m.name = "InternalCollector"
 	// This is for later use, also call it early
 	m.setup()
 	// Tell whether the collector should be run in parallel with others (reading files, ...)
@@ -74,7 +74,7 @@ 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.CCMessage) {
+func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	// Create a sample metric
 	timestamp := time.Now()
 
@@ -85,7 +85,7 @@ func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMessage)
 	// stop := readState()
 	// value = (stop - start) / interval.Seconds()
 
-	y, err := lp.NewMessage("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+	y, err := lp.New("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

@@ -5,8 +5,8 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // These are the fields we read from the JSON configuration
@@ -25,7 +25,7 @@ type SampleTimerCollector struct {
 	config   SampleTimerCollectorConfig // the configuration structure
 	interval time.Duration              // the interval parsed from configuration
 	ticker   *time.Ticker               // own timer
-	output   chan lp.CCMessage          // own internal output channel
+	output   chan lp.CCMetric           // own internal output channel
 }
 
 func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
@@ -100,14 +100,14 @@ func (m *SampleTimerCollector) ReadMetrics(timestamp time.Time) {
 	// stop := readState()
 	// value = (stop - start) / interval.Seconds()
 
-	y, err := lp.NewMessage("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+	y, err := lp.New("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.CCMessage) {
+func (m *SampleTimerCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	// Capture output channel
 	m.output = output
 }

collectors/schedstatMetric.go

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const SCHEDSTATFILE = `/proc/schedstat`
@@ -96,7 +96,7 @@ func (m *SchedstatCollector) Init(config json.RawMessage) error {
 	return err
 }
 
-func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]string, output chan lp.CCMessage, now time.Time, tsdelta time.Duration) {
+func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
 	running, _ := strconv.ParseInt(linefields[7], 10, 64)
 	waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
 	diff_running := running - m.olddata[linefields[0]]["running"]
@@ -109,7 +109,7 @@ func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]
 	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)
+	y, err := lp.New("cpu_load_core", tags, m.meta, map[string]interface{}{"value": value}, now)
 	if err == nil {
 		// Send it to output channel
 		output <- y
@@ -118,7 +118,7 @@ func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]
 
 // 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) {
+func (m *SchedstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}

collectors/selfMetric.go

@@ -6,8 +6,8 @@ import (
 	"syscall"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 type SelfCollectorConfig struct {
@@ -42,56 +42,56 @@ func (m *SelfCollector) Init(config json.RawMessage) error {
 	return err
 }
 
-func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	timestamp := time.Now()
 
 	if m.config.MemStats {
 		var memstats runtime.MemStats
 		runtime.ReadMemStats(&memstats)
 
-		y, err := lp.NewMessage("total_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.TotalAlloc}, timestamp)
+		y, err := lp.New("total_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.TotalAlloc}, timestamp)
 		if err == nil {
 			y.AddMeta("unit", "Bytes")
 			output <- y
 		}
-		y, err = lp.NewMessage("heap_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapAlloc}, timestamp)
+		y, err = lp.New("heap_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapAlloc}, timestamp)
 		if err == nil {
 			y.AddMeta("unit", "Bytes")
 			output <- y
 		}
-		y, err = lp.NewMessage("heap_sys", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapSys}, timestamp)
+		y, err = lp.New("heap_sys", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapSys}, timestamp)
 		if err == nil {
 			y.AddMeta("unit", "Bytes")
 			output <- y
 		}
-		y, err = lp.NewMessage("heap_idle", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapIdle}, timestamp)
+		y, err = lp.New("heap_idle", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapIdle}, timestamp)
 		if err == nil {
 			y.AddMeta("unit", "Bytes")
 			output <- y
 		}
-		y, err = lp.NewMessage("heap_inuse", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapInuse}, timestamp)
+		y, err = lp.New("heap_inuse", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapInuse}, timestamp)
 		if err == nil {
 			y.AddMeta("unit", "Bytes")
 			output <- y
 		}
-		y, err = lp.NewMessage("heap_released", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapReleased}, timestamp)
+		y, err = lp.New("heap_released", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapReleased}, timestamp)
 		if err == nil {
 			y.AddMeta("unit", "Bytes")
 			output <- y
 		}
-		y, err = lp.NewMessage("heap_objects", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapObjects}, timestamp)
+		y, err = lp.New("heap_objects", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapObjects}, timestamp)
 		if err == nil {
 			output <- y
 		}
 	}
 	if m.config.GoRoutines {
-		y, err := lp.NewMessage("num_goroutines", m.tags, m.meta, map[string]interface{}{"value": runtime.NumGoroutine()}, timestamp)
+		y, err := lp.New("num_goroutines", m.tags, m.meta, map[string]interface{}{"value": runtime.NumGoroutine()}, timestamp)
 		if err == nil {
 			output <- y
 		}
 	}
 	if m.config.CgoCalls {
-		y, err := lp.NewMessage("num_cgo_calls", m.tags, m.meta, map[string]interface{}{"value": runtime.NumCgoCall()}, timestamp)
+		y, err := lp.New("num_cgo_calls", m.tags, m.meta, map[string]interface{}{"value": runtime.NumCgoCall()}, timestamp)
 		if err == nil {
 			output <- y
 		}
@@ -102,35 +102,35 @@ func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 		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)
+			y, err := lp.New("rusage_user_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
 			if err == nil {
 				y.AddMeta("unit", "seconds")
 				output <- y
 			}
 			sec, nsec = rusage.Stime.Unix()
 			t = float64(sec) + (float64(nsec) * 1e-9)
-			y, err = lp.NewMessage("rusage_system_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
+			y, err = lp.New("rusage_system_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
 			if err == nil {
 				y.AddMeta("unit", "seconds")
 				output <- y
 			}
-			y, err = lp.NewMessage("rusage_vol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nvcsw}, timestamp)
+			y, err = lp.New("rusage_vol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nvcsw}, timestamp)
 			if err == nil {
 				output <- y
 			}
-			y, err = lp.NewMessage("rusage_invol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nivcsw}, timestamp)
+			y, err = lp.New("rusage_invol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nivcsw}, timestamp)
 			if err == nil {
 				output <- y
 			}
-			y, err = lp.NewMessage("rusage_signals", m.tags, m.meta, map[string]interface{}{"value": rusage.Nsignals}, timestamp)
+			y, err = lp.New("rusage_signals", m.tags, m.meta, map[string]interface{}{"value": rusage.Nsignals}, timestamp)
 			if err == nil {
 				output <- y
 			}
-			y, err = lp.NewMessage("rusage_major_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Majflt}, timestamp)
+			y, err = lp.New("rusage_major_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Majflt}, timestamp)
 			if err == nil {
 				output <- y
 			}
-			y, err = lp.NewMessage("rusage_minor_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Minflt}, timestamp)
+			y, err = lp.New("rusage_minor_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Minflt}, timestamp)
 			if err == nil {
 				output <- y
 			}

collectors/tempMetric.go

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html
@@ -171,7 +171,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 	for _, sensor := range m.sensors {
 		// Read sensor file
@@ -190,7 +190,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 			continue
 		}
 		x /= 1000
-		y, err := lp.NewMessage(
+		y, err := lp.New(
 			sensor.metricName,
 			sensor.tags,
 			m.meta,
@@ -203,7 +203,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 
 		// max temperature
 		if m.config.ReportMaxTemp && sensor.maxTemp != 0 {
-			y, err := lp.NewMessage(
+			y, err := lp.New(
 				sensor.maxTempName,
 				sensor.tags,
 				m.meta,
@@ -217,7 +217,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 
 		// critical temperature
 		if m.config.ReportCriticalTemp && sensor.critTemp != 0 {
-			y, err := lp.NewMessage(
+			y, err := lp.New(
 				sensor.critTempName,
 				sensor.tags,
 				m.meta,

collectors/topprocsMetric.go

@@ -9,7 +9,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const MAX_NUM_PROCS = 10
@@ -53,7 +53,7 @@ func (m *TopProcsCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
+func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
@@ -68,7 +68,7 @@ func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessag
 	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.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": string(lines[i])}, time.Now())
+		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": string(lines[i])}, time.Now())
 		if err == nil {
 			output <- y
 		}

config.json

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

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": "10s",
-  "duration": "1s"
+  "interval": 10,
+  "duration": 1
 }
 ```
 

go.mod

@@ -1,48 +1,41 @@
 module github.com/ClusterCockpit/cc-metric-collector
 
-go 1.23.4
-
-toolchain go1.23.7
+go 1.21
 
 require (
-	github.com/ClusterCockpit/cc-lib v0.1.1
+	github.com/ClusterCockpit/cc-units v0.4.0
 	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/influxdb-client-go/v2 v2.13.0
 	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
 	github.com/influxdata/line-protocol/v2 v2.2.1
-	github.com/nats-io/nats.go v1.39.0
-	github.com/prometheus/client_golang v1.20.5
+	github.com/nats-io/nats.go v1.33.1
+	github.com/prometheus/client_golang v1.19.0
 	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
+	golang.org/x/exp v0.0.0-20240222234643-814bf88cf225
+	golang.org/x/sys v0.18.0
 )
 
 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 v2.3.0 // indirect
-	github.com/expr-lang/expr v1.17.0 // indirect
+	github.com/cespare/xxhash/v2 v2.2.0 // 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/klauspost/compress v1.17.7 // indirect
+	github.com/nats-io/nkeys v0.4.7 // indirect
 	github.com/nats-io/nuid v1.0.1 // indirect
 	github.com/oapi-codegen/runtime v1.1.1 // indirect
-	github.com/prometheus/client_model v0.6.1 // 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/prometheus/client_model v0.6.0 // indirect
+	github.com/prometheus/common v0.49.0 // indirect
+	github.com/prometheus/procfs v0.12.0 // indirect
 	github.com/shopspring/decimal v1.3.1 // indirect
 	github.com/tklauser/numcpus v0.7.0 // indirect
-	golang.org/x/crypto v0.35.0 // indirect
-	golang.org/x/net v0.36.0 // indirect
-	google.golang.org/protobuf v1.35.2 // indirect
+	golang.org/x/crypto v0.21.0 // indirect
+	golang.org/x/net v0.22.0 // indirect
+	google.golang.org/protobuf v1.33.0 // indirect
 )

go.sum

@@ -1,9 +1,3 @@
-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=
@@ -13,7 +7,6 @@ github.com/NVIDIA/go-nvml v0.12.0-2 h1:Sg239yy7jmopu/cuvYauoMj9fOpcGMngxVxxS1EBX
 github.com/NVIDIA/go-nvml v0.12.0-2/go.mod h1:7ruy85eOM73muOc/I37euONSwEyFqZsv5ED9AogD4G0=
 github.com/PaesslerAG/gval v1.2.2 h1:Y7iBzhgE09IGTt5QgGQ2IdaYYYOU134YGHBThD+wm9E=
 github.com/PaesslerAG/gval v1.2.2/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac=
-github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI=
 github.com/PaesslerAG/jsonpath v0.1.0/go.mod h1:4BzmtoM/PI8fPO4aQGIusjGxGir2BzcV0grWtFzq1Y8=
 github.com/RaveNoX/go-jsoncommentstrip v1.0.0/go.mod h1:78ihd09MekBnJnxpICcwzCMzGrKSKYe4AqU6PDYYpjk=
 github.com/apapsch/go-jsonmerge/v2 v2.0.0 h1:axGnT1gRIfimI7gJifB699GoE/oq+F2MU7Dml6nw9rQ=
@@ -21,78 +14,57 @@ github.com/apapsch/go-jsonmerge/v2 v2.0.0/go.mod h1:lvDnEdqiQrp0O42VQGgmlKpxL1AP
 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/cespare/xxhash/v2 v2.2.0 h1:DC2CZ1Ep5Y4k3ZQ899DldepgrayRUGE6BBZ/cd9Cj44=
+github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/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/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/influxdb-client-go/v2 v2.13.0 h1:ioBbLmR5NMbAjP4UVA5r9b5xGjpABD7j65pI8kFphDM=
+github.com/influxdata/influxdb-client-go/v2 v2.13.0/go.mod h1:k+spCbt9hcvqvUiz0sr5D8LolXHqAAOfPw9v/RIRHl4=
 github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf h1:7JTmneyiNEwVBOHSjoMxiWAqB992atOeepeFYegn5RU=
 github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
 github.com/influxdata/line-protocol-corpus v0.0.0-20210519164801-ca6fa5da0184/go.mod h1:03nmhxzZ7Xk2pdG+lmMd7mHDfeVOYFyhOgwO61qWU98=
-github.com/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/klauspost/compress v1.17.7 h1:ehO88t2UGzQK66LMdE8tibEd1ErmzZjNEqWkjLAKQQg=
+github.com/klauspost/compress v1.17.7/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/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
-github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
-github.com/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/nats.go v1.33.1 h1:8TxLZZ/seeEfR97qV0/Bl939tpDnt2Z2fK3HkPypj70=
+github.com/nats-io/nats.go v1.33.1/go.mod h1:Ubdu4Nh9exXdSz0RVWRFBbRfrbSxOYd26oF0wkWclB8=
+github.com/nats-io/nkeys v0.4.7 h1:RwNJbbIdYCoClSDNY7QVKZlyb/wfT6ugvFCiKy6vDvI=
+github.com/nats-io/nkeys v0.4.7/go.mod h1:kqXRgRDPlGy7nGaEDMuYzmiJCIAAWDK0IMBtDmGD0nc=
 github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw=
 github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OSON2c=
 github.com/niemeyer/pretty v0.0.0-20200227124842-a10e7caefd8e/go.mod h1:zD1mROLANZcx1PVRCS0qkT7pwLkGfwJo4zjcN/Tysno=
 github.com/oapi-codegen/runtime v1.1.1 h1:EXLHh0DXIJnWhdRPN2w4MXAzFyE4CskzhNLUmtpMYro=
 github.com/oapi-codegen/runtime v1.1.1/go.mod h1:SK9X900oXmPWilYR5/WKPzt3Kqxn/uS/+lbpREv+eCg=
-github.com/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/prometheus/client_golang v1.19.0 h1:ygXvpU1AoN1MhdzckN+PyD9QJOSD4x7kmXYlnfbA6JU=
+github.com/prometheus/client_golang v1.19.0/go.mod h1:ZRM9uEAypZakd+q/x7+gmsvXdURP+DABIEIjnmDdp+k=
+github.com/prometheus/client_model v0.6.0 h1:k1v3CzpSRUTrKMppY35TLwPvxHqBu0bYgxZzqGIgaos=
+github.com/prometheus/client_model v0.6.0/go.mod h1:NTQHnmxFpouOD0DpvP4XujX3CdOAGQPoaGhyTchlyt8=
+github.com/prometheus/common v0.49.0 h1:ToNTdK4zSnPVJmh698mGFkDor9wBI/iGaJy5dbH1EgI=
+github.com/prometheus/common v0.49.0/go.mod h1:Kxm+EULxRbUkjGU6WFsQqo3ORzB4tyKvlWFOE9mB2sE=
+github.com/prometheus/procfs v0.12.0 h1:jluTpSng7V9hY0O2R9DzzJHYb2xULk9VTR1V1R/k6Bo=
+github.com/prometheus/procfs v0.12.0/go.mod h1:pcuDEFsWDnvcgNzo4EEweacyhjeA9Zk3cnaOZAZEfOo=
 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=
@@ -105,35 +77,26 @@ github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UV
 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/crypto v0.21.0 h1:X31++rzVUdKhX5sWmSOFZxx8UW/ldWx55cbf08iNAMA=
+golang.org/x/crypto v0.21.0/go.mod h1:0BP7YvVV9gBbVKyeTG0Gyn+gZm94bibOW5BjDEYAOMs=
+golang.org/x/exp v0.0.0-20240222234643-814bf88cf225 h1:LfspQV/FYTatPTr/3HzIcmiUFH7PGP+OQ6mgDYo3yuQ=
+golang.org/x/exp v0.0.0-20240222234643-814bf88cf225/go.mod h1:CxmFvTBINI24O/j8iY7H1xHzx2i4OsyguNBmN/uPtqc=
+golang.org/x/net v0.22.0 h1:9sGLhx7iRIHEiX0oAJ3MRZMUCElJgy7Br1nO+AMN3Tc=
+golang.org/x/net v0.22.0/go.mod h1:JKghWKKOSdJwpW2GEx0Ja7fmaKnMsbu+MWVZTokSYmg=
 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/sys v0.18.0 h1:DBdB3niSjOA/O0blCZBqDefyWNYveAYMNF1Wum0DYQ4=
+golang.org/x/sys v0.18.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
-google.golang.org/protobuf v1.35.2 h1:8Ar7bF+apOIoThw1EdZl0p1oWvMqTHmpA2fRTyZO8io=
-google.golang.org/protobuf v1.35.2/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
+google.golang.org/protobuf v1.33.0 h1:uNO2rsAINq/JlFpSdYEKIZ0uKD/R9cpdv0T+yoGwGmI=
+google.golang.org/protobuf v1.33.0/go.mod h1:c6P6GXX6sHbq/GpV6MGZEdwhWPcYBgnhAHhKbcUYpos=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20200227125254-8fa46927fb4f/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/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/metricAggregator/metricAggregator.go

@@ -9,9 +9,9 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 
 	"github.com/PaesslerAG/gval"
@@ -31,14 +31,14 @@ type metricAggregator struct {
 	functions []*MetricAggregatorIntervalConfig
 	constants map[string]interface{}
 	language  gval.Language
-	output    chan lp.CCMessage
+	output    chan lp.CCMetric
 }
 
 type MetricAggregator interface {
 	AddAggregation(name, function, condition string, tags, meta map[string]string) error
 	DeleteAggregation(name string) error
-	Init(output chan lp.CCMessage) error
-	Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMessage)
+	Init(output chan lp.CCMetric) error
+	Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMetric)
 }
 
 var metricCacheLanguage = gval.NewLanguage(
@@ -74,7 +74,7 @@ var evaluables = struct {
 	mapping: make(map[string]gval.Evaluable),
 }
 
-func (c *metricAggregator) Init(output chan lp.CCMessage) error {
+func (c *metricAggregator) Init(output chan lp.CCMetric) error {
 	c.output = output
 	c.functions = make([]*MetricAggregatorIntervalConfig, 0)
 	c.constants = make(map[string]interface{})
@@ -112,7 +112,7 @@ func (c *metricAggregator) Init(output chan lp.CCMessage) error {
 	return nil
 }
 
-func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMessage) {
+func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics []lp.CCMetric) {
 	vars := make(map[string]interface{})
 	for k, v := range c.constants {
 		vars[k] = v
@@ -127,7 +127,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 		var valuesInt32 []int32
 		var valuesInt64 []int64
 		var valuesBool []bool
-		matches := make([]lp.CCMessage, 0)
+		matches := make([]lp.CCMetric, 0)
 		for _, m := range metrics {
 			vars["metric"] = m
 			//value, err := gval.Evaluate(f.Condition, vars, c.language)
@@ -216,7 +216,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 				break
 			}
 
-			copy_tags := func(tags map[string]string, metrics []lp.CCMessage) map[string]string {
+			copy_tags := func(tags map[string]string, metrics []lp.CCMetric) map[string]string {
 				out := make(map[string]string)
 				for key, value := range tags {
 					switch value {
@@ -233,7 +233,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 				}
 				return out
 			}
-			copy_meta := func(meta map[string]string, metrics []lp.CCMessage) map[string]string {
+			copy_meta := func(meta map[string]string, metrics []lp.CCMetric) map[string]string {
 				out := make(map[string]string)
 				for key, value := range meta {
 					switch value {
@@ -253,18 +253,18 @@ 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.CCMessage
+			var m lp.CCMetric
 			switch t := value.(type) {
 			case float64:
-				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			case float32:
-				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			case int:
-				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			case int64:
-				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			case string:
-				m, err = lp.NewMessage(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
+				m, err = lp.New(f.Name, tags, meta, map[string]interface{}{"value": t}, starttime)
 			default:
 				cclog.ComponentError("MetricCache", "Gval returned invalid type", t, "skipping metric", f.Name)
 			}
@@ -389,7 +389,7 @@ func EvalFloat64Condition(condition string, params map[string]float64) (float64,
 	return value, err
 }
 
-func NewAggregator(output chan lp.CCMessage) (MetricAggregator, error) {
+func NewAggregator(output chan lp.CCMetric) (MetricAggregator, error) {
 	a := new(metricAggregator)
 	err := a.Init(output)
 	if err != nil {

internal/metricRouter/README.md

@@ -1,21 +1,15 @@
 # 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 [CCMessages](https://pkg.go.dev/github.com/ClusterCockpit/cc-energy-manager@v0.0.0-20240919152819-92a17f2da4f7/pkg/cc-message.
-
+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).
 
 # Configuration
 
-**Note**: Use the [message processor configuration](../../pkg/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",
@@ -69,8 +63,6 @@ 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](../../pkg/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)
@@ -104,8 +96,6 @@ 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
@@ -117,8 +107,6 @@ 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
 {
@@ -130,8 +118,6 @@ 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.
@@ -143,8 +129,6 @@ 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.
@@ -186,8 +170,6 @@ 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
@@ -203,8 +185,6 @@ 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
@@ -220,22 +200,15 @@ 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 `change_unit_prefix` section
-
-__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-units). The setting works on the metric name and requires the new prefix for the metric. The cc-units package determines the scaling factor.
 
 # Aggregate metric values of the current interval with the `interval_aggregates` option
 
-**Note:** `interval_aggregates` works only if `num_cache_intervals` > 0 and is **experimental**
+**Note:** `interval_aggregates` works only if `num_cache_intervals` > 0
 
 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.
 

internal/metricRouter/metricCache.go

@@ -4,10 +4,10 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
@@ -16,7 +16,7 @@ type metricCachePeriod struct {
 	stopstamp   time.Time
 	numMetrics  int
 	sizeMetrics int
-	metrics     []lp.CCMessage
+	metrics     []lp.CCMetric
 }
 
 // Metric cache data structure
@@ -29,21 +29,21 @@ type metricCache struct {
 	ticker     mct.MultiChanTicker
 	tickchan   chan time.Time
 	done       chan bool
-	output     chan lp.CCMessage
+	output     chan lp.CCMetric
 	aggEngine  agg.MetricAggregator
 }
 
 type MetricCache interface {
-	Init(output chan lp.CCMessage, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error
+	Init(output chan lp.CCMetric, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error
 	Start()
-	Add(metric lp.CCMessage)
-	GetPeriod(index int) (time.Time, time.Time, []lp.CCMessage)
+	Add(metric lp.CCMetric)
+	GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric)
 	AddAggregation(name, function, condition string, tags, meta map[string]string) error
 	DeleteAggregation(name string) error
 	Close()
 }
 
-func (c *metricCache) Init(output chan lp.CCMessage, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error {
+func (c *metricCache) Init(output chan lp.CCMetric, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) error {
 	var err error = nil
 	c.done = make(chan bool)
 	c.wg = wg
@@ -55,7 +55,7 @@ func (c *metricCache) Init(output chan lp.CCMessage, ticker mct.MultiChanTicker,
 		p := new(metricCachePeriod)
 		p.numMetrics = 0
 		p.sizeMetrics = 0
-		p.metrics = make([]lp.CCMessage, 0)
+		p.metrics = make([]lp.CCMetric, 0)
 		c.intervals = append(c.intervals, p)
 	}
 
@@ -124,7 +124,7 @@ 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.CCMessage) {
+func (c *metricCache) Add(metric lp.CCMetric) {
 	if c.curPeriod >= 0 && c.curPeriod < c.numPeriods {
 		c.lock.Lock()
 		p := c.intervals[c.curPeriod]
@@ -153,10 +153,10 @@ 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.CCMessage) {
+func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric) {
 	var start time.Time = time.Now()
 	var stop time.Time = time.Now()
-	var metrics []lp.CCMessage
+	var metrics []lp.CCMetric
 	if index >= 0 && index < c.numPeriods {
 		pindex := c.curPeriod - index
 		if pindex < 0 {
@@ -168,10 +168,10 @@ func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMessage
 			metrics = c.intervals[pindex].metrics
 			//return c.intervals[pindex].startstamp, c.intervals[pindex].stopstamp, c.intervals[pindex].metrics
 		} else {
-			metrics = make([]lp.CCMessage, 0)
+			metrics = make([]lp.CCMetric, 0)
 		}
 	} else {
-		metrics = make([]lp.CCMessage, 0)
+		metrics = make([]lp.CCMetric, 0)
 	}
 	return start, stop, metrics
 }
@@ -182,7 +182,7 @@ func (c *metricCache) Close() {
 	c.done <- true
 }
 
-func NewCache(output chan lp.CCMessage, ticker mct.MultiChanTicker, wg *sync.WaitGroup, numPeriods int) (MetricCache, error) {
+func NewCache(output chan lp.CCMetric, 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

@@ -2,18 +2,17 @@ package metricRouter
 
 import (
 	"encoding/json"
-	"fmt"
 	"os"
 	"strings"
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-lib/ccMessage"
-	mp "github.com/ClusterCockpit/cc-lib/messageProcessor"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
+	units "github.com/ClusterCockpit/cc-units"
 )
 
 const ROUTER_MAX_FORWARD = 50
@@ -39,17 +38,16 @@ 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
-	MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
+	dropMetrics       map[string]bool                      // Internal map for O(1) lookup
 }
 
 // Metric router data structure
 type metricRouter struct {
 	hostname    string              // Hostname used in tags
-	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
+	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
 	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
@@ -58,15 +56,14 @@ 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, routerConfig json.RawMessage) error
-	AddCollectorInput(input chan lp.CCMessage)
-	AddReceiverInput(input chan lp.CCMessage)
-	AddOutput(output chan lp.CCMessage)
+	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)
 	Start()
 	Close()
 }
@@ -77,10 +74,10 @@ 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, routerConfig json.RawMessage) error {
-	r.outputs = make([]chan lp.CCMessage, 0)
+func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) error {
+	r.outputs = make([]chan lp.CCMetric, 0)
 	r.done = make(chan bool)
-	r.cache_input = make(chan lp.CCMessage)
+	r.cache_input = make(chan lp.CCMetric)
 	r.wg = wg
 	r.ticker = ticker
 	r.config.MaxForward = ROUTER_MAX_FORWARD
@@ -95,7 +92,15 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 	// Drop domain part of host name
 	r.hostname = strings.SplitN(hostname, `.`, 2)[0]
 
-	err = json.Unmarshal(routerConfig, &r.config)
+	// 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)
 	if err != nil {
 		cclog.ComponentError("MetricRouter", err.Error())
 		return err
@@ -114,56 +119,14 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 			r.cache.AddAggregation(agg.Name, agg.Function, agg.Condition, agg.Tags, agg.Meta)
 		}
 	}
-	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())
-		}
-	}
+	r.config.dropMetrics = make(map[string]bool)
 	for _, mname := range r.config.DropMetrics {
-		r.mp.AddDropMessagesByName(mname)
+		r.config.dropMetrics[mname] = true
 	}
-	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.CCMessage) map[string]interface{} {
+func getParamMap(point lp.CCMetric) map[string]interface{} {
 	params := make(map[string]interface{})
 	params["metric"] = point
 	params["name"] = point.Name()
@@ -181,7 +144,7 @@ func getParamMap(point lp.CCMessage) map[string]interface{} {
 }
 
 // DoAddTags adds a tag when condition is fullfiled
-func (r *metricRouter) DoAddTags(point lp.CCMessage) {
+func (r *metricRouter) DoAddTags(point lp.CCMetric) {
 	var conditionMatches bool
 	for _, m := range r.config.AddTags {
 		if m.Condition == "*" {
@@ -203,81 +166,81 @@ func (r *metricRouter) DoAddTags(point lp.CCMessage) {
 }
 
 // DoDelTags removes a tag when condition is fullfiled
-// 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)
-// 		}
-// 	}
-// }
+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)
+		}
+	}
+}
 
 // Conditional test whether a metric should be dropped
-// func (r *metricRouter) dropMetric(point lp.CCMessage) bool {
-// 	// Simple drop check
-// 	if conditionMatches, ok := r.config.dropMetrics[point.Name()]; ok {
-// 		return conditionMatches
-// 	}
+func (r *metricRouter) dropMetric(point lp.CCMetric) 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.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 {
+func (r *metricRouter) prepareUnit(point lp.CCMetric) bool {
+	if r.config.NormalizeUnits {
+		if in_unit, ok := point.GetMeta("unit"); ok {
+			u := units.NewUnit(in_unit)
+			if u.Valid() {
+				point.AddMeta("unit", u.Short())
+			}
+		}
+	}
+	if newP, ok := r.config.ChangeUnitPrefix[point.Name()]; ok {
 
-// 		newPrefix := units.NewPrefix(newP)
+		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() {
@@ -296,75 +259,59 @@ func (r *metricRouter) Start() {
 
 	// Forward takes a received metric, adds or deletes tags
 	// and forwards it to the output channels
-	// 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)
-	// 	}
+	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)
+		}
 
-	// 	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.CCMessage) {
+	coll_forward := func(p lp.CCMetric) {
 		// 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)
 		}
-		m, err := r.mp.ProcessMessage(p)
-		if err == nil && m != nil {
-			for _, o := range r.outputs {
-				o <- m
-			}
+		if !r.dropMetric(p) {
+			forward(p)
 		}
-		// 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(m)
+			r.cache.Add(p)
 		}
 	}
 
 	// Forward message received from receivers channel
-	recv_forward := func(p lp.CCMessage) {
+	recv_forward := func(p lp.CCMetric) {
 		// receive from receive manager
 		if r.config.IntervalStamp {
 			p.SetTime(r.timestamp)
 		}
-		m, err := r.mp.ProcessMessage(p)
-		if err == nil && m != nil {
-			for _, o := range r.outputs {
-				o <- m
-			}
+		if !r.dropMetric(p) {
+			forward(p)
 		}
-		// if !r.dropMetric(p) {
-		// 	forward(p)
-		// }
 	}
 
 	// Forward message received from cache channel
-	cache_forward := func(p lp.CCMessage) {
+	cache_forward := func(p lp.CCMetric) {
 		// receive from metric collector
-		m, err := r.mp.ProcessMessage(p)
-		if err == nil && m != nil {
-			for _, o := range r.outputs {
-				o <- m
-			}
+		if !r.dropMetric(p) {
+			p.AddTag(r.config.HostnameTagName, r.hostname)
+			forward(p)
 		}
 	}
 
@@ -411,17 +358,17 @@ func (r *metricRouter) Start() {
 }
 
 // AddCollectorInput adds a channel between metric collector and metric router
-func (r *metricRouter) AddCollectorInput(input chan lp.CCMessage) {
+func (r *metricRouter) AddCollectorInput(input chan lp.CCMetric) {
 	r.coll_input = input
 }
 
 // AddReceiverInput adds a channel between metric receiver and metric router
-func (r *metricRouter) AddReceiverInput(input chan lp.CCMessage) {
+func (r *metricRouter) AddReceiverInput(input chan lp.CCMetric) {
 	r.recv_input = input
 }
 
 // AddOutput adds a output channel to the metric router
-func (r *metricRouter) AddOutput(output chan lp.CCMessage) {
+func (r *metricRouter) AddOutput(output chan lp.CCMetric) {
 	r.outputs = append(r.outputs, output)
 }
 
@@ -441,9 +388,9 @@ func (r *metricRouter) Close() {
 }
 
 // New creates a new initialized metric router
-func New(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfig json.RawMessage) (MetricRouter, error) {
+func New(ticker mct.MultiChanTicker, wg *sync.WaitGroup, routerConfigFile string) (MetricRouter, error) {
 	r := new(metricRouter)
-	err := r.Init(ticker, wg, routerConfig)
+	err := r.Init(ticker, wg, routerConfigFile)
 	if err != nil {
 		return nil, err
 	}

pkg/ccLogger/cclogger.go

@@ -0,0 +1,113 @@
+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()
+}

pkg/ccMetric/README.md

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

pkg/ccMetric/ccMetric.go

@@ -0,0 +1,353 @@
+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
+	"golang.org/x/exp/maps"
+)
+
+// 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() string                                   // Return line-protocol like string
+}
+
+// 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, use_as_tag := range metaAsTags {
+		if use_as_tag {
+			if value, ok := m.GetMeta(key); ok {
+				p.AddTag(key, value)
+			}
+		}
+	}
+	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:   maps.Clone(tags),
+		meta:   maps.Clone(meta),
+		fields: make(map[string]interface{}, len(fields)),
+		tm:     tm,
+	}
+
+	// deep copy fields
+	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 {
+
+	return &ccMetric{
+		name:   other.Name(),
+		tags:   maps.Clone(other.Tags()),
+		meta:   maps.Clone(other.Meta()),
+		fields: maps.Clone(other.Fields()),
+		tm:     other.Time(),
+	}
+}
+
+// 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
+}

pkg/ccTopology/ccTopology.go

@@ -9,7 +9,7 @@ import (
 	"strconv"
 	"strings"
 
-	cclogger "github.com/ClusterCockpit/cc-lib/ccLogger"
+	cclogger "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 	"golang.org/x/exp/slices"
 )
 
@@ -296,25 +296,6 @@ func GetTypeList(topology_type string) []int {
 	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
@@ -442,22 +423,3 @@ func GetCoreHwthreads(core int) []int {
 	}
 	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/multiChanTicker.go

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

receivers/README.md

@@ -0,0 +1,32 @@
+# 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
+- [`ipmi`](./ipmiReceiver.md): Read IPMI sensor readings
+- [`redfish`](redfishReceiver.md) Use the Redfish (specification) to query thermal and power metrics
+
+## 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

@@ -0,0 +1,227 @@
+package receivers
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"net/http"
+	"strings"
+	"sync"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
+)
+
+const HTTP_RECEIVER_PORT = "8080"
+
+type HttpReceiverConfig struct {
+	Type string `json:"type"`
+	Addr string `json:"address"`
+	Port string `json:"port"`
+	Path string `json:"path"`
+
+	// Maximum amount of time to wait for the next request when keep-alives are enabled
+	// should be larger than the measurement interval to keep the connection open
+	IdleTimeout string `json:"idle_timeout"`
+	idleTimeout time.Duration
+
+	// Controls whether HTTP keep-alives are enabled. By default, keep-alives are enabled
+	KeepAlivesEnabled bool `json:"keep_alives_enabled"`
+
+	// Basic authentication
+	Username     string `json:"username"`
+	Password     string `json:"password"`
+	useBasicAuth bool
+}
+
+type HttpReceiver struct {
+	receiver
+	meta   map[string]string
+	config HttpReceiverConfig
+	server *http.Server
+	wg     sync.WaitGroup
+}
+
+func (r *HttpReceiver) Init(name string, config json.RawMessage) error {
+	r.name = fmt.Sprintf("HttpReceiver(%s)", name)
+
+	// Set default values
+	r.config.Port = HTTP_RECEIVER_PORT
+	r.config.KeepAlivesEnabled = true
+	// should be larger than the measurement interval to keep the connection open
+	r.config.IdleTimeout = "120s"
+
+	// Read config
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &r.config)
+		if err != nil {
+			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")
+	}
+
+	// Check idle timeout config
+	if len(r.config.IdleTimeout) > 0 {
+		t, err := time.ParseDuration(r.config.IdleTimeout)
+		if err == nil {
+			cclog.ComponentDebug(r.name, "idleTimeout", t)
+			r.config.idleTimeout = t
+		}
+	}
+
+	// Check basic authentication config
+	if len(r.config.Username) > 0 || len(r.config.Password) > 0 {
+		r.config.useBasicAuth = true
+	}
+	if r.config.useBasicAuth && len(r.config.Username) == 0 {
+		return errors.New("basic authentication requires username")
+	}
+	if r.config.useBasicAuth && len(r.config.Password) == 0 {
+		return errors.New("basic authentication requires password")
+	}
+
+	r.meta = map[string]string{"source": r.name}
+	p := r.config.Path
+	if !strings.HasPrefix(p, "/") {
+		p = "/" + p
+	}
+	addr := fmt.Sprintf("%s:%s", r.config.Addr, r.config.Port)
+	uri := addr + p
+	cclog.ComponentDebug(r.name, "INIT", "listen on:", uri)
+
+	// Register handler function r.ServerHttp for path p in the DefaultServeMux
+	http.HandleFunc(p, r.ServerHttp)
+
+	// Create http server
+	r.server = &http.Server{
+		Addr:        addr,
+		Handler:     nil, // handler to invoke, http.DefaultServeMux if nil
+		IdleTimeout: r.config.idleTimeout,
+	}
+	r.server.SetKeepAlivesEnabled(r.config.KeepAlivesEnabled)
+
+	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) {
+
+	// Check request method, only post method is handled
+	if req.Method != http.MethodPost {
+		http.Error(w, "Method Not Allowed", http.StatusMethodNotAllowed)
+		return
+	}
+
+	// Check basic authentication
+	if r.config.useBasicAuth {
+		username, password, ok := req.BasicAuth()
+		if !ok || username != r.config.Username || password != r.config.Password {
+			http.Error(w, "Unauthorized", http.StatusUnauthorized)
+			return
+		}
+	}
+
+	d := influx.NewDecoder(req.Body)
+	for d.Next() {
+
+		// Decode measurement name
+		measurement, err := d.Measurement()
+		if err != nil {
+			msg := "ServerHttp: Failed to decode measurement: " + err.Error()
+			cclog.ComponentError(r.name, msg)
+			http.Error(w, msg, http.StatusInternalServerError)
+			return
+		}
+
+		// Decode tags
+		tags := make(map[string]string)
+		for {
+			key, value, err := d.NextTag()
+			if err != nil {
+				msg := "ServerHttp: Failed to decode tag: " + err.Error()
+				cclog.ComponentError(r.name, msg)
+				http.Error(w, msg, http.StatusInternalServerError)
+				return
+			}
+			if key == nil {
+				break
+			}
+			tags[string(key)] = string(value)
+		}
+
+		// Decode fields
+		fields := make(map[string]interface{})
+		for {
+			key, value, err := d.NextField()
+			if err != nil {
+				msg := "ServerHttp: Failed to decode field: " + err.Error()
+				cclog.ComponentError(r.name, msg)
+				http.Error(w, msg, http.StatusInternalServerError)
+				return
+			}
+			if key == nil {
+				break
+			}
+			fields[string(key)] = value.Interface()
+		}
+
+		// Decode time stamp
+		t, err := d.Time(influx.Nanosecond, time.Time{})
+		if err != nil {
+			msg := "ServerHttp: Failed to decode time stamp: " + err.Error()
+			cclog.ComponentError(r.name, msg)
+			http.Error(w, msg, http.StatusInternalServerError)
+			return
+		}
+
+		y, _ := lp.New(
+			string(measurement),
+			tags,
+			r.meta,
+			fields,
+			t,
+		)
+
+		if r.sink != nil {
+			r.sink <- y
+		}
+	}
+
+	// Check for IO errors
+	err := d.Err()
+	if err != nil {
+		msg := "ServerHttp: Failed to decode: " + err.Error()
+		cclog.ComponentError(r.name, msg)
+		http.Error(w, msg, http.StatusInternalServerError)
+		return
+	}
+
+	w.WriteHeader(http.StatusOK)
+}
+
+func (r *HttpReceiver) Close() {
+	r.server.Shutdown(context.Background())
+}
+
+func NewHttpReceiver(name string, config json.RawMessage) (Receiver, error) {
+	r := new(HttpReceiver)
+	err := r.Init(name, config)
+	return r, err
+}

receivers/httpReceiver.md

@@ -0,0 +1,43 @@
+## `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",
+    "idle_timeout": "120s",
+    "username": "myUser",
+    "password": "myPW"
+  }
+}
+```
+
+- `type`: makes the receiver a `http` receiver
+- `address`: Listen address
+- `port`: Listen port
+- `path`: URL path for the write endpoint
+- `idle_timeout`: Maximum amount of time to wait for the next request when keep-alives are enabled should be larger than the measurement interval to keep the connection open
+- `keep_alives_enabled`: Controls whether HTTP keep-alives are enabled. By default, keep-alives are enabled.
+- `username`: username for basic authentication
+- `password`: password for basic authentication
+
+The HTTP endpoint listens to `http://<address>:<port>/<path>`
+
+### Debugging
+
+- Install [curl](https://curl.se/)
+- Use curl to send message to `http` receiver
+
+  ```bash
+  curl http://localhost:8080/write \
+  --user "myUser:myPW" \
+  --data \
+  "myMetric,hostname=myHost,type=hwthread,type-id=0,unit=Hz value=400000i 1694777161164284635
+  myMetric,hostname=myHost,type=hwthread,type-id=1,unit=Hz value=400001i 1694777161164284635"
+  ```

receivers/ipmiReceiver.go

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

receivers/ipmiReceiver.md

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

receivers/metricReceiver.go

@@ -0,0 +1,40 @@
+package receivers
+
+import (
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/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

@@ -0,0 +1,147 @@
+package receivers
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
+	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
+	meta   map[string]string
+	config NatsReceiverConfig
+}
+
+// Start subscribes to the configured NATS subject
+// Messages wil be handled by r._NatsReceive
+func (r *NatsReceiver) Start() {
+	cclog.ComponentDebug(r.name, "START")
+	r.nc.Subscribe(r.config.Subject, r._NatsReceive)
+}
+
+// _NatsReceive receives subscribed messages from the NATS server
+func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
+
+	d := influx.NewDecoderWithBytes(m.Data)
+	for d.Next() {
+
+		// Decode measurement name
+		measurement, err := d.Measurement()
+		if err != nil {
+			msg := "_NatsReceive: Failed to decode measurement: " + err.Error()
+			cclog.ComponentError(r.name, msg)
+			return
+		}
+
+		// Decode tags
+		tags := make(map[string]string)
+		for {
+			key, value, err := d.NextTag()
+			if err != nil {
+				msg := "_NatsReceive: Failed to decode tag: " + err.Error()
+				cclog.ComponentError(r.name, msg)
+				return
+			}
+			if key == nil {
+				break
+			}
+			tags[string(key)] = string(value)
+		}
+
+		// Decode fields
+		fields := make(map[string]interface{})
+		for {
+			key, value, err := d.NextField()
+			if err != nil {
+				msg := "_NatsReceive: Failed to decode field: " + err.Error()
+				cclog.ComponentError(r.name, msg)
+				return
+			}
+			if key == nil {
+				break
+			}
+			fields[string(key)] = value.Interface()
+		}
+
+		// Decode time stamp
+		t, err := d.Time(influx.Nanosecond, time.Time{})
+		if err != nil {
+			msg := "_NatsReceive: Failed to decode time: " + err.Error()
+			cclog.ComponentError(r.name, msg)
+			return
+		}
+
+		y, _ := lp.New(
+			string(measurement),
+			tags,
+			r.meta,
+			fields,
+			t,
+		)
+
+		if r.sink != nil {
+			r.sink <- y
+		}
+	}
+}
+
+// Close closes the connection to the NATS server
+func (r *NatsReceiver) Close() {
+	if r.nc != nil {
+		cclog.ComponentDebug(r.name, "CLOSE")
+		r.nc.Close()
+	}
+}
+
+// NewNatsReceiver creates a new Receiver which subscribes to messages from a NATS server
+func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
+	r := new(NatsReceiver)
+	r.name = fmt.Sprintf("NatsReceiver(%s)", name)
+
+	// Read configuration file, allow overwriting default config
+	r.config.Addr = "localhost"
+	r.config.Port = "4222"
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &r.config)
+		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")
+	}
+
+	// Set metadata
+	r.meta = map[string]string{
+		"source": r.name,
+	}
+
+	// Connect to NATS server
+	url := fmt.Sprintf("nats://%s:%s", r.config.Addr, r.config.Port)
+	cclog.ComponentDebug(r.name, "NewNatsReceiver", url, "Subject", r.config.Subject)
+	if nc, err := nats.Connect(url); err == nil {
+		r.nc = nc
+	} else {
+		r.nc = nil
+		return nil, err
+	}
+
+	return r, nil
+}

receivers/natsReceiver.md

@@ -0,0 +1,50 @@
+## `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
+
+### Debugging
+
+- Install NATS server and command line client
+- Start NATS server
+
+  ```bash
+  nats-server --net nats-server.example.org --port 4222
+  ```
+
+- Check NATS server works as expected
+
+  ```bash
+  nats --server=nats-server-db.example.org:4222 server check
+  ```
+
+- Use NATS command line client to subscribe to all messages
+
+  ```bash
+  nats --server=nats-server-db.example.org:4222 sub ">"
+  ```
+
+- Use NATS command line client to send message to NATS receiver
+
+  ```bash
+  nats --server=nats-server-db.example.org:4222 pub subject \
+  "myMetric,hostname=myHost,type=hwthread,type-id=0,unit=Hz value=400000i 1694777161164284635
+  myMetric,hostname=myHost,type=hwthread,type-id=1,unit=Hz value=400001i 1694777161164284635"
+  ```

receivers/prometheusReceiver.go

@@ -0,0 +1,122 @@
+package receivers
+
+import (
+	"bufio"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"log"
+	"net/http"
+	"strconv"
+	"strings"
+	"sync"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/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

@@ -0,0 +1,27 @@
+## `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

@@ -0,0 +1,122 @@
+package receivers
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"sync"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
+	"http":    NewHttpReceiver,
+	"ipmi":    NewIPMIReceiver,
+	"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 config.Type == "" {
+		cclog.ComponentError("ReceiveManager", "SKIP", "JSON config for receiver", name, "does not contain a receiver type")
+		return fmt.Errorf("JSON config for receiver %s does not contain a receiver type", name)
+	}
+	if _, found := AvailableReceivers[config.Type]; !found {
+		cclog.ComponentError("ReceiveManager", "SKIP", "unknown receiver type:", config.Type)
+		return fmt.Errorf("unknown receiver type: %s", config.Type)
+	}
+	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.md

@@ -0,0 +1,65 @@
+## Redfish receiver
+
+The Redfish receiver uses the [Redfish (specification)](https://www.dmtf.org/standards/redfish) to query thermal and power metrics. Thermal metrics may include various fan speeds and temperatures. Power metrics may include the current power consumption of various hardware components. It may also include the minimum, maximum and average power consumption of these components in a given time interval. The receiver will poll each configured redfish device once in a given interval. Multiple devices can be accessed in parallel to increase throughput.
+
+### Configuration structure
+
+```json
+{
+    "<redfish receiver name>": {
+        "type": "redfish",
+        "username": "<Username>",
+        "password": "<Password>",
+        "endpoint": "https://%h-bmc",
+        "exclude_metrics": [ "min_consumed_watts" ],
+        "client_config": [
+            {
+                "host_list": "n[1,2-4]"
+            },
+            {
+                "host_list": "n5",
+                "disable_power_metrics": true,
+                "disable_processor_metrics": true,
+                "disable_thermal_metrics": true
+            },
+            {
+                "host_list": "n6" ],
+                "username": "<Username 2>",
+                "password": "<Password 2>",
+                "endpoint": "https://%h-BMC",
+                "disable_sensor_metrics": true
+            }
+        ]
+    }
+}
+```
+
+Global settings:
+
+- `fanout`: Maximum number of simultaneous redfish connections (default: 64)
+- `interval`: How often the redfish power metrics should be read and send to the sink (default: 30 s)
+- `http_insecure`: Control whether a client verifies the server's certificate (default: true == do not verify server's certificate)
+- `http_timeout`: Time limit for requests made by this HTTP client (default: 10 s)
+
+Global and per redfish device settings (per redfish device settings overwrite the global settings):
+
+- `disable_power_metrics`:
+  disable collection of power metrics
+  (`/redfish/v1/Chassis/{ChassisId}/Power`)
+- `disable_processor_metrics`:
+  disable collection of processor metrics
+  (`/redfish/v1/Systems/{ComputerSystemId}/Processors/{ProcessorId}/ProcessorMetrics`)
+- `disable_sensors`:
+  disable collection of fan, power and thermal sensor metrics
+  (`/redfish/v1/Chassis/{ChassisId}/Sensors/{SensorId}`)
+- `disable_thermal_metrics`:
+  disable collection of thermal metrics
+  (`/redfish/v1/Chassis/{ChassisId}/Thermal`)
+- `exclude_metrics`: list of excluded metrics
+- `username`: User name to authenticate with
+- `password`: Password to use for authentication
+- `endpoint`: URL of the redfish service (placeholder `%h` gets replaced by the hostname)
+
+Per redfish device settings:
+
+- `host_list`: List of hosts with the same client configuration

receivers/sampleReceiver.go

@@ -0,0 +1,101 @@
+package receivers
+
+import (
+	"encoding/json"
+	"fmt"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/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
+}

router.json

@@ -1,23 +1,22 @@
 {
-    "process_messages" : {
-        "add_tag_if": [
-            {
-                "key" : "cluster",
-                "value" : "testcluster",
-                "if" : "true"
-            },
-            {
-                "key" : "test",
-                "value" : "testing",
-                "if" : "name == 'temp_package_id_0'"
-            }
-        ],
-        "delete_tag_if": [
-            {
-                "key" : "unit",
-                "if" : "true"
-            }
-        ]
-    },
+    "add_tags" : [
+        {
+            "key" : "cluster",
+            "value" : "testcluster",
+            "if" : "*"
+        },
+        {
+            "key" : "test",
+            "value" : "testing",
+            "if" : "name == 'temp_package_id_0'"
+        }
+    ],
+    "delete_tags" : [
+        {
+            "key" : "unit",
+            "value" : "*",
+            "if" : "*"
+        }
+    ],
     "interval_timestamp" : true
 }

scripts/generate_docs.sh

@@ -1,175 +0,0 @@
-#!/bin/bash -l
-
-SRCDIR="$(pwd)"
-DESTDIR="$1"
-
-if [ -z "$DESTDIR" ]; then
-    echo "Destination folder not provided"
-    exit 1
-fi
-
-
-COLLECTORS=$(find "${SRCDIR}/collectors" -name "*Metric.md")
-SINKS=$(find "${SRCDIR}/sinks"  -name "*Sink.md")
-RECEIVERS=$(find "${SRCDIR}/receivers"  -name "*Receiver.md")
-
-
-
-# Collectors
-mkdir -p "${DESTDIR}/collectors"
-for F in $COLLECTORS; do
-    echo "$F"
-    FNAME=$(basename "$F")
-    TITLE=$(grep -E "^##" "$F" | head -n 1 | sed -e 's+## ++g')
-    echo "'${TITLE//\`/}'"
-    if [ "${TITLE}" == "" ]; then continue; fi
-    rm --force "${DESTDIR}/collectors/${FNAME}"
-    cat << EOF >> "${DESTDIR}/collectors/${FNAME}"
----
-title: ${TITLE//\`/}
-description: >
-  Toplevel ${FNAME/.md/}
-categories: [cc-metric-collector]
-tags: [cc-metric-collector, Collector, ${FNAME/Metric.md/}]
-weight: 2
----
-
-EOF
-    cat "$F" >> "${DESTDIR}/collectors/${FNAME}"
-done
-
-if [ -e "${SRCDIR}/collectors/README.md" ]; then
-    cat << EOF > "${DESTDIR}/collectors/_index.md"
----
-title: cc-metric-collector's collectors
-description: Documentation of cc-metric-collector's collectors
-categories: [cc-metric-collector]
-tags: [cc-metric-collector, Collector, General]
-weight: 40
----
-
-EOF
-    cat "${SRCDIR}/collectors/README.md" >> "${DESTDIR}/collectors/_index.md"
-fi
-
-# Sinks
-mkdir -p "${DESTDIR}/sinks"
-for F in $SINKS; do
-    echo "$F"
-    FNAME=$(basename "$F")
-    TITLE=$(grep -E "^##" "$F" | head -n 1 | sed -e 's+## ++g')
-    echo "'${TITLE//\`/}'"
-    if [ "${TITLE}" == "" ]; then continue; fi
-    rm --force "${DESTDIR}/sinks/${FNAME}"
-    cat << EOF >> "${DESTDIR}/sinks/${FNAME}"
----
-title: ${TITLE//\`/}
-description: >
-  Toplevel ${FNAME/.md/}
-categories: [cc-metric-collector]
-tags: [cc-metric-collector, Sink, ${FNAME/Sink.md/}]
-weight: 2
----
-
-EOF
-    cat "$F" >> "${DESTDIR}/sinks/${FNAME}"
-done
-
-if [ -e "${SRCDIR}/collectors/README.md" ]; then
-    cat << EOF > "${DESTDIR}/sinks/_index.md"
----
-title: cc-metric-collector's sinks
-description: Documentation of cc-metric-collector's sinks
-categories: [cc-metric-collector]
-tags: [cc-metric-collector, Sink, General]
-weight: 40
----
-
-EOF
-    cat "${SRCDIR}/sinks/README.md" >> "${DESTDIR}/sinks/_index.md"
-fi
-
-
-# Receivers
-mkdir -p "${DESTDIR}/receivers"
-for F in $RECEIVERS; do
-    echo "$F"
-    FNAME=$(basename "$F")
-    TITLE=$(grep -E "^##" "$F" | head -n 1 | sed -e 's+## ++g')
-    echo "'${TITLE//\`/}'"
-    if [ "${TITLE}" == "" ]; then continue; fi
-    rm --force "${DESTDIR}/receivers/${FNAME}"
-    cat << EOF >> "${DESTDIR}/receivers/${FNAME}"
----
-title: ${TITLE//\`/}
-description: >
-  Toplevel ${FNAME/.md/}
-categories: [cc-metric-collector]
-tags: [cc-metric-collector, Receiver, ${FNAME/Receiver.md/}]
-weight: 2
----
-
-EOF
-    cat "$F" >> "${DESTDIR}/receivers/${FNAME}"
-done
-
-if [ -e "${SRCDIR}/receivers/README.md" ]; then
-    cat << EOF > "${DESTDIR}/receivers/_index.md"
----
-title: cc-metric-collector's receivers
-description: Documentation of cc-metric-collector's receivers
-categories: [cc-metric-collector]
-tags: [cc-metric-collector, Receiver, General]
-weight: 40
----
-
-EOF
-    cat "${SRCDIR}/receivers/README.md" >> "${DESTDIR}/receivers/_index.md"
-fi
-
-mkdir -p "${DESTDIR}/internal/metricRouter"
-if [ -e "${SRCDIR}/internal/metricRouter/README.md" ]; then
-    cat << EOF > "${DESTDIR}/internal/metricRouter/_index.md"
----
-title: cc-metric-collector's router
-description: Documentation of cc-metric-collector's router
-categories: [cc-metric-collector]
-tags: [cc-metric-collector, Router, General]
-weight: 40
----
-
-EOF
-    cat "${SRCDIR}/internal/metricRouter/README.md" >> "${DESTDIR}/internal/metricRouter/_index.md"
-fi
-
-if [ -e "${SRCDIR}/README.md" ]; then
-    cat << EOF > "${DESTDIR}/_index.md"
----
-title: cc-metric-collector
-description: Documentation of cc-metric-collector
-categories: [cc-metric-collector]
-tags: [cc-metric-collector, General]
-weight: 40
----
-
-EOF
-    cat "${SRCDIR}/README.md" >> "${DESTDIR}/_index.md"
-    sed -i -e 's+README.md+_index.md+g' "${DESTDIR}/_index.md"
-fi
-
-
-mkdir -p "${DESTDIR}/pkg/messageProcessor"
-if [ -e "${SRCDIR}/pkg/messageProcessor/README.md" ]; then
-    cat << EOF > "${DESTDIR}/pkg/messageProcessor/_index.md"
----
-title: cc-metric-collector's message processor
-description: Documentation of cc-metric-collector's message processor
-categories: [cc-metric-collector]
-tags: [cc-metric-collector, Message Processor]
-weight: 40
----
-
-EOF
-    cat "${SRCDIR}/pkg/messageProcessor/README.md" >> "${DESTDIR}/pkg/messageProcessor/_index.md"
-fi
-

sinks/README.md

@@ -0,0 +1,108 @@
+# CCMetric sinks
+
+This folder contains the SinkManager and sink implementations for the cc-metric-collector.
+
+# Available sinks:
+- [`stdout`](./stdoutSink.md): Print all metrics to `stdout`, `stderr` or a file
+- [`http`](./httpSink.md): Send metrics to an HTTP server as POST requests
+- [`influxdb`](./influxSink.md): Send metrics to an [InfluxDB](https://www.influxdata.com/products/influxdb/) database
+- [`influxasync`](./influxAsyncSink.md): Send metrics to an [InfluxDB](https://www.influxdata.com/products/influxdb/) database with non-blocking write API
+- [`nats`](./natsSink.md): Publish metrics to the [NATS](https://nats.io/) network overlay system
+- [`ganglia`](./gangliaSink.md): Publish metrics in the [Ganglia Monitoring System](http://ganglia.info/) using the `gmetric` CLI tool
+- [`libganglia`](./libgangliaSink.md): Publish metrics in the [Ganglia Monitoring System](http://ganglia.info/) directly using `libganglia.so`
+- [`prometeus`](./prometheusSink.md): Publish metrics for the [Prometheus Monitoring System](https://prometheus.io/)
+
+# Configuration
+
+The configuration file for the sinks is a list of configurations. The `type` field in each specifies which sink to initialize.
+
+```json
+[
+  "mystdout" : {
+    "type" : "stdout",
+    "meta_as_tags" : [
+    	"unit"
+    ]
+  },
+  "metricstore" : {
+    "type" : "http",
+    "host" : "localhost",
+    "port" : "4123",
+    "database" : "ccmetric",
+    "password" : "<jwt token>"
+  }
+]
+```
+
+
+
+
+# Contributing own sinks
+A sink contains five functions and is derived from the type `sink`:
+* `Init(name string, config json.RawMessage) error`
+* `Write(point CCMetric) error`
+* `Flush() error`
+* `Close()`
+* `New<Typename>(name string, config json.RawMessage) (Sink, error)` (calls the `Init()` function)
+
+The data structures should be set up in `Init()` like opening a file or server connection. The `Write()` function writes/sends the data. For non-blocking sinks, the `Flush()` method tells the sink to drain its internal buffers. The `Close()` function should tear down anything created in `Init()`.
+
+Finally, the sink needs to be registered in the `sinkManager.go`. There is a list of sinks called `AvailableSinks` which is a map (`sink_type_string` -> `pointer to sink interface`). Add a new entry with a descriptive name and the new sink.
+
+## Sample sink
+
+```go
+package sinks
+
+import (
+	"encoding/json"
+	"log"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+)
+
+type SampleSinkConfig struct {
+	defaultSinkConfig  // defines JSON tags for 'name' and 'meta_as_tags'
+}
+
+type SampleSink struct {
+	sink              // declarate 'name' and 'meta_as_tags'
+	config StdoutSinkConfig // entry point to the SampleSinkConfig
+}
+
+// Initialize the sink by giving it a name and reading in the config JSON
+func (s *SampleSink) Init(name string, config json.RawMessage) error {
+	s.name = fmt.Sprintf("SampleSink(%s)", name)   // Always specify a name here
+  // Read in the config JSON
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// Code to submit a single CCMetric to the sink
+func (s *SampleSink) Write(point lp.CCMetric) error {
+	log.Print(point)
+	return nil
+}
+
+// If the sink uses batched sends internally, you can tell to flush its buffers
+func (s *SampleSink) Flush() error {
+	return nil
+}
+
+
+// Close sink: close network connection, close files, close libraries, ...
+func (s *SampleSink) Close() {}
+
+
+// New function to create a new instance of the sink
+func NewSampleSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(SampleSink)
+	err := s.Init(name, config)
+	return s, err
+}
+
+```

sinks/gangliaCommon.go

@@ -0,0 +1,269 @@
+package sinks
+
+import (
+	"fmt"
+	"strings"
+
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+func GangliaMetricName(point lp.CCMetric) string {
+	name := point.Name()
+	metricType, typeOK := point.GetTag("type")
+	metricTid, tidOk := point.GetTag("type-id")
+	gangliaType := metricType + metricTid
+	if strings.Contains(name, metricType) && tidOk {
+		name = strings.Replace(name, metricType, gangliaType, -1)
+	} else if typeOK && tidOk {
+		name = metricType + metricTid + "_" + name
+	} else if point.HasTag("device") {
+		device, _ := point.GetTag("device")
+		name = name + "_" + device
+	}
+
+	return name
+}
+
+func GangliaMetricRename(name string) string {
+	if name == "net_bytes_in" {
+		return "bytes_in"
+	} else if name == "net_bytes_out" {
+		return "bytes_out"
+	} else if name == "net_pkts_in" {
+		return "pkts_in"
+	} else if name == "net_pkts_out" {
+		return "pkts_out"
+	} else if name == "cpu_iowait" {
+		return "cpu_wio"
+	}
+	return name
+}
+
+func GangliaSlopeType(point lp.CCMetric) uint {
+	name := point.Name()
+	if name == "mem_total" || name == "swap_total" {
+		return 0
+	}
+	return 3
+}
+
+const DEFAULT_GANGLIA_METRIC_TMAX = 300
+const DEFAULT_GANGLIA_METRIC_SLOPE = "both"
+
+type GangliaMetric struct {
+	Name  string
+	Type  string
+	Slope string
+	Tmax  int
+	Unit  string
+}
+
+type GangliaMetricGroup struct {
+	Name    string
+	Metrics []GangliaMetric
+}
+
+var CommonGangliaMetrics = []GangliaMetricGroup{
+	{
+		Name: "memory",
+		Metrics: []GangliaMetric{
+			{"mem_total", "float", "zero", 1200, "KB"},
+			{"swap_total", "float", "zero", 1200, "KB"},
+			{"mem_free", "float", "both", 180, "KB"},
+			{"mem_shared", "float", "both", 180, "KB"},
+			{"mem_buffers", "float", "both", 180, "KB"},
+			{"mem_cached", "float", "both", 180, "KB"},
+			{"swap_free", "float", "both", 180, "KB"},
+			{"mem_sreclaimable", "float", "both", 180, "KB"},
+			{"mem_slab", "float", "both", 180, "KB"},
+		},
+	},
+	{
+		Name: "cpu",
+		Metrics: []GangliaMetric{
+			{"cpu_num", "uint32", "zero", 1200, "CPUs"},
+			{"cpu_speed", "uint32", "zero", 1200, "MHz"},
+			{"cpu_user", "float", "both", 90, "%"},
+			{"cpu_nice", "float", "both", 90, "%"},
+			{"cpu_system", "float", "both", 90, "%"},
+			{"cpu_idle", "float", "both", 3800, "%"},
+			{"cpu_aidle", "float", "both", 90, "%"},
+			{"cpu_wio", "float", "both", 90, "%"},
+			{"cpu_intr", "float", "both", 90, "%"},
+			{"cpu_sintr", "float", "both", 90, "%"},
+			{"cpu_steal", "float", "both", 90, "%"},
+			{"cpu_guest", "float", "both", 90, "%"},
+			{"cpu_gnice", "float", "both", 90, "%"},
+		},
+	},
+	{
+		Name: "load",
+		Metrics: []GangliaMetric{
+			{"load_one", "float", "both", 70, ""},
+			{"load_five", "float", "both", 325, ""},
+			{"load_fifteen", "float", "both", 950, ""},
+		},
+	},
+	{
+		Name: "disk",
+		Metrics: []GangliaMetric{
+			{"disk_total", "double", "both", 1200, "GB"},
+			{"disk_free", "double", "both", 180, "GB"},
+			{"part_max_used", "float", "both", 180, "%"},
+		},
+	},
+	{
+		Name: "network",
+		Metrics: []GangliaMetric{
+			{"bytes_out", "float", "both", 300, "bytes/sec"},
+			{"bytes_in", "float", "both", 300, "bytes/sec"},
+			{"pkts_in", "float", "both", 300, "packets/sec"},
+			{"pkts_out", "float", "both", 300, "packets/sec"},
+		},
+	},
+	{
+		Name: "process",
+		Metrics: []GangliaMetric{
+			{"proc_run", "uint32", "both", 950, ""},
+			{"proc_total", "uint32", "both", 950, ""},
+		},
+	},
+	{
+		Name: "system",
+		Metrics: []GangliaMetric{
+			{"boottime", "uint32", "zero", 1200, "s"},
+			{"sys_clock", "uint32", "zero", 1200, "s"},
+			{"machine_type", "string", "zero", 1200, ""},
+			{"os_name", "string", "zero", 1200, ""},
+			{"os_release", "string", "zero", 1200, ""},
+			{"mtu", "uint32", "both", 1200, ""},
+		},
+	},
+}
+
+type GangliaMetricConfig struct {
+	Type  string
+	Slope string
+	Tmax  int
+	Unit  string
+	Group string
+	Value string
+	Name  string
+}
+
+func GetCommonGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
+	mname := GangliaMetricRename(point.Name())
+	if oldname, ok := point.GetMeta("oldname"); ok {
+		mname = GangliaMetricRename(oldname)
+	}
+	for _, group := range CommonGangliaMetrics {
+		for _, metric := range group.Metrics {
+			if metric.Name == mname {
+				valueStr := ""
+				value, ok := point.GetField("value")
+				if ok {
+					switch real := value.(type) {
+					case float64:
+						valueStr = fmt.Sprintf("%f", real)
+					case float32:
+						valueStr = fmt.Sprintf("%f", real)
+					case int64:
+						valueStr = fmt.Sprintf("%d", real)
+					case int32:
+						valueStr = fmt.Sprintf("%d", real)
+					case int:
+						valueStr = fmt.Sprintf("%d", real)
+					case uint64:
+						valueStr = fmt.Sprintf("%d", real)
+					case uint32:
+						valueStr = fmt.Sprintf("%d", real)
+					case uint:
+						valueStr = fmt.Sprintf("%d", real)
+					case string:
+						valueStr = real
+					default:
+					}
+				}
+				return GangliaMetricConfig{
+					Group: group.Name,
+					Type:  metric.Type,
+					Slope: metric.Slope,
+					Tmax:  metric.Tmax,
+					Unit:  metric.Unit,
+					Value: valueStr,
+					Name:  GangliaMetricRename(mname),
+				}
+			}
+		}
+	}
+	return GangliaMetricConfig{
+		Group: "",
+		Type:  "",
+		Slope: "",
+		Tmax:  0,
+		Unit:  "",
+		Value: "",
+		Name:  "",
+	}
+}
+
+func GetGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
+	mname := GangliaMetricRename(point.Name())
+	if oldname, ok := point.GetMeta("oldname"); ok {
+		mname = GangliaMetricRename(oldname)
+	}
+	group := ""
+	if g, ok := point.GetMeta("group"); ok {
+		group = g
+	}
+	unit := ""
+	if u, ok := point.GetMeta("unit"); ok {
+		unit = u
+	}
+	valueType := "double"
+	valueStr := ""
+	value, ok := point.GetField("value")
+	if ok {
+		switch real := value.(type) {
+		case float64:
+			valueStr = fmt.Sprintf("%f", real)
+			valueType = "double"
+		case float32:
+			valueStr = fmt.Sprintf("%f", real)
+			valueType = "float"
+		case int64:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "int32"
+		case int32:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "int32"
+		case int:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "int32"
+		case uint64:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "uint32"
+		case uint32:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "uint32"
+		case uint:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "uint32"
+		case string:
+			valueStr = real
+			valueType = "string"
+		default:
+			valueType = "invalid"
+		}
+	}
+
+	return GangliaMetricConfig{
+		Group: group,
+		Type:  valueType,
+		Slope: DEFAULT_GANGLIA_METRIC_SLOPE,
+		Tmax:  DEFAULT_GANGLIA_METRIC_TMAX,
+		Unit:  unit,
+		Value: valueStr,
+		Name:  GangliaMetricRename(mname),
+	}
+}

sinks/gangliaSink.go

@@ -0,0 +1,126 @@
+package sinks
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"strings"
+
+	//	"time"
+	"os/exec"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+const GMETRIC_EXEC = `gmetric`
+const GMETRIC_CONFIG = `/etc/ganglia/gmond.conf`
+
+type GangliaSinkConfig struct {
+	defaultSinkConfig
+	GmetricPath     string `json:"gmetric_path,omitempty"`
+	GmetricConfig   string `json:"gmetric_config,omitempty"`
+	AddGangliaGroup bool   `json:"add_ganglia_group,omitempty"`
+	AddTagsAsDesc   bool   `json:"add_tags_as_desc,omitempty"`
+	ClusterName     string `json:"cluster_name,omitempty"`
+	AddTypeToName   bool   `json:"add_type_to_name,omitempty"`
+	AddUnits        bool   `json:"add_units,omitempty"`
+}
+
+type GangliaSink struct {
+	sink
+	gmetric_path   string
+	gmetric_config string
+	config         GangliaSinkConfig
+}
+
+func (s *GangliaSink) Write(point lp.CCMetric) error {
+	var err error = nil
+	//var tagsstr []string
+	var argstr []string
+
+	// Get metric config (type, value, ... in suitable format)
+	conf := GetCommonGangliaConfig(point)
+	if len(conf.Type) == 0 {
+		conf = GetGangliaConfig(point)
+	}
+	if len(conf.Type) == 0 {
+		return fmt.Errorf("metric %q (Ganglia name %q) has no 'value' field", point.Name(), conf.Name)
+	}
+
+	if s.config.AddGangliaGroup {
+		argstr = append(argstr, fmt.Sprintf("--group=%s", conf.Group))
+	}
+	if s.config.AddUnits && len(conf.Unit) > 0 {
+		argstr = append(argstr, fmt.Sprintf("--units=%s", conf.Unit))
+	}
+
+	if len(s.config.ClusterName) > 0 {
+		argstr = append(argstr, fmt.Sprintf("--cluster=%s", s.config.ClusterName))
+	}
+	// if s.config.AddTagsAsDesc && len(tagsstr) > 0 {
+	// 	argstr = append(argstr, fmt.Sprintf("--desc=%q", strings.Join(tagsstr, ",")))
+	// }
+	if len(s.gmetric_config) > 0 {
+		argstr = append(argstr, fmt.Sprintf("--conf=%s", s.gmetric_config))
+	}
+	if s.config.AddTypeToName {
+		argstr = append(argstr, fmt.Sprintf("--name=%s", GangliaMetricName(point)))
+	} else {
+		argstr = append(argstr, fmt.Sprintf("--name=%s", conf.Name))
+	}
+	argstr = append(argstr, fmt.Sprintf("--slope=%s", conf.Slope))
+	argstr = append(argstr, fmt.Sprintf("--value=%s", conf.Value))
+	argstr = append(argstr, fmt.Sprintf("--type=%s", conf.Type))
+	argstr = append(argstr, fmt.Sprintf("--tmax=%d", conf.Tmax))
+
+	cclog.ComponentDebug(s.name, s.gmetric_path, strings.Join(argstr, " "))
+	command := exec.Command(s.gmetric_path, argstr...)
+	command.Wait()
+	_, err = command.Output()
+	return err
+}
+
+func (s *GangliaSink) Flush() error {
+	return nil
+}
+
+func (s *GangliaSink) Close() {
+}
+
+func NewGangliaSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(GangliaSink)
+	s.name = fmt.Sprintf("GangliaSink(%s)", name)
+	s.config.AddTagsAsDesc = false
+	s.config.AddGangliaGroup = false
+	if len(config) > 0 {
+		d := json.NewDecoder(bytes.NewReader(config))
+		d.DisallowUnknownFields()
+		if err := d.Decode(&s.config); err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+	s.gmetric_path = ""
+	s.gmetric_config = ""
+	if len(s.config.GmetricPath) > 0 {
+		p, err := exec.LookPath(s.config.GmetricPath)
+		if err == nil {
+			s.gmetric_path = p
+		}
+	}
+	if len(s.gmetric_path) == 0 {
+		p, err := exec.LookPath(string(GMETRIC_EXEC))
+		if err == nil {
+			s.gmetric_path = p
+		}
+	}
+	if len(s.gmetric_path) == 0 {
+		return nil, errors.New("cannot find executable 'gmetric'")
+	}
+	if len(s.config.GmetricConfig) > 0 {
+		s.gmetric_config = s.config.GmetricConfig
+	}
+	return s, nil
+}

sinks/gangliaSink.md

@@ -0,0 +1,21 @@
+## `ganglia` sink
+
+The `ganglia` sink uses the `gmetric` tool of the [Ganglia Monitoring System](http://ganglia.info/) to submit the metrics
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "ganglia",
+    "meta_as_tags" : true,
+    "gmetric_path" : "/path/to/gmetric",
+    "add_ganglia_group" : true
+  }
+}
+```
+
+- `type`: makes the sink an `ganglia` sink
+- `meta_as_tags`: print all meta information as tags in the output (optional)
+- `gmetric_path`: Path to `gmetric` executable (optional). If not given, the sink searches in `$PATH` for `gmetric`.
+- `add_ganglia_group`: Add `--group=X` based on meta information to the `gmetric` call. Some old versions of `gmetric` do not support the `--group` option. 

sinks/httpSink.go

@@ -0,0 +1,350 @@
+package sinks
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"net/http"
+	"sync"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
+	"golang.org/x/exp/slices"
+)
+
+type HttpSinkConfig struct {
+	defaultSinkConfig
+
+	// The full URL of the endpoint
+	URL string `json:"url"`
+
+	// JSON web tokens for authentication (Using the *Bearer* scheme)
+	JWT string `json:"jwt,omitempty"`
+
+	// Basic authentication
+	Username     string `json:"username"`
+	Password     string `json:"password"`
+	useBasicAuth bool
+
+	// time limit for requests made by the http client
+	Timeout string `json:"timeout,omitempty"`
+	timeout time.Duration
+
+	// Maximum amount of time an idle (keep-alive) connection will remain idle before closing itself
+	// should be larger than the measurement interval to keep the connection open
+	IdleConnTimeout string `json:"idle_connection_timeout,omitempty"`
+	idleConnTimeout time.Duration
+
+	// Batch all writes arriving in during this duration
+	// (default '5s', batching can be disabled by setting it to 0)
+	FlushDelay string `json:"flush_delay,omitempty"`
+	flushDelay time.Duration
+
+	// Maximum number of retries to connect to the http server (default: 3)
+	MaxRetries int `json:"max_retries,omitempty"`
+
+	// Timestamp precision
+	Precision string `json:"precision,omitempty"`
+}
+
+type key_value_pair struct {
+	key   string
+	value string
+}
+
+type HttpSink struct {
+	sink
+	client *http.Client
+	// influx line protocol encoder
+	encoder influx.Encoder
+	// List of tags and meta data tags which should be used as tags
+	extended_tag_list []key_value_pair
+	// Flush() runs in another goroutine and accesses the influx line protocol encoder,
+	// so this encoderLock has to protect the encoder
+	encoderLock sync.Mutex
+
+	// timer to run Flush()
+	flushTimer *time.Timer
+	// Lock to assure that only one timer is running at a time
+	timerLock sync.Mutex
+
+	config HttpSinkConfig
+}
+
+// Write sends metric m as http message
+func (s *HttpSink) Write(m lp.CCMetric) error {
+
+	// Lock for encoder usage
+	s.encoderLock.Lock()
+
+	// Encode measurement name
+	s.encoder.StartLine(m.Name())
+
+	// copy tags and meta data which should be used as tags
+	s.extended_tag_list = s.extended_tag_list[:0]
+	for key, value := range m.Tags() {
+		s.extended_tag_list =
+			append(
+				s.extended_tag_list,
+				key_value_pair{
+					key:   key,
+					value: value,
+				},
+			)
+	}
+	for _, key := range s.config.MetaAsTags {
+		if value, ok := m.GetMeta(key); ok {
+			s.extended_tag_list =
+				append(
+					s.extended_tag_list,
+					key_value_pair{
+						key:   key,
+						value: value,
+					},
+				)
+		}
+	}
+
+	// Encode tags (they musts be in lexical order)
+	slices.SortFunc(
+		s.extended_tag_list,
+		func(a key_value_pair, b key_value_pair) int {
+			if a.key < b.key {
+				return -1
+			}
+			if a.key > b.key {
+				return +1
+			}
+			return 0
+		},
+	)
+	for i := range s.extended_tag_list {
+		s.encoder.AddTag(
+			s.extended_tag_list[i].key,
+			s.extended_tag_list[i].value,
+		)
+	}
+
+	// Encode fields
+	for key, value := range m.Fields() {
+		s.encoder.AddField(key, influx.MustNewValue(value))
+	}
+
+	// Encode time stamp
+	s.encoder.EndLine(m.Time())
+
+	// Check for encoder errors
+	err := s.encoder.Err()
+
+	// Unlock encoder usage
+	s.encoderLock.Unlock()
+
+	// Check that encoding worked
+	if err != nil {
+		return fmt.Errorf("encoding failed: %v", err)
+	}
+
+	if s.config.flushDelay == 0 {
+
+		// Directly flush if no flush delay is configured
+		return s.Flush()
+	} else if s.timerLock.TryLock() {
+
+		// Setup flush timer when flush delay is configured
+		// and no other timer is already running
+		if s.flushTimer != nil {
+
+			// Restarting existing flush timer
+			cclog.ComponentDebug(s.name, "Write(): Restarting flush timer")
+			s.flushTimer.Reset(s.config.flushDelay)
+		} else {
+
+			// Creating and starting flush timer
+			cclog.ComponentDebug(s.name, "Write(): Starting new flush timer")
+			s.flushTimer = time.AfterFunc(
+				s.config.flushDelay,
+				func() {
+					defer s.timerLock.Unlock()
+					cclog.ComponentDebug(s.name, "Starting flush triggered by flush timer")
+					if err := s.Flush(); err != nil {
+						cclog.ComponentError(s.name, "Flush triggered by flush timer: flush failed:", err)
+					}
+				})
+		}
+	}
+
+	return nil
+}
+
+// Flush sends all metrics stored in encoder to HTTP server
+func (s *HttpSink) Flush() error {
+
+	// Lock for encoder usage
+	// Own lock for as short as possible: the time it takes to clone the buffer.
+	s.encoderLock.Lock()
+
+	buf := slices.Clone(s.encoder.Bytes())
+	s.encoder.Reset()
+
+	// Unlock encoder usage
+	s.encoderLock.Unlock()
+
+	if len(buf) == 0 {
+		return nil
+	}
+
+	cclog.ComponentDebug(s.name, "Flush(): Flushing")
+
+	var res *http.Response
+	for i := 0; i < s.config.MaxRetries; i++ {
+		// Create new request to send buffer
+		req, err := http.NewRequest(http.MethodPost, s.config.URL, bytes.NewReader(buf))
+		if err != nil {
+			cclog.ComponentError(s.name, "Flush(): Failed to create HTTP request:", err)
+			return err
+		}
+
+		// Set authorization header
+		if len(s.config.JWT) != 0 {
+			req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", s.config.JWT))
+		}
+
+		// Set basic authentication
+		if s.config.useBasicAuth {
+			req.SetBasicAuth(s.config.Username, s.config.Password)
+		}
+
+		// Do request
+		res, err = s.client.Do(req)
+		if err != nil {
+			cclog.ComponentError(s.name, "Flush(): transport/tcp error:", err)
+			// Wait between retries
+			time.Sleep(time.Duration(i+1) * (time.Second / 2))
+			continue
+		}
+
+		break
+	}
+
+	if res == nil {
+		return errors.New("flush failed due to repeated errors")
+	}
+
+	// Handle application errors
+	if res.StatusCode != http.StatusOK {
+		err := errors.New(res.Status)
+		cclog.ComponentError(s.name, "Flush(): Application error:", err)
+		return err
+	}
+
+	return nil
+}
+
+func (s *HttpSink) Close() {
+	cclog.ComponentDebug(s.name, "Closing HTTP connection")
+
+	// Stop existing timer and immediately flush
+	if s.flushTimer != nil {
+		if ok := s.flushTimer.Stop(); ok {
+			s.timerLock.Unlock()
+		}
+	}
+
+	// Flush
+	if err := s.Flush(); err != nil {
+		cclog.ComponentError(s.name, "Close(): Flush failed:", err)
+	}
+
+	s.client.CloseIdleConnections()
+}
+
+// NewHttpSink creates a new http sink
+func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(HttpSink)
+	// Set default values
+	s.name = fmt.Sprintf("HttpSink(%s)", name)
+	// should be larger than the measurement interval to keep the connection open
+	s.config.IdleConnTimeout = "120s"
+	s.config.Timeout = "5s"
+	s.config.FlushDelay = "5s"
+	s.config.MaxRetries = 3
+	s.config.Precision = "ns"
+	cclog.ComponentDebug(s.name, "Init()")
+
+	// Read config
+	if len(config) > 0 {
+		d := json.NewDecoder(bytes.NewReader(config))
+		d.DisallowUnknownFields()
+		if err := d.Decode(&s.config); err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+	if len(s.config.URL) == 0 {
+		return nil, errors.New("`url` config option is required for HTTP sink")
+	}
+
+	// Check basic authentication config
+	if len(s.config.Username) > 0 || len(s.config.Password) > 0 {
+		s.config.useBasicAuth = true
+	}
+	if s.config.useBasicAuth && len(s.config.Username) == 0 {
+		return nil, errors.New("basic authentication requires username")
+	}
+	if s.config.useBasicAuth && len(s.config.Password) == 0 {
+		return nil, errors.New("basic authentication requires password")
+	}
+
+	if len(s.config.IdleConnTimeout) > 0 {
+		t, err := time.ParseDuration(s.config.IdleConnTimeout)
+		if err == nil {
+			cclog.ComponentDebug(s.name, "Init(): idleConnTimeout", t)
+			s.config.idleConnTimeout = t
+		}
+	}
+	if len(s.config.Timeout) > 0 {
+		t, err := time.ParseDuration(s.config.Timeout)
+		if err == nil {
+			s.config.timeout = t
+			cclog.ComponentDebug(s.name, "Init(): timeout", t)
+		}
+	}
+	if len(s.config.FlushDelay) > 0 {
+		t, err := time.ParseDuration(s.config.FlushDelay)
+		if err == nil {
+			s.config.flushDelay = t
+			cclog.ComponentDebug(s.name, "Init(): flushDelay", t)
+		}
+	}
+	precision := influx.Nanosecond
+	if len(s.config.Precision) > 0 {
+		switch s.config.Precision {
+		case "s":
+			precision = influx.Second
+		case "ms":
+			precision = influx.Millisecond
+		case "us":
+			precision = influx.Microsecond
+		case "ns":
+			precision = influx.Nanosecond
+		}
+	}
+
+	// Create http client
+	s.client = &http.Client{
+		Transport: &http.Transport{
+			MaxIdleConns:    1, // We will only ever talk to one host.
+			IdleConnTimeout: s.config.idleConnTimeout,
+		},
+		Timeout: s.config.timeout,
+	}
+
+	// Configure influx line protocol encoder
+	s.encoder.SetPrecision(precision)
+	s.extended_tag_list = make([]key_value_pair, 0)
+
+	return s, nil
+}

sinks/httpSink.md

@@ -0,0 +1,42 @@
+## `http` sink
+
+The `http` sink uses POST requests to a HTTP server to submit the metrics in the InfluxDB line-protocol format. It uses JSON web tokens for authentification. The sink creates batches of metrics before sending, to reduce the HTTP traffic.
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "http",
+    "meta_as_tags" : [
+      "meta-key"
+    ],
+    "url" : "https://my-monitoring.example.com:1234/api/write",
+    "jwt" : "blabla.blabla.blabla",
+    "username": "myUser",
+    "password": "myPW",
+    "timeout": "5s",
+    "idle_connection_timeout" : "5s",
+    "flush_delay": "2s",
+    "batch_size": 1000,
+    "precision": "s"
+  }
+}
+```
+
+- `type`: makes the sink an `http` sink
+- `meta_as_tags`: Move specific meta information to the tags in the output (optional)
+- `url`: The full URL of the endpoint
+- `jwt`: JSON web tokens for authentication (Using the *Bearer* scheme)
+- `username`: username for basic authentication
+- `password`: password for basic authentication
+- `timeout`: General timeout for the HTTP client (default '5s')
+- `max_retries`: Maximum number of retries to connect to the http server
+- `idle_connection_timeout`: Timeout for idle connections (default '120s'). Should be larger than the measurement interval to keep the connection open
+- `flush_delay`: Batch all writes arriving in during this duration (default '1s', batching can be disabled by setting it to 0)
+- `batch_size`: Maximal batch size. If `batch_size` is reached before the end of `flush_delay`, the metrics are sent without further delay
+- `precision`: Precision of the timestamp. Valid values are 's', 'ms', 'us' and 'ns'. (default is 'ns')
+
+### Using HttpSink for communication with cc-metric-store
+
+The cc-metric-store only accepts metrics with a timestamp precision in seconds, so it is required to set `"precision": "s"`.

sinks/influxAsyncSink.go

@@ -0,0 +1,242 @@
+package sinks
+
+import (
+	"bytes"
+	"context"
+	"crypto/tls"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
+	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
+	influxdb2ApiHttp "github.com/influxdata/influxdb-client-go/v2/api/http"
+)
+
+type InfluxAsyncSinkConfig struct {
+	defaultSinkConfig
+	Host         string `json:"host,omitempty"`
+	Port         string `json:"port,omitempty"`
+	Database     string `json:"database,omitempty"`
+	User         string `json:"user,omitempty"`
+	Password     string `json:"password,omitempty"`
+	Organization string `json:"organization,omitempty"`
+	SSL          bool   `json:"ssl,omitempty"`
+	// Maximum number of points sent to server in single request. Default 5000
+	BatchSize uint `json:"batch_size,omitempty"`
+	// Interval, in ms, in which is buffer flushed if it has not been already written (by reaching batch size) . Default 1000ms
+	FlushInterval         uint   `json:"flush_interval,omitempty"`
+	InfluxRetryInterval   string `json:"retry_interval,omitempty"`
+	InfluxExponentialBase uint   `json:"retry_exponential_base,omitempty"`
+	InfluxMaxRetries      uint   `json:"max_retries,omitempty"`
+	InfluxMaxRetryTime    string `json:"max_retry_time,omitempty"`
+	CustomFlushInterval   string `json:"custom_flush_interval,omitempty"`
+	MaxRetryAttempts      uint   `json:"max_retry_attempts,omitempty"`
+}
+
+type InfluxAsyncSink struct {
+	sink
+	client              influxdb2.Client
+	writeApi            influxdb2Api.WriteAPI
+	errors              <-chan error
+	config              InfluxAsyncSinkConfig
+	influxRetryInterval uint
+	influxMaxRetryTime  uint
+	customFlushInterval time.Duration
+	flushTimer          *time.Timer
+}
+
+func (s *InfluxAsyncSink) connect() error {
+	var auth string
+	var uri string
+	if s.config.SSL {
+		uri = fmt.Sprintf("https://%s:%s", s.config.Host, s.config.Port)
+	} else {
+		uri = fmt.Sprintf("http://%s:%s", s.config.Host, s.config.Port)
+	}
+	if len(s.config.User) == 0 {
+		auth = s.config.Password
+	} else {
+		auth = fmt.Sprintf("%s:%s", s.config.User, s.config.Password)
+	}
+	cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
+	clientOptions := influxdb2.DefaultOptions()
+	if s.config.BatchSize != 0 {
+		cclog.ComponentDebug(s.name, "Batch size", s.config.BatchSize)
+		clientOptions.SetBatchSize(s.config.BatchSize)
+	}
+	if s.config.FlushInterval != 0 {
+		cclog.ComponentDebug(s.name, "Flush interval", s.config.FlushInterval)
+		clientOptions.SetFlushInterval(s.config.FlushInterval)
+	}
+	if s.influxRetryInterval != 0 {
+		cclog.ComponentDebug(s.name, "MaxRetryInterval", s.influxRetryInterval)
+		clientOptions.SetMaxRetryInterval(s.influxRetryInterval)
+	}
+	if s.influxMaxRetryTime != 0 {
+		cclog.ComponentDebug(s.name, "MaxRetryTime", s.influxMaxRetryTime)
+		clientOptions.SetMaxRetryTime(s.influxMaxRetryTime)
+	}
+	if s.config.InfluxExponentialBase != 0 {
+		cclog.ComponentDebug(s.name, "Exponential Base", s.config.InfluxExponentialBase)
+		clientOptions.SetExponentialBase(s.config.InfluxExponentialBase)
+	}
+	if s.config.InfluxMaxRetries != 0 {
+		cclog.ComponentDebug(s.name, "Max Retries", s.config.InfluxMaxRetries)
+		clientOptions.SetMaxRetries(s.config.InfluxMaxRetries)
+	}
+	clientOptions.SetTLSConfig(
+		&tls.Config{
+			InsecureSkipVerify: true,
+		},
+	).SetPrecision(time.Second)
+
+	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
+	s.writeApi = s.client.WriteAPI(s.config.Organization, s.config.Database)
+	ok, err := s.client.Ping(context.Background())
+	if err != nil {
+		return err
+	}
+	if !ok {
+		return fmt.Errorf("connection to %s not healthy", uri)
+	}
+	s.writeApi.SetWriteFailedCallback(func(batch string, err influxdb2ApiHttp.Error, retryAttempts uint) bool {
+		mlist := strings.Split(batch, "\n")
+		cclog.ComponentError(s.name, fmt.Sprintf("Failed to write batch with %d metrics %d times (max: %d): %s", len(mlist), retryAttempts, s.config.MaxRetryAttempts, err.Error()))
+		return retryAttempts <= s.config.MaxRetryAttempts
+	})
+	return nil
+}
+
+func (s *InfluxAsyncSink) Write(m lp.CCMetric) error {
+	if s.customFlushInterval != 0 && s.flushTimer == nil {
+		// Run a batched flush for all lines that have arrived in the defined interval
+		s.flushTimer = time.AfterFunc(s.customFlushInterval, func() {
+			if err := s.Flush(); err != nil {
+				cclog.ComponentError(s.name, "flush failed:", err.Error())
+			}
+		})
+	}
+	s.writeApi.WritePoint(
+		m.ToPoint(s.meta_as_tags),
+	)
+	return nil
+}
+
+func (s *InfluxAsyncSink) Flush() error {
+	cclog.ComponentDebug(s.name, "Flushing")
+	s.writeApi.Flush()
+	if s.customFlushInterval != 0 && s.flushTimer != nil {
+		s.flushTimer = nil
+	}
+	return nil
+}
+
+func (s *InfluxAsyncSink) Close() {
+	cclog.ComponentDebug(s.name, "Closing InfluxDB connection")
+	s.writeApi.Flush()
+	s.client.Close()
+}
+
+func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(InfluxAsyncSink)
+	s.name = fmt.Sprintf("InfluxSink(%s)", name)
+
+	// Set default for maximum number of points sent to server in single request.
+	s.config.BatchSize = 0
+	s.influxRetryInterval = 0
+	//s.config.InfluxRetryInterval = "1s"
+	s.influxMaxRetryTime = 0
+	//s.config.InfluxMaxRetryTime = "168h"
+	s.config.InfluxMaxRetries = 0
+	s.config.InfluxExponentialBase = 0
+	s.config.FlushInterval = 0
+	s.config.CustomFlushInterval = ""
+	s.customFlushInterval = time.Duration(0)
+	s.config.MaxRetryAttempts = 1
+
+	// Default retry intervals (in seconds)
+	// 1 2
+	// 2 4
+	// 4 8
+	// 8 16
+	// 16 32
+	// 32 64
+	// 64 128
+	// 128 256
+	// 256 512
+	// 512 1024
+	// 1024 2048
+	// 2048 4096
+	// 4096 8192
+	// 8192 16384
+	// 16384 32768
+	// 32768 65536
+	// 65536 131072
+	// 131072 262144
+	// 262144 524288
+
+	if len(config) > 0 {
+		d := json.NewDecoder(bytes.NewReader(config))
+		d.DisallowUnknownFields()
+		if err := d.Decode(&s.config); err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+	if len(s.config.Port) == 0 {
+		return nil, errors.New("missing port configuration required by InfluxSink")
+	}
+	if len(s.config.Database) == 0 {
+		return nil, errors.New("missing database configuration required by InfluxSink")
+	}
+	if len(s.config.Organization) == 0 {
+		return nil, errors.New("missing organization configuration required by InfluxSink")
+	}
+	if len(s.config.Password) == 0 {
+		return nil, errors.New("missing password configuration required by InfluxSink")
+	}
+	// Create lookup map to use meta infos as tags in the output metric
+	s.meta_as_tags = make(map[string]bool)
+	for _, k := range s.config.MetaAsTags {
+		s.meta_as_tags[k] = true
+	}
+
+	toUint := func(duration string, def uint) uint {
+		t, err := time.ParseDuration(duration)
+		if err == nil {
+			return uint(t.Milliseconds())
+		}
+		return def
+	}
+	s.influxRetryInterval = toUint(s.config.InfluxRetryInterval, s.influxRetryInterval)
+	s.influxMaxRetryTime = toUint(s.config.InfluxMaxRetryTime, s.influxMaxRetryTime)
+
+	// Use a own timer for calling Flush()
+	if len(s.config.CustomFlushInterval) > 0 {
+		t, err := time.ParseDuration(s.config.CustomFlushInterval)
+		if err != nil {
+			return nil, fmt.Errorf("invalid duration in 'custom_flush_interval': %v", err)
+		}
+		s.customFlushInterval = t
+	}
+
+	// Connect to InfluxDB server
+	if err := s.connect(); err != nil {
+		return nil, fmt.Errorf("unable to connect: %v", err)
+	}
+
+	// Start background: Read from error channel
+	s.errors = s.writeApi.Errors()
+	go func() {
+		for err := range s.errors {
+			cclog.ComponentError(s.name, err.Error())
+		}
+	}()
+
+	return s, nil
+}

sinks/influxAsyncSink.md

@@ -0,0 +1,44 @@
+## `influxasync` sink
+
+The `influxasync` sink uses the official [InfluxDB golang client](https://pkg.go.dev/github.com/influxdata/influxdb-client-go/v2) to write the metrics to an InfluxDB database in a **non-blocking** fashion. It provides only support for V2 write endpoints (InfluxDB 1.8.0 or later).
+
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "influxasync",
+    "database" : "mymetrics",
+    "host": "dbhost.example.com",
+    "port": "4222",
+    "user": "exampleuser",
+    "password" : "examplepw",
+    "organization": "myorg",
+    "ssl": true,
+    "batch_size": 200,
+    "retry_interval" : "1s",
+    "retry_exponential_base" : 2,
+    "max_retries": 20,
+    "max_retry_time" : "168h",
+    "meta_as_tags" : [],
+  }
+}
+```
+
+- `type`: makes the sink an `influxdb` sink
+- `database`: All metrics are written to this bucket 
+- `host`: Hostname of the InfluxDB database server
+- `port`: Portnumber (as string) of the InfluxDB database server
+- `user`: Username for basic authentification
+- `password`: Password for basic authentification
+- `organization`: Organization in the InfluxDB
+- `ssl`: Use SSL connection
+- `batch_size`: batch up metrics internally, default 100
+- `retry_interval`: Base retry interval for failed write requests, default 1s
+- `retry_exponential_base`: The retry interval is exponentially increased with this base, default 2
+- `max_retries`: Maximal number of retry attempts
+- `max_retry_time`: Maximal time to retry failed writes, default 168h (one week)
+- `meta_as_tags`: move meta information keys to tags (optional)
+
+For information about the calculation of the retry interval settings, see [offical influxdb-client-go documentation](https://github.com/influxdata/influxdb-client-go#handling-of-failed-async-writes)

sinks/influxSink.go

@@ -0,0 +1,475 @@
+package sinks
+
+import (
+	"bytes"
+	"context"
+	"crypto/tls"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"sync"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
+	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
+	influx "github.com/influxdata/line-protocol/v2/lineprotocol"
+	"golang.org/x/exp/slices"
+)
+
+type InfluxSink struct {
+	sink
+	client   influxdb2.Client
+	writeApi influxdb2Api.WriteAPIBlocking
+	config   struct {
+		defaultSinkConfig
+		Host         string `json:"host,omitempty"`
+		Port         string `json:"port,omitempty"`
+		Database     string `json:"database,omitempty"`
+		User         string `json:"user,omitempty"`
+		Password     string `json:"password,omitempty"`
+		Organization string `json:"organization,omitempty"`
+		SSL          bool   `json:"ssl,omitempty"`
+		// Maximum number of points sent to server in single request.
+		// Default: 1000
+		BatchSize int `json:"batch_size,omitempty"`
+
+		// Time interval for delayed sending of metrics.
+		// If the buffers are already filled before the end of this interval,
+		// the metrics are sent without further delay.
+		// Default: 1s
+		FlushInterval string `json:"flush_delay,omitempty"`
+		flushDelay    time.Duration
+
+		// Influx client options:
+
+		// HTTP request timeout
+		HTTPRequestTimeout string `json:"http_request_timeout"`
+		// Retry interval
+		InfluxRetryInterval string `json:"retry_interval,omitempty"`
+		// maximum delay between each retry attempt
+		InfluxMaxRetryInterval string `json:"max_retry_interval,omitempty"`
+		// base for the exponential retry delay
+		InfluxExponentialBase uint `json:"retry_exponential_base,omitempty"`
+		// maximum count of retry attempts of failed writes
+		InfluxMaxRetries uint `json:"max_retries,omitempty"`
+		// maximum total retry timeout
+		InfluxMaxRetryTime string `json:"max_retry_time,omitempty"`
+		// Specify whether to use GZip compression in write requests
+		InfluxUseGzip bool `json:"use_gzip"`
+	}
+
+	// influx line protocol encoder
+	encoder influx.Encoder
+	// number of records stored in the encoder
+	numRecordsInEncoder int
+	// List of tags and meta data tags which should be used as tags
+	extended_tag_list []key_value_pair
+	// Flush() runs in another goroutine and accesses the influx line protocol encoder,
+	// so this encoderLock has to protect the encoder and numRecordsInEncoder
+	encoderLock sync.Mutex
+
+	// timer to run Flush()
+	flushTimer *time.Timer
+	// Lock to assure that only one timer is running at a time
+	timerLock sync.Mutex
+
+	// WaitGroup to ensure only one send operation is running at a time
+	sendWaitGroup sync.WaitGroup
+}
+
+// connect connects to the InfluxDB server
+func (s *InfluxSink) connect() error {
+
+	// URI options:
+	// * http://host:port
+	// * https://host:port
+	var uri string
+	if s.config.SSL {
+		uri = fmt.Sprintf("https://%s:%s", s.config.Host, s.config.Port)
+	} else {
+		uri = fmt.Sprintf("http://%s:%s", s.config.Host, s.config.Port)
+	}
+
+	// Authentication options:
+	// * token
+	// * username:password
+	var auth string
+	if len(s.config.User) == 0 {
+		auth = s.config.Password
+	} else {
+		auth = fmt.Sprintf("%s:%s", s.config.User, s.config.Password)
+	}
+	cclog.ComponentDebug(s.name, "connect():",
+		"Using URI='"+uri+"'",
+		"Org='"+s.config.Organization+"'",
+		"Bucket='"+s.config.Database+"'")
+
+	// Set influxDB client options
+	clientOptions := influxdb2.DefaultOptions()
+
+	// set HTTP request timeout
+	if len(s.config.HTTPRequestTimeout) > 0 {
+		if t, err := time.ParseDuration(s.config.HTTPRequestTimeout); err == nil {
+			httpRequestTimeout := uint(t.Seconds())
+			clientOptions.SetHTTPRequestTimeout(httpRequestTimeout)
+		} else {
+			cclog.ComponentError(s.name, "connect():", "Failed to parse duration for HTTP RequestTimeout: ", s.config.HTTPRequestTimeout)
+		}
+	}
+	cclog.ComponentDebug(
+		s.name,
+		"connect():",
+		"Influx client options HTTPRequestTimeout:",
+		time.Second*time.Duration(clientOptions.HTTPRequestTimeout()))
+
+	// Set retry interval
+	if len(s.config.InfluxRetryInterval) > 0 {
+		if t, err := time.ParseDuration(s.config.InfluxRetryInterval); err == nil {
+			influxRetryInterval := uint(t.Milliseconds())
+			clientOptions.SetRetryInterval(influxRetryInterval)
+		} else {
+			cclog.ComponentError(s.name, "connect():", "Failed to parse duration for Influx RetryInterval: ", s.config.InfluxRetryInterval)
+		}
+	}
+	cclog.ComponentDebug(
+		s.name,
+		"connect():",
+		"Influx client options RetryInterval:",
+		time.Millisecond*time.Duration(clientOptions.RetryInterval()))
+
+	// Set the maximum delay between each retry attempt
+	if len(s.config.InfluxMaxRetryInterval) > 0 {
+		if t, err := time.ParseDuration(s.config.InfluxMaxRetryInterval); err == nil {
+			influxMaxRetryInterval := uint(t.Milliseconds())
+			clientOptions.SetMaxRetryInterval(influxMaxRetryInterval)
+		} else {
+			cclog.ComponentError(s.name, "connect():", "Failed to parse duration for Influx MaxRetryInterval: ", s.config.InfluxMaxRetryInterval)
+		}
+	}
+	cclog.ComponentDebug(
+		s.name,
+		"connect():",
+		"Influx client options MaxRetryInterval:",
+		time.Millisecond*time.Duration(clientOptions.MaxRetryInterval()))
+
+	// Set the base for the exponential retry delay
+	if s.config.InfluxExponentialBase != 0 {
+		clientOptions.SetExponentialBase(s.config.InfluxExponentialBase)
+	}
+	cclog.ComponentDebug(
+		s.name,
+		"connect():",
+		"Influx client options ExponentialBase:",
+		clientOptions.ExponentialBase())
+
+	// Set maximum count of retry attempts of failed writes
+	if s.config.InfluxMaxRetries != 0 {
+		clientOptions.SetMaxRetries(s.config.InfluxMaxRetries)
+	}
+	cclog.ComponentDebug(
+		s.name,
+		"connect():",
+		"Influx client options MaxRetries:",
+		clientOptions.MaxRetries())
+
+	// Set the maximum total retry timeout
+	if len(s.config.InfluxMaxRetryTime) > 0 {
+		if t, err := time.ParseDuration(s.config.InfluxMaxRetryTime); err == nil {
+			influxMaxRetryTime := uint(t.Milliseconds())
+			cclog.ComponentDebug(s.name, "connect():", "MaxRetryTime", s.config.InfluxMaxRetryTime)
+			clientOptions.SetMaxRetryTime(influxMaxRetryTime)
+		} else {
+			cclog.ComponentError(s.name, "connect():", "Failed to parse duration for Influx MaxRetryInterval: ", s.config.InfluxMaxRetryInterval)
+		}
+	}
+	cclog.ComponentDebug(
+		s.name,
+		"connect():",
+		"Influx client options MaxRetryTime:",
+		time.Millisecond*time.Duration(clientOptions.MaxRetryTime()))
+
+	// Specify whether to use GZip compression in write requests
+	clientOptions.SetUseGZip(s.config.InfluxUseGzip)
+	cclog.ComponentDebug(
+		s.name,
+		"connect():",
+		"Influx client options UseGZip:",
+		clientOptions.UseGZip())
+
+	// Do not check InfluxDB certificate
+	clientOptions.SetTLSConfig(
+		&tls.Config{
+			InsecureSkipVerify: true,
+		},
+	)
+
+	// Set time precision
+	clientOptions.SetPrecision(time.Nanosecond)
+
+	// Create new writeAPI
+	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
+	s.writeApi = s.client.WriteAPIBlocking(s.config.Organization, s.config.Database)
+
+	// Check InfluxDB server accessibility
+	ok, err := s.client.Ping(context.Background())
+	if err != nil {
+		return err
+	}
+	if !ok {
+		return fmt.Errorf("connection to %s not healthy", uri)
+	}
+	return nil
+}
+
+// Write sends metric m in influxDB line protocol
+func (s *InfluxSink) Write(m lp.CCMetric) error {
+
+	// Lock for encoder usage
+	s.encoderLock.Lock()
+
+	// Encode measurement name
+	s.encoder.StartLine(m.Name())
+
+	// copy tags and meta data which should be used as tags
+	s.extended_tag_list = s.extended_tag_list[:0]
+	for key, value := range m.Tags() {
+		s.extended_tag_list =
+			append(
+				s.extended_tag_list,
+				key_value_pair{
+					key:   key,
+					value: value,
+				},
+			)
+	}
+	for _, key := range s.config.MetaAsTags {
+		if value, ok := m.GetMeta(key); ok {
+			s.extended_tag_list =
+				append(
+					s.extended_tag_list,
+					key_value_pair{
+						key:   key,
+						value: value,
+					},
+				)
+		}
+	}
+
+	// Encode tags (they musts be in lexical order)
+	slices.SortFunc(
+		s.extended_tag_list,
+		func(a key_value_pair, b key_value_pair) int {
+			if a.key < b.key {
+				return -1
+			}
+			if a.key > b.key {
+				return +1
+			}
+			return 0
+		},
+	)
+	for i := range s.extended_tag_list {
+		s.encoder.AddTag(
+			s.extended_tag_list[i].key,
+			s.extended_tag_list[i].value,
+		)
+	}
+
+	// Encode fields
+	for key, value := range m.Fields() {
+		s.encoder.AddField(key, influx.MustNewValue(value))
+	}
+
+	// Encode time stamp
+	s.encoder.EndLine(m.Time())
+
+	// Check for encoder errors
+	if err := s.encoder.Err(); err != nil {
+		// Unlock encoder usage
+		s.encoderLock.Unlock()
+
+		return fmt.Errorf("Encoding failed: %v", err)
+	}
+	s.numRecordsInEncoder++
+
+	if s.config.flushDelay == 0 {
+		// Unlock encoder usage
+		s.encoderLock.Unlock()
+
+		// Directly flush if no flush delay is configured
+		return s.Flush()
+	} else if s.numRecordsInEncoder == s.config.BatchSize {
+		// Unlock encoder usage
+		s.encoderLock.Unlock()
+
+		// Stop flush timer
+		if s.flushTimer != nil {
+			if ok := s.flushTimer.Stop(); ok {
+				cclog.ComponentDebug(s.name, "Write(): Stopped flush timer. Batch size limit reached before flush delay")
+				s.timerLock.Unlock()
+			}
+		}
+
+		// Flush if batch size is reached
+		return s.Flush()
+	} else if s.timerLock.TryLock() {
+
+		// Setup flush timer when flush delay is configured
+		// and no other timer is already running
+		if s.flushTimer != nil {
+
+			// Restarting existing flush timer
+			cclog.ComponentDebug(s.name, "Write(): Restarting flush timer")
+			s.flushTimer.Reset(s.config.flushDelay)
+		} else {
+
+			// Creating and starting flush timer
+			cclog.ComponentDebug(s.name, "Write(): Starting new flush timer")
+			s.flushTimer = time.AfterFunc(
+				s.config.flushDelay,
+				func() {
+					defer s.timerLock.Unlock()
+					cclog.ComponentDebug(s.name, "Starting flush triggered by flush timer")
+					if err := s.Flush(); err != nil {
+						cclog.ComponentError(s.name, "Flush triggered by flush timer: flush failed:", err)
+					}
+				})
+		}
+	}
+
+	// Unlock encoder usage
+	s.encoderLock.Unlock()
+	return nil
+}
+
+// Flush sends all metrics stored in encoder to InfluxDB server
+func (s *InfluxSink) Flush() error {
+
+	// Lock for encoder usage
+	// Own lock for as short as possible: the time it takes to clone the buffer.
+	s.encoderLock.Lock()
+
+	buf := slices.Clone(s.encoder.Bytes())
+	numRecordsInBuf := s.numRecordsInEncoder
+	s.encoder.Reset()
+	s.numRecordsInEncoder = 0
+
+	// Unlock encoder usage
+	s.encoderLock.Unlock()
+
+	if len(buf) == 0 {
+		return nil
+	}
+
+	cclog.ComponentDebug(s.name, "Flush(): Flushing", numRecordsInBuf, "metrics")
+
+	// Asynchron send of encoder metrics
+	s.sendWaitGroup.Add(1)
+	go func() {
+		defer s.sendWaitGroup.Done()
+		startTime := time.Now()
+		err := s.writeApi.WriteRecord(context.Background(), string(buf))
+		if err != nil {
+			cclog.ComponentError(
+				s.name,
+				"Flush():",
+				"Flush failed:", err,
+				"(number of records =", numRecordsInBuf,
+				", buffer size =", len(buf),
+				", send duration =", time.Since(startTime),
+				")",
+			)
+			return
+		}
+	}()
+
+	return nil
+}
+
+func (s *InfluxSink) Close() {
+	cclog.ComponentDebug(s.name, "Closing InfluxDB connection")
+
+	// Stop existing timer and immediately flush
+	if s.flushTimer != nil {
+		if ok := s.flushTimer.Stop(); ok {
+			s.timerLock.Unlock()
+		}
+	}
+
+	// Flush
+	if err := s.Flush(); err != nil {
+		cclog.ComponentError(s.name, "Close():", "Flush failed:", err)
+	}
+
+	// Wait for send operations to finish
+	s.sendWaitGroup.Wait()
+
+	s.client.Close()
+}
+
+// NewInfluxSink create a new InfluxDB sink
+func NewInfluxSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(InfluxSink)
+	s.name = fmt.Sprintf("InfluxSink(%s)", name)
+
+	// Set config default values
+	s.config.BatchSize = 1000
+	s.config.FlushInterval = "1s"
+
+	// Read config
+	if len(config) > 0 {
+		d := json.NewDecoder(bytes.NewReader(config))
+		d.DisallowUnknownFields()
+		if err := d.Decode(&s.config); err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+
+	if len(s.config.Host) == 0 {
+		return s, errors.New("missing host configuration required by InfluxSink")
+	}
+	if len(s.config.Port) == 0 {
+		return s, errors.New("missing port configuration required by InfluxSink")
+	}
+	if len(s.config.Database) == 0 {
+		return s, errors.New("missing database configuration required by InfluxSink")
+	}
+	if len(s.config.Organization) == 0 {
+		return s, errors.New("missing organization configuration required by InfluxSink")
+	}
+	if len(s.config.Password) == 0 {
+		return s, errors.New("missing password configuration required by InfluxSink")
+	}
+
+	// Create lookup map to use meta infos as tags in the output metric
+	s.meta_as_tags = make(map[string]bool)
+	for _, k := range s.config.MetaAsTags {
+		s.meta_as_tags[k] = true
+	}
+
+	// Configure flush delay duration
+	if len(s.config.FlushInterval) > 0 {
+		t, err := time.ParseDuration(s.config.FlushInterval)
+		if err == nil {
+			s.config.flushDelay = t
+		}
+	}
+
+	if !(s.config.BatchSize > 0) {
+		return s, fmt.Errorf("batch_size=%d in InfluxDB config must be > 0", s.config.BatchSize)
+	}
+
+	// Connect to InfluxDB server
+	if err := s.connect(); err != nil {
+		return s, fmt.Errorf("unable to connect: %v", err)
+	}
+
+	// Configure influx line protocol encoder
+	s.encoder.SetPrecision(influx.Nanosecond)
+	s.extended_tag_list = make([]key_value_pair, 0)
+
+	return s, nil
+}

sinks/influxSink.md

@@ -0,0 +1,48 @@
+## `influxdb` sink
+
+The `influxdb` sink uses the official [InfluxDB golang client](https://pkg.go.dev/github.com/influxdata/influxdb-client-go/v2) to write the metrics to an InfluxDB database in a **blocking** fashion. It provides only support for V2 write endpoints (InfluxDB 1.8.0 or later).
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "influxdb",
+    "database" : "mymetrics",
+    "host": "dbhost.example.com",
+    "port": "4222",
+    "user": "exampleuser",
+    "password" : "examplepw",
+    "organization": "myorg",
+    "ssl": true,
+    "flush_delay" : "1s",
+    "batch_size" : 1000,
+    "use_gzip": true
+    "meta_as_tags" : [],
+  }
+}
+```
+
+- `type`: makes the sink an `influxdb` sink
+- `meta_as_tags`: print all meta information as tags in the output (optional)
+- `database`: All metrics are written to this bucket
+- `host`: Hostname of the InfluxDB database server
+- `port`: Port number (as string) of the InfluxDB database server
+- `user`: Username for basic authentication
+- `password`: Password for basic authentication
+- `organization`: Organization in the InfluxDB
+- `ssl`: Use SSL connection
+- `flush_delay`: Group metrics coming in to a single batch
+- `batch_size`: Maximal batch size. If `batch_size` is reached before the end of `flush_delay`, the metrics are sent without further delay
+
+Influx client options:
+=======
+- `batch_size`: Maximal batch size
+- `meta_as_tags`: move meta information keys to tags (optional)
+- `http_request_timeout`: HTTP request timeout
+- `retry_interval`: retry interval
+- `max_retry_interval`: maximum delay between each retry attempt
+- `retry_exponential_base`: base for the exponential retry delay
+- `max_retries`: maximum count of retry attempts of failed writes
+- `max_retry_time`: maximum total retry timeout
+- `use_gzip`: Specify whether to use GZip compression in write requests

sinks/libgangliaSink.go

@@ -0,0 +1,285 @@
+package sinks
+
+/*
+#cgo CFLAGS: -DGM_PROTOCOL_GUARD
+#cgo LDFLAGS: -L. -Wl,--unresolved-symbols=ignore-in-object-files
+#include <stdlib.h>
+
+// This is a copy&paste snippet of ganglia.h (BSD-3 license)
+// See https://github.com/ganglia/monitor-core
+// for further information
+
+enum ganglia_slope {
+   GANGLIA_SLOPE_ZERO = 0,
+   GANGLIA_SLOPE_POSITIVE,
+   GANGLIA_SLOPE_NEGATIVE,
+   GANGLIA_SLOPE_BOTH,
+   GANGLIA_SLOPE_UNSPECIFIED,
+   GANGLIA_SLOPE_DERIVATIVE,
+   GANGLIA_SLOPE_LAST_LEGAL_VALUE=GANGLIA_SLOPE_DERIVATIVE
+};
+typedef enum ganglia_slope ganglia_slope_t;
+
+typedef struct Ganglia_pool* Ganglia_pool;
+typedef struct Ganglia_gmond_config* Ganglia_gmond_config;
+typedef struct Ganglia_udp_send_channels* Ganglia_udp_send_channels;
+
+struct Ganglia_metric {
+   Ganglia_pool pool;
+   struct Ganglia_metadata_message *msg;
+   char *value;
+   void *extra;
+};
+typedef struct Ganglia_metric * Ganglia_metric;
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+Ganglia_gmond_config Ganglia_gmond_config_create(char *path, int fallback_to_default);
+//void Ganglia_gmond_config_destroy(Ganglia_gmond_config config);
+
+Ganglia_udp_send_channels Ganglia_udp_send_channels_create(Ganglia_pool p, Ganglia_gmond_config config);
+void Ganglia_udp_send_channels_destroy(Ganglia_udp_send_channels channels);
+
+int Ganglia_udp_send_message(Ganglia_udp_send_channels channels, char *buf, int len );
+
+Ganglia_metric Ganglia_metric_create( Ganglia_pool parent_pool );
+int Ganglia_metric_set( Ganglia_metric gmetric, char *name, char *value, char *type, char *units, unsigned int slope, unsigned int tmax, unsigned int dmax);
+int Ganglia_metric_send( Ganglia_metric gmetric, Ganglia_udp_send_channels send_channels );
+//int Ganglia_metadata_send( Ganglia_metric gmetric, Ganglia_udp_send_channels send_channels );
+//int Ganglia_metadata_send_real( Ganglia_metric gmetric, Ganglia_udp_send_channels send_channels, char *override_string );
+void Ganglia_metadata_add( Ganglia_metric gmetric, char *name, char *value );
+//int Ganglia_value_send( Ganglia_metric gmetric, Ganglia_udp_send_channels send_channels );
+void Ganglia_metric_destroy( Ganglia_metric gmetric );
+
+Ganglia_pool Ganglia_pool_create( Ganglia_pool parent );
+void Ganglia_pool_destroy( Ganglia_pool pool );
+
+//ganglia_slope_t cstr_to_slope(const char* str);
+//const char*     slope_to_cstr(unsigned int slope);
+
+#ifdef __cplusplus
+}
+#endif
+*/
+import "C"
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"unsafe"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	"github.com/NVIDIA/go-nvml/pkg/dl"
+)
+
+const (
+	GANGLIA_LIB_NAME     = "libganglia.so"
+	GANGLIA_LIB_DL_FLAGS = dl.RTLD_LAZY | dl.RTLD_GLOBAL
+	GMOND_CONFIG_FILE    = `/etc/ganglia/gmond.conf`
+)
+
+// type LibgangliaSinkSpecialMetric struct {
+// 	MetricName string `json:"metric_name,omitempty"`
+// 	NewName    string `json:"new_name,omitempty"`
+// 	Slope      string `json:"slope,omitempty"`
+// }
+
+type LibgangliaSinkConfig struct {
+	defaultSinkConfig
+	GangliaLib      string `json:"libganglia_path,omitempty"`
+	GmondConfig     string `json:"gmond_config,omitempty"`
+	AddGangliaGroup bool   `json:"add_ganglia_group,omitempty"`
+	AddTypeToName   bool   `json:"add_type_to_name,omitempty"`
+	AddUnits        bool   `json:"add_units,omitempty"`
+	ClusterName     string `json:"cluster_name,omitempty"`
+	//SpecialMetrics  map[string]LibgangliaSinkSpecialMetric `json:"rename_metrics,omitempty"` // Map to rename metric name from key to value
+	//AddTagsAsDesc   bool              `json:"add_tags_as_desc,omitempty"`
+}
+
+type LibgangliaSink struct {
+	sink
+	config         LibgangliaSinkConfig
+	global_context C.Ganglia_pool
+	gmond_config   C.Ganglia_gmond_config
+	send_channels  C.Ganglia_udp_send_channels
+	cstrCache      map[string]*C.char
+}
+
+func (s *LibgangliaSink) Write(point lp.CCMetric) error {
+	var err error = nil
+	var c_name *C.char
+	var c_value *C.char
+	var c_type *C.char
+	var c_unit *C.char
+
+	// helper function for looking up C strings in the cache
+	lookup := func(key string) *C.char {
+		if _, exist := s.cstrCache[key]; !exist {
+			s.cstrCache[key] = C.CString(key)
+		}
+		return s.cstrCache[key]
+	}
+
+	conf := GetCommonGangliaConfig(point)
+	if len(conf.Type) == 0 {
+		conf = GetGangliaConfig(point)
+	}
+	if len(conf.Type) == 0 {
+		return fmt.Errorf("metric %q (Ganglia name %q) has no 'value' field", point.Name(), conf.Name)
+	}
+
+	if s.config.AddTypeToName {
+		conf.Name = GangliaMetricName(point)
+	}
+
+	c_value = C.CString(conf.Value)
+	c_type = lookup(conf.Type)
+	c_name = lookup(conf.Name)
+
+	// Add unit
+	unit := ""
+	if s.config.AddUnits {
+		unit = conf.Unit
+	}
+	c_unit = lookup(unit)
+
+	// Determine the slope of the metric. Ganglia's own collector mostly use
+	// 'both' but the mem and swap total uses 'zero'.
+	slope_type := C.GANGLIA_SLOPE_BOTH
+	switch conf.Slope {
+	case "zero":
+		slope_type = C.GANGLIA_SLOPE_ZERO
+	case "both":
+		slope_type = C.GANGLIA_SLOPE_BOTH
+	}
+
+	// Create a new Ganglia metric
+	gmetric := C.Ganglia_metric_create(s.global_context)
+	// Set name, value, type and unit in the Ganglia metric
+	// The default slope_type is both directions, so up and down. Some metrics want 'zero' slope, probably constant.
+	// The 'tmax' value is by default 300.
+	rval := C.int(0)
+	rval = C.Ganglia_metric_set(gmetric, c_name, c_value, c_type, c_unit, C.uint(slope_type), C.uint(conf.Tmax), 0)
+	switch rval {
+	case 1:
+		C.free(unsafe.Pointer(c_value))
+		return errors.New("invalid parameters")
+	case 2:
+		C.free(unsafe.Pointer(c_value))
+		return errors.New("one of your parameters has an invalid character '\"'")
+	case 3:
+		C.free(unsafe.Pointer(c_value))
+		return fmt.Errorf("the type parameter \"%s\" is not a valid type", conf.Type)
+	case 4:
+		C.free(unsafe.Pointer(c_value))
+		return fmt.Errorf("the value parameter \"%s\" does not represent a number", conf.Value)
+	default:
+	}
+
+	// Set the cluster name, otherwise it takes it from the configuration file
+	if len(s.config.ClusterName) > 0 {
+		C.Ganglia_metadata_add(gmetric, lookup("CLUSTER"), lookup(s.config.ClusterName))
+	}
+	// Set the group metadata in the Ganglia metric if configured
+	if s.config.AddGangliaGroup {
+		c_group := lookup(conf.Group)
+		C.Ganglia_metadata_add(gmetric, lookup("GROUP"), c_group)
+	}
+
+	// Now we send the metric
+	// gmetric does provide some more options like description and other options
+	// but they are not provided by the collectors
+	rval = C.Ganglia_metric_send(gmetric, s.send_channels)
+	if rval != 0 {
+		err = fmt.Errorf("there was an error sending metric %s to %d of the send channels ", point.Name(), rval)
+		// fall throuph to use Ganglia_metric_destroy from common cleanup
+	}
+	// Cleanup Ganglia metric
+	C.Ganglia_metric_destroy(gmetric)
+	// Free the value C string, the only one not stored in the cache
+	C.free(unsafe.Pointer(c_value))
+	return err
+}
+
+func (s *LibgangliaSink) Flush() error {
+	return nil
+}
+
+func (s *LibgangliaSink) Close() {
+	// Destroy Ganglia configration struct
+	// (not done by gmetric, I thought I am more clever but no...)
+	//C.Ganglia_gmond_config_destroy(s.gmond_config)
+	// Destroy Ganglia pool
+	C.Ganglia_pool_destroy(s.global_context)
+
+	// Cleanup C string cache
+	for _, cstr := range s.cstrCache {
+		C.free(unsafe.Pointer(cstr))
+	}
+}
+
+func NewLibgangliaSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(LibgangliaSink)
+	var err error = nil
+	s.name = fmt.Sprintf("LibgangliaSink(%s)", name)
+	//s.config.AddTagsAsDesc = false
+	s.config.AddGangliaGroup = false
+	s.config.AddTypeToName = false
+	s.config.AddUnits = true
+	s.config.GmondConfig = string(GMOND_CONFIG_FILE)
+	s.config.GangliaLib = string(GANGLIA_LIB_NAME)
+	if len(config) > 0 {
+		d := json.NewDecoder(bytes.NewReader(config))
+		d.DisallowUnknownFields()
+		if err := d.Decode(&s.config); err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+	lib := dl.New(s.config.GangliaLib, GANGLIA_LIB_DL_FLAGS)
+	if lib == nil {
+		return nil, fmt.Errorf("error instantiating DynamicLibrary for %s", s.config.GangliaLib)
+	}
+	err = lib.Open()
+	if err != nil {
+		return nil, fmt.Errorf("error opening %s: %v", s.config.GangliaLib, err)
+	}
+
+	// Set up cache for the C strings
+	s.cstrCache = make(map[string]*C.char)
+	// s.cstrCache["globals"] = C.CString("globals")
+
+	// s.cstrCache["override_hostname"] = C.CString("override_hostname")
+	// s.cstrCache["override_ip"] = C.CString("override_ip")
+
+	// Add some constant strings
+	s.cstrCache["GROUP"] = C.CString("GROUP")
+	s.cstrCache["CLUSTER"] = C.CString("CLUSTER")
+	s.cstrCache[""] = C.CString("")
+
+	// Add cluster name for lookup in Write()
+	if len(s.config.ClusterName) > 0 {
+		s.cstrCache[s.config.ClusterName] = C.CString(s.config.ClusterName)
+	}
+	// Add supported types for later lookup in Write()
+	s.cstrCache["double"] = C.CString("double")
+	s.cstrCache["int32"] = C.CString("int32")
+	s.cstrCache["string"] = C.CString("string")
+
+	// Create Ganglia pool
+	s.global_context = C.Ganglia_pool_create(nil)
+	// Load Ganglia configuration
+	s.cstrCache[s.config.GmondConfig] = C.CString(s.config.GmondConfig)
+	s.gmond_config = C.Ganglia_gmond_config_create(s.cstrCache[s.config.GmondConfig], 0)
+	//globals := C.cfg_getsec(gmond_config, s.cstrCache["globals"])
+	//override_hostname := C.cfg_getstr(globals, s.cstrCache["override_hostname"])
+	//override_ip := C.cfg_getstr(globals, s.cstrCache["override_ip"])
+
+	s.send_channels = C.Ganglia_udp_send_channels_create(s.global_context, s.gmond_config)
+	return s, nil
+}

sinks/libgangliaSink.md

@@ -0,0 +1,41 @@
+## `libganglia` sink
+
+The `libganglia` sink interacts directly with the library of the [Ganglia Monitoring System](http://ganglia.info/) to submit the metrics. Consequently, it needs to be installed on all nodes. But this is commonly the case if you want to use Ganglia, because it requires at least a node daemon (`gmond` or `ganglia-monitor`) to work.
+
+The `libganglia` sink has probably less overhead compared to the `ganglia` sink because it does not require any process generation but initializes the environment and UDP connections only once.
+
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "libganglia",
+    "gmetric_config" : "/path/to/gmetric/config",
+    "cluster_name": "MyCluster",
+    "add_ganglia_group" : true,
+    "add_type_to_name": true,
+    "add_units" : true
+  }
+}
+```
+
+- `type`: makes the sink an `libganglia` sink
+- `meta_as_tags`: print all meta information as tags in the output (optional)
+- `gmond_config`: Path to the Ganglia configuration file `gmond.conf` (default: `/etc/ganglia/gmond.conf`)
+- `cluster_name`: Set a cluster name for the metric. If not set, it is taken from `gmond_config`
+- `add_ganglia_group`: Add a Ganglia metric group based on meta information. Some old versions of `gmetric` do not support the `--group` option
+- `add_type_to_name`: Ganglia commonly uses only node-level metrics but with cc-metric-collector, there are metrics for cpus, memory domains, CPU sockets and the whole node. In order to get  eeng, this option prefixes the metric name with `<type><type-id>_` or `device_` depending on the metric tags and meta information. For metrics of the whole node `type=node`, no prefix is added
+- `add_units`: Add metric value unit if there is a `unit` entry in the metric tags or meta information
+
+### Ganglia Installation
+
+My development system is Ubuntu 20.04. To install the required libraries with `apt`:
+
+```
+$ sudo apt install libganglia1
+```
+
+The `libganglia.so` gets installed in `/usr/lib`. The Ganglia headers `libganglia1-dev` are **not** required.
+
+I added a `Makefile` in the `sinks` subfolder that searches for the library in `/usr` and creates a symlink (`sinks/libganglia.so`) for running/building the cc-metric-collector. So just type `make` before running/building in the main folder or the `sinks` subfolder.

sinks/metricSink.go

@@ -0,0 +1,27 @@
+package sinks
+
+import (
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+type defaultSinkConfig struct {
+	MetaAsTags []string `json:"meta_as_tags,omitempty"`
+	Type       string   `json:"type"`
+}
+
+type sink struct {
+	meta_as_tags map[string]bool // Use meta data tags as tags
+	name         string          // Name of the sink
+}
+
+type Sink interface {
+	Write(point lp.CCMetric) error // Write metric to the sink
+	Flush() error                  // Flush buffered metrics
+	Close()                        // Close / finish metric sink
+	Name() string                  // Name of the metric sink
+}
+
+// Name returns the name of the metric sink
+func (s *sink) Name() string {
+	return s.name
+}

sinks/natsSink.go

@@ -0,0 +1,149 @@
+package sinks
+
+import (
+	"bytes"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"sync"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	influx "github.com/influxdata/line-protocol"
+	nats "github.com/nats-io/nats.go"
+)
+
+type NatsSinkConfig struct {
+	defaultSinkConfig
+	Host       string `json:"host,omitempty"`
+	Port       string `json:"port,omitempty"`
+	Subject    string `json:"subject,omitempty"`
+	User       string `json:"user,omitempty"`
+	Password   string `json:"password,omitempty"`
+	FlushDelay string `json:"flush_delay,omitempty"`
+}
+
+type NatsSink struct {
+	sink
+	client  *nats.Conn
+	encoder *influx.Encoder
+	buffer  *bytes.Buffer
+	config  NatsSinkConfig
+
+	lock       sync.Mutex
+	flushDelay time.Duration
+	flushTimer *time.Timer
+}
+
+func (s *NatsSink) connect() error {
+	var err error
+	var uinfo nats.Option = nil
+	var nc *nats.Conn
+	if len(s.config.User) > 0 && len(s.config.Password) > 0 {
+		uinfo = nats.UserInfo(s.config.User, s.config.Password)
+	}
+	uri := fmt.Sprintf("nats://%s:%s", s.config.Host, s.config.Port)
+	cclog.ComponentDebug(s.name, "Connect to", uri)
+	s.client = nil
+	if uinfo != nil {
+		nc, err = nats.Connect(uri, uinfo)
+	} else {
+		nc, err = nats.Connect(uri)
+	}
+	if err != nil {
+		cclog.ComponentError(s.name, "Connect to", uri, "failed:", err.Error())
+		return err
+	}
+	s.client = nc
+	return nil
+}
+
+func (s *NatsSink) Write(m lp.CCMetric) error {
+	s.lock.Lock()
+	_, err := s.encoder.Encode(m.ToPoint(s.meta_as_tags))
+	s.lock.Unlock()
+	if err != nil {
+		cclog.ComponentError(s.name, "Write:", err.Error())
+		return err
+	}
+
+	if s.flushDelay == 0 {
+		s.Flush()
+	} else if s.flushTimer == nil {
+		s.flushTimer = time.AfterFunc(s.flushDelay, func() {
+			s.Flush()
+		})
+	} else {
+		s.flushTimer.Reset(s.flushDelay)
+	}
+
+	return nil
+}
+
+func (s *NatsSink) Flush() error {
+	s.lock.Lock()
+	buf := append([]byte{}, s.buffer.Bytes()...) // copy bytes
+	s.buffer.Reset()
+	s.lock.Unlock()
+
+	if len(buf) == 0 {
+		return nil
+	}
+
+	if err := s.client.Publish(s.config.Subject, buf); err != nil {
+		cclog.ComponentError(s.name, "Flush:", err.Error())
+		return err
+	}
+	return nil
+}
+
+func (s *NatsSink) Close() {
+	cclog.ComponentDebug(s.name, "Close")
+	s.client.Close()
+}
+
+func NewNatsSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(NatsSink)
+	s.name = fmt.Sprintf("NatsSink(%s)", name)
+	s.flushDelay = 10 * time.Second
+	if len(config) > 0 {
+		d := json.NewDecoder(bytes.NewReader(config))
+		d.DisallowUnknownFields()
+		if err := d.Decode(&s.config); err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+	if len(s.config.Host) == 0 ||
+		len(s.config.Port) == 0 ||
+		len(s.config.Subject) == 0 {
+		return nil, errors.New("not all configuration variables set required by NatsSink")
+	}
+	// Create lookup map to use meta infos as tags in the output metric
+	s.meta_as_tags = make(map[string]bool)
+	for _, k := range s.config.MetaAsTags {
+		s.meta_as_tags[k] = true
+	}
+	// Setup Influx line protocol
+	s.buffer = &bytes.Buffer{}
+	s.buffer.Grow(1025)
+	s.encoder = influx.NewEncoder(s.buffer)
+	s.encoder.SetPrecision(time.Second)
+	s.encoder.SetMaxLineBytes(1024)
+	// Setup infos for connection
+	if err := s.connect(); err != nil {
+		return nil, fmt.Errorf("unable to connect: %v", err)
+	}
+
+	s.flushTimer = nil
+	if len(s.config.FlushDelay) != 0 {
+		var err error
+		s.flushDelay, err = time.ParseDuration(s.config.FlushDelay)
+		if err != nil {
+			return nil, err
+		}
+	}
+
+	return s, nil
+}

sinks/natsSink.md

@@ -0,0 +1,27 @@
+## `nats` sink
+
+The `nats` sink publishes all metrics into a NATS network. The publishing key is the database name provided in the configuration file
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "nats",
+    "database" : "mymetrics",
+    "host": "dbhost.example.com",
+    "port": "4222",
+    "user": "exampleuser",
+    "password" : "examplepw",
+    "meta_as_tags" : [],
+  }
+}
+```
+
+- `type`: makes the sink an `nats` sink
+- `database`: All metrics are published with this subject
+- `host`: Hostname of the NATS server
+- `port`: Port number (as string) of the NATS server
+- `user`: Username for basic authentication
+- `password`: Password for basic authentication
+- `meta_as_tags`: print all meta information as tags in the output (optional)

sinks/prometheusSink.go

@@ -0,0 +1,201 @@
+package sinks
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"net/http"
+	"strings"
+	"sync"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	"github.com/gorilla/mux"
+	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/promhttp"
+)
+
+type PrometheusSinkConfig struct {
+	defaultSinkConfig
+	Host             string `json:"host,omitempty"`
+	Port             string `json:"port"`
+	Path             string `json:"path,omitempty"`
+	GroupAsNameSpace bool   `json:"group_as_namespace,omitempty"`
+	// User       string `json:"user,omitempty"`
+	// Password   string `json:"password,omitempty"`
+	// FlushDelay string `json:"flush_delay,omitempty"`
+}
+
+type PrometheusSink struct {
+	sink
+	config       PrometheusSinkConfig
+	labelMetrics map[string]*prometheus.GaugeVec
+	nodeMetrics  map[string]prometheus.Gauge
+	promWg       sync.WaitGroup
+	promServer   *http.Server
+}
+
+func intToFloat64(input interface{}) (float64, error) {
+	switch value := input.(type) {
+	case float64:
+		return value, nil
+	case float32:
+		return float64(value), nil
+	case int:
+		return float64(value), nil
+	case int32:
+		return float64(value), nil
+	case int64:
+		return float64(value), nil
+	}
+	return 0, errors.New("cannot cast value to float64")
+}
+
+func getLabelValue(metric lp.CCMetric) []string {
+	labelValues := []string{}
+	if tid, tidok := metric.GetTag("type-id"); tidok && metric.HasTag("type") {
+		labelValues = append(labelValues, tid)
+	}
+	if d, ok := metric.GetTag("device"); ok {
+		labelValues = append(labelValues, d)
+	} else if d, ok := metric.GetMeta("device"); ok {
+		labelValues = append(labelValues, d)
+	}
+	return labelValues
+}
+
+func getLabelNames(metric lp.CCMetric) []string {
+	labelNames := []string{}
+	if t, tok := metric.GetTag("type"); tok && metric.HasTag("type-id") {
+		labelNames = append(labelNames, t)
+	}
+	if _, ok := metric.GetTag("device"); ok {
+		labelNames = append(labelNames, "device")
+	} else if _, ok := metric.GetMeta("device"); ok {
+		labelNames = append(labelNames, "device")
+	}
+	return labelNames
+}
+
+func (s *PrometheusSink) newMetric(metric lp.CCMetric) error {
+	var value float64 = 0
+	name := metric.Name()
+	opts := prometheus.GaugeOpts{
+		Name: name,
+	}
+	labels := getLabelNames(metric)
+	labelValues := getLabelValue(metric)
+	if len(labels) > 0 && len(labels) != len(labelValues) {
+		return fmt.Errorf("cannot detect metric labels for metric %s", name)
+	}
+
+	if metricValue, ok := metric.GetField("value"); ok {
+		if floatValue, err := intToFloat64(metricValue); err == nil {
+			value = floatValue
+		} else {
+			return fmt.Errorf("metric %s with value '%v' cannot be casted to float64", name, metricValue)
+		}
+	}
+	if s.config.GroupAsNameSpace && metric.HasMeta("group") {
+		g, _ := metric.GetMeta("group")
+		opts.Namespace = strings.ToLower(g)
+	}
+
+	if len(labels) > 0 {
+		new := prometheus.NewGaugeVec(opts, labels)
+		new.WithLabelValues(labelValues...).Set(value)
+		s.labelMetrics[name] = new
+		prometheus.Register(new)
+	} else {
+		new := prometheus.NewGauge(opts)
+		new.Set(value)
+		s.nodeMetrics[name] = new
+		prometheus.Register(new)
+	}
+	return nil
+}
+
+func (s *PrometheusSink) updateMetric(metric lp.CCMetric) error {
+	var value float64 = 0.0
+	name := metric.Name()
+	labelValues := getLabelValue(metric)
+
+	if metricValue, ok := metric.GetField("value"); ok {
+		if floatValue, err := intToFloat64(metricValue); err == nil {
+			value = floatValue
+		} else {
+			return fmt.Errorf("metric %s with value '%v' cannot be casted to float64", name, metricValue)
+		}
+	}
+
+	if len(labelValues) > 0 {
+		if _, ok := s.labelMetrics[name]; !ok {
+			err := s.newMetric(metric)
+			if err != nil {
+				return err
+			}
+		}
+		s.labelMetrics[name].WithLabelValues(labelValues...).Set(value)
+	} else {
+		if _, ok := s.labelMetrics[name]; !ok {
+			err := s.newMetric(metric)
+			if err != nil {
+				return err
+			}
+		}
+		s.nodeMetrics[name].Set(value)
+	}
+	return nil
+}
+
+func (s *PrometheusSink) Write(m lp.CCMetric) error {
+	return s.updateMetric(m)
+}
+
+func (s *PrometheusSink) Flush() error {
+	return nil
+}
+
+func (s *PrometheusSink) Close() {
+	cclog.ComponentDebug(s.name, "CLOSE")
+	s.promServer.Shutdown(context.Background())
+	s.promWg.Wait()
+}
+
+func NewPrometheusSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(PrometheusSink)
+	s.name = "PrometheusSink"
+	if len(config) > 0 {
+		d := json.NewDecoder(bytes.NewReader(config))
+		d.DisallowUnknownFields()
+		if err := d.Decode(&s.config); err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+	if len(s.config.Port) == 0 {
+		err := errors.New("not all configuration variables set required by PrometheusSink")
+		cclog.ComponentError(s.name, err.Error())
+		return nil, err
+	}
+	s.labelMetrics = make(map[string]*prometheus.GaugeVec)
+	s.nodeMetrics = make(map[string]prometheus.Gauge)
+	s.promWg.Add(1)
+	go func() {
+		router := mux.NewRouter()
+		// Prometheus endpoint
+		router.Path("/" + s.config.Path).Handler(promhttp.Handler())
+
+		url := fmt.Sprintf("%s:%s", s.config.Host, s.config.Port)
+		cclog.ComponentDebug(s.name, "Serving Prometheus metrics at", fmt.Sprintf("%s:%s/%s", s.config.Host, s.config.Port, s.config.Path))
+		s.promServer = &http.Server{Addr: url, Handler: router}
+		err := s.promServer.ListenAndServe()
+		if err != nil && err.Error() != "http: Server closed" {
+			cclog.ComponentError(s.name, err.Error())
+		}
+		s.promWg.Done()
+	}()
+	return s, nil
+}

sinks/prometheusSink.md

@@ -0,0 +1,23 @@
+## `prometheus` sink
+
+The `prometheus` sink publishes all metrics via an HTTP server ready to be scraped by a [Prometheus](https://prometheus.io) server. It creates gauge metrics for all node metrics and gauge vectors for all metrics with a subtype like 'device', 'cpu' or 'socket'. 
+
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "prometheus",
+    "host": "localhost",
+    "port": "8080",
+    "path": "metrics"
+  }
+}
+```
+
+- `type`: makes the sink an `prometheus` sink
+- `host`: The HTTP server gets bound to that IP/hostname
+- `port`: Portnumber (as string) for the HTTP server
+- `path`: Path where the metrics should be servered. The metrics will be published at `host`:`port`/`path`
+- `group_as_namespace`: Most metrics contain a group as meta information like 'memory', 'load'. With this the metric names are extended to `group`_`name` if possible.

sinks/sampleSink.go

@@ -0,0 +1,83 @@
+package sinks
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"log"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+type SampleSinkConfig struct {
+	// defines JSON tags for 'type' and 'meta_as_tags' (string list)
+	// See: metricSink.go
+	defaultSinkConfig
+	// Additional config options, for SampleSink
+}
+
+type SampleSink struct {
+	// declares elements 	'name' and 'meta_as_tags' (string to bool map!)
+	sink
+	config SampleSinkConfig // entry point to the SampleSinkConfig
+}
+
+// Implement functions required for Sink interface
+// Write(...), Flush(), Close()
+// See: metricSink.go
+
+// Code to submit a single CCMetric to the sink
+func (s *SampleSink) Write(point lp.CCMetric) error {
+	// based on s.meta_as_tags use meta infos as tags
+	log.Print(point)
+	return nil
+}
+
+// If the sink uses batched sends internally, you can tell to flush its buffers
+func (s *SampleSink) Flush() error {
+	return nil
+}
+
+// Close sink: close network connection, close files, close libraries, ...
+func (s *SampleSink) Close() {
+	cclog.ComponentDebug(s.name, "CLOSE")
+}
+
+// New function to create a new instance of the sink
+// Initialize the sink by giving it a name and reading in the config JSON
+func NewSampleSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(SampleSink)
+
+	// Set name of sampleSink
+	// The name should be chosen in such a way that different instances of SampleSink can be distinguished
+	s.name = fmt.Sprintf("SampleSink(%s)", name) // Always specify a name here
+
+	// Set defaults in s.config
+	// Allow overwriting these defaults by reading config JSON
+
+	// Read in the config JSON
+	if len(config) > 0 {
+		d := json.NewDecoder(bytes.NewReader(config))
+		d.DisallowUnknownFields()
+		if err := d.Decode(&s.config); err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+
+	// Create lookup map to use meta infos as tags in the output metric
+	s.meta_as_tags = make(map[string]bool)
+	for _, k := range s.config.MetaAsTags {
+		s.meta_as_tags[k] = true
+	}
+
+	// Check if all required fields in the config are set
+	// E.g. use 'len(s.config.Option) > 0' for string settings
+
+	// Establish connection to the server, library, ...
+	// Check required files exist and lookup path(s) of executable(s)
+
+	// Return (nil, meaningful error message) in case of errors
+	return s, nil
+}

sinks/sinkManager.go

@@ -0,0 +1,184 @@
+package sinks
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+	"sync"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+const SINK_MAX_FORWARD = 50
+
+// Map of all available sinks
+var AvailableSinks = map[string]func(name string, config json.RawMessage) (Sink, error){
+	"ganglia":     NewGangliaSink,
+	"libganglia":  NewLibgangliaSink,
+	"stdout":      NewStdoutSink,
+	"nats":        NewNatsSink,
+	"influxdb":    NewInfluxSink,
+	"influxasync": NewInfluxAsyncSink,
+	"http":        NewHttpSink,
+}
+
+// Metric collector manager data structure
+type sinkManager struct {
+	input      chan lp.CCMetric // input channel
+	done       chan bool        // channel to finish / stop metric sink manager
+	wg         *sync.WaitGroup  // wait group for all goroutines in cc-metric-collector
+	sinks      map[string]Sink  // Mapping sink name to sink
+	maxForward int              // number of metrics to write maximally in one iteration
+}
+
+// Sink manager access functions
+type SinkManager interface {
+	Init(wg *sync.WaitGroup, sinkConfigFile string) error
+	AddInput(input chan lp.CCMetric)
+	AddOutput(name string, config json.RawMessage) error
+	Start()
+	Close()
+}
+
+// Init initializes the sink manager by:
+// * Reading its configuration file
+// * Adding the configured sinks and providing them with the corresponding config
+func (sm *sinkManager) Init(wg *sync.WaitGroup, sinkConfigFile string) error {
+	sm.input = nil
+	sm.done = make(chan bool)
+	sm.wg = wg
+	sm.sinks = make(map[string]Sink, 0)
+	sm.maxForward = SINK_MAX_FORWARD
+
+	if len(sinkConfigFile) == 0 {
+		return nil
+	}
+
+	// Read sink config file
+	configFile, err := os.Open(sinkConfigFile)
+	if err != nil {
+		cclog.ComponentError("SinkManager", err.Error())
+		return err
+	}
+	defer configFile.Close()
+
+	// Parse config
+	jsonParser := json.NewDecoder(configFile)
+	var rawConfigs map[string]json.RawMessage
+	err = jsonParser.Decode(&rawConfigs)
+	if err != nil {
+		cclog.ComponentError("SinkManager", err.Error())
+		return err
+	}
+
+	// Start sinks
+	for name, raw := range rawConfigs {
+		err = sm.AddOutput(name, raw)
+		if err != nil {
+			cclog.ComponentError("SinkManager", err)
+			continue
+		}
+	}
+
+	// Check that at least one sink is running
+	if !(len(sm.sinks) > 0) {
+		cclog.ComponentError("SinkManager", "Found no usable sinks")
+		return fmt.Errorf("found no usable sinks")
+	}
+
+	return nil
+}
+
+// Start starts the sink managers background task, which
+// distributes received metrics to the sinks
+func (sm *sinkManager) Start() {
+	sm.wg.Add(1)
+	go func() {
+		defer sm.wg.Done()
+
+		// Sink manager is done
+		done := func() {
+			for _, s := range sm.sinks {
+				s.Close()
+			}
+
+			close(sm.done)
+			cclog.ComponentDebug("SinkManager", "DONE")
+		}
+
+		toTheSinks := func(p lp.CCMetric) {
+			// Send received metric to all outputs
+			cclog.ComponentDebug("SinkManager", "WRITE", p)
+			for _, s := range sm.sinks {
+				if err := s.Write(p); err != nil {
+					cclog.ComponentError("SinkManager", "WRITE", s.Name(), "write failed:", err.Error())
+				}
+			}
+		}
+
+		for {
+			select {
+			case <-sm.done:
+				done()
+				return
+
+			case p := <-sm.input:
+				toTheSinks(p)
+				for i := 0; len(sm.input) > 0 && i < sm.maxForward; i++ {
+					p := <-sm.input
+					toTheSinks(p)
+				}
+			}
+		}
+	}()
+
+	// Sink manager is started
+	cclog.ComponentDebug("SinkManager", "STARTED")
+}
+
+// AddInput adds the input channel to the sink manager
+func (sm *sinkManager) AddInput(input chan lp.CCMetric) {
+	sm.input = input
+}
+
+func (sm *sinkManager) AddOutput(name string, rawConfig json.RawMessage) error {
+	var err error
+	var sinkConfig defaultSinkConfig
+	if len(rawConfig) > 0 {
+		err := json.Unmarshal(rawConfig, &sinkConfig)
+		if err != nil {
+			return err
+		}
+	}
+	if _, found := AvailableSinks[sinkConfig.Type]; !found {
+		cclog.ComponentError("SinkManager", "SKIP", name, "unknown sink:", sinkConfig.Type)
+		return err
+	}
+	s, err := AvailableSinks[sinkConfig.Type](name, rawConfig)
+	if err != nil {
+		cclog.ComponentError("SinkManager", "SKIP", name, "initialization failed:", err.Error())
+		return err
+	}
+	sm.sinks[name] = s
+	cclog.ComponentDebug("SinkManager", "ADD SINK", s.Name(), "with name", fmt.Sprintf("'%s'", name))
+	return nil
+}
+
+// Close finishes / stops the sink manager
+func (sm *sinkManager) Close() {
+	cclog.ComponentDebug("SinkManager", "CLOSE")
+	sm.done <- true
+	// wait for close of channel sm.done
+	<-sm.done
+}
+
+// New creates a new initialized sink manager
+func New(wg *sync.WaitGroup, sinkConfigFile string) (SinkManager, error) {
+	sm := new(sinkManager)
+	err := sm.Init(wg, sinkConfigFile)
+	if err != nil {
+		return nil, err
+	}
+	return sm, err
+}

sinks/stdoutSink.go

@@ -0,0 +1,77 @@
+package sinks
+
+import (
+	"bytes"
+	"encoding/json"
+	"fmt"
+	"os"
+	"strings"
+
+	//	"time"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+type StdoutSink struct {
+	sink   // meta_as_tags, name
+	output *os.File
+	config struct {
+		defaultSinkConfig
+		Output string `json:"output_file,omitempty"`
+	}
+}
+
+func (s *StdoutSink) Write(m lp.CCMetric) error {
+	fmt.Fprint(
+		s.output,
+		m.ToLineProtocol(s.meta_as_tags),
+	)
+	return nil
+}
+
+func (s *StdoutSink) Flush() error {
+	s.output.Sync()
+	return nil
+}
+
+func (s *StdoutSink) Close() {
+	if s.output != os.Stdout && s.output != os.Stderr {
+		s.output.Close()
+	}
+}
+
+func NewStdoutSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(StdoutSink)
+	s.name = fmt.Sprintf("StdoutSink(%s)", name)
+	if len(config) > 0 {
+		d := json.NewDecoder(bytes.NewReader(config))
+		d.DisallowUnknownFields()
+		if err := d.Decode(&s.config); err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+
+	s.output = os.Stdout
+	if len(s.config.Output) > 0 {
+		switch strings.ToLower(s.config.Output) {
+		case "stdout":
+			s.output = os.Stdout
+		case "stderr":
+			s.output = os.Stderr
+		default:
+			f, err := os.OpenFile(s.config.Output, os.O_CREATE|os.O_WRONLY, os.FileMode(0600))
+			if err != nil {
+				return nil, err
+			}
+			s.output = f
+		}
+	}
+	// Create lookup map to use meta infos as tags in the output metric
+	s.meta_as_tags = make(map[string]bool)
+	for _, k := range s.config.MetaAsTags {
+		s.meta_as_tags[k] = true
+	}
+
+	return s, nil
+}

sinks/stdoutSink.md

@@ -0,0 +1,22 @@
+## `stdout` sink
+
+The `stdout` sink is the most simple sink provided by cc-metric-collector. It writes all metrics in InfluxDB line-procol format to the configurable output file or the common special files `stdout` and `stderr`.
+
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "stdout",
+    "meta_as_tags" : [],
+    "output_file" : "mylogfile.log"
+  }
+}
+```
+
+- `type`: makes the sink an `stdout` sink
+- `meta_as_tags`: print meta information as tags in the output (optional)
+- `output_file`: Write all data to the selected file (optional). There are two 'special' files: `stdout` and `stderr`. If this option is not provided, the default value is `stdout`
+
+