Set proper user for files

.github/workflows/AlmaLinux.yml

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

.github/workflows/RedHatUniversalBaseImage.yml

@@ -0,0 +1,64 @@
+# See: https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions
+
+# Workflow name
+name: Red Hat Universal Base Image 8 RPM build
+
+# Run on tag push
+on:
+ push:
+  tags:
+  - '**'
+
+jobs:
+
+  #
+  # Build on UBI 8 using go-toolset
+  #
+  UBI-8-RPM-build:
+    runs-on: ubuntu-latest
+    # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
+    container: registry.access.redhat.com/ubi8/ubi:8.5-226.1645809065
+    steps:
+
+    # Use dnf to install development packages
+    - name: Install development packages
+      run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros rpm-build-libs rpm-libs gcc make python38 git
+
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v2
+      with:
+        submodules: recursive
+        fetch-depth: 0
+
+    # Use dnf to install build dependencies
+    - name: Install build dependencies
+      run: dnf --assumeyes --disableplugin=subscription-manager builddep scripts/cc-metric-collector.spec
+
+    - name: RPM build MetricCollector
+      id: rpmbuild
+      run: make RPM
+
+    # See: https://github.com/actions/upload-artifact
+    - name: Save RPM as artifact
+      uses: actions/upload-artifact@v2
+      with:
+        name: cc-metric-collector RPM for UBI 8
+        path: ${{ steps.rpmbuild.outputs.RPM }}
+    - name: Save SRPM as artifact
+      uses: actions/upload-artifact@v2
+      with:
+        name: cc-metric-collector SRPM for UBI 8
+        path: ${{ steps.rpmbuild.outputs.SRPM }}
+
+    # See: https://github.com/softprops/action-gh-release
+    - name: Release
+      uses: softprops/action-gh-release@v1
+      if: startsWith(github.ref, 'refs/tags/')
+      with:
+        name: cc-metric-collector-${{github.ref_name}}
+        files: |
+         ${{ steps.rpmbuild.outputs.RPM }}
+         ${{ steps.rpmbuild.outputs.SRPM }}

.github/workflows/Release.yml

@@ -1,184 +0,0 @@
-# See: https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions
-
-# Workflow name
-name: Release
-
-# Run on tag push
-on:
- push:
-  tags:
-  - '**'
-
-jobs:
-
-  #
-  # Build on AlmaLinux 8.5 using go-toolset
-  #
-  AlmaLinux-RPM-build:
-    runs-on: ubuntu-latest
-    # See: https://hub.docker.com/_/almalinux
-    container: almalinux:8.5
-    # The job outputs link to the outputs of the 'rpmrename' step
-    # Only job outputs can be used in child jobs
-    outputs:
-      rpm : ${{steps.rpmrename.outputs.RPM}}
-      srpm : ${{steps.rpmrename.outputs.SRPM}}
-    steps:
-
-    # Use dnf to install development packages
-    - name: Install development packages
-      run: dnf --assumeyes group install "Development Tools" "RPM Development Tools"
-
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: dnf --assumeyes builddep scripts/cc-metric-collector.spec
-
-    - name: RPM build MetricCollector
-      id: rpmbuild
-      run: make RPM
-    
-    # AlmaLinux 8.5 is a derivate of RedHat Enterprise Linux 8 (UBI8),
-    # so the created RPM both contain the substring 'el8' in the RPM file names
-    # This step replaces the substring 'el8' to 'alma85'. It uses the move operation
-    # because it is unclear whether the default AlmaLinux 8.5 container contains the 
-    # 'rename' command. This way we also get the new names for output.
-    - name: Rename RPMs (s/el8/alma85/)
-      id: rpmrename
-      run: |
-        OLD_RPM="${{steps.rpmbuild.outputs.RPM}}"
-        OLD_SRPM="${{steps.rpmbuild.outputs.SRPM}}"
-        NEW_RPM="${OLD_RPM/el8/alma85}"
-        NEW_SRPM=${OLD_SRPM/el8/alma85}
-        mv "${OLD_RPM}" "${NEW_RPM}"
-        mv "${OLD_SRPM}" "${NEW_SRPM}"
-        echo "::set-output name=SRPM::${NEW_SRPM}"
-        echo "::set-output name=RPM::${NEW_RPM}"
-
-    # See: https://github.com/actions/upload-artifact
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector RPM for AlmaLinux 8.5
-        path: ${{ steps.rpmrename.outputs.RPM }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector SRPM for AlmaLinux 8.5
-        path: ${{ steps.rpmrename.outputs.SRPM }}
-
-  #
-  # Build on UBI 8 using go-toolset
-  #
-  UBI-8-RPM-build:
-    runs-on: ubuntu-latest
-    # See: https://catalog.redhat.com/software/containers/ubi8/ubi/5c359854d70cc534b3a3784e?container-tabs=gti
-    container: registry.access.redhat.com/ubi8/ubi:8.5-226.1645809065
-    # The job outputs link to the outputs of the 'rpmbuild' step
-    outputs:
-      rpm : ${{steps.rpmbuild.outputs.RPM}}
-      srpm : ${{steps.rpmbuild.outputs.SRPM}}
-    steps:
-
-    # Use dnf to install development packages
-    - name: Install development packages
-      run: dnf --assumeyes --disableplugin=subscription-manager install rpm-build go-srpm-macros rpm-build-libs rpm-libs gcc make python38 git
-
-    # Checkout git repository and submodules
-    # fetch-depth must be 0 to use git describe
-    # See: https://github.com/marketplace/actions/checkout
-    - name: Checkout
-      uses: actions/checkout@v2
-      with:
-        submodules: recursive
-        fetch-depth: 0
-
-    # Use dnf to install build dependencies
-    - name: Install build dependencies
-      run: dnf --assumeyes --disableplugin=subscription-manager builddep scripts/cc-metric-collector.spec
-
-    - name: RPM build MetricCollector
-      id: rpmbuild
-      run: make RPM
-
-    # See: https://github.com/actions/upload-artifact
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector RPM for UBI 8
-        path: ${{ steps.rpmbuild.outputs.RPM }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v2
-      with:
-        name: cc-metric-collector SRPM for UBI 8
-        path: ${{ steps.rpmbuild.outputs.SRPM }}
-
-  #
-  # Create release with fresh RPMs
-  #
-  Release:
-    runs-on: ubuntu-latest
-    # We need the RPMs, so add dependency
-    needs: [AlmaLinux-RPM-build, UBI-8-RPM-build]
-
-    steps:
-    # See: https://github.com/actions/download-artifact
-    - name: Download AlmaLinux 8.5 RPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-metric-collector RPM for AlmaLinux 8.5
-    - name: Download AlmaLinux 8.5 SRPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-metric-collector SRPM for AlmaLinux 8.5
-    
-    - name: Download UBI 8 RPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-metric-collector RPM for UBI 8
-    - name: Download UBI 8 SRPM
-      uses: actions/download-artifact@v2
-      with:
-        name: cc-metric-collector SRPM for UBI 8
-
-    # The download actions do not publish the name of the downloaded file,
-    # so we re-use the job outputs of the parent jobs. The files are all
-    # downloaded to the current folder.
-    # The gh-release action afterwards does not accept file lists but all
-    # files have to be listed at 'files'. The step creates one output per
-    # RPM package (2 per distro)
-    - name: Set RPM variables
-      id: files
-      run: |
-        ALMA_85_RPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.rpm}}")
-        ALMA_85_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
-        UBI_8_RPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.rpm}}")
-        UBI_8_SRPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.srpm}}")
-        echo "ALMA_85_RPM::${ALMA_85_RPM}"
-        echo "ALMA_85_SRPM::${ALMA_85_SRPM}"
-        echo "UBI_8_RPM::${UBI_8_RPM}"
-        echo "UBI_8_SRPM::${UBI_8_SRPM}"
-        echo "::set-output name=ALMA_85_RPM::${ALMA_85_RPM}"
-        echo "::set-output name=ALMA_85_SRPM::${ALMA_85_SRPM}"
-        echo "::set-output name=UBI_8_RPM::${UBI_8_RPM}"
-        echo "::set-output name=UBI_8_SRPM::${UBI_8_SRPM}"
-
-    # See: https://github.com/softprops/action-gh-release
-    - name: Release
-      uses: softprops/action-gh-release@v1
-      if: startsWith(github.ref, 'refs/tags/')
-      with:
-        name: cc-metric-collector-${{github.ref_name}}
-        files: |
-         ${{ steps.files.outputs.ALMA_85_RPM }}
-         ${{ steps.files.outputs.ALMA_85_SRPM }}
-         ${{ steps.files.outputs.UBI_8_RPM }}
-         ${{ steps.files.outputs.UBI_8_SRPM }}

Makefile

@@ -15,8 +15,6 @@ COMPONENT_DIRS   := collectors \
 			internal/ccTopology \
 			internal/multiChanTicker
 
-BINDIR = bin
-
 
 .PHONY: all
 all: $(APP)
@@ -26,27 +24,15 @@ $(APP): $(GOSRC)
 	go get
 	go build -o $(APP) $(GOSRC_APP)
 
-install: $(APP)
-	@WORKSPACE=$(PREFIX)
-	@if [ -z "$${WORKSPACE}" ]; then exit 1; fi
-	@mkdir --parents --verbose $${WORKSPACE}/usr/$(BINDIR)
-	@install -Dpm 755 $(APP) $${WORKSPACE}/usr/$(BINDIR)/$(APP)
-	@mkdir --parents --verbose $${WORKSPACE}/etc/cc-metric-collector $${WORKSPACE}/etc/default $${WORKSPACE}/etc/systemd/system $${WORKSPACE}/etc/init.d
-	@install -Dpm 600 config.json $${WORKSPACE}/etc/cc-metric-collector/cc-metric-collector.json
-	@sed -i -e s+"\"./"+"\"/etc/cc-metric-collector/"+g $${WORKSPACE}/etc/cc-metric-collector/cc-metric-collector.json
-	@install -Dpm 600 sinks.json $${WORKSPACE}/etc/cc-metric-collector/sinks.json
-	@install -Dpm 600 collectors.json $${WORKSPACE}/etc/cc-metric-collector/collectors.json
-	@install -Dpm 600 router.json $${WORKSPACE}/etc/cc-metric-collector/router.json
-	@install -Dpm 600 receivers.json $${WORKSPACE}/etc/cc-metric-collector/receivers.json
-	@install -Dpm 600 scripts/cc-metric-collector.config $${WORKSPACE}/etc/default/cc-metric-collector
-	@install -Dpm 644 scripts/cc-metric-collector.service $${WORKSPACE}/etc/systemd/system/cc-metric-collector.service
-	@install -Dpm 644 scripts/cc-metric-collector.init $${WORKSPACE}/etc/init.d/cc-metric-collector
-
-
 .PHONY: clean
 .ONESHELL:
 clean:
-	@for COMP in $(COMPONENT_DIRS); do if [ -e $$COMP/Makefile ]; then make -C $$COMP clean;  fi; done
+	@for COMP in $(COMPONENT_DIRS)
+	do
+	    if [[ -e $$COMP/Makefile ]]; then
+	        make -C $$COMP clean
+	    fi
+	done
 	rm -f $(APP)
 
 .PHONY: fmt
@@ -83,7 +69,7 @@ RPM: scripts/cc-metric-collector.spec
 	@COMMITISH="HEAD"
 	@VERS=$$(git describe --tags $${COMMITISH})
 	@VERS=$${VERS#v}
-	@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
+	@VERS=$${VERS//-/_}
 	@eval $$(rpmspec --query --queryformat "NAME='%{name}' VERSION='%{version}' RELEASE='%{release}' NVR='%{NVR}' NVRA='%{NVRA}'" --define="VERS $${VERS}" "$${SPECFILE}")
 	@PREFIX="$${NAME}-$${VERSION}"
 	@FORMAT="tar.gz"
@@ -100,28 +86,3 @@ RPM: scripts/cc-metric-collector.spec
 	@     echo "::set-output name=SRPM::$${SRPMFILE}"
 	@     echo "::set-output name=RPM::$${RPMFILE}"
 	@fi
-
-.PHONY: DEB
-DEB: scripts/cc-metric-collector.deb.control $(APP)
-	@BASEDIR=$${PWD}
-	@WORKSPACE=$${PWD}/.dpkgbuild
-	@DEBIANDIR=$${WORKSPACE}/debian
-	@DEBIANBINDIR=$${WORKSPACE}/DEBIAN
-	@mkdir --parents --verbose $$WORKSPACE $$DEBIANBINDIR
-	#@mkdir --parents --verbose $$DEBIANDIR
-	@CONTROLFILE="$${BASEDIR}/scripts/cc-metric-collector.deb.control"
-	@COMMITISH="HEAD"
-	@VERS=$$(git describe --tags --abbrev=0 $${COMMITISH})
-	@VERS=$${VERS#v}
-	@VERS=$$(echo $$VERS | sed -e s+'-'+'_'+g)
-	@ARCH=$$(uname -m)
-	@ARCH=$$(echo $$ARCH | sed -e s+'_'+'-'+g)
-	@PREFIX="$${NAME}-$${VERSION}_$${ARCH}"
-	@SIZE_BYTES=$$(du -bcs --exclude=.dpkgbuild "$$WORKSPACE"/ | awk '{print $$1}' | head -1 | sed -e 's/^0\+//')
-	@SIZE="$$(awk -v size="$$SIZE_BYTES" 'BEGIN {print (size/1024)+1}' | awk '{print int($$0)}')"
-	#@sed -e s+"{VERSION}"+"$$VERS"+g -e s+"{INSTALLED_SIZE}"+"$$SIZE"+g -e s+"{ARCH}"+"$$ARCH"+g $$CONTROLFILE > $${DEBIANDIR}/control
-	@sed -e s+"{VERSION}"+"$$VERS"+g -e s+"{INSTALLED_SIZE}"+"$$SIZE"+g -e s+"{ARCH}"+"$$ARCH"+g $$CONTROLFILE > $${DEBIANBINDIR}/control
-	@make PREFIX=$${WORKSPACE} install
-	@DEB_FILE="cc-metric-collector_$${VERS}_$${ARCH}.deb"
-	@dpkg-deb -b $${WORKSPACE} "$$DEB_FILE"
-	@rm -r "$${WORKSPACE}"

collectors.json

@@ -12,12 +12,6 @@
             "proc_total"
         ]
     },
-    "netstat": {
-        "include_devices": [
-            "enp5s0"
-        ],
-        "send_derived_values": true
-    },
     "numastats": {},
     "nvidia": {},
     "tempstat": {

collectors/Makefile

@@ -1,25 +1,79 @@
+# Use central installation
+CENTRAL_INSTALL = false
+# How to access hardware performance counters through LIKWID.
+# Recommended is 'direct' mode
+ACCESSMODE = direct
 
-all: likwid
-
-
-# LIKWID version
+#######################################################################
+# if CENTRAL_INSTALL == true
+#######################################################################
+# Path to central installation (if CENTRAL_INSTALL=true)
+LIKWID_BASE=/apps/likwid/5.2.1
+# LIKWID version (should be same major version as central installation, 5.2.x)
 LIKWID_VERSION = 5.2.1
 
-.ONESHELL:
-.PHONY: likwid
-likwid:
-	INSTALL_FOLDER="$${PWD}/likwid"
-	BUILD_FOLDER="$${PWD}/likwidbuild"
-	if [ -d $${INSTALL_FOLDER} ]; then rm -r $${INSTALL_FOLDER}; fi
-	mkdir --parents --verbose  $${INSTALL_FOLDER} $${BUILD_FOLDER}
-	wget -P "$${BUILD_FOLDER}" ftp://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz
-	tar -C $${BUILD_FOLDER} -xf $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION).tar.gz
-	install -Dpm 0644 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/likwid*.h $${INSTALL_FOLDER}/
-	install -Dpm 0644 $${BUILD_FOLDER}/likwid-$(LIKWID_VERSION)/src/includes/bstrlib.h $${INSTALL_FOLDER}/
-	rm -r $${BUILD_FOLDER}
+#######################################################################
+# if CENTRAL_INSTALL == false and ACCESSMODE == accessdaemon
+#######################################################################
+# Where to install the accessdaemon
+DAEMON_INSTALLDIR = /usr/local
+# Which user to use for the accessdaemon
+DAEMON_USER = root
+# Which group to use for the accessdaemon
+DAEMON_GROUP = root
 
 
-clean:
+
+#################################################
+# No need to change anything below this line
+#################################################
+INSTALL_FOLDER = ./likwid
+BUILD_FOLDER = ./likwid/build
+
+ifneq ($(strip $(CENTRAL_INSTALL)),true)
+LIKWID_BASE := $(shell pwd)/$(INSTALL_FOLDER)
+DAEMON_BASE := $(LIKWID_BASE)
+GROUPS_BASE := $(LIKWID_BASE)/groups
+all: $(INSTALL_FOLDER)/liblikwid.a cleanup
+else
+DAEMON_BASE= $(LIKWID_BASE)/sbin
+all: $(INSTALL_FOLDER)/liblikwid.a cleanup
+endif
+
+
+
+$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz: $(BUILD_FOLDER)
+	wget -P $(BUILD_FOLDER) ftp://ftp.rrze.uni-erlangen.de/mirrors/likwid/likwid-$(LIKWID_VERSION).tar.gz
+
+$(BUILD_FOLDER):
+	mkdir -p $(BUILD_FOLDER)
+
+$(INSTALL_FOLDER):
+	mkdir -p $(INSTALL_FOLDER)
+
+$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION): $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz
+	tar -C $(BUILD_FOLDER) -xf $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz
+
+$(INSTALL_FOLDER)/liblikwid.a: $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION) $(INSTALL_FOLDER)
+	cd "$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)" && make "PREFIX=$(LIKWID_BASE)" "SHARED_LIBRARY=false" "ACCESSMODE=$(ACCESSMODE)" "INSTALLED_ACCESSDAEMON=$(DAEMON_INSTALLDIR)/likwid-accessD"
+	cp \
+	    $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/liblikwid.a \
+	    $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/ext/hwloc/liblikwid-hwloc.a \
+	    $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/src/includes/likwid*.h \
+	    $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/src/includes/bstrlib.h \
+	    $(INSTALL_FOLDER)
+
+$(DAEMON_INSTALLDIR)/likwid-accessD: $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/likwid-accessD
+	sudo -u $(DAEMON_USER) -g $(DAEMON_GROUP) install -m 4775 $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/likwid-accessD $(DAEMON_INSTALLDIR)/likwid-accessD
+
+prepare_collector: likwidMetric.go
+	cp likwidMetric.go likwidMetric.go.orig
+	sed -i -e s+"const GROUPPATH =.*"+"const GROUPPATH = \`$(GROUPS_BASE)\`"+g likwidMetric.go
+
+cleanup:
+	rm -rf $(BUILD_FOLDER)
+
+clean: cleanup
 	rm -rf likwid
 
 .PHONY: clean

collectors/README.md

@@ -37,8 +37,6 @@ In contrast to the configuration files for sinks and receivers, the collectors c
 * [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
 * [`numastat`](./numastatMetric.md)
 * [`gpfs`](./gpfsMetric.md)
-* [`beegfs_meta`](./beegfsmetaMetric.md)
-* [`beegfs_storage`](./beegfsstorageMetric.md)
 
 ## Todos
 

collectors/beegfsmetaMetric.go

@@ -1,229 +0,0 @@
-package collectors
-
-import (
-	"bufio"
-	"bytes"
-	"encoding/json"
-	"fmt"
-	"io/ioutil"
-	"os"
-	"os/exec"
-	"os/user"
-	"regexp"
-	"strconv"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-)
-
-const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
-
-// Struct for the collector-specific JSON config
-type BeegfsMetaCollectorConfig struct {
-	Beegfs            string   `json:"beegfs_path"`
-	ExcludeMetrics    []string `json:"exclude_metrics,omitempty"`
-	ExcludeFilesystem []string `json:"exclude_filesystem"`
-}
-
-type BeegfsMetaCollector struct {
-	metricCollector
-	tags    map[string]string
-	matches map[string]string
-	config  BeegfsMetaCollectorConfig
-	skipFS  map[string]struct{}
-}
-
-func (m *BeegfsMetaCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-	// Metrics
-	var nodeMdstat_array = [39]string{
-		"sum", "ack", "close", "entInf",
-		"fndOwn", "mkdir", "create", "rddir",
-		"refrEn", "mdsInf", "rmdir", "rmLnk",
-		"mvDirIns", "mvFiIns", "open", "ren",
-		"sChDrct", "sAttr", "sDirPat", "stat",
-		"statfs", "trunc", "symlnk", "unlnk",
-		"lookLI", "statLI", "revalLI", "openLI",
-		"createLI", "hardlnk", "flckAp", "flckEn",
-		"flckRg", "dirparent", "listXA", "getXA",
-		"rmXA", "setXA", "mirror"}
-
-	m.name = "BeegfsMetaCollector"
-	m.setup()
-	// Set default beegfs-ctl binary
-
-	m.config.Beegfs = DEFAULT_BEEGFS_CMD
-
-	// Read JSON configuration
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &m.config)
-		if err != nil {
-			return err
-		}
-	}
-
-	//create map with possible variables
-	m.matches = make(map[string]string)
-	for _, value := range nodeMdstat_array {
-		_, skip := stringArrayContains(m.config.ExcludeMetrics, value)
-		if skip {
-			m.matches["other"] = "0"
-		} else {
-			m.matches["beegfs_cmeta_"+value] = "0"
-		}
-	}
-
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "BeegfsMeta",
-	}
-	m.tags = map[string]string{
-		"type":       "node",
-		"filesystem": "",
-	}
-	m.skipFS = make(map[string]struct{})
-	for _, fs := range m.config.ExcludeFilesystem {
-		m.skipFS[fs] = struct{}{}
-	}
-
-	// Beegfs file system statistics can only be queried by user root
-	user, err := user.Current()
-	if err != nil {
-		return fmt.Errorf("BeegfsMetaCollector.Init(): Failed to get current user: %v", err)
-	}
-	if user.Uid != "0" {
-		return fmt.Errorf("BeegfsMetaCollector.Init(): BeeGFS file system statistics can only be queried by user root")
-	}
-
-	// Check if beegfs-ctl is in executable search path
-	_, err = exec.LookPath(m.config.Beegfs)
-	if err != nil {
-		return fmt.Errorf("BeegfsMetaCollector.Init(): Failed to find beegfs-ctl binary '%s': %v", m.config.Beegfs, err)
-	}
-	m.init = true
-	return nil
-}
-
-func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	if !m.init {
-		return
-	}
-	//get mounpoint
-	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
-	mounts := strings.Split(string(buffer), "\n")
-	var mountpoints []string
-	for _, line := range mounts {
-		if len(line) == 0 {
-			continue
-		}
-		f := strings.Fields(line)
-		if strings.Contains(f[0], "beegfs_ondemand") {
-			// Skip excluded filesystems
-			if _, skip := m.skipFS[f[1]]; skip {
-				continue
-			}
-			mountpoints = append(mountpoints, f[1])
-		}
-	}
-
-	if len(mountpoints) == 0 {
-		return
-	}
-
-	for _, mountpoint := range mountpoints {
-		m.tags["filesystem"] = mountpoint
-
-		// bwwgfs-ctl:
-		// --clientstats: Show client IO statistics.
-		// --nodetype=meta: The node type to query (meta, storage).
-		// --interval:
-		// --mount=/mnt/beeond/: Which mount point
-		//cmd := exec.Command(m.config.Beegfs, "/root/mc/test.txt")
-		mountoption := "--mount=" + mountpoint
-		cmd := exec.Command(m.config.Beegfs, "--clientstats",
-			"--nodetype=meta", mountoption, "--allstats")
-		cmd.Stdin = strings.NewReader("\n")
-		cmdStdout := new(bytes.Buffer)
-		cmdStderr := new(bytes.Buffer)
-		cmd.Stdout = cmdStdout
-		cmd.Stderr = cmdStderr
-		err := cmd.Run()
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
-			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
-			data, _ := ioutil.ReadAll(cmdStderr)
-			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = ioutil.ReadAll(cmdStdout)
-			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stdout: \"%s\"\n", string(data))
-			return
-		}
-		// Read I/O statistics
-		scanner := bufio.NewScanner(cmdStdout)
-
-		sumLine := regexp.MustCompile(`^Sum:\s+\d+\s+\[[a-zA-Z]+\]+`)
-		//Line := regexp.MustCompile(`^(.*)\s+(\d)+\s+\[([a-zA-Z]+)\]+`)
-		statsLine := regexp.MustCompile(`^(.*?)\s+?(\d.*?)$`)
-		singleSpacePattern := regexp.MustCompile(`\s+`)
-		removePattern := regexp.MustCompile(`[\[|\]]`)
-
-		for scanner.Scan() {
-			readLine := scanner.Text()
-			//fmt.Println(readLine)
-			// Jump few lines, we only want the I/O stats from nodes
-			if !sumLine.MatchString(readLine) {
-				continue
-			}
-
-			match := statsLine.FindStringSubmatch(readLine)
-			// nodeName = "Sum:" or would be nodes
-			// nodeName := match[1]
-			//Remove multiple whitespaces
-			dummy := removePattern.ReplaceAllString(match[2], " ")
-			metaStats := strings.TrimSpace(singleSpacePattern.ReplaceAllString(dummy, " "))
-			split := strings.Split(metaStats, " ")
-
-			// fill map with values
-			// split[i+1] = mdname
-			// split[i] = amount of md operations
-			for i := 0; i <= len(split)-1; i += 2 {
-				if _, ok := m.matches[split[i+1]]; ok {
-					m.matches["beegfs_cmeta_"+split[i+1]] = split[i]
-				} else {
-					f1, err := strconv.ParseFloat(m.matches["other"], 32)
-					if err != nil {
-						cclog.ComponentError(
-							m.name,
-							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
-						continue
-					}
-					f2, err := strconv.ParseFloat(split[i], 32)
-					if err != nil {
-						cclog.ComponentError(
-							m.name,
-							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
-						continue
-					}
-					//mdStat["other"] = fmt.Sprintf("%f", f1+f2)
-					m.matches["beegfs_cstorage_other"] = fmt.Sprintf("%f", f1+f2)
-				}
-			}
-
-			for key, data := range m.matches {
-				value, _ := strconv.ParseFloat(data, 32)
-				y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-	}
-}
-
-func (m *BeegfsMetaCollector) Close() {
-	m.init = false
-}

collectors/beegfsmetaMetric.md

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

collectors/beegfsstorageMetric.go

@@ -1,221 +0,0 @@
-package collectors
-
-import (
-	"bufio"
-	"bytes"
-	"encoding/json"
-	"fmt"
-	"io/ioutil"
-	"os"
-	"os/exec"
-	"os/user"
-	"regexp"
-	"strconv"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-)
-
-// Struct for the collector-specific JSON config
-type BeegfsStorageCollectorConfig struct {
-	Beegfs            string   `json:"beegfs_path"`
-	ExcludeMetrics    []string `json:"exclude_metrics,omitempty"`
-	ExcludeFilesystem []string `json:"exclude_filesystem"`
-}
-
-type BeegfsStorageCollector struct {
-	metricCollector
-	tags    map[string]string
-	matches map[string]string
-	config  BeegfsStorageCollectorConfig
-	skipFS  map[string]struct{}
-}
-
-func (m *BeegfsStorageCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-	// Metrics
-	var storageStat_array = [18]string{
-		"sum", "ack", "sChDrct", "getFSize",
-		"sAttr", "statfs", "trunc", "close",
-		"fsync", "ops-rd", "MiB-rd/s", "ops-wr",
-		"MiB-wr/s", "gendbg", "hrtbeat", "remNode",
-		"storInf", "unlnk"}
-
-	m.name = "BeegfsStorageCollector"
-	m.setup()
-	// Set default beegfs-ctl binary
-
-	m.config.Beegfs = DEFAULT_BEEGFS_CMD
-
-	// Read JSON configuration
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &m.config)
-		if err != nil {
-			return err
-		}
-	}
-	println(m.config.Beegfs)
-	//create map with possible variables
-	m.matches = make(map[string]string)
-	for _, value := range storageStat_array {
-		_, skip := stringArrayContains(m.config.ExcludeMetrics, value)
-		if skip {
-			m.matches["other"] = "0"
-		} else {
-			m.matches["beegfs_cstorage_"+value] = "0"
-		}
-	}
-
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "BeegfsStorage",
-	}
-	m.tags = map[string]string{
-		"type":       "node",
-		"filesystem": "",
-	}
-	m.skipFS = make(map[string]struct{})
-	for _, fs := range m.config.ExcludeFilesystem {
-		m.skipFS[fs] = struct{}{}
-	}
-
-	// Beegfs file system statistics can only be queried by user root
-	user, err := user.Current()
-	if err != nil {
-		return fmt.Errorf("BeegfsStorageCollector.Init(): Failed to get current user: %v", err)
-	}
-	if user.Uid != "0" {
-		return fmt.Errorf("BeegfsStorageCollector.Init(): BeeGFS file system statistics can only be queried by user root")
-	}
-
-	// Check if beegfs-ctl is in executable search path
-	_, err = exec.LookPath(m.config.Beegfs)
-	if err != nil {
-		return fmt.Errorf("BeegfsStorageCollector.Init(): Failed to find beegfs-ctl binary '%s': %v", m.config.Beegfs, err)
-	}
-	m.init = true
-	return nil
-}
-
-func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	if !m.init {
-		return
-	}
-	//get mounpoint
-	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
-	mounts := strings.Split(string(buffer), "\n")
-	var mountpoints []string
-	for _, line := range mounts {
-		if len(line) == 0 {
-			continue
-		}
-		f := strings.Fields(line)
-		if strings.Contains(f[0], "beegfs_ondemand") {
-			// Skip excluded filesystems
-			if _, skip := m.skipFS[f[1]]; skip {
-				continue
-			}
-			mountpoints = append(mountpoints, f[1])
-		}
-	}
-	if len(mountpoints) == 0 {
-		return
-	}
-	// collects stats for each BeeGFS on Demand FS
-	for _, mountpoint := range mountpoints {
-		m.tags["filesystem"] = mountpoint
-
-		// bwwgfs-ctl:
-		// --clientstats: Show client IO statistics.
-		// --nodetype=meta: The node type to query (meta, storage).
-		// --interval:
-		// --mount=/mnt/beeond/: Which mount point
-		//cmd := exec.Command(m.config.Beegfs, "/root/mc/test.txt")
-		mountoption := "--mount=" + mountpoint
-		cmd := exec.Command(m.config.Beegfs, "--clientstats",
-			"--nodetype=storage", mountoption, "--allstats")
-		cmd.Stdin = strings.NewReader("\n")
-		cmdStdout := new(bytes.Buffer)
-		cmdStderr := new(bytes.Buffer)
-		cmd.Stdout = cmdStdout
-		cmd.Stderr = cmdStderr
-		err := cmd.Run()
-		if err != nil {
-			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
-			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
-			data, _ := ioutil.ReadAll(cmdStderr)
-			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = ioutil.ReadAll(cmdStdout)
-			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stdout: \"%s\"\n", string(data))
-			return
-		}
-		// Read I/O statistics
-		scanner := bufio.NewScanner(cmdStdout)
-
-		sumLine := regexp.MustCompile(`^Sum:\s+\d+\s+\[[a-zA-Z]+\]+`)
-		//Line := regexp.MustCompile(`^(.*)\s+(\d)+\s+\[([a-zA-Z]+)\]+`)
-		statsLine := regexp.MustCompile(`^(.*?)\s+?(\d.*?)$`)
-		singleSpacePattern := regexp.MustCompile(`\s+`)
-		removePattern := regexp.MustCompile(`[\[|\]]`)
-
-		for scanner.Scan() {
-			readLine := scanner.Text()
-			//fmt.Println(readLine)
-			// Jump few lines, we only want the I/O stats from nodes
-			if !sumLine.MatchString(readLine) {
-				continue
-			}
-
-			match := statsLine.FindStringSubmatch(readLine)
-			// nodeName = "Sum:" or would be nodes
-			// nodeName := match[1]
-			//Remove multiple whitespaces
-			dummy := removePattern.ReplaceAllString(match[2], " ")
-			metaStats := strings.TrimSpace(singleSpacePattern.ReplaceAllString(dummy, " "))
-			split := strings.Split(metaStats, " ")
-
-			// fill map with values
-			// split[i+1] = mdname
-			// split[i] = amount of operations
-			for i := 0; i <= len(split)-1; i += 2 {
-				if _, ok := m.matches[split[i+1]]; ok {
-					m.matches["beegfs_cstorage_"+split[i+1]] = split[i]
-					//m.matches[split[i+1]] = split[i]
-				} else {
-					f1, err := strconv.ParseFloat(m.matches["other"], 32)
-					if err != nil {
-						cclog.ComponentError(
-							m.name,
-							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
-						continue
-					}
-					f2, err := strconv.ParseFloat(split[i], 32)
-					if err != nil {
-						cclog.ComponentError(
-							m.name,
-							fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
-						continue
-					}
-					m.matches["beegfs_cstorage_other"] = fmt.Sprintf("%f", f1+f2)
-				}
-			}
-
-			for key, data := range m.matches {
-				value, _ := strconv.ParseFloat(data, 32)
-				y, err := lp.New(key, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-				if err == nil {
-					output <- y
-				}
-			}
-		}
-	}
-}
-
-func (m *BeegfsStorageCollector) Close() {
-	m.init = false
-}

collectors/beegfsstorageMetric.md

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

collectors/collectorManager.go

@@ -19,6 +19,7 @@ var AvailableCollectors = map[string]MetricCollector{
 	"memstat":          new(MemstatCollector),
 	"netstat":          new(NetstatCollector),
 	"ibstat":           new(InfinibandCollector),
+	"ibstat_perfquery": new(InfinibandPerfQueryCollector),
 	"lustrestat":       new(LustreCollector),
 	"cpustat":          new(CpustatCollector),
 	"topprocs":         new(TopProcsCollector),
@@ -34,8 +35,6 @@ var AvailableCollectors = map[string]MetricCollector{
 	"nfs3stat":         new(Nfs3Collector),
 	"nfs4stat":         new(Nfs4Collector),
 	"numastats":        new(NUMAStatsCollector),
-	"beegfs_meta":      new(BeegfsMetaCollector),
-	"beegfs_storage":   new(BeegfsStorageCollector),
 }
 
 // Metric collector manager data structure

collectors/cpufreqCpuinfoMetric.go

@@ -57,7 +57,7 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 	const cpuInfoFile = "/proc/cpuinfo"
 	file, err := os.Open(cpuInfoFile)
 	if err != nil {
-		return fmt.Errorf("failed to open file '%s': %v", cpuInfoFile, err)
+		return fmt.Errorf("Failed to open file '%s': %v", cpuInfoFile, err)
 	}
 	defer file.Close()
 
@@ -106,14 +106,14 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 			topology.coreID = coreID
 			topology.coreID_int, err = strconv.ParseInt(coreID, 10, 64)
 			if err != nil {
-				return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
+				return fmt.Errorf("Unable to convert coreID '%s' to int64: %v", coreID, err)
 			}
 
 			// Physical package ID
 			topology.physicalPackageID = physicalPackageID
 			topology.physicalPackageID_int, err = strconv.ParseInt(physicalPackageID, 10, 64)
 			if err != nil {
-				return fmt.Errorf("unable to convert physicalPackageID '%s' to int64: %v", physicalPackageID, err)
+				return fmt.Errorf("Unable to convert physicalPackageID '%s' to int64: %v", physicalPackageID, err)
 			}
 
 			// increase maximun socket / package ID, when required

collectors/cpufreqMetric.go

@@ -70,10 +70,10 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	globPattern := filepath.Join(baseDir, "cpu[0-9]*")
 	cpuDirs, err := filepath.Glob(globPattern)
 	if err != nil {
-		return fmt.Errorf("unable to glob files with pattern '%s': %v", globPattern, err)
+		return fmt.Errorf("Unable to glob files with pattern '%s': %v", globPattern, err)
 	}
 	if cpuDirs == nil {
-		return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
+		return fmt.Errorf("Unable to find any files with pattern '%s'", globPattern)
 	}
 
 	// Initialize CPU topology
@@ -82,38 +82,38 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 		processor := strings.TrimPrefix(cpuDir, "/sys/devices/system/cpu/cpu")
 		processor_int, err := strconv.ParseInt(processor, 10, 64)
 		if err != nil {
-			return fmt.Errorf("unable to convert cpuID '%s' to int64: %v", processor, err)
+			return fmt.Errorf("Unable to convert cpuID '%s' to int64: %v", processor, err)
 		}
 
 		// Read package ID
 		physicalPackageIDFile := filepath.Join(cpuDir, "topology", "physical_package_id")
 		line, err := ioutil.ReadFile(physicalPackageIDFile)
 		if err != nil {
-			return fmt.Errorf("unable to read physical package ID from file '%s': %v", physicalPackageIDFile, err)
+			return fmt.Errorf("Unable to read physical package ID from file '%s': %v", physicalPackageIDFile, err)
 		}
 		physicalPackageID := strings.TrimSpace(string(line))
 		physicalPackageID_int, err := strconv.ParseInt(physicalPackageID, 10, 64)
 		if err != nil {
-			return fmt.Errorf("unable to convert packageID '%s' to int64: %v", physicalPackageID, err)
+			return fmt.Errorf("Unable to convert packageID '%s' to int64: %v", physicalPackageID, err)
 		}
 
 		// Read core ID
 		coreIDFile := filepath.Join(cpuDir, "topology", "core_id")
 		line, err = ioutil.ReadFile(coreIDFile)
 		if err != nil {
-			return fmt.Errorf("unable to read core ID from file '%s': %v", coreIDFile, err)
+			return fmt.Errorf("Unable to read core ID from file '%s': %v", coreIDFile, err)
 		}
 		coreID := strings.TrimSpace(string(line))
 		coreID_int, err := strconv.ParseInt(coreID, 10, 64)
 		if err != nil {
-			return fmt.Errorf("unable to convert coreID '%s' to int64: %v", coreID, err)
+			return fmt.Errorf("Unable to convert coreID '%s' to int64: %v", coreID, err)
 		}
 
 		// Check access to current frequency file
 		scalingCurFreqFile := filepath.Join(cpuDir, "cpufreq", "scaling_cur_freq")
 		err = unix.Access(scalingCurFreqFile, unix.R_OK)
 		if err != nil {
-			return fmt.Errorf("unable to access file '%s': %v", scalingCurFreqFile, err)
+			return fmt.Errorf("Unable to access file '%s': %v", scalingCurFreqFile, err)
 		}
 
 		t := &m.topology[processor_int]

collectors/cpustatMetric.go

@@ -21,10 +21,11 @@ type CpustatCollectorConfig struct {
 
 type CpustatCollector struct {
 	metricCollector
-	config   CpustatCollectorConfig
-	matches  map[string]int
-	cputags  map[string]map[string]string
-	nodetags map[string]string
+	config          CpustatCollectorConfig
+	matches         map[string]int
+	cputags         map[string]map[string]string
+	nodetags        map[string]string
+	num_cpus_metric lp.CCMetric
 }
 
 func (m *CpustatCollector) Init(config json.RawMessage) error {

collectors/customCmdMetric.go

@@ -61,7 +61,7 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
 		}
 	}
 	if len(m.files) == 0 && len(m.commands) == 0 {
-		return errors.New("no metrics to collect")
+		return errors.New("No metrics to collect")
 	}
 	m.handler = influx.NewMetricHandler()
 	m.parser = influx.NewParser(m.handler)

collectors/diskstatMetric.go

@@ -3,6 +3,7 @@ package collectors
 import (
 	"bufio"
 	"encoding/json"
+	"fmt"
 	"os"
 	"strings"
 	"syscall"
@@ -80,7 +81,8 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric
 		stat := syscall.Statfs_t{}
 		err := syscall.Statfs(path, &stat)
 		if err != nil {
-			continue
+			fmt.Println(err.Error())
+			return
 		}
 		tags := map[string]string{"type": "node", "device": linefields[0]}
 		total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)

collectors/gpfsMetric.go

@@ -17,24 +17,14 @@ import (
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const DEFAULT_GPFS_CMD = "mmpmon"
-
-type GpfsCollectorLastState struct {
-	bytesRead    int64
-	bytesWritten int64
-}
-
 type GpfsCollector struct {
 	metricCollector
 	tags   map[string]string
 	config struct {
 		Mmpmon            string   `json:"mmpmon_path,omitempty"`
 		ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
-		SendBandwidths    bool     `json:"send_bandwidths"`
 	}
-	skipFS        map[string]struct{}
-	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
-	lastState     map[string]GpfsCollectorLastState
+	skipFS map[string]struct{}
 }
 
 func (m *GpfsCollector) Init(config json.RawMessage) error {
@@ -48,7 +38,7 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 	m.setup()
 
 	// Set default mmpmon binary
-	m.config.Mmpmon = DEFAULT_GPFS_CMD
+	m.config.Mmpmon = "/usr/lpp/mmfs/bin/mmpmon"
 
 	// Read JSON configuration
 	if len(config) > 0 {
@@ -70,23 +60,21 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 	for _, fs := range m.config.ExcludeFilesystem {
 		m.skipFS[fs] = struct{}{}
 	}
-	m.lastState = make(map[string]GpfsCollectorLastState)
 
 	// GPFS / IBM Spectrum Scale file system statistics can only be queried by user root
 	user, err := user.Current()
 	if err != nil {
-		return fmt.Errorf("failed to get current user: %v", err)
+		return fmt.Errorf("Failed to get current user: %v", err)
 	}
 	if user.Uid != "0" {
 		return fmt.Errorf("GPFS file system statistics can only be queried by user root")
 	}
 
 	// Check if mmpmon is in executable search path
-	p, err := exec.LookPath(m.config.Mmpmon)
+	_, err = exec.LookPath(m.config.Mmpmon)
 	if err != nil {
-		return fmt.Errorf("failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err)
+		return fmt.Errorf("Failed to find mmpmon binary '%s': %v", m.config.Mmpmon, err)
 	}
-	m.config.Mmpmon = p
 
 	m.init = true
 	return nil
@@ -98,13 +86,6 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 		return
 	}
 
-	// Current time stamp
-	now := time.Now()
-	// time difference to last time stamp
-	timeDiff := now.Sub(m.lastTimestamp).Seconds()
-	// Save current timestamp
-	m.lastTimestamp = now
-
 	// mmpmon:
 	// -p: generate output that can be parsed
 	// -s: suppress the prompt on input
@@ -163,19 +144,8 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 			continue
 		}
 
-		// Add filesystem tag
 		m.tags["filesystem"] = filesystem
 
-		// Create initial last state
-		if m.config.SendBandwidths {
-			if _, ok := m.lastState[filesystem]; !ok {
-				m.lastState[filesystem] = GpfsCollectorLastState{
-					bytesRead:    -1,
-					bytesWritten: -1,
-				}
-			}
-		}
-
 		// return code
 		rc, err := strconv.Atoi(key_value["_rc_"])
 		if err != nil {
@@ -218,14 +188,6 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 		if y, err := lp.New("gpfs_bytes_read", m.tags, m.meta, map[string]interface{}{"value": bytesRead}, timestamp); err == nil {
 			output <- y
 		}
-		if m.config.SendBandwidths {
-			if lastBytesRead := m.lastState[filesystem].bytesRead; lastBytesRead >= 0 {
-				bwRead := float64(bytesRead-lastBytesRead) / timeDiff
-				if y, err := lp.New("gpfs_bw_read", m.tags, m.meta, map[string]interface{}{"value": bwRead}, timestamp); err == nil {
-					output <- y
-				}
-			}
-		}
 
 		// bytes written
 		bytesWritten, err := strconv.ParseInt(key_value["_bw_"], 10, 64)
@@ -238,21 +200,6 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 		if y, err := lp.New("gpfs_bytes_written", m.tags, m.meta, map[string]interface{}{"value": bytesWritten}, timestamp); err == nil {
 			output <- y
 		}
-		if m.config.SendBandwidths {
-			if lastBytesWritten := m.lastState[filesystem].bytesRead; lastBytesWritten >= 0 {
-				bwWrite := float64(bytesWritten-lastBytesWritten) / timeDiff
-				if y, err := lp.New("gpfs_bw_write", m.tags, m.meta, map[string]interface{}{"value": bwWrite}, timestamp); err == nil {
-					output <- y
-				}
-			}
-		}
-
-		if m.config.SendBandwidths {
-			m.lastState[filesystem] = GpfsCollectorLastState{
-				bytesRead:    bytesRead,
-				bytesWritten: bytesWritten,
-			}
-		}
 
 		// number of opens
 		numOpens, err := strconv.ParseInt(key_value["_oc_"], 10, 64)

collectors/gpfsMetric.md

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

collectors/infinibandMetric.go

@@ -16,31 +16,22 @@ import (
 	"time"
 )
 
-const IB_BASEPATH = "/sys/class/infiniband/"
-
-type InfinibandCollectorMetric struct {
-	path string
-	unit string
-}
+const IB_BASEPATH = `/sys/class/infiniband/`
 
 type InfinibandCollectorInfo struct {
-	LID              string                               // IB local Identifier (LID)
-	device           string                               // IB device
-	port             string                               // IB device port
-	portCounterFiles map[string]InfinibandCollectorMetric // mapping counter name -> InfinibandCollectorMetric
-	tagSet           map[string]string                    // corresponding tag list
-	lastState        map[string]int64                     // State from last measurement
+	LID              string            // IB local Identifier (LID)
+	device           string            // IB device
+	port             string            // IB device port
+	portCounterFiles map[string]string // mapping counter name -> sysfs file
+	tagSet           map[string]string // corresponding tag list
 }
 
 type InfinibandCollector struct {
 	metricCollector
 	config struct {
-		ExcludeDevices     []string `json:"exclude_devices,omitempty"` // IB device to exclude e.g. mlx5_0
-		SendAbsoluteValues bool     `json:"send_abs_values"`           // Send absolut values as read from sys filesystem
-		SendDerivedValues  bool     `json:"send_derived_values"`       // Send derived values e.g. rates
+		ExcludeDevices []string `json:"exclude_devices,omitempty"` // IB device to exclude e.g. mlx5_0
 	}
-	info          []*InfinibandCollectorInfo
-	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
+	info []*InfinibandCollectorInfo
 }
 
 // Init initializes the Infiniband collector by walking through files below IB_BASEPATH
@@ -58,11 +49,6 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 		"source": m.name,
 		"group":  "Network",
 	}
-
-	// Set default configuration,
-	m.config.SendAbsoluteValues = true
-	m.config.SendDerivedValues = false
-	// Read configuration file, allow overwriting default config
 	if len(config) > 0 {
 		err = json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -74,10 +60,10 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	globPattern := filepath.Join(IB_BASEPATH, "*", "ports", "*")
 	ibDirs, err := filepath.Glob(globPattern)
 	if err != nil {
-		return fmt.Errorf("unable to glob files with pattern %s: %v", globPattern, err)
+		return fmt.Errorf("Unable to glob files with pattern %s: %v", globPattern, err)
 	}
 	if ibDirs == nil {
-		return fmt.Errorf("unable to find any directories with pattern %s", globPattern)
+		return fmt.Errorf("Unable to find any directories with pattern %s", globPattern)
 	}
 
 	for _, path := range ibDirs {
@@ -111,25 +97,19 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 
 		// Check access to counter files
 		countersDir := filepath.Join(path, "counters")
-		portCounterFiles := map[string]InfinibandCollectorMetric{
-			"ib_recv":      {path: filepath.Join(countersDir, "port_rcv_data"), unit: "bytes"},
-			"ib_xmit":      {path: filepath.Join(countersDir, "port_xmit_data"), unit: "bytes"},
-			"ib_recv_pkts": {path: filepath.Join(countersDir, "port_rcv_packets"), unit: "packets"},
-			"ib_xmit_pkts": {path: filepath.Join(countersDir, "port_xmit_packets"), unit: "packets"},
+		portCounterFiles := map[string]string{
+			"ib_recv":      filepath.Join(countersDir, "port_rcv_data"),
+			"ib_xmit":      filepath.Join(countersDir, "port_xmit_data"),
+			"ib_recv_pkts": filepath.Join(countersDir, "port_rcv_packets"),
+			"ib_xmit_pkts": filepath.Join(countersDir, "port_xmit_packets"),
 		}
-		for _, counter := range portCounterFiles {
-			err := unix.Access(counter.path, unix.R_OK)
+		for _, counterFile := range portCounterFiles {
+			err := unix.Access(counterFile, unix.R_OK)
 			if err != nil {
-				return fmt.Errorf("unable to access %s: %v", counter.path, err)
+				return fmt.Errorf("Unable to access %s: %v", counterFile, err)
 			}
 		}
 
-		// Initialize last state
-		lastState := make(map[string]int64)
-		for counter := range portCounterFiles {
-			lastState[counter] = -1
-		}
-
 		m.info = append(m.info,
 			&InfinibandCollectorInfo{
 				LID:              LID,
@@ -142,12 +122,11 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 					"port":   port,
 					"lid":    LID,
 				},
-				lastState: lastState,
 			})
 	}
 
 	if len(m.info) == 0 {
-		return fmt.Errorf("found no IB devices")
+		return fmt.Errorf("Found no IB devices")
 	}
 
 	m.init = true
@@ -162,27 +141,17 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 		return
 	}
 
-	// Current time stamp
 	now := time.Now()
-	// time difference to last time stamp
-	timeDiff := now.Sub(m.lastTimestamp).Seconds()
-	// Save current timestamp
-	m.lastTimestamp = now
-
 	for _, info := range m.info {
-		for counterName, counterDef := range info.portCounterFiles {
-
-			// Read counter file
-			line, err := ioutil.ReadFile(counterDef.path)
+		for counterName, counterFile := range info.portCounterFiles {
+			line, err := ioutil.ReadFile(counterFile)
 			if err != nil {
 				cclog.ComponentError(
 					m.name,
-					fmt.Sprintf("Read(): Failed to read from file '%s': %v", counterDef.path, err))
+					fmt.Sprintf("Read(): Failed to read from file '%s': %v", counterFile, err))
 				continue
 			}
 			data := strings.TrimSpace(string(line))
-
-			// convert counter to int64
 			v, err := strconv.ParseInt(data, 10, 64)
 			if err != nil {
 				cclog.ComponentError(
@@ -190,26 +159,8 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterName, data, err))
 				continue
 			}
-
-			// Send absolut values
-			if m.config.SendAbsoluteValues {
-				if y, err := lp.New(counterName, info.tagSet, m.meta, map[string]interface{}{"value": v}, now); err == nil {
-					y.AddMeta("unit", counterDef.unit)
-					output <- y
-				}
-			}
-
-			// Send derived values
-			if m.config.SendDerivedValues {
-				if info.lastState[counterName] >= 0 {
-					rate := float64((v - info.lastState[counterName])) / timeDiff
-					if y, err := lp.New(counterName+"_bw", info.tagSet, m.meta, map[string]interface{}{"value": rate}, now); err == nil {
-						y.AddMeta("unit", counterDef.unit+"/sec")
-						output <- y
-					}
-				}
-				// Save current state
-				info.lastState[counterName] = v
+			if y, err := lp.New(counterName, info.tagSet, m.meta, map[string]interface{}{"value": v}, now); err == nil {
+				output <- y
 			}
 		}
 

collectors/infinibandMetric.md

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

collectors/infinibandPerfQueryMetric.go

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

collectors/infinibandPerfQueryMetric.md

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

collectors/ipmiMetric.go

@@ -54,7 +54,7 @@ func (m *IpmiCollector) Init(config json.RawMessage) error {
 		m.ipmisensors = p
 	}
 	if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
-		return errors.New("no IPMI reader found")
+		return errors.New("No IPMI reader found")
 	}
 	m.init = true
 	return nil

collectors/likwidMetric.go

@@ -15,12 +15,9 @@ import (
 	"io/ioutil"
 	"math"
 	"os"
-	"os/signal"
-	"sort"
+	"regexp"
 	"strconv"
 	"strings"
-	"sync"
-	"syscall"
 	"time"
 	"unsafe"
 
@@ -31,6 +28,48 @@ import (
 	"github.com/NVIDIA/go-nvml/pkg/dl"
 )
 
+type MetricScope string
+
+const (
+	METRIC_SCOPE_HWTHREAD = iota
+	METRIC_SCOPE_CORE
+	METRIC_SCOPE_LLC
+	METRIC_SCOPE_NUMA
+	METRIC_SCOPE_DIE
+	METRIC_SCOPE_SOCKET
+	METRIC_SCOPE_NODE
+)
+
+func (ms MetricScope) String() string {
+	return string(ms)
+}
+
+func (ms MetricScope) Likwid() string {
+	LikwidDomains := map[string]string{
+		"cpu":        "",
+		"core":       "",
+		"llc":        "C",
+		"numadomain": "M",
+		"die":        "D",
+		"socket":     "S",
+		"node":       "N",
+	}
+	return LikwidDomains[string(ms)]
+}
+
+func (ms MetricScope) Granularity() int {
+	for i, g := range GetAllMetricScopes() {
+		if ms == g {
+			return i
+		}
+	}
+	return -1
+}
+
+func GetAllMetricScopes() []MetricScope {
+	return []MetricScope{"cpu" /*, "core", "llc", "numadomain", "die",*/, "socket", "node"}
+}
+
 const (
 	LIKWID_LIB_NAME       = "liblikwid.so"
 	LIKWID_LIB_DL_FLAGS   = dl.RTLD_LAZY | dl.RTLD_GLOBAL
@@ -38,26 +77,18 @@ 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, cpu, ...)
-	Publish bool   `json:"publish"`
-	Unit    string `json:"unit"` // Unit of metric if any
+	Name string `json:"name"` // Name of the metric
+	Calc string `json:"calc"` // Calculation for the metric using
+	//Aggr        string      `json:"aggregation"` // if scope unequal to LIKWID metric scope, the values are combined (sum, min, max, mean or avg, median)
+	Scope       MetricScope `json:"scope"` // scope for calculation. subscopes are aggregated using the 'aggregation' function
+	Publish     bool        `json:"publish"`
+	granulatity MetricScope
 }
 
 type LikwidCollectorEventsetConfig struct {
-	Events  map[string]string             `json:"events"`
-	Metrics []LikwidCollectorMetricConfig `json:"metrics"`
-}
-
-type LikwidEventsetConfig struct {
-	internal int
-	gid      C.int
-	eorder   []*C.char
-	estr     *C.char
-	go_estr  string
-	results  map[int]map[string]interface{}
-	metrics  map[int]map[string]float64
+	Events      map[string]string `json:"events"`
+	granulatity map[string]MetricScope
+	Metrics     []LikwidCollectorMetricConfig `json:"metrics"`
 }
 
 type LikwidCollectorConfig struct {
@@ -67,29 +98,28 @@ type LikwidCollectorConfig struct {
 	InvalidToZero  bool                            `json:"invalid_to_zero,omitempty"`
 	AccessMode     string                          `json:"access_mode,omitempty"`
 	DaemonPath     string                          `json:"accessdaemon_path,omitempty"`
-	LibraryPath    string                          `json:"liblikwid_path,omitempty"`
 }
 
 type LikwidCollector struct {
 	metricCollector
-	cpulist      []C.int
-	cpu2tid      map[int]int
-	sock2tid     map[int]int
-	metrics      map[C.int]map[string]int
-	groups       []C.int
-	config       LikwidCollectorConfig
-	gmresults    map[int]map[string]float64
-	basefreq     float64
-	running      bool
-	initialized  bool
-	likwidGroups map[C.int]LikwidEventsetConfig
-	lock         sync.Mutex
+	cpulist       []C.int
+	cpu2tid       map[int]int
+	sock2tid      map[int]int
+	scopeRespTids map[MetricScope]map[int]int
+	metrics       map[C.int]map[string]int
+	groups        []C.int
+	config        LikwidCollectorConfig
+	results       map[int]map[int]map[string]interface{}
+	mresults      map[int]map[int]map[string]float64
+	gmresults     map[int]map[string]float64
+	basefreq      float64
+	running       bool
 }
 
 type LikwidMetric struct {
 	name      string
 	search    string
-	scope     string
+	scope     MetricScope
 	group_idx int
 }
 
@@ -101,99 +131,152 @@ func eventsToEventStr(events map[string]string) string {
 	return strings.Join(elist, ",")
 }
 
-func genLikwidEventSet(input LikwidCollectorEventsetConfig) LikwidEventsetConfig {
-	tmplist := make([]string, 0)
-	clist := make([]string, 0)
-	for k := range input.Events {
-		clist = append(clist, k)
-	}
-	sort.Strings(clist)
-	elist := make([]*C.char, 0)
-	for _, k := range clist {
-		v := input.Events[k]
-		tmplist = append(tmplist, fmt.Sprintf("%s:%s", v, k))
-		c_counter := C.CString(k)
-		elist = append(elist, c_counter)
-	}
-	estr := strings.Join(tmplist, ",")
-	res := make(map[int]map[string]interface{})
-	met := make(map[int]map[string]float64)
-	for _, i := range topo.CpuList() {
-		res[i] = make(map[string]interface{})
-		for k := range input.Events {
-			res[i][k] = 0.0
-		}
-		met[i] = make(map[string]float64)
-		for _, v := range input.Metrics {
-			res[i][v.Name] = 0.0
+func getGranularity(counter, event string) MetricScope {
+	if strings.HasPrefix(counter, "PMC") || strings.HasPrefix(counter, "FIXC") {
+		return "cpu"
+	} else if strings.Contains(counter, "BOX") || strings.Contains(counter, "DEV") {
+		return "socket"
+	} else if strings.HasPrefix(counter, "PWR") {
+		if event == "RAPL_CORE_ENERGY" {
+			return "cpu"
+		} else {
+			return "socket"
 		}
 	}
-	return LikwidEventsetConfig{
-		gid:     -1,
-		eorder:  elist,
-		estr:    C.CString(estr),
-		go_estr: estr,
-		results: res,
-		metrics: met,
-	}
-}
-
-func testLikwidMetricFormula(formula string, params []string) bool {
-	myparams := make(map[string]interface{})
-	for _, p := range params {
-		myparams[p] = float64(1.0)
-	}
-	_, err := agg.EvalFloat64Condition(formula, myparams)
-	return err == nil
+	return "unknown"
 }
 
 func getBaseFreq() float64 {
-	files := []string{
-		"/sys/devices/system/cpu/cpu0/cpufreq/bios_limit",
-		"/sys/devices/system/cpu/cpu0/cpufreq/base_frequency",
-	}
 	var freq float64 = math.NaN()
-	for _, f := range files {
-		buffer, err := ioutil.ReadFile(f)
+	C.power_init(0)
+	info := C.get_powerInfo()
+	if float64(info.baseFrequency) != 0 {
+		freq = float64(info.baseFrequency) * 1e3
+	} else {
+		buffer, err := ioutil.ReadFile("/sys/devices/system/cpu/cpu0/cpufreq/bios_limit")
 		if err == nil {
 			data := strings.Replace(string(buffer), "\n", "", -1)
 			x, err := strconv.ParseInt(data, 0, 64)
 			if err == nil {
-				freq = float64(x) * 1e6
+				freq = float64(x) * 1e3
 			}
 		}
 	}
-
-	if math.IsNaN(freq) {
-		C.power_init(0)
-		info := C.get_powerInfo()
-		if float64(info.baseFrequency) != 0 {
-			freq = float64(info.baseFrequency) * 1e6
-		}
-		C.power_finalize()
-	}
 	return freq
 }
 
+func (m *LikwidCollector) initGranularity() {
+	splitRegex := regexp.MustCompile("[+-/*()]")
+	for _, evset := range m.config.Eventsets {
+		evset.granulatity = make(map[string]MetricScope)
+		for counter, event := range evset.Events {
+			gran := getGranularity(counter, event)
+			if gran.Granularity() >= 0 {
+				evset.granulatity[counter] = gran
+			}
+		}
+		for i, metric := range evset.Metrics {
+			s := splitRegex.Split(metric.Calc, -1)
+			gran := MetricScope("cpu")
+			evset.Metrics[i].granulatity = gran
+			for _, x := range s {
+				if _, ok := evset.Events[x]; ok {
+					if evset.granulatity[x].Granularity() > gran.Granularity() {
+						gran = evset.granulatity[x]
+					}
+				}
+			}
+			evset.Metrics[i].granulatity = gran
+		}
+	}
+	for i, metric := range m.config.Metrics {
+		s := splitRegex.Split(metric.Calc, -1)
+		gran := MetricScope("cpu")
+		m.config.Metrics[i].granulatity = gran
+		for _, x := range s {
+			for _, evset := range m.config.Eventsets {
+				for _, m := range evset.Metrics {
+					if m.Name == x && m.granulatity.Granularity() > gran.Granularity() {
+						gran = m.granulatity
+					}
+				}
+			}
+		}
+		m.config.Metrics[i].granulatity = gran
+	}
+}
+
+type TopoResolveFunc func(cpuid int) int
+
+func (m *LikwidCollector) getResponsiblities() map[MetricScope]map[int]int {
+	get_cpus := func(scope MetricScope) map[int]int {
+		var slist []int
+		var cpu C.int
+		var input func(index int) string
+		switch scope {
+		case "node":
+			slist = []int{0}
+			input = func(index int) string { return "N:0" }
+		case "socket":
+			input = func(index int) string { return fmt.Sprintf("%s%d:0", scope.Likwid(), index) }
+			slist = topo.SocketList()
+		// case "numadomain":
+		// 	input = func(index int) string { return fmt.Sprintf("%s%d:0", scope.Likwid(), index) }
+		// 	slist = topo.NumaNodeList()
+		// 	cclog.Debug(scope, " ", input(0), " ", slist)
+		// case "die":
+		// 	input = func(index int) string { return fmt.Sprintf("%s%d:0", scope.Likwid(), index) }
+		// 	slist = topo.DieList()
+		// case "llc":
+		// 	input = fmt.Sprintf("%s%d:0", scope.Likwid(), s)
+		// 	slist = topo.LLCacheList()
+		case "cpu":
+			input = func(index int) string { return fmt.Sprintf("%d", index) }
+			slist = topo.CpuList()
+		case "hwthread":
+			input = func(index int) string { return fmt.Sprintf("%d", index) }
+			slist = topo.CpuList()
+		}
+		outmap := make(map[int]int)
+		for _, s := range slist {
+			t := C.CString(input(s))
+			clen := C.cpustr_to_cpulist(t, &cpu, 1)
+			if int(clen) == 1 {
+				outmap[s] = m.cpu2tid[int(cpu)]
+			} else {
+				cclog.Error(fmt.Sprintf("Cannot determine responsible CPU for %s", input(s)))
+				outmap[s] = -1
+			}
+			C.free(unsafe.Pointer(t))
+		}
+		return outmap
+	}
+
+	scopes := GetAllMetricScopes()
+	complete := make(map[MetricScope]map[int]int)
+	for _, s := range scopes {
+		complete[s] = get_cpus(s)
+	}
+	return complete
+}
+
 func (m *LikwidCollector) Init(config json.RawMessage) error {
+	var ret C.int
 	m.name = "LikwidCollector"
-	m.initialized = false
-	m.running = false
 	m.config.AccessMode = LIKWID_DEF_ACCESSMODE
-	m.config.LibraryPath = LIKWID_LIB_NAME
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	lib := dl.New(m.config.LibraryPath, LIKWID_LIB_DL_FLAGS)
+	lib := dl.New(LIKWID_LIB_NAME, LIKWID_LIB_DL_FLAGS)
 	if lib == nil {
-		return fmt.Errorf("error instantiating DynamicLibrary for %s", m.config.LibraryPath)
+		return fmt.Errorf("error instantiating DynamicLibrary for %s", LIKWID_LIB_NAME)
 	}
 	err := lib.Open()
 	if err != nil {
-		return fmt.Errorf("error opening %s: %v", m.config.LibraryPath, err)
+		return fmt.Errorf("error opening %s: %v", LIKWID_LIB_NAME, err)
 	}
 
 	if m.config.ForceOverwrite {
@@ -202,7 +285,7 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 	}
 	m.setup()
 
-	m.meta = map[string]string{"group": "PerfCounter"}
+	m.meta = map[string]string{"source": m.name, "group": "PerfCounter"}
 	cclog.ComponentDebug(m.name, "Get cpulist and init maps and lists")
 	cpulist := topo.CpuList()
 	m.cpulist = make([]C.int, len(cpulist))
@@ -210,166 +293,194 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 	for i, c := range cpulist {
 		m.cpulist[i] = C.int(c)
 		m.cpu2tid[c] = i
+
+	}
+	m.results = make(map[int]map[int]map[string]interface{})
+	m.mresults = make(map[int]map[int]map[string]float64)
+	m.gmresults = make(map[int]map[string]float64)
+	cclog.ComponentDebug(m.name, "initialize LIKWID topology")
+	ret = C.topology_init()
+	if ret != 0 {
+		err := errors.New("failed to initialize LIKWID topology")
+		cclog.ComponentError(m.name, err.Error())
+		return err
 	}
 
-	m.likwidGroups = make(map[C.int]LikwidEventsetConfig)
+	// Determine which counter works at which level. PMC*: cpu, *BOX*: socket, ...
+	m.initGranularity()
+	// Generate map for MetricScope -> scope_id (like socket id) -> responsible id (offset in cpulist)
+	m.scopeRespTids = m.getResponsiblities()
+	switch m.config.AccessMode {
+	case "direct":
+		C.HPMmode(0)
+	case "accessdaemon":
+		if len(m.config.DaemonPath) > 0 {
+			p := os.Getenv("PATH")
+			os.Setenv("PATH", m.config.DaemonPath+":"+p)
+		}
+		C.HPMmode(1)
+	}
 
-	// m.results = make(map[int]map[int]map[string]interface{})
-	// m.mresults = make(map[int]map[int]map[string]float64)
-	m.gmresults = make(map[int]map[string]float64)
-	for _, tid := range m.cpu2tid {
-		m.gmresults[tid] = make(map[string]float64)
+	cclog.ComponentDebug(m.name, "initialize LIKWID perfmon module")
+	ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
+	if ret != 0 {
+		C.topology_finalize()
+		err := errors.New("failed to initialize LIKWID topology")
+		cclog.ComponentError(m.name, err.Error())
+		return err
 	}
 
 	// This is for the global metrics computation test
-	totalMetrics := 0
-	// Generate parameter list for the metric computing test
-	params := make([]string, 0)
-	params = append(params, "time", "inverseClock")
-	// Generate parameter list for the global metric computing test
-	globalParams := make([]string, 0)
-	globalParams = append(globalParams, "time", "inverseClock")
-	// We test the eventset metrics whether they can be computed at all
-	for _, evset := range m.config.Eventsets {
-		if len(evset.Events) > 0 {
-			params = params[:2]
-			for counter := range evset.Events {
-				params = append(params, counter)
+	globalParams := make(map[string]interface{})
+	globalParams["time"] = float64(1.0)
+	globalParams["inverseClock"] = float64(1.0)
+	// While adding the events, we test the metrics whether they can be computed at all
+	for i, evset := range m.config.Eventsets {
+		estr := eventsToEventStr(evset.Events)
+		// Generate parameter list for the metric computing test
+		params := make(map[string]interface{})
+		params["time"] = float64(1.0)
+		params["inverseClock"] = float64(1.0)
+		for counter := range evset.Events {
+			params[counter] = float64(1.0)
+		}
+		for _, metric := range evset.Metrics {
+			// Try to evaluate the metric
+			_, err := agg.EvalFloat64Condition(metric.Calc, params)
+			if err != nil {
+				cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
+				continue
 			}
-			for _, metric := range evset.Metrics {
-				// Try to evaluate the metric
-				if testLikwidMetricFormula(metric.Calc, params) {
-					// Add the computable metric to the parameter list for the global metrics
-					globalParams = append(globalParams, metric.Name)
-					totalMetrics++
-				} else {
-					metric.Calc = ""
-				}
+			// If the metric is not in the parameter list for the global metrics, add it
+			if _, ok := globalParams[metric.Name]; !ok {
+				globalParams[metric.Name] = float64(1.0)
+			}
+		}
+		// Now we add the list of events to likwid
+		cstr := C.CString(estr)
+		gid := C.perfmon_addEventSet(cstr)
+		if gid >= 0 {
+			m.groups = append(m.groups, gid)
+		}
+		C.free(unsafe.Pointer(cstr))
+		m.results[i] = make(map[int]map[string]interface{})
+		m.mresults[i] = make(map[int]map[string]float64)
+		for tid := range m.cpulist {
+			m.results[i][tid] = make(map[string]interface{})
+			m.mresults[i][tid] = make(map[string]float64)
+			if i == 0 {
+				m.gmresults[tid] = make(map[string]float64)
 			}
-		} else {
-			cclog.ComponentError(m.name, "Invalid Likwid eventset config, no events given")
-			continue
 		}
 	}
 	for _, metric := range m.config.Metrics {
 		// Try to evaluate the global metric
-		if !testLikwidMetricFormula(metric.Calc, globalParams) {
-			cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed")
-			metric.Calc = ""
-		} else {
-			totalMetrics++
+		_, err := agg.EvalFloat64Condition(metric.Calc, globalParams)
+		if err != nil {
+			cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
+			continue
 		}
 	}
 
 	// If no event set could be added, shut down LikwidCollector
-	if totalMetrics == 0 {
-		err := errors.New("no LIKWID eventset or metric usable")
+	if len(m.groups) == 0 {
+		C.perfmon_finalize()
+		C.topology_finalize()
+		err := errors.New("no LIKWID performance group initialized")
 		cclog.ComponentError(m.name, err.Error())
 		return err
 	}
+	m.basefreq = getBaseFreq()
+	cclog.ComponentDebug(m.name, "BaseFreq", m.basefreq)
 	m.init = true
 	return nil
 }
 
 // take a measurement for 'interval' seconds of event set index 'group'
-func (m *LikwidCollector) takeMeasurement(evset LikwidEventsetConfig, interval time.Duration) (bool, error) {
+func (m *LikwidCollector) takeMeasurement(group int, interval time.Duration) error {
 	var ret C.int
-	m.lock.Lock()
-	if m.initialized {
-		ret = C.perfmon_setupCounters(evset.gid)
-		if ret != 0 {
-			var err error = nil
-			var skip bool = false
-			if ret == -37 {
-				skip = true
-			} else {
-				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
-			}
-			m.lock.Unlock()
-			return skip, err
-		}
-		ret = C.perfmon_startCounters()
-		if ret != 0 {
-			var err error = nil
-			var skip bool = false
-			if ret == -37 {
-				skip = true
-			} else {
-				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
-			}
-			m.lock.Unlock()
-			return skip, err
-		}
-		m.running = true
-		time.Sleep(interval)
-		m.running = false
-		ret = C.perfmon_stopCounters()
-		if ret != 0 {
-			var err error = nil
-			var skip bool = false
-			if ret == -37 {
-				skip = true
-			} else {
-				err = fmt.Errorf("failed to setup performance group %d", evset.gid)
-			}
-			m.lock.Unlock()
-			return skip, err
-		}
+	gid := m.groups[group]
+	ret = C.perfmon_setupCounters(gid)
+	if ret != 0 {
+		gctr := C.GoString(C.perfmon_getGroupName(gid))
+		err := fmt.Errorf("failed to setup performance group %d (%s)", gid, gctr)
+		return err
 	}
-	m.lock.Unlock()
-	return false, nil
+	ret = C.perfmon_startCounters()
+	if ret != 0 {
+		gctr := C.GoString(C.perfmon_getGroupName(gid))
+		err := fmt.Errorf("failed to start performance group %d (%s)", gid, gctr)
+		return err
+	}
+	m.running = true
+	time.Sleep(interval)
+	m.running = false
+	ret = C.perfmon_stopCounters()
+	if ret != 0 {
+		gctr := C.GoString(C.perfmon_getGroupName(gid))
+		err := fmt.Errorf("failed to stop performance group %d (%s)", gid, gctr)
+		return err
+	}
+	return nil
 }
 
 // Get all measurement results for an event set, derive the metric values out of the measurement results and send it
-func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interval time.Duration, output chan lp.CCMetric) error {
+func (m *LikwidCollector) calcEventsetMetrics(group int, interval time.Duration, output chan lp.CCMetric) error {
+	var eidx C.int
+	evset := m.config.Eventsets[group]
+	gid := m.groups[group]
 	invClock := float64(1.0 / m.basefreq)
 
 	// Go over events and get the results
-	for eidx, counter := range evset.eorder {
-		gctr := C.GoString(counter)
-		for _, tid := range m.cpu2tid {
-			res := C.perfmon_getLastResult(evset.gid, C.int(eidx), C.int(tid))
-			fres := float64(res)
-			if m.config.InvalidToZero && (math.IsNaN(fres) || math.IsInf(fres, 0)) {
-				fres = 0.0
+	for eidx = 0; int(eidx) < len(evset.Events); eidx++ {
+		ctr := C.perfmon_getCounterName(gid, eidx)
+		ev := C.perfmon_getEventName(gid, eidx)
+		gctr := C.GoString(ctr)
+		gev := C.GoString(ev)
+		// MetricScope for the counter (and if needed the event)
+		scope := getGranularity(gctr, gev)
+		// Get the map scope-id -> tids
+		// This way we read less counters like only the responsible hardware thread for a socket
+		scopemap := m.scopeRespTids[scope]
+		for _, tid := range scopemap {
+			if tid >= 0 {
+				m.results[group][tid]["time"] = interval.Seconds()
+				m.results[group][tid]["inverseClock"] = invClock
+				res := C.perfmon_getLastResult(gid, eidx, C.int(tid))
+				m.results[group][tid][gctr] = float64(res)
 			}
-			evset.results[tid][gctr] = fres
-			evset.results[tid]["time"] = interval.Seconds()
-			evset.results[tid]["inverseClock"] = invClock
 		}
 	}
 
 	// Go over the event set metrics, derive the value out of the event:counter values and send it
-	for _, metric := range m.config.Eventsets[evset.internal].Metrics {
+	for _, metric := range evset.Metrics {
 		// The metric scope is determined in the Init() function
 		// Get the map scope-id -> tids
-		scopemap := m.cpu2tid
-		if metric.Type == "socket" {
-			scopemap = m.sock2tid
-		}
+		scopemap := m.scopeRespTids[metric.Scope]
 		for domain, tid := range scopemap {
-			if tid >= 0 && len(metric.Calc) > 0 {
-				value, err := agg.EvalFloat64Condition(metric.Calc, evset.results[tid])
+			if tid >= 0 {
+				value, err := agg.EvalFloat64Condition(metric.Calc, m.results[group][tid])
 				if err != nil {
 					cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
+					continue
+				}
+				m.mresults[group][tid][metric.Name] = value
+				if m.config.InvalidToZero && math.IsNaN(value) {
 					value = 0.0
 				}
-				if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {
+				if m.config.InvalidToZero && math.IsInf(value, 0) {
 					value = 0.0
 				}
-				evset.metrics[tid][metric.Name] = value
 				// Now we have the result, send it with the proper tags
 				if !math.IsNaN(value) {
 					if metric.Publish {
+						tags := map[string]string{"type": metric.Scope.String()}
+						if metric.Scope != "node" {
+							tags["type-id"] = fmt.Sprintf("%d", domain)
+						}
 						fields := map[string]interface{}{"value": value}
-						y, err := lp.New(metric.Name, map[string]string{"type": metric.Type}, m.meta, fields, time.Now())
+						y, err := lp.New(metric.Name, tags, m.meta, fields, time.Now())
 						if err == nil {
-							if metric.Type != "node" {
-								y.AddTag("type-id", fmt.Sprintf("%d", domain))
-							}
-							if len(metric.Unit) > 0 {
-								y.AddMeta("unit", metric.Unit)
-							}
 							output <- y
 						}
 					}
@@ -384,16 +495,13 @@ 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(interval time.Duration, output chan lp.CCMetric) error {
 	for _, metric := range m.config.Metrics {
-		scopemap := m.cpu2tid
-		if metric.Type == "socket" {
-			scopemap = m.sock2tid
-		}
+		scopemap := m.scopeRespTids[metric.Scope]
 		for domain, tid := range scopemap {
 			if tid >= 0 {
 				// Here we generate parameter list
 				params := make(map[string]interface{})
-				for _, evset := range m.likwidGroups {
-					for mname, mres := range evset.metrics[tid] {
+				for j := range m.groups {
+					for mname, mres := range m.mresults[j][tid] {
 						params[mname] = mres
 					}
 				}
@@ -401,25 +509,25 @@ func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan
 				value, err := agg.EvalFloat64Condition(metric.Calc, params)
 				if err != nil {
 					cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
-					value = 0.0
-				}
-				if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {
-					value = 0.0
+					continue
 				}
 				m.gmresults[tid][metric.Name] = value
+				if m.config.InvalidToZero && math.IsNaN(value) {
+					value = 0.0
+				}
+				if m.config.InvalidToZero && math.IsInf(value, 0) {
+					value = 0.0
+				}
 				// Now we have the result, send it with the proper tags
 				if !math.IsNaN(value) {
 					if metric.Publish {
-						tags := map[string]string{"type": metric.Type}
+						tags := map[string]string{"type": metric.Scope.String()}
+						if metric.Scope != "node" {
+							tags["type-id"] = fmt.Sprintf("%d", domain)
+						}
 						fields := map[string]interface{}{"value": value}
 						y, err := lp.New(metric.Name, tags, m.meta, fields, time.Now())
 						if err == nil {
-							if metric.Type != "node" {
-								y.AddTag("type-id", fmt.Sprintf("%d", domain))
-							}
-							if len(metric.Unit) > 0 {
-								y.AddMeta("unit", metric.Unit)
-							}
 							output <- y
 						}
 					}
@@ -430,163 +538,38 @@ func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan
 	return nil
 }
 
-func (m *LikwidCollector) LateInit() error {
-	var ret C.int
-	if m.initialized {
-		return nil
-	}
-	switch m.config.AccessMode {
-	case "direct":
-		C.HPMmode(0)
-	case "accessdaemon":
-		if len(m.config.DaemonPath) > 0 {
-			p := os.Getenv("PATH")
-			os.Setenv("PATH", m.config.DaemonPath+":"+p)
-		}
-		C.HPMmode(1)
-	}
-	cclog.ComponentDebug(m.name, "initialize LIKWID topology")
-	ret = C.topology_init()
-	if ret != 0 {
-		err := errors.New("failed to initialize LIKWID topology")
-		cclog.ComponentError(m.name, err.Error())
-		return err
-	}
-
-	m.sock2tid = make(map[int]int)
-	tmp := make([]C.int, 1)
-	for _, sid := range topo.SocketList() {
-		cstr := C.CString(fmt.Sprintf("S%d:0", sid))
-		ret = C.cpustr_to_cpulist(cstr, &tmp[0], 1)
-		if ret > 0 {
-			m.sock2tid[sid] = m.cpu2tid[int(tmp[0])]
-		}
-		C.free(unsafe.Pointer(cstr))
-	}
-
-	m.basefreq = getBaseFreq()
-	cclog.ComponentDebug(m.name, "BaseFreq", m.basefreq)
-
-	cclog.ComponentDebug(m.name, "initialize LIKWID perfmon module")
-	ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
-	if ret != 0 {
-		var err error = nil
-		C.topology_finalize()
-		if ret != -22 {
-			err = errors.New("failed to initialize LIKWID perfmon")
-			cclog.ComponentError(m.name, err.Error())
-		} else {
-			err = errors.New("access to LIKWID perfmon locked")
-		}
-		return err
-	}
-
-	// While adding the events, we test the metrics whether they can be computed at all
-	for i, evset := range m.config.Eventsets {
-		var gid C.int
-		if len(evset.Events) > 0 {
-			skip := false
-			likwidGroup := genLikwidEventSet(evset)
-			for _, g := range m.likwidGroups {
-				if likwidGroup.go_estr == g.go_estr {
-					skip = true
-					break
-				}
-			}
-			if skip {
-				continue
-			}
-			// Now we add the list of events to likwid
-			gid = C.perfmon_addEventSet(likwidGroup.estr)
-			if gid >= 0 {
-				likwidGroup.gid = gid
-				likwidGroup.internal = i
-				m.likwidGroups[gid] = likwidGroup
-			}
-		} else {
-			cclog.ComponentError(m.name, "Invalid Likwid eventset config, no events given")
-			continue
-		}
-
-	}
-
-	// If no event set could be added, shut down LikwidCollector
-	if len(m.likwidGroups) == 0 {
-		C.perfmon_finalize()
-		C.topology_finalize()
-		err := errors.New("no LIKWID performance group initialized")
-		cclog.ComponentError(m.name, err.Error())
-		return err
-	}
-	sigchan := make(chan os.Signal, 1)
-	signal.Notify(sigchan, syscall.SIGCHLD)
-	signal.Notify(sigchan, os.Interrupt)
-	go func() {
-		<-sigchan
-
-		signal.Stop(sigchan)
-		m.initialized = false
-	}()
-	m.initialized = true
-	return nil
-}
-
 // main read function taking multiple measurement rounds, each 'interval' seconds long
 func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	var skip bool = false
-	var err error
 	if !m.init {
 		return
 	}
 
-	if !m.initialized {
-		m.lock.Lock()
-		err = m.LateInit()
+	for i := range m.groups {
+		// measure event set 'i' for 'interval' seconds
+		err := m.takeMeasurement(i, interval)
 		if err != nil {
-			m.lock.Unlock()
+			cclog.ComponentError(m.name, err.Error())
 			return
 		}
-		m.initialized = true
-		m.lock.Unlock()
-	}
-
-	if m.initialized && !skip {
-		for _, evset := range m.likwidGroups {
-			if !skip {
-				// measure event set 'i' for 'interval' seconds
-				skip, err = m.takeMeasurement(evset, interval)
-				if err != nil {
-					cclog.ComponentError(m.name, err.Error())
-					return
-				}
-			}
-
-			if !skip {
-				// read measurements and derive event set metrics
-				m.calcEventsetMetrics(evset, interval, output)
-			}
-		}
-		if !skip {
-			// use the event set metrics to derive the global metrics
-			m.calcGlobalMetrics(interval, output)
-		}
+		// read measurements and derive event set metrics
+		m.calcEventsetMetrics(i, interval, output)
 	}
+	// use the event set metrics to derive the global metrics
+	m.calcGlobalMetrics(interval, output)
 }
 
 func (m *LikwidCollector) Close() {
 	if m.init {
-		m.init = false
 		cclog.ComponentDebug(m.name, "Closing ...")
-		m.lock.Lock()
-		if m.initialized {
-			cclog.ComponentDebug(m.name, "Finalize LIKWID perfmon module")
-			C.perfmon_finalize()
-			m.initialized = false
+		m.init = false
+		if m.running {
+			cclog.ComponentDebug(m.name, "Stopping counters")
+			C.perfmon_stopCounters()
 		}
-		m.lock.Unlock()
+		cclog.ComponentDebug(m.name, "Finalize LIKWID perfmon module")
+		C.perfmon_finalize()
 		cclog.ComponentDebug(m.name, "Finalize LIKWID topology module")
 		C.topology_finalize()
-
 		cclog.ComponentDebug(m.name, "Closing done")
 	}
 }

collectors/likwidMetric.md

@@ -3,63 +3,29 @@
 
 The `likwid` collector is probably the most complicated collector. The LIKWID library is included as static library with *direct* access mode. The *direct* access mode is suitable if the daemon is executed by a root user. The static library does not contain the performance groups, so all information needs to be provided in the configuration.
 
-```json
-  "likwid": {
-    "force_overwrite" : false,
-    "invalid_to_zero" : false,
-    "eventsets": [
-      {
-        "events" : {
-          "COUNTER0": "EVENT0",
-          "COUNTER1": "EVENT1",
-        },
-        "metrics" : [
-          {
-            "name": "sum_01",
-            "calc": "COUNTER0 + COUNTER1",
-            "publish": false,
-            "unit": "myunit",
-            "type": "cpu"
-          }
-        ]
-      }
-    ]
-    "globalmetrics" : [
-      {
-        "name": "global_sum",
-        "calc": "sum_01",
-        "publish": true,
-        "unit": "myunit",
-        "type": "cpu"
-      }
-    ]
-  }
-```
-
-The `likwid` configuration consists of two parts, the `eventsets` and `globalmetrics`:
-- An event set list itself has two parts, the `events` and a set of derivable `metrics`. Each of the `events` is a `counter:event` pair in LIKWID's syntax. The `metrics` are a list of formulas to derive the metric value from the measurements of the `events`' values. Each metric has a name, the formula, a type and a publish flag. There is an optional `unit` field. Counter names can be used like variables in the formulas, so `PMC0+PMC1` sums the measurements for the both events configured in the counters `PMC0` and `PMC1`. You can optionally use `time` for the measurement time and `inverseClock` for `1.0/baseCpuFrequency`. The type tells the LikwidCollector whether it is a metric for each hardware thread (`cpu`) or each CPU socket (`socket`). You may specify a unit for the metric with `unit`. The last one is the publishing flag. It tells the LikwidCollector whether a metric should be sent to the router or is only used internally to compute a global metric.
-- The `globalmetrics` are metrics which require data from multiple event set measurements to be derived. The inputs are the metrics in the event sets. Similar to the metrics in the event sets, the global metrics are defined by a name, a formula, a scope and a publish flag. See event set metrics for details. The only difference is that there is no access to the raw event measurements anymore but only to the metrics. Also `time` and `inverseClock` cannot be used anymore. So, the idea is to derive a metric in the `eventsets` section and reuse it in the `globalmetrics` part. If you need a metric only for deriving the global metrics, disable forwarding of the event set metrics (`"publish": false`). **Be aware** that the combination might be misleading because the "behavior" of a metric changes over time and the multiple measurements might count different computing phases. Similar to the metrics in the eventset, you can specify a metric unit with the `unit` field.
+The `likwid` configuration consists of two parts, the "eventsets" and "globalmetrics":
+- An event set list itself has two parts, the "events" and a set of derivable "metrics". Each of the "events" is a counter:event pair in LIKWID's syntax. The "metrics" are a list of formulas to derive the metric value from the measurements of the "events". Each metric has a name, the formula, a scope and a publish flag. Counter names can be used like variables in the formulas, so `PMC0+PMC1` sums the measurements for the both events configured in the counters `PMC0` and `PMC1`. The scope tells the Collector whether it is a metric for each hardware thread (`cpu`) or each CPU socket (`socket`). The last one is the publishing flag. It tells the collector whether a metric should be sent to the router.
+- The global metrics are metrics which require data from all event set measurements to be derived. The inputs are the metrics in the event sets. Similar to the metrics in the event sets, the global metrics are defined by a name, a formula, a scope and a publish flag. See event set metrics for details. The only difference is that there is no access to the raw event measurements anymore but only to the metrics. So, the idea is to derive a metric in the "eventsets" section and reuse it in the "globalmetrics" part. If you need a metric only for deriving the global metrics, disable forwarding of the event set metrics. **Be aware** that the combination might be misleading because the "behavior" of a metric changes over time and the multiple measurements might count different computing phases.
 
 Additional options:
+- `access_mode` : Method to use for hardware performance monitoring (`direct` access as root user, `accessdaemon` for the daemon mode)
+- `accessdaemon_path`: Folder with the access daemon `likwid-accessD`, commonly `$LIKWID_INSTALL_LOC/sbin`
 - `force_overwrite`: Same as setting `LIKWID_FORCE=1`. In case counters are already in-use, LIKWID overwrites their configuration to do its measurements
-- `invalid_to_zero`: In some cases, the calculations result in `NaN` or `Inf`. With this option, all `NaN` and `Inf` values are replaces with `0.0`. See below in [seperate section](./likwidMetric.md#invalid_to_zero-option)
-- `access_mode`: Specify LIKWID access mode: `direct` for direct register access as root user or `accessdaemon`. The access mode `perf_event` is current untested.
-- `accessdaemon_path`: Folder of the accessDaemon `likwid-accessD` (like `/usr/local/sbin`)
-- `liblikwid_path`: Location of `liblikwid.so` including file name like `/usr/local/lib/liblikwid.so`
+- `invalid_to_zero`: In some cases, the calculations result in `NaN` or `Inf`. With this option, all `NaN` and `Inf` values are replaces with `0.0`.
 
 ### Available metric scopes
 
-Hardware performance counters are scattered all over the system nowadays. A counter coveres a specific part of the system. While there are hardware thread specific counter for CPU cycles, instructions and so on, some others are specific for a whole CPU socket/package. To address that, the LikwidCollector provides the specification of a `type` for each metric.
+Hardware performance counters are scattered all over the system nowadays. A counter coveres a specific part of the system. While there are hardware thread specific counter for CPU cycles, instructions and so on, some others are specific for a whole CPU socket/package. To address that, the collector provides the specification of a 'scope' for each metric.
 
 - `cpu` : One metric per CPU hardware thread with the tags `"type" : "cpu"` and `"type-id" : "$cpu_id"`
 - `socket` : One metric per CPU socket/package with the tags `"type" : "socket"` and `"type-id" : "$socket_id"`
 
-**Note:** You should not specify the `socket` type for a metric that is measured at `cpu` scope and vice versa, so some kind of expert knowledge or lookup work in the [Likwid Wiki](https://github.com/RRZE-HPC/likwid/wiki) is required. Get the scope of each counter from the *Architecture* pages and as soon as one counter in a metric is socket-specific, the whole metric is socket-specific.
+**Note:** You cannot specify `socket` scope for a metric that is measured at `cpu` scope, so some kind of expert knowledge or lookup work in the [Likwid Wiki](https://github.com/RRZE-HPC/likwid/wiki) is required. Get the scope of each counter from the *Architecture* pages and as soon as one counter in a metric is socket-specific, the whole metric is socket-specific.
 
 As a guideline:
 - All counters `FIXCx`, `PMCy` and `TMAz` have the scope `cpu`
 - All counters names containing `BOX` have the scope `socket`
-- All `PWRx` counters have scope `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `cpu` scope (AMD Zen)
+- All `PWRx` counters have scope `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `cpu` scope
 - All `DFCx` counters have scope `socket`
 
 ### Help with the configuration
@@ -81,7 +47,6 @@ $ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
 {
   "events": {
     "FIXC0": "INSTR_RETIRED_ANY",
-    "FIXC1": "CPU_CLK_UNHALTED_CORE",
     "..." : "..."
   },
   "metrics" : [
@@ -89,8 +54,7 @@ $ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
       "calc": "time",
       "name": "Runtime (RDTSC) [s]",
       "publish": true,
-      "unit": "seconds"
-      "scope": "cpu"
+      "scope": "hwthread"
     },
     {
       "..." : "..."
@@ -107,28 +71,21 @@ LIKWID checks the file `/var/run/likwid.lock` before performing any interfering
 
 Before (SLURM prolog, ...)
 ```
-$ chown $JOBUSER /var/run/likwid.lock
+$ chwon $JOBUSER /var/run/likwid.lock
 ```
 
 After (SLURM epilog, ...)
 ```
-$ chown $CCUSER /var/run/likwid.lock
+$ chwon $CCUSER /var/run/likwid.lock
 ```
 
-### `invalid_to_zero` option
-In some cases LIKWID returns `0.0` for some events that are further used in processing and maybe used as divisor in a calculation. After evaluation of a metric, the result might be `NaN` or `+-Inf`. These resulting metrics are commonly not created and forwarded to the router because the [InfluxDB line protocol](https://docs.influxdata.com/influxdb/cloud/reference/syntax/line-protocol/#float) does not support these special floating-point values. If you want to have them sent, this option forces these metric values to be `0.0` instead.
-
-One might think this does not happen often but often used metrics in the world of performance engineering like Instructions-per-Cycle (IPC) or more frequently the actual CPU clock are derived with events like `CPU_CLK_UNHALTED_CORE` (Intel) which do not increment in halted state (as the name implies). In there are different power management systems in a chip which can cause a hardware thread to go in such a state. Moreover, if no cycles are executed by the core, also many other events are not incremented as well (like `INSTR_RETIRED_ANY` for retired instructions and part of IPC).
-
-
 ### Example configuration
 
-#### AMD Zen3
 
 ```json
   "likwid": {
     "force_overwrite" : false,
-    "invalid_to_zero" : false,
+    "nan_to_zero" : false,
     "eventsets": [
       {
         "events": {
@@ -147,28 +104,25 @@ One might think this does not happen often but often used metrics in the world o
           {
             "name": "ipc",
             "calc": "PMC0/PMC1",
-            "type": "cpu",
+            "scope": "cpu",
             "publish": true
           },
           {
             "name": "flops_any",
             "calc": "0.000001*PMC2/time",
-            "unit": "MFlops/s",
-            "type": "cpu",
+            "scope": "cpu",
             "publish": true
           },
           {
-            "name": "clock",
+            "name": "clock_mhz",
             "calc": "0.000001*(FIXC1/FIXC2)/inverseClock",
-            "type": "cpu",
-            "unit": "MHz",
+            "scope": "cpu",
             "publish": true
           },
           {
             "name": "mem1",
             "calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
-            "unit": "Mbyte/s",
-            "type": "socket",
+            "scope": "socket",
             "publish": false
           }
         ]
@@ -186,22 +140,19 @@ One might think this does not happen often but often used metrics in the world o
           {
             "name": "pwr_core",
             "calc": "PWR0/time",
-            "unit": "Watt"
-            "type": "socket",
+            "scope": "socket",
             "publish": true
           },
           {
             "name": "pwr_pkg",
             "calc": "PWR1/time",
-            "type": "socket",
-            "unit": "Watt"
+            "scope": "socket",
             "publish": true
           },
           {
             "name": "mem2",
             "calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
-            "unit": "Mbyte/s",
-            "type": "socket",
+            "scope": "socket",
             "publish": false
           }
         ]
@@ -211,11 +162,39 @@ One might think this does not happen often but often used metrics in the world o
       {
         "name": "mem_bw",
         "calc": "mem1+mem2",
-        "type": "socket",
-        "unit": "Mbyte/s",
+        "scope": "socket",
         "publish": true
       }
     ]
   }
 ```
 
+### How to get the eventsets and metrics from LIKWID
+
+The `likwid` collector reads hardware performance counters at a **cpu** and **socket** level. The configuration looks quite complicated but it is basically copy&paste from [LIKWID's performance groups](https://github.com/RRZE-HPC/likwid/tree/master/groups). The collector made multiple iterations and tried to use the performance groups but it lacked flexibility. The current way of configuration provides most flexibility.
+
+The logic is as following: There are multiple eventsets, each consisting of a list of counters+events and a list of metrics. If you compare a common performance group with the example setting above, there is not much difference:
+```
+EVENTSET                         ->   "events": {
+FIXC1 ACTUAL_CPU_CLOCK           ->     "FIXC1": "ACTUAL_CPU_CLOCK",
+FIXC2 MAX_CPU_CLOCK              ->     "FIXC2": "MAX_CPU_CLOCK",
+PMC0  RETIRED_INSTRUCTIONS       ->     "PMC0" : "RETIRED_INSTRUCTIONS",
+PMC1  CPU_CLOCKS_UNHALTED        ->     "PMC1" : "CPU_CLOCKS_UNHALTED",
+PMC2  RETIRED_SSE_AVX_FLOPS_ALL  ->     "PMC2": "RETIRED_SSE_AVX_FLOPS_ALL",
+PMC3  MERGE                      ->     "PMC3": "MERGE",
+                                 ->   }
+```
+
+The metrics are following the same procedure:
+
+```
+METRICS                          ->   "metrics": [
+IPC   PMC0/PMC1                  ->     {
+                                 ->       "name" : "IPC",
+                                 ->       "calc" : "PMC0/PMC1",
+                                 ->       "scope": "cpu",
+                                 ->       "publish": true
+                                 ->     }
+                                 ->   ]
+```
+

collectors/lustreMetric.go

@@ -19,31 +19,20 @@ const LCTL_CMD = `lctl`
 const LCTL_OPTION = `get_param`
 
 type LustreCollectorConfig struct {
-	LCtlCommand        string   `json:"lctl_command,omitempty"`
-	ExcludeMetrics     []string `json:"exclude_metrics,omitempty"`
-	Sudo               bool     `json:"use_sudo,omitempty"`
-	SendAbsoluteValues bool     `json:"send_abs_values,omitempty"`
-	SendDerivedValues  bool     `json:"send_derived_values,omitempty"`
-	SendDiffValues     bool     `json:"send_diff_values,omitempty"`
-}
-
-type LustreMetricDefinition struct {
-	name       string
-	lineprefix string
-	lineoffset int
-	unit       string
-	calc       string
+	LCtlCommand    string   `json:"lctl_command"`
+	ExcludeMetrics []string `json:"exclude_metrics"`
+	SendAllMetrics bool     `json:"send_all_metrics"`
+	Sudo           bool     `json:"use_sudo"`
 }
 
 type LustreCollector struct {
 	metricCollector
-	tags          map[string]string
-	config        LustreCollectorConfig
-	lctl          string
-	sudoCmd       string
-	lastTimestamp time.Time                   // Store time stamp of last tick to derive bandwidths
-	definitions   []LustreMetricDefinition    // Combined list without excluded metrics
-	stats         map[string]map[string]int64 // Data for last value per device and metric
+	tags    map[string]string
+	matches map[string]map[string]int
+	stats   map[string]map[string]int64
+	config  LustreCollectorConfig
+	lctl    string
+	sudoCmd string
 }
 
 func (m *LustreCollector) getDeviceDataCommand(device string) []string {
@@ -86,16 +75,6 @@ func (m *LustreCollector) getDevices() []string {
 	return devices
 }
 
-func getMetricData(lines []string, prefix string, offset int) (int64, error) {
-	for _, line := range lines {
-		if strings.HasPrefix(line, prefix) {
-			lf := strings.Fields(line)
-			return strconv.ParseInt(lf[offset], 0, 64)
-		}
-	}
-	return 0, errors.New("no such line in data")
-}
-
 // //Version reading the stats data of a device from sysfs
 // func (m *LustreCollector) getDeviceDataSysfs(device string) []string {
 // 	llitedir := filepath.Join(LUSTRE_SYSFS, "llite")
@@ -108,183 +87,6 @@ func getMetricData(lines []string, prefix string, offset int) (int64, error) {
 // 	return strings.Split(string(buffer), "\n")
 // }
 
-var LustreAbsMetrics = []LustreMetricDefinition{
-	{
-		name:       "lustre_read_requests",
-		lineprefix: "read_bytes",
-		lineoffset: 1,
-		unit:       "requests",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_write_requests",
-		lineprefix: "write_bytes",
-		lineoffset: 1,
-		unit:       "requests",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_read_bytes",
-		lineprefix: "read_bytes",
-		lineoffset: 6,
-		unit:       "bytes",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_write_bytes",
-		lineprefix: "write_bytes",
-		lineoffset: 6,
-		unit:       "bytes",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_open",
-		lineprefix: "open",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_close",
-		lineprefix: "close",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_setattr",
-		lineprefix: "setattr",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_getattr",
-		lineprefix: "getattr",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_statfs",
-		lineprefix: "statfs",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-	{
-		name:       "lustre_inode_permission",
-		lineprefix: "inode_permission",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "none",
-	},
-}
-
-var LustreDiffMetrics = []LustreMetricDefinition{
-	{
-		name:       "lustre_read_requests_diff",
-		lineprefix: "read_bytes",
-		lineoffset: 1,
-		unit:       "requests",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_write_requests_diff",
-		lineprefix: "write_bytes",
-		lineoffset: 1,
-		unit:       "requests",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_read_bytes_diff",
-		lineprefix: "read_bytes",
-		lineoffset: 6,
-		unit:       "bytes",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_write_bytes_diff",
-		lineprefix: "write_bytes",
-		lineoffset: 6,
-		unit:       "bytes",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_open_diff",
-		lineprefix: "open",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_close_diff",
-		lineprefix: "close",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_setattr_diff",
-		lineprefix: "setattr",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_getattr_diff",
-		lineprefix: "getattr",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_statfs_diff",
-		lineprefix: "statfs",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-	{
-		name:       "lustre_inode_permission_diff",
-		lineprefix: "inode_permission",
-		lineoffset: 1,
-		unit:       "",
-		calc:       "difference",
-	},
-}
-
-var LustreDeriveMetrics = []LustreMetricDefinition{
-	{
-		name:       "lustre_read_requests_rate",
-		lineprefix: "read_bytes",
-		lineoffset: 1,
-		unit:       "requests/sec",
-		calc:       "derivative",
-	},
-	{
-		name:       "lustre_write_requests_rate",
-		lineprefix: "write_bytes",
-		lineoffset: 1,
-		unit:       "requests/sec",
-		calc:       "derivative",
-	},
-	{
-		name:       "lustre_read_bw",
-		lineprefix: "read_bytes",
-		lineoffset: 6,
-		unit:       "bytes/sec",
-		calc:       "derivative",
-	},
-	{
-		name:       "lustre_write_bw",
-		lineprefix: "write_bytes",
-		lineoffset: 6,
-		unit:       "bytes/sec",
-		calc:       "derivative",
-	},
-}
-
 func (m *LustreCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "LustreCollector"
@@ -297,28 +99,42 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
 	m.setup()
 	m.tags = map[string]string{"type": "node"}
 	m.meta = map[string]string{"source": m.name, "group": "Lustre"}
+	defmatches := map[string]map[string]int{
+		"read_bytes":       {"lustre_read_bytes": 6, "lustre_read_requests": 1},
+		"write_bytes":      {"lustre_write_bytes": 6, "lustre_write_requests": 1},
+		"open":             {"lustre_open": 1},
+		"close":            {"lustre_close": 1},
+		"setattr":          {"lustre_setattr": 1},
+		"getattr":          {"lustre_getattr": 1},
+		"statfs":           {"lustre_statfs": 1},
+		"inode_permission": {"lustre_inode_permission": 1}}
 
 	// Lustre file system statistics can only be queried by user root
-	// or with password-less sudo
-	if !m.config.Sudo {
-		user, err := user.Current()
-		if err != nil {
-			cclog.ComponentError(m.name, "Failed to get current user:", err.Error())
-			return err
-		}
-		if user.Uid != "0" {
-			cclog.ComponentError(m.name, "Lustre file system statistics can only be queried by user root")
-			return err
-		}
-	} else {
-		p, err := exec.LookPath("sudo")
-		if err != nil {
-			cclog.ComponentError(m.name, "Cannot find 'sudo'")
-			return err
-		}
-		m.sudoCmd = p
+	user, err := user.Current()
+	if err != nil {
+		cclog.ComponentError(m.name, "Failed to get current user:", err.Error())
+		return err
+	}
+	if user.Uid != "0" {
+		cclog.ComponentError(m.name, "Lustre file system statistics can only be queried by user root")
+		return err
 	}
 
+	m.matches = make(map[string]map[string]int)
+	for lineprefix, names := range defmatches {
+		for metricname, offset := range names {
+			_, skip := stringArrayContains(m.config.ExcludeMetrics, metricname)
+			if skip {
+				continue
+			}
+			if _, prefixExist := m.matches[lineprefix]; !prefixExist {
+				m.matches[lineprefix] = make(map[string]int)
+			}
+			if _, metricExist := m.matches[lineprefix][metricname]; !metricExist {
+				m.matches[lineprefix][metricname] = offset
+			}
+		}
+	}
 	p, err := exec.LookPath(m.config.LCtlCommand)
 	if err != nil {
 		p, err = exec.LookPath(LCTL_CMD)
@@ -327,51 +143,26 @@ func (m *LustreCollector) Init(config json.RawMessage) error {
 		}
 	}
 	m.lctl = p
-
-	m.definitions = []LustreMetricDefinition{}
-	if m.config.SendAbsoluteValues {
-		for _, def := range LustreAbsMetrics {
-			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
-				m.definitions = append(m.definitions, def)
-			}
+	if m.config.Sudo {
+		p, err := exec.LookPath("sudo")
+		if err != nil {
+			m.sudoCmd = p
 		}
 	}
-	if m.config.SendDiffValues {
-		for _, def := range LustreDiffMetrics {
-			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
-				m.definitions = append(m.definitions, def)
-			}
-		}
-	}
-	if m.config.SendDerivedValues {
-		for _, def := range LustreDeriveMetrics {
-			if _, skip := stringArrayContains(m.config.ExcludeMetrics, def.name); !skip {
-				m.definitions = append(m.definitions, def)
-			}
-		}
-	}
-	if len(m.definitions) == 0 {
-		return errors.New("no metrics to collect")
-	}
 
 	devices := m.getDevices()
 	if len(devices) == 0 {
-		return errors.New("no Lustre devices found")
+		return errors.New("no metrics to collect")
 	}
 	m.stats = make(map[string]map[string]int64)
 	for _, d := range devices {
 		m.stats[d] = make(map[string]int64)
-		data := m.getDeviceDataCommand(d)
-		for _, def := range m.definitions {
-			x, err := getMetricData(data, def.lineprefix, def.lineoffset)
-			if err == nil {
-				m.stats[d][def.name] = x
-			} else {
-				m.stats[d][def.name] = 0
+		for _, names := range m.matches {
+			for metricname := range names {
+				m.stats[d][metricname] = 0
 			}
 		}
 	}
-	m.lastTimestamp = time.Now()
 	m.init = true
 	return nil
 }
@@ -380,49 +171,54 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	if !m.init {
 		return
 	}
-	now := time.Now()
-	tdiff := now.Sub(m.lastTimestamp)
 	for device, devData := range m.stats {
-		data := m.getDeviceDataCommand(device)
-		for _, def := range m.definitions {
-			var use_x int64
-			var err error
-			var y lp.CCMetric
-			x, err := getMetricData(data, def.lineprefix, def.lineoffset)
-			if err == nil {
-				use_x = x
-			} else {
-				use_x = devData[def.name]
-			}
-			var value interface{}
-			switch def.calc {
-			case "none":
-				value = use_x
-				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-			case "difference":
-				value = use_x - devData[def.name]
-				if value.(int64) < 0 {
-					value = 0
+		stats := m.getDeviceDataCommand(device)
+		processed := []string{}
+
+		for _, line := range stats {
+			lf := strings.Fields(line)
+			if len(lf) > 1 {
+				if fields, ok := m.matches[lf[0]]; ok {
+					for name, idx := range fields {
+						x, err := strconv.ParseInt(lf[idx], 0, 64)
+						if err != nil {
+							continue
+						}
+						value := x - devData[name]
+						devData[name] = x
+						if value < 0 {
+							value = 0
+						}
+						y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+						if err == nil {
+							y.AddTag("device", device)
+							if strings.Contains(name, "byte") {
+								y.AddMeta("unit", "Byte")
+							}
+							output <- y
+							if m.config.SendAllMetrics {
+								processed = append(processed, name)
+							}
+						}
+					}
 				}
-				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
-			case "derivative":
-				value = float64(use_x-devData[def.name]) / tdiff.Seconds()
-				if value.(float64) < 0 {
-					value = 0
-				}
-				y, err = lp.New(def.name, m.tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			}
-			if err == nil {
-				y.AddTag("device", device)
-				if len(def.unit) > 0 {
-					y.AddMeta("unit", def.unit)
+		}
+		if m.config.SendAllMetrics {
+			for name := range devData {
+				if _, done := stringArrayContains(processed, name); !done {
+					y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": 0}, time.Now())
+					if err == nil {
+						y.AddTag("device", device)
+						if strings.Contains(name, "byte") {
+							y.AddMeta("unit", "Byte")
+						}
+						output <- y
+					}
 				}
-				output <- y
 			}
-			devData[def.name] = use_x
 		}
 	}
-	m.lastTimestamp = now
 }
 
 func (m *LustreCollector) Close() {

collectors/lustreMetric.md

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

collectors/memstatMetric.go

@@ -32,21 +32,15 @@ type MemstatCollectorNode struct {
 
 type MemstatCollector struct {
 	metricCollector
-	stats       map[string]int64
-	tags        map[string]string
-	matches     map[string]string
-	config      MemstatCollectorConfig
-	nodefiles   map[int]MemstatCollectorNode
-	sendMemUsed bool
+	stats     map[string]int64
+	tags      map[string]string
+	matches   map[string]string
+	config    MemstatCollectorConfig
+	nodefiles map[int]MemstatCollectorNode
 }
 
-type MemstatStats struct {
-	value float64
-	unit  string
-}
-
-func getStats(filename string) map[string]MemstatStats {
-	stats := make(map[string]MemstatStats)
+func getStats(filename string) map[string]float64 {
+	stats := make(map[string]float64)
 	file, err := os.Open(filename)
 	if err != nil {
 		cclog.Error(err.Error())
@@ -60,18 +54,12 @@ func getStats(filename string) map[string]MemstatStats {
 		if len(linefields) == 3 {
 			v, err := strconv.ParseFloat(linefields[1], 64)
 			if err == nil {
-				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
-					value: v,
-					unit:  linefields[2],
-				}
+				stats[strings.Trim(linefields[0], ":")] = v
 			}
 		} else if len(linefields) == 5 {
 			v, err := strconv.ParseFloat(linefields[3], 64)
 			if err == nil {
-				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
-					value: v,
-					unit:  linefields[4],
-				}
+				stats[strings.Trim(linefields[0], ":")] = v
 			}
 		}
 	}
@@ -89,7 +77,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 			return err
 		}
 	}
-	m.meta = map[string]string{"source": m.name, "group": "Memory"}
+	m.meta = map[string]string{"source": m.name, "group": "Memory", "unit": "kByte"}
 	m.stats = make(map[string]int64)
 	m.matches = make(map[string]string)
 	m.tags = map[string]string{"type": "node"}
@@ -111,10 +99,6 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 			m.matches[k] = v
 		}
 	}
-	m.sendMemUsed = false
-	if _, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_used"); !skip {
-		m.sendMemUsed = true
-	}
 	if len(m.matches) == 0 {
 		return errors.New("no metrics to collect")
 	}
@@ -162,53 +146,29 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		return
 	}
 
-	sendStats := func(stats map[string]MemstatStats, tags map[string]string) {
+	sendStats := func(stats map[string]float64, tags map[string]string) {
 		for match, name := range m.matches {
 			var value float64 = 0
-			var unit string = ""
 			if v, ok := stats[match]; ok {
-				value = v.value
-				if len(v.unit) > 0 {
-					unit = v.unit
-				}
+				value = v
 			}
-
 			y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now())
 			if err == nil {
-				if len(unit) > 0 {
-					y.AddMeta("unit", unit)
-				}
 				output <- y
 			}
 		}
-		if m.sendMemUsed {
-			memUsed := 0.0
-			unit := ""
-			if totalVal, total := stats["MemTotal"]; total {
-				if freeVal, free := stats["MemFree"]; free {
-					if bufVal, buffers := stats["Buffers"]; buffers {
-						if cacheVal, cached := stats["Cached"]; cached {
-							memUsed = totalVal.value - (freeVal.value + bufVal.value + cacheVal.value)
-							if len(totalVal.unit) > 0 {
-								unit = totalVal.unit
-							} else if len(freeVal.unit) > 0 {
-								unit = freeVal.unit
-							} else if len(bufVal.unit) > 0 {
-								unit = bufVal.unit
-							} else if len(cacheVal.unit) > 0 {
-								unit = cacheVal.unit
-							}
+		if _, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_used"); !skip {
+			if freeVal, free := stats["MemFree"]; free {
+				if bufVal, buffers := stats["Buffers"]; buffers {
+					if cacheVal, cached := stats["Cached"]; cached {
+						memUsed := stats["MemTotal"] - (freeVal + bufVal + cacheVal)
+						y, err := lp.New("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
+						if err == nil {
+							output <- y
 						}
 					}
 				}
 			}
-			y, err := lp.New("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
-			if err == nil {
-				if len(unit) > 0 {
-					y.AddMeta("unit", unit)
-				}
-				output <- y
-			}
 		}
 	}
 

collectors/metricCollector.go

@@ -125,5 +125,5 @@ func RemoveFromStringList(s []string, r string) ([]string, error) {
 			return append(s[:i], s[i+1:]...), nil
 		}
 	}
-	return s, fmt.Errorf("no such string in list")
+	return s, fmt.Errorf("No such string in list")
 }

collectors/netstatMetric.go

@@ -13,27 +13,22 @@ import (
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const NETSTATFILE = "/proc/net/dev"
+const NETSTATFILE = `/proc/net/dev`
 
 type NetstatCollectorConfig struct {
-	IncludeDevices     []string `json:"include_devices"`
-	SendAbsoluteValues bool     `json:"send_abs_values"`
-	SendDerivedValues  bool     `json:"send_derived_values"`
+	IncludeDevices []string `json:"include_devices"`
 }
 
 type NetstatCollectorMetric struct {
-	name       string
-	index      int
-	tags       map[string]string
-	meta       map[string]string
-	meta_rates map[string]string
-	lastValue  int64
+	index     int
+	lastValue float64
 }
 
 type NetstatCollector struct {
 	metricCollector
 	config        NetstatCollectorConfig
-	matches       map[string][]NetstatCollectorMetric
+	matches       map[string]map[string]NetstatCollectorMetric
+	devtags       map[string]map[string]string
 	lastTimestamp time.Time
 }
 
@@ -41,33 +36,15 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 	m.name = "NetstatCollector"
 	m.setup()
 	m.lastTimestamp = time.Now()
-
-	const (
-		fieldInterface = iota
-		fieldReceiveBytes
-		fieldReceivePackets
-		fieldReceiveErrs
-		fieldReceiveDrop
-		fieldReceiveFifo
-		fieldReceiveFrame
-		fieldReceiveCompressed
-		fieldReceiveMulticast
-		fieldTransmitBytes
-		fieldTransmitPackets
-		fieldTransmitErrs
-		fieldTransmitDrop
-		fieldTransmitFifo
-		fieldTransmitColls
-		fieldTransmitCarrier
-		fieldTransmitCompressed
-	)
-
-	m.matches = make(map[string][]NetstatCollectorMetric)
-
-	// Set default configuration,
-	m.config.SendAbsoluteValues = true
-	m.config.SendDerivedValues = false
-	// Read configuration file, allow overwriting default config
+	m.meta = map[string]string{"source": m.name, "group": "Network"}
+	m.devtags = make(map[string]map[string]string)
+	nameIndexMap := map[string]int{
+		"net_bytes_in":  1,
+		"net_pkts_in":   2,
+		"net_bytes_out": 9,
+		"net_pkts_out":  10,
+	}
+	m.matches = make(map[string]map[string]NetstatCollectorMetric)
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -75,9 +52,7 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 			return err
 		}
 	}
-
-	// Check access to net statistic file
-	file, err := os.Open(NETSTATFILE)
+	file, err := os.Open(string(NETSTATFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return err
@@ -87,65 +62,23 @@ func (m *NetstatCollector) Init(config json.RawMessage) error {
 	scanner := bufio.NewScanner(file)
 	for scanner.Scan() {
 		l := scanner.Text()
-
-		// Skip lines with no net device entry
 		if !strings.Contains(l, ":") {
 			continue
 		}
-
-		// Split line into fields
 		f := strings.Fields(l)
-
-		// Get net device entry
 		dev := strings.Trim(f[0], ": ")
-
-		// Check if device is a included device
 		if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
-			tags := map[string]string{"device": dev, "type": "node"}
-			meta_unit_byte := map[string]string{"source": m.name, "group": "Network", "unit": "bytes"}
-			meta_unit_byte_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "bytes/sec"}
-			meta_unit_pkts := map[string]string{"source": m.name, "group": "Network", "unit": "packets"}
-			meta_unit_pkts_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "packets/sec"}
-
-			m.matches[dev] = []NetstatCollectorMetric{
-				{
-					name:       "net_bytes_in",
-					index:      fieldReceiveBytes,
-					lastValue:  -1,
-					tags:       tags,
-					meta:       meta_unit_byte,
-					meta_rates: meta_unit_byte_per_sec,
-				},
-				{
-					name:       "net_pkts_in",
-					index:      fieldReceivePackets,
-					lastValue:  -1,
-					tags:       tags,
-					meta:       meta_unit_pkts,
-					meta_rates: meta_unit_pkts_per_sec,
-				},
-				{
-					name:       "net_bytes_out",
-					index:      fieldTransmitBytes,
-					lastValue:  -1,
-					tags:       tags,
-					meta:       meta_unit_byte,
-					meta_rates: meta_unit_byte_per_sec,
-				},
-				{
-					name:       "net_pkts_out",
-					index:      fieldTransmitPackets,
-					lastValue:  -1,
-					tags:       tags,
-					meta:       meta_unit_pkts,
-					meta_rates: meta_unit_pkts_per_sec,
-				},
+			m.matches[dev] = make(map[string]NetstatCollectorMetric)
+			for name, idx := range nameIndexMap {
+				m.matches[dev][name] = NetstatCollectorMetric{
+					index:     idx,
+					lastValue: 0,
+				}
 			}
+			m.devtags[dev] = map[string]string{"device": dev, "type": "node"}
 		}
-
 	}
-
-	if len(m.matches) == 0 {
+	if len(m.devtags) == 0 {
 		return errors.New("no devices to collector metrics found")
 	}
 	m.init = true
@@ -156,62 +89,50 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	if !m.init {
 		return
 	}
-	// Current time stamp
 	now := time.Now()
-	// time difference to last time stamp
-	timeDiff := now.Sub(m.lastTimestamp).Seconds()
-	// Save current timestamp
-	m.lastTimestamp = now
-
 	file, err := os.Open(string(NETSTATFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
 		return
 	}
 	defer file.Close()
+	tdiff := now.Sub(m.lastTimestamp)
 
 	scanner := bufio.NewScanner(file)
 	for scanner.Scan() {
 		l := scanner.Text()
-
-		// Skip lines with no net device entry
 		if !strings.Contains(l, ":") {
 			continue
 		}
-
-		// Split line into fields
 		f := strings.Fields(l)
-
-		// Get net device entry
 		dev := strings.Trim(f[0], ":")
 
-		// Check if device is a included device
 		if devmetrics, ok := m.matches[dev]; ok {
-			for i := range devmetrics {
-				metric := &devmetrics[i]
-
-				// Read value
-				v, err := strconv.ParseInt(f[metric.index], 10, 64)
-				if err != nil {
-					continue
-				}
-				if m.config.SendAbsoluteValues {
-					if y, err := lp.New(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
+			for name, data := range devmetrics {
+				v, err := strconv.ParseFloat(f[data.index], 64)
+				if err == nil {
+					vdiff := v - data.lastValue
+					value := vdiff / tdiff.Seconds()
+					if data.lastValue == 0 {
+						value = 0
+					}
+					data.lastValue = v
+					y, err := lp.New(name, m.devtags[dev], m.meta, map[string]interface{}{"value": value}, now)
+					if err == nil {
+						switch {
+						case strings.Contains(name, "byte"):
+							y.AddMeta("unit", "bytes/sec")
+						case strings.Contains(name, "pkt"):
+							y.AddMeta("unit", "packets/sec")
+						}
 						output <- y
 					}
-				}
-				if m.config.SendDerivedValues {
-					if metric.lastValue >= 0 {
-						rate := float64(v-metric.lastValue) / timeDiff
-						if y, err := lp.New(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]interface{}{"value": rate}, now); err == nil {
-							output <- y
-						}
-					}
-					metric.lastValue = v
+					devmetrics[name] = data
 				}
 			}
 		}
 	}
+	m.lastTimestamp = time.Now()
 }
 
 func (m *NetstatCollector) Close() {

collectors/netstatMetric.md

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

collectors/nfsMetric.go

@@ -36,7 +36,7 @@ type nfsCollector struct {
 }
 
 func (m *nfsCollector) initStats() error {
-	cmd := exec.Command(m.config.Nfsstats, `-l`, `--all`)
+	cmd := exec.Command(m.config.Nfsstats, `-l`)
 	cmd.Wait()
 	buffer, err := cmd.Output()
 	if err == nil {
@@ -52,7 +52,7 @@ func (m *nfsCollector) initStats() error {
 					if err == nil {
 						x := m.data[name]
 						x.current = value
-						x.last = value
+						x.last = 0
 						m.data[name] = x
 					}
 				}
@@ -63,7 +63,7 @@ func (m *nfsCollector) initStats() error {
 }
 
 func (m *nfsCollector) updateStats() error {
-	cmd := exec.Command(m.config.Nfsstats, `-l`, `--all`)
+	cmd := exec.Command(m.config.Nfsstats, `-l`)
 	cmd.Wait()
 	buffer, err := cmd.Output()
 	if err == nil {

collectors/tempMetric.go

@@ -70,10 +70,10 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 	globPattern := filepath.Join("/sys/class/hwmon", "*", "temp*_input")
 	inputFiles, err := filepath.Glob(globPattern)
 	if err != nil {
-		return fmt.Errorf("unable to glob files with pattern '%s': %v", globPattern, err)
+		return fmt.Errorf("Unable to glob files with pattern '%s': %v", globPattern, err)
 	}
 	if inputFiles == nil {
-		return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
+		return fmt.Errorf("Unable to find any files with pattern '%s'", globPattern)
 	}
 
 	// Get sensor name for each temperature sensor file
@@ -158,7 +158,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 
 	// Empty sensors map
 	if len(m.sensors) == 0 {
-		return fmt.Errorf("no temperature sensors found")
+		return fmt.Errorf("No temperature sensors found")
 	}
 
 	// Finished initialization

collectors/topprocsMetric.go

@@ -39,14 +39,14 @@ func (m *TopProcsCollector) Init(config json.RawMessage) error {
 		m.config.Num_procs = int(DEFAULT_NUM_PROCS)
 	}
 	if m.config.Num_procs <= 0 || m.config.Num_procs > MAX_NUM_PROCS {
-		return fmt.Errorf("num_procs option must be set in 'topprocs' config (range: 1-%d)", MAX_NUM_PROCS)
+		return errors.New(fmt.Sprintf("num_procs option must be set in 'topprocs' config (range: 1-%d)", MAX_NUM_PROCS))
 	}
 	m.setup()
 	command := exec.Command("ps", "-Ao", "comm", "--sort=-pcpu")
 	command.Wait()
 	_, err = command.Output()
 	if err != nil {
-		return errors.New("failed to execute command")
+		return errors.New("Failed to execute command")
 	}
 	m.init = true
 	return nil

docs/configuration.md

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

go.mod

@@ -3,14 +3,17 @@ module github.com/ClusterCockpit/cc-metric-collector
 go 1.16
 
 require (
-	github.com/NVIDIA/go-nvml v0.11.6-0
-	github.com/PaesslerAG/gval v1.1.2
-	github.com/gorilla/mux v1.8.0
-	github.com/influxdata/influxdb-client-go/v2 v2.8.1
+	github.com/NVIDIA/go-nvml v0.11.1-0
+	github.com/influxdata/influxdb-client-go/v2 v2.7.0
 	github.com/influxdata/line-protocol v0.0.0-20210922203350-b1ad95c89adf
-	github.com/nats-io/nats-server/v2 v2.8.0 // indirect
-	github.com/nats-io/nats.go v1.14.0
-	github.com/prometheus/client_golang v1.12.1
-	github.com/stmcginnis/gofish v0.13.0
-	golang.org/x/sys v0.0.0-20220412211240-33da011f77ad
+	github.com/nats-io/nats.go v1.13.1-0.20211122170419-d7c1d78a50fc
+	golang.org/x/sys v0.0.0-20220114195835-da31bd327af9
+	gopkg.in/Knetic/govaluate.v2 v2.3.0
+)
+
+require (
+	github.com/PaesslerAG/gval v1.1.2
+	github.com/golang/protobuf v1.5.2 // indirect
+	github.com/nats-io/nats-server/v2 v2.7.0 // indirect
+	google.golang.org/protobuf v1.27.1 // indirect
 )

internal/ccMetric/ccMetric.go

@@ -24,8 +24,8 @@ type ccMetric struct {
 
 // 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
+	ToPoint(metaAsTags bool) *write.Point  // Generate influxDB point for data type ccMetric
+	ToLineProtocol(metaAsTags bool) string // Generate influxDB line protocol for data type ccMetric
 
 	Name() string        // Get metric name
 	SetName(name string) // Set metric name
@@ -61,18 +61,25 @@ func (m *ccMetric) String() string {
 }
 
 // ToLineProtocol generates influxDB line protocol for data type ccMetric
-func (m *ccMetric) ToPoint(metaAsTags map[string]bool) (p *write.Point) {
-	p = influxdb2.NewPoint(m.name, m.tags, m.fields, m.tm)
-	for key, ok1 := range metaAsTags {
-		if val, ok2 := m.GetMeta(key); ok1 && ok2 {
-			p.AddTag(key, val)
+func (m *ccMetric) ToPoint(metaAsTags bool) (p *write.Point) {
+
+	if !metaAsTags {
+		p = influxdb2.NewPoint(m.name, m.tags, m.fields, m.tm)
+	} else {
+		tags := make(map[string]string, len(m.tags)+len(m.meta))
+		for key, value := range m.tags {
+			tags[key] = value
 		}
+		for key, value := range m.meta {
+			tags[key] = value
+		}
+		p = influxdb2.NewPoint(m.name, tags, m.fields, m.tm)
 	}
-	return p
+	return
 }
 
 // ToLineProtocol generates influxDB line protocol for data type ccMetric
-func (m *ccMetric) ToLineProtocol(metaAsTags map[string]bool) string {
+func (m *ccMetric) ToLineProtocol(metaAsTags bool) string {
 
 	return write.PointToLineProtocol(
 		m.ToPoint(metaAsTags),

internal/ccTopology/ccTopology.go

@@ -169,10 +169,7 @@ func DieList() []int {
 			}
 		}
 	}
-	if len(dielist) > 0 {
-		return dielist
-	}
-	return SocketList()
+	return dielist
 }
 
 type CpuEntry struct {
@@ -264,7 +261,7 @@ func CpuData() []CpuEntry {
 	for _, c := range CpuList() {
 		clist = append(clist, CpuEntry{Cpuid: c})
 	}
-	for i, centry := range clist {
+	for _, centry := range clist {
 		centry.Socket = -1
 		centry.Numadomain = -1
 		centry.Die = -1
@@ -292,8 +289,6 @@ func CpuData() []CpuEntry {
 		// Lookup NUMA domain id
 		centry.Numadomain = getNumaDomain(base)
 
-		// Update values in output list
-		clist[i] = centry
 	}
 	return clist
 }

internal/metricRouter/README.md

@@ -8,8 +8,6 @@ The CCMetric router sits in between the collectors and the sinks and can be used
 {
     "num_cache_intervals" : 1,
     "interval_timestamp" : true,
-    "hostname_tag" : "hostname",
-    "max_forward" : 50,
     "add_tags" : [
         {
             "key" : "cluster",
@@ -57,20 +55,6 @@ 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.
-
-# Processing order in the router
-
-- Add the `hostname_tag` tag (if sent by collectors or cache)
-- If `interval_timestamp == true`, change time of metrics
-- Check if metric should be dropped (`drop_metrics` and `drop_metrics_if`)
-- Add tags from `add_tags`
-- Delete tags from `del_tags`
-- Rename metric based on `rename_metrics` and store old name as `oldname` in meta information
-- Add tags from `add_tags` (if you used the new name in the `if` condition)
-- Delete tags from `del_tags` (if you used the new name in the `if` condition)
-- Send to sinks
-- Move to cache (if `num_cache_intervals > 0`)
-
 # The `interval_timestamp` option
 
 The collectors' `Read()` functions are not called simultaneously and therefore the metrics gathered in an interval can have different timestamps. If you want to avoid that and have a common timestamp (the beginning of the interval), set this option to `true` and the MetricRouter sets the time.
@@ -81,14 +65,6 @@ If the MetricRouter should buffer metrics of intervals in a MetricCache, this op
 
 A `num_cache_intervals > 0` is required to use the `interval_aggregates` option.
 
-# The `hostname_tag` option
-
-By default, the router tags metrics with the hostname for all locally created metrics. The default tag name is `hostname`, but it can be changed if your organization wants anything else
-
-# The `max_forward` option
-
-Every time the router receives a metric through any of the channels, it tries to directly read up to `max_forward` metrics from the same channel. This was done as the router thread would go to sleep and wake up with every arriving metric. The default are `50` metrics at once and `max_forward` needs to greater than `1`.
-
 # The `rename_metrics` option
 
 In the ClusterCockpit world we specified a set of standard metrics. Since some collectors determine the metric names based on files, execuables and libraries, they might change from system to system (or installation to installtion, OS to OS, ...). In order to get the common names, you can rename incoming metrics before sending them to the sink. If the metric name matches the `oldname`, it is changed to `newname`

internal/metricRouter/metricRouter.go

@@ -25,7 +25,6 @@ type metricRouterTagConfig struct {
 
 // Metric router configuration
 type metricRouterConfig struct {
-	HostnameTagName   string                               `json:"hostname_tag"`        // Key name used when adding the hostname to a metric (default 'hostname')
 	AddTags           []metricRouterTagConfig              `json:"add_tags"`            // List of tags that are added when the condition is met
 	DelTags           []metricRouterTagConfig              `json:"delete_tags"`         // List of tags that are removed when the condition is met
 	IntervalAgg       []agg.MetricAggregatorIntervalConfig `json:"interval_aggregates"` // List of aggregation function processed at the end of an interval
@@ -34,7 +33,6 @@ type metricRouterConfig struct {
 	RenameMetrics     map[string]string                    `json:"rename_metrics"`      // Map to rename metric name from key to value
 	IntervalStamp     bool                                 `json:"interval_timestamp"`  // Update timestamp periodically by ticker each interval?
 	NumCacheIntervals int                                  `json:"num_cache_intervals"` // Number of intervals of cached metrics for evaluation
-	MaxForward        int                                  `json:"max_forward"`         // Number of maximal forwarded metrics at one select
 	dropMetrics       map[string]bool                      // Internal map for O(1) lookup
 }
 
@@ -48,6 +46,7 @@ type metricRouter struct {
 	done        chan bool           // channel to finish / stop metric router
 	wg          *sync.WaitGroup     // wait group for all goroutines in cc-metric-collector
 	timestamp   time.Time           // timestamp periodically updated by ticker each interval
+	timerdone   chan bool           // channel to finish / stop timestamp updater
 	ticker      mct.MultiChanTicker // periodically ticking once each interval
 	config      metricRouterConfig  // json encoded config for metric router
 	cache       MetricCache         // pointer to MetricCache
@@ -77,8 +76,7 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 	r.cache_input = make(chan lp.CCMetric)
 	r.wg = wg
 	r.ticker = ticker
-	r.config.MaxForward = ROUTER_MAX_FORWARD
-	r.config.HostnameTagName = "hostname"
+	r.maxForward = ROUTER_MAX_FORWARD
 
 	// Set hostname
 	hostname, err := os.Hostname()
@@ -102,10 +100,6 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 		cclog.ComponentError("MetricRouter", err.Error())
 		return err
 	}
-	r.maxForward = 1
-	if r.config.MaxForward > r.maxForward {
-		r.maxForward = r.config.MaxForward
-	}
 	if r.config.NumCacheIntervals > 0 {
 		r.cache, err = NewCache(r.cache_input, r.ticker, &r.cachewg, r.config.NumCacheIntervals)
 		if err != nil {
@@ -123,6 +117,29 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 	return nil
 }
 
+// StartTimer starts a timer which updates timestamp periodically
+func (r *metricRouter) StartTimer() {
+	m := make(chan time.Time)
+	r.ticker.AddChannel(m)
+	r.timerdone = make(chan bool)
+
+	r.wg.Add(1)
+	go func() {
+		defer r.wg.Done()
+		for {
+			select {
+			case <-r.timerdone:
+				close(r.timerdone)
+				cclog.ComponentDebug("MetricRouter", "TIMER DONE")
+				return
+			case t := <-m:
+				r.timestamp = t
+			}
+		}
+	}()
+	cclog.ComponentDebug("MetricRouter", "TIMER START")
+}
+
 func getParamMap(point lp.CCMetric) map[string]interface{} {
 	params := make(map[string]interface{})
 	params["metric"] = point
@@ -211,9 +228,8 @@ func (r *metricRouter) dropMetric(point lp.CCMetric) bool {
 func (r *metricRouter) Start() {
 	// start timer if configured
 	r.timestamp = time.Now()
-	timeChan := make(chan time.Time)
 	if r.config.IntervalStamp {
-		r.ticker.AddChannel(timeChan)
+		r.StartTimer()
 	}
 
 	// Router manager is done
@@ -228,10 +244,8 @@ func (r *metricRouter) Start() {
 		cclog.ComponentDebug("MetricRouter", "FORWARD", point)
 		r.DoAddTags(point)
 		r.DoDelTags(point)
-		name := point.Name()
-		if new, ok := r.config.RenameMetrics[name]; ok {
+		if new, ok := r.config.RenameMetrics[point.Name()]; ok {
 			point.SetName(new)
-			point.AddMeta("oldname", name)
 		}
 		r.DoAddTags(point)
 		r.DoDelTags(point)
@@ -244,7 +258,7 @@ func (r *metricRouter) Start() {
 	// Foward message received from collector channel
 	coll_forward := func(p lp.CCMetric) {
 		// receive from metric collector
-		p.AddTag(r.config.HostnameTagName, r.hostname)
+		p.AddTag("hostname", r.hostname)
 		if r.config.IntervalStamp {
 			p.SetTime(r.timestamp)
 		}
@@ -273,7 +287,7 @@ func (r *metricRouter) Start() {
 	cache_forward := func(p lp.CCMetric) {
 		// receive from metric collector
 		if !r.dropMetric(p) {
-			p.AddTag(r.config.HostnameTagName, r.hostname)
+			p.AddTag("hostname", r.hostname)
 			forward(p)
 		}
 	}
@@ -293,25 +307,21 @@ func (r *metricRouter) Start() {
 				done()
 				return
 
-			case timestamp := <-timeChan:
-				r.timestamp = timestamp
-				cclog.ComponentDebug("MetricRouter", "Update timestamp", r.timestamp.UnixNano())
-
 			case p := <-r.coll_input:
 				coll_forward(p)
-				for i := 0; len(r.coll_input) > 0 && i < (r.maxForward-1); i++ {
+				for i := 0; len(r.coll_input) > 0 && i < r.maxForward; i++ {
 					coll_forward(<-r.coll_input)
 				}
 
 			case p := <-r.recv_input:
 				recv_forward(p)
-				for i := 0; len(r.recv_input) > 0 && i < (r.maxForward-1); i++ {
+				for i := 0; len(r.recv_input) > 0 && i < r.maxForward; i++ {
 					recv_forward(<-r.recv_input)
 				}
 
 			case p := <-r.cache_input:
 				cache_forward(p)
-				for i := 0; len(r.cache_input) > 0 && i < (r.maxForward-1); i++ {
+				for i := 0; len(r.cache_input) > 0 && i < r.maxForward; i++ {
 					cache_forward(<-r.cache_input)
 				}
 			}
@@ -342,6 +352,14 @@ func (r *metricRouter) Close() {
 	// wait for close of channel r.done
 	<-r.done
 
+	// stop timer
+	if r.config.IntervalStamp {
+		cclog.ComponentDebug("MetricRouter", "TIMER CLOSE")
+		r.timerdone <- true
+		// wait for close of channel r.timerdone
+		<-r.timerdone
+	}
+
 	// stop metric cache
 	if r.config.NumCacheIntervals > 0 {
 		cclog.ComponentDebug("MetricRouter", "CACHE CLOSE")

receivers.json

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

receivers/README.md

@@ -21,7 +21,6 @@ This allows to specify
 
 - [`nats`](./natsReceiver.md): Receive metrics from the NATS network
 - [`prometheus`](./prometheusReceiver.md): Scrape data from a Prometheus client
-- [`http`](./httpReceiver.md): Listen for HTTP Post requests transporting metrics in InfluxDB line protocol
 
 # Contributing own receivers
 A receiver contains a few functions and is derived from the type `Receiver` (in `metricReceiver.go`):

receivers/httpReceiver.go

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

receivers/httpReceiver.md

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

receivers/receiveManager.go

@@ -10,13 +10,14 @@ import (
 )
 
 var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
-	"nats":    NewNatsReceiver,
-	"redfish": NewRedfishReceiver,
+	"nats": NewNatsReceiver,
 }
 
 type receiveManager struct {
 	inputs []Receiver
 	output chan lp.CCMetric
+	done   chan bool
+	wg     *sync.WaitGroup
 	config []json.RawMessage
 }
 
@@ -32,6 +33,8 @@ func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) er
 	// Initialize struct fields
 	rm.inputs = make([]Receiver, 0)
 	rm.output = nil
+	rm.done = make(chan bool)
+	rm.wg = wg
 	rm.config = make([]json.RawMessage, 0)
 
 	configFile, err := os.Open(receiverConfigFile)
@@ -55,7 +58,7 @@ func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) er
 }
 
 func (rm *receiveManager) Start() {
-	cclog.ComponentDebug("ReceiveManager", "START")
+	rm.wg.Add(1)
 
 	for _, r := range rm.inputs {
 		cclog.ComponentDebug("ReceiveManager", "START", r.Name())
@@ -94,19 +97,16 @@ func (rm *receiveManager) AddOutput(output chan lp.CCMetric) {
 }
 
 func (rm *receiveManager) Close() {
-	cclog.ComponentDebug("ReceiveManager", "CLOSE")
-
-	// Close all receivers
 	for _, r := range rm.inputs {
 		cclog.ComponentDebug("ReceiveManager", "CLOSE", r.Name())
 		r.Close()
 	}
-
-	cclog.ComponentDebug("ReceiveManager", "DONE")
+	rm.wg.Done()
+	cclog.ComponentDebug("ReceiveManager", "CLOSE")
 }
 
 func New(wg *sync.WaitGroup, receiverConfigFile string) (ReceiveManager, error) {
-	r := new(receiveManager)
+	r := &receiveManager{}
 	err := r.Init(wg, receiverConfigFile)
 	if err != nil {
 		return nil, err

receivers/redfishReceiver.go

@@ -1,324 +0,0 @@
-package receivers
-
-import (
-	"encoding/json"
-	"fmt"
-	"strconv"
-	"sync"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-
-	// See: https://pkg.go.dev/github.com/stmcginnis/gofish
-	"github.com/stmcginnis/gofish"
-)
-
-// RedfishReceiver configuration:
-type RedfishReceiver struct {
-	receiver
-	config struct {
-		Type     string `json:"type"`
-		Fanout   int    `json:"fanout,omitempty"`   // Default fanout: 64
-		Interval int    `json:"interval,omitempty"` // Default interval: 30s
-
-		// Client config for each redfish service
-		ClientConfigs []struct {
-			Hostname       *string  `json:"hostname"`
-			Username       *string  `json:"username"`
-			Password       *string  `json:"password"`
-			Endpoint       *string  `json:"endpoint"`
-			Insecure       *bool    `json:"insecure,omitempty"`
-			ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-			gofish         gofish.ClientConfig
-		} `json:"client_config"`
-	}
-
-	done chan bool      // channel to finish / stop redfish receiver
-	wg   sync.WaitGroup // wait group for redfish receiver
-}
-
-// Start starts the redfish receiver
-func (r *RedfishReceiver) Start() {
-	cclog.ComponentDebug(r.name, "START")
-
-	// readPowerMetric reads readfish power metric from the endpoint configured in conf
-	readPowerMetric := func(clientConfigIndex int) error {
-
-		clientConfig := &r.config.ClientConfigs[clientConfigIndex]
-
-		// Connect to redfish service
-		c, err := gofish.Connect(clientConfig.gofish)
-		if err != nil {
-			c := struct {
-				Username  string
-				Endpoint  string
-				BasicAuth bool
-				Insecure  bool
-			}{
-				Username:  clientConfig.gofish.Username,
-				Endpoint:  clientConfig.gofish.Endpoint,
-				BasicAuth: clientConfig.gofish.BasicAuth,
-				Insecure:  clientConfig.gofish.Insecure,
-			}
-			return fmt.Errorf("readPowerMetric: gofish.Connect(%+v) failed: %v", c, err)
-		}
-		defer c.Logout()
-
-		// Get all chassis managed by this service
-		chassis_list, err := c.Service.Chassis()
-		if err != nil {
-			return fmt.Errorf("readPowerMetric: c.Service.Chassis() failed: %v", err)
-		}
-
-		for _, chassis := range chassis_list {
-			timestamp := time.Now()
-
-			// Get power information for each chassis
-			power, err := chassis.Power()
-			if err != nil {
-				return fmt.Errorf("readPowerMetric: chassis.Power() failed: %v", err)
-			}
-			if power == nil {
-				continue
-			}
-
-			// Read min, max and average consumed watts for each power control
-			for _, pc := range power.PowerControl {
-
-				// Map of collected metrics
-				metrics := map[string]float32{
-					// PowerConsumedWatts shall represent the actual power being consumed (in
-					// Watts) by the chassis
-					"consumed_watts": pc.PowerConsumedWatts,
-					// AverageConsumedWatts shall represent the
-					// average power level that occurred averaged over the last IntervalInMin
-					// minutes.
-					"average_consumed_watts": pc.PowerMetrics.AverageConsumedWatts,
-					// MinConsumedWatts shall represent the
-					// minimum power level in watts that occurred within the last
-					// IntervalInMin minutes.
-					"min_consumed_watts": pc.PowerMetrics.MinConsumedWatts,
-					// MaxConsumedWatts shall represent the
-					// maximum power level in watts that occurred within the last
-					// IntervalInMin minutes
-					"max_consumed_watts": pc.PowerMetrics.MaxConsumedWatts,
-				}
-				intervalInMin := strconv.FormatFloat(float64(pc.PowerMetrics.IntervalInMin), 'f', -1, 32)
-
-				// Metrics to exclude
-				for _, key := range clientConfig.ExcludeMetrics {
-					delete(metrics, key)
-				}
-
-				// Set tags
-				tags := map[string]string{
-					"hostname": *clientConfig.Hostname,
-					"type":     "node",
-					// ID uniquely identifies the resource
-					"id": pc.ID,
-					// MemberID shall uniquely identify the member within the collection. For
-					// services supporting Redfish v1.6 or higher, this value shall be the
-					// zero-based array index.
-					"member_id": pc.MemberID,
-					// PhysicalContext shall be a description of the affected device(s) or region
-					// within the chassis to which this power control applies.
-					"physical_context": string(pc.PhysicalContext),
-					// Name
-					"power_control_name": pc.Name,
-				}
-
-				// Delete empty tags
-				for key, value := range tags {
-					if value == "" {
-						delete(tags, key)
-					}
-				}
-
-				// Set meta data tags
-				meta := map[string]string{
-					"source":              r.name,
-					"group":               "Energy",
-					"interval_in_minutes": intervalInMin,
-					"unit":                "watts",
-				}
-
-				// Delete empty meta data tags
-				for key, value := range meta {
-					if value == "" {
-						delete(meta, key)
-					}
-				}
-
-				for name, value := range metrics {
-
-					y, err := lp.New(name, tags, meta,
-						map[string]interface{}{
-							"value": value,
-						},
-						timestamp)
-					if err == nil {
-						r.sink <- y
-					}
-				}
-			}
-		}
-
-		return nil
-	}
-
-	// doReadPowerMetric read power metrics for all configure redfish services.
-	// To compensate latencies of the Redfish services a fanout is used.
-	doReadPowerMetric := func() {
-
-		// Compute fanout to use
-		realFanout := r.config.Fanout
-		if len(r.config.ClientConfigs) < realFanout {
-			realFanout = len(r.config.ClientConfigs)
-		}
-
-		// Create wait group and input channel for workers
-		var workerWaitGroup sync.WaitGroup
-		workerInput := make(chan int, realFanout)
-
-		// Create worker go routines
-		for i := 0; i < realFanout; i++ {
-			// Increment worker wait group counter
-			workerWaitGroup.Add(1)
-			go func() {
-				// Decrement worker wait group counter
-				defer workerWaitGroup.Done()
-
-				// Read power metrics for each client config
-				for clientConfigIndex := range workerInput {
-					err := readPowerMetric(clientConfigIndex)
-					if err != nil {
-						cclog.ComponentError(r.name, err)
-					}
-				}
-			}()
-		}
-
-		// Distribute client configs to workers
-		for i := range r.config.ClientConfigs {
-			// Check done channel status
-			select {
-			case workerInput <- i:
-			case <-r.done:
-				// process done event
-				// Stop workers, clear channel and wait for all workers to finish
-				close(workerInput)
-				for range workerInput {
-				}
-				workerWaitGroup.Wait()
-				return
-			}
-		}
-
-		// Stop workers and wait for all workers to finish
-		close(workerInput)
-		workerWaitGroup.Wait()
-	}
-
-	// Start redfish receiver
-	r.wg.Add(1)
-	go func() {
-		defer r.wg.Done()
-
-		// Create ticker
-		ticker := time.NewTicker(time.Duration(r.config.Interval) * time.Second)
-		defer ticker.Stop()
-
-		for {
-			doReadPowerMetric()
-
-			select {
-			case <-ticker.C:
-				// process ticker event -> continue
-				continue
-			case <-r.done:
-				// process done event
-				return
-			}
-		}
-	}()
-
-	cclog.ComponentDebug(r.name, "STARTED")
-}
-
-// Close redfish receiver
-func (r *RedfishReceiver) Close() {
-	cclog.ComponentDebug(r.name, "CLOSE")
-
-	// Send the signal and wait
-	close(r.done)
-	r.wg.Wait()
-
-	cclog.ComponentDebug(r.name, "DONE")
-}
-
-// New function to create a new instance of the receiver
-// Initialize the receiver by giving it a name and reading in the config JSON
-func NewRedfishReceiver(name string, config json.RawMessage) (Receiver, error) {
-	r := new(RedfishReceiver)
-
-	// Set name
-	r.name = fmt.Sprintf("RedfishReceiver(%s)", name)
-
-	// Create done channel
-	r.done = make(chan bool)
-
-	// Set defaults in r.config
-	// Allow overwriting these defaults by reading config JSON
-	r.config.Fanout = 64
-	r.config.Interval = 30
-
-	// Read the redfish receiver specific JSON config
-	if len(config) > 0 {
-		err := json.Unmarshal(config, &r.config)
-		if err != nil {
-			cclog.ComponentError(r.name, "Error reading config:", err.Error())
-			return nil, err
-		}
-	}
-
-	// Create gofish client config
-	for i := range r.config.ClientConfigs {
-		clientConfig := &r.config.ClientConfigs[i]
-		gofishConfig := &clientConfig.gofish
-
-		if clientConfig.Hostname == nil {
-			err := fmt.Errorf("client config number %v requires hostname", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-
-		if clientConfig.Endpoint == nil {
-			err := fmt.Errorf("client config number %v requires endpoint", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		gofishConfig.Endpoint = *clientConfig.Endpoint
-
-		if clientConfig.Username == nil {
-			err := fmt.Errorf("client config number %v requires username", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		gofishConfig.Username = *clientConfig.Username
-
-		if clientConfig.Password == nil {
-			err := fmt.Errorf("client config number %v requires password", i)
-			cclog.ComponentError(r.name, err)
-			return nil, err
-		}
-		gofishConfig.Password = *clientConfig.Password
-
-		gofishConfig.Insecure = true
-		if clientConfig.Insecure != nil {
-			gofishConfig.Insecure = *clientConfig.Insecure
-		}
-	}
-
-	return r, nil
-}

receivers/sampleReceiver.go

@@ -36,26 +36,16 @@ func (r *SampleReceiver) Start() {
 
 	// or use own go routine but always make sure it exits
 	// as soon as it gets the signal of the r.done channel
-	//
-	// r.done = make(chan bool)
 	// r.wg.Add(1)
 	// go func() {
-	//      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
-	//          }
-	//      }
+	// 	for {
+	// 		select {
+	// 		case <-r.done:
+	// 			r.wg.Done()
+	// 			return
+	// 		}
+	// 	}
+	// 	r.wg.Done()
 	// }()
 }
 

scripts/cc-metric-collector.deb.control

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

scripts/cc-metric-collector.spec

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

sinks.json

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

sinks/gangliaCommon.go

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

sinks/gangliaSink.go

@@ -39,13 +39,16 @@ func (s *GangliaSink) Write(point lp.CCMetric) error {
 	//var tagsstr []string
 	var argstr []string
 
+	// Get metric name
+	metricname := GangliaMetricRename(point.Name())
+
 	// Get metric config (type, value, ... in suitable format)
 	conf := GetCommonGangliaConfig(point)
 	if len(conf.Type) == 0 {
 		conf = GetGangliaConfig(point)
 	}
 	if len(conf.Type) == 0 {
-		return fmt.Errorf("metric %q (Ganglia name %q) has no 'value' field", point.Name(), conf.Name)
+		return fmt.Errorf("metric %s has no 'value' field", metricname)
 	}
 
 	if s.config.AddGangliaGroup {
@@ -67,7 +70,7 @@ func (s *GangliaSink) Write(point lp.CCMetric) error {
 	if s.config.AddTypeToName {
 		argstr = append(argstr, fmt.Sprintf("--name=%s", GangliaMetricName(point)))
 	} else {
-		argstr = append(argstr, fmt.Sprintf("--name=%s", conf.Name))
+		argstr = append(argstr, fmt.Sprintf("--name=%s", metricname))
 	}
 	argstr = append(argstr, fmt.Sprintf("--slope=%s", conf.Slope))
 	argstr = append(argstr, fmt.Sprintf("--value=%s", conf.Value))

sinks/httpSink.go

@@ -22,7 +22,6 @@ type HttpSinkConfig struct {
 	MaxIdleConns    int    `json:"max_idle_connections,omitempty"`
 	IdleConnTimeout string `json:"idle_connection_timeout,omitempty"`
 	FlushDelay      string `json:"flush_delay,omitempty"`
-	BatchSize       int    `json:"batch_size,omitempty"`
 }
 
 type HttpSink struct {
@@ -37,33 +36,30 @@ type HttpSink struct {
 	idleConnTimeout time.Duration
 	timeout         time.Duration
 	flushDelay      time.Duration
-	batchSize       int
 }
 
 func (s *HttpSink) Write(m lp.CCMetric) error {
 	if s.buffer.Len() == 0 && s.flushDelay != 0 {
 		// This is the first write since the last flush, start the flushTimer!
 		if s.flushTimer != nil && s.flushTimer.Stop() {
-			cclog.ComponentDebug(s.name, "unexpected: the flushTimer was already running?")
+			cclog.ComponentDebug("HttpSink", "unexpected: the flushTimer was already running?")
 		}
 
 		// Run a batched flush for all lines that have arrived in the last second
 		s.flushTimer = time.AfterFunc(s.flushDelay, func() {
 			if err := s.Flush(); err != nil {
-				cclog.ComponentError(s.name, "flush failed:", err.Error())
+				cclog.ComponentError("HttpSink", "flush failed:", err.Error())
 			}
 		})
 	}
 
-	p := m.ToPoint(s.meta_as_tags)
+	p := m.ToPoint(s.config.MetaAsTags)
 
 	s.lock.Lock()
 	_, err := s.encoder.Encode(p)
-	s.batchSize++
 	s.lock.Unlock() // defer does not work here as Flush() takes the lock as well
 
 	if err != nil {
-		cclog.ComponentError(s.name, "encoding failed:", err.Error())
 		return err
 	}
 
@@ -71,9 +67,6 @@ func (s *HttpSink) Write(m lp.CCMetric) error {
 	if s.flushDelay == 0 {
 		return s.Flush()
 	}
-	if s.batchSize == s.config.BatchSize {
-		return s.Flush()
-	}
 
 	return err
 }
@@ -91,7 +84,6 @@ func (s *HttpSink) Flush() error {
 	// Create new request to send buffer
 	req, err := http.NewRequest(http.MethodPost, s.config.URL, s.buffer)
 	if err != nil {
-		cclog.ComponentError(s.name, "failed to create request:", err.Error())
 		return err
 	}
 
@@ -105,19 +97,15 @@ func (s *HttpSink) Flush() error {
 
 	// Clear buffer
 	s.buffer.Reset()
-	s.batchSize = 0
 
 	// Handle transport/tcp errors
 	if err != nil {
-		cclog.ComponentError(s.name, "transport/tcp error:", err.Error())
 		return err
 	}
 
 	// Handle application errors
 	if res.StatusCode != http.StatusOK {
-		err = errors.New(res.Status)
-		cclog.ComponentError(s.name, "application error:", err.Error())
-		return err
+		return errors.New(res.Status)
 	}
 
 	return nil
@@ -126,7 +114,7 @@ func (s *HttpSink) Flush() error {
 func (s *HttpSink) Close() {
 	s.flushTimer.Stop()
 	if err := s.Flush(); err != nil {
-		cclog.ComponentError(s.name, "flush failed:", err.Error())
+		cclog.ComponentError("HttpSink", "flush failed:", err.Error())
 	}
 	s.client.CloseIdleConnections()
 }
@@ -139,7 +127,6 @@ func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
 	s.config.IdleConnTimeout = "5s"
 	s.config.Timeout = "5s"
 	s.config.FlushDelay = "1s"
-	s.config.BatchSize = 100
 
 	// Read config
 	if len(config) > 0 {
@@ -172,11 +159,6 @@ func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
 			s.flushDelay = t
 		}
 	}
-	// Create lookup map to use meta infos as tags in the output metric
-	s.meta_as_tags = make(map[string]bool)
-	for _, k := range s.config.MetaAsTags {
-		s.meta_as_tags[k] = true
-	}
 	tr := &http.Transport{
 		MaxIdleConns:    s.maxIdleConns,
 		IdleConnTimeout: s.idleConnTimeout,

sinks/httpSink.md

@@ -15,7 +15,6 @@ The `http` sink uses POST requests to a HTTP server to submit the metrics in the
     "max_idle_connections" : 10,
     "idle_connection_timeout" : "5s",
     "flush_delay": "2s",
-    "batch_size" : 100
   }
 }
 ```
@@ -28,4 +27,3 @@ The `http` sink uses POST requests to a HTTP server to submit the metrics in the
 - `max_idle_connections`: Maximally idle connections (default 10)
 - `idle_connection_timeout`: Timeout for idle connections (default '5s')
 - `flush_delay`: Batch all writes arriving in during this duration (default '1s', batching can be disabled by setting it to 0)
-- `batch_size`: Maximal number of batched metrics. Either it is flushed because batch size or the `flush_delay` is reached

sinks/influxAsyncSink.go

@@ -6,14 +6,11 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"strings"
-	"time"
 
 	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	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 {
@@ -29,25 +26,15 @@ type InfluxAsyncSinkConfig struct {
 	// 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"`
+	FlushInterval uint `json:"flush_interval,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
+	client   influxdb2.Client
+	writeApi influxdb2Api.WriteAPI
+	errors   <-chan error
+	config   InfluxAsyncSinkConfig
 }
 
 func (s *InfluxAsyncSink) connect() error {
@@ -66,35 +53,16 @@ func (s *InfluxAsyncSink) connect() error {
 	cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
 	clientOptions := influxdb2.DefaultOptions()
 	if s.config.BatchSize != 0 {
-		cclog.ComponentDebug(s.name, "Batch size", s.config.BatchSize)
 		clientOptions.SetBatchSize(s.config.BatchSize)
 	}
 	if s.config.FlushInterval != 0 {
-		cclog.ComponentDebug(s.name, "Flush interval", s.config.FlushInterval)
 		clientOptions.SetFlushInterval(s.config.FlushInterval)
 	}
-	if s.influxRetryInterval != 0 {
-		cclog.ComponentDebug(s.name, "MaxRetryInterval", s.influxRetryInterval)
-		clientOptions.SetMaxRetryInterval(s.influxRetryInterval)
-	}
-	if s.influxMaxRetryTime != 0 {
-		cclog.ComponentDebug(s.name, "MaxRetryTime", s.influxMaxRetryTime)
-		clientOptions.SetMaxRetryTime(s.influxMaxRetryTime)
-	}
-	if s.config.InfluxExponentialBase != 0 {
-		cclog.ComponentDebug(s.name, "Exponential Base", s.config.InfluxExponentialBase)
-		clientOptions.SetExponentialBase(s.config.InfluxExponentialBase)
-	}
-	if s.config.InfluxMaxRetries != 0 {
-		cclog.ComponentDebug(s.name, "Max Retries", s.config.InfluxMaxRetries)
-		clientOptions.SetMaxRetries(s.config.InfluxMaxRetries)
-	}
 	clientOptions.SetTLSConfig(
 		&tls.Config{
 			InsecureSkipVerify: true,
 		},
-	).SetPrecision(time.Second)
-
+	)
 	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
 	s.writeApi = s.client.WriteAPI(s.config.Organization, s.config.Database)
 	ok, err := s.client.Ping(context.Background())
@@ -104,35 +72,18 @@ func (s *InfluxAsyncSink) connect() error {
 	if !ok {
 		return fmt.Errorf("connection to %s not healthy", uri)
 	}
-	s.writeApi.SetWriteFailedCallback(func(batch string, err influxdb2ApiHttp.Error, retryAttempts uint) bool {
-		mlist := strings.Split(batch, "\n")
-		cclog.ComponentError(s.name, fmt.Sprintf("Failed to write batch with %d metrics %d times (max: %d): %s", len(mlist), retryAttempts, s.config.MaxRetryAttempts, err.Error()))
-		return retryAttempts <= s.config.MaxRetryAttempts
-	})
 	return nil
 }
 
 func (s *InfluxAsyncSink) Write(m lp.CCMetric) error {
-	if s.customFlushInterval != 0 && s.flushTimer == nil {
-		// Run a batched flush for all lines that have arrived in the defined interval
-		s.flushTimer = time.AfterFunc(s.customFlushInterval, func() {
-			if err := s.Flush(); err != nil {
-				cclog.ComponentError(s.name, "flush failed:", err.Error())
-			}
-		})
-	}
 	s.writeApi.WritePoint(
-		m.ToPoint(s.meta_as_tags),
+		m.ToPoint(s.config.MetaAsTags),
 	)
 	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
 }
 
@@ -147,38 +98,7 @@ func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
 	s.name = fmt.Sprintf("InfluxSink(%s)", name)
 
 	// Set default for maximum number of points sent to server in single request.
-	s.config.BatchSize = 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
+	s.config.BatchSize = 100
 
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &s.config)
@@ -193,30 +113,6 @@ func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
 		len(s.config.Password) == 0 {
 		return nil, errors.New("not all configuration variables set required by InfluxAsyncSink")
 	}
-	// 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 {

sinks/influxAsyncSink.md

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

sinks/influxSink.go

@@ -6,14 +6,11 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"sync"
-	"time"
 
 	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
 	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
-	"github.com/influxdata/influxdb-client-go/v2/api/write"
 )
 
 type InfluxSinkConfig struct {
@@ -25,88 +22,38 @@ type InfluxSinkConfig struct {
 	Password     string `json:"password,omitempty"`
 	Organization string `json:"organization,omitempty"`
 	SSL          bool   `json:"ssl,omitempty"`
-	FlushDelay   string `json:"flush_delay,omitempty"`
-	BatchSize    int    `json:"batch_size,omitempty"`
 	RetentionPol string `json:"retention_policy,omitempty"`
-	// InfluxRetryInterval   string `json:"retry_interval"`
-	// InfluxExponentialBase uint   `json:"retry_exponential_base"`
-	// InfluxMaxRetries      uint   `json:"max_retries"`
-	// InfluxMaxRetryTime    string `json:"max_retry_time"`
-	//InfluxMaxRetryDelay  string `json:"max_retry_delay"` // It is mentioned in the docs but there is no way to set it
 }
 
 type InfluxSink struct {
 	sink
-	client              influxdb2.Client
-	writeApi            influxdb2Api.WriteAPIBlocking
-	config              InfluxSinkConfig
-	influxRetryInterval uint
-	influxMaxRetryTime  uint
-	batch               []*write.Point
-	flushTimer          *time.Timer
-	flushDelay          time.Duration
-	lock                sync.Mutex // Flush() runs in another goroutine, so this lock has to protect the buffer
-	//influxMaxRetryDelay uint
+	client   influxdb2.Client
+	writeApi influxdb2Api.WriteAPIBlocking
+	config   InfluxSinkConfig
 }
 
-// connect connects to the InfluxDB server
 func (s *InfluxSink) connect() error {
-
-	// URI options:
-	// * http://host:port
-	// * https://host:port
+	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)
 	}
-
-	// Authentication options:
-	// * token
-	// * username:password
-	var auth string
 	if len(s.config.User) == 0 {
 		auth = s.config.Password
 	} else {
 		auth = fmt.Sprintf("%s:%s", s.config.User, s.config.Password)
 	}
 	cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
-
-	// Set influxDB client options
 	clientOptions := influxdb2.DefaultOptions()
-
-	// 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)
-	// }
-
-	// Do not check InfluxDB certificate
 	clientOptions.SetTLSConfig(
 		&tls.Config{
 			InsecureSkipVerify: true,
 		},
 	)
-
-	clientOptions.SetPrecision(time.Second)
-
-	// Create new writeAPI
 	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
 	s.writeApi = s.client.WriteAPIBlocking(s.config.Organization, s.config.Database)
-
-	// Check InfluxDB server accessibility
 	ok, err := s.client.Ping(context.Background())
 	if err != nil {
 		return err
@@ -118,142 +65,39 @@ func (s *InfluxSink) connect() error {
 }
 
 func (s *InfluxSink) Write(m lp.CCMetric) error {
-
-	if len(s.batch) == 0 && s.flushDelay != 0 {
-		// This is the first write since the last flush, start the flushTimer!
-		if s.flushTimer != nil && s.flushTimer.Stop() {
-			cclog.ComponentDebug(s.name, "unexpected: the flushTimer was already running?")
-		}
-
-		// Run a batched flush for all lines that have arrived in the last flush delay interval
-		s.flushTimer = time.AfterFunc(s.flushDelay, func() {
-			if err := s.Flush(); err != nil {
-				cclog.ComponentError(s.name, "flush failed:", err.Error())
-			}
-		})
-	}
-
-	// Append metric to batch slice
-	p := m.ToPoint(s.meta_as_tags)
-	s.lock.Lock()
-	s.batch = append(s.batch, p)
-	s.lock.Unlock()
-
-	// Flush synchronously if "flush_delay" is zero
-	if s.flushDelay == 0 {
-		return s.Flush()
-	}
-
-	// Flush if batch size is reached
-	if len(s.batch) == s.config.BatchSize {
-		return s.Flush()
-	}
-
-	return nil
+	err :=
+		s.writeApi.WritePoint(
+			context.Background(),
+			m.ToPoint(s.config.MetaAsTags),
+		)
+	return err
 }
 
-// Flush sends all metrics buffered in batch slice to InfluxDB server
 func (s *InfluxSink) Flush() error {
-
-	// Lock access to batch slice
-	s.lock.Lock()
-	defer s.lock.Unlock()
-
-	// Nothing to do, batch slice is empty
-	if len(s.batch) == 0 {
-		return nil
-	}
-
-	// Send metrics from batch slice
-	err := s.writeApi.WritePoint(context.Background(), s.batch...)
-	if err != nil {
-		cclog.ComponentError(s.name, "flush failed:", err.Error())
-		return err
-	}
-
-	// Clear batch slice
-	for i := range s.batch {
-		s.batch[i] = nil
-	}
-	s.batch = s.batch[:0]
-
 	return nil
 }
 
 func (s *InfluxSink) Close() {
 	cclog.ComponentDebug(s.name, "Closing InfluxDB connection")
-	s.flushTimer.Stop()
-	s.Flush()
 	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 = 100
-	s.config.FlushDelay = "1s"
-
-	// Read config
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &s.config)
 		if err != nil {
 			return nil, err
 		}
 	}
-	s.influxRetryInterval = 0
-	s.influxMaxRetryTime = 0
-	// s.config.InfluxRetryInterval = ""
-	// s.config.InfluxMaxRetryTime = ""
-	// s.config.InfluxMaxRetries = 0
-	// s.config.InfluxExponentialBase = 0
-
-	if len(s.config.Host) == 0 {
-		return nil, errors.New("Missing host configuration required by InfluxSink")
+	if len(s.config.Host) == 0 ||
+		len(s.config.Port) == 0 ||
+		len(s.config.Database) == 0 ||
+		len(s.config.Organization) == 0 ||
+		len(s.config.Password) == 0 {
+		return nil, errors.New("not all configuration variables set required by InfluxSink")
 	}
-	if len(s.config.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 {
-	// 	if len(duration) > 0 {
-	// 		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)
-
-	// Configure flush delay duration
-	if len(s.config.FlushDelay) > 0 {
-		t, err := time.ParseDuration(s.config.FlushDelay)
-		if err == nil {
-			s.flushDelay = t
-		}
-	}
-
-	// allocate batch slice
-	s.batch = make([]*write.Point, 0, s.config.BatchSize)
 
 	// Connect to InfluxDB server
 	if err := s.connect(); err != nil {

sinks/influxSink.md

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

sinks/libgangliaSink.go

@@ -124,21 +124,24 @@ func (s *LibgangliaSink) Write(point lp.CCMetric) error {
 		return s.cstrCache[key]
 	}
 
+	// Get metric name
+	metricname := GangliaMetricRename(point.Name())
+
 	conf := GetCommonGangliaConfig(point)
 	if len(conf.Type) == 0 {
 		conf = GetGangliaConfig(point)
 	}
 	if len(conf.Type) == 0 {
-		return fmt.Errorf("metric %q (Ganglia name %q) has no 'value' field", point.Name(), conf.Name)
+		return fmt.Errorf("metric %s has no 'value' field", metricname)
 	}
 
 	if s.config.AddTypeToName {
-		conf.Name = GangliaMetricName(point)
+		metricname = GangliaMetricName(point)
 	}
 
 	c_value = C.CString(conf.Value)
 	c_type = lookup(conf.Type)
-	c_name = lookup(conf.Name)
+	c_name = lookup(metricname)
 
 	// Add unit
 	unit := ""

sinks/metricSink.go

@@ -5,13 +5,13 @@ import (
 )
 
 type defaultSinkConfig struct {
-	MetaAsTags []string `json:"meta_as_tags,omitempty"`
-	Type       string   `json:"type"`
+	MetaAsTags bool   `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
+	meta_as_tags bool   // Use meta data tags as tags
+	name         string // Name of the sink
 }
 
 type Sink interface {

sinks/natsSink.go

@@ -55,7 +55,7 @@ func (s *NatsSink) connect() error {
 
 func (s *NatsSink) Write(m lp.CCMetric) error {
 	if s.client != nil {
-		_, err := s.encoder.Encode(m.ToPoint(s.meta_as_tags))
+		_, err := s.encoder.Encode(m.ToPoint(s.config.MetaAsTags))
 		if err != nil {
 			cclog.ComponentError(s.name, "Write:", err.Error())
 			return err
@@ -97,11 +97,6 @@ func NewNatsSink(name string, config json.RawMessage) (Sink, error) {
 		len(s.config.Database) == 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)
@@ -110,7 +105,7 @@ func NewNatsSink(name string, config json.RawMessage) (Sink, error) {
 	s.encoder.SetMaxLineBytes(1024)
 	// Setup infos for connection
 	if err := s.connect(); err != nil {
-		return nil, fmt.Errorf("unable to connect: %v", err)
+		return nil, fmt.Errorf("Unable to connect: %v", err)
 	}
 	return s, nil
 }

sinks/sampleSink.go

@@ -10,14 +10,14 @@ import (
 )
 
 type SampleSinkConfig struct {
-	// defines JSON tags for 'type' and 'meta_as_tags' (string list)
+	// defines JSON tags for 'type' and 'meta_as_tags'
 	// See: metricSink.go
 	defaultSinkConfig
 	// Additional config options, for SampleSink
 }
 
 type SampleSink struct {
-	// declares elements 	'name' and 'meta_as_tags' (string to bool map!)
+	// declares elements 	'name' and 'meta_as_tags'
 	sink
 	config SampleSinkConfig // entry point to the SampleSinkConfig
 }
@@ -28,7 +28,6 @@ type SampleSink struct {
 
 // 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
 }
@@ -63,12 +62,6 @@ func NewSampleSink(name string, config json.RawMessage) (Sink, error) {
 		}
 	}
 
-	// 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
 

sinks/stdoutSink.go

@@ -63,11 +63,7 @@ func NewStdoutSink(name string, config json.RawMessage) (Sink, error) {
 			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
-	}
+	s.meta_as_tags = s.config.MetaAsTags
 
 	return s, nil
 }