Set proper user for files

Add Red Hat Universal Base Image 8 Workflow

.github/ci-receivers.json

@@ -1 +1 @@
-[]
+{}

.github/ci-sinks.json

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

.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/rpmbuild.yml

@@ -1,61 +0,0 @@
-name: Run RPM Build
-on: push
-
-jobs:
-  build-centos8:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-    - uses: TomTheBear/rpmbuild@master
-      id: rpm
-      name: Build RPM package on CentOS8
-      with:
-        spec_file: "./scripts/cc-metric-collector.spec"
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v1.0.0
-      with:
-        name: cc-metric-collector RPM CentOS8
-        path: ${{ steps.rpm.outputs.rpm_dir_path }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v1.0.0
-      with:
-        name: cc-metric-collector SRPM CentOS8
-        path: ${{ steps.rpm.outputs.source_rpm_path }}
-  build-centos-latest:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-    - uses: TomTheBear/rpmbuild@centos_latest
-      id: rpm
-      name: Build RPM package on CentOS 'Latest'
-      with:
-        spec_file: "./scripts/cc-metric-collector.spec"
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v1.0.0
-      with:
-        name: cc-metric-collector RPM CentOS 'Latest'
-        path: ${{ steps.rpm.outputs.rpm_dir_path }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v1.0.0
-      with:
-        name: cc-metric-collector SRPM CentOS 'Latest'
-        path: ${{ steps.rpm.outputs.source_rpm_path }}
-  build-alma-8_5:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v2
-    - uses: TomTheBear/rpmbuild@alma8.5
-      id: rpm
-      name: Build RPM package on AlmaLinux 8.5
-      with:
-        spec_file: "./scripts/cc-metric-collector.spec"
-    - name: Save RPM as artifact
-      uses: actions/upload-artifact@v1.0.0
-      with:
-        name: cc-metric-collector RPM AlmaLinux 8.5
-        path: ${{ steps.rpm.outputs.rpm_dir_path }}
-    - name: Save SRPM as artifact
-      uses: actions/upload-artifact@v1.0.0
-      with:
-        name: cc-metric-collector SRPM AlmaLinux 8.5
-        path: ${{ steps.rpm.outputs.source_rpm_path }}

.github/workflows/runonce.yml

@@ -1,20 +1,68 @@
+# See: https://docs.github.com/en/actions/using-workflows/workflow-syntax-for-github-actions
+
+# Workflow name
 name: Run Test
+
+# Run on event push
 on: push
 
 jobs:
-  build:
+  #
+  # Job build-1-17
+  # Build on latest Ubuntu using golang version 1.17 
+  #
+  build-1-17:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@v2
+    # See: https://github.com/marketplace/actions/checkout
+    # Checkout git repository and submodules
+    - name: Checkout
+      uses: actions/checkout@v2
+      with:
+        submodules: recursive
 
     # See: https://github.com/marketplace/actions/setup-go-environment
     - name: Setup Golang
-      uses: actions/setup-go@v2.1.5
+      uses: actions/setup-go@v2
       with:
-        go-version: '^1.17.6'
+        go-version: '^1.17.7'
+
+    # Install libganglia
+    - name: Setup Ganglia
+      run: sudo apt install ganglia-monitor libganglia1
 
     - name: Build MetricCollector
       run: make
 
-    - name: Run MetricCollector
+    - name: Run MetricCollector once
+      run: ./cc-metric-collector --once --config .github/ci-config.json
+
+  #
+  # Job build-1-16
+  # Build on latest Ubuntu using golang version 1.16
+  #
+  build-1-16:
+    runs-on: ubuntu-latest
+    steps:
+    # See: https://github.com/marketplace/actions/checkout
+    # Checkout git repository and submodules
+    - name: Checkout
+      uses: actions/checkout@v2
+      with:
+        submodules: recursive
+
+    # See: https://github.com/marketplace/actions/setup-go-environment
+    - name: Setup Golang
+      uses: actions/setup-go@v2
+      with:
+        go-version: '^1.16.7' # The version AlmaLinux 8.5 uses
+
+    # Install libganglia
+    - name: Setup Ganglia
+      run: sudo apt install ganglia-monitor libganglia1
+
+    - name: Build MetricCollector
+      run: make
+
+    - name: Run MetricCollector once
       run: ./cc-metric-collector --once --config .github/ci-config.json

.gitmodules

@@ -0,0 +1,4 @@
+[submodule ".github/actions/rpmbuild-centos8-golang"]
+	path = .github/actions/rpmbuild-centos8-golang
+	url = https://github.com/naveenrajm7/rpmbuild.git
+	branch = centos8

Makefile

@@ -1,10 +1,19 @@
 APP = cc-metric-collector
-GOSRC_APP        := metric-collector.go
+GOSRC_APP        := cc-metric-collector.go
 GOSRC_COLLECTORS := $(wildcard collectors/*.go)
 GOSRC_SINKS      := $(wildcard sinks/*.go)
 GOSRC_RECEIVERS  := $(wildcard receivers/*.go)
 GOSRC_INTERNAL   := $(wildcard internal/*/*.go)
 GOSRC            := $(GOSRC_APP) $(GOSRC_COLLECTORS) $(GOSRC_SINKS) $(GOSRC_RECEIVERS) $(GOSRC_INTERNAL)
+COMPONENT_DIRS   := collectors \
+			sinks \
+			receivers \
+			internal/metricRouter \
+			internal/ccMetric \
+			internal/metricAggregator \
+			internal/ccLogger \
+			internal/ccTopology \
+			internal/multiChanTicker
 
 
 .PHONY: all
@@ -16,8 +25,14 @@ $(APP): $(GOSRC)
 	go build -o $(APP) $(GOSRC_APP)
 
 .PHONY: clean
+.ONESHELL:
 clean:
-	make -C collectors clean
+	@for COMP in $(COMPONENT_DIRS)
+	do
+	    if [[ -e $$COMP/Makefile ]]; then
+	        make -C $$COMP clean
+	    fi
+	done
 	rm -f $(APP)
 
 .PHONY: fmt
@@ -41,3 +56,33 @@ vet:
 staticcheck:
 	go install honnef.co/go/tools/cmd/staticcheck@latest
 	$$(go env GOPATH)/bin/staticcheck ./...
+
+.ONESHELL:
+.PHONY: RPM
+RPM: scripts/cc-metric-collector.spec
+	@WORKSPACE="$${PWD}"
+	@SPECFILE="$${WORKSPACE}/scripts/cc-metric-collector.spec"
+	# Setup RPM build tree
+	@eval $$(rpm --eval "ARCH='%{_arch}' RPMDIR='%{_rpmdir}' SOURCEDIR='%{_sourcedir}' SPECDIR='%{_specdir}' SRPMDIR='%{_srcrpmdir}' BUILDDIR='%{_builddir}'")
+	@mkdir --parents --verbose "$${RPMDIR}" "$${SOURCEDIR}" "$${SPECDIR}" "$${SRPMDIR}" "$${BUILDDIR}"
+	# Create source tarball
+	@COMMITISH="HEAD"
+	@VERS=$$(git describe --tags $${COMMITISH})
+	@VERS=$${VERS#v}
+	@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"
+	@SRCFILE="$${SOURCEDIR}/$${PREFIX}.$${FORMAT}"
+	@git archive --verbose --format "$${FORMAT}" --prefix="$${PREFIX}/" --output="$${SRCFILE}" $${COMMITISH}
+	# Build RPM and SRPM
+	@rpmbuild -ba --define="VERS $${VERS}" --rmsource --clean "$${SPECFILE}"
+	# Report RPMs and SRPMs when in GitHub Workflow
+	@if [[ "$${GITHUB_ACTIONS}" == true ]]; then
+	@     RPMFILE="$${RPMDIR}/$${ARCH}/$${NVRA}.rpm"
+	@     SRPMFILE="$${SRPMDIR}/$${NVR}.src.rpm"
+	@     echo "RPM: $${RPMFILE}"
+	@     echo "SRPM: $${SRPMFILE}"
+	@     echo "::set-output name=SRPM::$${SRPMFILE}"
+	@     echo "::set-output name=RPM::$${RPMFILE}"
+	@fi

README.md

@@ -39,14 +39,15 @@ See the component READMEs for their configuration:
 ```
 $ git clone git@github.com:ClusterCockpit/cc-metric-collector.git
 $ make (downloads LIKWID, builds it as static library with 'direct' accessmode and copies all required files for the collector)
-$ go get (requires at least golang 1.13)
-$ go build metric-collector
+$ go get (requires at least golang 1.16)
+$ make
 ```
 
+
 # Running
 
 ```
-$ ./metric-collector --help
+$ ./cc-metric-collector --help
 Usage of metric-collector:
   -config string
     	Path to configuration file (default "./config.json")
@@ -54,10 +55,42 @@ Usage of metric-collector:
     	Path for logfile (default "stderr")
   -once
     	Run all collectors only once
-  -pidfile string
-    	Path for PID file (default "/var/run/cc-metric-collector.pid")
+```
+# Scenarios
+
+The metric collector was designed with flexibility in mind, so it can be used in many scenarios. Here are a few:
+
+```mermaid
+flowchart TD
+  subgraph a ["Cluster A"]
+  nodeA[NodeA with CC collector]
+  nodeB[NodeB with CC collector]
+  nodeC[NodeC with CC collector]
+  end
+  a --> db[(Database)]
+  db <--> ccweb("Webfrontend")
 ```
 
+``` mermaid
+flowchart TD
+  subgraph a [ClusterA]
+  direction LR
+  nodeA[NodeA with CC collector]
+  nodeB[NodeB with CC collector]
+  nodeC[NodeC with CC collector]
+  end
+  subgraph b [ClusterB]
+  direction LR
+  nodeD[NodeD with CC collector]
+  nodeE[NodeE with CC collector]
+  nodeF[NodeF with CC collector]
+  end
+  a --> ccrecv{"CC collector as receiver"}
+  b --> ccrecv
+  ccrecv --> db[("Database1")]
+  ccrecv -.-> db2[("Database2")]
+  db <-.-> ccweb("Webfrontend")
+```
 
 # Contributing
 The ClusterCockpit ecosystem is designed to be used by different HPC computing centers. Since configurations and setups differ between the centers, the centers likely have to put some work into the cc-metric-collector to gather all desired metrics.

cc-metric-collector.go

@@ -24,7 +24,6 @@ import (
 type CentralConfigFile struct {
 	Interval            int    `json:"interval"`
 	Duration            int    `json:"duration"`
-	Pidfile             string `json:"pidfile,omitempty"`
 	CollectorConfigFile string `json:"collectors"`
 	RouterConfigFile    string `json:"router"`
 	SinkConfigFile      string `json:"sinks"`
@@ -87,14 +86,12 @@ func ReadCli() map[string]string {
 	var m map[string]string
 	cfg := flag.String("config", "./config.json", "Path to configuration file")
 	logfile := flag.String("log", "stderr", "Path for logfile")
-	pidfile := flag.String("pidfile", "/var/run/cc-metric-collector.pid", "Path for PID file")
 	once := flag.Bool("once", false, "Run all collectors only once")
 	debug := flag.Bool("debug", false, "Activate debug output")
 	flag.Parse()
 	m = make(map[string]string)
 	m["configfile"] = *cfg
 	m["logfile"] = *logfile
-	m["pidfile"] = *pidfile
 	if *once {
 		m["once"] = "true"
 	} else {
@@ -125,25 +122,6 @@ func ReadCli() map[string]string {
 //	return nil
 //}
 
-//func CreatePidfile(pidfile string) error {
-//	file, err := os.OpenFile(pidfile, os.O_CREATE|os.O_RDWR, 0600)
-//	if err != nil {
-//		log.Print(err)
-//		return err
-//	}
-//	file.Write([]byte(fmt.Sprintf("%d", os.Getpid())))
-//	file.Close()
-//	return nil
-//}
-
-//func RemovePidfile(pidfile string) error {
-//	info, err := os.Stat(pidfile)
-//	if !os.IsNotExist(err) && !info.IsDir() {
-//		os.Remove(pidfile)
-//	}
-//	return nil
-//}
-
 // General shutdownHandler function that gets executed in case of interrupt or graceful shutdownHandler
 func shutdownHandler(config *RuntimeConfig, shutdownSignal chan os.Signal) {
 	defer config.Sync.Done()
@@ -174,11 +152,6 @@ func shutdownHandler(config *RuntimeConfig, shutdownSignal chan os.Signal) {
 		cclog.Debug("Shutdown SinkManager...")
 		config.SinkManager.Close()
 	}
-
-	//	pidfile := config.ConfigFile.Pidfile
-	//	RemovePidfile(pidfile)
-	//	pidfile = config.CliArgs["pidfile"]
-	//	RemovePidfile(pidfile)
 }
 
 func mainFunc() int {
@@ -226,8 +199,6 @@ func mainFunc() int {
 		return 1
 	}
 
-	//	err = CreatePidfile(rcfg.CliArgs["pidfile"])
-
 	// Set log file
 	if logfile := rcfg.CliArgs["logfile"]; logfile != "stderr" {
 		cclog.SetOutput(logfile)

collectors.json

@@ -1,15 +1,31 @@
 {
+    "cpufreq": {},
+    "cpufreq_cpuinfo": {},
+    "gpfs": {
+        "exclude_filesystem": [
+            "test_fs"
+        ]
+    },
+    "ibstat": {},
+    "loadavg": {
+        "exclude_metrics": [
+            "proc_total"
+        ]
+    },
+    "numastats": {},
+    "nvidia": {},
     "tempstat": {
-      "tag_override": {
-        "hwmon0" : {
-            "type" : "socket",
-            "type-id" : "0"
-        },
-        "hwmon1" : {
-            "type" : "socket",
-            "type-id" : "1"
+        "report_max_temperature": true,
+        "report_critical_temperature": true,
+        "tag_override": {
+            "hwmon0": {
+                "type": "socket",
+                "type-id": "0"
+            },
+            "hwmon1": {
+                "type": "socket",
+                "type-id": "1"
+            }
         }
-      }
     }
-    
-}
+}

collectors/Makefile

@@ -55,16 +55,13 @@ $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION): $(BUILD_FOLDER)/likwid-$(LIKWID_VERSIO
 	tar -C $(BUILD_FOLDER) -xf $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION).tar.gz
 
 $(INSTALL_FOLDER)/liblikwid.a: $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION) $(INSTALL_FOLDER)
-	sed -i -e s+"PREFIX ?= .*"+"PREFIX = $(LIKWID_BASE)"+g \
-		-e s+"SHARED_LIBRARY = .*"+"SHARED_LIBRARY = false"+g \
-		-e s+"ACCESSMODE = .*"+"ACCESSMODE = $(ACCESSMODE)"+g \
-		-e s+"INSTALLED_ACCESSDAEMON = .*"+"INSTALLED_ACCESSDAEMON = $(DAEMON_INSTALLDIR)/likwid-accessD"+g \
-		$(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/config.mk
-	cd $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION) && make
-	cp $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/liblikwid.a $(INSTALL_FOLDER)
-	cp $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/ext/hwloc/liblikwid-hwloc.a $(INSTALL_FOLDER)
-	cp $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/src/includes/likwid*.h $(INSTALL_FOLDER)
-	cp $(BUILD_FOLDER)/likwid-$(LIKWID_VERSION)/src/includes/bstrlib.h $(INSTALL_FOLDER)
+	cd "$(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

collectors/README.md

@@ -18,21 +18,28 @@ In contrast to the configuration files for sinks and receivers, the collectors c
 
 * [`cpustat`](./cpustatMetric.md)
 * [`memstat`](./memstatMetric.md)
+* [`iostat`](./iostatMetric.md)
 * [`diskstat`](./diskstatMetric.md)
 * [`loadavg`](./loadavgMetric.md)
 * [`netstat`](./netstatMetric.md)
 * [`ibstat`](./infinibandMetric.md)
+* [`ibstat_perfquery`](./infinibandPerfQueryMetric.md)
 * [`tempstat`](./tempMetric.md)
-* [`lustre`](./lustreMetric.md)
+* [`lustrestat`](./lustreMetric.md)
 * [`likwid`](./likwidMetric.md)
 * [`nvidia`](./nvidiaMetric.md)
 * [`customcmd`](./customCmdMetric.md)
 * [`ipmistat`](./ipmiMetric.md)
 * [`topprocs`](./topprocsMetric.md)
+* [`nfs3stat`](./nfs3Metric.md)
+* [`nfs4stat`](./nfs4Metric.md)
+* [`cpufreq`](./cpufreqMetric.md)
+* [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
+* [`numastat`](./numastatMetric.md)
+* [`gpfs`](./gpfsMetric.md)
 
 ## Todos
 
-* [ ] Exclude devices for `diskstat` collector
 * [ ] Aggreate metrics to higher topology entity (sum hwthread metrics to socket metric, ...). Needs to be configurable
 
 # Contributing own collectors
@@ -71,6 +78,11 @@ type SampleCollector struct {
 }
 
 func (m *SampleCollector) Init(config json.RawMessage) error {
+    // Check if already initialized
+    if m.init {
+        return nil
+    }
+
     m.name = "SampleCollector"
     m.setup()
     if len(config) > 0 {
@@ -91,10 +103,15 @@ func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric)
     }
     // tags for the metric, if type != node use proper type and type-id
     tags := map[string]string{"type" : "node"}
+
+    x, err := GetMetric()
+    if err != nil {
+        cclog.ComponentError(m.name, fmt.Sprintf("Read(): %v", err))
+    }
+
     // Each metric has exactly one field: value !
-    value := map[string]interface{}{"value": int(x)}
-    y, err := lp.New("sample_metric", tags, m.meta, value, time.Now())
-    if err == nil {
+    value := map[string]interface{}{"value": int64(x)}
+    if y, err := lp.New("sample_metric", tags, m.meta, value, time.Now()); err == nil {
         output <- y
     }
 }

collectors/collectorManager.go

@@ -25,13 +25,16 @@ var AvailableCollectors = map[string]MetricCollector{
 	"topprocs":         new(TopProcsCollector),
 	"nvidia":           new(NvidiaCollector),
 	"customcmd":        new(CustomCmdCollector),
+	"iostat":           new(IOstatCollector),
 	"diskstat":         new(DiskstatCollector),
 	"tempstat":         new(TempCollector),
 	"ipmistat":         new(IpmiCollector),
 	"gpfs":             new(GpfsCollector),
 	"cpufreq":          new(CPUFreqCollector),
 	"cpufreq_cpuinfo":  new(CPUFreqCpuInfoCollector),
-	"nfsstat":          new(NfsCollector),
+	"nfs3stat":         new(Nfs3Collector),
+	"nfs4stat":         new(Nfs4Collector),
+	"numastats":        new(NUMAStatsCollector),
 }
 
 // Metric collector manager data structure

collectors/cpufreqCpuinfoMetric.go

@@ -5,13 +5,13 @@ import (
 	"encoding/json"
 
 	"fmt"
-	"log"
 	"os"
 	"strconv"
 	"strings"
 	"time"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 //
@@ -23,45 +23,55 @@ import (
 type CPUFreqCpuInfoCollectorTopology struct {
 	processor               string // logical processor number (continuous, starting at 0)
 	coreID                  string // socket local core ID
-	coreID_int              int
+	coreID_int              int64
 	physicalPackageID       string // socket / package ID
-	physicalPackageID_int   int
+	physicalPackageID_int   int64
 	numPhysicalPackages     string // number of  sockets / packages
-	numPhysicalPackages_int int
+	numPhysicalPackages_int int64
 	isHT                    bool
 	numNonHT                string // number of non hyperthreading processors
-	numNonHT_int            int
+	numNonHT_int            int64
 	tagSet                  map[string]string
 }
 
 type CPUFreqCpuInfoCollector struct {
 	metricCollector
-	topology []CPUFreqCpuInfoCollectorTopology
+	topology []*CPUFreqCpuInfoCollectorTopology
 }
 
 func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+
+	m.setup()
+
 	m.name = "CPUFreqCpuInfoCollector"
 	m.meta = map[string]string{
 		"source": m.name,
-		"group":  "cpufreq",
+		"group":  "CPU",
+		"unit":   "MHz",
 	}
 
 	const cpuInfoFile = "/proc/cpuinfo"
 	file, err := os.Open(cpuInfoFile)
 	if err != nil {
-		return fmt.Errorf("Failed to open '%s': %v", cpuInfoFile, err)
+		return fmt.Errorf("Failed to open file '%s': %v", cpuInfoFile, err)
 	}
 	defer file.Close()
 
 	// Collect topology information from file cpuinfo
 	foundFreq := false
 	processor := ""
-	numNonHT_int := 0
+	var numNonHT_int int64 = 0
 	coreID := ""
 	physicalPackageID := ""
-	maxPhysicalPackageID := 0
-	m.topology = make([]CPUFreqCpuInfoCollectorTopology, 0)
+	var maxPhysicalPackageID int64 = 0
+	m.topology = make([]*CPUFreqCpuInfoCollectorTopology, 0)
 	coreSeenBefore := make(map[string]bool)
+
+	// Read cpuinfo file, line by line
 	scanner := bufio.NewScanner(file)
 	for scanner.Scan() {
 		lineSplit := strings.Split(scanner.Text(), ":")
@@ -87,39 +97,41 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 			len(coreID) > 0 &&
 			len(physicalPackageID) > 0 {
 
-			coreID_int, err := strconv.Atoi(coreID)
+			topology := new(CPUFreqCpuInfoCollectorTopology)
+
+			// Processor
+			topology.processor = processor
+
+			// Core ID
+			topology.coreID = coreID
+			topology.coreID_int, err = strconv.ParseInt(coreID, 10, 64)
 			if err != nil {
-				return fmt.Errorf("Unable to convert coreID to int: %v", err)
+				return fmt.Errorf("Unable to convert coreID '%s' to int64: %v", coreID, err)
 			}
-			physicalPackageID_int, err := strconv.Atoi(physicalPackageID)
+
+			// 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 to int: %v", err)
+				return fmt.Errorf("Unable to convert physicalPackageID '%s' to int64: %v", physicalPackageID, err)
 			}
 
 			// increase maximun socket / package ID, when required
-			if physicalPackageID_int > maxPhysicalPackageID {
-				maxPhysicalPackageID = physicalPackageID_int
+			if topology.physicalPackageID_int > maxPhysicalPackageID {
+				maxPhysicalPackageID = topology.physicalPackageID_int
 			}
 
+			// is hyperthread?
 			globalID := physicalPackageID + ":" + coreID
-			isHT := coreSeenBefore[globalID]
+			topology.isHT = coreSeenBefore[globalID]
 			coreSeenBefore[globalID] = true
-			if !isHT {
+			if !topology.isHT {
 				// increase number on non hyper thread cores
 				numNonHT_int++
 			}
 
 			// store collected topology information
-			m.topology = append(
-				m.topology,
-				CPUFreqCpuInfoCollectorTopology{
-					processor:             processor,
-					coreID:                coreID,
-					coreID_int:            coreID_int,
-					physicalPackageID:     physicalPackageID,
-					physicalPackageID_int: physicalPackageID_int,
-					isHT:                  isHT,
-				})
+			m.topology = append(m.topology, topology)
 
 			// reset topology information
 			foundFreq = false
@@ -132,18 +144,15 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 	numPhysicalPackageID_int := maxPhysicalPackageID + 1
 	numPhysicalPackageID := fmt.Sprint(numPhysicalPackageID_int)
 	numNonHT := fmt.Sprint(numNonHT_int)
-	for i := range m.topology {
-		t := &m.topology[i]
+	for _, t := range m.topology {
 		t.numPhysicalPackages = numPhysicalPackageID
 		t.numPhysicalPackages_int = numPhysicalPackageID_int
 		t.numNonHT = numNonHT
 		t.numNonHT_int = numNonHT_int
 		t.tagSet = map[string]string{
-			"type":        "cpu",
-			"type-id":     t.processor,
-			"num_core":    t.numNonHT,
-			"package_id":  t.physicalPackageID,
-			"num_package": t.numPhysicalPackages,
+			"type":       "cpu",
+			"type-id":    t.processor,
+			"package_id": t.physicalPackageID,
 		}
 	}
 
@@ -151,15 +160,18 @@ func (m *CPUFreqCpuInfoCollector) Init(config json.RawMessage) error {
 	return nil
 }
 
-
 func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	// Check if already initialized
 	if !m.init {
 		return
 	}
+
 	const cpuInfoFile = "/proc/cpuinfo"
 	file, err := os.Open(cpuInfoFile)
 	if err != nil {
-		log.Printf("Failed to open '%s': %v", cpuInfoFile, err)
+		cclog.ComponentError(
+			m.name,
+			fmt.Sprintf("Read(): Failed to open file '%s': %v", cpuInfoFile, err))
 		return
 	}
 	defer file.Close()
@@ -174,15 +186,16 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
 
 			// frequency
 			if key == "cpu MHz" {
-				t := &m.topology[processorCounter]
+				t := m.topology[processorCounter]
 				if !t.isHT {
 					value, err := strconv.ParseFloat(strings.TrimSpace(lineSplit[1]), 64)
 					if err != nil {
-						log.Printf("Failed to convert cpu MHz to float: %v", err)
+						cclog.ComponentError(
+							m.name,
+							fmt.Sprintf("Read(): Failed to convert cpu MHz '%s' to float64: %v", lineSplit[1], err))
 						return
 					}
-					y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now)
-					if err == nil {
+					if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": value}, now); err == nil {
 						output <- y
 					}
 				}

collectors/cpufreqCpuinfoMetric.md

@@ -0,0 +1,10 @@
+
+## `cpufreq_cpuinfo` collector
+```json
+  "cpufreq_cpuinfo": {}
+```
+
+The `cpufreq_cpuinfo` collector reads the clock frequency from `/proc/cpuinfo` and outputs a handful **cpu** metrics.
+
+Metrics:
+* `cpufreq`

collectors/cpufreqMetric.go

@@ -1,48 +1,30 @@
 package collectors
 
 import (
-	"bufio"
 	"encoding/json"
 	"fmt"
-	"log"
-	"os"
+	"io/ioutil"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	"golang.org/x/sys/unix"
 )
 
-//
-// readOneLine reads one line from a file.
-// It returns ok when file was successfully read.
-// In this case text contains the first line of the files contents.
-//
-func readOneLine(filename string) (text string, ok bool) {
-	file, err := os.Open(filename)
-	if err != nil {
-		return
-	}
-	defer file.Close()
-	scanner := bufio.NewScanner(file)
-	ok = scanner.Scan()
-	text = scanner.Text()
-	return
-}
-
 type CPUFreqCollectorTopology struct {
 	processor               string // logical processor number (continuous, starting at 0)
 	coreID                  string // socket local core ID
-	coreID_int              int
+	coreID_int              int64
 	physicalPackageID       string // socket / package ID
-	physicalPackageID_int   int
+	physicalPackageID_int   int64
 	numPhysicalPackages     string // number of  sockets / packages
-	numPhysicalPackages_int int
+	numPhysicalPackages_int int64
 	isHT                    bool
 	numNonHT                string // number of non hyperthreading processors
-	numNonHT_int            int
+	numNonHT_int            int64
 	scalingCurFreqFile      string
 	tagSet                  map[string]string
 }
@@ -64,6 +46,11 @@ type CPUFreqCollector struct {
 }
 
 func (m *CPUFreqCollector) Init(config json.RawMessage) error {
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+
 	m.name = "CPUFreqCollector"
 	m.setup()
 	if len(config) > 0 {
@@ -74,7 +61,8 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	}
 	m.meta = map[string]string{
 		"source": m.name,
-		"group":  "CPU Frequency",
+		"group":  "CPU",
+		"unit":   "MHz",
 	}
 
 	// Loop for all CPU directories
@@ -82,48 +70,50 @@ 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("CPUFreqCollector.Init() 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("CPUFreqCollector.Init() unable to find any files with pattern %s", globPattern)
+		return fmt.Errorf("Unable to find any files with pattern '%s'", globPattern)
 	}
 
 	// Initialize CPU topology
 	m.topology = make([]CPUFreqCollectorTopology, len(cpuDirs))
 	for _, cpuDir := range cpuDirs {
 		processor := strings.TrimPrefix(cpuDir, "/sys/devices/system/cpu/cpu")
-		processor_int, err := strconv.Atoi(processor)
+		processor_int, err := strconv.ParseInt(processor, 10, 64)
 		if err != nil {
-			return fmt.Errorf("CPUFreqCollector.Init() unable to convert cpuID to int: %v", 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")
-		physicalPackageID, ok := readOneLine(physicalPackageIDFile)
-		if !ok {
-			return fmt.Errorf("CPUFreqCollector.Init() unable to read physical package ID from %s", physicalPackageIDFile)
-		}
-		physicalPackageID_int, err := strconv.Atoi(physicalPackageID)
+		line, err := ioutil.ReadFile(physicalPackageIDFile)
 		if err != nil {
-			return fmt.Errorf("CPUFreqCollector.Init() unable to convert packageID to int: %v", 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)
 		}
 
 		// Read core ID
 		coreIDFile := filepath.Join(cpuDir, "topology", "core_id")
-		coreID, ok := readOneLine(coreIDFile)
-		if !ok {
-			return fmt.Errorf("CPUFreqCollector.Init() unable to read core ID from %s", coreIDFile)
-		}
-		coreID_int, err := strconv.Atoi(coreID)
+		line, err = ioutil.ReadFile(coreIDFile)
 		if err != nil {
-			return fmt.Errorf("CPUFreqCollector.Init() unable to convert coreID to int: %v", 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)
 		}
 
 		// 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("CPUFreqCollector.Init() unable to access %s: %v", scalingCurFreqFile, err)
+			return fmt.Errorf("Unable to access file '%s': %v", scalingCurFreqFile, err)
 		}
 
 		t := &m.topology[processor_int]
@@ -146,8 +136,8 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 	}
 
 	// number of non hyper thread cores and packages / sockets
-	numNonHT_int := 0
-	maxPhysicalPackageID := 0
+	var numNonHT_int int64 = 0
+	var maxPhysicalPackageID int64 = 0
 	for i := range m.topology {
 		t := &m.topology[i]
 
@@ -171,11 +161,9 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 		t.numNonHT = numNonHT
 		t.numNonHT_int = numNonHT_int
 		t.tagSet = map[string]string{
-			"type":        "cpu",
-			"type-id":     t.processor,
-			"num_core":    t.numNonHT,
-			"package_id":  t.physicalPackageID,
-			"num_package": t.numPhysicalPackages,
+			"type":       "cpu",
+			"type-id":    t.processor,
+			"package_id": t.physicalPackageID,
 		}
 	}
 
@@ -184,6 +172,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 }
 
 func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	// Check if already initialized
 	if !m.init {
 		return
 	}
@@ -198,19 +187,22 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		}
 
 		// Read current frequency
-		line, ok := readOneLine(t.scalingCurFreqFile)
-		if !ok {
-			log.Printf("CPUFreqCollector.Read(): Failed to read one line from file '%s'", t.scalingCurFreqFile)
+		line, err := ioutil.ReadFile(t.scalingCurFreqFile)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to read file '%s': %v", t.scalingCurFreqFile, err))
 			continue
 		}
-		cpuFreq, err := strconv.Atoi(line)
+		cpuFreq, err := strconv.ParseInt(strings.TrimSpace(string(line)), 10, 64)
 		if err != nil {
-			log.Printf("CPUFreqCollector.Read(): Failed to convert CPU frequency '%s': %v", line, err)
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert CPU frequency '%s' to int64: %v", line, err))
 			continue
 		}
 
-		y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now)
-		if err == nil {
+		if y, err := lp.New("cpufreq", t.tagSet, m.meta, map[string]interface{}{"value": cpuFreq}, now); err == nil {
 			output <- y
 		}
 	}

collectors/cpufreqMetric.md

@@ -0,0 +1,11 @@
+## `cpufreq_cpuinfo` collector
+```json
+  "cpufreq": {
+    "exclude_metrics": []
+  }
+```
+
+The `cpufreq` collector reads the clock frequency from `/sys/devices/system/cpu/cpu*/cpufreq` and outputs a handful **cpu** metrics.
+
+Metrics:
+* `cpufreq`

collectors/cpustatMetric.go

@@ -1,12 +1,15 @@
 package collectors
 
 import (
+	"bufio"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"os"
 	"strconv"
 	"strings"
 	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
@@ -18,72 +21,128 @@ type CpustatCollectorConfig struct {
 
 type CpustatCollector struct {
 	metricCollector
-	config CpustatCollectorConfig
+	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 {
 	m.name = "CpustatCollector"
 	m.setup()
-	m.meta = map[string]string{"source": m.name, "group": "CPU"}
+	m.meta = map[string]string{"source": m.name, "group": "CPU", "unit": "Percent"}
+	m.nodetags = map[string]string{"type": "node"}
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
+	matches := map[string]int{
+		"cpu_user":       1,
+		"cpu_nice":       2,
+		"cpu_system":     3,
+		"cpu_idle":       4,
+		"cpu_iowait":     5,
+		"cpu_irq":        6,
+		"cpu_softirq":    7,
+		"cpu_steal":      8,
+		"cpu_guest":      9,
+		"cpu_guest_nice": 10,
+	}
+
+	m.matches = make(map[string]int)
+	for match, index := range matches {
+		doExclude := false
+		for _, exclude := range m.config.ExcludeMetrics {
+			if match == exclude {
+				doExclude = true
+				break
+			}
+		}
+		if !doExclude {
+			m.matches[match] = index
+		}
+	}
+
+	// Check input file
+	file, err := os.Open(string(CPUSTATFILE))
+	if err != nil {
+		cclog.ComponentError(m.name, err.Error())
+	}
+	defer file.Close()
+
+	// Pre-generate tags for all CPUs
+	num_cpus := 0
+	m.cputags = make(map[string]map[string]string)
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := scanner.Text()
+		linefields := strings.Fields(line)
+		if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
+			cpustr := strings.TrimLeft(linefields[0], "cpu")
+			cpu, _ := strconv.Atoi(cpustr)
+			m.cputags[linefields[0]] = map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", cpu)}
+			num_cpus++
+		}
+	}
 	m.init = true
 	return nil
 }
 
-func (c *CpustatCollector) parseStatLine(line string, cpu int, exclude []string, output chan lp.CCMetric) {
-	ls := strings.Fields(line)
-	matches := []string{"", "cpu_user", "cpu_nice", "cpu_system", "cpu_idle", "cpu_iowait", "cpu_irq", "cpu_softirq", "cpu_steal", "cpu_guest", "cpu_guest_nice"}
-	for _, ex := range exclude {
-		matches, _ = RemoveFromStringList(matches, ex)
-	}
-
-	var tags map[string]string
-	if cpu < 0 {
-		tags = map[string]string{"type": "node"}
-	} else {
-		tags = map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", cpu)}
-	}
-	for i, m := range matches {
-		if len(m) > 0 {
-			x, err := strconv.ParseInt(ls[i], 0, 64)
+func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric) {
+	values := make(map[string]float64)
+	total := 0.0
+	for match, index := range m.matches {
+		if len(match) > 0 {
+			x, err := strconv.ParseInt(linefields[index], 0, 64)
 			if err == nil {
-				y, err := lp.New(m, tags, c.meta, map[string]interface{}{"value": int(x)}, time.Now())
-				if err == nil {
-					output <- y
-				}
+				values[match] = float64(x)
+				total += values[match]
 			}
 		}
 	}
+	t := time.Now()
+	for name, value := range values {
+		y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": (value * 100.0) / total}, t)
+		if err == nil {
+			output <- y
+		}
+	}
 }
 
 func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
-	buffer, err := ioutil.ReadFile(string(CPUSTATFILE))
-
+	num_cpus := 0
+	file, err := os.Open(string(CPUSTATFILE))
 	if err != nil {
-		return
+		cclog.ComponentError(m.name, err.Error())
+	}
+	defer file.Close()
+
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := scanner.Text()
+		linefields := strings.Fields(line)
+		if strings.Compare(linefields[0], "cpu") == 0 {
+			m.parseStatLine(linefields, m.nodetags, output)
+		} else if strings.HasPrefix(linefields[0], "cpu") {
+			m.parseStatLine(linefields, m.cputags[linefields[0]], output)
+			num_cpus++
+		}
 	}
 
-	ll := strings.Split(string(buffer), "\n")
-	for _, line := range ll {
-		if len(line) == 0 {
-			continue
-		}
-		ls := strings.Fields(line)
-		if strings.Compare(ls[0], "cpu") == 0 {
-			m.parseStatLine(line, -1, m.config.ExcludeMetrics, output)
-		} else if strings.HasPrefix(ls[0], "cpu") {
-			cpustr := strings.TrimLeft(ls[0], "cpu")
-			cpu, _ := strconv.Atoi(cpustr)
-			m.parseStatLine(line, cpu, m.config.ExcludeMetrics, output)
-		}
+	num_cpus_metric, err := lp.New("num_cpus",
+		m.nodetags,
+		m.meta,
+		map[string]interface{}{"value": int(num_cpus)},
+		time.Now(),
+	)
+	if err == nil {
+		output <- num_cpus_metric
 	}
 }
 

collectors/customCmdMetric.go

@@ -97,7 +97,8 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 			if skip {
 				continue
 			}
-			y, err := lp.New(c.Name(), Tags2Map(c), m.meta, Fields2Map(c), c.Time())
+
+			y := lp.FromInfluxMetric(c)
 			if err == nil {
 				output <- y
 			}
@@ -119,7 +120,7 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 			if skip {
 				continue
 			}
-			y, err := lp.New(f.Name(), Tags2Map(f), m.meta, Fields2Map(f), f.Time())
+			y := lp.FromInfluxMetric(f)
 			if err == nil {
 				output <- y
 			}

collectors/diskstatMetric.go

@@ -1,18 +1,21 @@
 package collectors
 
 import (
-	"io/ioutil"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	//	"log"
+	"bufio"
 	"encoding/json"
-	"errors"
-	"strconv"
+	"fmt"
+	"os"
 	"strings"
+	"syscall"
 	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const DISKSTATFILE = `/proc/diskstats`
-const DISKSTAT_SYSFSPATH = `/sys/block`
+//	"log"
+
+const MOUNTFILE = `/proc/self/mounts`
 
 type DiskstatCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
@@ -20,93 +23,89 @@ type DiskstatCollectorConfig struct {
 
 type DiskstatCollector struct {
 	metricCollector
-	matches map[int]string
-	config  DiskstatCollectorConfig
+	//matches map[string]int
+	config IOstatCollectorConfig
+	//devices map[string]IOstatCollectorEntry
 }
 
 func (m *DiskstatCollector) Init(config json.RawMessage) error {
-	var err error
 	m.name = "DiskstatCollector"
 	m.meta = map[string]string{"source": m.name, "group": "Disk"}
 	m.setup()
 	if len(config) > 0 {
-		err = json.Unmarshal(config, &m.config)
+		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	// https://www.kernel.org/doc/html/latest/admin-guide/iostats.html
-	matches := map[int]string{
-		3:  "reads",
-		4:  "reads_merged",
-		5:  "read_sectors",
-		6:  "read_ms",
-		7:  "writes",
-		8:  "writes_merged",
-		9:  "writes_sectors",
-		10: "writes_ms",
-		11: "ioops",
-		12: "ioops_ms",
-		13: "ioops_weighted_ms",
-		14: "discards",
-		15: "discards_merged",
-		16: "discards_sectors",
-		17: "discards_ms",
-		18: "flushes",
-		19: "flushes_ms",
+	file, err := os.Open(string(MOUNTFILE))
+	if err != nil {
+		cclog.ComponentError(m.name, err.Error())
+		return err
 	}
-	m.matches = make(map[int]string)
-	for k, v := range matches {
-		_, skip := stringArrayContains(m.config.ExcludeMetrics, v)
-		if !skip {
-			m.matches[k] = v
-		}
-	}
-	if len(m.matches) == 0 {
-		return errors.New("No metrics to collect")
-	}
-	_, err = ioutil.ReadFile(string(DISKSTATFILE))
-	if err == nil {
-		m.init = true
-	}
-	return err
+	defer file.Close()
+	m.init = true
+	return nil
 }
 
 func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	var lines []string
 	if !m.init {
 		return
 	}
 
-	buffer, err := ioutil.ReadFile(string(DISKSTATFILE))
+	file, err := os.Open(string(MOUNTFILE))
 	if err != nil {
+		cclog.ComponentError(m.name, err.Error())
 		return
 	}
-	lines = strings.Split(string(buffer), "\n")
+	defer file.Close()
 
-	for _, line := range lines {
+	part_max_used := uint64(0)
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := scanner.Text()
 		if len(line) == 0 {
 			continue
 		}
-		f := strings.Fields(line)
-		if strings.Contains(f[2], "loop") {
+		if !strings.HasPrefix(line, "/dev") {
 			continue
 		}
-		tags := map[string]string{
-			"device": f[2],
-			"type":   "node",
+		linefields := strings.Fields(line)
+		if strings.Contains(linefields[0], "loop") {
+			continue
 		}
-		for idx, name := range m.matches {
-			if idx < len(f) {
-				x, err := strconv.ParseInt(f[idx], 0, 64)
-				if err == nil {
-					y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": int(x)}, time.Now())
-					if err == nil {
-						output <- y
-					}
-				}
-			}
+		if strings.Contains(linefields[1], "boot") {
+			continue
 		}
+		path := strings.Replace(linefields[1], `\040`, " ", -1)
+		stat := syscall.Statfs_t{}
+		err := syscall.Statfs(path, &stat)
+		if err != nil {
+			fmt.Println(err.Error())
+			return
+		}
+		tags := map[string]string{"type": "node", "device": linefields[0]}
+		total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)
+		y, err := lp.New("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now())
+		if err == nil {
+			y.AddMeta("unit", "GBytes")
+			output <- y
+		}
+		free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000000000)
+		y, err = lp.New("disk_free", tags, m.meta, map[string]interface{}{"value": free}, time.Now())
+		if err == nil {
+			y.AddMeta("unit", "GBytes")
+			output <- y
+		}
+		perc := (100 * (total - free)) / total
+		if perc > part_max_used {
+			part_max_used = perc
+		}
+	}
+	y, err := lp.New("part_max_used", map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": int(part_max_used)}, time.Now())
+	if err == nil {
+		y.AddMeta("unit", "percent")
+		output <- y
 	}
 }
 

collectors/diskstatMetric.md

@@ -4,31 +4,18 @@
 ```json
   "diskstat": {
     "exclude_metrics": [
-      "read_ms"
+      "disk_total"
     ],
   }
 ```
 
-The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
+The `diskstat` collector reads data from `/proc/self/mounts` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
 
-Metrics:
-* `reads`
-* `reads_merged`
-* `read_sectors`
-* `read_ms`
-* `writes`
-* `writes_merged`
-* `writes_sectors`
-* `writes_ms`
-* `ioops`
-* `ioops_ms`
-* `ioops_weighted_ms`
-* `discards`
-* `discards_merged`
-* `discards_sectors`
-* `discards_ms`
-* `flushes`
-* `flushes_ms`
+Metrics per device (with `device` tag):
+* `disk_total` (unit `GBytes`)
+* `disk_free` (unit `GBytes`)
+
+Global metrics:
+* `part_max_used` (unit `percent`)
 
-The device name is added as tag `device`.
 

collectors/gpfsMetric.go

@@ -7,13 +7,13 @@ import (
 	"fmt"
 	"io/ioutil"
 	"log"
-	"os"
 	"os/exec"
 	"os/user"
 	"strconv"
 	"strings"
 	"time"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
@@ -21,11 +21,18 @@ type GpfsCollector struct {
 	metricCollector
 	tags   map[string]string
 	config struct {
-		Mmpmon string `json:"mmpmon"`
+		Mmpmon            string   `json:"mmpmon_path,omitempty"`
+		ExcludeFilesystem []string `json:"exclude_filesystem,omitempty"`
 	}
+	skipFS map[string]struct{}
 }
 
 func (m *GpfsCollector) Init(config json.RawMessage) error {
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+
 	var err error
 	m.name = "GpfsCollector"
 	m.setup()
@@ -49,20 +56,24 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 		"type":       "node",
 		"filesystem": "",
 	}
+	m.skipFS = make(map[string]struct{})
+	for _, fs := range m.config.ExcludeFilesystem {
+		m.skipFS[fs] = struct{}{}
+	}
 
 	// GPFS / IBM Spectrum Scale file system statistics can only be queried by user root
 	user, err := user.Current()
 	if err != nil {
-		return fmt.Errorf("GpfsCollector.Init(): Failed to get current user: %v", err)
+		return fmt.Errorf("Failed to get current user: %v", err)
 	}
 	if user.Uid != "0" {
-		return fmt.Errorf("GpfsCollector.Init(): GPFS file system statistics can only be queried by user root")
+		return fmt.Errorf("GPFS file system statistics can only be queried by user root")
 	}
 
 	// Check if mmpmon is in executable search path
 	_, err = exec.LookPath(m.config.Mmpmon)
 	if err != nil {
-		return fmt.Errorf("GpfsCollector.Init(): 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.init = true
@@ -70,6 +81,7 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
 }
 
 func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	// Check if already initialized
 	if !m.init {
 		return
 	}
@@ -86,12 +98,15 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	cmd.Stderr = cmdStderr
 	err := cmd.Run()
 	if err != nil {
-		fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
-		fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
-		data, _ := ioutil.ReadAll(cmdStderr)
-		fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): command stderr: \"%s\"\n", string(data))
-		data, _ = ioutil.ReadAll(cmdStdout)
-		fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): command stdout: \"%s\"\n", string(data))
+		dataStdErr, _ := ioutil.ReadAll(cmdStderr)
+		dataStdOut, _ := ioutil.ReadAll(cmdStdout)
+		cclog.ComponentError(
+			m.name,
+			fmt.Sprintf("Read(): Failed to execute command \"%s\": %v\n", cmd.String(), err),
+			fmt.Sprintf("Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode()),
+			fmt.Sprintf("Read(): command stderr: \"%s\"\n", string(dataStdErr)),
+			fmt.Sprintf("Read(): command stdout: \"%s\"\n", string(dataStdOut)),
+		)
 		return
 	}
 
@@ -99,148 +114,163 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	scanner := bufio.NewScanner(cmdStdout)
 	for scanner.Scan() {
 		lineSplit := strings.Fields(scanner.Text())
-		if lineSplit[0] == "_fs_io_s_" {
-			key_value := make(map[string]string)
-			for i := 1; i < len(lineSplit); i += 2 {
-				key_value[lineSplit[i]] = lineSplit[i+1]
-			}
 
-			// Ignore keys:
-			// _n_:  node IP address,
-			// _nn_: node name,
-			// _cl_: cluster name,
-			// _d_:  number of disks
+		// Only process lines starting with _fs_io_s_
+		if lineSplit[0] != "_fs_io_s_" {
+			continue
+		}
 
-			filesystem, ok := key_value["_fs_"]
-			if !ok {
-				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to get filesystem name.\n")
-				continue
-			}
+		key_value := make(map[string]string)
+		for i := 1; i < len(lineSplit); i += 2 {
+			key_value[lineSplit[i]] = lineSplit[i+1]
+		}
 
-			m.tags["filesystem"] = filesystem
+		// Ignore keys:
+		// _n_:  node IP address,
+		// _nn_: node name,
+		// _cl_: cluster name,
+		// _d_:  number of disks
 
-			// return code
-			rc, err := strconv.Atoi(key_value["_rc_"])
-			if err != nil {
-				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert return code: %s\n", err.Error())
-				continue
-			}
-			if rc != 0 {
-				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Filesystem %s not ok.", filesystem)
-				continue
-			}
+		filesystem, ok := key_value["_fs_"]
+		if !ok {
+			cclog.ComponentError(
+				m.name,
+				"Read(): Failed to get filesystem name.")
+			continue
+		}
 
-			sec, err := strconv.ParseInt(key_value["_t_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr,
-					"GpfsCollector.Read(): Failed to convert seconds to int '%s': %v\n",
-					key_value["_t_"], err)
-				continue
-			}
-			msec, err := strconv.ParseInt(key_value["_tu_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr,
-					"GpfsCollector.Read(): Failed to convert micro seconds to int '%s': %v\n",
-					key_value["_tu_"], err)
-				continue
-			}
-			timestamp := time.Unix(sec, msec*1000)
+		// Skip excluded filesystems
+		if _, skip := m.skipFS[filesystem]; skip {
+			continue
+		}
 
-			// bytes read
-			bytesRead, err := strconv.ParseInt(key_value["_br_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr,
-					"GpfsCollector.Read(): Failed to convert bytes read '%s': %s\n",
-					key_value["_br_"], err.Error())
-				continue
-			}
+		m.tags["filesystem"] = filesystem
 
-			y, err := lp.New("gpfs_bytes_read", m.tags, m.meta, map[string]interface{}{"value": bytesRead}, timestamp)
-			if err == nil {
-				output <- y
-			}
+		// return code
+		rc, err := strconv.Atoi(key_value["_rc_"])
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert return code '%s' to int: %v", key_value["_rc_"], err))
+			continue
+		}
+		if rc != 0 {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Filesystem '%s' is not ok.", filesystem))
+			continue
+		}
 
-			// bytes written
-			bytesWritten, err := strconv.ParseInt(key_value["_bw_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr,
-					"GpfsCollector.Read(): Failed to convert bytes written '%s': %s\n",
-					key_value["_bw_"], err.Error())
-				continue
-			}
+		sec, err := strconv.ParseInt(key_value["_t_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert seconds '%s' to int64: %v", key_value["_t_"], err))
+			continue
+		}
+		msec, err := strconv.ParseInt(key_value["_tu_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert micro seconds '%s' to int64: %v", key_value["_tu_"], err))
+			continue
+		}
+		timestamp := time.Unix(sec, msec*1000)
 
-			y, err = lp.New("gpfs_bytes_written", m.tags, m.meta, map[string]interface{}{"value": bytesWritten}, timestamp)
-			if err == nil {
-				output <- y
-			}
+		// bytes read
+		bytesRead, err := strconv.ParseInt(key_value["_br_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert bytes read '%s' to int64: %v", key_value["_br_"], err))
+			continue
+		}
+		if y, err := lp.New("gpfs_bytes_read", m.tags, m.meta, map[string]interface{}{"value": bytesRead}, timestamp); err == nil {
+			output <- y
+		}
 
-			// number of opens
-			numOpens, err := strconv.ParseInt(key_value["_oc_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr,
-					"GpfsCollector.Read(): Failed to convert number of opens '%s': %s\n",
-					key_value["_oc_"], err.Error())
-				continue
-			}
-			y, err = lp.New("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp)
-			if err == nil {
-				output <- y
-			}
+		// bytes written
+		bytesWritten, err := strconv.ParseInt(key_value["_bw_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert bytes written '%s' to int64: %v", key_value["_bw_"], err))
+			continue
+		}
+		if y, err := lp.New("gpfs_bytes_written", m.tags, m.meta, map[string]interface{}{"value": bytesWritten}, timestamp); err == nil {
+			output <- y
+		}
 
-			// number of closes
-			numCloses, err := strconv.ParseInt(key_value["_cc_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert number of closes: %s\n", err.Error())
-				continue
-			}
-			y, err = lp.New("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp)
-			if err == nil {
-				output <- y
-			}
+		// number of opens
+		numOpens, err := strconv.ParseInt(key_value["_oc_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert number of opens '%s' to int64: %v", key_value["_oc_"], err))
+			continue
+		}
+		if y, err := lp.New("gpfs_num_opens", m.tags, m.meta, map[string]interface{}{"value": numOpens}, timestamp); err == nil {
+			output <- y
+		}
 
-			// number of reads
-			numReads, err := strconv.ParseInt(key_value["_rdc_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert number of reads: %s\n", err.Error())
-				continue
-			}
-			y, err = lp.New("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp)
-			if err == nil {
-				output <- y
-			}
+		// number of closes
+		numCloses, err := strconv.ParseInt(key_value["_cc_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert number of closes: '%s' to int64: %v", key_value["_cc_"], err))
+			continue
+		}
+		if y, err := lp.New("gpfs_num_closes", m.tags, m.meta, map[string]interface{}{"value": numCloses}, timestamp); err == nil {
+			output <- y
+		}
 
-			// number of writes
-			numWrites, err := strconv.ParseInt(key_value["_wc_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert number of writes: %s\n", err.Error())
-				continue
-			}
-			y, err = lp.New("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp)
-			if err == nil {
-				output <- y
-			}
+		// number of reads
+		numReads, err := strconv.ParseInt(key_value["_rdc_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert number of reads: '%s' to int64: %v", key_value["_rdc_"], err))
+			continue
+		}
+		if y, err := lp.New("gpfs_num_reads", m.tags, m.meta, map[string]interface{}{"value": numReads}, timestamp); err == nil {
+			output <- y
+		}
 
-			// number of read directories
-			numReaddirs, err := strconv.ParseInt(key_value["_dir_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert number of read directories: %s\n", err.Error())
-				continue
-			}
-			y, err = lp.New("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp)
-			if err == nil {
-				output <- y
-			}
+		// number of writes
+		numWrites, err := strconv.ParseInt(key_value["_wc_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert number of writes: '%s' to int64: %v", key_value["_wc_"], err))
+			continue
+		}
+		if y, err := lp.New("gpfs_num_writes", m.tags, m.meta, map[string]interface{}{"value": numWrites}, timestamp); err == nil {
+			output <- y
+		}
 
-			// Number of inode updates
-			numInodeUpdates, err := strconv.ParseInt(key_value["_iu_"], 10, 64)
-			if err != nil {
-				fmt.Fprintf(os.Stderr, "GpfsCollector.Read(): Failed to convert Number of inode updates: %s\n", err.Error())
-				continue
-			}
-			y, err = lp.New("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp)
-			if err == nil {
-				output <- y
-			}
+		// number of read directories
+		numReaddirs, err := strconv.ParseInt(key_value["_dir_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert number of read directories: '%s' to int64: %v", key_value["_dir_"], err))
+			continue
+		}
+		if y, err := lp.New("gpfs_num_readdirs", m.tags, m.meta, map[string]interface{}{"value": numReaddirs}, timestamp); err == nil {
+			output <- y
+		}
+
+		// Number of inode updates
+		numInodeUpdates, err := strconv.ParseInt(key_value["_iu_"], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert number of inode updates: '%s' to int: %v", key_value["_iu_"], err))
+			continue
+		}
+		if y, err := lp.New("gpfs_num_inode_updates", m.tags, m.meta, map[string]interface{}{"value": numInodeUpdates}, timestamp); err == nil {
+			output <- y
 		}
 	}
 }

collectors/gpfsMetric.md

@@ -0,0 +1,30 @@
+## `gpfs` collector
+
+```json
+  "ibstat": {
+    "mmpmon_path": "/path/to/mmpmon",
+    "exclude_filesystem": [
+      "fs1"
+    ]
+  }
+```
+
+The `gpfs` collector uses the `mmpmon` command to read performance metrics for
+GPFS / IBM Spectrum Scale filesystems.
+
+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.
+
+Metrics:
+* `bytes_read`
+* `gpfs_bytes_written`
+* `gpfs_num_opens`
+* `gpfs_num_closes`
+* `gpfs_num_reads`
+* `gpfs_num_readdirs`
+* `gpfs_num_inode_updates`
+
+The collector adds a `filesystem` tag to all metrics

collectors/infinibandMetric.go

@@ -2,8 +2,10 @@ package collectors
 
 import (
 	"fmt"
+	"io/ioutil"
 	"os"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	"golang.org/x/sys/unix"
 
@@ -20,7 +22,7 @@ type InfinibandCollectorInfo struct {
 	LID              string            // IB local Identifier (LID)
 	device           string            // IB device
 	port             string            // IB device port
-	portCounterFiles map[string]string // mapping counter name -> file
+	portCounterFiles map[string]string // mapping counter name -> sysfs file
 	tagSet           map[string]string // corresponding tag list
 }
 
@@ -29,29 +31,17 @@ type InfinibandCollector struct {
 	config struct {
 		ExcludeDevices []string `json:"exclude_devices,omitempty"` // IB device to exclude e.g. mlx5_0
 	}
-	info []InfinibandCollectorInfo
-}
-
-func (m *InfinibandCollector) Help() {
-	fmt.Println("This collector includes all devices that can be found below ", IB_BASEPATH)
-	fmt.Println("and where any of the ports provides a 'lid' file (glob ", IB_BASEPATH, "/<dev>/ports/<port>/lid).")
-	fmt.Println("The devices can be filtered with the 'exclude_devices' option in the configuration.")
-	fmt.Println("For each found LIDs the collector calls the 'perfquery' command")
-	fmt.Println("")
-	fmt.Println("Full configuration object:")
-	fmt.Println("\"ibstat\" : {")
-	fmt.Println("  \"exclude_devices\" : [\"dev1\"]")
-	fmt.Println("}")
-	fmt.Println("")
-	fmt.Println("Metrics:")
-	fmt.Println("- ib_recv")
-	fmt.Println("- ib_xmit")
-	fmt.Println("- ib_recv_pkts")
-	fmt.Println("- ib_xmit_pkts")
+	info []*InfinibandCollectorInfo
 }
 
 // Init initializes the Infiniband collector by walking through files below IB_BASEPATH
 func (m *InfinibandCollector) Init(config json.RawMessage) error {
+
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+
 	var err error
 	m.name = "InfinibandCollector"
 	m.setup()
@@ -79,8 +69,12 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	for _, path := range ibDirs {
 
 		// Skip, when no LID is assigned
-		LID, ok := readOneLine(path + "/lid")
-		if !ok || LID == "0x0" {
+		line, err := ioutil.ReadFile(filepath.Join(path, "lid"))
+		if err != nil {
+			continue
+		}
+		LID := strings.TrimSpace(string(line))
+		if LID == "0x0" {
 			continue
 		}
 
@@ -117,7 +111,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 		}
 
 		m.info = append(m.info,
-			InfinibandCollectorInfo{
+			&InfinibandCollectorInfo{
 				LID:              LID,
 				device:           device,
 				port:             port,
@@ -148,19 +142,28 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 	}
 
 	now := time.Now()
-	for i := range m.info {
-
-		// device info
-		info := &m.info[i]
+	for _, info := range m.info {
 		for counterName, counterFile := range info.portCounterFiles {
-			if data, ok := readOneLine(counterFile); ok {
-				if v, err := strconv.ParseInt(data, 10, 64); err == nil {
-					if y, err := lp.New(counterName, info.tagSet, m.meta, map[string]interface{}{"value": v}, now); err == nil {
-						output <- y
-					}
-				}
+			line, err := ioutil.ReadFile(counterFile)
+			if err != nil {
+				cclog.ComponentError(
+					m.name,
+					fmt.Sprintf("Read(): Failed to read from file '%s': %v", counterFile, err))
+				continue
+			}
+			data := strings.TrimSpace(string(line))
+			v, err := strconv.ParseInt(data, 10, 64)
+			if err != nil {
+				cclog.ComponentError(
+					m.name,
+					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterName, data, err))
+				continue
+			}
+			if y, err := lp.New(counterName, info.tagSet, m.meta, map[string]interface{}{"value": v}, now); err == nil {
+				output <- y
 			}
 		}
+
 	}
 }
 

collectors/infinibandMetric.md

@@ -3,17 +3,24 @@
 
 ```json
   "ibstat": {
-    "perfquery_path" : "<path to perfquery command>",
     "exclude_devices": [
       "mlx4"
     ]
   }
 ```
 
-The `ibstat` collector reads either data through the `perfquery` command or the sysfs files below `/sys/class/infiniband/<device>`.
+The `ibstat` 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 reads data through the sysfs files below `/sys/class/infiniband/<device>`.
 
 Metrics:
 * `ib_recv`
 * `ib_xmit`
+* `ib_recv_pkts`
+* `ib_xmit_pkts`
 
 The collector adds a `device` tag to all metrics

collectors/infinibandPerfQueryMetric.go

@@ -29,27 +29,6 @@ type InfinibandPerfQueryCollector struct {
 	}
 }
 
-func (m *InfinibandPerfQueryCollector) Help() {
-	fmt.Println("This collector includes all devices that can be found below ", IB_BASEPATH)
-	fmt.Println("and where any of the ports provides a 'lid' file (glob ", IB_BASEPATH, "/<dev>/ports/<port>/lid).")
-	fmt.Println("The devices can be filtered with the 'exclude_devices' option in the configuration.")
-	fmt.Println("For each found LIDs the collector calls the 'perfquery' command")
-	fmt.Println("The path to the 'perfquery' command can be configured with the 'perfquery_path' option")
-	fmt.Println("in the configuration")
-	fmt.Println("")
-	fmt.Println("Full configuration object:")
-	fmt.Println("\"ibstat\" : {")
-	fmt.Println("  \"perfquery_path\" : \"path/to/perfquery\"  # if omitted, it searches in $PATH")
-	fmt.Println("  \"exclude_devices\" : [\"dev1\"]")
-	fmt.Println("}")
-	fmt.Println("")
-	fmt.Println("Metrics:")
-	fmt.Println("- ib_recv")
-	fmt.Println("- ib_xmit")
-	fmt.Println("- ib_recv_pkts")
-	fmt.Println("- ib_xmit_pkts")
-}
-
 func (m *InfinibandPerfQueryCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "InfinibandCollectorPerfQuery"
@@ -71,6 +50,9 @@ func (m *InfinibandPerfQueryCollector) Init(config json.RawMessage) error {
 	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 {

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/iostatMetric.go

@@ -0,0 +1,155 @@
+package collectors
+
+import (
+	"bufio"
+	"os"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+
+	//	"log"
+	"encoding/json"
+	"errors"
+	"strconv"
+	"strings"
+	"time"
+)
+
+const IOSTATFILE = `/proc/diskstats`
+const IOSTAT_SYSFSPATH = `/sys/block`
+
+type IOstatCollectorConfig struct {
+	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+}
+
+type IOstatCollectorEntry struct {
+	lastValues map[string]int64
+	tags       map[string]string
+}
+
+type IOstatCollector struct {
+	metricCollector
+	matches map[string]int
+	config  IOstatCollectorConfig
+	devices map[string]IOstatCollectorEntry
+}
+
+func (m *IOstatCollector) Init(config json.RawMessage) error {
+	var err error
+	m.name = "IOstatCollector"
+	m.meta = map[string]string{"source": m.name, "group": "Disk"}
+	m.setup()
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			return err
+		}
+	}
+	// https://www.kernel.org/doc/html/latest/admin-guide/iostats.html
+	matches := map[string]int{
+		"io_reads":             3,
+		"io_reads_merged":      4,
+		"io_read_sectors":      5,
+		"io_read_ms":           6,
+		"io_writes":            7,
+		"io_writes_merged":     8,
+		"io_writes_sectors":    9,
+		"io_writes_ms":         10,
+		"io_ioops":             11,
+		"io_ioops_ms":          12,
+		"io_ioops_weighted_ms": 13,
+		"io_discards":          14,
+		"io_discards_merged":   15,
+		"io_discards_sectors":  16,
+		"io_discards_ms":       17,
+		"io_flushes":           18,
+		"io_flushes_ms":        19,
+	}
+	m.devices = make(map[string]IOstatCollectorEntry)
+	m.matches = make(map[string]int)
+	for k, v := range matches {
+		if _, skip := stringArrayContains(m.config.ExcludeMetrics, k); !skip {
+			m.matches[k] = v
+		}
+	}
+	if len(m.matches) == 0 {
+		return errors.New("no metrics to collect")
+	}
+	file, err := os.Open(string(IOSTATFILE))
+	if err != nil {
+		cclog.ComponentError(m.name, err.Error())
+		return err
+	}
+	defer file.Close()
+
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := scanner.Text()
+		linefields := strings.Fields(line)
+		device := linefields[2]
+		if strings.Contains(device, "loop") {
+			continue
+		}
+		values := make(map[string]int64)
+		for m := range m.matches {
+			values[m] = 0
+		}
+		m.devices[device] = IOstatCollectorEntry{
+			tags: map[string]string{
+				"device": linefields[2],
+				"type":   "node",
+			},
+			lastValues: values,
+		}
+	}
+	m.init = true
+	return err
+}
+
+func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	if !m.init {
+		return
+	}
+
+	file, err := os.Open(string(IOSTATFILE))
+	if err != nil {
+		cclog.ComponentError(m.name, err.Error())
+		return
+	}
+	defer file.Close()
+
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := scanner.Text()
+		if len(line) == 0 {
+			continue
+		}
+		linefields := strings.Fields(line)
+		device := linefields[2]
+		if strings.Contains(device, "loop") {
+			continue
+		}
+		if _, ok := m.devices[device]; !ok {
+			continue
+		}
+		entry := m.devices[device]
+		for name, idx := range m.matches {
+			if idx < len(linefields) {
+				x, err := strconv.ParseInt(linefields[idx], 0, 64)
+				if err == nil {
+					diff := x - entry.lastValues[name]
+					y, err := lp.New(name, entry.tags, m.meta, map[string]interface{}{"value": int(diff)}, time.Now())
+					if err == nil {
+						output <- y
+					}
+				}
+				entry.lastValues[name] = x
+			}
+		}
+		m.devices[device] = entry
+	}
+}
+
+func (m *IOstatCollector) Close() {
+	m.init = false
+}

collectors/iostatMetric.md

@@ -0,0 +1,34 @@
+
+## `iostat` collector
+
+```json
+  "iostat": {
+    "exclude_metrics": [
+      "read_ms"
+    ],
+  }
+```
+
+The `iostat` collector reads data from `/proc/diskstats` and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink.
+
+Metrics:
+* `io_reads`
+* `io_reads_merged`
+* `io_read_sectors`
+* `io_read_ms`
+* `io_writes`
+* `io_writes_merged`
+* `io_writes_sectors`
+* `io_writes_ms`
+* `io_ioops`
+* `io_ioops_ms`
+* `io_ioops_weighted_ms`
+* `io_discards`
+* `io_discards_merged`
+* `io_discards_sectors`
+* `io_discards_ms`
+* `io_flushes`
+* `io_flushes_ms`
+
+The device name is added as tag `device`. For more details, see https://www.kernel.org/doc/html/latest/admin-guide/iostats.html
+

collectors/ipmiMetric.go

@@ -9,11 +9,12 @@ import (
 	"strconv"
 	"strings"
 	"time"
+
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const IPMITOOL_PATH = `/usr/bin/ipmitool`
-const IPMISENSORS_PATH = `/usr/sbin/ipmi-sensors`
+const IPMITOOL_PATH = `ipmitool`
+const IPMISENSORS_PATH = `ipmi-sensors`
 
 type IpmiCollectorConfig struct {
 	ExcludeDevices  []string `json:"exclude_devices"`
@@ -23,30 +24,36 @@ type IpmiCollectorConfig struct {
 
 type IpmiCollector struct {
 	metricCollector
-	tags    map[string]string
-	matches map[string]string
-	config  IpmiCollectorConfig
+	//tags        map[string]string
+	//matches     map[string]string
+	config      IpmiCollectorConfig
+	ipmitool    string
+	ipmisensors string
 }
 
 func (m *IpmiCollector) Init(config json.RawMessage) error {
 	m.name = "IpmiCollector"
 	m.setup()
 	m.meta = map[string]string{"source": m.name, "group": "IPMI"}
+	m.config.IpmitoolPath = string(IPMITOOL_PATH)
+	m.config.IpmisensorsPath = string(IPMISENSORS_PATH)
+	m.ipmitool = ""
+	m.ipmisensors = ""
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	_, err1 := os.Stat(m.config.IpmitoolPath)
-	_, err2 := os.Stat(m.config.IpmisensorsPath)
-	if err1 != nil {
-		m.config.IpmitoolPath = ""
+	p, err := exec.LookPath(m.config.IpmitoolPath)
+	if err == nil {
+		m.ipmitool = p
 	}
-	if err2 != nil {
-		m.config.IpmisensorsPath = ""
+	p, err = exec.LookPath(m.config.IpmisensorsPath)
+	if err == nil {
+		m.ipmisensors = p
 	}
-	if err1 != nil && err2 != nil {
+	if len(m.ipmitool) == 0 && len(m.ipmisensors) == 0 {
 		return errors.New("No IPMI reader found")
 	}
 	m.init = true

collectors/likwidMetric.go

@@ -2,7 +2,7 @@ package collectors
 
 /*
 #cgo CFLAGS: -I./likwid
-#cgo LDFLAGS: -L./likwid -llikwid -llikwid-hwloc -lm
+#cgo LDFLAGS: -Wl,--unresolved-symbols=ignore-in-object-files
 #include <stdlib.h>
 #include <likwid.h>
 */
@@ -13,67 +13,114 @@ import (
 	"errors"
 	"fmt"
 	"io/ioutil"
-	"log"
 	"math"
 	"os"
+	"regexp"
 	"strconv"
 	"strings"
 	"time"
 	"unsafe"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	"gopkg.in/Knetic/govaluate.v2"
+	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
+	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
+	"github.com/NVIDIA/go-nvml/pkg/dl"
 )
 
-type MetricScope int
+type MetricScope string
 
 const (
 	METRIC_SCOPE_HWTHREAD = iota
-	METRIC_SCOPE_SOCKET
+	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{"Head", "Shoulder", "Knee", "Toe"}[ms]
+	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
+	LIKWID_DEF_ACCESSMODE = "direct"
+)
+
 type LikwidCollectorMetricConfig struct {
-	Name    string      `json:"name"`
-	Calc    string      `json:"calc"`
-	Scope   MetricScope `json:"socket_scope"`
-	Publish bool        `json:"publish"`
+	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"`
+	Events      map[string]string `json:"events"`
+	granulatity map[string]MetricScope
+	Metrics     []LikwidCollectorMetricConfig `json:"metrics"`
 }
 
 type LikwidCollectorConfig struct {
 	Eventsets      []LikwidCollectorEventsetConfig `json:"eventsets"`
-	Metrics        []LikwidCollectorMetricConfig   `json:"globalmetrics"`
-	ExcludeMetrics []string                        `json:"exclude_metrics"`
-	ForceOverwrite bool                            `json:"force_overwrite"`
+	Metrics        []LikwidCollectorMetricConfig   `json:"globalmetrics,omitempty"`
+	ForceOverwrite bool                            `json:"force_overwrite,omitempty"`
+	InvalidToZero  bool                            `json:"invalid_to_zero,omitempty"`
+	AccessMode     string                          `json:"access_mode,omitempty"`
+	DaemonPath     string                          `json:"accessdaemon_path,omitempty"`
 }
 
 type LikwidCollector struct {
 	metricCollector
-	cpulist   []C.int
-	sock2tid  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
+	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
-	socket_scope bool
-	group_idx    int
+	name      string
+	search    string
+	scope     MetricScope
+	group_idx int
 }
 
 func eventsToEventStr(events map[string]string) string {
@@ -84,12 +131,27 @@ func eventsToEventStr(events map[string]string) string {
 	return strings.Join(elist, ",")
 }
 
+func getGranularity(counter, event string) MetricScope {
+	if strings.HasPrefix(counter, "PMC") || strings.HasPrefix(counter, "FIXC") {
+		return "cpu"
+	} else if strings.Contains(counter, "BOX") || strings.Contains(counter, "DEV") {
+		return "socket"
+	} else if strings.HasPrefix(counter, "PWR") {
+		if event == "RAPL_CORE_ENERGY" {
+			return "cpu"
+		} else {
+			return "socket"
+		}
+	}
+	return "unknown"
+}
+
 func getBaseFreq() float64 {
 	var freq float64 = math.NaN()
 	C.power_init(0)
 	info := C.get_powerInfo()
 	if float64(info.baseFrequency) != 0 {
-		freq = float64(info.baseFrequency)
+		freq = float64(info.baseFrequency) * 1e3
 	} else {
 		buffer, err := ioutil.ReadFile("/sys/devices/system/cpu/cpu0/cpufreq/bios_limit")
 		if err == nil {
@@ -103,61 +165,198 @@ func getBaseFreq() float64 {
 	return freq
 }
 
-func getSocketCpus() map[C.int]int {
-	slist := SocketList()
-	var cpu C.int
-	outmap := make(map[C.int]int)
-	for _, s := range slist {
-		t := C.CString(fmt.Sprintf("S%d", s))
-		clen := C.cpustr_to_cpulist(t, &cpu, 1)
-		if int(clen) == 1 {
-			outmap[cpu] = s
+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
 		}
 	}
-	return outmap
+	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.config.AccessMode = LIKWID_DEF_ACCESSMODE
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
-	m.setup()
-	m.meta = map[string]string{"source": m.name, "group": "PerfCounter"}
-	cpulist := CpuList()
-	m.cpulist = make([]C.int, len(cpulist))
-	slist := getSocketCpus()
+	lib := dl.New(LIKWID_LIB_NAME, LIKWID_LIB_DL_FLAGS)
+	if lib == nil {
+		return fmt.Errorf("error instantiating DynamicLibrary for %s", LIKWID_LIB_NAME)
+	}
+	err := lib.Open()
+	if err != nil {
+		return fmt.Errorf("error opening %s: %v", LIKWID_LIB_NAME, err)
+	}
 
-	m.sock2tid = make(map[int]int)
-	//	m.numa2tid = make(map[int]int)
+	if m.config.ForceOverwrite {
+		cclog.ComponentDebug(m.name, "Set LIKWID_FORCE=1")
+		os.Setenv("LIKWID_FORCE", "1")
+	}
+	m.setup()
+
+	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))
+	m.cpu2tid = make(map[int]int)
 	for i, c := range cpulist {
 		m.cpulist[i] = C.int(c)
-		if sid, found := slist[m.cpulist[i]]; found {
-			m.sock2tid[sid] = i
-		}
+		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 {
-		return errors.New("Failed to initialize LIKWID topology")
+		err := errors.New("failed to initialize LIKWID topology")
+		cclog.ComponentError(m.name, err.Error())
+		return err
 	}
-	if m.config.ForceOverwrite {
-		os.Setenv("LIKWID_FORCE", "1")
+
+	// Determine which counter works at which level. PMC*: cpu, *BOX*: socket, ...
+	m.initGranularity()
+	// Generate map for MetricScope -> scope_id (like socket id) -> responsible id (offset in cpulist)
+	m.scopeRespTids = m.getResponsiblities()
+	switch m.config.AccessMode {
+	case "direct":
+		C.HPMmode(0)
+	case "accessdaemon":
+		if len(m.config.DaemonPath) > 0 {
+			p := os.Getenv("PATH")
+			os.Setenv("PATH", m.config.DaemonPath+":"+p)
+		}
+		C.HPMmode(1)
 	}
+
+	cclog.ComponentDebug(m.name, "initialize LIKWID perfmon module")
 	ret = C.perfmon_init(C.int(len(m.cpulist)), &m.cpulist[0])
 	if ret != 0 {
 		C.topology_finalize()
-		return errors.New("Failed to initialize LIKWID topology")
+		err := errors.New("failed to initialize LIKWID topology")
+		cclog.ComponentError(m.name, err.Error())
+		return err
 	}
 
+	// This is for the global metrics computation test
+	globalParams := make(map[string]interface{})
+	globalParams["time"] = float64(1.0)
+	globalParams["inverseClock"] = float64(1.0)
+	// While adding the events, we test the metrics whether they can be computed at all
 	for i, evset := range m.config.Eventsets {
 		estr := eventsToEventStr(evset.Events)
+		// Generate parameter list for the metric computing test
+		params := make(map[string]interface{})
+		params["time"] = float64(1.0)
+		params["inverseClock"] = float64(1.0)
+		for counter := range evset.Events {
+			params[counter] = float64(1.0)
+		}
+		for _, metric := range evset.Metrics {
+			// Try to evaluate the metric
+			_, err := agg.EvalFloat64Condition(metric.Calc, params)
+			if err != nil {
+				cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
+				continue
+			}
+			// 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 {
@@ -169,161 +368,208 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
 		for tid := range m.cpulist {
 			m.results[i][tid] = make(map[string]interface{})
 			m.mresults[i][tid] = make(map[string]float64)
-			m.gmresults[tid] = make(map[string]float64)
+			if i == 0 {
+				m.gmresults[tid] = make(map[string]float64)
+			}
+		}
+	}
+	for _, metric := range m.config.Metrics {
+		// Try to evaluate the global metric
+		_, err := agg.EvalFloat64Condition(metric.Calc, globalParams)
+		if err != nil {
+			cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
+			continue
 		}
 	}
 
+	// If no event set could be added, shut down LikwidCollector
 	if len(m.groups) == 0 {
 		C.perfmon_finalize()
 		C.topology_finalize()
-		return errors.New("No LIKWID performance group initialized")
+		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(group int, interval time.Duration) error {
+	var ret C.int
+	gid := m.groups[group]
+	ret = C.perfmon_setupCounters(gid)
+	if ret != 0 {
+		gctr := C.GoString(C.perfmon_getGroupName(gid))
+		err := fmt.Errorf("failed to setup performance group %d (%s)", gid, gctr)
+		return err
+	}
+	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(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 = 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)
+			}
+		}
+	}
+
+	// Go over the event set metrics, derive the value out of the event:counter values and send it
+	for _, metric := range evset.Metrics {
+		// The metric scope is determined in the Init() function
+		// Get the map scope-id -> tids
+		scopemap := m.scopeRespTids[metric.Scope]
+		for domain, tid := range scopemap {
+			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.IsInf(value, 0) {
+					value = 0.0
+				}
+				// Now we have the result, send it with the proper tags
+				if !math.IsNaN(value) {
+					if metric.Publish {
+						tags := map[string]string{"type": metric.Scope.String()}
+						if metric.Scope != "node" {
+							tags["type-id"] = fmt.Sprintf("%d", domain)
+						}
+						fields := map[string]interface{}{"value": value}
+						y, err := lp.New(metric.Name, tags, m.meta, fields, time.Now())
+						if err == nil {
+							output <- y
+						}
+					}
+				}
+			}
+		}
+	}
+
+	return nil
+}
+
+// Go over the global metrics, derive the value out of the event sets' metric values and send it
+func (m *LikwidCollector) calcGlobalMetrics(interval time.Duration, output chan lp.CCMetric) error {
+	for _, metric := range m.config.Metrics {
+		scopemap := m.scopeRespTids[metric.Scope]
+		for domain, tid := range scopemap {
+			if tid >= 0 {
+				// Here we generate parameter list
+				params := make(map[string]interface{})
+				for j := range m.groups {
+					for mname, mres := range m.mresults[j][tid] {
+						params[mname] = mres
+					}
+				}
+				// Evaluate the metric
+				value, err := agg.EvalFloat64Condition(metric.Calc, params)
+				if err != nil {
+					cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
+					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.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 {
+							output <- y
+						}
+					}
+				}
+			}
+		}
+	}
+	return nil
+}
+
+// main read function taking multiple measurement rounds, each 'interval' seconds long
 func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
-	var ret C.int
 
-	for i, gid := range m.groups {
-		evset := m.config.Eventsets[i]
-		ret = C.perfmon_setupCounters(gid)
-		if ret != 0 {
-			log.Print("Failed to setup performance group ", C.perfmon_getGroupName(gid))
-			continue
-		}
-		ret = C.perfmon_startCounters()
-		if ret != 0 {
-			log.Print("Failed to start performance group ", C.perfmon_getGroupName(gid))
-			continue
-		}
-		time.Sleep(interval)
-		ret = C.perfmon_stopCounters()
-		if ret != 0 {
-			log.Print("Failed to stop performance group ", C.perfmon_getGroupName(gid))
-			continue
-		}
-		var eidx C.int
-		for tid := range m.cpulist {
-			for eidx = 0; int(eidx) < len(evset.Events); eidx++ {
-				ctr := C.perfmon_getCounterName(gid, eidx)
-				gctr := C.GoString(ctr)
-				res := C.perfmon_getLastResult(gid, eidx, C.int(tid))
-				m.results[i][tid][gctr] = float64(res)
-			}
-			m.results[i][tid]["time"] = interval.Seconds()
-			m.results[i][tid]["inverseClock"] = float64(1.0 / m.basefreq)
-			for _, metric := range evset.Metrics {
-				expression, err := govaluate.NewEvaluableExpression(metric.Calc)
-				if err != nil {
-					log.Print(err.Error())
-					continue
-				}
-				result, err := expression.Evaluate(m.results[i][tid])
-				if err != nil {
-					log.Print(err.Error())
-					continue
-				}
-				m.mresults[i][tid][metric.Name] = float64(result.(float64))
-			}
-		}
-	}
-
-	for _, metric := range m.config.Metrics {
-		for tid := range m.cpulist {
-			var params map[string]interface{}
-			expression, err := govaluate.NewEvaluableExpression(metric.Calc)
-			if err != nil {
-				log.Print(err.Error())
-				continue
-			}
-			params = make(map[string]interface{})
-			for j := range m.groups {
-				for mname, mres := range m.mresults[j][tid] {
-					params[mname] = mres
-				}
-			}
-			result, err := expression.Evaluate(params)
-			if err != nil {
-				log.Print(err.Error())
-				continue
-			}
-			m.gmresults[tid][metric.Name] = float64(result.(float64))
-		}
-	}
 	for i := range m.groups {
-		evset := m.config.Eventsets[i]
-		for _, metric := range evset.Metrics {
-			_, skip := stringArrayContains(m.config.ExcludeMetrics, metric.Name)
-			if metric.Publish && !skip {
-				if metric.Scope.String() == "socket" {
-					for sid, tid := range m.sock2tid {
-						y, err := lp.New(metric.Name,
-							map[string]string{"type": "socket",
-								"type-id": fmt.Sprintf("%d", int(sid))},
-							m.meta,
-							map[string]interface{}{"value": m.mresults[i][tid][metric.Name]},
-							time.Now())
-						if err == nil {
-							output <- y
-						}
-					}
-				} else if metric.Scope.String() == "hwthread" {
-					for tid, cpu := range m.cpulist {
-						y, err := lp.New(metric.Name,
-							map[string]string{"type": "cpu",
-								"type-id": fmt.Sprintf("%d", int(cpu))},
-							m.meta,
-							map[string]interface{}{"value": m.mresults[i][tid][metric.Name]},
-							time.Now())
-						if err == nil {
-							output <- y
-						}
-					}
-				}
-			}
-		}
-	}
-	for _, metric := range m.config.Metrics {
-		_, skip := stringArrayContains(m.config.ExcludeMetrics, metric.Name)
-		if metric.Publish && !skip {
-			if metric.Scope.String() == "socket" {
-				for sid, tid := range m.sock2tid {
-					y, err := lp.New(metric.Name,
-						map[string]string{"type": "socket",
-							"type-id": fmt.Sprintf("%d", int(sid))},
-						m.meta,
-						map[string]interface{}{"value": m.gmresults[tid][metric.Name]},
-						time.Now())
-					if err == nil {
-						output <- y
-					}
-				}
-			} else {
-				for tid, cpu := range m.cpulist {
-					y, err := lp.New(metric.Name,
-						map[string]string{"type": "cpu",
-							"type-id": fmt.Sprintf("%d", int(cpu))},
-						m.meta,
-						map[string]interface{}{"value": m.gmresults[tid][metric.Name]},
-						time.Now())
-					if err == nil {
-						output <- y
-					}
-				}
-			}
+		// measure event set 'i' for 'interval' seconds
+		err := m.takeMeasurement(i, interval)
+		if err != nil {
+			cclog.ComponentError(m.name, err.Error())
+			return
 		}
+		// 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 {
+		cclog.ComponentDebug(m.name, "Closing ...")
 		m.init = false
+		if m.running {
+			cclog.ComponentDebug(m.name, "Stopping counters")
+			C.perfmon_stopCounters()
+		}
+		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

@@ -1,7 +1,91 @@
 
 ## `likwid` collector
+
+The `likwid` collector is probably the most complicated collector. The LIKWID library is included as static library with *direct* access mode. The *direct* access mode is suitable if the daemon is executed by a root user. The static library does not contain the performance groups, so all information needs to be provided in the configuration.
+
+The `likwid` configuration consists of two parts, the "eventsets" and "globalmetrics":
+- An event set list itself has two parts, the "events" and a set of derivable "metrics". Each of the "events" is a counter:event pair in LIKWID's syntax. The "metrics" are a list of formulas to derive the metric value from the measurements of the "events". Each metric has a name, the formula, a scope and a publish flag. Counter names can be used like variables in the formulas, so `PMC0+PMC1` sums the measurements for the both events configured in the counters `PMC0` and `PMC1`. The scope tells the Collector whether it is a metric for each hardware thread (`cpu`) or each CPU socket (`socket`). The last one is the publishing flag. It tells the collector whether a metric should be sent to the router.
+- The global metrics are metrics which require data from all event set measurements to be derived. The inputs are the metrics in the event sets. Similar to the metrics in the event sets, the global metrics are defined by a name, a formula, a scope and a publish flag. See event set metrics for details. The only difference is that there is no access to the raw event measurements anymore but only to the metrics. So, the idea is to derive a metric in the "eventsets" section and reuse it in the "globalmetrics" part. If you need a metric only for deriving the global metrics, disable forwarding of the event set metrics. **Be aware** that the combination might be misleading because the "behavior" of a metric changes over time and the multiple measurements might count different computing phases.
+
+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 `$LIKWID_INSTALL_LOC/sbin`
+- `force_overwrite`: Same as setting `LIKWID_FORCE=1`. In case counters are already in-use, LIKWID overwrites their configuration to do its measurements
+- `invalid_to_zero`: In some cases, the calculations result in `NaN` or `Inf`. With this option, all `NaN` and `Inf` values are replaces with `0.0`.
+
+### Available metric scopes
+
+Hardware performance counters are scattered all over the system nowadays. A counter coveres a specific part of the system. While there are hardware thread specific counter for CPU cycles, instructions and so on, some others are specific for a whole CPU socket/package. To address that, the collector provides the specification of a 'scope' for each metric.
+
+- `cpu` : One metric per CPU hardware thread with the tags `"type" : "cpu"` and `"type-id" : "$cpu_id"`
+- `socket` : One metric per CPU socket/package with the tags `"type" : "socket"` and `"type-id" : "$socket_id"`
+
+**Note:** You cannot specify `socket` scope for a metric that is measured at `cpu` scope, so some kind of expert knowledge or lookup work in the [Likwid Wiki](https://github.com/RRZE-HPC/likwid/wiki) is required. Get the scope of each counter from the *Architecture* pages and as soon as one counter in a metric is socket-specific, the whole metric is socket-specific.
+
+As a guideline:
+- All counters `FIXCx`, `PMCy` and `TMAz` have the scope `cpu`
+- All counters names containing `BOX` have the scope `socket`
+- All `PWRx` counters have scope `socket`, except `"PWR1" : "RAPL_CORE_ENERGY"` has `cpu` scope
+- All `DFCx` counters have scope `socket`
+
+### Help with the configuration
+
+The configuration for the `likwid` collector is quite complicated. Most users don't use LIKWID with the event:counter notation but rely on the performance groups defined by the LIKWID team for each architecture. In order to help with the `likwid` collector configuration, we included a script `scripts/likwid_perfgroup_to_cc_config.py` that creates the configuration of an `eventset` from a performance group (using a LIKWID installation in `$PATH`):
+```
+$ likwid-perfctr -i
+[...]
+short name: ICX
+[...]
+$ likwid-perfctr -a
+[...]
+MEM_DP
+MEM
+FLOPS_SP
+CLOCK
+[...]
+$ scripts/likwid_perfgroup_to_cc_config.py ICX MEM_DP
+{
+  "events": {
+    "FIXC0": "INSTR_RETIRED_ANY",
+    "..." : "..."
+  },
+  "metrics" : [
+    {
+      "calc": "time",
+      "name": "Runtime (RDTSC) [s]",
+      "publish": true,
+      "scope": "hwthread"
+    },
+    {
+      "..." : "..."
+    }
+  ]
+}
+```
+
+You can copy this JSON and add it to the `eventsets` list. If you specify multiple event sets, you can add globally derived metrics in the extra `global_metrics` section with the metric names as variables.
+
+### Mixed usage between daemon and users
+
+LIKWID checks the file `/var/run/likwid.lock` before performing any interfering operations. Who is allowed to access the counters is determined by the owner of the file. If it does not exist, it is created for the current user. So, if you want to temporarly allow counter access to a user (e.g. in a job):
+
+Before (SLURM prolog, ...)
+```
+$ chwon $JOBUSER /var/run/likwid.lock
+```
+
+After (SLURM epilog, ...)
+```
+$ chwon $CCUSER /var/run/likwid.lock
+```
+
+### Example configuration
+
+
 ```json
   "likwid": {
+    "force_overwrite" : false,
+    "nan_to_zero" : false,
     "eventsets": [
       {
         "events": {
@@ -20,25 +104,25 @@
           {
             "name": "ipc",
             "calc": "PMC0/PMC1",
-            "socket_scope": false,
+            "scope": "cpu",
             "publish": true
           },
           {
             "name": "flops_any",
             "calc": "0.000001*PMC2/time",
-            "socket_scope": false,
+            "scope": "cpu",
             "publish": true
           },
           {
             "name": "clock_mhz",
             "calc": "0.000001*(FIXC1/FIXC2)/inverseClock",
-            "socket_scope": false,
+            "scope": "cpu",
             "publish": true
           },
           {
             "name": "mem1",
             "calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
-            "socket_scope": true,
+            "scope": "socket",
             "publish": false
           }
         ]
@@ -56,19 +140,19 @@
           {
             "name": "pwr_core",
             "calc": "PWR0/time",
-            "socket_scope": false,
+            "scope": "socket",
             "publish": true
           },
           {
             "name": "pwr_pkg",
             "calc": "PWR1/time",
-            "socket_scope": true,
+            "scope": "socket",
             "publish": true
           },
           {
             "name": "mem2",
             "calc": "0.000001*(DFC0+DFC1+DFC2+DFC3)*64.0/time",
-            "socket_scope": true,
+            "scope": "socket",
             "publish": false
           }
         ]
@@ -78,16 +162,16 @@
       {
         "name": "mem_bw",
         "calc": "mem1+mem2",
-        "socket_scope": true,
+        "scope": "socket",
         "publish": true
       }
     ]
   }
 ```
 
-_Example config suitable for AMD Zen3_
+### How to get the eventsets and metrics from LIKWID
 
-The `likwid` collector reads hardware performance counters at a **hwthread** and **socket** level. The configuration looks quite complicated but it is basically copy&paste from [LIKWID's performance groups](https://github.com/RRZE-HPC/likwid/tree/master/groups). The collector made multiple iterations and tried to use the performance groups but it lacked flexibility. The current way of configuration provides most flexibility.
+The `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:
 ```
@@ -108,12 +192,9 @@ METRICS                          ->   "metrics": [
 IPC   PMC0/PMC1                  ->     {
                                  ->       "name" : "IPC",
                                  ->       "calc" : "PMC0/PMC1",
-                                 ->       "socket_scope": false,
+                                 ->       "scope": "cpu",
                                  ->       "publish": true
                                  ->     }
                                  ->   ]
 ```
 
-The `socket_scope` option tells whether it is submitted per socket or per hwthread. If a metric is only used for internal calculations, you can set `publish = false`.
-
-Since some metrics can only be gathered in multiple measurements (like the memory bandwidth on AMD Zen3 chips), configure multiple eventsets like in the example config and use the `globalmetrics` section to combine them. **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.

collectors/loadavgMetric.go

@@ -2,25 +2,36 @@ package collectors
 
 import (
 	"encoding/json"
+	"fmt"
 	"io/ioutil"
 	"strconv"
 	"strings"
 	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const LOADAVGFILE = `/proc/loadavg`
-
-type LoadavgCollectorConfig struct {
-	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-}
+//
+// LoadavgCollector collects:
+// * load average of last 1, 5 & 15 minutes
+// * number of processes currently runnable
+// * total number of processes in system
+//
+// See: https://www.kernel.org/doc/html/latest/filesystems/proc.html
+//
+const LOADAVGFILE = "/proc/loadavg"
 
 type LoadavgCollector struct {
 	metricCollector
 	tags         map[string]string
 	load_matches []string
+	load_skips   []bool
 	proc_matches []string
-	config       LoadavgCollectorConfig
+	proc_skips   []bool
+	config       struct {
+		ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+	}
 }
 
 func (m *LoadavgCollector) Init(config json.RawMessage) error {
@@ -32,46 +43,82 @@ func (m *LoadavgCollector) Init(config json.RawMessage) error {
 			return err
 		}
 	}
-	m.meta = map[string]string{"source": m.name, "group": "LOAD"}
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "LOAD"}
 	m.tags = map[string]string{"type": "node"}
-	m.load_matches = []string{"load_one", "load_five", "load_fifteen"}
-	m.proc_matches = []string{"proc_run", "proc_total"}
+	m.load_matches = []string{
+		"load_one",
+		"load_five",
+		"load_fifteen"}
+	m.load_skips = make([]bool, len(m.load_matches))
+	m.proc_matches = []string{
+		"proc_run",
+		"proc_total"}
+	m.proc_skips = make([]bool, len(m.proc_matches))
+
+	for i, name := range m.load_matches {
+		_, m.load_skips[i] = stringArrayContains(m.config.ExcludeMetrics, name)
+	}
+	for i, name := range m.proc_matches {
+		_, m.proc_skips[i] = stringArrayContains(m.config.ExcludeMetrics, name)
+	}
 	m.init = true
 	return nil
 }
 
 func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	var skip bool
 	if !m.init {
 		return
 	}
-	buffer, err := ioutil.ReadFile(string(LOADAVGFILE))
-
+	buffer, err := ioutil.ReadFile(LOADAVGFILE)
 	if err != nil {
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err))
+		}
 		return
 	}
+	now := time.Now()
 
+	// Load metrics
 	ls := strings.Split(string(buffer), ` `)
 	for i, name := range m.load_matches {
 		x, err := strconv.ParseFloat(ls[i], 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert '%s' to float64: %v", ls[i], err))
+			continue
+		}
+		if m.load_skips[i] {
+			continue
+		}
+		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
 		if err == nil {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, name)
-			y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": float64(x)}, time.Now())
-			if err == nil && !skip {
-				output <- y
-			}
+			output <- y
 		}
 	}
+
+	// Process metrics
 	lv := strings.Split(ls[3], `/`)
 	for i, name := range m.proc_matches {
-		x, err := strconv.ParseFloat(lv[i], 64)
-		if err == nil {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, name)
-			y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": float64(x)}, time.Now())
-			if err == nil && !skip {
-				output <- y
-			}
+		x, err := strconv.ParseInt(lv[i], 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert '%s' to float64: %v", lv[i], err))
+			continue
 		}
+		if m.proc_skips[i] {
+			continue
+		}
+		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
+		if err == nil {
+			output <- y
+		}
+
 	}
 }
 

collectors/lustreMetric.go

@@ -3,29 +3,90 @@ package collectors
 import (
 	"encoding/json"
 	"errors"
-	"io/ioutil"
-	"log"
+	"fmt"
+	"os/exec"
+	"os/user"
 	"strconv"
 	"strings"
 	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const LUSTREFILE = `/proc/fs/lustre/llite/lnec-XXXXXX/stats`
+const LUSTRE_SYSFS = `/sys/fs/lustre`
+const LCTL_CMD = `lctl`
+const LCTL_OPTION = `get_param`
 
 type LustreCollectorConfig struct {
-	Procfiles      []string `json:"procfiles"`
+	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
 	matches map[string]map[string]int
-	devices []string
+	stats   map[string]map[string]int64
 	config  LustreCollectorConfig
+	lctl    string
+	sudoCmd string
 }
 
+func (m *LustreCollector) getDeviceDataCommand(device string) []string {
+	var command *exec.Cmd
+	statsfile := fmt.Sprintf("llite.%s.stats", device)
+	if m.config.Sudo {
+		command = exec.Command(m.sudoCmd, m.lctl, LCTL_OPTION, statsfile)
+	} else {
+		command = exec.Command(m.lctl, LCTL_OPTION, statsfile)
+	}
+	command.Wait()
+	stdout, _ := command.Output()
+	return strings.Split(string(stdout), "\n")
+}
+
+func (m *LustreCollector) getDevices() []string {
+	devices := make([]string, 0)
+
+	// //Version reading devices from sysfs
+	// globPattern := filepath.Join(LUSTRE_SYSFS, "llite/*/stats")
+	// files, err := filepath.Glob(globPattern)
+	// if err != nil {
+	// 	return devices
+	// }
+	// for _, f := range files {
+	// 	pathlist := strings.Split(f, "/")
+	// 	devices = append(devices, pathlist[4])
+	// }
+
+	data := m.getDeviceDataCommand("*")
+
+	for _, line := range data {
+		if strings.HasPrefix(line, "llite") {
+			linefields := strings.Split(line, ".")
+			if len(linefields) > 2 {
+				devices = append(devices, linefields[1])
+			}
+		}
+	}
+	return devices
+}
+
+// //Version reading the stats data of a device from sysfs
+// func (m *LustreCollector) getDeviceDataSysfs(device string) []string {
+// 	llitedir := filepath.Join(LUSTRE_SYSFS, "llite")
+// 	devdir := filepath.Join(llitedir, device)
+// 	statsfile := filepath.Join(devdir, "stats")
+// 	buffer, err := ioutil.ReadFile(statsfile)
+// 	if err != nil {
+// 		return make([]string, 0)
+// 	}
+// 	return strings.Split(string(buffer), "\n")
+// }
+
 func (m *LustreCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "LustreCollector"
@@ -38,27 +99,69 @@ 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"}
-	m.matches = map[string]map[string]int{"read_bytes": {"read_bytes": 6, "read_requests": 1},
-		"write_bytes":      {"write_bytes": 6, "write_requests": 1},
-		"open":             {"open": 1},
-		"close":            {"close": 1},
-		"setattr":          {"setattr": 1},
-		"getattr":          {"getattr": 1},
-		"statfs":           {"statfs": 1},
-		"inode_permission": {"inode_permission": 1}}
-	m.devices = make([]string, 0)
-	for _, p := range m.config.Procfiles {
-		_, err := ioutil.ReadFile(p)
-		if err == nil {
-			m.devices = append(m.devices, p)
-		} else {
-			log.Print(err.Error())
-			continue
+	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
+	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)
+		if err != nil {
+			return err
+		}
+	}
+	m.lctl = p
+	if m.config.Sudo {
+		p, err := exec.LookPath("sudo")
+		if err != nil {
+			m.sudoCmd = p
 		}
 	}
 
-	if len(m.devices) == 0 {
-		return errors.New("No metrics to collect")
+	devices := m.getDevices()
+	if len(devices) == 0 {
+		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)
+		for _, names := range m.matches {
+			for metricname := range names {
+				m.stats[d][metricname] = 0
+			}
+		}
 	}
 	m.init = true
 	return nil
@@ -68,39 +171,53 @@ func (m *LustreCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	if !m.init {
 		return
 	}
-	for _, p := range m.devices {
-		buffer, err := ioutil.ReadFile(p)
+	for device, devData := range m.stats {
+		stats := m.getDeviceDataCommand(device)
+		processed := []string{}
 
-		if err != nil {
-			log.Print(err)
-			return
-		}
-
-		for _, line := range strings.Split(string(buffer), "\n") {
+		for _, line := range stats {
 			lf := strings.Fields(line)
 			if len(lf) > 1 {
-				for match, fields := range m.matches {
-					if lf[0] == match {
-						for name, idx := range fields {
-							_, skip := stringArrayContains(m.config.ExcludeMetrics, name)
-							if skip {
-								continue
+				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")
 							}
-							x, err := strconv.ParseInt(lf[idx], 0, 64)
-							if err == nil {
-								y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, time.Now())
-								if err == nil {
-									if strings.Contains(name, "byte") {
-										y.AddMeta("unit", "Byte")
-									}
-									output <- y
-								}
+							output <- y
+							if m.config.SendAllMetrics {
+								processed = append(processed, name)
 							}
 						}
 					}
 				}
 			}
 		}
+		if m.config.SendAllMetrics {
+			for name := range devData {
+				if _, done := stringArrayContains(processed, name); !done {
+					y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": 0}, time.Now())
+					if err == nil {
+						y.AddTag("device", device)
+						if strings.Contains(name, "byte") {
+							y.AddMeta("unit", "Byte")
+						}
+						output <- y
+					}
+				}
+			}
+		}
 	}
 }
 

collectors/memstatMetric.go

@@ -1,35 +1,76 @@
 package collectors
 
 import (
+	"bufio"
 	"encoding/json"
 	"errors"
 	"fmt"
-	"io/ioutil"
-	"log"
+	"os"
+	"path/filepath"
+	"regexp"
 	"strconv"
 	"strings"
 	"time"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const MEMSTATFILE = `/proc/meminfo`
+const MEMSTATFILE = "/proc/meminfo"
+const NUMA_MEMSTAT_BASE = "/sys/devices/system/node"
 
 type MemstatCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics"`
+	NodeStats      bool     `json:"node_stats,omitempty"`
+	NumaStats      bool     `json:"numa_stats,omitempty"`
+}
+
+type MemstatCollectorNode struct {
+	file string
+	tags map[string]string
 }
 
 type MemstatCollector struct {
 	metricCollector
-	stats   map[string]int64
-	tags    map[string]string
-	matches map[string]string
-	config  MemstatCollectorConfig
+	stats     map[string]int64
+	tags      map[string]string
+	matches   map[string]string
+	config    MemstatCollectorConfig
+	nodefiles map[int]MemstatCollectorNode
+}
+
+func getStats(filename string) map[string]float64 {
+	stats := make(map[string]float64)
+	file, err := os.Open(filename)
+	if err != nil {
+		cclog.Error(err.Error())
+	}
+	defer file.Close()
+
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := scanner.Text()
+		linefields := strings.Fields(line)
+		if len(linefields) == 3 {
+			v, err := strconv.ParseFloat(linefields[1], 64)
+			if err == nil {
+				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], ":")] = v
+			}
+		}
+	}
+	return stats
 }
 
 func (m *MemstatCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "MemstatCollector"
+	m.config.NodeStats = true
+	m.config.NumaStats = false
 	if len(config) > 0 {
 		err = json.Unmarshal(config, &m.config)
 		if err != nil {
@@ -40,7 +81,8 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 	m.stats = make(map[string]int64)
 	m.matches = make(map[string]string)
 	m.tags = map[string]string{"type": "node"}
-	matches := map[string]string{`MemTotal`: "mem_total",
+	matches := map[string]string{
+		"MemTotal":     "mem_total",
 		"SwapTotal":    "swap_total",
 		"SReclaimable": "mem_sreclaimable",
 		"Slab":         "mem_slab",
@@ -48,7 +90,9 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 		"Buffers":      "mem_buffers",
 		"Cached":       "mem_cached",
 		"MemAvailable": "mem_available",
-		"SwapFree":     "swap_free"}
+		"SwapFree":     "swap_free",
+		"MemShared":    "mem_shared",
+	}
 	for k, v := range matches {
 		_, skip := stringArrayContains(m.config.ExcludeMetrics, k)
 		if !skip {
@@ -56,13 +100,44 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 		}
 	}
 	if len(m.matches) == 0 {
-		return errors.New("No metrics to collect")
+		return errors.New("no metrics to collect")
 	}
 	m.setup()
-	_, err = ioutil.ReadFile(string(MEMSTATFILE))
-	if err == nil {
-		m.init = true
+
+	if m.config.NodeStats {
+		if stats := getStats(MEMSTATFILE); len(stats) == 0 {
+			return fmt.Errorf("cannot read data from file %s", MEMSTATFILE)
+		}
 	}
+
+	if m.config.NumaStats {
+		globPattern := filepath.Join(NUMA_MEMSTAT_BASE, "node[0-9]*", "meminfo")
+		regex := regexp.MustCompile(filepath.Join(NUMA_MEMSTAT_BASE, "node(\\d+)", "meminfo"))
+		files, err := filepath.Glob(globPattern)
+		if err == nil {
+			m.nodefiles = make(map[int]MemstatCollectorNode)
+			for _, f := range files {
+				if stats := getStats(f); len(stats) == 0 {
+					return fmt.Errorf("cannot read data from file %s", f)
+				}
+				rematch := regex.FindStringSubmatch(f)
+				if len(rematch) == 2 {
+					id, err := strconv.Atoi(rematch[1])
+					if err == nil {
+						f := MemstatCollectorNode{
+							file: f,
+							tags: map[string]string{
+								"type":    "memoryDomain",
+								"type-id": fmt.Sprintf("%d", id),
+							},
+						}
+						m.nodefiles[id] = f
+					}
+				}
+			}
+		}
+	}
+	m.init = true
 	return err
 }
 
@@ -71,56 +146,41 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		return
 	}
 
-	buffer, err := ioutil.ReadFile(string(MEMSTATFILE))
-	if err != nil {
-		log.Print(err)
-		return
-	}
-
-	ll := strings.Split(string(buffer), "\n")
-	for _, line := range ll {
-		ls := strings.Split(line, `:`)
-		if len(ls) > 1 {
-			lv := strings.Fields(ls[1])
-			m.stats[ls[0]], err = strconv.ParseInt(lv[0], 0, 64)
+	sendStats := func(stats map[string]float64, tags map[string]string) {
+		for match, name := range m.matches {
+			var value float64 = 0
+			if v, ok := stats[match]; ok {
+				value = v
+			}
+			y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value}, time.Now())
+			if err == nil {
+				output <- y
+			}
 		}
-	}
-
-	if _, exists := m.stats[`MemTotal`]; !exists {
-		err = errors.New("Parse error")
-		log.Print(err)
-		return
-	}
-
-	for match, name := range m.matches {
-		if _, exists := m.stats[match]; !exists {
-			err = fmt.Errorf("Parse error for %s : %s", match, name)
-			log.Print(err)
-			continue
-		}
-		y, err := lp.New(name, m.tags, m.meta, map[string]interface{}{"value": int(float64(m.stats[match]) * 1.0e-3)}, time.Now())
-		if err == nil {
-			output <- y
-		}
-	}
-
-	if _, free := m.stats[`MemFree`]; free {
-		if _, buffers := m.stats[`Buffers`]; buffers {
-			if _, cached := m.stats[`Cached`]; cached {
-				memUsed := m.stats[`MemTotal`] - (m.stats[`MemFree`] + m.stats[`Buffers`] + m.stats[`Cached`])
-				_, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_used")
-				y, err := lp.New("mem_used", m.tags, m.meta, map[string]interface{}{"value": int(float64(memUsed) * 1.0e-3)}, time.Now())
-				if err == nil && !skip {
-					output <- y
+		if _, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_used"); !skip {
+			if freeVal, free := stats["MemFree"]; free {
+				if bufVal, buffers := stats["Buffers"]; buffers {
+					if cacheVal, cached := stats["Cached"]; cached {
+						memUsed := stats["MemTotal"] - (freeVal + bufVal + cacheVal)
+						y, err := lp.New("mem_used", tags, m.meta, map[string]interface{}{"value": memUsed}, time.Now())
+						if err == nil {
+							output <- y
+						}
+					}
 				}
 			}
 		}
 	}
-	if _, found := m.stats[`MemShared`]; found {
-		_, skip := stringArrayContains(m.config.ExcludeMetrics, "mem_shared")
-		y, err := lp.New("mem_shared", m.tags, m.meta, map[string]interface{}{"value": int(float64(m.stats[`MemShared`]) * 1.0e-3)}, time.Now())
-		if err == nil && !skip {
-			output <- y
+
+	if m.config.NodeStats {
+		nodestats := getStats(MEMSTATFILE)
+		sendStats(nodestats, m.tags)
+	}
+
+	if m.config.NumaStats {
+		for _, nodeConf := range m.nodefiles {
+			stats := getStats(nodeConf.file)
+			sendStats(stats, nodeConf.tags)
 		}
 	}
 }

collectors/metricCollector.go

@@ -10,33 +10,33 @@ import (
 	"time"
 
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	influx "github.com/influxdata/line-protocol"
 )
 
 type MetricCollector interface {
-	Name() string
-	Init(config json.RawMessage) error
-	Initialized() bool
-	Read(duration time.Duration, output chan lp.CCMetric)
-	Close()
+	Name() string                                         // Name of the metric collector
+	Init(config json.RawMessage) error                    // Initialize metric collector
+	Initialized() bool                                    // Is metric collector initialized?
+	Read(duration time.Duration, output chan lp.CCMetric) // Read metrics from metric collector
+	Close()                                               // Close / finish metric collector
 }
 
 type metricCollector struct {
-	name string
-	init bool
-	meta map[string]string
+	name string            // name of the metric
+	init bool              // is metric collector initialized?
+	meta map[string]string // static meta data tags
 }
 
-// Name() returns the name of the metric collector
+// Name returns the name of the metric collector
 func (c *metricCollector) Name() string {
 	return c.name
 }
 
+// Setup is for future use
 func (c *metricCollector) setup() error {
 	return nil
 }
 
-// Initialized() indicates whether the metric collector has been initialized.
+// Initialized indicates whether the metric collector has been initialized
 func (c *metricCollector) Initialized() bool {
 	return c.init
 }
@@ -65,6 +65,7 @@ func stringArrayContains(array []string, str string) (int, bool) {
 	return -1, false
 }
 
+// SocketList returns the list of physical sockets as read from /proc/cpuinfo
 func SocketList() []int {
 	buffer, err := ioutil.ReadFile("/proc/cpuinfo")
 	if err != nil {
@@ -90,6 +91,7 @@ func SocketList() []int {
 	return packs
 }
 
+// CpuList returns the list of physical CPUs (in contrast to logical CPUs) as read from /proc/cpuinfo
 func CpuList() []int {
 	buffer, err := ioutil.ReadFile("/proc/cpuinfo")
 	if err != nil {
@@ -115,29 +117,11 @@ func CpuList() []int {
 	return cpulist
 }
 
-// Tags2Map stores a InfluxDB list of tags in a map of key value pairs
-func Tags2Map(metric influx.Metric) map[string]string {
-	tags := make(map[string]string)
-	for _, t := range metric.TagList() {
-		tags[t.Key] = t.Value
-	}
-	return tags
-}
-
-// Fields2Map stores a InfluxDB list of fields in a map of key value pairs
-func Fields2Map(metric influx.Metric) map[string]interface{} {
-	fields := make(map[string]interface{})
-	for _, f := range metric.FieldList() {
-		fields[f.Key] = f.Value
-	}
-	return fields
-}
-
 // RemoveFromStringList removes the string r from the array of strings s
 // If r is not contained in the array an error is returned
 func RemoveFromStringList(s []string, r string) ([]string, error) {
-	for i, item := range s {
-		if r == item {
+	for i := range s {
+		if r == s[i] {
 			return append(s[:i], s[i+1:]...), nil
 		}
 	}

collectors/netstatMetric.go

@@ -1,92 +1,138 @@
 package collectors
 
 import (
+	"bufio"
 	"encoding/json"
-	"io/ioutil"
-	"log"
+	"errors"
+	"os"
 	"strconv"
 	"strings"
 	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 const NETSTATFILE = `/proc/net/dev`
 
 type NetstatCollectorConfig struct {
-	ExcludeDevices []string `json:"exclude_devices"`
+	IncludeDevices []string `json:"include_devices"`
+}
+
+type NetstatCollectorMetric struct {
+	index     int
+	lastValue float64
 }
 
 type NetstatCollector struct {
 	metricCollector
-	config  NetstatCollectorConfig
-	matches map[int]string
+	config        NetstatCollectorConfig
+	matches       map[string]map[string]NetstatCollectorMetric
+	devtags       map[string]map[string]string
+	lastTimestamp time.Time
 }
 
 func (m *NetstatCollector) Init(config json.RawMessage) error {
 	m.name = "NetstatCollector"
 	m.setup()
-	m.meta = map[string]string{"source": m.name, "group": "Memory"}
-	m.matches = map[int]string{
-		1:  "bytes_in",
-		9:  "bytes_out",
-		2:  "pkts_in",
-		10: "pkts_out",
+	m.lastTimestamp = time.Now()
+	m.meta = map[string]string{"source": m.name, "group": "Network"}
+	m.devtags = make(map[string]map[string]string)
+	nameIndexMap := map[string]int{
+		"net_bytes_in":  1,
+		"net_pkts_in":   2,
+		"net_bytes_out": 9,
+		"net_pkts_out":  10,
 	}
+	m.matches = make(map[string]map[string]NetstatCollectorMetric)
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
-			log.Print(err.Error())
+			cclog.ComponentError(m.name, "Error reading config:", err.Error())
 			return err
 		}
 	}
-	_, err := ioutil.ReadFile(string(NETSTATFILE))
-	if err == nil {
-		m.init = true
-	}
-	return nil
-}
-
-func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
-	data, err := ioutil.ReadFile(string(NETSTATFILE))
+	file, err := os.Open(string(NETSTATFILE))
 	if err != nil {
-		log.Print(err.Error())
-		return
+		cclog.ComponentError(m.name, err.Error())
+		return err
 	}
+	defer file.Close()
 
-	lines := strings.Split(string(data), "\n")
-	for _, l := range lines {
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		l := scanner.Text()
 		if !strings.Contains(l, ":") {
 			continue
 		}
 		f := strings.Fields(l)
-		dev := f[0][0 : len(f[0])-1]
-		cont := false
-		for _, d := range m.config.ExcludeDevices {
-			if d == dev {
-				cont = true
+		dev := strings.Trim(f[0], ": ")
+		if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
+			m.matches[dev] = make(map[string]NetstatCollectorMetric)
+			for name, idx := range nameIndexMap {
+				m.matches[dev][name] = NetstatCollectorMetric{
+					index:     idx,
+					lastValue: 0,
+				}
 			}
+			m.devtags[dev] = map[string]string{"device": dev, "type": "node"}
 		}
-		if cont {
+	}
+	if len(m.devtags) == 0 {
+		return errors.New("no devices to collector metrics found")
+	}
+	m.init = true
+	return nil
+}
+
+func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	if !m.init {
+		return
+	}
+	now := time.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()
+		if !strings.Contains(l, ":") {
 			continue
 		}
-		tags := map[string]string{"device": dev, "type": "node"}
-		for i, name := range m.matches {
-			v, err := strconv.ParseInt(f[i], 10, 0)
-			if err == nil {
-				y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": int(float64(v) * 1.0e-3)}, time.Now())
+		f := strings.Fields(l)
+		dev := strings.Trim(f[0], ":")
+
+		if devmetrics, ok := m.matches[dev]; ok {
+			for name, data := range devmetrics {
+				v, err := strconv.ParseFloat(f[data.index], 64)
 				if err == nil {
-					switch {
-					case strings.Contains(name, "byte"):
-						y.AddMeta("unit", "Byte")
-					case strings.Contains(name, "pkt"):
-						y.AddMeta("unit", "Packets")
+					vdiff := v - data.lastValue
+					value := vdiff / tdiff.Seconds()
+					if data.lastValue == 0 {
+						value = 0
 					}
-					output <- y
+					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
+					}
+					devmetrics[name] = data
 				}
 			}
 		}
 	}
-
+	m.lastTimestamp = time.Now()
 }
 
 func (m *NetstatCollector) Close() {

collectors/netstatMetric.md

@@ -3,19 +3,19 @@
 
 ```json
   "netstat": {
-    "exclude_devices": [
-      "lo"
+    "include_devices": [
+      "eth0"
     ]
   }
 ```
 
-The `netstat` collector reads data from `/proc/net/dev` and outputs a handful **node** metrics. If a device is not required, it can be excluded from forwarding it to the sink. Commonly the `lo` device should be excluded.
+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:
-* `bytes_in`
-* `bytes_out`
-* `pkts_in`
-* `pkts_out`
+* `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/nfs3Metric.md

@@ -0,0 +1,39 @@
+
+## `nfs3stat` collector
+
+```json
+  "nfs3stat": {
+    "nfsstat" : "/path/to/nfsstat",
+    "exclude_metrics": [
+      "nfs3_total"
+    ]
+  }
+```
+
+The `nfs3stat` collector reads data from `nfsstat` command and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink. There is currently no possibility to get the metrics per mount point.
+
+
+Metrics:
+* `nfs3_total` 
+* `nfs3_null` 
+* `nfs3_getattr` 
+* `nfs3_setattr` 
+* `nfs3_lookup` 
+* `nfs3_access` 
+* `nfs3_readlink` 
+* `nfs3_read` 
+* `nfs3_write` 
+* `nfs3_create` 
+* `nfs3_mkdir` 
+* `nfs3_symlink` 
+* `nfs3_remove` 
+* `nfs3_rmdir` 
+* `nfs3_rename` 
+* `nfs3_link` 
+* `nfs3_readdir` 
+* `nfs3_readdirplus` 
+* `nfs3_fsstat` 
+* `nfs3_fsinfo` 
+* `nfs3_pathconf` 
+* `nfs3_commit` 
+

collectors/nfs4Metric.md

@@ -0,0 +1,62 @@
+
+## `nfs4stat` collector
+
+```json
+  "nfs4stat": {
+    "nfsstat" : "/path/to/nfsstat",
+    "exclude_metrics": [
+      "nfs4_total"
+    ]
+  }
+```
+
+The `nfs4stat` collector reads data from `nfsstat` command and outputs a handful **node** metrics. If a metric is not required, it can be excluded from forwarding it to the sink. There is currently no possibility to get the metrics per mount point.
+
+
+Metrics:
+* `nfs4_total` 
+* `nfs4_null` 
+* `nfs4_read` 
+* `nfs4_write` 
+* `nfs4_commit` 
+* `nfs4_open` 
+* `nfs4_open_conf` 
+* `nfs4_open_noat` 
+* `nfs4_open_dgrd` 
+* `nfs4_close` 
+* `nfs4_setattr` 
+* `nfs4_fsinfo` 
+* `nfs4_renew` 
+* `nfs4_setclntid` 
+* `nfs4_confirm` 
+* `nfs4_lock` 
+* `nfs4_lockt` 
+* `nfs4_locku` 
+* `nfs4_access` 
+* `nfs4_getattr` 
+* `nfs4_lookup` 
+* `nfs4_lookup_root` 
+* `nfs4_remove` 
+* `nfs4_rename` 
+* `nfs4_link` 
+* `nfs4_symlink` 
+* `nfs4_create` 
+* `nfs4_pathconf` 
+* `nfs4_statfs` 
+* `nfs4_readlink` 
+* `nfs4_readdir` 
+* `nfs4_server_caps` 
+* `nfs4_delegreturn` 
+* `nfs4_getacl` 
+* `nfs4_setacl` 
+* `nfs4_rel_lkowner` 
+* `nfs4_exchange_id` 
+* `nfs4_create_session` 
+* `nfs4_destroy_session` 
+* `nfs4_sequence` 
+* `nfs4_get_lease_time` 
+* `nfs4_reclaim_comp` 
+* `nfs4_secinfo_no` 
+* `nfs4_bind_conn_to_ses` 
+
+

collectors/nfsMetric.go

@@ -14,23 +14,29 @@ import (
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
+// First part contains the code for the general NfsCollector.
+// Later, the general NfsCollector is more limited to Nfs3- and Nfs4Collector.
+
+const NFSSTAT_EXEC = `nfsstat`
+
 type NfsCollectorData struct {
 	current int64
 	last    int64
 }
 
-type NfsCollector struct {
+type nfsCollector struct {
 	metricCollector
-	tags   map[string]string
-	config struct {
-		Nfsutils       string   `json:"nfsutils"`
+	tags    map[string]string
+	version string
+	config  struct {
+		Nfsstats       string   `json:"nfsstat"`
 		ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
 	}
-	data map[string]map[string]NfsCollectorData
+	data map[string]NfsCollectorData
 }
 
-func (m *NfsCollector) initStats() error {
-	cmd := exec.Command(m.config.Nfsutils, "-l")
+func (m *nfsCollector) initStats() error {
+	cmd := exec.Command(m.config.Nfsstats, `-l`)
 	cmd.Wait()
 	buffer, err := cmd.Output()
 	if err == nil {
@@ -39,17 +45,16 @@ func (m *NfsCollector) initStats() error {
 			if len(lf) != 5 {
 				continue
 			}
-			if _, exist := m.data[lf[1]]; !exist {
-				m.data[lf[1]] = make(map[string]NfsCollectorData)
-			}
-			name := strings.Trim(lf[3], ":")
-			if _, exist := m.data[lf[1]][name]; !exist {
-				value, err := strconv.ParseInt(lf[4], 0, 64)
-				if err == nil {
-					x := m.data[lf[1]][name]
-					x.current = value
-					x.last = 0
-					m.data[lf[1]][name] = x
+			if lf[1] == m.version {
+				name := strings.Trim(lf[3], ":")
+				if _, exist := m.data[name]; !exist {
+					value, err := strconv.ParseInt(lf[4], 0, 64)
+					if err == nil {
+						x := m.data[name]
+						x.current = value
+						x.last = 0
+						m.data[name] = x
+					}
 				}
 			}
 		}
@@ -57,8 +62,8 @@ func (m *NfsCollector) initStats() error {
 	return err
 }
 
-func (m *NfsCollector) updateStats() error {
-	cmd := exec.Command(m.config.Nfsutils, "-l")
+func (m *nfsCollector) updateStats() error {
+	cmd := exec.Command(m.config.Nfsstats, `-l`)
 	cmd.Wait()
 	buffer, err := cmd.Output()
 	if err == nil {
@@ -67,17 +72,16 @@ func (m *NfsCollector) updateStats() error {
 			if len(lf) != 5 {
 				continue
 			}
-			if _, exist := m.data[lf[1]]; !exist {
-				m.data[lf[1]] = make(map[string]NfsCollectorData)
-			}
-			name := strings.Trim(lf[3], ":")
-			if _, exist := m.data[lf[1]][name]; exist {
-				value, err := strconv.ParseInt(lf[4], 0, 64)
-				if err == nil {
-					x := m.data[lf[1]][name]
-					x.last = x.current
-					x.current = value
-					m.data[lf[1]][name] = x
+			if lf[1] == m.version {
+				name := strings.Trim(lf[3], ":")
+				if _, exist := m.data[name]; exist {
+					value, err := strconv.ParseInt(lf[4], 0, 64)
+					if err == nil {
+						x := m.data[name]
+						x.last = x.current
+						x.current = value
+						m.data[name] = x
+					}
 				}
 			}
 		}
@@ -85,17 +89,11 @@ func (m *NfsCollector) updateStats() error {
 	return err
 }
 
-func (m *NfsCollector) Init(config json.RawMessage) error {
-	var err error
-	m.name = "NfsCollector"
-	m.setup()
-
-	// Set default mmpmon binary
-	m.config.Nfsutils = "/usr/sbin/nfsstat"
-
+func (m *nfsCollector) MainInit(config json.RawMessage) error {
+	m.config.Nfsstats = string(NFSSTAT_EXEC)
 	// Read JSON configuration
 	if len(config) > 0 {
-		err = json.Unmarshal(config, &m.config)
+		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			log.Print(err.Error())
 			return err
@@ -108,40 +106,69 @@ func (m *NfsCollector) Init(config json.RawMessage) error {
 	m.tags = map[string]string{
 		"type": "node",
 	}
-	// Check if mmpmon is in executable search path
-	_, err = exec.LookPath(m.config.Nfsutils)
+	// Check if nfsstat is in executable search path
+	_, err := exec.LookPath(m.config.Nfsstats)
 	if err != nil {
-		return fmt.Errorf("NfsCollector.Init(): Failed to find nfsstat binary '%s': %v", m.config.Nfsutils, err)
+		return fmt.Errorf("NfsCollector.Init(): Failed to find nfsstat binary '%s': %v", m.config.Nfsstats, err)
 	}
-	m.data = make(map[string]map[string]NfsCollectorData)
+	m.data = make(map[string]NfsCollectorData)
 	m.initStats()
 	m.init = true
 	return nil
 }
 
-func (m *NfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
 		return
 	}
 	timestamp := time.Now()
 
 	m.updateStats()
+	prefix := ""
+	switch m.version {
+	case "v3":
+		prefix = "nfs3"
+	case "v4":
+		prefix = "nfs4"
+	default:
+		prefix = "nfs"
+	}
 
-	for version, metrics := range m.data {
-		for name, data := range metrics {
-			if _, skip := stringArrayContains(m.config.ExcludeMetrics, name); skip {
-				continue
-			}
-			value := data.current - data.last
-			y, err := lp.New(fmt.Sprintf("nfs_%s", name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
-			if err == nil {
-				y.AddMeta("version", version)
-				output <- y
-			}
+	for name, data := range m.data {
+		if _, skip := stringArrayContains(m.config.ExcludeMetrics, name); skip {
+			continue
+		}
+		value := data.current - data.last
+		y, err := lp.New(fmt.Sprintf("%s_%s", prefix, name), m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+		if err == nil {
+			y.AddMeta("version", m.version)
+			output <- y
 		}
 	}
 }
 
-func (m *NfsCollector) Close() {
+func (m *nfsCollector) Close() {
 	m.init = false
 }
+
+type Nfs3Collector struct {
+	nfsCollector
+}
+
+type Nfs4Collector struct {
+	nfsCollector
+}
+
+func (m *Nfs3Collector) Init(config json.RawMessage) error {
+	m.name = "Nfs3Collector"
+	m.version = `v3`
+	m.setup()
+	return m.MainInit(config)
+}
+
+func (m *Nfs4Collector) Init(config json.RawMessage) error {
+	m.name = "Nfs4Collector"
+	m.version = `v4`
+	m.setup()
+	return m.MainInit(config)
+}

collectors/numastatsMetric.go

@@ -0,0 +1,139 @@
+package collectors
+
+import (
+	"bufio"
+	"encoding/json"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strconv"
+	"strings"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+)
+
+//
+// Numa policy hit/miss statistics
+//
+// numa_hit:
+//   A process wanted to allocate memory from this node, and succeeded.
+// numa_miss:
+//   A process wanted to allocate memory from another node,
+//   but ended up with memory from this node.
+// numa_foreign:
+//   A process wanted to allocate on this node,
+//   but ended up with memory from another node.
+// local_node:
+//   A process ran on this node's CPU,
+//   and got memory from this node.
+// other_node:
+//   A process ran on a different node's CPU
+//   and got memory from this node.
+// interleave_hit:
+//   Interleaving wanted to allocate from this node
+//   and succeeded.
+//
+// See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
+//
+type NUMAStatsCollectorTopolgy struct {
+	file   string
+	tagSet map[string]string
+}
+
+type NUMAStatsCollector struct {
+	metricCollector
+	topology []NUMAStatsCollectorTopolgy
+}
+
+func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+
+	m.name = "NUMAStatsCollector"
+	m.setup()
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "NUMA",
+	}
+
+	// Loop for all NUMA node directories
+	base := "/sys/devices/system/node/node"
+	globPattern := base + "[0-9]*"
+	dirs, err := filepath.Glob(globPattern)
+	if err != nil {
+		return fmt.Errorf("unable to glob files with pattern '%s'", globPattern)
+	}
+	if dirs == nil {
+		return fmt.Errorf("unable to find any files with pattern '%s'", globPattern)
+	}
+	m.topology = make([]NUMAStatsCollectorTopolgy, 0, len(dirs))
+	for _, dir := range dirs {
+		node := strings.TrimPrefix(dir, base)
+		file := filepath.Join(dir, "numastat")
+		m.topology = append(m.topology,
+			NUMAStatsCollectorTopolgy{
+				file:   file,
+				tagSet: map[string]string{"memoryDomain": node},
+			})
+	}
+
+	m.init = true
+	return nil
+}
+
+func (m *NUMAStatsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	if !m.init {
+		return
+	}
+
+	for i := range m.topology {
+		// Loop for all NUMA domains
+		t := &m.topology[i]
+
+		now := time.Now()
+		file, err := os.Open(t.file)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to open file '%s': %v", t.file, err))
+			return
+		}
+		scanner := bufio.NewScanner(file)
+
+		// Read line by line
+		for scanner.Scan() {
+			split := strings.Fields(scanner.Text())
+			if len(split) != 2 {
+				continue
+			}
+			key := split[0]
+			value, err := strconv.ParseInt(split[1], 10, 64)
+			if err != nil {
+				cclog.ComponentError(
+					m.name,
+					fmt.Sprintf("Read(): Failed to convert %s='%s' to int64: %v", key, split[1], err))
+				continue
+			}
+			y, err := lp.New(
+				"numastats_"+key,
+				t.tagSet,
+				m.meta,
+				map[string]interface{}{"value": value},
+				now,
+			)
+			if err == nil {
+				output <- y
+			}
+		}
+
+		file.Close()
+	}
+}
+
+func (m *NUMAStatsCollector) Close() {
+	m.init = false
+}

collectors/numastatsMetric.md

@@ -0,0 +1,15 @@
+
+## `numastat` collector
+```json
+  "numastat": {}
+```
+
+The `numastat` collector reads data from `/sys/devices/system/node/node*/numastat` and outputs a handful **memoryDomain** metrics. See: https://www.kernel.org/doc/html/latest/admin-guide/numastat.html
+
+Metrics:
+* `numastats_numa_hit`: A process wanted to allocate memory from this node, and succeeded.
+* `numastats_numa_miss`: A process wanted to allocate memory from another node, but ended up with memory from this node.
+* `numastats_numa_foreign`: A process wanted to allocate on this node, but ended up with memory from another node.
+* `numastats_local_node`: A process ran on this node's CPU, and got memory from this node.
+* `numastats_other_node`: A process ran on a different node's CPU, and got memory from this node.
+* `numastats_interleave_hit`: Interleaving wanted to allocate from this node and succeeded.

collectors/nvidiaMetric.go

@@ -6,6 +6,8 @@ import (
 	"fmt"
 	"log"
 	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	"github.com/NVIDIA/go-nvml/pkg/nvml"
 )
@@ -13,12 +15,20 @@ import (
 type NvidiaCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
 	ExcludeDevices []string `json:"exclude_devices,omitempty"`
+	AddPciInfoTag  bool     `json:"add_pci_info_tag,omitempty"`
+}
+
+type NvidiaCollectorDevice struct {
+	device         nvml.Device
+	excludeMetrics map[string]bool
+	tags           map[string]string
 }
 
 type NvidiaCollector struct {
 	metricCollector
 	num_gpus int
 	config   NvidiaCollectorConfig
+	gpus     []NvidiaCollectorDevice
 }
 
 func (m *NvidiaCollector) CatchPanic() {
@@ -31,26 +41,86 @@ func (m *NvidiaCollector) CatchPanic() {
 func (m *NvidiaCollector) Init(config json.RawMessage) error {
 	var err error
 	m.name = "NvidiaCollector"
+	m.config.AddPciInfoTag = false
 	m.setup()
-	m.meta = map[string]string{"source": m.name, "group": "Nvidia"}
 	if len(config) > 0 {
 		err = json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "Nvidia",
+	}
+
 	m.num_gpus = 0
 	defer m.CatchPanic()
+
+	// Initialize NVIDIA Management Library (NVML)
 	ret := nvml.Init()
 	if ret != nvml.SUCCESS {
 		err = errors.New(nvml.ErrorString(ret))
+		cclog.ComponentError(m.name, "Unable to initialize NVML", err.Error())
 		return err
 	}
-	m.num_gpus, ret = nvml.DeviceGetCount()
+
+	// Number of NVIDIA GPUs
+	num_gpus, ret := nvml.DeviceGetCount()
 	if ret != nvml.SUCCESS {
 		err = errors.New(nvml.ErrorString(ret))
+		cclog.ComponentError(m.name, "Unable to get device count", err.Error())
 		return err
 	}
+
+	// For all GPUs
+	m.gpus = make([]NvidiaCollectorDevice, num_gpus)
+	for i := 0; i < num_gpus; i++ {
+		g := &m.gpus[i]
+
+		// Skip excluded devices
+		str_i := fmt.Sprintf("%d", i)
+		if _, skip := stringArrayContains(m.config.ExcludeDevices, str_i); skip {
+			continue
+		}
+
+		// Get device handle
+		device, ret := nvml.DeviceGetHandleByIndex(i)
+		if ret != nvml.SUCCESS {
+			err = errors.New(nvml.ErrorString(ret))
+			cclog.ComponentError(m.name, "Unable to get device at index", i, ":", err.Error())
+			return err
+		}
+		g.device = device
+
+		// Add tags
+		g.tags = map[string]string{
+			"type":    "accelerator",
+			"type-id": str_i,
+		}
+
+		// Add excluded metrics
+		g.excludeMetrics = map[string]bool{}
+		for _, e := range m.config.ExcludeMetrics {
+			g.excludeMetrics[e] = true
+		}
+
+		// Add PCI info as tag
+		if m.config.AddPciInfoTag {
+			pciInfo, ret := nvml.DeviceGetPciInfo(g.device)
+			if ret != nvml.SUCCESS {
+				err = errors.New(nvml.ErrorString(ret))
+				cclog.ComponentError(m.name, "Unable to get PCI info for device at index", i, ":", err.Error())
+				return err
+			}
+			g.tags["pci_identifier"] = fmt.Sprintf(
+				"%08X:%02X:%02X.0",
+				pciInfo.Domain,
+				pciInfo.Bus,
+				pciInfo.Device)
+		}
+	}
+
 	m.init = true
 	return nil
 }
@@ -59,207 +129,335 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMetric)
 	if !m.init {
 		return
 	}
-	for i := 0; i < m.num_gpus; i++ {
-		device, ret := nvml.DeviceGetHandleByIndex(i)
-		if ret != nvml.SUCCESS {
-			log.Fatalf("Unable to get device at index %d: %v", i, nvml.ErrorString(ret))
-			return
-		}
-		_, skip := stringArrayContains(m.config.ExcludeDevices, fmt.Sprintf("%d", i))
-		if skip {
-			continue
-		}
-		tags := map[string]string{"type": "accelerator", "type-id": fmt.Sprintf("%d", i)}
 
-		util, ret := nvml.DeviceGetUtilizationRates(device)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_util")
-			y, err := lp.New("nv_util", tags, m.meta, map[string]interface{}{"value": float64(util.Gpu)}, time.Now())
-			if err == nil && !skip {
-				output <- y
-			}
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_mem_util")
-			y, err = lp.New("nv_mem_util", tags, m.meta, map[string]interface{}{"value": float64(util.Memory)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+	for i := range m.gpus {
+		device := &m.gpus[i]
+
+		if !device.excludeMetrics["nv_util"] || !device.excludeMetrics["nv_mem_util"] {
+			// Retrieves the current utilization rates for the device's major subsystems.
+			//
+			// Available utilization rates
+			// * Gpu: Percent of time over the past sample period during which one or more kernels was executing on the GPU.
+			// * Memory: Percent of time over the past sample period during which global (device) memory was being read or written
+			//
+			// Note:
+			// * During driver initialization when ECC is enabled one can see high GPU and Memory Utilization readings.
+			//   This is caused by ECC Memory Scrubbing mechanism that is performed during driver initialization.
+			// * On MIG-enabled GPUs, querying device utilization rates is not currently supported.
+			util, ret := nvml.DeviceGetUtilizationRates(device.device)
+			if ret == nvml.SUCCESS {
+				if !device.excludeMetrics["nv_util"] {
+					y, err := lp.New("nv_util", device.tags, m.meta, map[string]interface{}{"value": float64(util.Gpu)}, time.Now())
+					if err == nil {
+						y.AddMeta("unit", "%")
+						output <- y
+					}
+				}
+				if !device.excludeMetrics["nv_mem_util"] {
+					y, err := lp.New("nv_mem_util", device.tags, m.meta, map[string]interface{}{"value": float64(util.Memory)}, time.Now())
+					if err == nil {
+						y.AddMeta("unit", "%")
+						output <- y
+					}
+				}
 			}
 		}
 
-		meminfo, ret := nvml.DeviceGetMemoryInfo(device)
-		if ret == nvml.SUCCESS {
-			t := float64(meminfo.Total) / (1024 * 1024)
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_mem_total")
-			y, err := lp.New("nv_mem_total", tags, m.meta, map[string]interface{}{"value": t}, time.Now())
-			if err == nil && !skip {
-				y.AddMeta("unit", "MByte")
-				output <- y
-			}
-			f := float64(meminfo.Used) / (1024 * 1024)
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_fb_memory")
-			y, err = lp.New("nv_fb_memory", tags, m.meta, map[string]interface{}{"value": f}, time.Now())
-			if err == nil && !skip {
-				y.AddMeta("unit", "MByte")
-				output <- y
+		if !device.excludeMetrics["nv_mem_total"] || !device.excludeMetrics["nv_fb_memory"] {
+			// Retrieves the amount of used, free and total memory available on the device, in bytes.
+			//
+			// Enabling ECC reduces the amount of total available memory, due to the extra required parity bits.
+			//
+			// The reported amount of used memory is equal to the sum of memory allocated by all active channels on the device.
+			//
+			// Available memory info:
+			// * Free: Unallocated FB memory (in bytes).
+			// * Total: Total installed FB memory (in bytes).
+			// * Used: Allocated FB memory (in bytes). Note that the driver/GPU always sets aside a small amount of memory for bookkeeping.
+			//
+			// Note:
+			// In MIG mode, if device handle is provided, the API returns aggregate information, only if the caller has appropriate privileges.
+			// Per-instance information can be queried by using specific MIG device handles.
+			meminfo, ret := nvml.DeviceGetMemoryInfo(device.device)
+			if ret == nvml.SUCCESS {
+				if !device.excludeMetrics["nv_mem_total"] {
+					t := float64(meminfo.Total) / (1024 * 1024)
+					y, err := lp.New("nv_mem_total", device.tags, m.meta, map[string]interface{}{"value": t}, time.Now())
+					if err == nil {
+						y.AddMeta("unit", "MByte")
+						output <- y
+					}
+				}
+
+				if !device.excludeMetrics["nv_fb_memory"] {
+					f := float64(meminfo.Used) / (1024 * 1024)
+					y, err := lp.New("nv_fb_memory", device.tags, m.meta, map[string]interface{}{"value": f}, time.Now())
+					if err == nil {
+						y.AddMeta("unit", "MByte")
+						output <- y
+					}
+				}
 			}
 		}
 
-		temp, ret := nvml.DeviceGetTemperature(device, nvml.TEMPERATURE_GPU)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_temp")
-			y, err := lp.New("nv_temp", tags, m.meta, map[string]interface{}{"value": float64(temp)}, time.Now())
-			if err == nil && !skip {
-				y.AddMeta("unit", "degC")
-				output <- y
+		if !device.excludeMetrics["nv_temp"] {
+			// Retrieves the current temperature readings for the device, in degrees C.
+			//
+			// Available temperature sensors:
+			// * TEMPERATURE_GPU: Temperature sensor for the GPU die.
+			// * NVML_TEMPERATURE_COUNT
+			temp, ret := nvml.DeviceGetTemperature(device.device, nvml.TEMPERATURE_GPU)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_temp", device.tags, m.meta, map[string]interface{}{"value": float64(temp)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "degC")
+					output <- y
+				}
 			}
 		}
 
-		fan, ret := nvml.DeviceGetFanSpeed(device)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_fan")
-			y, err := lp.New("nv_fan", tags, m.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_fan"] {
+			// Retrieves the intended operating speed of the device's fan.
+			//
+			// Note: The reported speed is the intended fan speed.
+			// If the fan is physically blocked and unable to spin, the output will not match the actual fan speed.
+			//
+			// For all discrete products with dedicated fans.
+			//
+			// The fan speed is expressed as a percentage of the product's maximum noise tolerance fan speed.
+			// This value may exceed 100% in certain cases.
+			fan, ret := nvml.DeviceGetFanSpeed(device.device)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_fan", device.tags, m.meta, map[string]interface{}{"value": float64(fan)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "%")
+					output <- y
+				}
 			}
 		}
 
-		_, ecc_pend, ret := nvml.DeviceGetEccMode(device)
-		if ret == nvml.SUCCESS {
-			var y lp.CCMetric
-			var err error
-			switch ecc_pend {
-			case nvml.FEATURE_DISABLED:
-				y, err = lp.New("nv_ecc_mode", tags, m.meta, map[string]interface{}{"value": string("OFF")}, time.Now())
-			case nvml.FEATURE_ENABLED:
-				y, err = lp.New("nv_ecc_mode", tags, m.meta, map[string]interface{}{"value": string("ON")}, time.Now())
-			default:
-				y, err = lp.New("nv_ecc_mode", tags, m.meta, map[string]interface{}{"value": string("UNKNOWN")}, time.Now())
-			}
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_ecc_mode")
-			if err == nil && !skip {
-				output <- y
-			}
-		} else if ret == nvml.ERROR_NOT_SUPPORTED {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_ecc_mode")
-			y, err := lp.New("nv_ecc_mode", tags, m.meta, map[string]interface{}{"value": string("N/A")}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_ecc_mode"] {
+			// Retrieves the current and pending ECC modes for the device.
+			//
+			// For Fermi or newer fully supported devices. Only applicable to devices with ECC.
+			// Requires NVML_INFOROM_ECC version 1.0 or higher.
+			//
+			// Changing ECC modes requires a reboot.
+			// The "pending" ECC mode refers to the target mode following the next reboot.
+			_, ecc_pend, ret := nvml.DeviceGetEccMode(device.device)
+			if ret == nvml.SUCCESS {
+				var y lp.CCMetric
+				var err error
+				switch ecc_pend {
+				case nvml.FEATURE_DISABLED:
+					y, err = lp.New("nv_ecc_mode", device.tags, m.meta, map[string]interface{}{"value": "OFF"}, time.Now())
+				case nvml.FEATURE_ENABLED:
+					y, err = lp.New("nv_ecc_mode", device.tags, m.meta, map[string]interface{}{"value": "ON"}, time.Now())
+				default:
+					y, err = lp.New("nv_ecc_mode", device.tags, m.meta, map[string]interface{}{"value": "UNKNOWN"}, time.Now())
+				}
+				if err == nil {
+					output <- y
+				}
+			} else if ret == nvml.ERROR_NOT_SUPPORTED {
+				y, err := lp.New("nv_ecc_mode", device.tags, m.meta, map[string]interface{}{"value": "N/A"}, time.Now())
+				if err == nil {
+					output <- y
+				}
 			}
 		}
 
-		pstate, ret := nvml.DeviceGetPerformanceState(device)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_perf_state")
-			y, err := lp.New("nv_perf_state", tags, m.meta, map[string]interface{}{"value": fmt.Sprintf("P%d", int(pstate))}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_perf_state"] {
+			// Retrieves the current performance state for the device.
+			//
+			// Allowed PStates:
+			//  0: Maximum Performance.
+			// ..
+			// 15: Minimum Performance.
+			// 32: Unknown performance state.
+			pState, ret := nvml.DeviceGetPerformanceState(device.device)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_perf_state", device.tags, m.meta, map[string]interface{}{"value": fmt.Sprintf("P%d", int(pState))}, time.Now())
+				if err == nil {
+					output <- y
+				}
 			}
 		}
 
-		power, ret := nvml.DeviceGetPowerUsage(device)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_power_usage_report")
-			y, err := lp.New("nv_power_usage_report", tags, m.meta, map[string]interface{}{"value": float64(power) / 1000}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_power_usage_report"] {
+			// Retrieves power usage for this GPU in milliwatts and its associated circuitry (e.g. memory)
+			//
+			// On Fermi and Kepler GPUs the reading is accurate to within +/- 5% of current power draw.
+			//
+			// It is only available if power management mode is supported
+			power, ret := nvml.DeviceGetPowerUsage(device.device)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_power_usage_report", device.tags, m.meta, map[string]interface{}{"value": float64(power) / 1000}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "watts")
+					output <- y
+				}
 			}
 		}
 
-		gclk, ret := nvml.DeviceGetClockInfo(device, nvml.CLOCK_GRAPHICS)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_graphics_clock_report")
-			y, err := lp.New("nv_graphics_clock_report", tags, m.meta, map[string]interface{}{"value": float64(gclk)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		// Retrieves the current clock speeds for the device.
+		//
+		// Available clock information:
+		// * CLOCK_GRAPHICS: Graphics clock domain.
+		// * CLOCK_SM: Streaming Multiprocessor clock domain.
+		// * CLOCK_MEM: Memory clock domain.
+		if !device.excludeMetrics["nv_graphics_clock_report"] {
+			graphicsClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_GRAPHICS)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_graphics_clock_report", device.tags, m.meta, map[string]interface{}{"value": float64(graphicsClock)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "MHz")
+					output <- y
+				}
 			}
 		}
 
-		smclk, ret := nvml.DeviceGetClockInfo(device, nvml.CLOCK_SM)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_sm_clock_report")
-			y, err := lp.New("nv_sm_clock_report", tags, m.meta, map[string]interface{}{"value": float64(smclk)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_sm_clock_report"] {
+			smCock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_sm_clock_report", device.tags, m.meta, map[string]interface{}{"value": float64(smCock)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "MHz")
+					output <- y
+				}
 			}
 		}
 
-		memclk, ret := nvml.DeviceGetClockInfo(device, nvml.CLOCK_MEM)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_mem_clock_report")
-			y, err := lp.New("nv_mem_clock_report", tags, m.meta, map[string]interface{}{"value": float64(memclk)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_mem_clock_report"] {
+			memClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_mem_clock_report", device.tags, m.meta, map[string]interface{}{"value": float64(memClock)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "MHz")
+					output <- y
+				}
 			}
 		}
 
-		max_gclk, ret := nvml.DeviceGetMaxClockInfo(device, nvml.CLOCK_GRAPHICS)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_max_graphics_clock")
-			y, err := lp.New("nv_max_graphics_clock", tags, m.meta, map[string]interface{}{"value": float64(max_gclk)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		// Retrieves the maximum clock speeds for the device.
+		//
+		// Available clock information:
+		// * CLOCK_GRAPHICS: Graphics clock domain.
+		// * CLOCK_SM:       Streaming multiprocessor clock domain.
+		// * CLOCK_MEM:      Memory clock domain.
+		// * CLOCK_VIDEO:    Video encoder/decoder clock domain.
+		// * CLOCK_COUNT:    Count of clock types.
+		//
+		// Note:
+		/// On GPUs from Fermi family current P0 clocks (reported by nvmlDeviceGetClockInfo) can differ from max clocks by few MHz.
+		if !device.excludeMetrics["nv_max_graphics_clock"] {
+			max_gclk, ret := nvml.DeviceGetMaxClockInfo(device.device, nvml.CLOCK_GRAPHICS)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_max_graphics_clock", device.tags, m.meta, map[string]interface{}{"value": float64(max_gclk)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "MHz")
+					output <- y
+				}
 			}
 		}
 
-		max_smclk, ret := nvml.DeviceGetClockInfo(device, nvml.CLOCK_SM)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_max_sm_clock")
-			y, err := lp.New("nv_max_sm_clock", tags, m.meta, map[string]interface{}{"value": float64(max_smclk)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_max_sm_clock"] {
+			maxSmClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_SM)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_max_sm_clock", device.tags, m.meta, map[string]interface{}{"value": float64(maxSmClock)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "MHz")
+					output <- y
+				}
 			}
 		}
 
-		max_memclk, ret := nvml.DeviceGetClockInfo(device, nvml.CLOCK_MEM)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_max_mem_clock")
-			y, err := lp.New("nv_max_mem_clock", tags, m.meta, map[string]interface{}{"value": float64(max_memclk)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_max_mem_clock"] {
+			maxMemClock, ret := nvml.DeviceGetClockInfo(device.device, nvml.CLOCK_MEM)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_max_mem_clock", device.tags, m.meta, map[string]interface{}{"value": float64(maxMemClock)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "MHz")
+					output <- y
+				}
 			}
 		}
 
-		ecc_db, ret := nvml.DeviceGetTotalEccErrors(device, 1, 1)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_ecc_db_error")
-			y, err := lp.New("nv_ecc_db_error", tags, m.meta, map[string]interface{}{"value": float64(ecc_db)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_ecc_db_error"] {
+			// Retrieves the total ECC error counts for the device.
+			//
+			// For Fermi or newer fully supported devices.
+			// Only applicable to devices with ECC.
+			// Requires NVML_INFOROM_ECC version 1.0 or higher.
+			// Requires ECC Mode to be enabled.
+			//
+			// The total error count is the sum of errors across each of the separate memory systems,
+			// i.e. the total set of errors across the entire device.
+			ecc_db, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_UNCORRECTED, nvml.AGGREGATE_ECC)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_ecc_db_error", device.tags, m.meta, map[string]interface{}{"value": float64(ecc_db)}, time.Now())
+				if err == nil {
+					output <- y
+				}
 			}
 		}
 
-		ecc_sb, ret := nvml.DeviceGetTotalEccErrors(device, 0, 1)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_ecc_sb_error")
-			y, err := lp.New("nv_ecc_sb_error", tags, m.meta, map[string]interface{}{"value": float64(ecc_sb)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_ecc_sb_error"] {
+			ecc_sb, ret := nvml.DeviceGetTotalEccErrors(device.device, nvml.MEMORY_ERROR_TYPE_CORRECTED, nvml.AGGREGATE_ECC)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_ecc_sb_error", device.tags, m.meta, map[string]interface{}{"value": float64(ecc_sb)}, time.Now())
+				if err == nil {
+					output <- y
+				}
 			}
 		}
 
-		pwr_limit, ret := nvml.DeviceGetPowerManagementLimit(device)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_power_man_limit")
-			y, err := lp.New("nv_power_man_limit", tags, m.meta, map[string]interface{}{"value": float64(pwr_limit)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_power_man_limit"] {
+			// Retrieves the power management limit associated with this device.
+			//
+			// For Fermi or newer fully supported devices.
+			//
+			// The power limit defines the upper boundary for the card's power draw.
+			// If the card's total power draw reaches this limit the power management algorithm kicks in.
+			pwr_limit, ret := nvml.DeviceGetPowerManagementLimit(device.device)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_power_man_limit", device.tags, m.meta, map[string]interface{}{"value": float64(pwr_limit) / 1000}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "watts")
+					output <- y
+				}
 			}
 		}
 
-		enc_util, _, ret := nvml.DeviceGetEncoderUtilization(device)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_encoder_util")
-			y, err := lp.New("nv_encoder_util", tags, m.meta, map[string]interface{}{"value": float64(enc_util)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_encoder_util"] {
+			// Retrieves the current utilization and sampling size in microseconds for the Encoder
+			//
+			// For Kepler or newer fully supported devices.
+			//
+			// Note: On MIG-enabled GPUs, querying encoder utilization is not currently supported.
+			enc_util, _, ret := nvml.DeviceGetEncoderUtilization(device.device)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_encoder_util", device.tags, m.meta, map[string]interface{}{"value": float64(enc_util)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "%")
+					output <- y
+				}
 			}
 		}
 
-		dec_util, _, ret := nvml.DeviceGetDecoderUtilization(device)
-		if ret == nvml.SUCCESS {
-			_, skip = stringArrayContains(m.config.ExcludeMetrics, "nv_decoder_util")
-			y, err := lp.New("nv_decoder_util", tags, m.meta, map[string]interface{}{"value": float64(dec_util)}, time.Now())
-			if err == nil && !skip {
-				output <- y
+		if !device.excludeMetrics["nv_decoder_util"] {
+			// Retrieves the current utilization and sampling size in microseconds for the Decoder
+			//
+			// For Kepler or newer fully supported devices.
+			//
+			// Note: On MIG-enabled GPUs, querying decoder utilization is not currently supported.
+			dec_util, _, ret := nvml.DeviceGetDecoderUtilization(device.device)
+			if ret == nvml.SUCCESS {
+				y, err := lp.New("nv_decoder_util", device.tags, m.meta, map[string]interface{}{"value": float64(dec_util)}, time.Now())
+				if err == nil {
+					y.AddMeta("unit", "%")
+					output <- y
+				}
 			}
 		}
 	}

collectors/sampleMetric.go

@@ -0,0 +1,92 @@
+package collectors
+
+import (
+	"encoding/json"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+)
+
+// These are the fields we read from the JSON configuration
+type SampleCollectorConfig struct {
+	Interval string `json:"interval"`
+}
+
+// This contains all variables we need during execution and the variables
+// defined by metricCollector (name, init, ...)
+type SampleCollector struct {
+	metricCollector
+	config SampleTimerCollectorConfig // the configuration structure
+	meta   map[string]string          // default meta information
+	tags   map[string]string          // default tags
+}
+
+// Functions to implement MetricCollector interface
+// Init(...), Read(...), Close()
+// See: metricCollector.go
+
+// Init initializes the sample collector
+// Called once by the collector manager
+// All tags, meta data tags and metrics that do not change over the runtime should be set here
+func (m *SampleCollector) Init(config json.RawMessage) error {
+	var err error = nil
+	// Always set the name early in Init() to use it in cclog.Component* functions
+	m.name = "InternalCollector"
+	// This is for later use, also call it early
+	m.setup()
+	// Define meta information sent with each metric
+	// (Can also be dynamic or this is the basic set with extension through AddMeta())
+	m.meta = map[string]string{"source": m.name, "group": "SAMPLE"}
+	// Define tags sent with each metric
+	// The 'type' tag is always needed, it defines the granulatity of the metric
+	// node -> whole system
+	// socket -> CPU socket (requires socket ID as 'type-id' tag)
+	// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
+	m.tags = map[string]string{"type": "node"}
+	// Read in the JSON configuration
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			cclog.ComponentError(m.name, "Error reading config:", err.Error())
+			return err
+		}
+	}
+
+	// Set up everything that the collector requires during the Read() execution
+	// Check files required, test execution of some commands, create data structure
+	// for all topological entities (sockets, NUMA domains, ...)
+	// Return some useful error message in case of any failures
+
+	// Set this flag only if everything is initialized properly, all required files exist, ...
+	m.init = true
+	return err
+}
+
+// Read collects all metrics belonging to the sample collector
+// and sends them through the output channel to the collector manager
+func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	// Create a sample metric
+	timestamp := time.Now()
+
+	value := 1.0
+	// If you want to measure something for a specific amount of time, use interval
+	// start := readState()
+	// time.Sleep(interval)
+	// stop := readState()
+	// value = (stop - start) / interval.Seconds()
+
+	y, err := lp.New("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+	if err == nil {
+		// Send it to output channel
+		output <- y
+	}
+
+}
+
+// Close metric collector: close network connection, close files, close libraries, ...
+// Called once by the collector manager
+func (m *SampleCollector) Close() {
+	// Unset flag
+	m.init = false
+}

collectors/sampleTimerMetric.go

@@ -0,0 +1,122 @@
+package collectors
+
+import (
+	"encoding/json"
+	"sync"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+)
+
+// These are the fields we read from the JSON configuration
+type SampleTimerCollectorConfig struct {
+	Interval string `json:"interval"`
+}
+
+// This contains all variables we need during execution and the variables
+// defined by metricCollector (name, init, ...)
+type SampleTimerCollector struct {
+	metricCollector
+	wg       sync.WaitGroup             // sync group for management
+	done     chan bool                  // channel for management
+	meta     map[string]string          // default meta information
+	tags     map[string]string          // default tags
+	config   SampleTimerCollectorConfig // the configuration structure
+	interval time.Duration              // the interval parsed from configuration
+	ticker   *time.Ticker               // own timer
+	output   chan lp.CCMetric           // own internal output channel
+}
+
+func (m *SampleTimerCollector) Init(name string, config json.RawMessage) error {
+	var err error = nil
+	// Always set the name early in Init() to use it in cclog.Component* functions
+	m.name = "SampleTimerCollector"
+	// This is for later use, also call it early
+	m.setup()
+	// Define meta information sent with each metric
+	// (Can also be dynamic or this is the basic set with extension through AddMeta())
+	m.meta = map[string]string{"source": m.name, "group": "SAMPLE"}
+	// Define tags sent with each metric
+	// The 'type' tag is always needed, it defines the granulatity of the metric
+	// node -> whole system
+	// socket -> CPU socket (requires socket ID as 'type-id' tag)
+	// cpu -> single CPU hardware thread (requires cpu ID as 'type-id' tag)
+	m.tags = map[string]string{"type": "node"}
+	// Read in the JSON configuration
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			cclog.ComponentError(m.name, "Error reading config:", err.Error())
+			return err
+		}
+	}
+	// Parse the read interval duration
+	m.interval, err = time.ParseDuration(m.config.Interval)
+	if err != nil {
+		cclog.ComponentError(m.name, "Error parsing interval:", err.Error())
+		return err
+	}
+
+	// Storage for output channel
+	m.output = nil
+	// Mangement channel for the timer function.
+	m.done = make(chan bool)
+	// Create the own ticker
+	m.ticker = time.NewTicker(m.interval)
+
+	// Start the timer loop with return functionality by sending 'true' to the done channel
+	m.wg.Add(1)
+	go func() {
+		select {
+		case <-m.done:
+			// Exit the timer loop
+			cclog.ComponentDebug(m.name, "Closing...")
+			m.wg.Done()
+			return
+		case timestamp := <-m.ticker.C:
+			// This is executed every timer tick but we have to wait until the first
+			// Read() to get the output channel
+			if m.output != nil {
+				m.ReadMetrics(timestamp)
+			}
+		}
+	}()
+
+	// Set this flag only if everything is initialized properly, all required files exist, ...
+	m.init = true
+	return err
+}
+
+// This function is called at each interval timer tick
+func (m *SampleTimerCollector) ReadMetrics(timestamp time.Time) {
+	// Create a sample metric
+
+	value := 1.0
+
+	// If you want to measure something for a specific amout of time, use interval
+	// start := readState()
+	// time.Sleep(interval)
+	// stop := readState()
+	// value = (stop - start) / interval.Seconds()
+
+	y, err := lp.New("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
+	if err == nil && m.output != nil {
+		// Send it to output channel if we have a valid channel
+		m.output <- y
+	}
+}
+
+func (m *SampleTimerCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	// Capture output channel
+	m.output = output
+}
+
+func (m *SampleTimerCollector) Close() {
+	// Send signal to the timer loop to stop it
+	m.done <- true
+	// Wait until the timer loop is done
+	m.wg.Wait()
+	// Unset flag
+	m.init = false
+}

collectors/tempMetric.go

@@ -4,110 +4,227 @@ import (
 	"encoding/json"
 	"fmt"
 	"io/ioutil"
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-const HWMON_PATH = `/sys/class/hwmon`
+// See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html
+// /sys/class/hwmon/hwmon*/name -> coretemp
+// /sys/class/hwmon/hwmon*/temp*_label -> Core 0
+// /sys/class/hwmon/hwmon*/temp*_input -> 27800 = 27.8°C
+// /sys/class/hwmon/hwmon*/temp*_max -> 86000 = 86.0°C
+// /sys/class/hwmon/hwmon*/temp*_crit -> 100000 = 100.0°C
 
-type TempCollectorConfig struct {
-	ExcludeMetrics []string                     `json:"exclude_metrics"`
-	TagOverride    map[string]map[string]string `json:"tag_override"`
+type TempCollectorSensor struct {
+	name         string
+	label        string
+	metricName   string // Default: name_label
+	file         string
+	maxTempName  string
+	maxTemp      int64
+	critTempName string
+	critTemp     int64
+	tags         map[string]string
 }
 
 type TempCollector struct {
 	metricCollector
-	config TempCollectorConfig
+	config struct {
+		ExcludeMetrics     []string                     `json:"exclude_metrics"`
+		TagOverride        map[string]map[string]string `json:"tag_override"`
+		ReportMaxTemp      bool                         `json:"report_max_temperature"`
+		ReportCriticalTemp bool                         `json:"report_critical_temperature"`
+	}
+	sensors []*TempCollectorSensor
 }
 
 func (m *TempCollector) Init(config json.RawMessage) error {
+	// Check if already initialized
+	if m.init {
+		return nil
+	}
+
 	m.name = "TempCollector"
 	m.setup()
-	m.meta = map[string]string{"source": m.name, "group": "IPMI", "unit": "degC"}
 	if len(config) > 0 {
 		err := json.Unmarshal(config, &m.config)
 		if err != nil {
 			return err
 		}
 	}
+
+	m.meta = map[string]string{
+		"source": m.name,
+		"group":  "IPMI",
+		"unit":   "degC",
+	}
+
+	m.sensors = make([]*TempCollectorSensor, 0)
+
+	// Find all temperature sensor files
+	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)
+	}
+	if inputFiles == nil {
+		return fmt.Errorf("Unable to find any files with pattern '%s'", globPattern)
+	}
+
+	// Get sensor name for each temperature sensor file
+	for _, file := range inputFiles {
+		sensor := new(TempCollectorSensor)
+
+		// sensor name
+		nameFile := filepath.Join(filepath.Dir(file), "name")
+		name, err := ioutil.ReadFile(nameFile)
+		if err == nil {
+			sensor.name = strings.TrimSpace(string(name))
+		}
+
+		// sensor label
+		labelFile := strings.TrimSuffix(file, "_input") + "_label"
+		label, err := ioutil.ReadFile(labelFile)
+		if err == nil {
+			sensor.label = strings.TrimSpace(string(label))
+		}
+
+		// sensor metric name
+		switch {
+		case len(sensor.name) == 0 && len(sensor.label) == 0:
+			continue
+		case sensor.name == "coretemp" && strings.HasPrefix(sensor.label, "Core ") ||
+			sensor.name == "coretemp" && strings.HasPrefix(sensor.label, "Package id "):
+			sensor.metricName = "temp_" + sensor.label
+		case len(sensor.name) != 0 && len(sensor.label) != 0:
+			sensor.metricName = sensor.name + "_" + sensor.label
+		case len(sensor.name) != 0:
+			sensor.metricName = sensor.name
+		case len(sensor.label) != 0:
+			sensor.metricName = sensor.label
+		}
+		sensor.metricName = strings.ToLower(sensor.metricName)
+		sensor.metricName = strings.Replace(sensor.metricName, " ", "_", -1)
+		// Add temperature prefix, if required
+		if !strings.Contains(sensor.metricName, "temp") {
+			sensor.metricName = "temp_" + sensor.metricName
+		}
+
+		// Sensor file
+		sensor.file = file
+
+		// Sensor tags
+		sensor.tags = map[string]string{
+			"type": "node",
+		}
+
+		// Apply tag override configuration
+		for key, newtags := range m.config.TagOverride {
+			if strings.Contains(sensor.file, key) {
+				sensor.tags = newtags
+				break
+			}
+		}
+
+		// max temperature
+		if m.config.ReportMaxTemp {
+			maxTempFile := strings.TrimSuffix(file, "_input") + "_max"
+			if buffer, err := ioutil.ReadFile(maxTempFile); err == nil {
+				if x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64); err == nil {
+					sensor.maxTempName = strings.Replace(sensor.metricName, "temp", "max_temp", 1)
+					sensor.maxTemp = x / 1000
+				}
+			}
+		}
+
+		// critical temperature
+		if m.config.ReportCriticalTemp {
+			criticalTempFile := strings.TrimSuffix(file, "_input") + "_crit"
+			if buffer, err := ioutil.ReadFile(criticalTempFile); err == nil {
+				if x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64); err == nil {
+					sensor.critTempName = strings.Replace(sensor.metricName, "temp", "crit_temp", 1)
+					sensor.critTemp = x / 1000
+				}
+			}
+		}
+
+		m.sensors = append(m.sensors, sensor)
+	}
+
+	// Empty sensors map
+	if len(m.sensors) == 0 {
+		return fmt.Errorf("No temperature sensors found")
+	}
+
+	// Finished initialization
 	m.init = true
 	return nil
 }
 
-func get_hwmon_sensors() (map[string]map[string]string, error) {
-	var folders []string
-	var sensors map[string]map[string]string
-	sensors = make(map[string]map[string]string)
-	err := filepath.Walk(HWMON_PATH, func(p string, info os.FileInfo, err error) error {
-		if info.IsDir() {
-			return nil
-		}
-		folders = append(folders, p)
-		return nil
-	})
-	if err != nil {
-		return sensors, err
-	}
-
-	for _, f := range folders {
-		sensors[f] = make(map[string]string)
-		myp := fmt.Sprintf("%s/", f)
-		err := filepath.Walk(myp, func(path string, info os.FileInfo, err error) error {
-			dir, fname := filepath.Split(path)
-			if strings.Contains(fname, "temp") && strings.Contains(fname, "_input") {
-				namefile := fmt.Sprintf("%s/%s", dir, strings.Replace(fname, "_input", "_label", -1))
-				name, ierr := ioutil.ReadFile(namefile)
-				if ierr == nil {
-					sensors[f][strings.Replace(string(name), "\n", "", -1)] = path
-				}
-			}
-			return nil
-		})
-		if err != nil {
-			continue
-		}
-	}
-	return sensors, nil
-}
-
 func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
-	sensors, err := get_hwmon_sensors()
-	if err != nil {
-		return
-	}
-	for _, files := range sensors {
-		for name, file := range files {
-			tags := map[string]string{"type": "node"}
-			for key, newtags := range m.config.TagOverride {
-				if strings.Contains(file, key) {
-					tags = newtags
-					break
-				}
-			}
-			mname := strings.Replace(name, " ", "_", -1)
-			if !strings.Contains(mname, "temp") {
-				mname = fmt.Sprintf("temp_%s", mname)
-			}
-			buffer, err := ioutil.ReadFile(string(file))
-			if err != nil {
-				continue
-			}
-			x, err := strconv.ParseInt(strings.Replace(string(buffer), "\n", "", -1), 0, 64)
+	for _, sensor := range m.sensors {
+		// Read sensor file
+		buffer, err := ioutil.ReadFile(sensor.file)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to read file '%s': %v", sensor.file, err))
+			continue
+		}
+		x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64)
+		if err != nil {
+			cclog.ComponentError(
+				m.name,
+				fmt.Sprintf("Read(): Failed to convert temperature '%s' to int64: %v", buffer, err))
+			continue
+		}
+		x /= 1000
+		y, err := lp.New(
+			sensor.metricName,
+			sensor.tags,
+			m.meta,
+			map[string]interface{}{"value": x},
+			time.Now(),
+		)
+		if err == nil {
+			output <- y
+		}
+
+		// max temperature
+		if m.config.ReportMaxTemp && sensor.maxTemp != 0 {
+			y, err := lp.New(
+				sensor.maxTempName,
+				sensor.tags,
+				m.meta,
+				map[string]interface{}{"value": sensor.maxTemp},
+				time.Now(),
+			)
 			if err == nil {
-				y, err := lp.New(strings.ToLower(mname), tags, m.meta, map[string]interface{}{"value": int(float64(x) / 1000)}, time.Now())
-				if err == nil {
-					cclog.ComponentDebug(m.name, y)
-					output <- y
-				}
+				output <- y
+			}
+		}
+
+		// critical temperature
+		if m.config.ReportCriticalTemp && sensor.critTemp != 0 {
+			y, err := lp.New(
+				sensor.critTempName,
+				sensor.tags,
+				m.meta,
+				map[string]interface{}{"value": sensor.critTemp},
+				time.Now(),
+			)
+			if err == nil {
+				output <- y
 			}
 		}
 	}
+
 }
 
 func (m *TempCollector) Close() {

collectors/topprocsMetric.go

@@ -8,6 +8,7 @@ import (
 	"os/exec"
 	"strings"
 	"time"
+
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 

go.mod

@@ -14,7 +14,6 @@ require (
 require (
 	github.com/PaesslerAG/gval v1.1.2
 	github.com/golang/protobuf v1.5.2 // indirect
-	github.com/mattn/go-sqlite3 v1.14.11
 	github.com/nats-io/nats-server/v2 v2.7.0 // indirect
 	google.golang.org/protobuf v1.27.1 // indirect
 )

go.sum

@@ -54,8 +54,6 @@ github.com/mattn/go-colorable v0.1.8/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope
 github.com/mattn/go-isatty v0.0.8/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
 github.com/mattn/go-isatty v0.0.9/go.mod h1:YNRxwqDuOph6SZLI9vUUz6OYw3QyUt7WiY2yME+cCiQ=
 github.com/mattn/go-isatty v0.0.12/go.mod h1:cbi8OIDigv2wuxKPP5vlRcQ1OAZbq2CE4Kysco4FUpU=
-github.com/mattn/go-sqlite3 v1.14.11 h1:gt+cp9c0XGqe9S/wAHTL3n/7MqY+siPWgWJgqdsFrzQ=
-github.com/mattn/go-sqlite3 v1.14.11/go.mod h1:NyWgC/yNuGj7Q9rpYnZvas74GogHl5/Z4A/KQRfk6bU=
 github.com/minio/highwayhash v1.0.1 h1:dZ6IIu8Z14VlC0VpfKofAhCy74wu/Qb5gcn52yWoz/0=
 github.com/minio/highwayhash v1.0.1/go.mod h1:BQskDq+xkJ12lmlUUi7U0M5Swg3EWR+dLTk+kldvVxY=
 github.com/nats-io/jwt/v2 v2.2.1-0.20220113022732-58e87895b296 h1:vU9tpM3apjYlLLeY23zRWJ9Zktr5jp+mloR942LEOpY=

internal/ccMetric/ccMetric.go

@@ -2,239 +2,194 @@ package ccmetric
 
 import (
 	"fmt"
-	"sort"
 	"time"
 
+	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
+	write "github.com/influxdata/influxdb-client-go/v2/api/write"
 	lp "github.com/influxdata/line-protocol" // MIT license
 )
 
 // Most functions are derived from github.com/influxdata/line-protocol/metric.go
 // The metric type is extended with an extra meta information list re-using the Tag
 // type.
-
+//
+// See: https://docs.influxdata.com/influxdb/latest/reference/syntax/line-protocol/
 type ccMetric struct {
-	name   string
-	tags   []*lp.Tag
-	fields []*lp.Field
-	tm     time.Time
-	meta   []*lp.Tag
+	name   string                 // Measurement name
+	meta   map[string]string      // map of meta data tags
+	tags   map[string]string      // map of of tags
+	fields map[string]interface{} // map of of fields
+	tm     time.Time              // timestamp
 }
 
+// ccMetric access functions
 type CCMetric interface {
-	lp.MutableMetric
-	Name() string
-	AddTag(key, value string)
-	GetTag(key string) (string, bool)
-	HasTag(key string) bool
-	RemoveTag(key string)
-	Tags() map[string]string
-	TagList() []*lp.Tag
-	AddMeta(key, value string)
-	GetMeta(key string) (string, bool)
-	HasMeta(key string) bool
-	RemoveMeta(key string)
-	Meta() map[string]string
-	MetaList() []*lp.Tag
-	AddField(key string, value interface{})
-	GetField(key string) (interface{}, bool)
-	HasField(key string) bool
-	RemoveField(key string)
-	Fields() map[string]interface{}
-	FieldList() []*lp.Field
-	String() string
-	SetTime(t time.Time)
-}
-
-func (m *ccMetric) Meta() map[string]string {
-	meta := make(map[string]string, len(m.meta))
-	for _, m := range m.meta {
-		meta[m.Key] = m.Value
-	}
-	return meta
-}
-
-func (m *ccMetric) MetaList() []*lp.Tag {
-	return m.meta
+	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
+
+	Time() time.Time     // Get timestamp
+	SetTime(t time.Time) // Set timestamp
+
+	Tags() map[string]string                   // Map of tags
+	AddTag(key, value string)                  // Add a tag
+	GetTag(key string) (value string, ok bool) // Get a tag by its key
+	HasTag(key string) (ok bool)               // Check if a tag key is present
+	RemoveTag(key string)                      // Remove a tag by its key
+
+	Meta() map[string]string                    // Map of meta data tags
+	AddMeta(key, value string)                  // Add a meta data tag
+	GetMeta(key string) (value string, ok bool) // Get a meta data tab addressed by its key
+	HasMeta(key string) (ok bool)               // Check if a meta data key is present
+	RemoveMeta(key string)                      // Remove a meta data tag by its key
+
+	Fields() map[string]interface{}                   // Map of fields
+	AddField(key string, value interface{})           // Add a field
+	GetField(key string) (value interface{}, ok bool) // Get a field addressed by its key
+	HasField(key string) (ok bool)                    // Check if a field key is present
+	RemoveField(key string)                           // Remove a field addressed by its key
 }
 
+// String implements the stringer interface for data type ccMetric
 func (m *ccMetric) String() string {
-	return fmt.Sprintf("%s %v %v %v %d", m.name, m.Tags(), m.Meta(), m.Fields(), m.tm.UnixNano())
+	return fmt.Sprintf(
+		"Name: %s, Tags: %+v, Meta: %+v, fields: %+v, Timestamp: %d",
+		m.name, m.tags, m.meta, m.fields, m.tm.UnixNano(),
+	)
 }
 
+// ToLineProtocol generates influxDB line protocol for data type ccMetric
+func (m *ccMetric) ToPoint(metaAsTags 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
+}
+
+// ToLineProtocol generates influxDB line protocol for data type ccMetric
+func (m *ccMetric) ToLineProtocol(metaAsTags bool) string {
+
+	return write.PointToLineProtocol(
+		m.ToPoint(metaAsTags),
+		time.Nanosecond,
+	)
+}
+
+// Name returns the measurement name
 func (m *ccMetric) Name() string {
 	return m.name
 }
 
-func (m *ccMetric) Tags() map[string]string {
-	tags := make(map[string]string, len(m.tags))
-	for _, tag := range m.tags {
-		tags[tag.Key] = tag.Value
-	}
-	return tags
-}
-
-func (m *ccMetric) TagList() []*lp.Tag {
-	return m.tags
-}
-
-func (m *ccMetric) Fields() map[string]interface{} {
-	fields := make(map[string]interface{}, len(m.fields))
-	for _, field := range m.fields {
-		fields[field.Key] = field.Value
-	}
-
-	return fields
-}
-
-func (m *ccMetric) FieldList() []*lp.Field {
-	return m.fields
+// SetName sets the measurement name
+func (m *ccMetric) SetName(name string) {
+	m.name = name
 }
 
+// Time returns timestamp
 func (m *ccMetric) Time() time.Time {
 	return m.tm
 }
 
+// SetTime sets the timestamp
 func (m *ccMetric) SetTime(t time.Time) {
 	m.tm = t
 }
 
-func (m *ccMetric) HasTag(key string) bool {
-	for _, tag := range m.tags {
-		if tag.Key == key {
-			return true
-		}
-	}
-	return false
-}
-
-func (m *ccMetric) GetTag(key string) (string, bool) {
-	for _, tag := range m.tags {
-		if tag.Key == key {
-			return tag.Value, true
-		}
-	}
-	return "", false
-}
-
-func (m *ccMetric) RemoveTag(key string) {
-	for i, tag := range m.tags {
-		if tag.Key == key {
-			copy(m.tags[i:], m.tags[i+1:])
-			m.tags[len(m.tags)-1] = nil
-			m.tags = m.tags[:len(m.tags)-1]
-			return
-		}
-	}
+// Tags returns the the list of tags as key-value-mapping
+func (m *ccMetric) Tags() map[string]string {
+	return m.tags
 }
 
+// AddTag adds a tag (consisting of key and value) to the map of tags
 func (m *ccMetric) AddTag(key, value string) {
-	for i, tag := range m.tags {
-		if key > tag.Key {
-			continue
-		}
-
-		if key == tag.Key {
-			tag.Value = value
-			return
-		}
-
-		m.tags = append(m.tags, nil)
-		copy(m.tags[i+1:], m.tags[i:])
-		m.tags[i] = &lp.Tag{Key: key, Value: value}
-		return
-	}
-
-	m.tags = append(m.tags, &lp.Tag{Key: key, Value: value})
+	m.tags[key] = value
 }
 
-func (m *ccMetric) HasMeta(key string) bool {
-	for _, tag := range m.meta {
-		if tag.Key == key {
-			return true
-		}
-	}
-	return false
+// GetTag returns the tag with tag's key equal to <key>
+func (m *ccMetric) GetTag(key string) (string, bool) {
+	value, ok := m.tags[key]
+	return value, ok
 }
 
-func (m *ccMetric) GetMeta(key string) (string, bool) {
-	for _, tag := range m.meta {
-		if tag.Key == key {
-			return tag.Value, true
-		}
-	}
-	return "", false
+// HasTag checks if a tag with key equal to <key> is present in the list of tags
+func (m *ccMetric) HasTag(key string) bool {
+	_, ok := m.tags[key]
+	return ok
 }
 
-func (m *ccMetric) RemoveMeta(key string) {
-	for i, tag := range m.meta {
-		if tag.Key == key {
-			copy(m.meta[i:], m.meta[i+1:])
-			m.meta[len(m.meta)-1] = nil
-			m.meta = m.meta[:len(m.meta)-1]
-			return
-		}
-	}
+// RemoveTag removes the tag with tag's key equal to <key>
+func (m *ccMetric) RemoveTag(key string) {
+	delete(m.tags, key)
 }
 
+// Meta returns the meta data tags as key-value mapping
+func (m *ccMetric) Meta() map[string]string {
+	return m.meta
+}
+
+// AddMeta adds a meta data tag (consisting of key and value) to the map of meta data tags
 func (m *ccMetric) AddMeta(key, value string) {
-	for i, tag := range m.meta {
-		if key > tag.Key {
-			continue
-		}
-
-		if key == tag.Key {
-			tag.Value = value
-			return
-		}
-
-		m.meta = append(m.meta, nil)
-		copy(m.meta[i+1:], m.meta[i:])
-		m.meta[i] = &lp.Tag{Key: key, Value: value}
-		return
-	}
-
-	m.meta = append(m.meta, &lp.Tag{Key: key, Value: value})
+	m.meta[key] = value
 }
 
+// GetMeta returns the meta data tag with meta data's key equal to <key>
+func (m *ccMetric) GetMeta(key string) (string, bool) {
+	value, ok := m.meta[key]
+	return value, ok
+}
+
+// HasMeta checks if a meta data tag with meta data's key equal to <key> is present in the map of meta data tags
+func (m *ccMetric) HasMeta(key string) bool {
+	_, ok := m.meta[key]
+	return ok
+}
+
+// RemoveMeta removes the meta data tag with tag's key equal to <key>
+func (m *ccMetric) RemoveMeta(key string) {
+	delete(m.meta, key)
+}
+
+// Fields returns the list of fields as key-value-mapping
+func (m *ccMetric) Fields() map[string]interface{} {
+	return m.fields
+}
+
+// AddField adds a field (consisting of key and value) to the map of fields
 func (m *ccMetric) AddField(key string, value interface{}) {
-	for i, field := range m.fields {
-		if key == field.Key {
-			m.fields[i] = &lp.Field{Key: key, Value: convertField(value)}
-			return
-		}
-	}
-	m.fields = append(m.fields, &lp.Field{Key: key, Value: convertField(value)})
+	m.fields[key] = value
 }
 
+// GetField returns the field with field's key equal to <key>
 func (m *ccMetric) GetField(key string) (interface{}, bool) {
-	for _, field := range m.fields {
-		if field.Key == key {
-			return field.Value, true
-		}
-	}
-	return "", false
+	v, ok := m.fields[key]
+	return v, ok
 }
 
+// HasField checks if a field with field's key equal to <key> is present in the map of fields
 func (m *ccMetric) HasField(key string) bool {
-	for _, field := range m.fields {
-		if field.Key == key {
-			return true
-		}
-	}
-	return false
+	_, ok := m.fields[key]
+	return ok
 }
 
+// RemoveField removes the field with field's key equal to <key>
+// from the map of fields
 func (m *ccMetric) RemoveField(key string) {
-	for i, field := range m.fields {
-		if field.Key == key {
-			copy(m.fields[i:], m.fields[i+1:])
-			m.fields[len(m.fields)-1] = nil
-			m.fields = m.fields[:len(m.fields)-1]
-			return
-		}
-	}
+	delete(m.fields, key)
 }
 
+// New creates a new measurement point
 func New(
 	name string,
 	tags map[string]string,
@@ -244,85 +199,79 @@ func New(
 ) (CCMetric, error) {
 	m := &ccMetric{
 		name:   name,
-		tags:   nil,
-		fields: nil,
+		tags:   make(map[string]string, len(tags)),
+		meta:   make(map[string]string, len(meta)),
+		fields: make(map[string]interface{}, len(fields)),
 		tm:     tm,
-		meta:   nil,
 	}
 
-	if len(tags) > 0 {
-		m.tags = make([]*lp.Tag, 0, len(tags))
-		for k, v := range tags {
-			m.tags = append(m.tags,
-				&lp.Tag{Key: k, Value: v})
-		}
-		sort.Slice(m.tags, func(i, j int) bool { return m.tags[i].Key < m.tags[j].Key })
+	// deep copy tags, meta data tags and fields
+	for k, v := range tags {
+		m.tags[k] = v
 	}
-
-	if len(meta) > 0 {
-		m.meta = make([]*lp.Tag, 0, len(meta))
-		for k, v := range meta {
-			m.meta = append(m.meta,
-				&lp.Tag{Key: k, Value: v})
-		}
-		sort.Slice(m.meta, func(i, j int) bool { return m.meta[i].Key < m.meta[j].Key })
+	for k, v := range meta {
+		m.meta[k] = v
 	}
-
-	if len(fields) > 0 {
-		m.fields = make([]*lp.Field, 0, len(fields))
-		for k, v := range fields {
-			v := convertField(v)
-			if v == nil {
-				continue
-			}
-			m.AddField(k, v)
+	for k, v := range fields {
+		v := convertField(v)
+		if v == nil {
+			continue
 		}
+		m.fields[k] = v
 	}
 
 	return m, nil
 }
 
-func FromMetric(other CCMetric) CCMetric {
+// FromMetric copies the metric <other>
+func FromMetric(other ccMetric) CCMetric {
 	m := &ccMetric{
 		name:   other.Name(),
-		tags:   make([]*lp.Tag, len(other.TagList())),
-		fields: make([]*lp.Field, len(other.FieldList())),
-		meta:   make([]*lp.Tag, len(other.MetaList())),
+		tags:   make(map[string]string, len(other.tags)),
+		meta:   make(map[string]string, len(other.meta)),
+		fields: make(map[string]interface{}, len(other.fields)),
 		tm:     other.Time(),
 	}
 
-	for i, tag := range other.TagList() {
-		m.tags[i] = &lp.Tag{Key: tag.Key, Value: tag.Value}
+	// deep copy tags, meta data tags and fields
+	for key, value := range other.tags {
+		m.tags[key] = value
 	}
-	for i, s := range other.MetaList() {
-		m.meta[i] = &lp.Tag{Key: s.Key, Value: s.Value}
+	for key, value := range other.meta {
+		m.meta[key] = value
 	}
-
-	for i, field := range other.FieldList() {
-		m.fields[i] = &lp.Field{Key: field.Key, Value: field.Value}
+	for key, value := range other.fields {
+		m.fields[key] = value
 	}
 	return m
 }
 
+// FromInfluxMetric copies the influxDB line protocol metric <other>
 func FromInfluxMetric(other lp.Metric) CCMetric {
 	m := &ccMetric{
 		name:   other.Name(),
-		tags:   make([]*lp.Tag, len(other.TagList())),
-		fields: make([]*lp.Field, len(other.FieldList())),
-		meta:   make([]*lp.Tag, 0),
+		tags:   make(map[string]string),
+		meta:   make(map[string]string),
+		fields: make(map[string]interface{}),
 		tm:     other.Time(),
 	}
 
-	for i, tag := range other.TagList() {
-		m.tags[i] = &lp.Tag{Key: tag.Key, Value: tag.Value}
+	// deep copy tags and fields
+	for _, otherTag := range other.TagList() {
+		m.tags[otherTag.Key] = otherTag.Value
 	}
-
-	for i, field := range other.FieldList() {
-		m.fields[i] = &lp.Field{Key: field.Key, Value: field.Value}
+	for _, otherField := range other.FieldList() {
+		m.fields[otherField.Key] = otherField.Value
 	}
 	return m
 }
 
+// convertField converts data types of fields by the following schemata:
+//                         *float32, *float64,                      float32, float64 -> float64
+//  *int,  *int8,  *int16,   *int32,   *int64,  int,  int8,  int16,   int32,   int64 ->   int64
+// *uint, *uint8, *uint16,  *uint32,  *uint64, uint, uint8, uint16,  uint32,  uint64 ->  uint64
+// *[]byte, *string,                           []byte, string                        -> string
+// *bool,                                      bool                                  -> bool
 func convertField(v interface{}) interface{} {
 	switch v := v.(type) {
 	case float64:

internal/ccTopology/ccTopology.go

@@ -6,12 +6,17 @@ import (
 	"log"
 	"os"
 	"path/filepath"
+	"regexp"
 	"strconv"
 	"strings"
 
 	cclogger "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 )
 
+const SYSFS_NUMABASE = `/sys/devices/system/node`
+const SYSFS_CPUBASE = `/sys/devices/system/cpu`
+const PROCFS_CPUINFO = `/proc/cpuinfo`
+
 // intArrayContains scans an array of ints if the value str is present in the array
 // If the specified value is found, the corresponding array index is returned.
 // The bool value is used to signal success or failure
@@ -24,20 +29,26 @@ func intArrayContains(array []int, str int) (int, bool) {
 	return -1, false
 }
 
-// stringArrayContains scans an array of strings if the value str is present in the array
-// If the specified value is found, the corresponding array index is returned.
-// The bool value is used to signal success or failure
-// func stringArrayContains(array []string, str string) (int, bool) {
-// 	for i, a := range array {
-// 		if a == str {
-// 			return i, true
-// 		}
-// 	}
-// 	return -1, false
-// }
+func fileToInt(path string) int {
+	buffer, err := ioutil.ReadFile(path)
+	if err != nil {
+		log.Print(err)
+		cclogger.ComponentError("ccTopology", "Reading", path, ":", err.Error())
+		return -1
+	}
+	sbuffer := strings.Replace(string(buffer), "\n", "", -1)
+	var id int64
+	//_, err = fmt.Scanf("%d", sbuffer, &id)
+	id, err = strconv.ParseInt(sbuffer, 10, 32)
+	if err != nil {
+		cclogger.ComponentError("ccTopology", "Parsing", path, ":", sbuffer, err.Error())
+		return -1
+	}
+	return int(id)
+}
 
 func SocketList() []int {
-	buffer, err := ioutil.ReadFile("/proc/cpuinfo")
+	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
 	if err != nil {
 		log.Print(err)
 		return nil
@@ -62,13 +73,13 @@ func SocketList() []int {
 }
 
 func CpuList() []int {
-	buffer, err := ioutil.ReadFile("/proc/cpuinfo")
+	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
 	if err != nil {
 		log.Print(err)
 		return nil
 	}
 	ll := strings.Split(string(buffer), "\n")
-	var cpulist []int
+	cpulist := make([]int, 0)
 	for _, line := range ll {
 		if strings.HasPrefix(line, "processor") {
 			lv := strings.Fields(line)
@@ -86,6 +97,81 @@ func CpuList() []int {
 	return cpulist
 }
 
+func CoreList() []int {
+	buffer, err := ioutil.ReadFile(string(PROCFS_CPUINFO))
+	if err != nil {
+		log.Print(err)
+		return nil
+	}
+	ll := strings.Split(string(buffer), "\n")
+	corelist := make([]int, 0)
+	for _, line := range ll {
+		if strings.HasPrefix(line, "core id") {
+			lv := strings.Fields(line)
+			id, err := strconv.ParseInt(lv[3], 10, 32)
+			if err != nil {
+				log.Print(err)
+				return corelist
+			}
+			_, found := intArrayContains(corelist, int(id))
+			if !found {
+				corelist = append(corelist, int(id))
+			}
+		}
+	}
+	return corelist
+}
+
+func NumaNodeList() []int {
+	numaList := make([]int, 0)
+	globPath := filepath.Join(string(SYSFS_NUMABASE), "node*")
+	regexPath := filepath.Join(string(SYSFS_NUMABASE), "node(\\d+)")
+	regex := regexp.MustCompile(regexPath)
+	files, err := filepath.Glob(globPath)
+	if err != nil {
+		cclogger.ComponentError("CCTopology", "NumaNodeList", err.Error())
+	}
+	for _, f := range files {
+		if !regex.MatchString(f) {
+			continue
+		}
+		finfo, err := os.Lstat(f)
+		if err != nil {
+			continue
+		}
+		if !finfo.IsDir() {
+			continue
+		}
+		matches := regex.FindStringSubmatch(f)
+		if len(matches) == 2 {
+			id, err := strconv.Atoi(matches[1])
+			if err == nil {
+				if _, found := intArrayContains(numaList, id); !found {
+					numaList = append(numaList, id)
+				}
+			}
+		}
+
+	}
+	return numaList
+}
+
+func DieList() []int {
+	cpulist := CpuList()
+	dielist := make([]int, 0)
+	for _, c := range cpulist {
+		diepath := filepath.Join(string(SYSFS_CPUBASE), fmt.Sprintf("cpu%d", c), "topology/die_id")
+		dieid := fileToInt(diepath)
+		if dieid > 0 {
+			_, found := intArrayContains(dielist, int(dieid))
+			if !found {
+				dielist = append(dielist, int(dieid))
+			}
+		}
+	}
+	return dielist
+}
+
 type CpuEntry struct {
 	Cpuid      int
 	SMT        int
@@ -101,7 +187,7 @@ func CpuData() []CpuEntry {
 		buffer, err := ioutil.ReadFile(path)
 		if err != nil {
 			log.Print(err)
-			cclogger.ComponentError("ccTopology", "Reading", path, ":", err.Error())
+			//cclogger.ComponentError("ccTopology", "Reading", path, ":", err.Error())
 			return -1
 		}
 		sbuffer := strings.Replace(string(buffer), "\n", "", -1)
@@ -129,14 +215,14 @@ func CpuData() []CpuEntry {
 	getSMT := func(cpuid int, basepath string) int {
 		buffer, err := ioutil.ReadFile(fmt.Sprintf("%s/thread_siblings_list", basepath))
 		if err != nil {
-			log.Print(err)
+			cclogger.ComponentError("CCTopology", "CpuData:getSMT", err.Error())
 		}
 		threadlist := make([]int, 0)
 		sbuffer := strings.Replace(string(buffer), "\n", "", -1)
 		for _, x := range strings.Split(sbuffer, ",") {
 			id, err := strconv.ParseInt(x, 10, 32)
 			if err != nil {
-				log.Print(err)
+				cclogger.ComponentError("CCTopology", "CpuData:getSMT", err.Error())
 			}
 			threadlist = append(threadlist, int(id))
 		}
@@ -149,18 +235,22 @@ func CpuData() []CpuEntry {
 	}
 
 	getNumaDomain := func(basepath string) int {
-		files, err := filepath.Glob(fmt.Sprintf("%s/node*", basepath))
+		globPath := filepath.Join(basepath, "node*")
+		regexPath := filepath.Join(basepath, "node(\\d+)")
+		regex := regexp.MustCompile(regexPath)
+		files, err := filepath.Glob(globPath)
 		if err != nil {
-			log.Print(err)
+			cclogger.ComponentError("CCTopology", "CpuData:getNumaDomain", err.Error())
 		}
 		for _, f := range files {
 			finfo, err := os.Lstat(f)
-			if err == nil && (finfo.IsDir() || finfo.Mode()&os.ModeSymlink != 0) {
-				var id int
-				parts := strings.Split(f, "/")
-				_, err = fmt.Scanf("node%d", parts[len(parts)-1], &id)
-				if err == nil {
-					return id
+			if err == nil && finfo.IsDir() {
+				matches := regex.FindStringSubmatch(f)
+				if len(matches) == 2 {
+					id, err := strconv.Atoi(matches[1])
+					if err == nil {
+						return id
+					}
 				}
 			}
 		}
@@ -177,19 +267,24 @@ func CpuData() []CpuEntry {
 		centry.Die = -1
 		centry.Core = -1
 		// Set base directory for topology lookup
-		base := fmt.Sprintf("/sys/devices/system/cpu/cpu%d/topology", centry.Cpuid)
+		cpustr := fmt.Sprintf("cpu%d", centry.Cpuid)
+		base := filepath.Join("/sys/devices/system/cpu", cpustr)
+		topoBase := filepath.Join(base, "topology")
 
 		// Lookup CPU core id
-		centry.Core = getCore(base)
+		centry.Core = getCore(topoBase)
 
 		// Lookup CPU socket id
-		centry.Socket = getSocket(base)
+		centry.Socket = getSocket(topoBase)
 
 		// Lookup CPU die id
-		centry.Die = getDie(base)
+		centry.Die = getDie(topoBase)
+		if centry.Die < 0 {
+			centry.Die = centry.Socket
+		}
 
 		// Lookup SMT thread id
-		centry.SMT = getSMT(centry.Cpuid, base)
+		centry.SMT = getSMT(centry.Cpuid, topoBase)
 
 		// Lookup NUMA domain id
 		centry.Numadomain = getNumaDomain(base)
@@ -203,35 +298,41 @@ type CpuInformation struct {
 	SMTWidth       int
 	NumSockets     int
 	NumDies        int
+	NumCores       int
 	NumNumaDomains int
 }
 
 func CpuInfo() CpuInformation {
 	var c CpuInformation
 
-	smt := 0
-	numa := 0
-	die := 0
-	socket := 0
+	smtList := make([]int, 0)
+	numaList := make([]int, 0)
+	dieList := make([]int, 0)
+	socketList := make([]int, 0)
+	coreList := make([]int, 0)
 	cdata := CpuData()
 	for _, d := range cdata {
-		if d.SMT > smt {
-			smt = d.SMT
+		if _, ok := intArrayContains(smtList, d.SMT); !ok {
+			smtList = append(smtList, d.SMT)
 		}
-		if d.Numadomain > numa {
-			numa = d.Numadomain
+		if _, ok := intArrayContains(numaList, d.Numadomain); !ok {
+			numaList = append(numaList, d.Numadomain)
 		}
-		if d.Die > die {
-			die = d.Die
+		if _, ok := intArrayContains(dieList, d.Die); !ok {
+			dieList = append(dieList, d.Die)
 		}
-		if d.Socket > socket {
-			socket = d.Socket
+		if _, ok := intArrayContains(socketList, d.Socket); !ok {
+			socketList = append(socketList, d.Socket)
+		}
+		if _, ok := intArrayContains(coreList, d.Core); !ok {
+			coreList = append(coreList, d.Core)
 		}
 	}
-	c.NumNumaDomains = numa + 1
-	c.SMTWidth = smt + 1
-	c.NumDies = die + 1
-	c.NumSockets = socket + 1
+	c.NumNumaDomains = len(numaList)
+	c.SMTWidth = len(smtList)
+	c.NumDies = len(dieList)
+	c.NumCores = len(coreList)
+	c.NumSockets = len(socketList)
 	c.NumHWthreads = len(cdata)
 	return c
 }
@@ -275,3 +376,47 @@ func GetCpuCore(cpuid int) int {
 	}
 	return -1
 }
+
+func GetSocketCpus(socket int) []int {
+	all := CpuData()
+	cpulist := make([]int, 0)
+	for _, d := range all {
+		if d.Socket == socket {
+			cpulist = append(cpulist, d.Cpuid)
+		}
+	}
+	return cpulist
+}
+
+func GetNumaDomainCpus(domain int) []int {
+	all := CpuData()
+	cpulist := make([]int, 0)
+	for _, d := range all {
+		if d.Numadomain == domain {
+			cpulist = append(cpulist, d.Cpuid)
+		}
+	}
+	return cpulist
+}
+
+func GetDieCpus(die int) []int {
+	all := CpuData()
+	cpulist := make([]int, 0)
+	for _, d := range all {
+		if d.Die == die {
+			cpulist = append(cpulist, d.Cpuid)
+		}
+	}
+	return cpulist
+}
+
+func GetCoreCpus(core int) []int {
+	all := CpuData()
+	cpulist := make([]int, 0)
+	for _, d := range all {
+		if d.Core == core {
+			cpulist = append(cpulist, d.Cpuid)
+		}
+	}
+	return cpulist
+}

internal/metricAggregator/README.md

@@ -0,0 +1,38 @@
+# The MetricAggregator
+
+In some cases, further combination of metrics or raw values is required. For that strings like `foo + 1` with runtime dependent `foo` need to be evaluated. The MetricAggregator relies on the [`gval`](https://github.com/PaesslerAG/gval) Golang package to perform all expression evaluation. The `gval` package provides the basic arithmetic operations but the MetricAggregator defines additional ones.
+
+**Note**: To get an impression which expressions can be handled by `gval`, see its [README](https://github.com/PaesslerAG/gval/blob/master/README.md)
+
+## Simple expression evaluation
+
+For simple expression evaluation, the MetricAggregator provides two function for different use-cases:
+- `EvalBoolCondition(expression string, params map[string]interface{}`: Used by the MetricRouter to match metrics like `metric.Name() == 'mymetric'`
+- `EvalFloat64Condition(expression string, params map[string]interface{})`: Used by the MetricRouter and LikwidCollector to derive new values like `(PMC0+PMC1)/PMC3`
+
+## MetricAggregator extensions for `gval`
+
+The MetricAggregator provides these functions additional to the `Full` language in `gval`:
+- `sum(array)`: Sum up values in an array like `sum(values)`
+- `min(array)`: Get the minimum value in an array like `min(values)`
+- `avg(array)`: Get the mean value in an array like `avg(values)`
+- `mean(array)`: Get the mean value in an array like `mean(values)`
+- `max(array)`: Get the maximum value in an array like `max(values)`
+- `len(array)`: Get the length of an array like `len(values)`
+- `median(array)`: Get the median value in an array like `mean(values)`
+- `in`: Check existence in an array like `0 in getCpuList()` to check whether there is an entry `0`. Also substring matching works like `temp in metric.Name()`
+- `match`: Regular-expression matching like `match('temp_cores_%d+', metric.Name())`. **Note** all `\` in an regex has to be replaced with `%`
+- `getCpuCore(cpuid)`: For a CPU id, the the corresponding CPU core id like `getCpuCore(0)`
+- `getCpuSocket(cpuid)`: For a CPU id, the the corresponding CPU socket id
+- `getCpuNuma(cpuid)`: For a CPU id, the the corresponding NUMA domain id
+- `getCpuDie(cpuid)`: For a CPU id, the the corresponding CPU die id
+- `getSockCpuList(sockid)`: For a given CPU socket id, the list of CPU ids is returned like the CPUs on socket 1 `getSockCpuList(1)`
+- `getNumaCpuList(numaid)`: For a given NUMA node id, the list of CPU ids is returned
+- `getDieCpuList(dieid)`: For a given CPU die id, the list of CPU ids is returned
+- `getCoreCpuList(coreid)`: For a given CPU core id, the list of CPU ids is returned
+- `getCpuList`: Get the list of all CPUs
+
+## Limitations
+
+- Since the metrics are written in JSON files which do not allow `""` without proper escaping inside of JSON strings, you have to use `''` for strings.
+- Since `\` is interpreted by JSON as escape character, it cannot be used in metrics. But it is required to write regular expressions. So instead of `/`, use `%` and the MetricAggregator replaces them after reading the JSON file.

internal/metricAggregator/metricAggregator.go

@@ -1,10 +1,12 @@
-package metricRouter
+package metricAggregator
 
 import (
 	"context"
 	"fmt"
+	"math"
 	"os"
 	"strings"
+	"sync"
 	"time"
 
 	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
@@ -15,7 +17,7 @@ import (
 	"github.com/PaesslerAG/gval"
 )
 
-type metricAggregatorIntervalConfig struct {
+type MetricAggregatorIntervalConfig struct {
 	Name      string            `json:"name"`     // Metric name for the new metric
 	Function  string            `json:"function"` // Function to apply on the metric
 	Condition string            `json:"if"`       // Condition for applying function
@@ -26,7 +28,7 @@ type metricAggregatorIntervalConfig struct {
 }
 
 type metricAggregator struct {
-	functions []*metricAggregatorIntervalConfig
+	functions []*MetricAggregatorIntervalConfig
 	constants map[string]interface{}
 	language  gval.Language
 	output    chan lp.CCMetric
@@ -61,10 +63,20 @@ var metricCacheLanguage = gval.NewLanguage(
 	gval.Function("getCpuList", getCpuListOfNode),
 	gval.Function("getCpuListOfType", getCpuListOfType),
 )
+var language gval.Language = gval.NewLanguage(
+	gval.Full(),
+	metricCacheLanguage,
+)
+var evaluables = struct {
+	mapping map[string]gval.Evaluable
+	mutex   sync.Mutex
+}{
+	mapping: make(map[string]gval.Evaluable),
+}
 
 func (c *metricAggregator) Init(output chan lp.CCMetric) error {
 	c.output = output
-	c.functions = make([]*metricAggregatorIntervalConfig, 0)
+	c.functions = make([]*MetricAggregatorIntervalConfig, 0)
 	c.constants = make(map[string]interface{})
 
 	// add constants like hostname, numSockets, ... to constants list
@@ -84,7 +96,7 @@ func (c *metricAggregator) Init(output chan lp.CCMetric) error {
 	c.constants["smtWidth"] = cinfo.SMTWidth
 
 	c.language = gval.NewLanguage(
-		gval.Base(),
+		gval.Full(),
 		metricCacheLanguage,
 	)
 
@@ -245,15 +257,16 @@ func (c *metricAggregator) AddAggregation(name, function, condition string, tags
 			return nil
 		}
 	}
-	var agg metricAggregatorIntervalConfig
-	agg.Name = name
-	agg.Condition = newcond
-	agg.gvalCond = gvalCond
-	agg.Function = newfunc
-	agg.gvalFunc = gvalFunc
-	agg.Tags = tags
-	agg.Meta = meta
-	c.functions = append(c.functions, &agg)
+	agg := &MetricAggregatorIntervalConfig{
+		Name:      name,
+		Condition: newcond,
+		gvalCond:  gvalCond,
+		Function:  newfunc,
+		gvalFunc:  gvalFunc,
+		Tags:      tags,
+		Meta:      meta,
+	}
+	c.functions = append(c.functions, agg)
 	return nil
 }
 
@@ -281,6 +294,50 @@ func (c *metricAggregator) AddFunction(name string, function func(args ...interf
 	c.language = gval.NewLanguage(c.language, gval.Function(name, function))
 }
 
+func EvalBoolCondition(condition string, params map[string]interface{}) (bool, error) {
+	evaluables.mutex.Lock()
+	evaluable, ok := evaluables.mapping[condition]
+	evaluables.mutex.Unlock()
+	if !ok {
+		newcond :=
+			strings.ReplaceAll(
+				strings.ReplaceAll(
+					condition, "'", "\""), "%", "\\")
+		var err error
+		evaluable, err = language.NewEvaluable(newcond)
+		if err != nil {
+			return false, err
+		}
+		evaluables.mutex.Lock()
+		evaluables.mapping[condition] = evaluable
+		evaluables.mutex.Unlock()
+	}
+	value, err := evaluable.EvalBool(context.Background(), params)
+	return value, err
+}
+
+func EvalFloat64Condition(condition string, params map[string]interface{}) (float64, error) {
+	evaluables.mutex.Lock()
+	evaluable, ok := evaluables.mapping[condition]
+	evaluables.mutex.Unlock()
+	if !ok {
+		newcond :=
+			strings.ReplaceAll(
+				strings.ReplaceAll(
+					condition, "'", "\""), "%", "\\")
+		var err error
+		evaluable, err = language.NewEvaluable(newcond)
+		if err != nil {
+			return math.NaN(), err
+		}
+		evaluables.mutex.Lock()
+		evaluables.mapping[condition] = evaluable
+		evaluables.mutex.Unlock()
+	}
+	value, err := evaluable.EvalFloat64(context.Background(), params)
+	return value, err
+}
+
 func NewAggregator(output chan lp.CCMetric) (MetricAggregator, error) {
 	a := new(metricAggregator)
 	err := a.Init(output)

internal/metricAggregator/metricAggregatorFunctions.go

@@ -1,4 +1,4 @@
-package metricRouter
+package metricAggregator
 
 import (
 	"errors"

internal/metricRouter/README.md

@@ -6,6 +6,8 @@ The CCMetric router sits in between the collectors and the sinks and can be used
 
 ```json
 {
+    "num_cache_intervals" : 1,
+    "interval_timestamp" : true,
     "add_tags" : [
         {
             "key" : "cluster",
@@ -25,16 +27,58 @@ The CCMetric router sits in between the collectors and the sinks and can be used
             "if" : "*"
         }
     ],
-    "interval_timestamp" : true
+    "interval_aggregates" : [
+        {
+            "name" : "temp_cores_avg",
+            "if" : "match('temp_core_%d+', metric.Name())",
+            "function" : "avg(values)",
+            "tags" : {
+                "type" : "node"
+            },
+            "meta" : {
+                "group": "IPMI",
+                "unit": "degC",
+                "source": "TempCollector"
+            }
+        }
+    ],
+    "drop_metrics" : [
+        "not_interesting_metric_at_all"
+    ],
+    "drop_metrics_if" : [
+        "match('temp_core_%d+', metric.Name())"
+    ],
+    "rename_metrics" : {
+        "metric_12345" : "mymetric"
+    }
 }
 ```
 
 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.
+# The `interval_timestamp` option
 
-# Conditional manipulation of tags
+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.
 
-The `if` setting allows conditional testing of a single metric like in the example:
+# The `num_cache_intervals` option
 
+If the MetricRouter should buffer metrics of intervals in a MetricCache, this option specifies the number of past intervals that should be kept. If `num_cache_intervals = 0`, the cache is disabled. With `num_cache_intervals = 1`, only the metrics of the last interval are buffered.
+
+A `num_cache_intervals > 0` is required to use the `interval_aggregates` option.
+
+# 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`
+
+```json
+{
+  "oldname" : "newname",
+  "clock_mhz" : "clock"
+}
+```
+
+# Conditional manipulation of tags (`add_tags` and `del_tags`)
+
+Common config format:
 ```json
 {
     "key" : "test",
@@ -43,8 +87,131 @@ The `if` setting allows conditional testing of a single metric like in the examp
 }
 ```
 
-If the CCMetric name is equal to 'temp_package_id_0', it adds an additional tag `test=testing` to the metric.
+## The `del_tags` option
 
-In order to match all metrics, you can use `*`, so in order to add a flag per default, like the `cluster=testcluster` tag in the example.
+The collectors are free to add whatever `key=value` pair to the metric tags (although the usage of tags should be minimized). If you want to delete a tag afterwards, you can do that. When the `if` condition matches on a metric, the `key` is removed from the metric's tags.
+
+If you want to remove a tag for all metrics, use the condition wildcard `*`. The `value` field can be omitted in the `del_tags` case.
+
+Never delete tags:
+- `hostname`
+- `type`
+- `type-id`
+
+## The `add_tags` option
+
+In some cases, metrics should be tagged or an existing tag changed based on some condition. This can be done in the `add_tags` section. When the `if` condition evaluates to `true`, the tag `key` is added or gets changed to the new `value`.
+
+If the CCMetric name is equal to `temp_package_id_0`, it adds an additional tag `test=testing` to the metric.
+
+For this metric, a more useful example would be:
+
+```json
+[
+  {
+    "key" : "type",
+    "value" : "socket",
+    "if" : "name == 'temp_package_id_0'"
+  },
+  {
+    "key" : "type-id",
+    "value" : "0",
+    "if" : "name == 'temp_package_id_0'"
+  },
+]
+```
+
+The metric `temp_package_id_0` corresponds to the tempature of the first CPU socket (=package). With the above configuration, the tags would reflect that because commonly the [TempCollector](../../collectors/tempMetric.md) submits only `node` metrics.
+
+In order to match all metrics, you can use `*`, so in order to add a flag per default. This is useful to attached system-specific tags like `cluster=testcluster`:
+
+```json
+{
+    "key" : "cluster",
+    "value" : "testcluster",
+    "if" : "*"
+}
+```
+
+# Dropping metrics
+
+In some cases, you want to drop a metric and don't get it forwarded to the sinks. There are two options based on the required specification:
+- Based only on the metric name -> `drop_metrics` section
+- An evaluable condition with more overhead -> `drop_metrics_if` section
+
+## The `drop_metrics` section
+
+The argument is a list of metric names. No futher checks are performed, only a comparison of the metric name
+
+```json
+{
+  "drop_metrics" : [
+      "drop_metric_1",
+      "drop_metric_2"
+  ]
+}
+```
+
+The example drops all metrics with the name `drop_metric_1` and `drop_metric_2`.
+
+## The `drop_metrics_if` section
+
+This option takes a list of evaluable conditions and performs them one after the other on **all** metrics incoming from the collectors and the metric cache (aka `interval_aggregates`).
+
+```json
+{
+  "drop_metrics_if" : [
+      "match('drop_metric_%d+', name)",
+      "match('cpu', type) && type-id == 0"
+  ]
+}
+```
+The first line is comparable with the example in `drop_metrics`, it drops all metrics starting with `drop_metric_` and ending with a number. The second line drops all metrics of the first hardware thread (**not** recommended)
 
 
+# Aggregate metric values of the current interval with the `interval_aggregates` option
+
+**Note:** `interval_aggregates` works only if `num_cache_intervals` > 0
+
+In some cases, you need to derive new metrics based on the metrics arriving during an interval. This can be done in the `interval_aggregates` section. The logic is similar to the other metric manipulation and filtering options. A cache stores all metrics that arrive during an interval. At the beginning of the *next* interval, the list of metrics is submitted to the MetricAggregator. It derives new metrics and submits them back to the MetricRouter, so they are sent in the next interval but have the timestamp of the previous interval beginning.
+
+```json
+"interval_aggregates" : [
+  {
+    "name" : "new_metric_name",
+    "if" : "match('sub_metric_%d+', metric.Name())",
+    "function" : "avg(values)",
+    "tags" : {
+      "key" : "value",
+      "type" : "node"
+    },
+    "meta" : {
+      "key" : "value",
+      "group": "IPMI",
+      "unit": "<copy>",
+    }
+  }
+]
+```
+
+The above configuration, collects all metric values for metrics evaluating `if` to `true`. Afterwards it calculates the average `avg` of the `values` (list of all metrics' field `value`) and creates a new CCMetric with the name `new_metric_name` and adds the tags in `tags` and the meta information in `meta`. The special value `<copy>` searches the input metrics and copies the value of the first match of `key` to the new CCMetric.
+
+If you are not interested in the input metrics `sub_metric_%d+` at all, you can add the same condition used here to the `drop_metrics_if` section to drop them.
+
+Use cases for `interval_aggregates`:
+- Combine multiple metrics of the a collector to a new one like the [MemstatCollector](../../collectors/memstatMetric.md) does it for `mem_used`)):
+```json
+  {
+    "name" : "mem_used",
+    "if" : "source == 'MemstatCollector'",
+    "function" : "sum(mem_total) - (sum(mem_free) + sum(mem_buffers) + sum(mem_cached))",
+    "tags" : {
+      "type" : "node"
+    },
+    "meta" : {
+      "group": "<copy>",
+      "unit": "<copy>",
+      "source": "<copy>"
+    }
+  }
+```

internal/metricRouter/metricCache.go

@@ -7,6 +7,7 @@ import (
 	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
 	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
 )
 
@@ -22,13 +23,14 @@ type metricCachePeriod struct {
 type metricCache struct {
 	numPeriods int
 	curPeriod  int
+	lock       sync.Mutex
 	intervals  []*metricCachePeriod
 	wg         *sync.WaitGroup
 	ticker     mct.MultiChanTicker
 	tickchan   chan time.Time
 	done       chan bool
 	output     chan lp.CCMetric
-	aggEngine  MetricAggregator
+	aggEngine  agg.MetricAggregator
 }
 
 type MetricCache interface {
@@ -59,7 +61,7 @@ func (c *metricCache) Init(output chan lp.CCMetric, ticker mct.MultiChanTicker,
 
 	// Create a new aggregation engine. No separate goroutine at the moment
 	// The code is executed by the MetricCache goroutine
-	c.aggEngine, err = NewAggregator(c.output)
+	c.aggEngine, err = agg.NewAggregator(c.output)
 	if err != nil {
 		cclog.ComponentError("MetricCache", "Cannot create aggregator")
 		return err
@@ -102,9 +104,11 @@ func (c *metricCache) Start() {
 				done()
 				return
 			case tick := <-c.tickchan:
+				c.lock.Lock()
 				old := rotate(tick)
 				// Get the last period and evaluate aggregation metrics
 				starttime, endtime, metrics := c.GetPeriod(old)
+				c.lock.Unlock()
 				if len(metrics) > 0 {
 					c.aggEngine.Eval(starttime, endtime, metrics)
 				} else {
@@ -122,6 +126,7 @@ func (c *metricCache) Start() {
 // to avoid reallocations
 func (c *metricCache) Add(metric lp.CCMetric) {
 	if c.curPeriod >= 0 && c.curPeriod < c.numPeriods {
+		c.lock.Lock()
 		p := c.intervals[c.curPeriod]
 		if p.numMetrics < p.sizeMetrics {
 			p.metrics[p.numMetrics] = metric
@@ -133,6 +138,7 @@ func (c *metricCache) Add(metric lp.CCMetric) {
 			p.sizeMetrics = p.sizeMetrics + 1
 			p.stopstamp = metric.Time()
 		}
+		c.lock.Unlock()
 	}
 }
 
@@ -148,16 +154,26 @@ func (c *metricCache) DeleteAggregation(name string) error {
 // is the current one, index=1 the last interval and so on. Returns and empty array if a wrong index
 // is given (negative index, index larger than configured number of total intervals, ...)
 func (c *metricCache) GetPeriod(index int) (time.Time, time.Time, []lp.CCMetric) {
+	var start time.Time = time.Now()
+	var stop time.Time = time.Now()
+	var metrics []lp.CCMetric
 	if index >= 0 && index < c.numPeriods {
 		pindex := c.curPeriod - index
 		if pindex < 0 {
 			pindex = c.numPeriods - pindex
 		}
 		if pindex >= 0 && pindex < c.numPeriods {
-			return c.intervals[pindex].startstamp, c.intervals[pindex].stopstamp, c.intervals[pindex].metrics
+			start = c.intervals[pindex].startstamp
+			stop = c.intervals[pindex].stopstamp
+			metrics = c.intervals[pindex].metrics
+			//return c.intervals[pindex].startstamp, c.intervals[pindex].stopstamp, c.intervals[pindex].metrics
+		} else {
+			metrics = make([]lp.CCMetric, 0)
 		}
+	} else {
+		metrics = make([]lp.CCMetric, 0)
 	}
-	return time.Now(), time.Now(), make([]lp.CCMetric, 0)
+	return start, stop, metrics
 }
 
 // Close finishes / stops the metric cache

internal/metricRouter/metricRouter.go

@@ -10,10 +10,12 @@ import (
 	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
 	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
-	"gopkg.in/Knetic/govaluate.v2"
 )
 
+const ROUTER_MAX_FORWARD = 50
+
 // Metric router tag configuration
 type metricRouterTagConfig struct {
 	Key       string `json:"key"`   // Tag name
@@ -23,11 +25,15 @@ type metricRouterTagConfig struct {
 
 // Metric router configuration
 type metricRouterConfig struct {
-	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       []metricAggregatorIntervalConfig `json:"interval_aggregates"` // List of aggregation function processed at the end of an interval
-	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
+	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
+	DropMetrics       []string                             `json:"drop_metrics"`        // List of metric names to drop. For fine-grained dropping use drop_metrics_if
+	DropMetricsIf     []string                             `json:"drop_metrics_if"`     // List of evaluatable terms to drop metrics
+	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
+	dropMetrics       map[string]bool                      // Internal map for O(1) lookup
 }
 
 // Metric router data structure
@@ -45,6 +51,7 @@ type metricRouter struct {
 	config      metricRouterConfig  // json encoded config for metric router
 	cache       MetricCache         // pointer to MetricCache
 	cachewg     sync.WaitGroup      // wait group for MetricCache
+	maxForward  int                 // number of metrics to forward maximally in one iteration
 }
 
 // MetricRouter access functions
@@ -69,6 +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.maxForward = ROUTER_MAX_FORWARD
 
 	// Set hostname
 	hostname, err := os.Hostname()
@@ -92,17 +100,19 @@ func (r *metricRouter) Init(ticker mct.MultiChanTicker, wg *sync.WaitGroup, rout
 		cclog.ComponentError("MetricRouter", err.Error())
 		return err
 	}
-	numIntervals := r.config.NumCacheIntervals
-	if numIntervals <= 0 {
-		numIntervals = 1
+	if r.config.NumCacheIntervals > 0 {
+		r.cache, err = NewCache(r.cache_input, r.ticker, &r.cachewg, r.config.NumCacheIntervals)
+		if err != nil {
+			cclog.ComponentError("MetricRouter", "MetricCache initialization failed:", err.Error())
+			return err
+		}
+		for _, agg := range r.config.IntervalAgg {
+			r.cache.AddAggregation(agg.Name, agg.Function, agg.Condition, agg.Tags, agg.Meta)
+		}
 	}
-	r.cache, err = NewCache(r.cache_input, r.ticker, &r.cachewg, numIntervals)
-	if err != nil {
-		cclog.ComponentError("MetricRouter", "MetricCache initialization failed:", err.Error())
-		return err
-	}
-	for _, agg := range r.config.IntervalAgg {
-		r.cache.AddAggregation(agg.Name, agg.Function, agg.Condition, agg.Tags, agg.Meta)
+	r.config.dropMetrics = make(map[string]bool)
+	for _, mname := range r.config.DropMetrics {
+		r.config.dropMetrics[mname] = true
 	}
 	return nil
 }
@@ -130,47 +140,34 @@ func (r *metricRouter) StartTimer() {
 	cclog.ComponentDebug("MetricRouter", "TIMER START")
 }
 
-// EvalCondition evaluates condition cond for metric data from point
-func (r *metricRouter) EvalCondition(cond string, point lp.CCMetric) (bool, error) {
-	expression, err := govaluate.NewEvaluableExpression(cond)
-	if err != nil {
-		cclog.ComponentDebug("MetricRouter", cond, " = ", err.Error())
-		return false, err
-	}
-
-	// Add metric name, tags, meta data, fields and timestamp to the parameter list
+func getParamMap(point lp.CCMetric) map[string]interface{} {
 	params := make(map[string]interface{})
+	params["metric"] = point
 	params["name"] = point.Name()
-	for _, t := range point.TagList() {
-		params[t.Key] = t.Value
+	for key, value := range point.Tags() {
+		params[key] = value
 	}
-	for _, m := range point.MetaList() {
-		params[m.Key] = m.Value
+	for key, value := range point.Meta() {
+		params[key] = value
 	}
-	for _, f := range point.FieldList() {
-		params[f.Key] = f.Value
+	for key, value := range point.Fields() {
+		params[key] = value
 	}
 	params["timestamp"] = point.Time()
-
-	// evaluate condition
-	result, err := expression.Evaluate(params)
-	if err != nil {
-		cclog.ComponentDebug("MetricRouter", cond, " = ", err.Error())
-		return false, err
-	}
-	return bool(result.(bool)), err
+	return params
 }
 
 // DoAddTags adds a tag when condition is fullfiled
 func (r *metricRouter) DoAddTags(point lp.CCMetric) {
+	var conditionMatches bool
 	for _, m := range r.config.AddTags {
-		var conditionMatches bool
-
 		if m.Condition == "*" {
+			// Condition is always matched
 			conditionMatches = true
 		} else {
+			// Evaluate condition
 			var err error
-			conditionMatches, err = r.EvalCondition(m.Condition, point)
+			conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point))
 			if err != nil {
 				cclog.ComponentError("MetricRouter", err.Error())
 				conditionMatches = false
@@ -184,14 +181,15 @@ func (r *metricRouter) DoAddTags(point lp.CCMetric) {
 
 // DoDelTags removes a tag when condition is fullfiled
 func (r *metricRouter) DoDelTags(point lp.CCMetric) {
+	var conditionMatches bool
 	for _, m := range r.config.DelTags {
-		var conditionMatches bool
-
 		if m.Condition == "*" {
+			// Condition is always matched
 			conditionMatches = true
 		} else {
+			// Evaluate condition
 			var err error
-			conditionMatches, err = r.EvalCondition(m.Condition, point)
+			conditionMatches, err = agg.EvalBoolCondition(m.Condition, getParamMap(point))
 			if err != nil {
 				cclog.ComponentError("MetricRouter", err.Error())
 				conditionMatches = false
@@ -203,9 +201,31 @@ func (r *metricRouter) DoDelTags(point lp.CCMetric) {
 	}
 }
 
+// Conditional test whether a metric should be dropped
+func (r *metricRouter) dropMetric(point lp.CCMetric) bool {
+	// Simple drop check
+	if conditionMatches, ok := r.config.dropMetrics[point.Name()]; ok {
+		return conditionMatches
+	}
+
+	// Checking the dropping conditions
+	for _, m := range r.config.DropMetricsIf {
+		conditionMatches, err := agg.EvalBoolCondition(m, getParamMap(point))
+		if err != nil {
+			cclog.ComponentError("MetricRouter", err.Error())
+			conditionMatches = false
+		}
+		if conditionMatches {
+			return conditionMatches
+		}
+	}
+
+	// No dropping condition met
+	return false
+}
+
 // Start starts the metric router
 func (r *metricRouter) Start() {
-
 	// start timer if configured
 	r.timestamp = time.Now()
 	if r.config.IntervalStamp {
@@ -224,17 +244,63 @@ func (r *metricRouter) Start() {
 		cclog.ComponentDebug("MetricRouter", "FORWARD", point)
 		r.DoAddTags(point)
 		r.DoDelTags(point)
+		if new, ok := r.config.RenameMetrics[point.Name()]; ok {
+			point.SetName(new)
+		}
+		r.DoAddTags(point)
+		r.DoDelTags(point)
+
 		for _, o := range r.outputs {
 			o <- point
 		}
 	}
 
+	// Foward message received from collector channel
+	coll_forward := func(p lp.CCMetric) {
+		// receive from metric collector
+		p.AddTag("hostname", r.hostname)
+		if r.config.IntervalStamp {
+			p.SetTime(r.timestamp)
+		}
+		if !r.dropMetric(p) {
+			forward(p)
+		}
+		// even if the metric is dropped, it is stored in the cache for
+		// aggregations
+		if r.config.NumCacheIntervals > 0 {
+			r.cache.Add(p)
+		}
+	}
+
+	// Forward message received from receivers channel
+	recv_forward := func(p lp.CCMetric) {
+		// receive from receive manager
+		if r.config.IntervalStamp {
+			p.SetTime(r.timestamp)
+		}
+		if !r.dropMetric(p) {
+			forward(p)
+		}
+	}
+
+	// Forward message received from cache channel
+	cache_forward := func(p lp.CCMetric) {
+		// receive from metric collector
+		if !r.dropMetric(p) {
+			p.AddTag("hostname", r.hostname)
+			forward(p)
+		}
+	}
+
 	// Start Metric Cache
-	r.cache.Start()
+	if r.config.NumCacheIntervals > 0 {
+		r.cache.Start()
+	}
 
 	r.wg.Add(1)
 	go func() {
 		defer r.wg.Done()
+
 		for {
 			select {
 			case <-r.done:
@@ -242,25 +308,22 @@ func (r *metricRouter) Start() {
 				return
 
 			case p := <-r.coll_input:
-				// receive from metric collector
-				p.AddTag("hostname", r.hostname)
-				if r.config.IntervalStamp {
-					p.SetTime(r.timestamp)
+				coll_forward(p)
+				for i := 0; len(r.coll_input) > 0 && i < r.maxForward; i++ {
+					coll_forward(<-r.coll_input)
 				}
-				forward(p)
-				r.cache.Add(p)
 
 			case p := <-r.recv_input:
-				// receive from receive manager
-				if r.config.IntervalStamp {
-					p.SetTime(r.timestamp)
+				recv_forward(p)
+				for i := 0; len(r.recv_input) > 0 && i < r.maxForward; i++ {
+					recv_forward(<-r.recv_input)
 				}
-				forward(p)
 
 			case p := <-r.cache_input:
-				// receive from metric collector
-				p.AddTag("hostname", r.hostname)
-				forward(p)
+				cache_forward(p)
+				for i := 0; len(r.cache_input) > 0 && i < r.maxForward; i++ {
+					cache_forward(<-r.cache_input)
+				}
 			}
 		}
 	}()
@@ -288,14 +351,21 @@ func (r *metricRouter) Close() {
 	r.done <- true
 	// 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
 	}
-	r.cache.Close()
-	r.cachewg.Wait()
+
+	// stop metric cache
+	if r.config.NumCacheIntervals > 0 {
+		cclog.ComponentDebug("MetricRouter", "CACHE CLOSE")
+		r.cache.Close()
+		r.cachewg.Wait()
+	}
 }
 
 // New creates a new initialized metric router

receivers.json

@@ -1,8 +1,8 @@
-[
-    {
+{
+    "natsrecv" : {
         "type": "nats",
         "address": "nats://my-url",
         "port" : "4222",
         "database": "testcluster"
     }
-]
+}

receivers/README.md

@@ -6,39 +6,23 @@ This folder contains the ReceiveManager and receiver implementations for the cc-
 
 The configuration file for the receivers is a list of configurations. The `type` field in each specifies which receiver to initialize.
 
-```json
-[
-  {
-    "type": "nats",
-    "address": "nats://my-url",
-    "port" : "4222",
-    "database": "testcluster"
-  }
-]
-```
-
-
-## Type `nats`
-
 ```json
 {
-  "type": "nats",
-  "address": "<nats-URI or hostname>",
-  "port" : "<portnumber>",
-  "database": "<subscribe topic>"
+  "myreceivername" : {
+    "type": "receiver-type",
+    <receiver-specific configuration>
+  }
 }
 ```
 
-The `nats` receiver subscribes to the topic `database` and listens on `address` and `port` for metrics in the InfluxDB line protocol.
+This allows to specify
+
+## Available receivers
+
+- [`nats`](./natsReceiver.md): Receive metrics from the NATS network
+- [`prometheus`](./prometheusReceiver.md): Scrape data from a Prometheus client
 
 # Contributing own receivers
-A receiver contains three functions and is derived from the type `Receiver` (in `metricReceiver.go`):
-* `Init(config ReceiverConfig) error`
-* `Start() error`
-* `Close()`
-* `Name() string`
-* `SetSink(sink chan ccMetric.CCMetric)`
+A receiver contains a few functions and is derived from the type `Receiver` (in `metricReceiver.go`):
 
-The data structures should be set up in `Init()` like opening a file or server connection. The `Start()` function should either start a go routine or issue some other asynchronous mechanism for receiving metrics. The `Close()` function should tear down anything created in `Init()`.
-
-Finally, the receiver needs to be registered in the `receiveManager.go`. There is a list of receivers called `AvailableReceivers` which is a map (`receiver_type_string` -> `pointer to Receiver interface`). Add a new entry with a descriptive name and the new receiver.
+For an example, check the [sample receiver](./sampleReceiver.go)

receivers/metricReceiver.go

@@ -1,11 +1,14 @@
 package receivers
 
 import (
-	//	"time"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	influx "github.com/influxdata/line-protocol"
 )
 
+type defaultReceiverConfig struct {
+	Type string `json:"type"`
+}
+
+// Receiver configuration: Listen address, port
 type ReceiverConfig struct {
 	Addr         string `json:"address"`
 	Port         string `json:"port"`
@@ -15,42 +18,23 @@ type ReceiverConfig struct {
 }
 
 type receiver struct {
-	name         string
-	addr         string
-	port         string
-	database     string
-	organization string
-	sink         chan lp.CCMetric
+	name string
+	sink chan lp.CCMetric
 }
 
 type Receiver interface {
-	Init(config ReceiverConfig) error
 	Start()
-	Close()
-	Name() string
-	SetSink(sink chan lp.CCMetric)
+	Close()                        // Close / finish metric receiver
+	Name() string                  // Name of the metric receiver
+	SetSink(sink chan lp.CCMetric) // Set sink channel
 }
 
+// Name returns the name of the metric receiver
 func (r *receiver) Name() string {
 	return r.name
 }
 
+// SetSink set the sink channel
 func (r *receiver) SetSink(sink chan lp.CCMetric) {
 	r.sink = sink
 }
-
-func Tags2Map(metric influx.Metric) map[string]string {
-	tags := make(map[string]string)
-	for _, t := range metric.TagList() {
-		tags[t.Key] = t.Value
-	}
-	return tags
-}
-
-func Fields2Map(metric influx.Metric) map[string]interface{} {
-	fields := make(map[string]interface{})
-	for _, f := range metric.FieldList() {
-		fields[f.Key] = f.Value
-	}
-	return fields
-}

receivers/natsReceiver.go

@@ -1,19 +1,22 @@
 package receivers
 
 import (
+	"encoding/json"
 	"errors"
 	"fmt"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 	nats "github.com/nats-io/nats.go"
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	"time"
 )
 
 type NatsReceiverConfig struct {
-	Addr     string `json:"address"`
-	Port     string `json:"port"`
-	Database string `json:"database"`
+	Type    string `json:"type"`
+	Addr    string `json:"address"`
+	Port    string `json:"port"`
+	Subject string `json:"subject"`
 }
 
 type NatsReceiver struct {
@@ -22,49 +25,16 @@ type NatsReceiver struct {
 	handler *influx.MetricHandler
 	parser  *influx.Parser
 	meta    map[string]string
-	config  ReceiverConfig
+	config  NatsReceiverConfig
 }
 
 var DefaultTime = func() time.Time {
 	return time.Unix(42, 0)
 }
 
-func (r *NatsReceiver) Init(config ReceiverConfig) error {
-	r.name = "NatsReceiver"
-	r.config = config
-	if len(r.config.Addr) == 0 ||
-		len(r.config.Port) == 0 ||
-		len(r.config.Database) == 0 {
-		return errors.New("Not all configuration variables set required by NatsReceiver")
-	}
-	r.meta = map[string]string{"source": r.name}
-	r.addr = r.config.Addr
-	if len(r.addr) == 0 {
-		r.addr = nats.DefaultURL
-	}
-	r.port = r.config.Port
-	if len(r.port) == 0 {
-		r.port = "4222"
-	}
-	uri := fmt.Sprintf("%s:%s", r.addr, r.port)
-	cclog.ComponentDebug("NatsReceiver", "INIT", uri)
-	nc, err := nats.Connect(uri)
-	if err == nil {
-		r.database = r.config.Database
-		r.nc = nc
-	} else {
-		r.nc = nil
-		return err
-	}
-	r.handler = influx.NewMetricHandler()
-	r.parser = influx.NewParser(r.handler)
-	r.parser.SetTimeFunc(DefaultTime)
-	return err
-}
-
 func (r *NatsReceiver) Start() {
-	cclog.ComponentDebug("NatsReceiver", "START")
-	r.nc.Subscribe(r.database, r._NatsReceive)
+	cclog.ComponentDebug(r.name, "START")
+	r.nc.Subscribe(r.config.Subject, r._NatsReceive)
 }
 
 func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
@@ -84,7 +54,39 @@ func (r *NatsReceiver) _NatsReceive(m *nats.Msg) {
 
 func (r *NatsReceiver) Close() {
 	if r.nc != nil {
-		cclog.ComponentDebug("NatsReceiver", "CLOSE")
+		cclog.ComponentDebug(r.name, "CLOSE")
 		r.nc.Close()
 	}
 }
+
+func NewNatsReceiver(name string, config json.RawMessage) (Receiver, error) {
+	r := new(NatsReceiver)
+	r.name = fmt.Sprintf("NatsReceiver(%s)", name)
+	r.config.Addr = nats.DefaultURL
+	r.config.Port = "4222"
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &r.config)
+		if err != nil {
+			cclog.ComponentError(r.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+	if len(r.config.Addr) == 0 ||
+		len(r.config.Port) == 0 ||
+		len(r.config.Subject) == 0 {
+		return nil, errors.New("not all configuration variables set required by NatsReceiver")
+	}
+	r.meta = map[string]string{"source": r.name}
+	uri := fmt.Sprintf("%s:%s", r.config.Addr, r.config.Port)
+	cclog.ComponentDebug(r.name, "NewNatsReceiver", uri, "Subject", r.config.Subject)
+	if nc, err := nats.Connect(uri); err == nil {
+		r.nc = nc
+	} else {
+		r.nc = nil
+		return nil, err
+	}
+	r.handler = influx.NewMetricHandler()
+	r.parser = influx.NewParser(r.handler)
+	r.parser.SetTimeFunc(DefaultTime)
+	return r, nil
+}

receivers/natsReceiver.md

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

receivers/prometheusReceiver.go

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

receivers/prometheusReceiver.md

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

receivers/receiveManager.go

@@ -9,8 +9,8 @@ import (
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-var AvailableReceivers = map[string]Receiver{
-	"nats": &NatsReceiver{},
+var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){
+	"nats": NewNatsReceiver,
 }
 
 type receiveManager struct {
@@ -18,23 +18,25 @@ type receiveManager struct {
 	output chan lp.CCMetric
 	done   chan bool
 	wg     *sync.WaitGroup
-	config []ReceiverConfig
+	config []json.RawMessage
 }
 
 type ReceiveManager interface {
 	Init(wg *sync.WaitGroup, receiverConfigFile string) error
-	AddInput(rawConfig json.RawMessage) error
+	AddInput(name string, rawConfig json.RawMessage) error
 	AddOutput(output chan lp.CCMetric)
 	Start()
 	Close()
 }
 
 func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) error {
+	// Initialize struct fields
 	rm.inputs = make([]Receiver, 0)
 	rm.output = nil
 	rm.done = make(chan bool)
 	rm.wg = wg
-	rm.config = make([]ReceiverConfig, 0)
+	rm.config = make([]json.RawMessage, 0)
+
 	configFile, err := os.Open(receiverConfigFile)
 	if err != nil {
 		cclog.ComponentError("ReceiveManager", err.Error())
@@ -42,15 +44,16 @@ func (rm *receiveManager) Init(wg *sync.WaitGroup, receiverConfigFile string) er
 	}
 	defer configFile.Close()
 	jsonParser := json.NewDecoder(configFile)
-	var rawConfigs []json.RawMessage
+	var rawConfigs map[string]json.RawMessage
 	err = jsonParser.Decode(&rawConfigs)
 	if err != nil {
 		cclog.ComponentError("ReceiveManager", err.Error())
 		return err
 	}
-	for _, raw := range rawConfigs {
-		rm.AddInput(raw)
+	for name, raw := range rawConfigs {
+		rm.AddInput(name, raw)
 	}
+
 	return nil
 }
 
@@ -64,8 +67,8 @@ func (rm *receiveManager) Start() {
 	cclog.ComponentDebug("ReceiveManager", "STARTED")
 }
 
-func (rm *receiveManager) AddInput(rawConfig json.RawMessage) error {
-	var config ReceiverConfig
+func (rm *receiveManager) AddInput(name string, rawConfig json.RawMessage) error {
+	var config defaultReceiverConfig
 	err := json.Unmarshal(rawConfig, &config)
 	if err != nil {
 		cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "JSON config error:", err.Error())
@@ -75,14 +78,13 @@ func (rm *receiveManager) AddInput(rawConfig json.RawMessage) error {
 		cclog.ComponentError("ReceiveManager", "SKIP", config.Type, "unknown receiver:", err.Error())
 		return err
 	}
-	r := AvailableReceivers[config.Type]
-	err = r.Init(config)
+	r, err := AvailableReceivers[config.Type](name, rawConfig)
 	if err != nil {
-		cclog.ComponentError("ReceiveManager", "SKIP", r.Name(), "initialization failed:", err.Error())
+		cclog.ComponentError("ReceiveManager", "SKIP", name, "initialization failed:", err.Error())
 		return err
 	}
 	rm.inputs = append(rm.inputs, r)
-	rm.config = append(rm.config, config)
+	rm.config = append(rm.config, rawConfig)
 	cclog.ComponentDebug("ReceiveManager", "ADD RECEIVER", r.Name())
 	return nil
 }

receivers/sampleReceiver.go

@@ -0,0 +1,91 @@
+package receivers
+
+import (
+	"encoding/json"
+	"fmt"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+)
+
+// SampleReceiver configuration: receiver type, listen address, port
+type SampleReceiverConfig struct {
+	Type string `json:"type"`
+	Addr string `json:"address"`
+	Port string `json:"port"`
+}
+
+type SampleReceiver struct {
+	receiver
+	config SampleReceiverConfig
+
+	// Storage for static information
+	meta map[string]string
+	// Use in case of own go routine
+	// done chan bool
+	// wg   sync.WaitGroup
+}
+
+// Implement functions required for Receiver interface
+// Start(), Close()
+// See: metricReceiver.go
+
+func (r *SampleReceiver) Start() {
+	cclog.ComponentDebug(r.name, "START")
+
+	// Start server process like http.ListenAndServe()
+
+	// or use own go routine but always make sure it exits
+	// as soon as it gets the signal of the r.done channel
+	// r.wg.Add(1)
+	// go func() {
+	// 	for {
+	// 		select {
+	// 		case <-r.done:
+	// 			r.wg.Done()
+	// 			return
+	// 		}
+	// 	}
+	// 	r.wg.Done()
+	// }()
+}
+
+// Close receiver: close network connection, close files, close libraries, ...
+func (r *SampleReceiver) Close() {
+	cclog.ComponentDebug(r.name, "CLOSE")
+
+	// Close server like http.Shutdown()
+
+	// in case of own go routine, send the signal and wait
+	// r.done <- true
+	// r.wg.Wait()
+}
+
+// New function to create a new instance of the receiver
+// Initialize the receiver by giving it a name and reading in the config JSON
+func NewSampleReceiver(name string, config json.RawMessage) (Receiver, error) {
+	r := new(SampleReceiver)
+
+	// Set name of SampleReceiver
+	// The name should be chosen in such a way that different instances of SampleReceiver can be distinguished
+	r.name = fmt.Sprintf("SampleReceiver(%s)", name)
+
+	// Set static information
+	r.meta = map[string]string{"source": r.name}
+
+	// Set defaults in r.config
+	// Allow overwriting these defaults by reading config JSON
+
+	// Read the sample receiver specific JSON config
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &r.config)
+		if err != nil {
+			cclog.ComponentError(r.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+
+	// Check that all required fields in the configuration are set
+	// Use 'if len(r.config.Option) > 0' for strings
+
+	return r, nil
+}

scripts/cc-metric-collector.config

@@ -15,6 +15,3 @@ CONF_DIR=/etc/cc-metric-collector
 CONF_FILE=/etc/cc-metric-collector/cc-metric-collector.json
 
 RESTART_ON_UPGRADE=true
-
-# Only used on systemd systems
-PID_FILE_DIR=/var/run

scripts/cc-metric-collector.service

@@ -14,11 +14,7 @@ Restart=on-failure
 WorkingDirectory=/tmp
 RuntimeDirectory=cc-metric-collector
 RuntimeDirectoryMode=0750
-ExecStart=/usr/sbin/cc-metric-collector                                             \
-                            --config=${CONF_FILE}                                   \
-                            --pidfile=${PID_FILE_DIR}/cc-metric-collector.pid
-
-
+ExecStart=/usr/sbin/cc-metric-collector --config=${CONF_FILE}
 LimitNOFILE=10000
 TimeoutStopSec=20
 UMask=0027

scripts/cc-metric-collector.spec

@@ -1,5 +1,5 @@
 Name:           cc-metric-collector
-Version:        0.1
+Version:        %{VERS}
 Release:        1%{?dist}
 Summary:        Metric collection daemon from the ClusterCockpit suite
 
@@ -7,6 +7,7 @@ License:        MIT
 Source0:        %{name}-%{version}.tar.gz
 
 BuildRequires:  go-toolset
+BuildRequires:  systemd-rpm-macros
 # for internal LIKWID installation
 BuildRequires:  wget perl-Data-Dumper
 
@@ -26,15 +27,23 @@ make
 
 
 %install
-install -Dpm 0755 %{name} %{buildroot}%{_sbindir}/%{name}
+install -Dpm 0750 %{name} %{buildroot}%{_sbindir}/%{name}
 install -Dpm 0600 config.json %{buildroot}%{_sysconfdir}/%{name}/%{name}.json
-install -Dpm 644 scripts/%{name}.service %{buildroot}%{_unitdir}/%{name}.service
-install -Dpm 600 scripts/%{name}.config %{buildroot}%{_sysconfdir}/default/%{name}
+install -Dpm 0600 collectors.json %{buildroot}%{_sysconfdir}/%{name}/collectors.json
+install -Dpm 0600 sinks.json %{buildroot}%{_sysconfdir}/%{name}/sinks.json
+install -Dpm 0600 receivers.json %{buildroot}%{_sysconfdir}/%{name}/receivers.json
+install -Dpm 0600 router.json %{buildroot}%{_sysconfdir}/%{name}/router.json
+install -Dpm 0644 scripts/%{name}.service %{buildroot}%{_unitdir}/%{name}.service
+install -Dpm 0600 scripts/%{name}.config %{buildroot}%{_sysconfdir}/default/%{name}
+install -Dpm 0644 scripts/%{name}.sysusers %{buildroot}%{_sysusersdir}/%{name}.conf
 
 
 %check
 # go test should be here... :)
 
+%pre
+%sysusers_create_package scripts/%{name}.sysusers
+
 %post
 %systemd_post %{name}.service
 
@@ -42,13 +51,25 @@ install -Dpm 600 scripts/%{name}.config %{buildroot}%{_sysconfdir}/default/%{nam
 %systemd_preun %{name}.service
 
 %files
+# Binary
+%attr(-,clustercockpit,clustercockpit) %{_sbindir}/%{name}
+# Configuration
 %dir %{_sysconfdir}/%{name}
-%{_sbindir}/%{name}
+%attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/%{name}.json
+%attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/collectors.json
+%attr(0600,clustercockpit,clustercockpit) %config(noreplace) %{_sysconfdir}/%{name}/sinks.json
+%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}
-%config(noreplace) %{_sysconfdir}/%{name}/%{name}.json
-
 
 %changelog
+* Thu Mar 03 2022 Thomas Gruber - 0.3
+- Add clustercockpit user installation
+* Mon Feb 14 2022 Thomas Gruber - 0.2
+- Add component specific configuration files
+- Add %attr to config files
 * Mon Nov 22 2021 Thomas Gruber - 0.1
 - Initial spec file

scripts/cc-metric-collector.sysusers

@@ -0,0 +1,2 @@
+#Type Name           ID GECOS                     Home directory           Shell
+u     clustercockpit -  "User for ClusterCockpit" /run/cc-metric-collector /sbin/nologin

scripts/likwid_perfgroup_to_cc_config.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+
+import os, os.path, sys, getopt, re, json
+
+def which(cmd):
+    ospath = os.environ.get("PATH", "")
+    for p in ospath.split(":"):
+        testcmd = os.path.join(p, cmd)
+        if os.access(testcmd, os.X_OK):
+            return testcmd
+    return None
+
+def group_to_json(groupfile):
+    gdata = []
+    with open(groupfile, "r") as fp:
+        gdata = fp.read().strip().split("\n")
+    events = {}
+    metrics = []
+    parse_events = False
+    parse_metrics = False
+    for line in gdata:
+        if line == "EVENTSET":
+            parse_events = True
+            parse_metrics = False
+            continue
+        if line == "METRICS":
+            parse_events = False
+            parse_metrics = True
+            continue
+        if len(line) == 0 or line.startswith("SHORT") or line == "LONG":
+            parse_events = False
+            parse_metrics = False
+            continue
+        if parse_events:
+            m = re.match("([\w\d]+)\s+([\w\d_]+)", line)
+            if m:
+                events[m.group(1)] = m.group(2)
+        if parse_metrics:
+            llist = re.split("\s+", line)
+            calc = llist[-1]
+            metric = " ".join(llist[:-1])
+            scope = "cpu"
+            if "BOX" in calc:
+                scope = "socket"
+            if "PWR" in calc:
+                scope = "socket"
+
+            m = {"name" : metric, "calc": calc, "scope" : scope, "publish" : True}
+            metrics.append(m)
+    return {"events" : events, "metrics" : metrics}
+
+if len(sys.argv) != 3:
+    print("Usage: $0 <likwid-arch> <group-name>")
+    sys.exit(1)
+
+
+arch = sys.argv[1]
+group = sys.argv[2]
+
+ltopo = which("likwid-topology")
+if not ltopo:
+    print("Cannot find LIKWID installation. Please add LIKWID bin folder to your PATH.")
+    sys.exit(1)
+
+bindir = os.path.dirname(ltopo)
+
+groupdir = os.path.normpath(os.path.join(bindir, "../share/likwid/perfgroups"))
+if not os.path.exists(groupdir):
+    print("Cannot find LIKWID performance groups in default install location")
+    sys.exit(1)
+
+archdir = os.path.join(groupdir, arch)
+if not os.path.exists(archdir):
+    print("Cannot find LIKWID performance groups for architecture {}".format(arch))
+    sys.exit(1)
+
+groupfile = os.path.join(archdir, "{}.txt".format(group))
+if not os.path.exists(groupfile):
+    print("Cannot find LIKWID performance group {} for architecture {}".format(group, arch))
+    sys.exit(1)
+
+gdata = group_to_json(groupfile)
+print(json.dumps(gdata, sort_keys=True, indent=2))

sinks.json

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

sinks/README.md

@@ -2,17 +2,27 @@
 
 This folder contains the SinkManager and sink implementations for the cc-metric-collector.
 
+# Available sinks:
+- [`stdout`](./stdoutSink.md): Print all metrics to `stdout`, `stderr` or a file
+- [`http`](./httpSink.md): Send metrics to an HTTP server as POST requests
+- [`influxdb`](./influxSink.md): Send metrics to an [InfluxDB](https://www.influxdata.com/products/influxdb/) database
+- [`influxasync`](./influxAsyncSink.md): Send metrics to an [InfluxDB](https://www.influxdata.com/products/influxdb/) database with non-blocking write API
+- [`nats`](./natsSink.md): Publish metrics to the [NATS](https://nats.io/) network overlay system
+- [`ganglia`](./gangliaSink.md): Publish metrics in the [Ganglia Monitoring System](http://ganglia.info/) using the `gmetric` CLI tool
+- [`libganglia`](./libgangliaSink.md): Publish metrics in the [Ganglia Monitoring System](http://ganglia.info/) directly using `libganglia.so`
+- [`prometeus`](./prometheusSink.md): Publish metrics for the [Prometheus Monitoring System](https://prometheus.io/)
+
 # Configuration
 
 The configuration file for the sinks is a list of configurations. The `type` field in each specifies which sink to initialize.
 
 ```json
 [
-  {
+  "mystdout" : {
     "type" : "stdout",
     "meta_as_tags" : false
   },
-  {
+  "metricstore" : {
     "type" : "http",
     "host" : "localhost",
     "port" : "4123",
@@ -22,78 +32,75 @@ The configuration file for the sinks is a list of configurations. The `type` fie
 ]
 ```
 
-This example initializes two sinks, the `stdout` sink printing all metrics to the STDOUT and the `http` sink with the given `host`, `port`, `database` and `password`.
-
-If `meta_as_tags` is set, all meta information attached to CCMetric are printed out as tags.
-
-## Type `stdout`
-
-```json
-{
-  "type" : "stdout",
-  "meta_as_tags" : <true|false>
-}
-```
-
-The `stdout` sink dumps all metrics to the STDOUT.
-
-## Type `http`
-
-```json
-{
-  "type" : "http",
-  "host" : "<hostname>",
-  "port" : "<portnumber>",
-  "database" : "<database name>",
-  "password" : "<jwt token>",
-  "meta_as_tags" : <true|false>
-}
-```
-The sink uses POST requests to send metrics to `http://<host>:<port>/<database>` using the JWT token as a JWT in the 'Authorization' header.
-
-## Type `nats`
-
-```json
-{
-  "type" : "nats",
-  "host" : "<hostname>",
-  "port" : "<portnumber>",
-  "user" : "<username>",
-  "password" : "<password>",
-  "database" : "<database name>"
-  "meta_as_tags" : <true|false>
-}
-```
-
-This sink publishes the CCMetric in a NATS environment using `host`, `port`, `user` and `password` for connecting. The metrics are published using the topic `database`. 
-
-## Type `influxdb`
-
-```json
-{
-  "type" : "influxdb",
-  "host" : "<hostname>",
-  "port" : "<portnumber>",
-  "user" : "<username>",
-  "password" : "<password or API key>",
-  "database" : "<database name>"
-  "organization": "<InfluxDB v2 organization>",
-  "ssl" : <true|false>,
-  "meta_as_tags" : <true|false>
-}
-```
-
-This sink submits the CCMetrics to an InfluxDB time-series database. It uses `host`, `port` and `ssl` for connecting. For authentification, it uses either `user:password` if `user` is set and only `password` as API key. The `organization` and `database` are used for writing to the correct database.
 
 
 
 # Contributing own sinks
-A sink contains three functions and is derived from the type `Sink`:
-* `Init(config SinkConfig) error`
+A sink contains five functions and is derived from the type `sink`:
+* `Init(name string, config json.RawMessage) error`
 * `Write(point CCMetric) error`
 * `Flush() error`
 * `Close()`
+* `New<Typename>(name string, config json.RawMessage) (Sink, error)` (calls the `Init()` function)
 
 The data structures should be set up in `Init()` like opening a file or server connection. The `Write()` function writes/sends the data. For non-blocking sinks, the `Flush()` method tells the sink to drain its internal buffers. The `Close()` function should tear down anything created in `Init()`.
 
 Finally, the sink needs to be registered in the `sinkManager.go`. There is a list of sinks called `AvailableSinks` which is a map (`sink_type_string` -> `pointer to sink interface`). Add a new entry with a descriptive name and the new sink.
+
+## Sample sink
+
+```go
+package sinks
+
+import (
+	"encoding/json"
+	"log"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+)
+
+type SampleSinkConfig struct {
+	defaultSinkConfig  // defines JSON tags for 'name' and 'meta_as_tags'
+}
+
+type SampleSink struct {
+	sink              // declarate 'name' and 'meta_as_tags'
+	config StdoutSinkConfig // entry point to the SampleSinkConfig
+}
+
+// Initialize the sink by giving it a name and reading in the config JSON
+func (s *SampleSink) Init(name string, config json.RawMessage) error {
+	s.name = fmt.Sprintf("SampleSink(%s)", name)   // Always specify a name here
+  // Read in the config JSON
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// Code to submit a single CCMetric to the sink
+func (s *SampleSink) Write(point lp.CCMetric) error {
+	log.Print(point)
+	return nil
+}
+
+// If the sink uses batched sends internally, you can tell to flush its buffers
+func (s *SampleSink) Flush() error {
+	return nil
+}
+
+
+// Close sink: close network connection, close files, close libraries, ...
+func (s *SampleSink) Close() {}
+
+
+// New function to create a new instance of the sink
+func NewSampleSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(SampleSink)
+	err := s.Init(name, config)
+	return s, err
+}
+
+```

sinks/gangliaCommon.go

@@ -0,0 +1,258 @@
+package sinks
+
+import (
+	"fmt"
+	"strings"
+
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+)
+
+func GangliaMetricName(point lp.CCMetric) string {
+	name := point.Name()
+	metricType, typeOK := point.GetTag("type")
+	metricTid, tidOk := point.GetTag("type-id")
+	gangliaType := metricType + metricTid
+	if strings.Contains(name, metricType) && tidOk {
+		name = strings.Replace(name, metricType, gangliaType, -1)
+	} else if typeOK && tidOk {
+		name = metricType + metricTid + "_" + name
+	} else if point.HasTag("device") {
+		device, _ := point.GetTag("device")
+		name = name + "_" + device
+	}
+
+	return name
+}
+
+func GangliaMetricRename(name string) string {
+	if name == "net_bytes_in" {
+		return "bytes_in"
+	} else if name == "net_bytes_out" {
+		return "bytes_out"
+	} else if name == "net_pkts_in" {
+		return "pkts_in"
+	} else if name == "net_pkts_out" {
+		return "pkts_out"
+	} else if name == "cpu_iowait" {
+		return "cpu_wio"
+	}
+	return name
+}
+
+func GangliaSlopeType(point lp.CCMetric) uint {
+	name := point.Name()
+	if name == "mem_total" || name == "swap_total" {
+		return 0
+	}
+	return 3
+}
+
+const DEFAULT_GANGLIA_METRIC_TMAX = 300
+const DEFAULT_GANGLIA_METRIC_SLOPE = "both"
+
+type GangliaMetric struct {
+	Name  string
+	Type  string
+	Slope string
+	Tmax  int
+	Unit  string
+}
+
+type GangliaMetricGroup struct {
+	Name    string
+	Metrics []GangliaMetric
+}
+
+var CommonGangliaMetrics = []GangliaMetricGroup{
+	{
+		Name: "memory",
+		Metrics: []GangliaMetric{
+			{"mem_total", "float", "zero", 1200, "KB"},
+			{"swap_total", "float", "zero", 1200, "KB"},
+			{"mem_free", "float", "both", 180, "KB"},
+			{"mem_shared", "float", "both", 180, "KB"},
+			{"mem_buffers", "float", "both", 180, "KB"},
+			{"mem_cached", "float", "both", 180, "KB"},
+			{"swap_free", "float", "both", 180, "KB"},
+			{"mem_sreclaimable", "float", "both", 180, "KB"},
+			{"mem_slab", "float", "both", 180, "KB"},
+		},
+	},
+	{
+		Name: "cpu",
+		Metrics: []GangliaMetric{
+			{"cpu_num", "uint32", "zero", 1200, "CPUs"},
+			{"cpu_speed", "uint32", "zero", 1200, "MHz"},
+			{"cpu_user", "float", "both", 90, "%"},
+			{"cpu_nice", "float", "both", 90, "%"},
+			{"cpu_system", "float", "both", 90, "%"},
+			{"cpu_idle", "float", "both", 3800, "%"},
+			{"cpu_aidle", "float", "both", 90, "%"},
+			{"cpu_wio", "float", "both", 90, "%"},
+			{"cpu_intr", "float", "both", 90, "%"},
+			{"cpu_sintr", "float", "both", 90, "%"},
+			{"cpu_steal", "float", "both", 90, "%"},
+			{"cpu_guest", "float", "both", 90, "%"},
+			{"cpu_gnice", "float", "both", 90, "%"},
+		},
+	},
+	{
+		Name: "load",
+		Metrics: []GangliaMetric{
+			{"load_one", "float", "both", 70, ""},
+			{"load_five", "float", "both", 325, ""},
+			{"load_fifteen", "float", "both", 950, ""},
+		},
+	},
+	{
+		Name: "disk",
+		Metrics: []GangliaMetric{
+			{"disk_total", "double", "both", 1200, "GB"},
+			{"disk_free", "double", "both", 180, "GB"},
+			{"part_max_used", "float", "both", 180, "%"},
+		},
+	},
+	{
+		Name: "network",
+		Metrics: []GangliaMetric{
+			{"bytes_out", "float", "both", 300, "bytes/sec"},
+			{"bytes_in", "float", "both", 300, "bytes/sec"},
+			{"pkts_in", "float", "both", 300, "packets/sec"},
+			{"pkts_out", "float", "both", 300, "packets/sec"},
+		},
+	},
+	{
+		Name: "process",
+		Metrics: []GangliaMetric{
+			{"proc_run", "uint32", "both", 950, ""},
+			{"proc_total", "uint32", "both", 950, ""},
+		},
+	},
+	{
+		Name: "system",
+		Metrics: []GangliaMetric{
+			{"boottime", "uint32", "zero", 1200, "s"},
+			{"sys_clock", "uint32", "zero", 1200, "s"},
+			{"machine_type", "string", "zero", 1200, ""},
+			{"os_name", "string", "zero", 1200, ""},
+			{"os_release", "string", "zero", 1200, ""},
+			{"mtu", "uint32", "both", 1200, ""},
+		},
+	},
+}
+
+type GangliaMetricConfig struct {
+	Type  string
+	Slope string
+	Tmax  int
+	Unit  string
+	Group string
+	Value string
+}
+
+func GetCommonGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
+	mname := GangliaMetricRename(point.Name())
+	for _, group := range CommonGangliaMetrics {
+		for _, metric := range group.Metrics {
+			if metric.Name == mname {
+				valueStr := ""
+				value, ok := point.GetField("value")
+				if ok {
+					switch real := value.(type) {
+					case float64:
+						valueStr = fmt.Sprintf("%f", real)
+					case float32:
+						valueStr = fmt.Sprintf("%f", real)
+					case int64:
+						valueStr = fmt.Sprintf("%d", real)
+					case int32:
+						valueStr = fmt.Sprintf("%d", real)
+					case int:
+						valueStr = fmt.Sprintf("%d", real)
+					case uint64:
+						valueStr = fmt.Sprintf("%d", real)
+					case uint32:
+						valueStr = fmt.Sprintf("%d", real)
+					case uint:
+						valueStr = fmt.Sprintf("%d", real)
+					case string:
+						valueStr = real
+					default:
+					}
+				}
+				return GangliaMetricConfig{
+					Group: group.Name,
+					Type:  metric.Type,
+					Slope: metric.Slope,
+					Tmax:  metric.Tmax,
+					Unit:  metric.Unit,
+					Value: valueStr,
+				}
+			}
+		}
+	}
+	return GangliaMetricConfig{
+		Group: "",
+		Type:  "",
+		Slope: "",
+		Tmax:  0,
+		Unit:  "",
+		Value: "",
+	}
+}
+
+func GetGangliaConfig(point lp.CCMetric) GangliaMetricConfig {
+	group := ""
+	if g, ok := point.GetMeta("group"); ok {
+		group = g
+	}
+	unit := ""
+	if u, ok := point.GetMeta("unit"); ok {
+		unit = u
+	}
+	valueType := "double"
+	valueStr := ""
+	value, ok := point.GetField("value")
+	if ok {
+		switch real := value.(type) {
+		case float64:
+			valueStr = fmt.Sprintf("%f", real)
+			valueType = "double"
+		case float32:
+			valueStr = fmt.Sprintf("%f", real)
+			valueType = "float"
+		case int64:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "int32"
+		case int32:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "int32"
+		case int:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "int32"
+		case uint64:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "uint32"
+		case uint32:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "uint32"
+		case uint:
+			valueStr = fmt.Sprintf("%d", real)
+			valueType = "uint32"
+		case string:
+			valueStr = real
+			valueType = "string"
+		default:
+			valueType = "invalid"
+		}
+	}
+
+	return GangliaMetricConfig{
+		Group: group,
+		Type:  valueType,
+		Slope: DEFAULT_GANGLIA_METRIC_SLOPE,
+		Tmax:  DEFAULT_GANGLIA_METRIC_TMAX,
+		Unit:  unit,
+		Value: valueStr,
+	}
+}

sinks/gangliaSink.go

@@ -1,76 +1,86 @@
 package sinks
 
 import (
+	"encoding/json"
+	"errors"
 	"fmt"
-	"log"
 	"strings"
 
 	//	"time"
 	"os/exec"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
 const GMETRIC_EXEC = `gmetric`
+const GMETRIC_CONFIG = `/etc/ganglia/gmond.conf`
 
-type GangliaSink struct {
-	Sink
-	gmetric_path string
+type GangliaSinkConfig struct {
+	defaultSinkConfig
+	GmetricPath     string `json:"gmetric_path,omitempty"`
+	GmetricConfig   string `json:"gmetric_config,omitempty"`
+	AddGangliaGroup bool   `json:"add_ganglia_group,omitempty"`
+	AddTagsAsDesc   bool   `json:"add_tags_as_desc,omitempty"`
+	ClusterName     string `json:"cluster_name,omitempty"`
+	AddTypeToName   bool   `json:"add_type_to_name,omitempty"`
+	AddUnits        bool   `json:"add_units,omitempty"`
 }
 
-func (s *GangliaSink) Init(config sinkConfig) error {
-	p, err := exec.LookPath(string(GMETRIC_EXEC))
-	if err == nil {
-		s.gmetric_path = p
-	}
-	return err
+type GangliaSink struct {
+	sink
+	gmetric_path   string
+	gmetric_config string
+	config         GangliaSinkConfig
 }
 
 func (s *GangliaSink) Write(point lp.CCMetric) error {
 	var err error = nil
-	var tagsstr []string
+	//var tagsstr []string
 	var argstr []string
-	for _, t := range point.TagList() {
-		switch t.Key {
-		case "cluster":
-			argstr = append(argstr, fmt.Sprintf("--cluster=%s", t.Value))
-		case "unit":
-			argstr = append(argstr, fmt.Sprintf("--units=%s", t.Value))
-		case "group":
-			argstr = append(argstr, fmt.Sprintf("--group=%s", t.Value))
-		default:
-			tagsstr = append(tagsstr, fmt.Sprintf("%s=%s", t.Key, t.Value))
-		}
+
+	// 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(tagsstr) > 0 {
-		argstr = append(argstr, fmt.Sprintf("--desc=%q", strings.Join(tagsstr, ",")))
+	if len(conf.Type) == 0 {
+		return fmt.Errorf("metric %s has no 'value' field", metricname)
 	}
-	argstr = append(argstr, fmt.Sprintf("--name=%s", point.Name()))
-	for _, f := range point.FieldList() {
-		if f.Key == "value" {
-			switch f.Value.(type) {
-			case float64:
-				argstr = append(argstr, fmt.Sprintf("--value=%v", f.Value.(float64)))
-				argstr = append(argstr, "--type=double")
-			case float32:
-				argstr = append(argstr, fmt.Sprintf("--value=%v", f.Value.(float32)))
-				argstr = append(argstr, "--type=float")
-			case int:
-				argstr = append(argstr, fmt.Sprintf("--value=%d", f.Value.(int)))
-				argstr = append(argstr, "--type=int32")
-			case int64:
-				argstr = append(argstr, fmt.Sprintf("--value=%d", f.Value.(int64)))
-				argstr = append(argstr, "--type=int32")
-			case string:
-				argstr = append(argstr, fmt.Sprintf("--value=%q", f.Value.(string)))
-				argstr = append(argstr, "--type=string")
-			}
-		}
+
+	if s.config.AddGangliaGroup {
+		argstr = append(argstr, fmt.Sprintf("--group=%s", conf.Group))
 	}
-	log.Print(s.gmetric_path, " ", strings.Join(argstr, " "))
-	//	command := exec.Command(string(GMETRIC_EXEC), strings.Join(argstr, " "))
-	//	command.Wait()
-	//	_, err := command.Output()
+	if s.config.AddUnits && len(conf.Unit) > 0 {
+		argstr = append(argstr, fmt.Sprintf("--units=%s", conf.Unit))
+	}
+
+	if len(s.config.ClusterName) > 0 {
+		argstr = append(argstr, fmt.Sprintf("--cluster=%s", s.config.ClusterName))
+	}
+	// if s.config.AddTagsAsDesc && len(tagsstr) > 0 {
+	// 	argstr = append(argstr, fmt.Sprintf("--desc=%q", strings.Join(tagsstr, ",")))
+	// }
+	if len(s.gmetric_config) > 0 {
+		argstr = append(argstr, fmt.Sprintf("--conf=%s", s.gmetric_config))
+	}
+	if s.config.AddTypeToName {
+		argstr = append(argstr, fmt.Sprintf("--name=%s", GangliaMetricName(point)))
+	} else {
+		argstr = append(argstr, fmt.Sprintf("--name=%s", metricname))
+	}
+	argstr = append(argstr, fmt.Sprintf("--slope=%s", conf.Slope))
+	argstr = append(argstr, fmt.Sprintf("--value=%s", conf.Value))
+	argstr = append(argstr, fmt.Sprintf("--type=%s", conf.Type))
+	argstr = append(argstr, fmt.Sprintf("--tmax=%d", conf.Tmax))
+
+	cclog.ComponentDebug(s.name, s.gmetric_path, strings.Join(argstr, " "))
+	command := exec.Command(s.gmetric_path, argstr...)
+	command.Wait()
+	_, err = command.Output()
 	return err
 }
 
@@ -80,3 +90,38 @@ func (s *GangliaSink) Flush() error {
 
 func (s *GangliaSink) Close() {
 }
+
+func NewGangliaSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(GangliaSink)
+	s.name = fmt.Sprintf("GangliaSink(%s)", name)
+	s.config.AddTagsAsDesc = false
+	s.config.AddGangliaGroup = false
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			cclog.ComponentError(s.name, "Error reading config for", s.name, ":", err.Error())
+			return nil, err
+		}
+	}
+	s.gmetric_path = ""
+	s.gmetric_config = ""
+	if len(s.config.GmetricPath) > 0 {
+		p, err := exec.LookPath(s.config.GmetricPath)
+		if err == nil {
+			s.gmetric_path = p
+		}
+	}
+	if len(s.gmetric_path) == 0 {
+		p, err := exec.LookPath(string(GMETRIC_EXEC))
+		if err == nil {
+			s.gmetric_path = p
+		}
+	}
+	if len(s.gmetric_path) == 0 {
+		return nil, errors.New("cannot find executable 'gmetric'")
+	}
+	if len(s.config.GmetricConfig) > 0 {
+		s.gmetric_config = s.config.GmetricConfig
+	}
+	return s, nil
+}

sinks/gangliaSink.md

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

sinks/httpSink.go

@@ -2,63 +2,109 @@ package sinks
 
 import (
 	"bytes"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"net/http"
+	"sync"
 	"time"
 
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 )
 
+type HttpSinkConfig struct {
+	defaultSinkConfig
+	URL             string `json:"url,omitempty"`
+	JWT             string `json:"jwt,omitempty"`
+	Timeout         string `json:"timeout,omitempty"`
+	MaxIdleConns    int    `json:"max_idle_connections,omitempty"`
+	IdleConnTimeout string `json:"idle_connection_timeout,omitempty"`
+	FlushDelay      string `json:"flush_delay,omitempty"`
+}
+
 type HttpSink struct {
 	sink
-	client   *http.Client
-	url, jwt string
-	encoder  *influx.Encoder
-	buffer   *bytes.Buffer
+	client          *http.Client
+	encoder         *influx.Encoder
+	lock            sync.Mutex // Flush() runs in another goroutine, so this lock has to protect the buffer
+	buffer          *bytes.Buffer
+	flushTimer      *time.Timer
+	config          HttpSinkConfig
+	maxIdleConns    int
+	idleConnTimeout time.Duration
+	timeout         time.Duration
+	flushDelay      time.Duration
 }
 
-func (s *HttpSink) Init(config sinkConfig) error {
-	s.name = "HttpSink"
-	if len(config.Host) == 0 || len(config.Port) == 0 || len(config.Database) == 0 {
-		return errors.New("`host`, `port` and `database` config options required for TCP sink")
+func (s *HttpSink) Write(m lp.CCMetric) error {
+	if s.buffer.Len() == 0 && s.flushDelay != 0 {
+		// This is the first write since the last flush, start the flushTimer!
+		if s.flushTimer != nil && s.flushTimer.Stop() {
+			cclog.ComponentDebug("HttpSink", "unexpected: the flushTimer was already running?")
+		}
+
+		// Run a batched flush for all lines that have arrived in the last second
+		s.flushTimer = time.AfterFunc(s.flushDelay, func() {
+			if err := s.Flush(); err != nil {
+				cclog.ComponentError("HttpSink", "flush failed:", err.Error())
+			}
+		})
 	}
 
-	s.client = &http.Client{}
-	s.url = fmt.Sprintf("http://%s:%s/%s", config.Host, config.Port, config.Database)
-	s.port = config.Port
-	s.jwt = config.Password
-	s.buffer = &bytes.Buffer{}
-	s.encoder = influx.NewEncoder(s.buffer)
-	s.encoder.SetPrecision(time.Second)
+	p := m.ToPoint(s.config.MetaAsTags)
 
-	return nil
-}
+	s.lock.Lock()
+	_, err := s.encoder.Encode(p)
+	s.lock.Unlock() // defer does not work here as Flush() takes the lock as well
+
+	if err != nil {
+		return err
+	}
+
+	// Flush synchronously if "flush_delay" is zero
+	if s.flushDelay == 0 {
+		return s.Flush()
+	}
 
-func (s *HttpSink) Write(point lp.CCMetric) error {
-	_, err := s.encoder.Encode(point)
 	return err
 }
 
 func (s *HttpSink) Flush() error {
-	req, err := http.NewRequest(http.MethodPost, s.url, s.buffer)
+	// buffer is read by client.Do, prevent concurrent modifications
+	s.lock.Lock()
+	defer s.lock.Unlock()
+
+	// Do not flush empty buffer
+	if s.buffer.Len() == 0 {
+		return nil
+	}
+
+	// Create new request to send buffer
+	req, err := http.NewRequest(http.MethodPost, s.config.URL, s.buffer)
 	if err != nil {
 		return err
 	}
 
-	if len(s.jwt) != 0 {
-		req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", s.jwt))
+	// Set authorization header
+	if len(s.config.JWT) != 0 {
+		req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", s.config.JWT))
 	}
 
+	// Send
 	res, err := s.client.Do(req)
+
+	// Clear buffer
 	s.buffer.Reset()
 
+	// Handle transport/tcp errors
 	if err != nil {
 		return err
 	}
 
-	if res.StatusCode != 200 {
+	// Handle application errors
+	if res.StatusCode != http.StatusOK {
 		return errors.New(res.Status)
 	}
 
@@ -66,5 +112,60 @@ func (s *HttpSink) Flush() error {
 }
 
 func (s *HttpSink) Close() {
+	s.flushTimer.Stop()
+	if err := s.Flush(); err != nil {
+		cclog.ComponentError("HttpSink", "flush failed:", err.Error())
+	}
 	s.client.CloseIdleConnections()
 }
+
+func NewHttpSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(HttpSink)
+	// Set default values
+	s.name = fmt.Sprintf("HttpSink(%s)", name)
+	s.config.MaxIdleConns = 10
+	s.config.IdleConnTimeout = "5s"
+	s.config.Timeout = "5s"
+	s.config.FlushDelay = "1s"
+
+	// Read config
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			return nil, err
+		}
+	}
+	if len(s.config.URL) == 0 {
+		return nil, errors.New("`url` config option is required for HTTP sink")
+	}
+	if s.config.MaxIdleConns > 0 {
+		s.maxIdleConns = s.config.MaxIdleConns
+	}
+	if len(s.config.IdleConnTimeout) > 0 {
+		t, err := time.ParseDuration(s.config.IdleConnTimeout)
+		if err == nil {
+			s.idleConnTimeout = t
+		}
+	}
+	if len(s.config.Timeout) > 0 {
+		t, err := time.ParseDuration(s.config.Timeout)
+		if err == nil {
+			s.timeout = t
+		}
+	}
+	if len(s.config.FlushDelay) > 0 {
+		t, err := time.ParseDuration(s.config.FlushDelay)
+		if err == nil {
+			s.flushDelay = t
+		}
+	}
+	tr := &http.Transport{
+		MaxIdleConns:    s.maxIdleConns,
+		IdleConnTimeout: s.idleConnTimeout,
+	}
+	s.client = &http.Client{Transport: tr, Timeout: s.timeout}
+	s.buffer = &bytes.Buffer{}
+	s.encoder = influx.NewEncoder(s.buffer)
+	s.encoder.SetPrecision(time.Second)
+	return s, nil
+}

sinks/httpSink.md

@@ -0,0 +1,29 @@
+## `http` sink
+
+The `http` sink uses POST requests to a HTTP server to submit the metrics in the InfluxDB line-protocol format. It uses JSON web tokens for authentification. The sink creates batches of metrics before sending, to reduce the HTTP traffic.
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "http",
+    "meta_as_tags" : true,
+    "url" : "https://my-monitoring.example.com:1234/api/write",
+    "jwt" : "blabla.blabla.blabla",
+    "timeout": "5s",
+    "max_idle_connections" : 10,
+    "idle_connection_timeout" : "5s",
+    "flush_delay": "2s",
+  }
+}
+```
+
+- `type`: makes the sink an `http` sink
+- `meta_as_tags`: print all meta information as tags in the output (optional)
+- `url`: The full URL of the endpoint
+- `jwt`: JSON web tokens for authentification (Using the *Bearer* scheme)
+- `timeout`: General timeout for the HTTP client (default '5s')
+- `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)

sinks/influxAsyncSink.go

@@ -0,0 +1,131 @@
+package sinks
+
+import (
+	"context"
+	"crypto/tls"
+	"encoding/json"
+	"errors"
+	"fmt"
+
+	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"
+)
+
+type InfluxAsyncSinkConfig struct {
+	defaultSinkConfig
+	Host         string `json:"host,omitempty"`
+	Port         string `json:"port,omitempty"`
+	Database     string `json:"database,omitempty"`
+	User         string `json:"user,omitempty"`
+	Password     string `json:"password,omitempty"`
+	Organization string `json:"organization,omitempty"`
+	SSL          bool   `json:"ssl,omitempty"`
+	RetentionPol string `json:"retention_policy,omitempty"`
+	// Maximum number of points sent to server in single request. Default 5000
+	BatchSize uint `json:"batch_size,omitempty"`
+	// Interval, in ms, in which is buffer flushed if it has not been already written (by reaching batch size) . Default 1000ms
+	FlushInterval uint `json:"flush_interval,omitempty"`
+}
+
+type InfluxAsyncSink struct {
+	sink
+	client   influxdb2.Client
+	writeApi influxdb2Api.WriteAPI
+	errors   <-chan error
+	config   InfluxAsyncSinkConfig
+}
+
+func (s *InfluxAsyncSink) connect() error {
+	var auth string
+	var uri string
+	if s.config.SSL {
+		uri = fmt.Sprintf("https://%s:%s", s.config.Host, s.config.Port)
+	} else {
+		uri = fmt.Sprintf("http://%s:%s", s.config.Host, s.config.Port)
+	}
+	if len(s.config.User) == 0 {
+		auth = s.config.Password
+	} else {
+		auth = fmt.Sprintf("%s:%s", s.config.User, s.config.Password)
+	}
+	cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
+	clientOptions := influxdb2.DefaultOptions()
+	if s.config.BatchSize != 0 {
+		clientOptions.SetBatchSize(s.config.BatchSize)
+	}
+	if s.config.FlushInterval != 0 {
+		clientOptions.SetFlushInterval(s.config.FlushInterval)
+	}
+	clientOptions.SetTLSConfig(
+		&tls.Config{
+			InsecureSkipVerify: true,
+		},
+	)
+	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
+	s.writeApi = s.client.WriteAPI(s.config.Organization, s.config.Database)
+	ok, err := s.client.Ping(context.Background())
+	if err != nil {
+		return err
+	}
+	if !ok {
+		return fmt.Errorf("connection to %s not healthy", uri)
+	}
+	return nil
+}
+
+func (s *InfluxAsyncSink) Write(m lp.CCMetric) error {
+	s.writeApi.WritePoint(
+		m.ToPoint(s.config.MetaAsTags),
+	)
+	return nil
+}
+
+func (s *InfluxAsyncSink) Flush() error {
+	s.writeApi.Flush()
+	return nil
+}
+
+func (s *InfluxAsyncSink) Close() {
+	cclog.ComponentDebug(s.name, "Closing InfluxDB connection")
+	s.writeApi.Flush()
+	s.client.Close()
+}
+
+func NewInfluxAsyncSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(InfluxAsyncSink)
+	s.name = fmt.Sprintf("InfluxSink(%s)", name)
+
+	// Set default for maximum number of points sent to server in single request.
+	s.config.BatchSize = 100
+
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			return nil, err
+		}
+	}
+	if len(s.config.Host) == 0 ||
+		len(s.config.Port) == 0 ||
+		len(s.config.Database) == 0 ||
+		len(s.config.Organization) == 0 ||
+		len(s.config.Password) == 0 {
+		return nil, errors.New("not all configuration variables set required by InfluxAsyncSink")
+	}
+
+	// Connect to InfluxDB server
+	if err := s.connect(); err != nil {
+		return nil, fmt.Errorf("unable to connect: %v", err)
+	}
+
+	// Start background: Read from error channel
+	s.errors = s.writeApi.Errors()
+	go func() {
+		for err := range s.errors {
+			cclog.ComponentError(s.name, err.Error())
+		}
+	}()
+
+	return s, nil
+}

sinks/influxAsyncSink.md

@@ -0,0 +1,34 @@
+## `influxasync` sink
+
+The `influxasync` sink uses the official [InfluxDB golang client](https://pkg.go.dev/github.com/influxdata/influxdb-client-go/v2) to write the metrics to an InfluxDB database in a **non-blocking** fashion. It provides only support for V2 write endpoints (InfluxDB 1.8.0 or later).
+
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "influxasync",
+    "meta_as_tags" : true,
+    "database" : "mymetrics",
+    "host": "dbhost.example.com",
+    "port": "4222",
+    "user": "exampleuser",
+    "password" : "examplepw",
+    "organization": "myorg",
+    "ssl": true,
+    "batch_size": 200,
+  }
+}
+```
+
+- `type`: makes the sink an `influxdb` sink
+- `meta_as_tags`: print all meta information as tags in the output (optional)
+- `database`: All metrics are written to this bucket 
+- `host`: Hostname of the InfluxDB database server
+- `port`: Portnumber (as string) of the InfluxDB database server
+- `user`: Username for basic authentification
+- `password`: Password for basic authentification
+- `organization`: Organization in the InfluxDB
+- `ssl`: Use SSL connection
+- `batch_size`: batch up metrics internally, default 100

sinks/influxSink.go

@@ -3,77 +3,73 @@ package sinks
 import (
 	"context"
 	"crypto/tls"
+	"encoding/json"
 	"errors"
 	"fmt"
+
+	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"
-	"log"
 )
 
+type InfluxSinkConfig struct {
+	defaultSinkConfig
+	Host         string `json:"host,omitempty"`
+	Port         string `json:"port,omitempty"`
+	Database     string `json:"database,omitempty"`
+	User         string `json:"user,omitempty"`
+	Password     string `json:"password,omitempty"`
+	Organization string `json:"organization,omitempty"`
+	SSL          bool   `json:"ssl,omitempty"`
+	RetentionPol string `json:"retention_policy,omitempty"`
+}
+
 type InfluxSink struct {
 	sink
-	client    influxdb2.Client
-	writeApi  influxdb2Api.WriteAPIBlocking
-	retPolicy string
+	client   influxdb2.Client
+	writeApi influxdb2Api.WriteAPIBlocking
+	config   InfluxSinkConfig
 }
 
 func (s *InfluxSink) connect() error {
 	var auth string
 	var uri string
-	if s.ssl {
-		uri = fmt.Sprintf("https://%s:%s", s.host, s.port)
+	if s.config.SSL {
+		uri = fmt.Sprintf("https://%s:%s", s.config.Host, s.config.Port)
 	} else {
-		uri = fmt.Sprintf("http://%s:%s", s.host, s.port)
+		uri = fmt.Sprintf("http://%s:%s", s.config.Host, s.config.Port)
 	}
-	if len(s.user) == 0 {
-		auth = s.password
+	if len(s.config.User) == 0 {
+		auth = s.config.Password
 	} else {
-		auth = fmt.Sprintf("%s:%s", s.user, s.password)
+		auth = fmt.Sprintf("%s:%s", s.config.User, s.config.Password)
+	}
+	cclog.ComponentDebug(s.name, "Using URI", uri, "Org", s.config.Organization, "Bucket", s.config.Database)
+	clientOptions := influxdb2.DefaultOptions()
+	clientOptions.SetTLSConfig(
+		&tls.Config{
+			InsecureSkipVerify: true,
+		},
+	)
+	s.client = influxdb2.NewClientWithOptions(uri, auth, clientOptions)
+	s.writeApi = s.client.WriteAPIBlocking(s.config.Organization, s.config.Database)
+	ok, err := s.client.Ping(context.Background())
+	if err != nil {
+		return err
+	}
+	if !ok {
+		return fmt.Errorf("connection to %s not healthy", uri)
 	}
-	log.Print("Using URI ", uri, " Org ", s.organization, " Bucket ", s.database)
-	s.client = influxdb2.NewClientWithOptions(uri, auth,
-		influxdb2.DefaultOptions().SetTLSConfig(&tls.Config{InsecureSkipVerify: true}))
-	s.writeApi = s.client.WriteAPIBlocking(s.organization, s.database)
 	return nil
 }
 
-func (s *InfluxSink) Init(config sinkConfig) error {
-	s.name = "InfluxSink"
-	if len(config.Host) == 0 ||
-		len(config.Port) == 0 ||
-		len(config.Database) == 0 ||
-		len(config.Organization) == 0 ||
-		len(config.Password) == 0 {
-		return errors.New("Not all configuration variables set required by InfluxSink")
-	}
-	s.host = config.Host
-	s.port = config.Port
-	s.database = config.Database
-	s.organization = config.Organization
-	s.user = config.User
-	s.password = config.Password
-	s.ssl = config.SSL
-	s.meta_as_tags = config.MetaAsTags
-	return s.connect()
-}
-
-func (s *InfluxSink) Write(point lp.CCMetric) error {
-	tags := map[string]string{}
-	fields := map[string]interface{}{}
-	for _, t := range point.TagList() {
-		tags[t.Key] = t.Value
-	}
-	if s.meta_as_tags {
-		for _, m := range point.MetaList() {
-			tags[m.Key] = m.Value
-		}
-	}
-	for _, f := range point.FieldList() {
-		fields[f.Key] = f.Value
-	}
-	p := influxdb2.NewPoint(point.Name(), tags, fields, point.Time())
-	err := s.writeApi.WritePoint(context.Background(), p)
+func (s *InfluxSink) Write(m lp.CCMetric) error {
+	err :=
+		s.writeApi.WritePoint(
+			context.Background(),
+			m.ToPoint(s.config.MetaAsTags),
+		)
 	return err
 }
 
@@ -82,6 +78,30 @@ func (s *InfluxSink) Flush() error {
 }
 
 func (s *InfluxSink) Close() {
-	log.Print("Closing InfluxDB connection")
+	cclog.ComponentDebug(s.name, "Closing InfluxDB connection")
 	s.client.Close()
 }
+
+func NewInfluxSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(InfluxSink)
+	s.name = fmt.Sprintf("InfluxSink(%s)", name)
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			return nil, err
+		}
+	}
+	if len(s.config.Host) == 0 ||
+		len(s.config.Port) == 0 ||
+		len(s.config.Database) == 0 ||
+		len(s.config.Organization) == 0 ||
+		len(s.config.Password) == 0 {
+		return nil, errors.New("not all configuration variables set required by InfluxSink")
+	}
+
+	// Connect to InfluxDB server
+	if err := s.connect(); err != nil {
+		return nil, fmt.Errorf("unable to connect: %v", err)
+	}
+	return s, nil
+}

sinks/influxSink.md

@@ -0,0 +1,32 @@
+## `influxdb` sink
+
+The `influxdb` sink uses the official [InfluxDB golang client](https://pkg.go.dev/github.com/influxdata/influxdb-client-go/v2) to write the metrics to an InfluxDB database in a **blocking** fashion. It provides only support for V2 write endpoints (InfluxDB 1.8.0 or later).
+
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "influxdb",
+    "meta_as_tags" : true,
+    "database" : "mymetrics",
+    "host": "dbhost.example.com",
+    "port": "4222",
+    "user": "exampleuser",
+    "password" : "examplepw",
+    "organization": "myorg",
+    "ssl": true,
+  }
+}
+```
+
+- `type`: makes the sink an `influxdb` sink
+- `meta_as_tags`: print all meta information as tags in the output (optional)
+- `database`: All metrics are written to this bucket 
+- `host`: Hostname of the InfluxDB database server
+- `port`: Portnumber (as string) of the InfluxDB database server
+- `user`: Username for basic authentification
+- `password`: Password for basic authentification
+- `organization`: Organization in the InfluxDB
+- `ssl`: Use SSL connection

sinks/libgangliaSink.go

@@ -0,0 +1,286 @@
+package sinks
+
+/*
+#cgo CFLAGS: -DGM_PROTOCOL_GUARD
+#cgo LDFLAGS: -L. -Wl,--unresolved-symbols=ignore-in-object-files
+#include <stdlib.h>
+
+// This is a copy&paste snippet of ganglia.h (BSD-3 license)
+// See https://github.com/ganglia/monitor-core
+// for further information
+
+enum ganglia_slope {
+   GANGLIA_SLOPE_ZERO = 0,
+   GANGLIA_SLOPE_POSITIVE,
+   GANGLIA_SLOPE_NEGATIVE,
+   GANGLIA_SLOPE_BOTH,
+   GANGLIA_SLOPE_UNSPECIFIED,
+   GANGLIA_SLOPE_DERIVATIVE,
+   GANGLIA_SLOPE_LAST_LEGAL_VALUE=GANGLIA_SLOPE_DERIVATIVE
+};
+typedef enum ganglia_slope ganglia_slope_t;
+
+typedef struct Ganglia_pool* Ganglia_pool;
+typedef struct Ganglia_gmond_config* Ganglia_gmond_config;
+typedef struct Ganglia_udp_send_channels* Ganglia_udp_send_channels;
+
+struct Ganglia_metric {
+   Ganglia_pool pool;
+   struct Ganglia_metadata_message *msg;
+   char *value;
+   void *extra;
+};
+typedef struct Ganglia_metric * Ganglia_metric;
+
+#ifdef __cplusplus
+extern "C" {
+#endif
+
+Ganglia_gmond_config Ganglia_gmond_config_create(char *path, int fallback_to_default);
+//void Ganglia_gmond_config_destroy(Ganglia_gmond_config config);
+
+Ganglia_udp_send_channels Ganglia_udp_send_channels_create(Ganglia_pool p, Ganglia_gmond_config config);
+void Ganglia_udp_send_channels_destroy(Ganglia_udp_send_channels channels);
+
+int Ganglia_udp_send_message(Ganglia_udp_send_channels channels, char *buf, int len );
+
+Ganglia_metric Ganglia_metric_create( Ganglia_pool parent_pool );
+int Ganglia_metric_set( Ganglia_metric gmetric, char *name, char *value, char *type, char *units, unsigned int slope, unsigned int tmax, unsigned int dmax);
+int Ganglia_metric_send( Ganglia_metric gmetric, Ganglia_udp_send_channels send_channels );
+//int Ganglia_metadata_send( Ganglia_metric gmetric, Ganglia_udp_send_channels send_channels );
+//int Ganglia_metadata_send_real( Ganglia_metric gmetric, Ganglia_udp_send_channels send_channels, char *override_string );
+void Ganglia_metadata_add( Ganglia_metric gmetric, char *name, char *value );
+//int Ganglia_value_send( Ganglia_metric gmetric, Ganglia_udp_send_channels send_channels );
+void Ganglia_metric_destroy( Ganglia_metric gmetric );
+
+Ganglia_pool Ganglia_pool_create( Ganglia_pool parent );
+void Ganglia_pool_destroy( Ganglia_pool pool );
+
+//ganglia_slope_t cstr_to_slope(const char* str);
+//const char*     slope_to_cstr(unsigned int slope);
+
+#ifdef __cplusplus
+}
+#endif
+*/
+import "C"
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"unsafe"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	"github.com/NVIDIA/go-nvml/pkg/dl"
+)
+
+const (
+	GANGLIA_LIB_NAME     = "libganglia.so"
+	GANGLIA_LIB_DL_FLAGS = dl.RTLD_LAZY | dl.RTLD_GLOBAL
+	GMOND_CONFIG_FILE    = `/etc/ganglia/gmond.conf`
+)
+
+// type LibgangliaSinkSpecialMetric struct {
+// 	MetricName string `json:"metric_name,omitempty"`
+// 	NewName    string `json:"new_name,omitempty"`
+// 	Slope      string `json:"slope,omitempty"`
+// }
+
+type LibgangliaSinkConfig struct {
+	defaultSinkConfig
+	GangliaLib      string `json:"libganglia_path,omitempty"`
+	GmondConfig     string `json:"gmond_config,omitempty"`
+	AddGangliaGroup bool   `json:"add_ganglia_group,omitempty"`
+	AddTypeToName   bool   `json:"add_type_to_name,omitempty"`
+	AddUnits        bool   `json:"add_units,omitempty"`
+	ClusterName     string `json:"cluster_name,omitempty"`
+	//SpecialMetrics  map[string]LibgangliaSinkSpecialMetric `json:"rename_metrics,omitempty"` // Map to rename metric name from key to value
+	//AddTagsAsDesc   bool              `json:"add_tags_as_desc,omitempty"`
+}
+
+type LibgangliaSink struct {
+	sink
+	config         LibgangliaSinkConfig
+	global_context C.Ganglia_pool
+	gmond_config   C.Ganglia_gmond_config
+	send_channels  C.Ganglia_udp_send_channels
+	cstrCache      map[string]*C.char
+}
+
+func (s *LibgangliaSink) Write(point lp.CCMetric) error {
+	var err error = nil
+	var c_name *C.char
+	var c_value *C.char
+	var c_type *C.char
+	var c_unit *C.char
+
+	// helper function for looking up C strings in the cache
+	lookup := func(key string) *C.char {
+		if _, exist := s.cstrCache[key]; !exist {
+			s.cstrCache[key] = C.CString(key)
+		}
+		return s.cstrCache[key]
+	}
+
+	// Get metric name
+	metricname := GangliaMetricRename(point.Name())
+
+	conf := GetCommonGangliaConfig(point)
+	if len(conf.Type) == 0 {
+		conf = GetGangliaConfig(point)
+	}
+	if len(conf.Type) == 0 {
+		return fmt.Errorf("metric %s has no 'value' field", metricname)
+	}
+
+	if s.config.AddTypeToName {
+		metricname = GangliaMetricName(point)
+	}
+
+	c_value = C.CString(conf.Value)
+	c_type = lookup(conf.Type)
+	c_name = lookup(metricname)
+
+	// Add unit
+	unit := ""
+	if s.config.AddUnits {
+		unit = conf.Unit
+	}
+	c_unit = lookup(unit)
+
+	// Determine the slope of the metric. Ganglia's own collector mostly use
+	// 'both' but the mem and swap total uses 'zero'.
+	slope_type := C.GANGLIA_SLOPE_BOTH
+	switch conf.Slope {
+	case "zero":
+		slope_type = C.GANGLIA_SLOPE_ZERO
+	case "both":
+		slope_type = C.GANGLIA_SLOPE_BOTH
+	}
+
+	// Create a new Ganglia metric
+	gmetric := C.Ganglia_metric_create(s.global_context)
+	// Set name, value, type and unit in the Ganglia metric
+	// The default slope_type is both directions, so up and down. Some metrics want 'zero' slope, probably constant.
+	// The 'tmax' value is by default 300.
+	rval := C.int(0)
+	rval = C.Ganglia_metric_set(gmetric, c_name, c_value, c_type, c_unit, C.uint(slope_type), C.uint(conf.Tmax), 0)
+	switch rval {
+	case 1:
+		C.free(unsafe.Pointer(c_value))
+		return errors.New("invalid parameters")
+	case 2:
+		C.free(unsafe.Pointer(c_value))
+		return errors.New("one of your parameters has an invalid character '\"'")
+	case 3:
+		C.free(unsafe.Pointer(c_value))
+		return fmt.Errorf("the type parameter \"%s\" is not a valid type", conf.Type)
+	case 4:
+		C.free(unsafe.Pointer(c_value))
+		return fmt.Errorf("the value parameter \"%s\" does not represent a number", conf.Value)
+	default:
+	}
+
+	// Set the cluster name, otherwise it takes it from the configuration file
+	if len(s.config.ClusterName) > 0 {
+		C.Ganglia_metadata_add(gmetric, lookup("CLUSTER"), lookup(s.config.ClusterName))
+	}
+	// Set the group metadata in the Ganglia metric if configured
+	if s.config.AddGangliaGroup {
+		c_group := lookup(conf.Group)
+		C.Ganglia_metadata_add(gmetric, lookup("GROUP"), c_group)
+	}
+
+	// Now we send the metric
+	// gmetric does provide some more options like description and other options
+	// but they are not provided by the collectors
+	rval = C.Ganglia_metric_send(gmetric, s.send_channels)
+	if rval != 0 {
+		err = fmt.Errorf("there was an error sending metric %s to %d of the send channels ", point.Name(), rval)
+		// fall throuph to use Ganglia_metric_destroy from common cleanup
+	}
+	// Cleanup Ganglia metric
+	C.Ganglia_metric_destroy(gmetric)
+	// Free the value C string, the only one not stored in the cache
+	C.free(unsafe.Pointer(c_value))
+	return err
+}
+
+func (s *LibgangliaSink) Flush() error {
+	return nil
+}
+
+func (s *LibgangliaSink) Close() {
+	// Destroy Ganglia configration struct
+	// (not done by gmetric, I thought I am more clever but no...)
+	//C.Ganglia_gmond_config_destroy(s.gmond_config)
+	// Destroy Ganglia pool
+	C.Ganglia_pool_destroy(s.global_context)
+
+	// Cleanup C string cache
+	for _, cstr := range s.cstrCache {
+		C.free(unsafe.Pointer(cstr))
+	}
+}
+
+func NewLibgangliaSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(LibgangliaSink)
+	var err error = nil
+	s.name = fmt.Sprintf("LibgangliaSink(%s)", name)
+	//s.config.AddTagsAsDesc = false
+	s.config.AddGangliaGroup = false
+	s.config.AddTypeToName = false
+	s.config.AddUnits = true
+	s.config.GmondConfig = string(GMOND_CONFIG_FILE)
+	s.config.GangliaLib = string(GANGLIA_LIB_NAME)
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &s.config)
+		if err != nil {
+			cclog.ComponentError(s.name, "Error reading config:", err.Error())
+			return nil, err
+		}
+	}
+	lib := dl.New(s.config.GangliaLib, GANGLIA_LIB_DL_FLAGS)
+	if lib == nil {
+		return nil, fmt.Errorf("error instantiating DynamicLibrary for %s", s.config.GangliaLib)
+	}
+	err = lib.Open()
+	if err != nil {
+		return nil, fmt.Errorf("error opening %s: %v", s.config.GangliaLib, err)
+	}
+
+	// Set up cache for the C strings
+	s.cstrCache = make(map[string]*C.char)
+	// s.cstrCache["globals"] = C.CString("globals")
+
+	// s.cstrCache["override_hostname"] = C.CString("override_hostname")
+	// s.cstrCache["override_ip"] = C.CString("override_ip")
+
+	// Add some constant strings
+	s.cstrCache["GROUP"] = C.CString("GROUP")
+	s.cstrCache["CLUSTER"] = C.CString("CLUSTER")
+	s.cstrCache[""] = C.CString("")
+
+	// Add cluster name for lookup in Write()
+	if len(s.config.ClusterName) > 0 {
+		s.cstrCache[s.config.ClusterName] = C.CString(s.config.ClusterName)
+	}
+	// Add supported types for later lookup in Write()
+	s.cstrCache["double"] = C.CString("double")
+	s.cstrCache["int32"] = C.CString("int32")
+	s.cstrCache["string"] = C.CString("string")
+
+	// Create Ganglia pool
+	s.global_context = C.Ganglia_pool_create(nil)
+	// Load Ganglia configuration
+	s.cstrCache[s.config.GmondConfig] = C.CString(s.config.GmondConfig)
+	s.gmond_config = C.Ganglia_gmond_config_create(s.cstrCache[s.config.GmondConfig], 0)
+	//globals := C.cfg_getsec(gmond_config, s.cstrCache["globals"])
+	//override_hostname := C.cfg_getstr(globals, s.cstrCache["override_hostname"])
+	//override_ip := C.cfg_getstr(globals, s.cstrCache["override_ip"])
+
+	s.send_channels = C.Ganglia_udp_send_channels_create(s.global_context, s.gmond_config)
+	return s, nil
+}

sinks/libgangliaSink.md

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

sinks/metricSink.go

@@ -1,42 +1,27 @@
 package sinks
 
 import (
-	//	"time"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
-type sinkConfig struct {
-	Type         string `json:"type"`
-	Host         string `json:"host,omitempty"`
-	Port         string `json:"port,omitempty"`
-	Database     string `json:"database,omitempty"`
-	User         string `json:"user,omitempty"`
-	Password     string `json:"password,omitempty"`
-	Organization string `json:"organization,omitempty"`
-	SSL          bool   `json:"ssl,omitempty"`
-	MetaAsTags   bool   `json:"meta_as_tags,omitempty"`
+type defaultSinkConfig struct {
+	MetaAsTags bool   `json:"meta_as_tags,omitempty"`
+	Type       string `json:"type"`
 }
 
 type sink struct {
-	host         string
-	port         string
-	user         string
-	password     string
-	database     string
-	organization string
-	ssl          bool
-	meta_as_tags bool
-	name         string
+	meta_as_tags bool   // Use meta data tags as tags
+	name         string // Name of the sink
 }
 
 type Sink interface {
-	Init(config sinkConfig) error
-	Write(point lp.CCMetric) error
-	Flush() error
-	Close()
-	Name() string
+	Write(point lp.CCMetric) error // Write metric to the sink
+	Flush() error                  // Flush buffered metrics
+	Close()                        // Close / finish metric sink
+	Name() string                  // Name of the metric sink
 }
 
+// Name returns the name of the metric sink
 func (s *sink) Name() string {
 	return s.name
 }

sinks/natsSink.go

@@ -2,64 +2,62 @@ package sinks
 
 import (
 	"bytes"
+	"encoding/json"
 	"errors"
 	"fmt"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 	nats "github.com/nats-io/nats.go"
-	"log"
-	"time"
 )
 
+type NatsSinkConfig struct {
+	defaultSinkConfig
+	Host     string `json:"host,omitempty"`
+	Port     string `json:"port,omitempty"`
+	Database string `json:"database,omitempty"`
+	User     string `json:"user,omitempty"`
+	Password string `json:"password,omitempty"`
+}
+
 type NatsSink struct {
 	sink
 	client  *nats.Conn
 	encoder *influx.Encoder
 	buffer  *bytes.Buffer
+	config  NatsSinkConfig
 }
 
 func (s *NatsSink) connect() error {
-	uinfo := nats.UserInfo(s.user, s.password)
-	uri := fmt.Sprintf("nats://%s:%s", s.host, s.port)
-	log.Print("Using URI ", uri)
+	var err error
+	var uinfo nats.Option = nil
+	var nc *nats.Conn
+	if len(s.config.User) > 0 && len(s.config.Password) > 0 {
+		uinfo = nats.UserInfo(s.config.User, s.config.Password)
+	}
+	uri := fmt.Sprintf("nats://%s:%s", s.config.Host, s.config.Port)
+	cclog.ComponentDebug(s.name, "Connect to", uri)
 	s.client = nil
-	nc, err := nats.Connect(uri, uinfo)
+	if uinfo != nil {
+		nc, err = nats.Connect(uri, uinfo)
+	} else {
+		nc, err = nats.Connect(uri)
+	}
 	if err != nil {
-		log.Fatal(err)
+		cclog.ComponentError(s.name, "Connect to", uri, "failed:", err.Error())
 		return err
 	}
 	s.client = nc
 	return nil
 }
 
-func (s *NatsSink) Init(config sinkConfig) error {
-	s.name = "NatsSink"
-	if len(config.Host) == 0 ||
-		len(config.Port) == 0 ||
-		len(config.Database) == 0 {
-		return errors.New("Not all configuration variables set required by NatsSink")
-	}
-	s.host = config.Host
-	s.port = config.Port
-	s.database = config.Database
-	s.organization = config.Organization
-	s.user = config.User
-	s.password = config.Password
-	// Setup Influx line protocol
-	s.buffer = &bytes.Buffer{}
-	s.buffer.Grow(1025)
-	s.encoder = influx.NewEncoder(s.buffer)
-	s.encoder.SetPrecision(time.Second)
-	s.encoder.SetMaxLineBytes(1024)
-	// Setup infos for connection
-	return s.connect()
-}
-
-func (s *NatsSink) Write(point lp.CCMetric) error {
+func (s *NatsSink) Write(m lp.CCMetric) error {
 	if s.client != nil {
-		_, err := s.encoder.Encode(point)
+		_, err := s.encoder.Encode(m.ToPoint(s.config.MetaAsTags))
 		if err != nil {
-			log.Print(err)
+			cclog.ComponentError(s.name, "Write:", err.Error())
 			return err
 		}
 	}
@@ -68,7 +66,8 @@ func (s *NatsSink) Write(point lp.CCMetric) error {
 
 func (s *NatsSink) Flush() error {
 	if s.client != nil {
-		if err := s.client.Publish(s.database, s.buffer.Bytes()); err != nil {
+		if err := s.client.Publish(s.config.Database, s.buffer.Bytes()); err != nil {
+			cclog.ComponentError(s.name, "Flush:", err.Error())
 			return err
 		}
 		s.buffer.Reset()
@@ -77,8 +76,36 @@ func (s *NatsSink) Flush() error {
 }
 
 func (s *NatsSink) Close() {
-	log.Print("Closing Nats connection")
 	if s.client != nil {
+		cclog.ComponentDebug(s.name, "Close")
 		s.client.Close()
 	}
 }
+
+func NewNatsSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(NatsSink)
+	s.name = fmt.Sprintf("NatsSink(%s)", name)
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			cclog.ComponentError(s.name, "Error reading config for", s.name, ":", err.Error())
+			return nil, err
+		}
+	}
+	if len(s.config.Host) == 0 ||
+		len(s.config.Port) == 0 ||
+		len(s.config.Database) == 0 {
+		return nil, errors.New("not all configuration variables set required by NatsSink")
+	}
+	// Setup Influx line protocol
+	s.buffer = &bytes.Buffer{}
+	s.buffer.Grow(1025)
+	s.encoder = influx.NewEncoder(s.buffer)
+	s.encoder.SetPrecision(time.Second)
+	s.encoder.SetMaxLineBytes(1024)
+	// Setup infos for connection
+	if err := s.connect(); err != nil {
+		return nil, fmt.Errorf("Unable to connect: %v", err)
+	}
+	return s, nil
+}

sinks/natsSink.md

@@ -0,0 +1,28 @@
+## `nats` sink
+
+The `nats` sink publishes all metrics into a NATS network. The publishing key is the database name provided in the configuration file
+
+
+### Configuration structure
+
+```json
+{
+  "<name>": {
+    "type": "nats",
+    "meta_as_tags" : true,
+    "database" : "mymetrics",
+    "host": "dbhost.example.com",
+    "port": "4222",
+    "user": "exampleuser",
+    "password" : "examplepw"
+  }
+}
+```
+
+- `type`: makes the sink an `nats` sink
+- `meta_as_tags`: print all meta information as tags in the output (optional)
+- `database`: All metrics are published with this subject
+- `host`: Hostname of the NATS server
+- `port`: Portnumber (as string) of the NATS server
+- `user`: Username for basic authentification
+- `password`: Password for basic authentification

sinks/prometheusSink.go

@@ -0,0 +1,199 @@
+package sinks
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"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"
+	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/promhttp"
+)
+
+type PrometheusSinkConfig struct {
+	defaultSinkConfig
+	Host             string `json:"host,omitempty"`
+	Port             string `json:"port"`
+	Path             string `json:"path,omitempty"`
+	GroupAsNameSpace bool   `json:"group_as_namespace,omitempty"`
+	// User       string `json:"user,omitempty"`
+	// Password   string `json:"password,omitempty"`
+	// FlushDelay string `json:"flush_delay,omitempty"`
+}
+
+type PrometheusSink struct {
+	sink
+	config       PrometheusSinkConfig
+	labelMetrics map[string]*prometheus.GaugeVec
+	nodeMetrics  map[string]prometheus.Gauge
+	promWg       sync.WaitGroup
+	promServer   *http.Server
+}
+
+func intToFloat64(input interface{}) (float64, error) {
+	switch value := input.(type) {
+	case float64:
+		return value, nil
+	case float32:
+		return float64(value), nil
+	case int:
+		return float64(value), nil
+	case int32:
+		return float64(value), nil
+	case int64:
+		return float64(value), nil
+	}
+	return 0, errors.New("cannot cast value to float64")
+}
+
+func getLabelValue(metric lp.CCMetric) []string {
+	labelValues := []string{}
+	if tid, tidok := metric.GetTag("type-id"); tidok && metric.HasTag("type") {
+		labelValues = append(labelValues, tid)
+	}
+	if d, ok := metric.GetTag("device"); ok {
+		labelValues = append(labelValues, d)
+	} else if d, ok := metric.GetMeta("device"); ok {
+		labelValues = append(labelValues, d)
+	}
+	return labelValues
+}
+
+func getLabelNames(metric lp.CCMetric) []string {
+	labelNames := []string{}
+	if t, tok := metric.GetTag("type"); tok && metric.HasTag("type-id") {
+		labelNames = append(labelNames, t)
+	}
+	if _, ok := metric.GetTag("device"); ok {
+		labelNames = append(labelNames, "device")
+	} else if _, ok := metric.GetMeta("device"); ok {
+		labelNames = append(labelNames, "device")
+	}
+	return labelNames
+}
+
+func (s *PrometheusSink) newMetric(metric lp.CCMetric) error {
+	var value float64 = 0
+	name := metric.Name()
+	opts := prometheus.GaugeOpts{
+		Name: name,
+	}
+	labels := getLabelNames(metric)
+	labelValues := getLabelValue(metric)
+	if len(labels) > 0 && len(labels) != len(labelValues) {
+		return fmt.Errorf("cannot detect metric labels for metric %s", name)
+	}
+
+	if metricValue, ok := metric.GetField("value"); ok {
+		if floatValue, err := intToFloat64(metricValue); err == nil {
+			value = floatValue
+		} else {
+			return fmt.Errorf("metric %s with value '%v' cannot be casted to float64", name, metricValue)
+		}
+	}
+	if s.config.GroupAsNameSpace && metric.HasMeta("group") {
+		g, _ := metric.GetMeta("group")
+		opts.Namespace = strings.ToLower(g)
+	}
+
+	if len(labels) > 0 {
+		new := prometheus.NewGaugeVec(opts, labels)
+		new.WithLabelValues(labelValues...).Set(value)
+		s.labelMetrics[name] = new
+		prometheus.Register(new)
+	} else {
+		new := prometheus.NewGauge(opts)
+		new.Set(value)
+		s.nodeMetrics[name] = new
+		prometheus.Register(new)
+	}
+	return nil
+}
+
+func (s *PrometheusSink) updateMetric(metric lp.CCMetric) error {
+	var value float64 = 0.0
+	name := metric.Name()
+	labelValues := getLabelValue(metric)
+
+	if metricValue, ok := metric.GetField("value"); ok {
+		if floatValue, err := intToFloat64(metricValue); err == nil {
+			value = floatValue
+		} else {
+			return fmt.Errorf("metric %s with value '%v' cannot be casted to float64", name, metricValue)
+		}
+	}
+
+	if len(labelValues) > 0 {
+		if _, ok := s.labelMetrics[name]; !ok {
+			err := s.newMetric(metric)
+			if err != nil {
+				return err
+			}
+		}
+		s.labelMetrics[name].WithLabelValues(labelValues...).Set(value)
+	} else {
+		if _, ok := s.labelMetrics[name]; !ok {
+			err := s.newMetric(metric)
+			if err != nil {
+				return err
+			}
+		}
+		s.nodeMetrics[name].Set(value)
+	}
+	return nil
+}
+
+func (s *PrometheusSink) Write(m lp.CCMetric) error {
+	return s.updateMetric(m)
+}
+
+func (s *PrometheusSink) Flush() error {
+	return nil
+}
+
+func (s *PrometheusSink) Close() {
+	cclog.ComponentDebug(s.name, "CLOSE")
+	s.promServer.Shutdown(context.Background())
+	s.promWg.Wait()
+}
+
+func NewPrometheusSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(PrometheusSink)
+	s.name = "PrometheusSink"
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			cclog.ComponentError(s.name, "Error reading config for", s.name, ":", err.Error())
+			return nil, err
+		}
+	}
+	if len(s.config.Port) == 0 {
+		err := errors.New("not all configuration variables set required by PrometheusSink")
+		cclog.ComponentError(s.name, err.Error())
+		return nil, err
+	}
+	s.labelMetrics = make(map[string]*prometheus.GaugeVec)
+	s.nodeMetrics = make(map[string]prometheus.Gauge)
+	s.promWg.Add(1)
+	go func() {
+		router := mux.NewRouter()
+		// Prometheus endpoint
+		router.Path("/" + s.config.Path).Handler(promhttp.Handler())
+
+		url := fmt.Sprintf("%s:%s", s.config.Host, s.config.Port)
+		cclog.ComponentDebug(s.name, "Serving Prometheus metrics at", fmt.Sprintf("%s:%s/%s", s.config.Host, s.config.Port, s.config.Path))
+		s.promServer = &http.Server{Addr: url, Handler: router}
+		err := s.promServer.ListenAndServe()
+		if err != nil && err.Error() != "http: Server closed" {
+			cclog.ComponentError(s.name, err.Error())
+		}
+		s.promWg.Done()
+	}()
+	return s, nil
+}

sinks/prometheusSink.md

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

sinks/sampleSink.go

@@ -0,0 +1,73 @@
+package sinks
+
+import (
+	"encoding/json"
+	"fmt"
+	"log"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+)
+
+type SampleSinkConfig struct {
+	// 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'
+	sink
+	config SampleSinkConfig // entry point to the SampleSinkConfig
+}
+
+// Implement functions required for Sink interface
+// Write(...), Flush(), Close()
+// See: metricSink.go
+
+// Code to submit a single CCMetric to the sink
+func (s *SampleSink) Write(point lp.CCMetric) error {
+	log.Print(point)
+	return nil
+}
+
+// If the sink uses batched sends internally, you can tell to flush its buffers
+func (s *SampleSink) Flush() error {
+	return nil
+}
+
+// Close sink: close network connection, close files, close libraries, ...
+func (s *SampleSink) Close() {
+	cclog.ComponentDebug(s.name, "CLOSE")
+}
+
+// New function to create a new instance of the sink
+// Initialize the sink by giving it a name and reading in the config JSON
+func NewSampleSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(SampleSink)
+
+	// Set name of sampleSink
+	// The name should be chosen in such a way that different instances of SampleSink can be distinguished
+	s.name = fmt.Sprintf("SampleSink(%s)", name) // Always specify a name here
+
+	// Set defaults in s.config
+	// Allow overwriting these defaults by reading config JSON
+
+	// Read in the config JSON
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			return nil, err
+		}
+	}
+
+	// Check if all required fields in the config are set
+	// E.g. use 'len(s.config.Option) > 0' for string settings
+
+	// Establish connection to the server, library, ...
+	// Check required files exist and lookup path(s) of executable(s)
+
+	// Return (nil, meaningful error message) in case of errors
+	return s, nil
+}

sinks/sinkManager.go

@@ -2,6 +2,7 @@ package sinks
 
 import (
 	"encoding/json"
+	"fmt"
 	"os"
 	"sync"
 
@@ -9,76 +10,90 @@ import (
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 )
 
+const SINK_MAX_FORWARD = 50
+
 // Map of all available sinks
-var AvailableSinks = map[string]Sink{
-	"influxdb": new(InfluxSink),
-	"stdout":   new(StdoutSink),
-	"nats":     new(NatsSink),
-	"http":     new(HttpSink),
-	"ganglia":  new(GangliaSink),
+var AvailableSinks = map[string]func(name string, config json.RawMessage) (Sink, error){
+	"ganglia":     NewGangliaSink,
+	"libganglia":  NewLibgangliaSink,
+	"stdout":      NewStdoutSink,
+	"nats":        NewNatsSink,
+	"influxdb":    NewInfluxSink,
+	"influxasync": NewInfluxAsyncSink,
+	"http":        NewHttpSink,
 }
 
 // Metric collector manager data structure
 type sinkManager struct {
-	input   chan lp.CCMetric // input channel
-	outputs []Sink           // List of sinks to use
-	done    chan bool        // channel to finish / stop metric sink manager
-	wg      *sync.WaitGroup  // wait group for all goroutines in cc-metric-collector
-	config  []sinkConfig     // json encoded config for sink manager
+	input      chan lp.CCMetric // input channel
+	done       chan bool        // channel to finish / stop metric sink manager
+	wg         *sync.WaitGroup  // wait group for all goroutines in cc-metric-collector
+	sinks      map[string]Sink  // Mapping sink name to sink
+	maxForward int              // number of metrics to write maximally in one iteration
 }
 
 // Sink manager access functions
 type SinkManager interface {
 	Init(wg *sync.WaitGroup, sinkConfigFile string) error
 	AddInput(input chan lp.CCMetric)
-	AddOutput(config json.RawMessage) error
+	AddOutput(name string, config json.RawMessage) error
 	Start()
 	Close()
 }
 
+// Init initializes the sink manager by:
+// * Reading its configuration file
+// * Adding the configured sinks and providing them with the corresponding config
 func (sm *sinkManager) Init(wg *sync.WaitGroup, sinkConfigFile string) error {
 	sm.input = nil
-	sm.outputs = make([]Sink, 0)
 	sm.done = make(chan bool)
 	sm.wg = wg
-	sm.config = make([]sinkConfig, 0)
+	sm.sinks = make(map[string]Sink, 0)
+	sm.maxForward = SINK_MAX_FORWARD
+
+	if len(sinkConfigFile) == 0 {
+		return nil
+	}
 
 	// Read sink config file
-	if len(sinkConfigFile) > 0 {
-		configFile, err := os.Open(sinkConfigFile)
+	configFile, err := os.Open(sinkConfigFile)
+	if err != nil {
+		cclog.ComponentError("SinkManager", err.Error())
+		return err
+	}
+	defer configFile.Close()
+
+	// Parse config
+	jsonParser := json.NewDecoder(configFile)
+	var rawConfigs map[string]json.RawMessage
+	err = jsonParser.Decode(&rawConfigs)
+	if err != nil {
+		cclog.ComponentError("SinkManager", err.Error())
+		return err
+	}
+
+	// Start sinks
+	for name, raw := range rawConfigs {
+		err = sm.AddOutput(name, raw)
 		if err != nil {
 			cclog.ComponentError("SinkManager", err.Error())
-			return err
-		}
-		defer configFile.Close()
-		jsonParser := json.NewDecoder(configFile)
-		var rawConfigs []json.RawMessage
-		err = jsonParser.Decode(&rawConfigs)
-		if err != nil {
-			cclog.ComponentError("SinkManager", err.Error())
-			return err
-		}
-		for _, raw := range rawConfigs {
-			err = sm.AddOutput(raw)
-			if err != nil {
-				continue
-			}
+			continue
 		}
 	}
+
 	return nil
 }
 
+// Start starts the sink managers background task, which
+// distributes received metrics to the sinks
 func (sm *sinkManager) Start() {
-	batchcount := 20
-
 	sm.wg.Add(1)
 	go func() {
 		defer sm.wg.Done()
 
 		// Sink manager is done
 		done := func() {
-			for _, s := range sm.outputs {
-				s.Flush()
+			for _, s := range sm.sinks {
 				s.Close()
 			}
 
@@ -86,6 +101,16 @@ func (sm *sinkManager) Start() {
 			cclog.ComponentDebug("SinkManager", "DONE")
 		}
 
+		toTheSinks := func(p lp.CCMetric) {
+			// Send received metric to all outputs
+			cclog.ComponentDebug("SinkManager", "WRITE", p)
+			for _, s := range sm.sinks {
+				if err := s.Write(p); err != nil {
+					cclog.ComponentError("SinkManager", "WRITE", s.Name(), "write failed:", err.Error())
+				}
+			}
+		}
+
 		for {
 			select {
 			case <-sm.done:
@@ -93,21 +118,11 @@ func (sm *sinkManager) Start() {
 				return
 
 			case p := <-sm.input:
-				// Send received metric to all outputs
-				cclog.ComponentDebug("SinkManager", "WRITE", p)
-				for _, s := range sm.outputs {
-					s.Write(p)
+				toTheSinks(p)
+				for i := 0; len(sm.input) > 0 && i < sm.maxForward; i++ {
+					p := <-sm.input
+					toTheSinks(p)
 				}
-
-				// Flush all outputs
-				if batchcount == 0 {
-					cclog.ComponentDebug("SinkManager", "FLUSH")
-					for _, s := range sm.outputs {
-						s.Flush()
-					}
-					batchcount = 20
-				}
-				batchcount--
 			}
 		}
 	}()
@@ -121,29 +136,26 @@ func (sm *sinkManager) AddInput(input chan lp.CCMetric) {
 	sm.input = input
 }
 
-func (sm *sinkManager) AddOutput(rawConfig json.RawMessage) error {
+func (sm *sinkManager) AddOutput(name string, rawConfig json.RawMessage) error {
 	var err error
-	var config sinkConfig
-	if len(rawConfig) > 3 {
-		err = json.Unmarshal(rawConfig, &config)
+	var sinkConfig defaultSinkConfig
+	if len(rawConfig) > 0 {
+		err := json.Unmarshal(rawConfig, &sinkConfig)
 		if err != nil {
-			cclog.ComponentError("SinkManager", "SKIP", config.Type, "JSON config error:", err.Error())
 			return err
 		}
 	}
-	if _, found := AvailableSinks[config.Type]; !found {
-		cclog.ComponentError("SinkManager", "SKIP", config.Type, "unknown sink:", err.Error())
+	if _, found := AvailableSinks[sinkConfig.Type]; !found {
+		cclog.ComponentError("SinkManager", "SKIP", name, "unknown sink:", sinkConfig.Type)
 		return err
 	}
-	s := AvailableSinks[config.Type]
-	err = s.Init(config)
+	s, err := AvailableSinks[sinkConfig.Type](name, rawConfig)
 	if err != nil {
 		cclog.ComponentError("SinkManager", "SKIP", s.Name(), "initialization failed:", err.Error())
 		return err
 	}
-	sm.outputs = append(sm.outputs, s)
-	sm.config = append(sm.config, config)
-	cclog.ComponentDebug("SinkManager", "ADD SINK", s.Name())
+	sm.sinks[name] = s
+	cclog.ComponentDebug("SinkManager", "ADD SINK", s.Name(), "with name", fmt.Sprintf("'%s'", name))
 	return nil
 }
 
@@ -157,7 +169,7 @@ func (sm *sinkManager) Close() {
 
 // New creates a new initialized sink manager
 func New(wg *sync.WaitGroup, sinkConfigFile string) (SinkManager, error) {
-	sm := &sinkManager{}
+	sm := new(sinkManager)
 	err := sm.Init(wg, sinkConfigFile)
 	if err != nil {
 		return nil, err

sinks/sqliteSink.go

@@ -1,256 +0,0 @@
-package sinks
-
-import (
-	"database/sql"
-	"errors"
-	"fmt"
-	"log"
-	"sort"
-	"strings"
-
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	_ "github.com/mattn/go-sqlite3"
-)
-
-const SQLITE3_TIMESTAMP_NAME = `timestamp`
-const SQLITE3_TIMESTAMP_TYPE = `TIMESTAMP NOT NULL`
-
-type SqliteTable struct {
-	columns     []string
-	coltypes    []string
-	createQuery string
-	insertQuery string
-	primkeys    []string
-}
-
-type SqliteSink struct {
-	sink
-	db     *sql.DB
-	tables map[string]SqliteTable
-}
-
-type StrList []string
-
-func (list StrList) Len() int { return len(list) }
-
-func (list StrList) Swap(i, j int) { list[i], list[j] = list[j], list[i] }
-
-func (list StrList) Less(i, j int) bool {
-	var si string = list[i]
-	var sj string = list[j]
-	var si_lower = strings.ToLower(si)
-	var sj_lower = strings.ToLower(sj)
-	if si_lower == sj_lower {
-		return si < sj
-	}
-	return si_lower < sj_lower
-}
-
-func (s *SqliteSink) Init(config sinkConfig) error {
-	var err error
-	if len(config.Database) == 0 {
-		return errors.New("not all configuration variables set required by SqliteSink")
-	}
-	s.host = config.Host
-	s.port = config.Port
-	s.database = config.Database
-	s.organization = config.Organization
-	s.user = config.User
-	s.password = config.Password
-	log.Print("Opening Sqlite3 database ", s.database)
-	uri := fmt.Sprintf("file:./%s.db", s.database)
-	if len(s.user) > 0 && len(s.password) > 0 {
-		uri += fmt.Sprintf("?_auth&_auth_user=%s&_auth_pass=%s", s.user, s.password)
-	}
-	s.db, err = sql.Open("sqlite3", uri)
-	if err != nil {
-		log.Fatal(err)
-		s.db = nil
-		return err
-	}
-	s.tables = make(map[string]SqliteTable)
-
-	return nil
-}
-
-func getkeylist(point lp.CCMetric, include_meta bool) []string {
-	keys := make([]string, 0)
-	for k := range point.Tags() {
-		keys = append(keys, k)
-	}
-	if include_meta {
-		for k := range point.Meta() {
-			keys = append(keys, k)
-		}
-	}
-	for k := range point.Fields() {
-		keys = append(keys, k)
-	}
-	keys = append(keys, SQLITE3_TIMESTAMP_NAME)
-	sort.Sort(StrList(keys))
-	return keys
-}
-
-func getvaluelist(point lp.CCMetric, keys []string) []string {
-	values := make([]string, 0)
-	for _, key := range keys {
-		if key == SQLITE3_TIMESTAMP_NAME {
-			values = append(values, point.Time().String())
-		} else if val, ok := point.GetTag(key); ok {
-			values = append(values, val)
-		} else if val, ok := point.GetMeta(key); ok {
-			values = append(values, val)
-		} else if ival, ok := point.GetField(key); ok {
-			values = append(values, fmt.Sprintf("%v", ival))
-		} else {
-			values = append(values, "NULL")
-		}
-	}
-	return values
-}
-func gettypelist(point lp.CCMetric, keys []string) []string {
-	types := make([]string, 0)
-	for _, key := range keys {
-		if key == SQLITE3_TIMESTAMP_NAME {
-			types = append(types, SQLITE3_TIMESTAMP_TYPE)
-			continue
-		}
-		if point.HasTag(key) {
-			types = append(types, "TEXT")
-			continue
-		}
-		if point.HasMeta(key) {
-			types = append(types, "TEXT")
-			continue
-		}
-		ival, ok := point.GetField(key)
-		if ok {
-			switch ival.(type) {
-			case float64:
-				types = append(types, "DOUBLE")
-			case float32:
-				types = append(types, "FLOAT")
-			case string:
-				types = append(types, "TEXT")
-			case int:
-				types = append(types, "INT")
-			case int64:
-				types = append(types, "INT8")
-			}
-		}
-	}
-	return types
-}
-
-func getprimkey(keys []string) []string {
-	primkeys := make([]string, 0)
-	primkeys = append(primkeys, SQLITE3_TIMESTAMP_NAME)
-	for _, key := range keys {
-		switch key {
-		case "hostname":
-			primkeys = append(primkeys, "hostname")
-		case "type":
-			primkeys = append(primkeys, "type")
-		case "type-id":
-			primkeys = append(primkeys, "type-id")
-		}
-	}
-	return primkeys
-}
-
-func newCreateQuery(tablename string, keys []string, types []string, primkeys []string) string {
-
-	keytypelist := make([]string, 0)
-	for i, key := range keys {
-		keytypelist = append(keytypelist, fmt.Sprintf("%s %s", key, types[i]))
-	}
-	keytypelist = append(keytypelist, fmt.Sprintf("PRIMARY KEY (%s)", strings.Join(primkeys, ",")))
-	stmt := fmt.Sprintf("create table if not exists %s (%s);", tablename, keytypelist)
-	return stmt
-}
-
-func newInsertQuery(tablename string, keys []string) string {
-	v := strings.Repeat("?,", len(keys)) + "?"
-	stmt := fmt.Sprintf("insert into %s (%s) values(%s);", tablename, strings.Join(keys, ","), v)
-	return stmt
-}
-
-func (s *SqliteSink) Write(point lp.CCMetric) error {
-
-	if s.db != nil {
-		measurement := point.Name()
-		if tab, ok := s.tables[measurement]; !ok {
-			var tab SqliteTable
-			tab.columns = getkeylist(point, s.meta_as_tags)
-			tab.coltypes = gettypelist(point, tab.columns)
-			tab.primkeys = getprimkey(tab.columns)
-			tab.createQuery = newCreateQuery(measurement, tab.columns, tab.coltypes, tab.primkeys)
-			tab.insertQuery = newInsertQuery(measurement, tab.columns)
-
-			tx, err := s.db.Begin()
-			if err != nil {
-				cclog.ComponentError("SqliteSink", "Init DB session failed:", err.Error())
-				return err
-			}
-			_, err = tx.Exec(tab.createQuery)
-			if err != nil {
-				cclog.ComponentError("SqliteSink", "Execute CreateQuery failed:", err.Error())
-				return err
-			}
-			stmt, err := tx.Prepare(tab.insertQuery)
-			if err != nil {
-				cclog.ComponentError("SqliteSink", "Prepare InsertQuery failed:", err.Error())
-				return err
-			}
-			defer stmt.Close()
-			_, err = stmt.Exec(getvaluelist(point, tab.columns))
-			if err != nil {
-				cclog.ComponentError("SqliteSink", "Execute InsertQuery failed:", err.Error())
-				return err
-			}
-			tx.Commit()
-			s.tables[measurement] = tab
-
-		} else {
-
-			keys := getkeylist(point, s.meta_as_tags)
-			if len(keys) > len(tab.columns) {
-				cclog.ComponentDebug("SqliteSink", "Metric", measurement, "has different keys as creation keys, ignoring addition keys")
-			} else if len(keys) < len(tab.columns) {
-				cclog.ComponentDebug("SqliteSink", "Metric", measurement, "has different keys as creation keys, setting missing values with 'NULL'")
-			}
-			values := getvaluelist(point, tab.columns)
-			tx, err := s.db.Begin()
-			if err != nil {
-				cclog.ComponentError("SqliteSink", "Init DB session failed:", err.Error())
-				return err
-			}
-			stmt, err := tx.Prepare(tab.insertQuery)
-			if err != nil {
-				cclog.ComponentError("SqliteSink", "Prepare InsertQuery failed:", err.Error())
-				return err
-			}
-			defer stmt.Close()
-			_, err = stmt.Exec(values)
-			if err != nil {
-				cclog.ComponentError("SqliteSink", "Execute InsertQuery failed:", err.Error())
-				return err
-			}
-			tx.Commit()
-
-		}
-	}
-	return nil
-}
-
-func (s *SqliteSink) Flush() error {
-	return nil
-}
-
-func (s *SqliteSink) Close() {
-	log.Print("Closing Sqlite3 database ", s.database)
-	if s.db != nil {
-		s.db.Close()
-	}
-}

sinks/stdoutSink.go

@@ -1,8 +1,9 @@
 package sinks
 
 import (
+	"encoding/json"
 	"fmt"
-	"math"
+	"os"
 	"strings"
 
 	//	"time"
@@ -10,60 +11,59 @@ import (
 )
 
 type StdoutSink struct {
-	sink
+	sink   // meta_as_tags, name
+	output *os.File
+	config struct {
+		defaultSinkConfig
+		Output string `json:"output_file,omitempty"`
+	}
 }
 
-func (s *StdoutSink) Init(config sinkConfig) error {
-	s.name = "StdoutSink"
-	s.meta_as_tags = config.MetaAsTags
-	return nil
-}
-
-func (s *StdoutSink) Write(point lp.CCMetric) error {
-	var tagsstr []string
-	var fieldstr []string
-	for _, t := range point.TagList() {
-		tagsstr = append(tagsstr, fmt.Sprintf("%s=%s", t.Key, t.Value))
-	}
-	if s.meta_as_tags {
-		for _, m := range point.MetaList() {
-			tagsstr = append(tagsstr, fmt.Sprintf("%s=%s", m.Key, m.Value))
-		}
-	}
-	for _, f := range point.FieldList() {
-		switch f.Value.(type) {
-		case float64:
-			if !math.IsNaN(f.Value.(float64)) {
-				fieldstr = append(fieldstr, fmt.Sprintf("%s=%v", f.Key, f.Value.(float64)))
-			} else {
-				fieldstr = append(fieldstr, fmt.Sprintf("%s=0.0", f.Key))
-			}
-		case float32:
-			if !math.IsNaN(float64(f.Value.(float32))) {
-				fieldstr = append(fieldstr, fmt.Sprintf("%s=%v", f.Key, f.Value.(float32)))
-			} else {
-				fieldstr = append(fieldstr, fmt.Sprintf("%s=0.0", f.Key))
-			}
-		case int:
-			fieldstr = append(fieldstr, fmt.Sprintf("%s=%d", f.Key, f.Value.(int)))
-		case int64:
-			fieldstr = append(fieldstr, fmt.Sprintf("%s=%d", f.Key, f.Value.(int64)))
-		case string:
-			fieldstr = append(fieldstr, fmt.Sprintf("%s=%q", f.Key, f.Value.(string)))
-		default:
-			fieldstr = append(fieldstr, fmt.Sprintf("%s=%v", f.Key, f.Value))
-		}
-	}
-	if len(tagsstr) > 0 {
-		fmt.Printf("%s,%s %s %d\n", point.Name(), strings.Join(tagsstr, ","), strings.Join(fieldstr, ","), point.Time().Unix())
-	} else {
-		fmt.Printf("%s %s %d\n", point.Name(), strings.Join(fieldstr, ","), point.Time().Unix())
-	}
+func (s *StdoutSink) Write(m lp.CCMetric) error {
+	fmt.Fprint(
+		s.output,
+		m.ToLineProtocol(s.meta_as_tags),
+	)
 	return nil
 }
 
 func (s *StdoutSink) Flush() error {
+	s.output.Sync()
 	return nil
 }
 
-func (s *StdoutSink) Close() {}
+func (s *StdoutSink) Close() {
+	if s.output != os.Stdout && s.output != os.Stderr {
+		s.output.Close()
+	}
+}
+
+func NewStdoutSink(name string, config json.RawMessage) (Sink, error) {
+	s := new(StdoutSink)
+	s.name = fmt.Sprintf("StdoutSink(%s)", name)
+	if len(config) > 0 {
+		err := json.Unmarshal(config, &s.config)
+		if err != nil {
+			return nil, err
+		}
+	}
+
+	s.output = os.Stdout
+	if len(s.config.Output) > 0 {
+		switch strings.ToLower(s.config.Output) {
+		case "stdout":
+			s.output = os.Stdout
+		case "stderr":
+			s.output = os.Stderr
+		default:
+			f, err := os.OpenFile(s.config.Output, os.O_CREATE|os.O_WRONLY, os.FileMode(0600))
+			if err != nil {
+				return nil, err
+			}
+			s.output = f
+		}
+	}
+	s.meta_as_tags = s.config.MetaAsTags
+
+	return s, nil
+}

sinks/stdoutSink.md

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