Merge branch 'develop' into smartmon_collector

.github/workflows/Release.yml

@@ -133,13 +133,63 @@ jobs:
         name: cc-metric-collector SRPM for UBI 8
         path: ${{ steps.rpmbuild.outputs.SRPM }}
 
+  #
+  # Build on Ubuntu 20.04 using official go package
+  #
+  Ubuntu-focal-build:
+    runs-on: ubuntu-latest
+    container: ubuntu:20.04
+    # The job outputs link to the outputs of the 'debrename' step
+    # Only job outputs can be used in child jobs
+    outputs:
+      deb : ${{steps.debrename.outputs.DEB}}
+    steps:
+    # Use apt to install development packages
+    - name: Install development packages
+      run: |
+          apt update && apt --assume-yes upgrade
+          apt --assume-yes install build-essential sed git wget bash
+    # Checkout git repository and submodules
+    # fetch-depth must be 0 to use git describe
+    # See: https://github.com/marketplace/actions/checkout
+    - name: Checkout
+      uses: actions/checkout@v2
+      with:
+        submodules: recursive
+        fetch-depth: 0
+    # Use official golang package
+    - name: Install Golang
+      run: |
+          wget -q https://go.dev/dl/go1.19.1.linux-amd64.tar.gz
+          tar -C /usr/local -xzf go1.19.1.linux-amd64.tar.gz
+          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
+          go version
+    - name: DEB build MetricCollector
+      id: dpkg-build
+      run: |
+          export PATH=/usr/local/go/bin:/usr/local/go/pkg/tool/linux_amd64:$PATH
+          make DEB
+    - name: Rename DEB (add '_ubuntu20.04')
+      id: debrename
+      run: |
+        OLD_DEB_NAME=$(echo "${{steps.dpkg-build.outputs.DEB}}" | rev | cut -d '.' -f 2- | rev)
+        NEW_DEB_FILE="${OLD_DEB_NAME}_ubuntu20.04.deb"
+        mv "${{steps.dpkg-build.outputs.DEB}}" "${NEW_DEB_FILE}"
+        echo "::set-output name=DEB::${NEW_DEB_FILE}"
+    # See: https://github.com/actions/upload-artifact
+    - name: Save DEB as artifact
+      uses: actions/upload-artifact@v2
+      with:
+        name: cc-metric-collector DEB for Ubuntu 20.04
+        path: ${{ steps.debrename.outputs.DEB }}
+
   #
   # Create release with fresh RPMs
   #
   Release:
     runs-on: ubuntu-latest
     # We need the RPMs, so add dependency
-    needs: [AlmaLinux-RPM-build, UBI-8-RPM-build]
+    needs: [AlmaLinux-RPM-build, UBI-8-RPM-build, Ubuntu-focal-build]
 
     steps:
     # See: https://github.com/actions/download-artifact
@@ -161,6 +211,11 @@ jobs:
       with:
         name: cc-metric-collector SRPM for UBI 8
 
+    - name: Download Ubuntu 20.04 DEB
+      uses: actions/download-artifact@v2
+      with:
+        name: cc-metric-collector DEB for Ubuntu 20.04
+
     # The download actions do not publish the name of the downloaded file,
     # so we re-use the job outputs of the parent jobs. The files are all
     # downloaded to the current folder.
@@ -174,14 +229,17 @@ jobs:
         ALMA_85_SRPM=$(basename "${{ needs.AlmaLinux-RPM-build.outputs.srpm}}")
         UBI_8_RPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.rpm}}")
         UBI_8_SRPM=$(basename "${{ needs.UBI-8-RPM-build.outputs.srpm}}")
+        U_2004_DEB=$(basename "${{ needs.Ubuntu-focal-build.outputs.deb}}")
         echo "ALMA_85_RPM::${ALMA_85_RPM}"
         echo "ALMA_85_SRPM::${ALMA_85_SRPM}"
         echo "UBI_8_RPM::${UBI_8_RPM}"
         echo "UBI_8_SRPM::${UBI_8_SRPM}"
+        echo "U_2004_DEB::${U_2004_DEB}"
         echo "::set-output name=ALMA_85_RPM::${ALMA_85_RPM}"
         echo "::set-output name=ALMA_85_SRPM::${ALMA_85_SRPM}"
         echo "::set-output name=UBI_8_RPM::${UBI_8_RPM}"
         echo "::set-output name=UBI_8_SRPM::${UBI_8_SRPM}"
+        echo "::set-output name=U_2004_DEB::${U_2004_DEB}"
 
     # See: https://github.com/softprops/action-gh-release
     - name: Release
@@ -194,3 +252,4 @@ jobs:
          ${{ steps.files.outputs.ALMA_85_SRPM }}
          ${{ steps.files.outputs.UBI_8_RPM }}
          ${{ steps.files.outputs.UBI_8_SRPM }}
+         ${{ steps.files.outputs.U_2004_DEB }}

cc-metric-collector.go

@@ -15,10 +15,10 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	mr "github.com/ClusterCockpit/cc-metric-collector/internal/metricRouter"
-	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 type CentralConfigFile struct {

collectors/beegfsmetaMetric.go

@@ -5,7 +5,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"os"
 	"os/exec"
 	"os/user"
@@ -14,8 +14,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const DEFAULT_BEEGFS_CMD = "beegfs-ctl"
@@ -115,7 +115,7 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetr
 		return
 	}
 	//get mounpoint
-	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
+	buffer, _ := os.ReadFile(string("/proc/mounts"))
 	mounts := strings.Split(string(buffer), "\n")
 	var mountpoints []string
 	for _, line := range mounts {
@@ -157,9 +157,9 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMetr
 		if err != nil {
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
-			data, _ := ioutil.ReadAll(cmdStderr)
+			data, _ := io.ReadAll(cmdStderr)
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = ioutil.ReadAll(cmdStdout)
+			data, _ = io.ReadAll(cmdStdout)
 			fmt.Fprintf(os.Stderr, "BeegfsMetaCollector.Read(): command stdout: \"%s\"\n", string(data))
 			return
 		}

collectors/beegfsstorageMetric.go

@@ -5,7 +5,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"os"
 	"os/exec"
 	"os/user"
@@ -14,8 +14,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // Struct for the collector-specific JSON config
@@ -108,7 +108,7 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
 		return
 	}
 	//get mounpoint
-	buffer, _ := ioutil.ReadFile(string("/proc/mounts"))
+	buffer, _ := os.ReadFile(string("/proc/mounts"))
 	mounts := strings.Split(string(buffer), "\n")
 	var mountpoints []string
 	for _, line := range mounts {
@@ -149,9 +149,9 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
 		if err != nil {
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): Failed to execute command \"%s\": %s\n", cmd.String(), err.Error())
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command exit code: \"%d\"\n", cmd.ProcessState.ExitCode())
-			data, _ := ioutil.ReadAll(cmdStderr)
+			data, _ := io.ReadAll(cmdStderr)
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stderr: \"%s\"\n", string(data))
-			data, _ = ioutil.ReadAll(cmdStdout)
+			data, _ = io.ReadAll(cmdStdout)
 			fmt.Fprintf(os.Stderr, "BeegfsStorageCollector.Read(): command stdout: \"%s\"\n", string(data))
 			return
 		}

collectors/collectorManager.go

@@ -6,9 +6,9 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
-	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
+	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 // Map of all available metric collectors
@@ -37,7 +37,8 @@ var AvailableCollectors = map[string]MetricCollector{
 	"beegfs_meta":     new(BeegfsMetaCollector),
 	"beegfs_storage":  new(BeegfsStorageCollector),
 	"rocm_smi":        new(RocmSmiCollector),
-	"schedstat":	   new(SchedstatCollector),
+	"smartmon":        new(SmartMonCollector),
+	"schedstat":       new(SchedstatCollector),
 }
 
 // Metric collector manager data structure

collectors/cpufreqCpuinfoMetric.go

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 //

collectors/cpufreqMetric.go

@@ -3,14 +3,14 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"golang.org/x/sys/unix"
 )
 
@@ -88,7 +88,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 
 		// Read package ID
 		physicalPackageIDFile := filepath.Join(cpuDir, "topology", "physical_package_id")
-		line, err := ioutil.ReadFile(physicalPackageIDFile)
+		line, err := os.ReadFile(physicalPackageIDFile)
 		if err != nil {
 			return fmt.Errorf("unable to read physical package ID from file '%s': %v", physicalPackageIDFile, err)
 		}
@@ -100,7 +100,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
 
 		// Read core ID
 		coreIDFile := filepath.Join(cpuDir, "topology", "core_id")
-		line, err = ioutil.ReadFile(coreIDFile)
+		line, err = os.ReadFile(coreIDFile)
 		if err != nil {
 			return fmt.Errorf("unable to read core ID from file '%s': %v", coreIDFile, err)
 		}
@@ -188,7 +188,7 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		}
 
 		// Read current frequency
-		line, err := ioutil.ReadFile(t.scalingCurFreqFile)
+		line, err := os.ReadFile(t.scalingCurFreqFile)
 		if err != nil {
 			cclog.ComponentError(
 				m.name,

collectors/cpustatMetric.go

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	sysconf "github.com/tklauser/go-sysconf"
 )
 
@@ -22,12 +22,12 @@ type CpustatCollectorConfig struct {
 
 type CpustatCollector struct {
 	metricCollector
-	config   CpustatCollectorConfig
+	config        CpustatCollectorConfig
-	lastTimestamp time.Time                   // Store time stamp of last tick to derive values
+	lastTimestamp time.Time // Store time stamp of last tick to derive values
-	matches  map[string]int
+	matches       map[string]int
-	cputags  map[string]map[string]string
+	cputags       map[string]map[string]string
-	nodetags map[string]string
+	nodetags      map[string]string
-	olddata  map[string]map[string]int64
+	olddata       map[string]map[string]int64
 }
 
 func (m *CpustatCollector) Init(config json.RawMessage) error {
@@ -118,7 +118,7 @@ func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]st
 			}
 		}
 	}
-	
+
 	for name, value := range values {
 		y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value * 100}, now)
 		if err == nil {

collectors/customCmdMetric.go

@@ -3,13 +3,13 @@ package collectors
 import (
 	"encoding/json"
 	"errors"
-	"io/ioutil"
 	"log"
+	"os"
 	"os/exec"
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 )
 
@@ -53,7 +53,7 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
 		}
 	}
 	for _, f := range m.config.Files {
-		_, err = ioutil.ReadFile(f)
+		_, err = os.ReadFile(f)
 		if err == nil {
 			m.files = append(m.files, f)
 		} else {
@@ -106,7 +106,7 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetri
 		}
 	}
 	for _, file := range m.files {
-		buffer, err := ioutil.ReadFile(file)
+		buffer, err := os.ReadFile(file)
 		if err != nil {
 			log.Print(err)
 			return

collectors/diskstatMetric.go

@@ -8,8 +8,8 @@ import (
 	"syscall"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 //	"log"

collectors/gpfsMetric.go

@@ -5,7 +5,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"log"
 	"os/exec"
 	"os/user"
@@ -13,8 +13,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const DEFAULT_GPFS_CMD = "mmpmon"
@@ -118,8 +118,8 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	cmd.Stderr = cmdStderr
 	err := cmd.Run()
 	if err != nil {
-		dataStdErr, _ := ioutil.ReadAll(cmdStderr)
+		dataStdErr, _ := io.ReadAll(cmdStderr)
-		dataStdOut, _ := ioutil.ReadAll(cmdStdout)
+		dataStdOut, _ := io.ReadAll(cmdStdout)
 		cclog.ComponentError(
 			m.name,
 			fmt.Sprintf("Read(): Failed to execute command \"%s\": %v\n", cmd.String(), err),

collectors/infinibandMetric.go

@@ -2,11 +2,10 @@ package collectors
 
 import (
 	"fmt"
-	"io/ioutil"
 	"os"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"golang.org/x/sys/unix"
 
 	"encoding/json"
@@ -19,8 +18,9 @@ import (
 const IB_BASEPATH = "/sys/class/infiniband/"
 
 type InfinibandCollectorMetric struct {
-	path string
+	path  string
-	unit string
+	unit  string
+	scale int64
 }
 
 type InfinibandCollectorInfo struct {
@@ -84,7 +84,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	for _, path := range ibDirs {
 
 		// Skip, when no LID is assigned
-		line, err := ioutil.ReadFile(filepath.Join(path, "lid"))
+		line, err := os.ReadFile(filepath.Join(path, "lid"))
 		if err != nil {
 			continue
 		}
@@ -113,10 +113,10 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 		// Check access to counter files
 		countersDir := filepath.Join(path, "counters")
 		portCounterFiles := map[string]InfinibandCollectorMetric{
-			"ib_recv":      {path: filepath.Join(countersDir, "port_rcv_data"), unit: "bytes"},
+			"ib_recv":      {path: filepath.Join(countersDir, "port_rcv_data"), unit: "bytes", scale: 4},
-			"ib_xmit":      {path: filepath.Join(countersDir, "port_xmit_data"), unit: "bytes"},
+			"ib_xmit":      {path: filepath.Join(countersDir, "port_xmit_data"), unit: "bytes", scale: 4},
-			"ib_recv_pkts": {path: filepath.Join(countersDir, "port_rcv_packets"), unit: "packets"},
+			"ib_recv_pkts": {path: filepath.Join(countersDir, "port_rcv_packets"), unit: "packets", scale: 1},
-			"ib_xmit_pkts": {path: filepath.Join(countersDir, "port_xmit_packets"), unit: "packets"},
+			"ib_xmit_pkts": {path: filepath.Join(countersDir, "port_xmit_packets"), unit: "packets", scale: 1},
 		}
 		for _, counter := range portCounterFiles {
 			err := unix.Access(counter.path, unix.R_OK)
@@ -174,7 +174,7 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 		for counterName, counterDef := range info.portCounterFiles {
 
 			// Read counter file
-			line, err := ioutil.ReadFile(counterDef.path)
+			line, err := os.ReadFile(counterDef.path)
 			if err != nil {
 				cclog.ComponentError(
 					m.name,
@@ -191,6 +191,8 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMetr
 					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterName, data, err))
 				continue
 			}
+			// Scale raw value
+			v *= counterDef.scale
 
 			// Send absolut values
 			if m.config.SendAbsoluteValues {

collectors/iostatMetric.go

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

collectors/ipmiMetric.go

@@ -10,7 +10,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const IPMITOOL_PATH = `ipmitool`

collectors/likwidMetric.go

@@ -12,7 +12,6 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"io/ioutil"
 	"math"
 	"os"
 	"os/signal"
@@ -24,10 +23,10 @@ import (
 	"time"
 	"unsafe"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
-	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 	"github.com/NVIDIA/go-nvml/pkg/dl"
 )
 
@@ -154,12 +153,13 @@ func getBaseFreq() float64 {
 	}
 	var freq float64 = math.NaN()
 	for _, f := range files {
-		buffer, err := ioutil.ReadFile(f)
+		buffer, err := os.ReadFile(f)
 		if err == nil {
 			data := strings.Replace(string(buffer), "\n", "", -1)
 			x, err := strconv.ParseInt(data, 0, 64)
 			if err == nil {
-				freq = float64(x) * 1e6
+				freq = float64(x)
+				break
 			}
 		}
 	}
@@ -168,11 +168,11 @@ func getBaseFreq() float64 {
 		C.power_init(0)
 		info := C.get_powerInfo()
 		if float64(info.baseFrequency) != 0 {
-			freq = float64(info.baseFrequency) * 1e6
+			freq = float64(info.baseFrequency)
 		}
 		C.power_finalize()
 	}
-	return freq
+	return freq * 1e3
 }
 
 func (m *LikwidCollector) Init(config json.RawMessage) error {

collectors/likwidMetric.md

@@ -7,6 +7,9 @@ The `likwid` collector is probably the most complicated collector. The LIKWID li
   "likwid": {
     "force_overwrite" : false,
     "invalid_to_zero" : false,
+    "liblikwid_path" : "/path/to/liblikwid.so",
+    "accessdaemon_path" : "/folder/that/contains/likwid-accessD",
+    "access_mode" : "direct or accessdaemon or perf_event",
     "eventsets": [
       {
         "events" : {

collectors/loadavgMetric.go

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

collectors/lustreMetric.go

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const LUSTRE_SYSFS = `/sys/fs/lustre`

collectors/memstatMetric.go

@@ -12,8 +12,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const MEMSTATFILE = "/proc/meminfo"
@@ -68,7 +68,8 @@ func getStats(filename string) map[string]MemstatStats {
 		} else if len(linefields) == 5 {
 			v, err := strconv.ParseFloat(linefields[3], 64)
 			if err == nil {
-				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
+				cclog.ComponentDebug("getStats", strings.Trim(linefields[2], ":"), v, linefields[4])
+				stats[strings.Trim(linefields[2], ":")] = MemstatStats{
 					value: v,
 					unit:  linefields[4],
 				}
@@ -160,7 +161,6 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 
 func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 	if !m.init {
-		cclog.ComponentPrint(m.name, "Here")
 		return
 	}
 
@@ -188,16 +188,20 @@ func (m *MemstatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 			unit := ""
 			if totalVal, total := stats["MemTotal"]; total {
 				if freeVal, free := stats["MemFree"]; free {
+					memUsed = totalVal.value - freeVal.value
+					if len(totalVal.unit) > 0 {
+						unit = totalVal.unit
+					} else if len(freeVal.unit) > 0 {
+						unit = freeVal.unit
+					}
 					if bufVal, buffers := stats["Buffers"]; buffers {
+						memUsed -= bufVal.value
+						if len(bufVal.unit) > 0 && len(unit) == 0 {
+							unit = bufVal.unit
+						}
 						if cacheVal, cached := stats["Cached"]; cached {
-							memUsed = totalVal.value - (freeVal.value + bufVal.value + cacheVal.value)
+							memUsed -= cacheVal.value
-							if len(totalVal.unit) > 0 {
+							if len(cacheVal.unit) > 0 && len(unit) == 0 {
-								unit = totalVal.unit
-							} else if len(freeVal.unit) > 0 {
-								unit = freeVal.unit
-							} else if len(bufVal.unit) > 0 {
-								unit = bufVal.unit
-							} else if len(cacheVal.unit) > 0 {
 								unit = cacheVal.unit
 							}
 						}

collectors/metricCollector.go

@@ -5,7 +5,7 @@ import (
 	"fmt"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 type MetricCollector interface {

collectors/netstatMetric.go

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const NETSTATFILE = "/proc/net/dev"

collectors/nfsMetric.go

@@ -11,7 +11,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // First part contains the code for the general NfsCollector.

collectors/numastatsMetric.go

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 //

collectors/nvidiaMetric.go

@@ -8,8 +8,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"github.com/NVIDIA/go-nvml/pkg/nvml"
 )
 

collectors/rocmsmiMetric.go

@@ -6,8 +6,8 @@ import (
 	"fmt"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"github.com/ClusterCockpit/go-rocm-smi/pkg/rocm_smi"
 )
 
@@ -66,14 +66,14 @@ func (m *RocmSmiCollector) Init(config json.RawMessage) error {
 
 	ret := rocm_smi.Init()
 	if ret != rocm_smi.STATUS_SUCCESS {
-		err = errors.New("Failed to initialize ROCm SMI library")
+		err = errors.New("failed to initialize ROCm SMI library")
 		cclog.ComponentError(m.name, err.Error())
 		return err
 	}
 
 	numDevs, ret := rocm_smi.NumMonitorDevices()
 	if ret != rocm_smi.STATUS_SUCCESS {
-		err = errors.New("Failed to get number of GPUs from ROCm SMI library")
+		err = errors.New("failed to get number of GPUs from ROCm SMI library")
 		cclog.ComponentError(m.name, err.Error())
 		return err
 	}
@@ -98,14 +98,14 @@ func (m *RocmSmiCollector) Init(config json.RawMessage) error {
 		}
 		device, ret := rocm_smi.DeviceGetHandleByIndex(i)
 		if ret != rocm_smi.STATUS_SUCCESS {
-			err = fmt.Errorf("Failed to get handle for GPU %d", i)
+			err = fmt.Errorf("failed to get handle for GPU %d", i)
 			cclog.ComponentError(m.name, err.Error())
 			return err
 		}
 
 		pciInfo, ret := rocm_smi.DeviceGetPciInfo(device)
 		if ret != rocm_smi.STATUS_SUCCESS {
-			err = fmt.Errorf("Failed to get PCI information for GPU %d", i)
+			err = fmt.Errorf("failed to get PCI information for GPU %d", i)
 			cclog.ComponentError(m.name, err.Error())
 			return err
 		}

collectors/sampleMetric.go

@@ -4,8 +4,8 @@ import (
 	"encoding/json"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // These are the fields we read from the JSON configuration

collectors/sampleTimerMetric.go

@@ -5,8 +5,8 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // These are the fields we read from the JSON configuration

collectors/schedstatMetric.go

@@ -1,17 +1,17 @@
 package collectors
 
 import (
+	"bufio"
 	"encoding/json"
 	"fmt"
-	"bufio"
-	"time"
-	"os"
-	"strings"
-	"strconv"
 	"math"
+	"os"
+	"strconv"
+	"strings"
+	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const SCHEDSTATFILE = `/proc/schedstat`
@@ -25,11 +25,11 @@ type SchedstatCollectorConfig struct {
 // defined by metricCollector (name, init, ...)
 type SchedstatCollector struct {
 	metricCollector
-	config SchedstatCollectorConfig // the configuration structure
+	config        SchedstatCollectorConfig     // the configuration structure
-	lastTimestamp time.Time                   // Store time stamp of last tick to derive values
+	lastTimestamp time.Time                    // Store time stamp of last tick to derive values
-	meta   map[string]string          // default meta information
+	meta          map[string]string            // default meta information
-	cputags   map[string]map[string]string          // default tags
+	cputags       map[string]map[string]string // default tags
-	olddata   map[string]map[string]int64          // default tags
+	olddata       map[string]map[string]int64  // default tags
 }
 
 // Functions to implement MetricCollector interface
@@ -52,7 +52,7 @@ func (m *SchedstatCollector) Init(config json.RawMessage) error {
 	// Define meta information sent with each metric
 	// (Can also be dynamic or this is the basic set with extension through AddMeta())
 	m.meta = map[string]string{"source": m.name, "group": "SCHEDSTAT"}
-	
+
 	// Read in the JSON configuration
 	if len(config) > 0 {
 		err = json.Unmarshal(config, &m.config)
@@ -83,12 +83,11 @@ func (m *SchedstatCollector) Init(config json.RawMessage) error {
 			running, _ := strconv.ParseInt(linefields[7], 10, 64)
 			waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
 			m.cputags[linefields[0]] = map[string]string{"type": "hwthread", "type-id": fmt.Sprintf("%d", cpu)}
-			m.olddata[linefields[0]] = map[string]int64{"running" : running, "waiting" : waiting}
+			m.olddata[linefields[0]] = map[string]int64{"running": running, "waiting": waiting}
 			num_cpus++
 		}
 	}
 
-
 	// Save current timestamp
 	m.lastTimestamp = time.Now()
 
@@ -102,7 +101,7 @@ func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]
 	waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
 	diff_running := running - m.olddata[linefields[0]]["running"]
 	diff_waiting := waiting - m.olddata[linefields[0]]["waiting"]
-	
+
 	var l_running float64 = float64(diff_running) / tsdelta.Seconds() / (math.Pow(1000, 3))
 	var l_waiting float64 = float64(diff_waiting) / tsdelta.Seconds() / (math.Pow(1000, 3))
 
@@ -110,11 +109,11 @@ func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]
 	m.olddata[linefields[0]]["waiting"] = waiting
 	value := l_running + l_waiting
 
- 	y, err := lp.New("cpu_load_core", tags, m.meta, map[string]interface{}{"value": value}, now)
+	y, err := lp.New("cpu_load_core", tags, m.meta, map[string]interface{}{"value": value}, now)
 	if err == nil {
 		// Send it to output channel
 		output <- y
-	} 
+	}
 }
 
 // Read collects all metrics belonging to the sample collector

collectors/smartmonMetric.go

@@ -0,0 +1,220 @@
+package collectors
+
+import (
+	"encoding/json"
+	"os/exec"
+	"time"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+)
+
+type SmartMonCollectorConfig struct {
+	UseSudo        bool     `json:"use_sudo"`
+	ExcludeDevices []string `json:"exclude_devices"`
+}
+
+type SmartMonCollector struct {
+	metricCollector
+	config      SmartMonCollectorConfig // the configuration structure
+	meta        map[string]string       // default meta information
+	tags        map[string]string       // default tags
+	devices     []string                // smartmon devices
+	sudoCmd     string                  // Full path to 'sudo' command
+	smartCtlCmd string                  // Full path to 'smartctl' command
+}
+
+func (m *SmartMonCollector) getSmartmonDevices() error {
+	var command *exec.Cmd
+	var scan struct {
+		Devices []struct {
+			Name string `json:"name"`
+			Type string `json:"type"`
+		} `json:"devices"`
+	}
+	m.devices = make([]string, 0)
+	if m.config.UseSudo {
+		command = exec.Command(m.sudoCmd, m.smartCtlCmd, "--scan", "-j")
+	} else {
+		command = exec.Command(m.smartCtlCmd, "--scan", "-j")
+	}
+	command.Wait()
+	stdout, err := command.Output()
+	if err != nil {
+		return err
+	}
+	err = json.Unmarshal(stdout, &scan)
+	if err != nil {
+		return err
+	}
+	for _, d := range scan.Devices {
+		if len(d.Name) > 0 {
+			m.devices = append(m.devices, d.Name)
+		}
+	}
+
+	return nil
+}
+
+func (m *SmartMonCollector) Init(config json.RawMessage) error {
+	var err error = nil
+	m.name = "SmartMonCollector"
+	m.setup()
+	m.parallel = true
+	m.meta = map[string]string{"source": m.name, "group": "Disk"}
+	m.tags = map[string]string{"type": "node", "stype": "disk"}
+	// 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
+		}
+	}
+	if m.config.UseSudo {
+		p, err := exec.LookPath("sudo")
+		if err != nil {
+			return err
+		}
+		m.sudoCmd = p
+	}
+	p, err := exec.LookPath("smartctl")
+	if err != nil {
+		return err
+	}
+	m.smartCtlCmd = p
+	err = m.getSmartmonDevices()
+	if err != nil {
+		return err
+	}
+
+	m.init = true
+	return err
+}
+
+type SmartMonData struct {
+	SerialNumber string `json:"serial_number"`
+	UserCapacity struct {
+		Blocks int `json:"blocks"`
+		Bytes  int `json:"bytes"`
+	} `json:"user_capacity"`
+	HealthLog struct {
+		Temperature        int `json:"temperature"`
+		PercentageUsed     int `json:"percentage_used"`
+		AvailableSpare     int `json:"available_spare"`
+		DataUnitsRead      int `json:"data_units_read"`
+		DataUnitsWrite     int `json:"data_units_written"`
+		HostReads          int `json:"host_reads"`
+		HostWrites         int `json:"host_writes"`
+		PowerCycles        int `json:"power_cycles"`
+		PowerOnHours       int `json:"power_on_hours"`
+		UnsafeShutdowns    int `json:"unsafe_shutdowns"`
+		MediaErrors        int `json:"media_errors"`
+		NumErrorLogEntries int `json:"num_err_log_entries"`
+		WarnTempTime       int `json:"warning_temp_time"`
+		CriticalTempTime   int `json:"critical_comp_time"`
+	} `json:"nvme_smart_health_information_log"`
+}
+
+func (m *SmartMonCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	timestamp := time.Now()
+	for _, d := range m.devices {
+		var command *exec.Cmd
+		var data SmartMonData
+		if m.config.UseSudo {
+			command = exec.Command(m.sudoCmd, m.smartCtlCmd, "-j", "-a", d)
+		} else {
+			command = exec.Command(m.smartCtlCmd, "-j", "-a", d)
+		}
+		command.Wait()
+		stdout, err := command.Output()
+		if err != nil {
+			cclog.ComponentError(m.name, "cannot read data for device", d)
+			continue
+		}
+		err = json.Unmarshal(stdout, &data)
+		if err != nil {
+			cclog.ComponentError(m.name, "cannot unmarshal data for device", d)
+			continue
+		}
+		y, err := lp.New("smartmon_temp", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.Temperature}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			y.AddMeta("unit", "degC")
+			output <- y
+		}
+		y, err = lp.New("smartmon_percent_used", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.PercentageUsed}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			y.AddMeta("unit", "percent")
+			output <- y
+		}
+		y, err = lp.New("smartmon_avail_spare", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.AvailableSpare}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			y.AddMeta("unit", "percent")
+			output <- y
+		}
+		y, err = lp.New("smartmon_data_units_read", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.DataUnitsRead}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+		y, err = lp.New("smartmon_data_units_write", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.DataUnitsWrite}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+		y, err = lp.New("smartmon_host_reads", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.HostReads}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+		y, err = lp.New("smartmon_host_writes", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.HostWrites}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+		y, err = lp.New("smartmon_power_cycles", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.PowerCycles}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+		y, err = lp.New("smartmon_power_on", m.tags, m.meta, map[string]interface{}{"value": int64(data.HealthLog.PowerOnHours) * 3600}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			y.AddMeta("unit", "seconds")
+			output <- y
+		}
+		y, err = lp.New("smartmon_unsafe_shutdowns", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.UnsafeShutdowns}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+		y, err = lp.New("smartmon_media_errors", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.MediaErrors}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+		y, err = lp.New("smartmon_errlog_entries", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.NumErrorLogEntries}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+		y, err = lp.New("smartmon_warn_temp_time", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.WarnTempTime}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+		y, err = lp.New("smartmon_crit_temp_time", m.tags, m.meta, map[string]interface{}{"value": data.HealthLog.CriticalTempTime}, timestamp)
+		if err == nil {
+			y.AddTag("stype-id", d)
+			output <- y
+		}
+	}
+
+}
+
+func (m *SmartMonCollector) Close() {
+	m.init = false
+}

collectors/smartmonMetric.md

@@ -0,0 +1,29 @@
+## `smartmon` collector
+
+```json
+  "smartmon": {
+    "use_sudo" : true,
+    "exclude_devices": [
+      "/dev/sda",
+    ]
+  }
+```
+
+The `smartmon` collector reads the data from the command `smartctl`. It retrieves S.M.A.R.T data from disks
+
+Metrics:
+* `smartmon_temp`: Temperature of the device (`unit=degC`)
+* `smartmon_avail_spare`: Amount of spare left (`unit=percent`)
+* `smartmon_percent_used`: Percentage of the device is used (`unit=percent`)
+* `smartmon_data_units_read`: Read data units
+* `smartmon_data_units_write`: Written data units
+* `smartmon_host_reads`: Read operations
+* `smartmon_host_writes`: Write operations
+* `smartmon_power_cycles`: Number of power cycles
+* `smartmon_power_on`: Seconds the device is powered on (`unit=seconds`)
+* `smartmon_unsafe_shutdowns`: Count of unsafe shutdowns
+* `smartmon_media_errors`: Media errors of the device
+* `smartmon_errlog_entries`: Error log entries
+* `smartmon_warn_temp_time`: Time above the warning temperature threshold
+* `smartmon_crit_temp_time`: Time above the critical temperature threshold
+

collectors/tempMetric.go

@@ -3,14 +3,14 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 // See: https://www.kernel.org/doc/html/latest/hwmon/sysfs-interface.html
@@ -83,14 +83,14 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 
 		// sensor name
 		nameFile := filepath.Join(filepath.Dir(file), "name")
-		name, err := ioutil.ReadFile(nameFile)
+		name, err := os.ReadFile(nameFile)
 		if err == nil {
 			sensor.name = strings.TrimSpace(string(name))
 		}
 
 		// sensor label
 		labelFile := strings.TrimSuffix(file, "_input") + "_label"
-		label, err := ioutil.ReadFile(labelFile)
+		label, err := os.ReadFile(labelFile)
 		if err == nil {
 			sensor.label = strings.TrimSpace(string(label))
 		}
@@ -117,7 +117,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		}
 
 		// Sensor file
-		_, err = ioutil.ReadFile(file)
+		_, err = os.ReadFile(file)
 		if err != nil {
 			continue
 		}
@@ -139,7 +139,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		// max temperature
 		if m.config.ReportMaxTemp {
 			maxTempFile := strings.TrimSuffix(file, "_input") + "_max"
-			if buffer, err := ioutil.ReadFile(maxTempFile); err == nil {
+			if buffer, err := os.ReadFile(maxTempFile); err == nil {
 				if x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64); err == nil {
 					sensor.maxTempName = strings.Replace(sensor.metricName, "temp", "max_temp", 1)
 					sensor.maxTemp = x / 1000
@@ -150,7 +150,7 @@ func (m *TempCollector) Init(config json.RawMessage) error {
 		// critical temperature
 		if m.config.ReportCriticalTemp {
 			criticalTempFile := strings.TrimSuffix(file, "_input") + "_crit"
-			if buffer, err := ioutil.ReadFile(criticalTempFile); err == nil {
+			if buffer, err := os.ReadFile(criticalTempFile); err == nil {
 				if x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64); err == nil {
 					sensor.critTempName = strings.Replace(sensor.metricName, "temp", "crit_temp", 1)
 					sensor.critTemp = x / 1000
@@ -175,7 +175,7 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMetric) {
 
 	for _, sensor := range m.sensors {
 		// Read sensor file
-		buffer, err := ioutil.ReadFile(sensor.file)
+		buffer, err := os.ReadFile(sensor.file)
 		if err != nil {
 			cclog.ComponentError(
 				m.name,

collectors/topprocsMetric.go

@@ -9,7 +9,7 @@ import (
 	"strings"
 	"time"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const MAX_NUM_PROCS = 10

go.mod

@@ -13,6 +13,7 @@ require (
 	github.com/nats-io/nats.go v1.16.0
 	github.com/prometheus/client_golang v1.12.2
 	github.com/stmcginnis/gofish v0.13.0
+	github.com/tklauser/go-sysconf v0.3.10
 	golang.org/x/sys v0.0.0-20220712014510-0a85c31ab51e
 )
 
@@ -31,6 +32,7 @@ require (
 	github.com/prometheus/common v0.37.0 // indirect
 	github.com/prometheus/procfs v0.7.3 // indirect
 	github.com/shopspring/decimal v1.3.1 // indirect
+	github.com/tklauser/numcpus v0.4.0 // indirect
 	golang.org/x/crypto v0.0.0-20220622213112-05595931fe9d // indirect
 	golang.org/x/net v0.0.0-20220708220712-1185a9018129 // indirect
 	google.golang.org/protobuf v1.28.0 // indirect

go.sum

@@ -287,6 +287,10 @@ github.com/stretchr/testify v1.6.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.1 h1:5TQK59W5E3v0r2duFAb7P95B6hEeOyEnHRa8MjYSMTY=
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
+github.com/tklauser/go-sysconf v0.3.10 h1:IJ1AZGZRWbY8T5Vfk04D9WOA5WSejdflXxP03OUqALw=
+github.com/tklauser/go-sysconf v0.3.10/go.mod h1:C8XykCvCb+Gn0oNCWPIlcb0RuglQTYaQ2hGm7jmxEFk=
+github.com/tklauser/numcpus v0.4.0 h1:E53Dm1HjH1/R2/aoCtXtPgzmElmn51aOkhCFSuZq//o=
+github.com/tklauser/numcpus v0.4.0/go.mod h1:1+UI3pD8NW14VMwdgJNJ1ESk2UnwhAnz5hMwiKKqXCQ=
 github.com/ugorji/go v1.1.7/go.mod h1:kZn38zHttfInRq0xu/PH0az30d+z6vm202qpg1oXVMw=
 github.com/ugorji/go v1.2.7/go.mod h1:nF9osbDWLy6bDVv/Rtoh6QgnvNDpmCalQV5urGCCS6M=
 github.com/ugorji/go/codec v1.1.7/go.mod h1:Ax+UKWsSmolVDwsd+7N3ZtXu+yMGCf907BLYF3GoBXY=
@@ -445,6 +449,7 @@ golang.org/x/sys v0.0.0-20211019181941-9d821ace8654/go.mod h1:oPkhp1MJrh7nUepCBc
 golang.org/x/sys v0.0.0-20211103235746-7861aae1554b/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20211216021012-1d35b9e2eb4e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220114195835-da31bd327af9/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220128215802-99c3d69c2c27/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220513210249-45d2b4557a2a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220712014510-0a85c31ab51e h1:NHvCuwuS43lGnYhten69ZWqi2QOj/CiDNcKbVqwVoew=
 golang.org/x/sys v0.0.0-20220712014510-0a85c31ab51e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=

internal/metricAggregator/metricAggregator.go

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

internal/metricAggregator/metricAggregatorFunctions.go

@@ -8,8 +8,8 @@ import (
 	"sort"
 	"strings"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	topo "github.com/ClusterCockpit/cc-metric-collector/internal/ccTopology"
+	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 )
 
 /*

internal/metricRouter/metricCache.go

@@ -4,11 +4,11 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
-	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 )
 
 type metricCachePeriod struct {

internal/metricRouter/metricRouter.go

@@ -7,11 +7,11 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
 	agg "github.com/ClusterCockpit/cc-metric-collector/internal/metricAggregator"
-	mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
+	mct "github.com/ClusterCockpit/cc-metric-collector/pkg/multiChanTicker"
 	units "github.com/ClusterCockpit/cc-units"
 )
 

pkg/ccTopology/ccTopology.go

@@ -10,7 +10,7 @@ import (
 	"strconv"
 	"strings"
 
-	cclogger "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclogger "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 )
 
 const SYSFS_NUMABASE = `/sys/devices/system/node`

pkg/multiChanTicker/multiChanTicker.go

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

receivers/httpReceiver.go

@@ -10,8 +10,8 @@ import (
 	"strings"
 	"sync"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"github.com/gorilla/mux"
 	influx "github.com/influxdata/line-protocol"
 )

receivers/metricReceiver.go

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

receivers/natsReceiver.go

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

receivers/prometheusReceiver.go

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

receivers/receiveManager.go

@@ -5,8 +5,8 @@ import (
 	"os"
 	"sync"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 var AvailableReceivers = map[string]func(name string, config json.RawMessage) (Receiver, error){

receivers/redfishReceiver.go

@@ -10,8 +10,8 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 
 	// See: https://pkg.go.dev/github.com/stmcginnis/gofish
 	"github.com/stmcginnis/gofish"

receivers/sampleReceiver.go

@@ -4,7 +4,7 @@ import (
 	"encoding/json"
 	"fmt"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
 )
 
 // SampleReceiver configuration: receiver type, listen address, port

sinks/gangliaCommon.go

@@ -4,7 +4,7 @@ import (
 	"fmt"
 	"strings"
 
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 func GangliaMetricName(point lp.CCMetric) string {

sinks/gangliaSink.go

@@ -9,8 +9,8 @@ import (
 	//	"time"
 	"os/exec"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const GMETRIC_EXEC = `gmetric`

sinks/httpSink.go

@@ -9,8 +9,8 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influx "github.com/influxdata/line-protocol"
 )
 

sinks/influxAsyncSink.go

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
 	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
 	influxdb2ApiHttp "github.com/influxdata/influxdb-client-go/v2/api/http"

sinks/influxSink.go

@@ -9,8 +9,8 @@ import (
 	"sync"
 	"time"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	influxdb2 "github.com/influxdata/influxdb-client-go/v2"
 	influxdb2Api "github.com/influxdata/influxdb-client-go/v2/api"
 	"github.com/influxdata/influxdb-client-go/v2/api/write"

sinks/libgangliaSink.go

@@ -71,8 +71,8 @@ import (
 	"fmt"
 	"unsafe"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"github.com/NVIDIA/go-nvml/pkg/dl"
 )
 

sinks/metricSink.go

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

sinks/natsSink.go

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

sinks/prometheusSink.go

@@ -9,8 +9,8 @@ import (
 	"strings"
 	"sync"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 	"github.com/gorilla/mux"
 	"github.com/prometheus/client_golang/prometheus"
 	"github.com/prometheus/client_golang/prometheus/promhttp"

sinks/sampleSink.go

@@ -5,8 +5,8 @@ import (
 	"fmt"
 	"log"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 type SampleSinkConfig struct {

sinks/sinkManager.go

@@ -6,8 +6,8 @@ import (
 	"os"
 	"sync"
 
-	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 const SINK_MAX_FORWARD = 50

sinks/stdoutSink.go

@@ -7,7 +7,7 @@ import (
 	"strings"
 
 	//	"time"
-	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
 )
 
 type StdoutSink struct {