Merge branch 'develop' into smartmon_collector

collectors/README.md

@@ -35,7 +35,7 @@ In contrast to the configuration files for sinks and receivers, the collectors c
 * [`nfs4stat`](./nfs4Metric.md)
 * [`cpufreq`](./cpufreqMetric.md)
 * [`cpufreq_cpuinfo`](./cpufreqCpuinfoMetric.md)
-* [`numastat`](./numastatMetric.md)
+* [`numastats`](./numastatsMetric.md)
 * [`gpfs`](./gpfsMetric.md)
 * [`beegfs_meta`](./beegfsmetaMetric.md)
 * [`beegfs_storage`](./beegfsstorageMetric.md)

collectors/beegfsmetaMetric.go

@@ -5,7 +5,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"os"
 	"os/exec"
 	"os/user"
@@ -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"
@@ -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

@@ -38,6 +38,7 @@ var AvailableCollectors = map[string]MetricCollector{
 	"beegfs_storage":  new(BeegfsStorageCollector),
 	"rocm_smi":        new(RocmSmiCollector),
 	"smartmon":        new(SmartMonCollector),
+	"schedstat":	   new(SchedstatCollector),
 }
 
 // Metric collector manager data structure

collectors/cpufreqMetric.go

@@ -3,7 +3,7 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
@@ -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

@@ -11,6 +11,7 @@ import (
 
 	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
 	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+	sysconf "github.com/tklauser/go-sysconf"
 )
 
 const CPUSTATFILE = `/proc/stat`
@@ -22,9 +23,11 @@ type CpustatCollectorConfig struct {
 type CpustatCollector struct {
 	metricCollector
 	config   CpustatCollectorConfig
+	lastTimestamp time.Time                   // Store time stamp of last tick to derive values
 	matches  map[string]int
 	cputags  map[string]map[string]string
 	nodetags map[string]string
+	olddata  map[string]map[string]int64
 }
 
 func (m *CpustatCollector) Init(config json.RawMessage) error {
@@ -76,36 +79,48 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
 	// Pre-generate tags for all CPUs
 	num_cpus := 0
 	m.cputags = make(map[string]map[string]string)
+	m.olddata = make(map[string]map[string]int64)
 	scanner := bufio.NewScanner(file)
 	for scanner.Scan() {
 		line := scanner.Text()
 		linefields := strings.Fields(line)
-		if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
+		if strings.Compare(linefields[0], "cpu") == 0 {
+			m.olddata["cpu"] = make(map[string]int64)
+			for k, v := range m.matches {
+				m.olddata["cpu"][k], _ = strconv.ParseInt(linefields[v], 0, 64)
+			}
+		} else if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
 			cpustr := strings.TrimLeft(linefields[0], "cpu")
 			cpu, _ := strconv.Atoi(cpustr)
 			m.cputags[linefields[0]] = map[string]string{"type": "hwthread", "type-id": fmt.Sprintf("%d", cpu)}
+			m.olddata[linefields[0]] = make(map[string]int64)
+			for k, v := range m.matches {
+				m.olddata[linefields[0]][k], _ = strconv.ParseInt(linefields[v], 0, 64)
+			}
 			num_cpus++
 		}
 	}
+	m.lastTimestamp = time.Now()
 	m.init = true
 	return nil
 }
 
-func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric) {
+func (m *CpustatCollector) parseStatLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
 	values := make(map[string]float64)
-	total := 0.0
+	clktck, _ := sysconf.Sysconf(sysconf.SC_CLK_TCK)
 	for match, index := range m.matches {
 		if len(match) > 0 {
 			x, err := strconv.ParseInt(linefields[index], 0, 64)
 			if err == nil {
-				values[match] = float64(x)
-				total += values[match]
+				vdiff := x - m.olddata[linefields[0]][match]
+				m.olddata[linefields[0]][match] = x // Store new value for next run
+				values[match] = float64(vdiff) / float64(tsdelta.Seconds()) / float64(clktck)
 			}
 		}
 	}
-	t := time.Now()
+	
 	for name, value := range values {
-		y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": (value * 100.0) / total}, t)
+		y, err := lp.New(name, tags, m.meta, map[string]interface{}{"value": value * 100}, now)
 		if err == nil {
 			output <- y
 		}
@@ -117,6 +132,9 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		return
 	}
 	num_cpus := 0
+	now := time.Now()
+	tsdelta := now.Sub(m.lastTimestamp)
+
 	file, err := os.Open(string(CPUSTATFILE))
 	if err != nil {
 		cclog.ComponentError(m.name, err.Error())
@@ -128,9 +146,9 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		line := scanner.Text()
 		linefields := strings.Fields(line)
 		if strings.Compare(linefields[0], "cpu") == 0 {
-			m.parseStatLine(linefields, m.nodetags, output)
+			m.parseStatLine(linefields, m.nodetags, output, now, tsdelta)
 		} else if strings.HasPrefix(linefields[0], "cpu") {
-			m.parseStatLine(linefields, m.cputags[linefields[0]], output)
+			m.parseStatLine(linefields, m.cputags[linefields[0]], output, now, tsdelta)
 			num_cpus++
 		}
 	}
@@ -139,11 +157,13 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMetric)
 		m.nodetags,
 		m.meta,
 		map[string]interface{}{"value": int(num_cpus)},
-		time.Now(),
+		now,
 	)
 	if err == nil {
 		output <- num_cpus_metric
 	}
+
+	m.lastTimestamp = now
 }
 
 func (m *CpustatCollector) Close() {

collectors/customCmdMetric.go

@@ -3,8 +3,8 @@ package collectors
 import (
 	"encoding/json"
 	"errors"
-	"io/ioutil"
 	"log"
+	"os"
 	"os/exec"
 	"strings"
 	"time"
@@ -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/gpfsMetric.go

@@ -5,7 +5,7 @@ import (
 	"bytes"
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"io"
 	"log"
 	"os/exec"
 	"os/user"
@@ -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)
-		dataStdOut, _ := ioutil.ReadAll(cmdStdout)
+		dataStdErr, _ := io.ReadAll(cmdStderr)
+		dataStdOut, _ := io.ReadAll(cmdStdout)
 		cclog.ComponentError(
 			m.name,
 			fmt.Sprintf("Read(): Failed to execute command \"%s\": %v\n", cmd.String(), err),

collectors/infinibandMetric.go

@@ -2,7 +2,6 @@ package collectors
 
 import (
 	"fmt"
-	"io/ioutil"
 	"os"
 
 	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
@@ -19,8 +18,9 @@ import (
 const IB_BASEPATH = "/sys/class/infiniband/"
 
 type InfinibandCollectorMetric struct {
-	path string
-	unit string
+	path  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_xmit":      {path: filepath.Join(countersDir, "port_xmit_data"), unit: "bytes"},
-			"ib_recv_pkts": {path: filepath.Join(countersDir, "port_rcv_packets"), unit: "packets"},
-			"ib_xmit_pkts": {path: filepath.Join(countersDir, "port_xmit_packets"), unit: "packets"},
+			"ib_recv":      {path: filepath.Join(countersDir, "port_rcv_data"), unit: "bytes", scale: 4},
+			"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", scale: 1},
+			"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/likwidMetric.go

@@ -12,7 +12,6 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"io/ioutil"
 	"math"
 	"os"
 	"os/signal"
@@ -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

@@ -3,7 +3,7 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"os"
 	"strconv"
 	"strings"
 	"time"
@@ -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/memstatMetric.go

@@ -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)
-							if len(totalVal.unit) > 0 {
-								unit = totalVal.unit
-							} else if len(freeVal.unit) > 0 {
-								unit = freeVal.unit
-							} else if len(bufVal.unit) > 0 {
-								unit = bufVal.unit
-							} else if len(cacheVal.unit) > 0 {
+							memUsed -= cacheVal.value
+							if len(cacheVal.unit) > 0 && len(unit) == 0 {
 								unit = cacheVal.unit
 							}
 						}

collectors/rocmsmiMetric.go

@@ -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/schedstatMetric.go

@@ -0,0 +1,155 @@
+package collectors
+
+import (
+	"encoding/json"
+	"fmt"
+	"bufio"
+	"time"
+	"os"
+	"strings"
+	"strconv"
+	"math"
+
+	cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
+	lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
+)
+
+const SCHEDSTATFILE = `/proc/schedstat`
+
+// These are the fields we read from the JSON configuration
+type SchedstatCollectorConfig struct {
+	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
+}
+
+// This contains all variables we need during execution and the variables
+// defined by metricCollector (name, init, ...)
+type SchedstatCollector struct {
+	metricCollector
+	config SchedstatCollectorConfig // the configuration structure
+	lastTimestamp time.Time                   // Store time stamp of last tick to derive values
+	meta   map[string]string          // default meta information
+	cputags   map[string]map[string]string          // default tags
+	olddata   map[string]map[string]int64          // default tags
+}
+
+// Functions to implement MetricCollector interface
+// Init(...), Read(...), Close()
+// See: metricCollector.go
+
+// Init initializes the sample collector
+// Called once by the collector manager
+// All tags, meta data tags and metrics that do not change over the runtime should be set here
+func (m *SchedstatCollector) Init(config json.RawMessage) error {
+	var err error = nil
+	// Always set the name early in Init() to use it in cclog.Component* functions
+	m.name = "SchedstatCollector"
+	// This is for later use, also call it early
+	m.setup()
+	// Tell whether the collector should be run in parallel with others (reading files, ...)
+	// or it should be run serially, mostly for collectors acutally doing measurements
+	// because they should not measure the execution of the other collectors
+	m.parallel = true
+	// Define meta information sent with each metric
+	// (Can also be dynamic or this is the basic set with extension through AddMeta())
+	m.meta = map[string]string{"source": m.name, "group": "SCHEDSTAT"}
+	
+	// Read in the JSON configuration
+	if len(config) > 0 {
+		err = json.Unmarshal(config, &m.config)
+		if err != nil {
+			cclog.ComponentError(m.name, "Error reading config:", err.Error())
+			return err
+		}
+	}
+
+	// Check input file
+	file, err := os.Open(string(SCHEDSTATFILE))
+	if err != nil {
+		cclog.ComponentError(m.name, err.Error())
+	}
+	defer file.Close()
+
+	// Pre-generate tags for all CPUs
+	num_cpus := 0
+	m.cputags = make(map[string]map[string]string)
+	m.olddata = make(map[string]map[string]int64)
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := scanner.Text()
+		linefields := strings.Fields(line)
+		if strings.HasPrefix(linefields[0], "cpu") && strings.Compare(linefields[0], "cpu") != 0 {
+			cpustr := strings.TrimLeft(linefields[0], "cpu")
+			cpu, _ := strconv.Atoi(cpustr)
+			running, _ := strconv.ParseInt(linefields[7], 10, 64)
+			waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
+			m.cputags[linefields[0]] = map[string]string{"type": "hwthread", "type-id": fmt.Sprintf("%d", cpu)}
+			m.olddata[linefields[0]] = map[string]int64{"running" : running, "waiting" : waiting}
+			num_cpus++
+		}
+	}
+
+
+	// Save current timestamp
+	m.lastTimestamp = time.Now()
+
+	// Set this flag only if everything is initialized properly, all required files exist, ...
+	m.init = true
+	return err
+}
+
+func (m *SchedstatCollector) ParseProcLine(linefields []string, tags map[string]string, output chan lp.CCMetric, now time.Time, tsdelta time.Duration) {
+	running, _ := strconv.ParseInt(linefields[7], 10, 64)
+	waiting, _ := strconv.ParseInt(linefields[8], 10, 64)
+	diff_running := running - m.olddata[linefields[0]]["running"]
+	diff_waiting := waiting - m.olddata[linefields[0]]["waiting"]
+	
+	var l_running float64 = float64(diff_running) / tsdelta.Seconds() / (math.Pow(1000, 3))
+	var l_waiting float64 = float64(diff_waiting) / tsdelta.Seconds() / (math.Pow(1000, 3))
+
+	m.olddata[linefields[0]]["running"] = running
+	m.olddata[linefields[0]]["waiting"] = waiting
+	value := l_running + l_waiting
+
+ 	y, err := lp.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
+// and sends them through the output channel to the collector manager
+func (m *SchedstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
+	if !m.init {
+		return
+	}
+
+	//timestamps
+	now := time.Now()
+	tsdelta := now.Sub(m.lastTimestamp)
+
+	file, err := os.Open(string(SCHEDSTATFILE))
+	if err != nil {
+		cclog.ComponentError(m.name, err.Error())
+	}
+	defer file.Close()
+
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		line := scanner.Text()
+		linefields := strings.Fields(line)
+		if strings.HasPrefix(linefields[0], "cpu") {
+			m.ParseProcLine(linefields, m.cputags[linefields[0]], output, now, tsdelta)
+		}
+	}
+
+	m.lastTimestamp = now
+
+}
+
+// Close metric collector: close network connection, close files, close libraries, ...
+// Called once by the collector manager
+func (m *SchedstatCollector) Close() {
+	// Unset flag
+	m.init = false
+}

collectors/schedstatMetric.md

@@ -0,0 +1,11 @@
+
+## `schedstat` collector
+```json
+  "schedstat": {
+  }
+```
+
+The `schedstat` collector reads data from /proc/schedstat and calculates a load value, separated by hwthread. This might be useful to detect bad cpu pinning on shared nodes etc. 
+
+Metric:
+* `cpu_load_core`

collectors/tempMetric.go

@@ -3,7 +3,7 @@ package collectors
 import (
 	"encoding/json"
 	"fmt"
-	"io/ioutil"
+	"os"
 	"path/filepath"
 	"strconv"
 	"strings"
@@ -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,