Add metric 'nv_util_eff' like nvtop

2026-07-18 15:40:38 +02:00 · 2026-05-06 18:57:58 +02:00
21 changed files with 202 additions and 765 deletions
@@ -29,17 +29,15 @@ import (
 )

 type CentralConfigFile struct {
-	Interval      string `json:"interval"`
-	Duration      string `json:"duration"`
-	EnableMarkers bool   `json:"enable-markers"`
+	Interval string `json:"interval"`
+	Duration string `json:"duration"`
 }

 type RuntimeConfig struct {
-	Interval      time.Duration
-	Duration      time.Duration
-	EnableMarkers bool
-	CliArgs       map[string]string
-	ConfigFile    CentralConfigFile
+	Interval   time.Duration
+	Duration   time.Duration
+	CliArgs    map[string]string
+	ConfigFile CentralConfigFile

 	MetricRouter    mr.MetricRouter
 	CollectManager  collectors.CollectorManager
@@ -159,7 +157,6 @@ func mainFunc() int {
 		cclog.Error("The interval should be greater than duration")
 		return 1
 	}
-	rcfg.EnableMarkers = rcfg.ConfigFile.EnableMarkers

 	routerConf := ccconf.GetPackageConfig("router")
 	if len(routerConf) == 0 {
@@ -202,7 +199,7 @@ func mainFunc() int {
 	rcfg.MetricRouter.AddOutput(RouterToSinksChannel)

 	// Create new collector manager
-	rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, rcfg.EnableMarkers, &rcfg.Sync, collectorConf)
+	rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, &rcfg.Sync, collectorConf)
 	if err != nil {
 		cclog.Error(err.Error())
 		return 1
@@ -21,57 +21,54 @@ import (

 // Map of all available metric collectors
 var AvailableCollectors = map[string]MetricCollector{
-	"likwid":             new(LikwidCollector),
-	"loadavg":            new(LoadavgCollector),
-	"memstat":            new(MemstatCollector),
-	"netstat":            new(NetstatCollector),
-	"ibstat":             new(InfinibandCollector),
-	"lustrestat":         new(LustreCollector),
-	"cpustat":            new(CpustatCollector),
-	"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),
-	"nfs3stat":           new(Nfs3Collector),
-	"nfs4stat":           new(Nfs4Collector),
-	"numastats":          new(NUMAStatsCollector),
-	"beegfs_meta":        new(BeegfsMetaCollector),
-	"beegfs_storage":     new(BeegfsStorageCollector),
-	"rapl":               new(RAPLCollector),
-	"rocm_smi":           new(RocmSmiCollector),
-	"self":               new(SelfCollector),
-	"schedstat":          new(SchedstatCollector),
-	"nfsiostat":          new(NfsIOStatCollector),
-	"slurm_cgroup":       new(SlurmCgroupCollector),
-	"smartmon":           new(SmartMonCollector),
-	"lenovo_dense_power": new(LenovoDensePowerCollector),
-	"megware_eureka":     new(MegwareEurekaCollector),
+	"likwid":          new(LikwidCollector),
+	"loadavg":         new(LoadavgCollector),
+	"memstat":         new(MemstatCollector),
+	"netstat":         new(NetstatCollector),
+	"ibstat":          new(InfinibandCollector),
+	"lustrestat":      new(LustreCollector),
+	"cpustat":         new(CpustatCollector),
+	"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),
+	"nfs3stat":        new(Nfs3Collector),
+	"nfs4stat":        new(Nfs4Collector),
+	"numastats":       new(NUMAStatsCollector),
+	"beegfs_meta":     new(BeegfsMetaCollector),
+	"beegfs_storage":  new(BeegfsStorageCollector),
+	"rapl":            new(RAPLCollector),
+	"rocm_smi":        new(RocmSmiCollector),
+	"self":            new(SelfCollector),
+	"schedstat":       new(SchedstatCollector),
+	"nfsiostat":       new(NfsIOStatCollector),
+	"slurm_cgroup":    new(SlurmCgroupCollector),
+	"smartmon":        new(SmartMonCollector),
 }

 // Metric collector manager data structure
 type collectorManager struct {
-	collectors    []MetricCollector          // List of metric collectors to read in parallel
-	serial        []MetricCollector          // List of metric collectors to read serially
-	output        chan lp.CCMessage          // Output channels
-	done          chan bool                  // channel to finish / stop metric collector manager
-	ticker        mct.MultiChanTicker        // periodically ticking once each interval
-	duration      time.Duration              // duration (for metrics that measure over a given duration)
-	wg            *sync.WaitGroup            // wait group for all goroutines in cc-metric-collector
-	config        map[string]json.RawMessage // json encoded config for collector manager
-	collector_wg  sync.WaitGroup             // internally used wait group for the parallel reading of collector
-	parallel_run  bool                       // Flag whether the collectors are currently read in parallel
-	enableMarkers bool                       // Send ccmc-{begin,end} metrics
+	collectors   []MetricCollector          // List of metric collectors to read in parallel
+	serial       []MetricCollector          // List of metric collectors to read serially
+	output       chan lp.CCMessage          // Output channels
+	done         chan bool                  // channel to finish / stop metric collector manager
+	ticker       mct.MultiChanTicker        // periodically ticking once each interval
+	duration     time.Duration              // duration (for metrics that measure over a given duration)
+	wg           *sync.WaitGroup            // wait group for all goroutines in cc-metric-collector
+	config       map[string]json.RawMessage // json encoded config for collector manager
+	collector_wg sync.WaitGroup             // internally used wait group for the parallel reading of collector
+	parallel_run bool                       // Flag whether the collectors are currently read in parallel
 }

 // Metric collector manager access functions
 type CollectorManager interface {
-	Init(ticker mct.MultiChanTicker, duration time.Duration, enableMarkers bool, wg *sync.WaitGroup, collectConfig json.RawMessage) error
+	Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) error
 	AddOutput(output chan lp.CCMessage)
 	Start()
 	Close()
@@ -84,7 +81,7 @@ type CollectorManager interface {
 // * ticker (from variable ticker)
 // * configuration (read from config file in variable collectConfigFile)
 // Initialization is done for all configured collectors
-func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, enableMarkers bool, wg *sync.WaitGroup, collectConfig json.RawMessage) error {
+func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) error {
 	cm.collectors = make([]MetricCollector, 0)
 	cm.serial = make([]MetricCollector, 0)
 	cm.output = nil
@@ -92,7 +89,6 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
 	cm.wg = wg
 	cm.ticker = ticker
 	cm.duration = duration
-	cm.enableMarkers = enableMarkers

 	d := json.NewDecoder(bytes.NewReader(collectConfig))
 	d.DisallowUnknownFields()
@@ -150,9 +146,6 @@ func (cm *collectorManager) Start() {
 				done()
 				return
 			case t := <-tick:
-				if cm.enableMarkers {
-					lp.NewMetric("ccmc-begin", map[string]string{"type": "node"}, nil, map[string]interface{}{"value": 0}, time.Now())
-				}
 				cm.parallel_run = true
 				for _, c := range cm.collectors {
 					// Wait for done signal or execute the collector
@@ -184,9 +177,6 @@ func (cm *collectorManager) Start() {
 						c.Read(cm.duration, cm.output)
 					}
 				}
-				if cm.enableMarkers {
-					lp.NewMetric("ccmc-end", map[string]string{"type": "node"}, nil, map[string]interface{}{"value": 0}, time.Now())
-				}
 			}
 		}
 	})
@@ -209,9 +199,9 @@ func (cm *collectorManager) Close() {
 }

 // New creates a new initialized metric collector manager
-func New(ticker mct.MultiChanTicker, duration time.Duration, enableMarkers bool, wg *sync.WaitGroup, collectConfig json.RawMessage) (CollectorManager, error) {
+func New(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) (CollectorManager, error) {
 	cm := new(collectorManager)
-	err := cm.Init(ticker, duration, enableMarkers, wg, collectConfig)
+	err := cm.Init(ticker, duration, wg, collectConfig)
 	if err != nil {
 		return nil, err
 	}
@@ -116,9 +116,6 @@ func (m *CPUFreqCpuInfoCollector) Init(_ json.RawMessage) error {
 			physicalPackageID = ""
 		}
 	}
-	if err := scanner.Err(); err != nil {
-		return fmt.Errorf("%s Init(): Call to scanner.Err failed: %w", m.name, err)
-	}

 	if err := file.Close(); err != nil {
 		return fmt.Errorf("%s Init(): Call to file.Close() failed: %w", m.name, err)
@@ -182,9 +179,6 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
 			}
 		}
 	}
-	if err := scanner.Err(); err != nil {
-		cclog.ComponentErrorf(m.name, "Read(): Call to scanner.Err failed: %s", err.Error())
-	}
 }

 func (m *CPUFreqCpuInfoCollector) Close() {
@@ -27,7 +27,6 @@ const CPUSTATFILE = `/proc/stat`

 type CpustatCollectorConfig struct {
 	ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
-	excludeNumCPUs bool
 }

 type CpustatCollector struct {
@@ -44,7 +43,7 @@ type CpustatCollector struct {
 func (m *CpustatCollector) Init(config json.RawMessage) error {
 	m.name = "CpustatCollector"
 	if err := m.setup(); err != nil {
-		return fmt.Errorf("%s Init(): setup() call failed: %s", m.name, err.Error())
+		return fmt.Errorf("%s Init(): setup() call failed: %w", m.name, err)
 	}
 	m.parallel = true
 	m.meta = map[string]string{
@@ -58,7 +57,7 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
 		d := json.NewDecoder(bytes.NewReader(config))
 		d.DisallowUnknownFields()
 		if err := d.Decode(&m.config); err != nil {
-			return fmt.Errorf("%s Init(): Error decoding JSON config: %s", m.name, err.Error())
+			return fmt.Errorf("%s Init(): Error decoding JSON config: %w", m.name, err)
 		}
 	}
 	matches := map[string]int{
@@ -80,12 +79,11 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
 			m.matches[match] = index
 		}
 	}
-	m.config.excludeNumCPUs = slices.Contains(m.config.ExcludeMetrics, "num_cpus")

 	// Check input file
 	file, err := os.Open(CPUSTATFILE)
 	if err != nil {
-		return fmt.Errorf("%s Init(): Failed to open file '%s': %s", m.name, CPUSTATFILE, err.Error())
+		return fmt.Errorf("%s Init(): Failed to open file '%s': %w", m.name, CPUSTATFILE, err)
 	}

 	// Pre-generate tags for all CPUs
@@ -97,13 +95,11 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
 		line := scanner.Text()
 		linefields := strings.Fields(line)
 		if strings.Compare(linefields[0], "cpu") == 0 {
-			// Kernel system statistics for all CPUs
 			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 {
-			// Kernel system statistics per CPU
 			cpustr := strings.TrimLeft(linefields[0], "cpu")
 			cpu, _ := strconv.Atoi(cpustr)
 			m.cputags[linefields[0]] = map[string]string{
@@ -117,13 +113,10 @@ func (m *CpustatCollector) Init(config json.RawMessage) error {
 			num_cpus++
 		}
 	}
-	if err := scanner.Err(); err != nil {
-		return fmt.Errorf("%s Init(): Call to scanner.Err failed: %s", m.name, err.Error())
-	}

 	// Close file
 	if err := file.Close(); err != nil {
-		return fmt.Errorf("%s Init(): Failed to close file '%s': %s", m.name, CPUSTATFILE, err.Error())
+		return fmt.Errorf("%s Init(): Failed to close file '%s': %w", m.name, CPUSTATFILE, err)
 	}

 	m.lastTimestamp = time.Now()
@@ -176,13 +169,13 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMessage
 	if err != nil {
 		cclog.ComponentError(
 			m.name,
-			fmt.Sprintf("Read(): Failed to open file '%s': %v", CPUSTATFILE, err.Error()))
+			fmt.Sprintf("Read(): Failed to open file '%s': %v", CPUSTATFILE, err))
 	}
 	defer func() {
 		if err := file.Close(); err != nil {
 			cclog.ComponentError(
 				m.name,
-				fmt.Sprintf("Read(): Failed to close file '%s': %v", string(CPUSTATFILE), err.Error()))
+				fmt.Sprintf("Read(): Failed to close file '%s': %v", string(CPUSTATFILE), err))
 		}
 	}()

@@ -197,14 +190,10 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMessage
 			num_cpus++
 		}
 	}
-	if err := scanner.Err(); err != nil {
-		cclog.ComponentErrorf(m.name, "Init(): Call to scanner.Err failed: %s", err.Error())
-	}

-	if !m.config.excludeNumCPUs {
-		if num_cpus_metric, err := lp.NewMetric("num_cpus", m.nodetags, m.meta, num_cpus, now); err == nil {
-			output <- num_cpus_metric
-		}
+	num_cpus_metric, err := lp.NewMetric("num_cpus", m.nodetags, m.meta, num_cpus, now)
+	if err == nil {
+		output <- num_cpus_metric
 	}

 	m.lastTimestamp = now
@@ -147,11 +147,6 @@ mountLoop:
 			}
 		}
 	}
-	if err := scanner.Err(); err != nil {
-		cclog.ComponentErrorf(
-			m.name,
-			"Read(): Call to scanner.Err failed: %s", err.Error())
-	}
 	if m.allowedMetrics["part_max_used"] {
 		y, err := lp.NewMetric("part_max_used", map[string]string{"type": "node"}, m.meta, int(part_max_used), time.Now())
 		if err == nil {
@@ -23,29 +23,20 @@ import (
 	"golang.org/x/sys/unix"
 )

-// See: https://www.kernel.org/doc/Documentation/ABI/stable/sysfs-class-infiniband
-const (
-	ibBasePath     = "/sys/class/infiniband/"
-	ibDataUnit     = "bytes"
-	ibDataRateUnit = ibDataUnit + "/sec"
-	ibPkgUnit      = "packets"
-	ibPkgRateUnit  = ibPkgUnit + "/sec"
-)
+const IB_BASEPATH = "/sys/class/infiniband/"

 type InfinibandCollectorMetric struct {
-	name               string
-	path               string
-	unit               string
-	unitRates          string
-	scaleByFourLanes   bool
-	addToIBTotal       bool
-	addToIBTotalPkgs   bool
-	lastState          uint64
-	lastStateAvailable bool
+	name             string
+	path             string
+	unit             string
+	scale            int64
+	addToIBTotal     bool
+	addToIBTotalPkgs bool
+	lastState        int64
 }

 type InfinibandCollectorInfo struct {
-	lid              string                      // IB local Identifier (LID)
+	LID              string                      // IB local Identifier (LID)
 	device           string                      // IB device
 	port             string                      // IB device port
 	portCounterFiles []InfinibandCollectorMetric // mapping counter name -> InfinibandCollectorMetric
@@ -65,7 +56,7 @@ type InfinibandCollector struct {
 	lastTimestamp time.Time // Store time stamp of last tick to derive bandwidths
 }

-// Init initializes the Infiniband collector by walking through files below ibBasePath
+// 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 {
@@ -96,7 +87,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	}

 	// Loop for all InfiniBand directories
-	globPattern := filepath.Join(ibBasePath, "*", "ports", "*")
+	globPattern := filepath.Join(IB_BASEPATH, "*", "ports", "*")
 	ibDirs, err := filepath.Glob(globPattern)
 	if err != nil {
 		return fmt.Errorf("%s Init(): unable to glob files with pattern %s: %w", m.name, globPattern, err)
@@ -131,42 +122,36 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 		countersDir := filepath.Join(path, "counters")
 		portCounterFiles := []InfinibandCollectorMetric{
 			{
-				// Total number of data octets, divided by 4 (lanes), received on all VLs.
-				// This is 64 bit counter
-				name:             "ib_recv",
-				path:             filepath.Join(countersDir, "port_rcv_data"),
-				unit:             ibDataUnit,
-				unitRates:        ibDataRateUnit,
-				scaleByFourLanes: true,
-				addToIBTotal:     true,
+				name:         "ib_recv",
+				path:         filepath.Join(countersDir, "port_rcv_data"),
+				unit:         "bytes",
+				scale:        4,
+				addToIBTotal: true,
+				lastState:    -1,
 			},
 			{
-				// Total number of data octets, divided by 4 (lanes), transmitted on all VLs.
-				// This is 64 bit counter
-				name:             "ib_xmit",
-				path:             filepath.Join(countersDir, "port_xmit_data"),
-				unit:             ibDataUnit,
-				unitRates:        ibDataRateUnit,
-				scaleByFourLanes: true,
-				addToIBTotal:     true,
+				name:         "ib_xmit",
+				path:         filepath.Join(countersDir, "port_xmit_data"),
+				unit:         "bytes",
+				scale:        4,
+				addToIBTotal: true,
+				lastState:    -1,
 			},
 			{
-				// Total number of packets received on all VLs from this port (this may include packets containing Errors.
-				// This is 64 bit counter.
 				name:             "ib_recv_pkts",
 				path:             filepath.Join(countersDir, "port_rcv_packets"),
-				unit:             ibPkgUnit,
-				unitRates:        ibPkgRateUnit,
+				unit:             "packets",
+				scale:            1,
 				addToIBTotalPkgs: true,
+				lastState:        -1,
 			},
 			{
-				// Total number of packets transmitted on all VLs from this port. This may include packets with errors.
-				// This is 64 bit counter.
 				name:             "ib_xmit_pkts",
 				path:             filepath.Join(countersDir, "port_xmit_packets"),
-				unit:             ibPkgUnit,
-				unitRates:        ibPkgRateUnit,
+				unit:             "packets",
+				scale:            1,
 				addToIBTotalPkgs: true,
+				lastState:        -1,
 			},
 		}
 		for _, counter := range portCounterFiles {
@@ -178,7 +163,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {

 		m.info = append(m.info,
 			InfinibandCollectorInfo{
-				lid:              LID,
+				LID:              LID,
 				device:           device,
 				port:             port,
 				portCounterFiles: portCounterFiles,
@@ -199,7 +184,7 @@ func (m *InfinibandCollector) Init(config json.RawMessage) error {
 	return nil
 }

-// Read reads Infiniband counter files below ibBasePath
+// Read reads Infiniband counter files below IB_BASEPATH
 func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	// Check if already initialized
 	if !m.init {
@@ -216,9 +201,9 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
 	for i := range m.info {
 		info := &m.info[i]

-		var ibTotal, ibTotalPkts uint64      // sum of xmit and recv counters
-		var ibTotalBw, ibTotalPktsBw float64 // sum of xmit and recv rates
-		var ibTotalBwAvailable, ibTotalPktsBwAvailable bool
+		var ib_total, ib_total_last_state,
+			ib_total_pkts, ib_total_pkts_last_state int64
+		var ib_total_last_state_available, ib_total_pkts_last_state_available bool
 		for i := range info.portCounterFiles {
 			counterDef := &info.portCounterFiles[i]

@@ -228,30 +213,24 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess
 				cclog.ComponentError(
 					m.name,
 					fmt.Sprintf("Read(): Failed to read from file '%s': %v", counterDef.path, err))
-				// Current counter can not be saved as last state
-				counterDef.lastStateAvailable = false
 				continue
 			}
 			data := strings.TrimSpace(string(line))

-			// convert counter to uint64
-			vRawCounter, err := strconv.ParseUint(data, 10, 64)
+			// convert counter to int64
+			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 uint64: %v", counterDef.name, data, err))
-				// Current counter can not be saved as last state
-				counterDef.lastStateAvailable = false
+					fmt.Sprintf("Read(): Failed to convert Infininiband metrice %s='%s' to int64: %v", counterDef.name, data, err))
 				continue
 			}
-			vScaledCounter := vRawCounter
-			if counterDef.scaleByFourLanes {
-				vScaledCounter *= uint64(4)
-			}
+			// Scale raw value
+			v *= counterDef.scale

 			// Send absolut values
 			if m.config.SendAbsoluteValues {
-				if y, err := lp.NewMetric(counterDef.name, info.tagSet, m.meta, vScaledCounter, now); err == nil {
+				if y, err := lp.NewMetric(counterDef.name, info.tagSet, m.meta, v, now); err == nil {
 					y.AddMeta("unit", counterDef.unit)
 					output <- y
 				}
@@ -259,72 +238,63 @@ func (m *InfinibandCollector) Read(interval time.Duration, output chan lp.CCMess

 			// Send derived values
 			if m.config.SendDerivedValues {
-				if counterDef.lastStateAvailable {
-					var rate float64
-					// uint64 subtraction handles wraparound automatically
-					// in case vRawCounter < counterDef.lastState we would compute:
-					// math.MaxUint64 - lastState + vRawCounter + 1
-					// = (2^64 - 1) - lastState + vRawCounter + 1
-					// = 2^64 - lastState + vRawCounter
-					// ≡ vRawCounter - lastState (mod 2^64)
-					rate = float64(vRawCounter-counterDef.lastState) / timeDiff
-					if counterDef.scaleByFourLanes {
-						rate *= float64(4)
-					}
+				if counterDef.lastState >= 0 {
+					rate := float64((v - counterDef.lastState)) / timeDiff
 					if y, err := lp.NewMetric(counterDef.name+"_bw", info.tagSet, m.meta, rate, now); err == nil {
-						y.AddMeta("unit", counterDef.unitRates)
+						y.AddMeta("unit", counterDef.unit+"/sec")
 						output <- y
 					}

-					// Sum up rates for total rates
+					// Sum up total values of last state
 					if m.config.SendTotalValues {
 						switch {
 						case counterDef.addToIBTotal:
-							ibTotalBw += rate
-							ibTotalBwAvailable = true
+							ib_total_last_state += counterDef.lastState
+							ib_total_last_state_available = true
 						case counterDef.addToIBTotalPkgs:
-							ibTotalPktsBw += rate
-							ibTotalPktsBwAvailable = true
+							ib_total_pkts_last_state += counterDef.lastState
+							ib_total_pkts_last_state_available = true
 						}
 					}
 				}
-				counterDef.lastState = vRawCounter
-				counterDef.lastStateAvailable = true
+				counterDef.lastState = v
 			}

 			// Sum up total values
 			if m.config.SendTotalValues {
 				switch {
 				case counterDef.addToIBTotal:
-					ibTotal += vScaledCounter
+					ib_total += v
 				case counterDef.addToIBTotalPkgs:
-					ibTotalPkts += vScaledCounter
+					ib_total_pkts += v
 				}
 			}
 		}

 		// Send total values
 		if m.config.SendTotalValues {
-			if y, err := lp.NewMetric("ib_total", info.tagSet, m.meta, ibTotal, now); err == nil {
-				y.AddMeta("unit", ibDataUnit)
+			if y, err := lp.NewMetric("ib_total", info.tagSet, m.meta, ib_total, now); err == nil {
+				y.AddMeta("unit", "bytes")
 				output <- y
 			}

-			if y, err := lp.NewMetric("ib_total_pkts", info.tagSet, m.meta, ibTotalPkts, now); err == nil {
-				y.AddMeta("unit", ibPkgUnit)
+			if y, err := lp.NewMetric("ib_total_pkts", info.tagSet, m.meta, ib_total_pkts, now); err == nil {
+				y.AddMeta("unit", "packets")
 				output <- y
 			}

-			if m.config.SendDerivedValues && ibTotalBwAvailable {
-				if y, err := lp.NewMetric("ib_total_bw", info.tagSet, m.meta, ibTotalBw, now); err == nil {
-					y.AddMeta("unit", ibDataRateUnit)
+			if m.config.SendDerivedValues && ib_total_last_state_available {
+				rate := float64((ib_total - ib_total_last_state)) / timeDiff
+				if y, err := lp.NewMetric("ib_total_bw", info.tagSet, m.meta, rate, now); err == nil {
+					y.AddMeta("unit", "bytes/sec")
 					output <- y
 				}
 			}

-			if m.config.SendDerivedValues && ibTotalPktsBwAvailable {
-				if y, err := lp.NewMetric("ib_total_pkts_bw", info.tagSet, m.meta, ibTotalPktsBw, now); err == nil {
-					y.AddMeta("unit", ibPkgRateUnit)
+			if m.config.SendDerivedValues && ib_total_pkts_last_state_available {
+				rate := float64((ib_total_pkts - ib_total_pkts_last_state)) / timeDiff
+				if y, err := lp.NewMetric("ib_total_pkts_bw", info.tagSet, m.meta, rate, now); err == nil {
+					y.AddMeta("unit", "packets/sec")
 					output <- y
 				}
 			}
@@ -48,13 +48,13 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
 	m.parallel = true
 	m.meta = map[string]string{"source": m.name, "group": "Disk"}
 	if err := m.setup(); err != nil {
-		return fmt.Errorf("%s Init(): setup() call failed: %s", m.name, err.Error())
+		return fmt.Errorf("%s Init(): setup() call failed: %w", m.name, err)
 	}
 	if len(config) > 0 {
 		d := json.NewDecoder(bytes.NewReader(config))
 		d.DisallowUnknownFields()
 		if err := d.Decode(&m.config); err != nil {
-			return fmt.Errorf("%s Init(): Error decoding JSON config: %s", m.name, err.Error())
+			return fmt.Errorf("%s Init(): Error decoding JSON config: %w", m.name, err)
 		}
 	}
 	// https://www.kernel.org/doc/html/latest/admin-guide/iostats.html
@@ -89,7 +89,7 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
 	}
 	file, err := os.Open(IOSTATFILE)
 	if err != nil {
-		return fmt.Errorf("%s Init(): Failed to open file \"%s\": %s", m.name, IOSTATFILE, err.Error())
+		return fmt.Errorf("%s Init(): Failed to open file \"%s\": %w", m.name, IOSTATFILE, err)
 	}

 	scanner := bufio.NewScanner(file)
@@ -130,11 +130,8 @@ func (m *IOstatCollector) Init(config json.RawMessage) error {
 			lastValues:    lastValues,
 		}
 	}
-	if err := scanner.Err(); err != nil {
-		return fmt.Errorf("%s Init(): Failed to scan content of file %q: %s", m.name, IOSTATFILE, err.Error())
-	}
 	if err := file.Close(); err != nil {
-		return fmt.Errorf("%s Init(): Failed to close file \"%s\": %s", m.name, IOSTATFILE, err.Error())
+		return fmt.Errorf("%s Init(): Failed to close file \"%s\": %w", m.name, IOSTATFILE, err)
 	}

 	m.init = true
@@ -150,14 +147,14 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
 	if err != nil {
 		cclog.ComponentError(
 			m.name,
-			fmt.Sprintf("Read(): Failed to open file '%s': %s", IOSTATFILE, err.Error()))
+			fmt.Sprintf("Read(): Failed to open file '%s': %v", IOSTATFILE, err))
 		return
 	}
 	defer func() {
 		if err := file.Close(); err != nil {
 			cclog.ComponentError(
 				m.name,
-				fmt.Sprintf("Read(): Failed to close file '%s': %s", IOSTATFILE, err.Error()))
+				fmt.Sprintf("Read(): Failed to close file '%s': %v", IOSTATFILE, err))
 		}
 	}()

@@ -201,11 +198,6 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
 		}
 		m.devices[device] = entry
 	}
-	if err := scanner.Err(); err != nil {
-		cclog.ComponentErrorf(
-			m.name,
-			"Read(): Failed to scan content of file %q: %s", IOSTATFILE, err.Error())
-	}
 }

 func (m *IOstatCollector) Close() {
@@ -28,15 +28,13 @@ type IpmiCollector struct {
 	metricCollector

 	config struct {
-		IpmitoolPath    string   `json:"ipmitool_path"`
-		IpmisensorsPath string   `json:"ipmisensors_path"`
-		Sudo            bool     `json:"use_sudo"`
-		IncludeMetrics  []string `json:"include_metrics"`
+		IpmitoolPath    string `json:"ipmitool_path"`
+		IpmisensorsPath string `json:"ipmisensors_path"`
+		Sudo            bool   `json:"use_sudo"`
 	}

-	ipmitool       string
-	ipmisensors    string
-	includeMetrics map[string]bool
+	ipmitool    string
+	ipmisensors string
 }

 func (m *IpmiCollector) Init(config json.RawMessage) error {
@@ -66,15 +64,6 @@ func (m *IpmiCollector) Init(config json.RawMessage) error {
 		}
 	}

-	// Read metrics to include
-	m.includeMetrics = make(map[string]bool)
-	for _, metric := range m.config.IncludeMetrics {
-		metric = strings.ToLower(strings.TrimSpace(metric))
-		if metric != "" {
-			m.includeMetrics[metric] = true
-		}
-	}
-
 	m.ipmitool = m.config.IpmitoolPath
 	m.ipmisensors = m.config.IpmisensorsPath

@@ -156,11 +145,6 @@ func (m *IpmiCollector) readIpmiTool(output chan lp.CCMessage) error {
 			continue
 		}
 		name := strings.ToLower(strings.ReplaceAll(strings.TrimSpace(lv[0]), " ", "_"))
-
-		if len(m.includeMetrics) > 0 && !m.includeMetrics[name] {
-			continue
-		}
-
 		unit := strings.TrimSpace(lv[2])
 		switch unit {
 		case "Volts":
@@ -181,9 +165,6 @@ func (m *IpmiCollector) readIpmiTool(output chan lp.CCMessage) error {
 		y.AddMeta("unit", unit)
 		output <- y
 	}
-	if err := scanner.Err(); err != nil {
-		return fmt.Errorf("failed to scan output of command: %s", err.Error())
-	}

 	// Wait for command end
 	if err := command.Wait(); err != nil {
@@ -228,11 +209,6 @@ func (m *IpmiCollector) readIpmiSensors(output chan lp.CCMessage) error {
 			continue
 		}
 		name := strings.ToLower(strings.ReplaceAll(lv[1], " ", "_"))
-
-		if len(m.includeMetrics) > 0 && !m.includeMetrics[name] {
-			continue
-		}
-
 		y, err := lp.NewMetric(name, map[string]string{"type": "node"}, m.meta, v, time.Now())
 		if err != nil {
 			cclog.ComponentErrorf(m.name, "Failed to create message: %v", err)
@@ -15,8 +15,7 @@ hugo_path: docs/reference/cc-metric-collector/collectors/ipmi.md
  "ipmistat": {
    "ipmitool_path": "/path/to/ipmitool",
    "ipmisensors_path": "/path/to/ipmi-sensors",
-    "use_sudo": true,
-    "include_metrics" : []
+    "use_sudo": true
  }
 ```

@@ -37,5 +36,3 @@ Defaults: monitoring !log_allowed, !pam_session
 monitoring ALL = (root) NOPASSWD:/usr/bin/ipmitool sensor
 monitoring ALL = (root) NOPASSWD:/usr/sbin/ipmi-sensors --comma-separated-output --sdr-cache-recreate
 ```
-
-If `include_ipmi_metrics` contains any entry, ipmistat collector will only submit these metrics. Any other values will get discarded. 
@@ -1,170 +0,0 @@
-// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-// additional authors:
-// Michael Panzlaff (NHR@FAU)
-
-package collectors
-
-import (
-	"bytes"
-	"encoding/hex"
-	"encoding/json"
-	"fmt"
-	"os/exec"
-	"strconv"
-	"strings"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/v2/ccMessage"
-)
-
-type LenovoDensePowerCollector struct {
-	metricCollector
-
-	config struct {
-		IpmitoolPath string `json:"ipmitool_path"`
-		Sudo         bool   `json:"use_sudo"`
-	}
-
-	ipmitool string
-
-	energyValLast  float64
-	energyTimeLast time.Time
-}
-
-func (m *LenovoDensePowerCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
-	m.name = "LenovoDensePowerCollector"
-	if err := m.setup(); err != nil {
-		return fmt.Errorf("%s Init(): setup() call failed: %w", m.name, err)
-	}
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "IPMI",
-	}
-
-	m.config.IpmitoolPath = "ipmitool"
-
-	if len(config) > 0 {
-		d := json.NewDecoder(bytes.NewReader(config))
-		d.DisallowUnknownFields()
-		if err := d.Decode(&m.config); err != nil {
-			return fmt.Errorf("%s Init(): Error decoding JSON config: %w", m.name, err)
-		}
-	}
-
-	m.ipmitool = m.config.IpmitoolPath
-
-	energyVal, energyTime, err := m.readEnergy()
-	if err != nil {
-		return fmt.Errorf("energy reading test failed: %w", err)
-	}
-
-	m.energyValLast = energyVal
-	m.energyTimeLast = energyTime
-	m.init = true
-
-	return nil
-}
-
-func (m *LenovoDensePowerCollector) readEnergy() (float64, time.Time, error) {
-	argv := make([]string, 0)
-	if m.config.Sudo {
-		argv = append(argv, "sudo", "-n")
-	}
-
-	// The Lenovo hardware wants this magic byte string
-	lenovoRequestEnergyMsg := []uint8{0x3a, 0x32, 4, 2, 0, 0, 0}
-
-	argv = append(argv, m.ipmitool, "raw")
-
-	for _, val := range lenovoRequestEnergyMsg {
-		argv = append(argv, strconv.Itoa(int(val)))
-	}
-
-	cmd := exec.Command(argv[0], argv[1:]...)
-
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	cmd.Stdout = &stdout
-	cmd.Stderr = &stderr
-
-	err := cmd.Run()
-	if err != nil {
-		return 0, time.Unix(0, 0), fmt.Errorf("failed to run ipmitool: %w (stdout=%s stderr=%s)", err, stdout.String(), stderr.String())
-	}
-
-	data, err := hex.DecodeString(strings.ReplaceAll(strings.TrimSpace(stdout.String()), " ", ""))
-	if err != nil {
-		return 0, time.Unix(0, 0), fmt.Errorf("unable to decode ipmitool hex output: %w (stdout=%s)", err, stdout.String())
-	}
-
-	if len(data) != 14 {
-		return 0, time.Unix(0, 0), fmt.Errorf("result must be 14 bytes as specified in the documentation")
-	}
-
-	// data is laid out like this:
-	// data[0 to 1]: FIFO index of value (for debug only)
-	// data[2 to 5]: Integer part of energy in J (little endian)
-	// data[6 to 7]: Fraction part of energy in mJ (little endian)
-	// data[8 to 11]: Integer part of Unix time of measurement in seconds (little endian)
-	// data[12 to 13]: Fraction part of Unix time of measurement in milliseconds (little endian)
-	wholeJoules := (uint32(data[2]) << 0) | (uint32(data[3]) << 8) | (uint32(data[4]) << 16) | (uint32(data[5]) << 24)
-	milliJoules := uint16(data[6]) | (uint16(data[7]) << 8)
-	finalJoules := float64(wholeJoules) + float64(milliJoules)*1e-3
-
-	wholeSeconds := (uint32(data[8]) << 0) | (uint32(data[9]) << 8) | (uint32(data[10]) << 16) | (uint32(data[11]) << 24)
-	milliSeconds := uint16(data[12]) | (uint16(data[13]) << 8)
-	finalTime := time.Unix(int64(wholeSeconds), (int64(milliSeconds) * 1000000))
-
-	return finalJoules, finalTime, nil
-}
-
-func (m *LenovoDensePowerCollector) Read(interval time.Duration, output chan lp.CCMessage) {
-	// Check if already initialized
-	if !m.init {
-		return
-	}
-
-	energyVal, energyTime, err := m.readEnergy()
-	if err != nil {
-		cclog.ComponentErrorf(m.name, "readEnergy failed: %v", err)
-		return
-	}
-
-	powerVal := 0.0
-	if energyTime.Compare(m.energyTimeLast) != 0 {
-		// Check for overflow
-		energyValDiff := int64(energyVal) - int64(m.energyValLast)
-		if energyVal < m.energyValLast {
-			energyValDiff += int64(0x100000000)
-		}
-		energyTimeDiff := energyTime.Sub(m.energyTimeLast)
-		if energyTime.Before(m.energyTimeLast) {
-			energyTimeDiff = energyTimeDiff + 0x100000000*time.Second
-		}
-		powerVal = float64(energyValDiff) / energyTimeDiff.Seconds()
-
-		m.energyValLast = energyVal
-		m.energyTimeLast = energyTime
-	}
-
-	metric, err := lp.NewMetric("lenovo_node_power", map[string]string{"type": "node"}, m.meta, powerVal, energyTime)
-	if err != nil {
-		cclog.ComponentErrorf(m.name, "lp.NewMetric failed: %v", err)
-		return
-	}
-	metric.AddMeta("unit", "Watts")
-	output <- metric
-}
-
-func (m *LenovoDensePowerCollector) Close() {
-	m.init = false
-}
@@ -1,51 +0,0 @@
-<!--
---
-title: Lenovo Dense Power collector
-description: Collect power of Lenovo Dense machines using ipmitool raw
-categories: [cc-metric-collector]
-tags: ['Admin']
-weight: 2
-hugo_path: docs/reference/cc-metric-collector/collectors/lenovoDensePower.md
---
-->
-
-## `lenovo_dense_power` collector
-
-```json
-  "lenovo_dense_power": {
-    "ipmitool_path": "/path/to/ipmitool",
-    "use_sudo": true,
-    "include_metrics" : []
-  }
-```
-
-The `lenovo_dense_power` collector reads power from Lenovo Dense machines via `ipmitool` (`ipmitool raw ...`). This collector is known to only work on the following machines. Others are not supported, so use at your *OWN* risk:
-
-System                                    | Compatibility             | Power measured
---                                       | ---                       | ---
-Lenovo ThinkSystem SD650 V2/V3            | untested, but should work | node + riser1 + riser2
-Lenovo ThinkSystem SD650-N V2/ SD650-I V3 | untested, but should work | node + riser1 + riser2 + gpus
-Lenovo ThinkSystem SD665-N V3             | tested, known to work     | node + riser1 + riser2 + gpus
-
-To test if your system *may* be supported, you can run the following command *at your own risk*:
-
-```
-$ ipmitool raw 58 50 4 2 0 0 0
- c4 00 83 a9 cb d3 a2 03 df db 47 6a d8 01
-```
-
-Exactly 14 bytes should be returned.
-In case not or another error occurs your hardware is likely not supported.
-
-In addition, `ipmitool` typically require root to run.
-In order to run `cc-metric-collector` without root priviliges, you can enable `use_sudo`.
-Add a file like this in `/etc/sudoers.d/` to allow `cc-metric-collector` to run the required commands:
-
-```
-# Do not log the following sudo commands from monitoring, since this causes a lot of log spam.
-# However keep log_denied enabled, to detect failures
-Defaults: monitoring !log_allowed, !pam_session
-
-# Allow to use ipmitool for Lenovo power readings
-monitoring ALL = (root) NOPASSWD:/usr/bin/ipmitool raw 58 50 4 2 0 0 0
-```
@@ -38,7 +38,7 @@ import (
 	topo "github.com/ClusterCockpit/cc-metric-collector/pkg/ccTopology"
 	"github.com/NVIDIA/go-nvml/pkg/dl"
 	"github.com/fsnotify/fsnotify"
-	"golang.design/x/runtime/thread"
+	"golang.design/x/thread"
 )

 const (
@@ -1,194 +0,0 @@
-// Copyright (C) NHR@FAU, University Erlangen-Nuremberg.
-// All rights reserved.
-// Use of this source code is governed by a MIT-style
-// license that can be found in the LICENSE file.
-// additional authors:
-// Michael Panzlaff (NHR@FAU)
-
-package collectors
-
-import (
-	"bytes"
-	"encoding/json"
-	"fmt"
-	"os/exec"
-	"time"
-
-	cclog "github.com/ClusterCockpit/cc-lib/v2/ccLogger"
-	lp "github.com/ClusterCockpit/cc-lib/v2/ccMessage"
-)
-
-// MPS refers to Monolithic Power Systems, from which the MP5922 is used
-// to measure telemetry on the Eureka platform.
-type mpsData struct {
-	Cnt         int64   `json:"Cnt"` // No idea what this is, ignore
-	Energy      float64 `json:"Energy"`
-	Vin         float64 `json:"Vin"`
-	Iin         float64 `json:"Iin"`
-	Pin         float64 `json:"Pin"`
-	PinAvg      float64 `json:"PinAvg"`
-	Vout        float64 `json:"Vout"`
-	Iout        float64 `json:"Iout"`
-	Pout        float64 `json:"Pout"`
-	StandbyVout float64 `json:"StandbyVout"`
-	StandbyIout float64 `json:"StandbyIout"`
-	StandbyPout float64 `json:"StandbyPout"`
-	TempBusbar  float64 `json:"TempBusbar"`
-	TempSsd     float64 `json:"TempSsd"`
-	TempMps     float64 `json:"TempMps"`
-	// No idea what the ones below mean exactl. Ignore them for now.
-	EnergyTime         int64 `json:"EnergyTime"`
-	EnergyAccumulator  int64 `json:"EnergyAccumulator"`
-	EnergyRolloverCnt  int64 `json:"EnergyRolloverCnt"`
-	EnergySampleCntU24 int64 `json:"EnergySampleCntU24"`
-
-	Timestamp time.Time
-}
-
-type MegwareEurekaCollector struct {
-	metricCollector
-
-	config struct {
-		U20Path string `json:"u20_path"`
-		Sudo    bool   `json:"use_sudo"`
-	}
-
-	u20path string
-
-	energyValLast  float64
-	energyTimeLast time.Time
-}
-
-func (m *MegwareEurekaCollector) Init(config json.RawMessage) error {
-	// Check if already initialized
-	if m.init {
-		return nil
-	}
-
-	m.name = "MegwareEurekaCollector"
-	if err := m.setup(); err != nil {
-		return fmt.Errorf("%s Init(): setup() call failed: %w", m.name, err)
-	}
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "U20",
-	}
-
-	m.config.U20Path = "u20"
-
-	if len(config) > 0 {
-		d := json.NewDecoder(bytes.NewReader(config))
-		d.DisallowUnknownFields()
-		if err := d.Decode(&m.config); err != nil {
-			return fmt.Errorf("%s Init(): Error decoding JSON config: %w", m.name, err)
-		}
-	}
-
-	m.u20path = m.config.U20Path
-
-	data, err := m.readMpsData()
-	if err != nil {
-		return fmt.Errorf("energy reading test failed: %w", err)
-	}
-
-	m.energyValLast = data.Energy
-	m.energyTimeLast = time.Now()
-	m.init = true
-
-	return nil
-}
-
-func (m *MegwareEurekaCollector) readMpsData() (*mpsData, error) {
-	argv := make([]string, 0)
-	if m.config.Sudo {
-		argv = append(argv, "sudo", "-n")
-	}
-
-	argv = append(argv, m.u20path, "values", "--read", "GET_MPS_POLL_VALUES")
-
-	cmd := exec.Command(argv[0], argv[1:]...)
-
-	var stdout bytes.Buffer
-	var stderr bytes.Buffer
-	cmd.Stdout = &stdout
-	cmd.Stderr = &stderr
-
-	err := cmd.Run()
-	if err != nil {
-		return nil, fmt.Errorf("failed to run u20: %w (stdout=%s stderr=%s)", err, stdout.String(), stderr.String())
-	}
-
-	var u20output struct {
-		GetMpsPollValues mpsData `json:"GET_MPS_POLL_VALUES"`
-	}
-
-	err = json.Unmarshal(stdout.Bytes(), &u20output)
-	if err != nil {
-		return nil, fmt.Errorf("unable to decode u20 JSON output: %w (stdout=%s)", err, stdout.String())
-	}
-
-	u20output.GetMpsPollValues.Timestamp = time.Now()
-
-	return &u20output.GetMpsPollValues, nil
-}
-
-func (m *MegwareEurekaCollector) Read(interval time.Duration, output chan lp.CCMessage) {
-	// Check if already initialized
-	if !m.init {
-		return
-	}
-
-	data, err := m.readMpsData()
-	if err != nil {
-		cclog.ComponentErrorf(m.name, "readMpsData failed: %v", err)
-		return
-	}
-
-	powerVal := 0.0
-
-	if data.Timestamp.After(m.energyTimeLast) {
-		// Important, m.energy comes in Wh, so multiply by 3600 to get Ws (aka Joule)
-		energyValDiff := data.Energy - m.energyValLast
-		energyTimeDiff := data.Timestamp.Sub(m.energyTimeLast)
-		powerVal = energyValDiff * 3600 / energyTimeDiff.Seconds()
-
-		m.energyValLast = data.Energy
-		m.energyTimeLast = data.Timestamp
-	}
-
-	metricNamePrefix := "eureka_"
-	metricMap := map[string]struct {
-		value any
-		unit  string
-	}{
-		"power":        {value: powerVal, unit: "Watts"},
-		"vin":          {value: data.Vin, unit: "Volts"},
-		"iin":          {value: data.Iin, unit: "Amperes"},
-		"pin":          {value: data.Pin, unit: "Watts"},
-		"pin_avg":      {value: data.PinAvg, unit: "Watts"},
-		"vout":         {value: data.Vout, unit: "Volts"},
-		"iout":         {value: data.Iout, unit: "Amperes"},
-		"pout":         {value: data.Pout, unit: "Watts"},
-		"standby_vout": {value: data.StandbyVout, unit: "Volts"},
-		"standby_iout": {value: data.StandbyIout, unit: "Amperes"},
-		"standby_pout": {value: data.StandbyPout, unit: "Watts"},
-		"temp_busbar":  {value: data.TempBusbar, unit: "degC"},
-		"temp_ssd":     {value: data.TempSsd, unit: "degC"},
-		"temp_mps":     {value: data.TempMps, unit: "degC"},
-	}
-
-	for metricName, metricData := range metricMap {
-		metricName = metricNamePrefix + metricName
-		metric, err := lp.NewMetric(metricName, map[string]string{"type": "node"}, m.meta, metricData.value, data.Timestamp)
-		if err != nil {
-			cclog.ComponentErrorf(m.name, "lp.NewMetric failed: %v", err)
-			return
-		}
-		metric.AddMeta("unit", metricData.unit)
-		output <- metric
-	}
-}
-
-func (m *MegwareEurekaCollector) Close() {
-	m.init = false
-}
@@ -1,44 +0,0 @@
-<!--
---
-title: Megware Eureka collector
-description: Collect power and other metrics of Megware Eureka machines using u20
-categories: [cc-metric-collector]
-tags: ['Admin']
-weight: 2
-hugo_path: docs/reference/cc-metric-collector/collectors/lenovoDensePower.md
---
-->
-
-## `lenovo_dense_power` collector
-
-```json
-  "megware_eureka": {
-    "u20_path": "/path/to/ipmitool",
-    "use_sudo": true
-  }
-```
-
-The `megware_eureka` collector reads power and other metrics from Megware Eureka machines via `u20`.
-If the u20 tool is available for your machines, it's possible that this collector is compatible.
-If you don't have access to u20, please contact your Megware sales person.
-
-You can test the collector compatibility by running the following command:
-
-```
-$ u20 values --read GET_MPS_POLL_VALUES
-```
-
-If this returns a JSON with energy, voltage and current readings, you're fine.
-
-In addition, `u20` typically requires root to run.
-In order to run `cc-metric-collector` without root priviliges, you can enable `use_sudo`.
-Add a file like this in `/etc/sudoers.d/` to allow `cc-metric-collector` to run the required commands:
-
-```
-# Do not log the following sudo commands from monitoring, since this causes a lot of log spam.
-# However keep log_denied enabled, to detect failures
-Defaults: monitoring !log_allowed, !pam_session
-
-# Allow to use u20 for Megware power readings
-monitoring ALL = (root) NOPASSWD:/usr/bin/u20 values --read GET_MPS_POLL_VALUES
-```
@@ -72,8 +72,7 @@ func getStats(filename string) map[string]MemstatStats {
 	for scanner.Scan() {
 		line := scanner.Text()
 		linefields := strings.Fields(line)
-		switch len(linefields) {
-		case 3:
+		if len(linefields) == 3 {
 			v, err := strconv.ParseFloat(linefields[1], 64)
 			if err == nil {
 				stats[strings.Trim(linefields[0], ":")] = MemstatStats{
@@ -81,7 +80,7 @@ func getStats(filename string) map[string]MemstatStats {
 					unit:  linefields[2],
 				}
 			}
-		case 5:
+		} else if len(linefields) == 5 {
 			v, err := strconv.ParseFloat(linefields[3], 64)
 			if err == nil {
 				cclog.ComponentDebug("getStats", strings.Trim(linefields[2], ":"), v, linefields[4])
@@ -107,10 +106,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 			return fmt.Errorf("%s Init(): Error decoding JSON config: %w", m.name, err)
 		}
 	}
-	m.meta = map[string]string{
-		"source": m.name,
-		"group":  "Memory",
-	}
+	m.meta = map[string]string{"source": m.name, "group": "Memory"}
 	m.stats = make(map[string]int64)
 	m.matches = make(map[string]string)
 	m.tags = map[string]string{"type": "node"}
@@ -149,7 +145,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 		"KernelStack":     "mem_kernelstack",
 	}
 	for k, v := range matches {
-		if !slices.Contains(m.config.ExcludeMetrics, v) {
+		if !slices.Contains(m.config.ExcludeMetrics, k) {
 			m.matches[k] = v
 		}
 	}
@@ -157,7 +153,7 @@ func (m *MemstatCollector) Init(config json.RawMessage) error {
 	if !slices.Contains(m.config.ExcludeMetrics, "mem_used") {
 		m.sendMemUsed = true
 	}
-	if len(m.matches) == 0 && !m.sendMemUsed {
+	if len(m.matches) == 0 {
 		return fmt.Errorf("%s Init(): no metrics to collect", m.name)
 	}
 	if err := m.setup(); err != nil {
@@ -1115,6 +1115,31 @@ func readNVLinkStats(device *NvidiaCollectorDevice, output chan lp.CCMessage) er
 	return nil
 }

+func readEfficiency(device *NvidiaCollectorDevice, output chan lp.CCMessage) error {
+	if !device.excludeMetrics["nv_util_eff"] {
+		maxPower, ret := nvml.DeviceGetEnforcedPowerLimit(device.device)
+		if ret == nvml.SUCCESS {
+			curPower, ret := nvml.DeviceGetPowerUsage(device.device)
+			if ret == nvml.SUCCESS {
+				util, ret := nvml.DeviceGetUtilizationRates(device.device)
+				if ret == nvml.SUCCESS {
+					factor := float64(curPower) / float64(maxPower)
+					eff := uint32(float64(util.Gpu) * factor)
+					if eff > 100 {
+						eff = 100
+					}
+					y, err := lp.NewMetric("nv_util_eff", device.tags, device.meta, eff, time.Now())
+					if err == nil {
+						y.AddTag("unit", "percent")
+						output <- y
+					}
+				}
+			}
+		}
+	}
+	return nil
+}
+
 func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage) {
 	var err error
 	if !m.init {
@@ -1220,6 +1245,11 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage)
 		if err != nil {
 			cclog.ComponentDebug(m.name, "readNVLinkStats for device", name, "failed")
 		}
+
+		err = readEfficiency(device, output)
+		if err != nil {
+			cclog.ComponentDebug(m.name, "readEfficiency for device", name, "failed")
+		}
 	}

 	// Actual read loop over all attached Nvidia GPUs
@@ -85,5 +85,6 @@ Metrics:
 * `nv_energy`
 * `nv_energy_abs`
 * `nv_average_power`
+* `nv_util_eff` (`nv_util` * (`nv_power_usage` / `nv_power_max_limit`))

 Some metrics add the additional sub type tag (`stype`) like the `nv_nvlink_*` metrics set `stype=nvlink,stype-id=<link_number>`. 
@@ -7,7 +7,6 @@ import (
 	"os/exec"
 	"os/user"
 	"path/filepath"
-	"regexp"
 	"strconv"
 	"strings"
 	"time"
@@ -46,37 +45,6 @@ type SlurmCgroupCollector struct {

 const defaultCgroupBase = "/sys/fs/cgroup/system.slice/slurmstepd.scope"

-var (
-	// Slurm cgroup v2 directory layout:
-	// - Slurm <= 25.11: job_<numeric job id>
-	// - Slurm >= 26.05: SLUID, encoded as "s" + 13 Crockford Base32 characters
-	jobIDDirRE = regexp.MustCompile(`^job_[0-9]+$`)
-	sluidDirRE = regexp.MustCompile(`(?i)^s[0-9A-HJKMNP-TV-Z]{13}$`)
-)
-
-func (m *SlurmCgroupCollector) findSlurmJobDirs() ([]string, error) {
-	entries, err := os.ReadDir(m.cgroupBase)
-	if err != nil {
-		return nil, err
-	}
-
-	jobDirs := make([]string, 0)
-
-	for _, entry := range entries {
-		if !entry.IsDir() {
-			continue
-		}
-
-		name := entry.Name()
-
-		if jobIDDirRE.MatchString(name) || sluidDirRE.MatchString(name) {
-			jobDirs = append(jobDirs, filepath.Join(m.cgroupBase, name))
-		}
-	}
-
-	return jobDirs, nil
-}
-
 func ParseCPUs(cpuset string) ([]int, error) {
 	var result []int
 	if cpuset == "" {
@@ -269,9 +237,10 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
 		delete(m.cpuUsed, k)
 	}

-	jobDirs, err := m.findSlurmJobDirs()
+	globPattern := filepath.Join(m.cgroupBase, "job_*")
+	jobDirs, err := filepath.Glob(globPattern)
 	if err != nil {
-		cclog.ComponentError(m.name, "Error reading job directories:", err.Error())
+		cclog.ComponentError(m.name, "Error globbing job directories:", err.Error())
 		return
 	}

@@ -5,12 +5,12 @@ go 1.25.0
 require (
 	github.com/ClusterCockpit/cc-lib/v2 v2.12.0
 	github.com/ClusterCockpit/go-rocm-smi v0.4.0
-	github.com/NVIDIA/go-nvml v0.13.2-0
+	github.com/NVIDIA/go-nvml v0.13.0-1
 	github.com/PaesslerAG/gval v1.2.4
-	github.com/fsnotify/fsnotify v1.10.1
-	github.com/tklauser/go-sysconf v0.4.0
-	golang.design/x/runtime v0.3.0
-	golang.org/x/sys v0.45.0
+	github.com/fsnotify/fsnotify v1.10.0
+	github.com/tklauser/go-sysconf v0.3.16
+	golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1
+	golang.org/x/sys v0.43.0
 )

 require (
@@ -38,7 +38,7 @@ require (
 	github.com/santhosh-tekuri/jsonschema/v5 v5.3.1 // indirect
 	github.com/shopspring/decimal v1.4.0 // indirect
 	github.com/stmcginnis/gofish v0.21.6 // indirect
-	github.com/tklauser/numcpus v0.12.0 // indirect
+	github.com/tklauser/numcpus v0.11.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.4 // indirect
 	golang.org/x/crypto v0.50.0 // indirect
 	golang.org/x/net v0.53.0 // indirect
@@ -12,9 +12,8 @@ github.com/Microsoft/go-winio v0.6.1 h1:9/kr64B9VUZrLm5YYwbGtUJnMgqWVOdUAXu6Migc
 github.com/Microsoft/go-winio v0.6.1/go.mod h1:LRdKpFKfdobln8UmuiYcKPot9D2v6svN5+sAH+4kjUM=
 github.com/Microsoft/hcsshim v0.11.4 h1:68vKo2VN8DE9AdN4tnkWnmdhqdbpUFM8OF3Airm7fz8=
 github.com/Microsoft/hcsshim v0.11.4/go.mod h1:smjE4dvqPX9Zldna+t5FG3rnoHhaB7QYxPRqGcpAD9w=
+github.com/NVIDIA/go-nvml v0.13.0-1 h1:OLX8Jq3dONuPOQPC7rndB6+iDmDakw0XTYgzMxObkEw=
 github.com/NVIDIA/go-nvml v0.13.0-1/go.mod h1:+KNA7c7gIBH7SKSJ1ntlwkfN80zdx8ovl4hrK3LmPt4=
-github.com/NVIDIA/go-nvml v0.13.2-0 h1:7M4cFG62wSUHw8i0XSiNU7ejKODytTS6ZrW/vgB2NSI=
-github.com/NVIDIA/go-nvml v0.13.2-0/go.mod h1:ahi2psRYoa+wYUBIrZPRO+wJs9lcvMhxSSkjjvsJJNQ=
 github.com/PaesslerAG/gval v1.2.4 h1:rhX7MpjJlcxYwL2eTTYIOBUyEKZ+A96T9vQySWkVUiU=
 github.com/PaesslerAG/gval v1.2.4/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac=
 github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI=
@@ -54,8 +53,8 @@ github.com/expr-lang/expr v1.17.8 h1:W1loDTT+0PQf5YteHSTpju2qfUfNoBt4yw9+wOEU9VM
 github.com/expr-lang/expr v1.17.8/go.mod h1:8/vRC7+7HBzESEqt5kKpYXxrxkr31SaO8r40VO/1IT4=
 github.com/frankban/quicktest v1.13.0 h1:yNZif1OkDfNoDfb9zZa9aXIpejNR4F23Wely0c+Qdqk=
 github.com/frankban/quicktest v1.13.0/go.mod h1:qLE0fzW0VuyUAJgPU19zByoIr0HtCHN/r/VLSOOIySU=
-github.com/fsnotify/fsnotify v1.10.1 h1:b0/UzAf9yR5rhf3RPm9gf3ehBPpf0oZKIjtpKrx59Ho=
-github.com/fsnotify/fsnotify v1.10.1/go.mod h1:TLheqan6HD6GBK6PrDWyDPBaEV8LspOxvPSjC+bVfgo=
+github.com/fsnotify/fsnotify v1.10.0 h1:Xx/5Ydg9CeBDX/wi4VJqStNtohYjitZhhlHt4h3St1M=
+github.com/fsnotify/fsnotify v1.10.0/go.mod h1:TLheqan6HD6GBK6PrDWyDPBaEV8LspOxvPSjC+bVfgo=
 github.com/go-ole/go-ole v1.3.0 h1:Dt6ye7+vXGIKZ7Xtk4s6/xVdGDQynvom7xCFEdWr6uE=
 github.com/go-ole/go-ole v1.3.0/go.mod h1:5LS6F96DhAwUc7C+1HLexzMXY1xGRSryjyPPKW6zv78=
 github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
@@ -164,18 +163,18 @@ github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu
 github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
 github.com/testcontainers/testcontainers-go v0.26.0 h1:uqcYdoOHBy1ca7gKODfBd9uTHVK3a7UL848z09MVZ0c=
 github.com/testcontainers/testcontainers-go v0.26.0/go.mod h1:ICriE9bLX5CLxL9OFQ2N+2N+f+803LNJ1utJb1+Inx0=
-github.com/tklauser/go-sysconf v0.4.0 h1:7H0uAN+7RkwWRaxhYXDLqa5V3LPrJeV8wmD9dRUgPQU=
-github.com/tklauser/go-sysconf v0.4.0/go.mod h1:8mTNWyog7H+MpKijp4VmKJAd2bbYQ2zuUwkYRbUArPI=
-github.com/tklauser/numcpus v0.12.0 h1:NR85qdvHA9pFse3x3weVZ0r0ST8R6l5RHbZrlRaqob4=
-github.com/tklauser/numcpus v0.12.0/go.mod h1:ABHeXzJnr/qqwguhClkZKT1/8VABcYrsyUiUGobwWJg=
+github.com/tklauser/go-sysconf v0.3.16 h1:frioLaCQSsF5Cy1jgRBrzr6t502KIIwQ0MArYICU0nA=
+github.com/tklauser/go-sysconf v0.3.16/go.mod h1:/qNL9xxDhc7tx3HSRsLWNnuzbVfh3e7gh/BmM179nYI=
+github.com/tklauser/numcpus v0.11.0 h1:nSTwhKH5e1dMNsCdVBukSZrURJRoHbSEQjdEbY+9RXw=
+github.com/tklauser/numcpus v0.11.0/go.mod h1:z+LwcLq54uWZTX0u/bGobaV34u6V7KNlTZejzM6/3MQ=
 github.com/yusufpapurcu/wmi v1.2.3 h1:E1ctvB7uKFMOJw3fdOW32DwGE9I7t++CRUEMKvFoFiw=
 github.com/yusufpapurcu/wmi v1.2.3/go.mod h1:SBZ9tNy3G9/m5Oi98Zks0QjeHVDvuK0qfxQmPyzfmi0=
 go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
 go.yaml.in/yaml/v2 v2.4.4 h1:tuyd0P+2Ont/d6e2rl3be67goVK4R6deVxCUX5vyPaQ=
 go.yaml.in/yaml/v2 v2.4.4/go.mod h1:gMZqIpDtDqOfM0uNfy0SkpRhvUryYH0Z6wdMYcacYXQ=
-golang.design/x/runtime v0.3.0 h1:8bA+GQfO8A18JXJQlQA56pEc+Sgrbo4cmLzjzmJ58ZI=
-golang.design/x/runtime v0.3.0/go.mod h1:PjVKQjImLdSrvjIw4FmrnCPq9BGs5PMBHb8i6b2BN9I=
+golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1 h1:P7S/GeHBAFEZIYp0ePPs2kHXoazz8q2KsyxHyQVGCJg=
+golang.design/x/thread v0.0.0-20210122121316-335e9adffdf1/go.mod h1:9CWpnTUmlQkfdpdutA1nNf4iE5lAVt3QZOu0Z6hahBE=
 golang.org/x/crypto v0.50.0 h1:zO47/JPrL6vsNkINmLoo/PH1gcxpls50DNogFvB5ZGI=
 golang.org/x/crypto v0.50.0/go.mod h1:3muZ7vA7PBCE6xgPX7nkzzjiUq87kRItoJQM1Yo8S+Q=
 golang.org/x/exp v0.0.0-20231005195138-3e424a577f31 h1:9k5exFQKQglLo+RoP+4zMjOFE14P6+vyR0baDAi0Rcs=
@@ -184,8 +183,9 @@ golang.org/x/mod v0.13.0 h1:I/DsJXRlw/8l/0c24sM9yb0T4z9liZTduXvdAWYiysY=
 golang.org/x/mod v0.13.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
 golang.org/x/net v0.53.0 h1:d+qAbo5L0orcWAr0a9JweQpjXF19LMXJE8Ey7hwOdUA=
 golang.org/x/net v0.53.0/go.mod h1:JvMuJH7rrdiCfbeHoo3fCQU24Lf5JJwT9W3sJFulfgs=
-golang.org/x/sys v0.45.0 h1:dO4czNzziLiiXplLQgBCEpCvXQ3dnkn0SdaZSYdQ+FY=
-golang.org/x/sys v0.45.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
+golang.org/x/sys v0.0.0-20210122093101-04d7465088b8/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.43.0 h1:Rlag2XtaFTxp19wS8MXlJwTvoh8ArU6ezoyFsMyCTNI=
+golang.org/x/sys v0.43.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
 golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
 golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
 golang.org/x/tools v0.14.0 h1:jvNa2pY0M4r62jkRQ6RwEZZyPcymeL9XZMLBbV7U2nc=
@@ -128,7 +128,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 	vars["starttime"] = starttime
 	vars["endtime"] = endtime
 	for _, f := range c.functions {
-		cclog.ComponentDebugf("MetricCache", "COLLECT %s COND '%s'", f.Name, f.Condition)
+		cclog.ComponentDebug("MetricCache", "COLLECT", f.Name, "COND", f.Condition)
 		var valuesFloat64 []float64
 		var valuesFloat32 []float32
 		var valuesInt []int
@@ -140,7 +140,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 			vars["metric"] = m
 			value, err := f.gvalCond.EvalBool(context.Background(), vars)
 			if err != nil {
-				cclog.ComponentErrorf("MetricCache", "COLLECT %s COND '%s' : %s", f.Name, f.Condition, err.Error())
+				cclog.ComponentError("MetricCache", "COLLECT", f.Name, "COND", f.Condition, ":", err.Error())
 				continue
 			}
 			if value {
@@ -160,7 +160,7 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 					case bool:
 						valuesBool = append(valuesBool, x)
 					default:
-						cclog.ComponentErrorf("MetricCache", "COLLECT ADD VALUE %v FAILED", v)
+						cclog.ComponentError("MetricCache", "COLLECT ADD VALUE", v, "FAILED")
 					}
 				}
 				matches = append(matches, m)
@@ -213,13 +213,13 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 			vars["values"] = valuesBool
 			len_values = len(valuesBool)
 		}
-		cclog.ComponentDebugf("MetricCache", "EVALUATE %s METRICS %d CALC '%s'", f.Name, len_values, f.Function)
+		cclog.ComponentDebug("MetricCache", "EVALUATE", f.Name, "METRICS", len_values, "CALC", f.Function)

 		vars["metrics"] = matches
 		if len_values > 0 {
 			value, err := gval.Evaluate(f.Function, vars, c.language)
 			if err != nil {
-				cclog.ComponentErrorf("MetricCache", "EVALUATE %s METRICS %d CALC '%s': %s", f.Name, len_values, f.Function, err.Error())
+				cclog.ComponentError("MetricCache", "EVALUATE", f.Name, "METRICS", len_values, "CALC", f.Function, ":", err.Error())
 				break
 			}

@@ -273,12 +273,12 @@ func (c *metricAggregator) Eval(starttime time.Time, endtime time.Time, metrics
 			case string:
 				m, err = lp.NewMessage(f.Name, tags, meta, map[string]any{"value": t}, starttime)
 			default:
-				cclog.ComponentErrorf("MetricCache", "Gval returned invalid type %s skipping metric %s", t, f.Name)
+				cclog.ComponentError("MetricCache", "Gval returned invalid type", t, "skipping metric", f.Name)
 			}
 			if err != nil {
-				cclog.ComponentErrorf("MetricCache", "Cannot create metric from Gval result %v: %s", value, err.Error())
+				cclog.ComponentError("MetricCache", "Cannot create metric from Gval result", value, ":", err.Error())
 			}
-			cclog.ComponentDebugf("MetricCache", "SEND %s", m.ToLineProtocol(nil))
+			cclog.ComponentDebug("MetricCache", "SEND", m)
 			select {
 			case c.output <- m:
 			default:
@@ -295,12 +295,12 @@ func (c *metricAggregator) AddAggregation(name, function, condition string, tags
 	newcond := strings.ReplaceAll(condition, "'", "\"")
 	gvalCond, err := gval.Full(metricCacheLanguage).NewEvaluable(newcond)
 	if err != nil {
-		cclog.ComponentErrorf("MetricAggregator", "Cannot add aggregation, invalid if condition '%s': %s", newcond, err.Error())
+		cclog.ComponentError("MetricAggregator", "Cannot add aggregation, invalid if condition", newcond, ":", err.Error())
 		return err
 	}
 	gvalFunc, err := gval.Full(metricCacheLanguage).NewEvaluable(newfunc)
 	if err != nil {
-		cclog.ComponentErrorf("MetricAggregator", "Cannot add aggregation, invalid function condition %s: %s", newfunc, err.Error())
+		cclog.ComponentError("MetricAggregator", "Cannot add aggregation, invalid function condition", newfunc, ":", err.Error())
 		return err
 	}
 	for _, agg := range c.functions {