ClusterCockpit/cc-metric-collector
1
0
Fork 0
mirror of https://github.com/ClusterCockpit/cc-metric-collector.git synced 2026-06-10 05:47:30 +02:00
Code Issues Packages Projects Releases Wiki Activity

Update cclog calls

Browse Source
This commit is contained in:
Thomas Roehl
2026-06-08 14:52:24 +02:00
parent 5d55ee7a77
commit 037b4f1526
25 changed files with 144 additions and 149 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
cc-metric-collector.go
View File

@@ -132,11 +132,11 @@ func mainFunc() int {
if len(rcfg.ConfigFile.Interval) > 0 {
t, err := time.ParseDuration(rcfg.ConfigFile.Interval)
if err != nil {
cclog.Error("Configuration value 'interval' no valid duration")
cclog.Errorf("Configuration value interval=%s no valid duration", rcfg.ConfigFile.Interval)
}
rcfg.Interval = t
if rcfg.Interval == 0 {
cclog.Error("Configuration value 'interval' must be greater than zero")
cclog.Errorf("Configuration value interval=%s must be greater than zero", rcfg.ConfigFile.Interval)
return 1
}
}
@@ -145,11 +145,11 @@ func mainFunc() int {
if len(rcfg.ConfigFile.Duration) > 0 {
t, err := time.ParseDuration(rcfg.ConfigFile.Duration)
if err != nil {
cclog.Error("Configuration value 'duration' no valid duration")
cclog.Error("Configuration value duration=%s no valid duration", rcfg.ConfigFile.Duration)
}
rcfg.Duration = t
if rcfg.Duration == 0 {
cclog.Error("Configuration value 'duration' must be greater than zero")
cclog.Error("Configuration value duration=%s must be greater than zero", rcfg.ConfigFile.Duration)
return 1
}
}

8
collectors/beegfsmetaMetric.go
View File

@@ -209,16 +209,16 @@ func (m *BeegfsMetaCollector) Read(interval time.Duration, output chan lp.CCMess
} else {
f1, err := strconv.ParseFloat(m.matches["other"], 32)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
"Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err)
continue
}
f2, err := strconv.ParseFloat(split[i], 32)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
"Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err)
continue
}
m.matches["beegfs_cstorage_other"] = fmt.Sprintf("%f", f1+f2)

8
collectors/beegfsstorageMetric.go
View File

@@ -200,16 +200,16 @@ func (m *BeegfsStorageCollector) Read(interval time.Duration, output chan lp.CCM
} else {
f1, err := strconv.ParseFloat(m.matches["other"], 32)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
"Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err)
continue
}
f2, err := strconv.ParseFloat(split[i], 32)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err))
"Metric (other): Failed to convert str written '%s' to float: %v", m.matches["other"], err)
continue
}
m.matches["beegfs_cstorage_other"] = fmt.Sprintf("%f", f1+f2)

12
collectors/cpufreqCpuinfoMetric.go
View File

@@ -139,16 +139,16 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
const cpuInfoFile = "/proc/cpuinfo"
file, err := os.Open(cpuInfoFile)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to open file '%s': %v", cpuInfoFile, err))
"Read(): Failed to open file '%s': %v", cpuInfoFile, err)
return
}
defer func() {
if err := file.Close(); err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to close file '%s': %v", cpuInfoFile, err))
"Read(): Failed to close file '%s': %v", cpuInfoFile, err)
}
}()
@@ -166,9 +166,9 @@ func (m *CPUFreqCpuInfoCollector) Read(interval time.Duration, output chan lp.CC
if !t.isHT {
value, err := strconv.ParseFloat(strings.TrimSpace(lineSplit[1]), 64)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to convert cpu MHz '%s' to float64: %v", lineSplit[1], err))
"Read(): Failed to convert cpu MHz '%s' to float64: %v", lineSplit[1], err)
return
}
if y, err := lp.NewMetric("cpufreq", t.tagSet, m.meta, value, now); err == nil {

13
collectors/cpufreqMetric.go
View File

@@ -95,10 +95,7 @@ func (m *CPUFreqCollector) Init(config json.RawMessage) error {
}
// Initialized
cclog.ComponentDebug(
m.name,
"initialized",
len(m.topology), "non-hyper-threading CPUs")
cclog.ComponentDebugf(m.name, "initialized %d non-hyper-threading CPUs")
m.init = true
return nil
}
@@ -116,16 +113,14 @@ func (m *CPUFreqCollector) Read(interval time.Duration, output chan lp.CCMessage
// Read current frequency
line, err := os.ReadFile(t.scalingCurFreqFile)
if err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("Read(): Failed to read file '%s': %v", t.scalingCurFreqFile, err))
cclog.ComponentErrorf(
m.name, "Read(): Failed to read file '%s': %v", t.scalingCurFreqFile, err)
continue
}
cpuFreq, err := strconv.ParseInt(strings.TrimSpace(string(line)), 10, 64)
if err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("Read(): Failed to convert CPU frequency '%s' to int64: %v", line, err))
m.name, "Read(): Failed to convert CPU frequency '%s' to int64: %v", line, err)
continue
}

8
collectors/cpustatMetric.go
View File

@@ -171,15 +171,15 @@ func (m *CpustatCollector) Read(interval time.Duration, output chan lp.CCMessage
file, err := os.Open(CPUSTATFILE)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to open file '%s': %v", CPUSTATFILE, err))
"Read(): Failed to open file '%s': %v", CPUSTATFILE, err)
}
defer func() {
if err := file.Close(); err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to close file '%s': %v", string(CPUSTATFILE), err))
"Read(): Failed to close file '%s': %v", string(CPUSTATFILE), err)
}
}()

26
collectors/customCmdMetric.go
View File

@@ -64,9 +64,9 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
cmdFields := strings.Fields(c)
command := exec.Command(cmdFields[0], cmdFields[1:]...)
if _, err := command.Output(); err != nil {
cclog.ComponentWarn(
cclog.ComponentWarnf(
m.name,
fmt.Sprintf("%s Init(): Execution of command \"%s\" failed: %v", m.name, command.String(), err))
"%s Init(): Execution of command \"%s\" failed: %v", m.name, command.String(), err)
continue
}
m.cmdFieldsSlice = append(m.cmdFieldsSlice, cmdFields)
@@ -77,7 +77,7 @@ func (m *CustomCmdCollector) Init(config json.RawMessage) error {
if _, err := os.ReadFile(fileName); err != nil {
cclog.ComponentWarn(
m.name,
fmt.Sprintf("%s Init(): Reading of file \"%s\" failed: %v", m.name, fileName, err))
"%s Init(): Reading of file \"%s\" failed: %v", m.name, fileName, err)
continue
}
m.files = append(m.files, fileName)
@@ -100,20 +100,18 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMessa
command := exec.Command(cmdFields[0], cmdFields[1:]...)
stdout, err := command.Output()
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to read command output for command \"%s\": %v", command.String(), err),
)
"Read(): Failed to read command output for command \"%s\": %v", command.String(), err)
continue
}
// Read and decode influxDB line-protocol from command output
metrics, err := lp.FromBytes(stdout)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to decode influx Message: %v", err),
)
"Read(): Failed to decode influx Message: %v", err)
continue
}
for _, metric := range metrics {
@@ -128,20 +126,18 @@ func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMessa
for _, filename := range m.files {
input, err := os.ReadFile(filename)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to read file \"%s\": %v\n", filename, err),
)
"Read(): Failed to read file \"%s\": %v\n", filename, err)
continue
}
// Read and decode influxDB line-protocol from file
metrics, err := lp.FromBytes(input)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to decode influx Message: %v", err),
)
"Read(): Failed to decode influx Message: %v", err)
continue
}
for _, metric := range metrics {

6
collectors/diskstatMetric.go
View File

@@ -77,16 +77,16 @@ func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMessag
file, err := os.Open(MOUNTFILE)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to open file '%s': %v", MOUNTFILE, err))
"Read(): Failed to open file '%s': %v", MOUNTFILE, err)
return
}
defer func() {
if err := file.Close(); err != nil {
cclog.ComponentError(
m.name,
fmt.Sprintf("Read(): Failed to close file '%s': %v", MOUNTFILE, err))
"Read(): Failed to close file '%s': %v", MOUNTFILE, err)
}
}()

14
collectors/gpfsMetric.go
View File

@@ -371,7 +371,7 @@ func (m *GpfsCollector) Init(config json.RawMessage) error {
if err != nil {
// if using sudo, exec.lookPath will return EACCES (file mode r-x------), this can be ignored
if m.config.Sudo && errors.Is(err, syscall.EACCES) {
cclog.ComponentWarn(m.name, fmt.Sprintf("got error looking for mmpmon binary '%s': %v . This is expected when using sudo, continuing.", m.config.Mmpmon, err))
cclog.ComponentWarnf(m.name, "got error looking for mmpmon binary '%s': %v . This is expected when using sudo, continuing.", m.config.Mmpmon, err)
// the file was given in the config, use it
p = m.config.Mmpmon
} else {
@@ -517,23 +517,23 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// return code
rc, err := strconv.Atoi(key_value["_rc_"])
if err != nil {
cclog.ComponentError(m.name, fmt.Sprintf("Read(): Failed to convert return code '%s' to int: %v", key_value["_rc_"], err))
cclog.ComponentErrorf(m.name, "Read(): Failed to convert return code '%s' to int: %v", key_value["_rc_"], err)
continue
}
if rc != 0 {
cclog.ComponentError(m.name, fmt.Sprintf("Read(): Filesystem '%s' is not ok.", filesystem))
cclog.ComponentErrorf(m.name, "Read(): Filesystem '%s' is not ok.", filesystem)
continue
}
// timestamp
sec, err := strconv.ParseInt(key_value["_t_"], 10, 64)
if err != nil {
cclog.ComponentError(m.name, fmt.Sprintf("Read(): Failed to convert seconds '%s' to int64: %v", key_value["_t_"], err))
cclog.ComponentErrorf(m.name, "Read(): Failed to convert seconds '%s' to int64: %v", key_value["_t_"], err)
continue
}
msec, err := strconv.ParseInt(key_value["_tu_"], 10, 64)
if err != nil {
cclog.ComponentError(m.name, fmt.Sprintf("Read(): Failed to convert micro seconds '%s' to int64: %v", key_value["_tu_"], err))
cclog.ComponentErrorf(m.name, "Read(): Failed to convert micro seconds '%s' to int64: %v", key_value["_tu_"], err)
continue
}
timestamp := time.Unix(sec, msec*1000)
@@ -551,7 +551,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
for _, metric := range GpfsAbsMetrics {
value, err := strconv.ParseInt(key_value[metric.prefix], 10, 64)
if err != nil {
cclog.ComponentError(m.name, fmt.Sprintf("Read(): Failed to convert %s '%s' to int64: %v", metric.desc, key_value[metric.prefix], err))
cclog.ComponentErrorf(m.name, "Read(): Failed to convert %s '%s' to int64: %v", metric.desc, key_value[metric.prefix], err)
continue
}
newstate[metric.prefix] = value
@@ -636,7 +636,7 @@ func (m *GpfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
}
} else {
// the value could not be computed correctly
cclog.ComponentWarn(m.name, fmt.Sprintf("Read(): Could not compute value for filesystem %s of metric %s: vold_ok = %t, vnew_ok = %t", filesystem, metric.name, vold_ok, vnew_ok))
cclog.ComponentWarnf(m.name, "Read(): Could not compute value for filesystem %s of metric %s: vold_ok = %t, vnew_ok = %t", filesystem, metric.name, vold_ok, vnew_ok)
}
}

8
collectors/iostatMetric.go
View File

@@ -145,16 +145,16 @@ func (m *IOstatCollector) Read(interval time.Duration, output chan lp.CCMessage)
file, err := os.Open(IOSTATFILE)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to open file '%s': %v", IOSTATFILE, err))
"Read(): Failed to open file '%s': %v", IOSTATFILE, err)
return
}
defer func() {
if err := file.Close(); err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to close file '%s': %v", IOSTATFILE, err))
"Read(): Failed to close file '%s': %v", IOSTATFILE, err)
}
}()

32
collectors/likwidMetric.go
View File

@@ -12,6 +12,12 @@ package collectors
#cgo LDFLAGS: -Wl,--unresolved-symbols=ignore-in-object-files
#include <stdlib.h>
#include <likwid.h>
int cc_add_hwthread(int cpu_id) {
return HPMaddThread(cpu_id);
}
*/
import "C"
@@ -261,12 +267,12 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
}
for _, metric := range evset.Metrics {
// Try to evaluate the metric
cclog.ComponentDebug(m.name, "Checking", metric.Name)
cclog.ComponentDebugf(m.name, "Checking %s", metric.Name)
if !checkMetricType(metric.Type) {
cclog.ComponentError(m.name, "Metric", metric.Name, "uses invalid type", metric.Type)
cclog.ComponentErrorf(m.name, "Metric %s uses invalid type %s", metric.Name, metric.Type)
metric.Calc = ""
} else if !testLikwidMetricFormula(metric.Calc, params) {
cclog.ComponentError(m.name, "Metric", metric.Name, "cannot be calculated with given counters")
cclog.ComponentError(m.name, "Metric %s cannot be calculated with given counters", metric.Name)
metric.Calc = ""
} else {
globalParams = append(globalParams, metric.Name)
@@ -281,13 +287,13 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
for _, metric := range m.config.Metrics {
// Try to evaluate the global metric
if !checkMetricType(metric.Type) {
cclog.ComponentError(m.name, "Metric", metric.Name, "uses invalid type", metric.Type)
cclog.ComponentErrorf(m.name, "Metric %s uses invalid type %s", metric.Name, metric.Type)
metric.Calc = ""
} else if !testLikwidMetricFormula(metric.Calc, globalParams) {
cclog.ComponentError(m.name, "Metric", metric.Name, "cannot be calculated with given counters")
cclog.ComponentError(m.name, "Metric %s cannot be calculated with given counters", metric.Name)
metric.Calc = ""
} else if !checkMetricType(metric.Type) {
cclog.ComponentError(m.name, "Metric", metric.Name, "has invalid type")
cclog.ComponentError(m.name, "Metric %s has invalid type", metric.Name)
metric.Calc = ""
} else {
totalMetrics++
@@ -328,7 +334,7 @@ func (m *LikwidCollector) Init(config json.RawMessage) error {
for _, c := range m.cpulist {
m.measureThread.Call(
func() {
retCode := C.HPMaddThread(C.uint32_t(c))
retCode := C.cc_add_hwthread(C.int(c))
if retCode != 0 {
err := fmt.Errorf("C.HPMaddThread(%v) failed with return code %v", c, retCode)
cclog.ComponentError(m.name, err.Error())
@@ -375,16 +381,16 @@ func (m *LikwidCollector) takeMeasurement(evidx int, evset LikwidEventsetConfig,
// Watch changes for the lock file ()
watcher, err := fsnotify.NewWatcher()
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("takeMeasurement(): Failed to create a new fsnotify.Watcher: %v", err))
"takeMeasurement(): Failed to create a new fsnotify.Watcher: %v", err)
return true, err
}
defer func() {
if err := watcher.Close(); err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("takeMeasurement(): Failed to close fsnotify.Watcher: %v", err))
"takeMeasurement(): Failed to close fsnotify.Watcher: %v", err)
}
}()
if len(m.config.LockfilePath) > 0 {
@@ -597,7 +603,7 @@ func (m *LikwidCollector) calcEventsetMetrics(evset LikwidEventsetConfig, interv
if tid >= 0 && len(metric.Calc) > 0 {
value, err := agg.EvalFloat64Condition(metric.Calc, evset.results[tid])
if err != nil {
cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
cclog.ComponentErrorf(m.name, "Calculation for metric %s failed: %s", metric.Name, err.Error())
value = 0.0
}
if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {
@@ -762,7 +768,7 @@ func (m *LikwidCollector) calcGlobalMetrics(groups []LikwidEventsetConfig, inter
// Evaluate the metric
value, err := agg.EvalFloat64Condition(metric.Calc, params)
if err != nil {
cclog.ComponentError(m.name, "Calculation for metric", metric.Name, "failed:", err.Error())
cclog.ComponentErrorf(m.name, "Calculation for metric %s failed: %s", metric.Name, err.Error())
value = 0.0
}
if m.config.InvalidToZero && (math.IsNaN(value) || math.IsInf(value, 0)) {

12
collectors/loadavgMetric.go
View File

@@ -89,9 +89,9 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage
}
buffer, err := os.ReadFile(LOADAVGFILE)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err))
"Read(): Failed to read file '%s': %v", LOADAVGFILE, err)
return
}
now := time.Now()
@@ -101,9 +101,9 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage
for i, name := range m.load_matches {
x, err := strconv.ParseFloat(ls[i], 64)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to convert '%s' to float64: %v", ls[i], err))
"Read(): Failed to convert '%s' to float64: %v", ls[i], err)
continue
}
if m.load_skips[i] {
@@ -120,9 +120,9 @@ func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage
for i, name := range m.proc_matches {
x, err := strconv.ParseInt(lv[i], 10, 64)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to convert '%s' to float64: %v", lv[i], err))
"Read(): Failed to convert '%s' to float64: %v", lv[i], err)
continue
}
if m.proc_skips[i] {

2
collectors/memstatMetric.go
View File

@@ -84,7 +84,7 @@ func getStats(filename string) map[string]MemstatStats {
case 5:
v, err := strconv.ParseFloat(linefields[3], 64)
if err == nil {
cclog.ComponentDebug("getStats", strings.Trim(linefields[2], ":"), v, linefields[4])
cclog.ComponentDebug("MemstatCollector", "getStats %s value %v unit %s", strings.Trim(linefields[2], ":"), v, linefields[4])
stats[strings.Trim(linefields[2], ":")] = MemstatStats{
value: v,
unit: linefields[4],

8
collectors/netstatMetric.go
View File

@@ -222,16 +222,16 @@ func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage
file, err := os.Open(NETSTATFILE)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to open file '%s': %v", NETSTATFILE, err))
"Read(): Failed to open file '%s': %v", NETSTATFILE, err)
return
}
defer func() {
if err := file.Close(); err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to close file '%s': %v", NETSTATFILE, err))
"Read(): Failed to close file '%s': %v", NETSTATFILE, err)
}
}()

5
collectors/nfsMetric.go
View File

@@ -125,10 +125,9 @@ func (m *nfsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
timestamp := time.Now()
if err := m.updateStats(); err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): updateStats() failed: %v", err),
)
"Read(): updateStats() failed: %v", err)
return
}
var prefix string

2
collectors/numastatsMetric.go
View File

@@ -117,7 +117,7 @@ func (m *NUMAStatsCollector) Init(config json.RawMessage) error {
}
// Initialized
cclog.ComponentDebug(m.name, "initialized", len(m.topology), "NUMA domains")
cclog.ComponentDebugf(m.name, "initialized %d NUMA domains", len(m.topology))
m.init = true
return nil
}

56
collectors/nvidiaMetric.go
View File

@@ -113,7 +113,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
// Skip excluded devices by ID
str_i := strconv.Itoa(i)
if slices.Contains(m.config.ExcludeDevices, str_i) {
cclog.ComponentDebug(m.name, "Skipping excluded device", str_i)
cclog.ComponentDebugf(m.name, "Skipping excluded device %s", str_i)
continue
}
@@ -121,7 +121,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
device, ret := nvml.DeviceGetHandleByIndex(i)
if ret != nvml.SUCCESS {
err = errors.New(nvml.ErrorString(ret))
cclog.ComponentError(m.name, "Unable to get device at index", i, ":", err.Error())
cclog.ComponentErrorf(m.name, "Unable to get device at index %d: %s", i, err.Error())
continue
}
@@ -129,7 +129,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
pciInfo, ret := nvml.DeviceGetPciInfo(device)
if ret != nvml.SUCCESS {
err = errors.New(nvml.ErrorString(ret))
cclog.ComponentError(m.name, "Unable to get PCI info for device at index", i, ":", err.Error())
cclog.ComponentErrorf(m.name, "Unable to get PCI info for device at index %d: %s", i, err.Error())
continue
}
// Create PCI ID in the common format used by the NVML.
@@ -141,7 +141,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
// Skip excluded devices specified by PCI ID
if slices.Contains(m.config.ExcludeDevices, pci_id) {
cclog.ComponentDebug(m.name, "Skipping excluded device", pci_id)
cclog.ComponentDebugf(m.name, "Skipping excluded device %s", pci_id)
continue
}
@@ -183,7 +183,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
if m.config.AddBoardNumberMeta {
board, ret := nvml.DeviceGetBoardPartNumber(device)
if ret != nvml.SUCCESS {
cclog.ComponentError(m.name, "Unable to get boart part number for device at index", i, ":", err.Error())
cclog.ComponentErrorf(m.name, "Unable to get boart part number for device at index %d: %s", i, err.Error())
} else {
g.meta["board_number"] = board
}
@@ -191,7 +191,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
if m.config.AddSerialMeta {
serial, ret := nvml.DeviceGetSerial(device)
if ret != nvml.SUCCESS {
cclog.ComponentError(m.name, "Unable to get serial number for device at index", i, ":", err.Error())
cclog.ComponentErrorf(m.name, "Unable to get serial number for device at index %d: %s", i, err.Error())
} else {
g.meta["serial"] = serial
}
@@ -199,7 +199,7 @@ func (m *NvidiaCollector) Init(config json.RawMessage) error {
if m.config.AddUuidMeta {
uuid, ret := nvml.DeviceGetUUID(device)
if ret != nvml.SUCCESS {
cclog.ComponentError(m.name, "Unable to get UUID for device at index", i, ":", err.Error())
cclog.ComponentErrorf(m.name, "Unable to get UUID for device at index %d: %s", i, err.Error())
} else {
g.meta["uuid"] = uuid
}
@@ -1128,97 +1128,97 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage)
}
err = readMemoryInfo(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readMemoryInfo for device", name, "failed")
cclog.ComponentDebugf(m.name, "readMemoryInfo for device %s failed", name)
}
err = readUtilization(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readUtilization for device", name, "failed")
cclog.ComponentDebugf(m.name, "readUtilization for device %s failed", name)
}
err = readTemp(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readTemp for device", name, "failed")
cclog.ComponentDebugf(m.name, "readTemp for device %s failed", name)
}
err = readFan(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readFan for device", name, "failed")
cclog.ComponentDebugf(m.name, "readFan for device %s failed", name)
}
err = readEccMode(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readEccMode for device", name, "failed")
cclog.ComponentDebugf(m.name, "readEccMode for device %s failed", name)
}
err = readPerfState(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readPerfState for device", name, "failed")
cclog.ComponentDebugf(m.name, "readPerfState for device %s failed", name)
}
err = readPowerUsage(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readPowerUsage for device", name, "failed")
cclog.ComponentDebugf(m.name, "readPowerUsage for device %s failed", name)
}
err = readEnergyConsumption(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readEnergyConsumption for device", name, "failed")
cclog.ComponentDebugf(m.name, "readEnergyConsumption for device %s failed", name)
}
err = readClocks(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readClocks for device", name, "failed")
cclog.ComponentDebugf(m.name, "readClocks for device %s failed", name)
}
err = readMaxClocks(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readMaxClocks for device", name, "failed")
cclog.ComponentDebugf(m.name, "readMaxClocks for device %s failed", name)
}
err = readEccErrors(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readEccErrors for device", name, "failed")
cclog.ComponentDebugf(m.name, "readEccErrors for device %s failed", name)
}
err = readPowerLimit(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readPowerLimit for device", name, "failed")
cclog.ComponentDebugf(m.name, "readPowerLimit for device %s failed", name)
}
err = readEncUtilization(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readEncUtilization for device", name, "failed")
cclog.ComponentDebugf(m.name, "readEncUtilization for device %s failed", name)
}
err = readDecUtilization(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readDecUtilization for device", name, "failed")
cclog.ComponentDebugf(m.name, "readDecUtilization for device %s failed", name)
}
err = readRemappedRows(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readRemappedRows for device", name, "failed")
cclog.ComponentDebugf(m.name, "readRemappedRows for device %s failed", name)
}
err = readBarMemoryInfo(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readBarMemoryInfo for device", name, "failed")
cclog.ComponentDebugf(m.name, "readBarMemoryInfo for device %s failed", name)
}
err = readProcessCounts(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readProcessCounts for device", name, "failed")
cclog.ComponentDebugf(m.name, "readProcessCounts for device %s failed", name)
}
err = readViolationStats(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readViolationStats for device", name, "failed")
cclog.ComponentDebugf(m.name, "readViolationStats for device %s failed", name)
}
err = readNVLinkStats(device, output)
if err != nil {
cclog.ComponentDebug(m.name, "readNVLinkStats for device", name, "failed")
cclog.ComponentDebugf(m.name, "readNVLinkStats for device %s failed", name)
}
}
@@ -1244,7 +1244,7 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage)
if maxMig == 0 {
continue
}
cclog.ComponentDebug(m.name, "Reading MIG devices for GPU", i)
cclog.ComponentDebugf(m.name, "Reading MIG devices for GPU %d", i)
for j := range maxMig {
mdev, ret := nvml.DeviceGetMigDeviceHandleByIndex(m.gpus[i].device, j)
@@ -1268,7 +1268,7 @@ func (m *NvidiaCollector) Read(interval time.Duration, output chan lp.CCMessage)
if m.config.UseUuidForMigDevices {
uuid, ret := nvml.DeviceGetUUID(mdev)
if ret != nvml.SUCCESS {
cclog.ComponentError(m.name, "Unable to get UUID for mig device at index", j, ":", err.Error())
cclog.ComponentErrorf(m.name, "Unable to get UUID for mig device at index %d: %s", j, err.Error())
} else {
migDevice.tags["stype-id"] = uuid
}

7
collectors/raplMetric.go
View File

@@ -208,11 +208,10 @@ func (m *RAPLCollector) Init(config json.RawMessage) error {
}
// Initialized
cclog.ComponentDebug(
cclog.ComponentDebugf(
m.name,
"initialized",
len(m.RAPLZoneInfo),
"zones with running average power limit (RAPL) monitoring attributes")
"initialized %d zones with running average power limit (RAPL) monitoring attributes",
len(m.RAPLZoneInfo))
m.init = true
return err

4
collectors/rocmsmiMetric.go
View File

@@ -124,7 +124,7 @@ func (m *RocmSmiCollector) Init(config json.RawMessage) error {
if m.config.AddSerialMeta {
serial, ret := rocm_smi.DeviceGetSerialNumber(device)
if ret != rocm_smi.STATUS_SUCCESS {
cclog.ComponentError(m.name, "Unable to get serial number for device at index", i, ":", rocm_smi.StatusStringNoError(ret))
cclog.ComponentErrorf(m.name, "Unable to get serial number for device at index %d: %s", i, rocm_smi.StatusStringNoError(ret))
} else {
dev.meta["serial"] = serial
}
@@ -152,7 +152,7 @@ func (m *RocmSmiCollector) Read(interval time.Duration, output chan lp.CCMessage
for _, dev := range m.devices {
metrics, ret := rocm_smi.DeviceGetMetrics(dev.device)
if ret != rocm_smi.STATUS_SUCCESS {
cclog.ComponentError(m.name, "Unable to get metrics for device at index", dev.index, ":", rocm_smi.StatusStringNoError(ret))
cclog.ComponentErrorf(m.name, "Unable to get metrics for device at index %d: %s", dev.index, rocm_smi.StatusStringNoError(ret))
continue
}

8
collectors/schedstatMetric.go
View File

@@ -147,15 +147,15 @@ func (m *SchedstatCollector) Read(interval time.Duration, output chan lp.CCMessa
file, err := os.Open(SCHEDSTATFILE)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to open file '%s': %v", SCHEDSTATFILE, err))
"Read(): Failed to open file '%s': %v", SCHEDSTATFILE, err)
}
defer func() {
if err := file.Close(); err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to close file '%s': %v", SCHEDSTATFILE, err))
"Read(): Failed to close file '%s': %v", SCHEDSTATFILE, err)
}
}()

4
collectors/slurmCgroupMetric.go
View File

@@ -240,7 +240,7 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
globPattern := filepath.Join(m.cgroupBase, "job_*")
jobDirs, err := filepath.Glob(globPattern)
if err != nil {
cclog.ComponentError(m.name, "Error globbing job directories:", err.Error())
cclog.ComponentErrorf(m.name, "Error globbing job directories: %s", err.Error())
return
}
@@ -249,7 +249,7 @@ func (m *SlurmCgroupCollector) Read(interval time.Duration, output chan lp.CCMes
jobdata, err := m.ReadJobData(jKey)
if err != nil {
cclog.ComponentError(m.name, "Error reading job data for", jKey, ":", err.Error())
cclog.ComponentError(m.name, "Error reading job data for %s: %s", jKey, err.Error())
continue
}

4
collectors/smartmonMetric.go
View File

@@ -228,12 +228,12 @@ func (m *SmartMonCollector) Read(interval time.Duration, output chan lp.CCMessag
stdout, err := command.Output()
if err != nil {
cclog.ComponentError(m.name, "cannot read data for device", d.Name)
cclog.ComponentErrorf(m.name, "cannot read data for device %s", d.Name)
continue
}
err = json.Unmarshal(stdout, &data)
if err != nil {
cclog.ComponentError(m.name, "cannot unmarshal data for device", d.Name)
cclog.ComponentErrorf(m.name, "cannot unmarshal data for device %s", d.Name)
continue
}
if !m.excludeMetric.temp {

8
collectors/tempMetric.go
View File

@@ -188,16 +188,16 @@ func (m *TempCollector) Read(interval time.Duration, output chan lp.CCMessage) {
// Read sensor file
buffer, err := os.ReadFile(sensor.file)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to read file '%s': %v", sensor.file, err))
"Read(): Failed to read file '%s': %v", sensor.file, err)
continue
}
x, err := strconv.ParseInt(strings.TrimSpace(string(buffer)), 10, 64)
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to convert temperature '%s' to int64: %v", buffer, err))
"Read(): Failed to convert temperature '%s' to int64: %v", buffer, err)
continue
}
x /= 1000

4
collectors/topprocsMetric.go
View File

@@ -77,9 +77,9 @@ func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessag
command := exec.Command("ps", "-Ao", "comm", "--sort=-pcpu")
stdout, err := command.Output()
if err != nil {
cclog.ComponentError(
cclog.ComponentErrorf(
m.name,
fmt.Sprintf("Read(): Failed to read output from command \"%s\": %v", command.String(), err))
"Read(): Failed to read output from command \"%s\": %v", command.String(), err)
return
}

26
internal/metricRouter/metricRouter.go
View File

@@ -35,18 +35,18 @@ type metricRouterTagConfig struct {
// Metric router configuration
type metricRouterConfig struct {
HostnameTagName string `json:"hostname_tag"` // Key name used when adding the hostname to a metric (default 'hostname')
AddTags []metricRouterTagConfig `json:"add_tags"` // List of tags that are added when the condition is met
DelTags []metricRouterTagConfig `json:"delete_tags"` // List of tags that are removed when the condition is met
IntervalAgg []agg.MetricAggregatorIntervalConfig `json:"interval_aggregates"` // List of aggregation function processed at the end of an interval
DropMetrics []string `json:"drop_metrics"` // List of metric names to drop. For fine-grained dropping use drop_metrics_if
DropMetricsIf []string `json:"drop_metrics_if"` // List of evaluatable terms to drop metrics
RenameMetrics map[string]string `json:"rename_metrics"` // Map to rename metric name from key to value
IntervalStamp bool `json:"interval_timestamp"` // Update timestamp periodically by ticker each interval?
NumCacheIntervals int `json:"num_cache_intervals"` // Number of intervals of cached metrics for evaluation
MaxForward int `json:"max_forward"` // Number of maximal forwarded metrics at one select
NormalizeUnits bool `json:"normalize_units"` // Check unit meta flag and normalize it using cc-units
ChangeUnitPrefix map[string]string `json:"change_unit_prefix"` // Add prefix that should be applied to the metrics
HostnameTagName string `json:"hostname_tag,omitempty"` // Key name used when adding the hostname to a metric (default 'hostname')
AddTags []metricRouterTagConfig `json:"add_tags,omitempty"` // List of tags that are added when the condition is met
DelTags []metricRouterTagConfig `json:"delete_tags,omitempty"` // List of tags that are removed when the condition is met
IntervalAgg []agg.MetricAggregatorIntervalConfig `json:"interval_aggregates,omitempty"` // List of aggregation function processed at the end of an interval
DropMetrics []string `json:"drop_metrics,omitempty"` // List of metric names to drop. For fine-grained dropping use drop_metrics_if
DropMetricsIf []string `json:"drop_metrics_if,omitempty"` // List of evaluatable terms to drop metrics
RenameMetrics map[string]string `json:"rename_metrics,omitempty"` // Map to rename metric name from key to value
IntervalStamp bool `json:"interval_timestamp,omitempty"` // Update timestamp periodically by ticker each interval?
NumCacheIntervals int `json:"num_cache_intervals,omitempty"` // Number of intervals of cached metrics for evaluation
MaxForward int `json:"max_forward,omitempty"` // Number of maximal forwarded metrics at one select
NormalizeUnits bool `json:"normalize_units,omitempty"` // Check unit meta flag and normalize it using cc-units
ChangeUnitPrefix map[string]string `json:"change_unit_prefix,omitempty"` // Add prefix that should be applied to the metrics
MessageProcessor json.RawMessage `json:"process_messages,omitempty"`
}
@@ -297,7 +297,7 @@ func (r *metricRouter) Start() {
case timestamp := <-timeChan:
r.timestamp = timestamp
cclog.ComponentDebug("MetricRouter", "Update timestamp", r.timestamp.UnixNano())
cclog.ComponentDebugf("MetricRouter", "Update timestamp %d", r.timestamp.UnixNano())
case p := <-r.coll_input:
coll_forward(p)