mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-12-26 07:29:04 +01:00
7840de7b82
* Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Update README.md Use right JSON type in configuration * Update sink's README * Test whether ipmitool or ipmi-sensors can be executed without errors * Little fixes to the prometheus sink (#115) * Add uint64 to float64 cast option * Add prometheus sink to the list of available sinks * Add aggregated counters by gpu for nvlink errors --------- Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de> * Ccmessage migration (#119) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Switch to CCMessage for all files. --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Switch to ccmessage also for latest additions in nvidiaMetric * New Message processor (#118) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * New message processor to check whether a message should be dropped or manipulate it in flight * Create a copy of message before manipulation --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Update collector's Makefile and go.mod/sum files * Use message processor in router, all sinks and all receivers * Add support for credential file (NKEY) to NATS sink and receiver * Fix JSON keys in message processor configuration * Update docs for message processor, router and the default router config file * Add link to expr syntax and fix regex matching docs * Update sample collectors * Minor style change in collector manager * Some helpers for ccTopology * LIKWID collector: write log owner change only once * Fix for metrics without units and reduce debugging messages for messageProcessor * Use shorted hostname for hostname added by router * Define default port for NATS * CPUstat collector: only add unit for applicable metrics * Add precision option to all sinks using Influx's encoder * Add message processor to all sink documentation * Add units to documentation of cpustat collector --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: oscarminus <me@oscarminus.de> Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de>
145 lines
4.4 KiB
Go
145 lines
4.4 KiB
Go
package collectors
|
|
|
|
import (
|
|
"encoding/json"
|
|
"runtime"
|
|
"syscall"
|
|
"time"
|
|
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
|
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
|
)
|
|
|
|
type SelfCollectorConfig struct {
|
|
MemStats bool `json:"read_mem_stats"`
|
|
GoRoutines bool `json:"read_goroutines"`
|
|
CgoCalls bool `json:"read_cgo_calls"`
|
|
Rusage bool `json:"read_rusage"`
|
|
}
|
|
|
|
type SelfCollector struct {
|
|
metricCollector
|
|
config SelfCollectorConfig // the configuration structure
|
|
meta map[string]string // default meta information
|
|
tags map[string]string // default tags
|
|
}
|
|
|
|
func (m *SelfCollector) Init(config json.RawMessage) error {
|
|
var err error = nil
|
|
m.name = "SelfCollector"
|
|
m.setup()
|
|
m.parallel = true
|
|
m.meta = map[string]string{"source": m.name, "group": "Self"}
|
|
m.tags = map[string]string{"type": "node"}
|
|
if len(config) > 0 {
|
|
err = json.Unmarshal(config, &m.config)
|
|
if err != nil {
|
|
cclog.ComponentError(m.name, "Error reading config:", err.Error())
|
|
return err
|
|
}
|
|
}
|
|
m.init = true
|
|
return err
|
|
}
|
|
|
|
func (m *SelfCollector) Read(interval time.Duration, output chan lp.CCMessage) {
|
|
timestamp := time.Now()
|
|
|
|
if m.config.MemStats {
|
|
var memstats runtime.MemStats
|
|
runtime.ReadMemStats(&memstats)
|
|
|
|
y, err := lp.NewMessage("total_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.TotalAlloc}, timestamp)
|
|
if err == nil {
|
|
y.AddMeta("unit", "Bytes")
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("heap_alloc", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapAlloc}, timestamp)
|
|
if err == nil {
|
|
y.AddMeta("unit", "Bytes")
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("heap_sys", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapSys}, timestamp)
|
|
if err == nil {
|
|
y.AddMeta("unit", "Bytes")
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("heap_idle", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapIdle}, timestamp)
|
|
if err == nil {
|
|
y.AddMeta("unit", "Bytes")
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("heap_inuse", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapInuse}, timestamp)
|
|
if err == nil {
|
|
y.AddMeta("unit", "Bytes")
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("heap_released", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapReleased}, timestamp)
|
|
if err == nil {
|
|
y.AddMeta("unit", "Bytes")
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("heap_objects", m.tags, m.meta, map[string]interface{}{"value": memstats.HeapObjects}, timestamp)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
if m.config.GoRoutines {
|
|
y, err := lp.NewMessage("num_goroutines", m.tags, m.meta, map[string]interface{}{"value": runtime.NumGoroutine()}, timestamp)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
if m.config.CgoCalls {
|
|
y, err := lp.NewMessage("num_cgo_calls", m.tags, m.meta, map[string]interface{}{"value": runtime.NumCgoCall()}, timestamp)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
if m.config.Rusage {
|
|
var rusage syscall.Rusage
|
|
err := syscall.Getrusage(syscall.RUSAGE_SELF, &rusage)
|
|
if err == nil {
|
|
sec, nsec := rusage.Utime.Unix()
|
|
t := float64(sec) + (float64(nsec) * 1e-9)
|
|
y, err := lp.NewMessage("rusage_user_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
|
|
if err == nil {
|
|
y.AddMeta("unit", "seconds")
|
|
output <- y
|
|
}
|
|
sec, nsec = rusage.Stime.Unix()
|
|
t = float64(sec) + (float64(nsec) * 1e-9)
|
|
y, err = lp.NewMessage("rusage_system_time", m.tags, m.meta, map[string]interface{}{"value": t}, timestamp)
|
|
if err == nil {
|
|
y.AddMeta("unit", "seconds")
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("rusage_vol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nvcsw}, timestamp)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("rusage_invol_ctx_switch", m.tags, m.meta, map[string]interface{}{"value": rusage.Nivcsw}, timestamp)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("rusage_signals", m.tags, m.meta, map[string]interface{}{"value": rusage.Nsignals}, timestamp)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("rusage_major_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Majflt}, timestamp)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
y, err = lp.NewMessage("rusage_minor_pgfaults", m.tags, m.meta, map[string]interface{}{"value": rusage.Minflt}, timestamp)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
|
|
}
|
|
}
|
|
|
|
func (m *SelfCollector) Close() {
|
|
m.init = false
|
|
}
|