mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-12-26 15:29:04 +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>
125 lines
2.8 KiB
Go
125 lines
2.8 KiB
Go
package collectors
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"os"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
|
)
|
|
|
|
// LoadavgCollector collects:
|
|
// * load average of last 1, 5 & 15 minutes
|
|
// * number of processes currently runnable
|
|
// * total number of processes in system
|
|
//
|
|
// See: https://www.kernel.org/doc/html/latest/filesystems/proc.html
|
|
const LOADAVGFILE = "/proc/loadavg"
|
|
|
|
type LoadavgCollector struct {
|
|
metricCollector
|
|
tags map[string]string
|
|
load_matches []string
|
|
load_skips []bool
|
|
proc_matches []string
|
|
proc_skips []bool
|
|
config struct {
|
|
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
|
|
}
|
|
}
|
|
|
|
func (m *LoadavgCollector) Init(config json.RawMessage) error {
|
|
m.name = "LoadavgCollector"
|
|
m.parallel = true
|
|
m.setup()
|
|
if len(config) > 0 {
|
|
err := json.Unmarshal(config, &m.config)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
m.meta = map[string]string{
|
|
"source": m.name,
|
|
"group": "LOAD"}
|
|
m.tags = map[string]string{"type": "node"}
|
|
m.load_matches = []string{
|
|
"load_one",
|
|
"load_five",
|
|
"load_fifteen"}
|
|
m.load_skips = make([]bool, len(m.load_matches))
|
|
m.proc_matches = []string{
|
|
"proc_run",
|
|
"proc_total"}
|
|
m.proc_skips = make([]bool, len(m.proc_matches))
|
|
|
|
for i, name := range m.load_matches {
|
|
_, m.load_skips[i] = stringArrayContains(m.config.ExcludeMetrics, name)
|
|
}
|
|
for i, name := range m.proc_matches {
|
|
_, m.proc_skips[i] = stringArrayContains(m.config.ExcludeMetrics, name)
|
|
}
|
|
m.init = true
|
|
return nil
|
|
}
|
|
|
|
func (m *LoadavgCollector) Read(interval time.Duration, output chan lp.CCMessage) {
|
|
if !m.init {
|
|
return
|
|
}
|
|
buffer, err := os.ReadFile(LOADAVGFILE)
|
|
if err != nil {
|
|
cclog.ComponentError(
|
|
m.name,
|
|
fmt.Sprintf("Read(): Failed to read file '%s': %v", LOADAVGFILE, err))
|
|
return
|
|
}
|
|
now := time.Now()
|
|
|
|
// Load metrics
|
|
ls := strings.Split(string(buffer), ` `)
|
|
for i, name := range m.load_matches {
|
|
x, err := strconv.ParseFloat(ls[i], 64)
|
|
if err != nil {
|
|
cclog.ComponentError(
|
|
m.name,
|
|
fmt.Sprintf("Read(): Failed to convert '%s' to float64: %v", ls[i], err))
|
|
continue
|
|
}
|
|
if m.load_skips[i] {
|
|
continue
|
|
}
|
|
y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
|
|
// Process metrics
|
|
lv := strings.Split(ls[3], `/`)
|
|
for i, name := range m.proc_matches {
|
|
x, err := strconv.ParseInt(lv[i], 10, 64)
|
|
if err != nil {
|
|
cclog.ComponentError(
|
|
m.name,
|
|
fmt.Sprintf("Read(): Failed to convert '%s' to float64: %v", lv[i], err))
|
|
continue
|
|
}
|
|
if m.proc_skips[i] {
|
|
continue
|
|
}
|
|
y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
|
|
}
|
|
}
|
|
|
|
func (m *LoadavgCollector) Close() {
|
|
m.init = false
|
|
}
|