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>
81 lines
1.8 KiB
Go
81 lines
1.8 KiB
Go
package collectors
|
|
|
|
import (
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"log"
|
|
"os/exec"
|
|
"strings"
|
|
"time"
|
|
|
|
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
|
)
|
|
|
|
const MAX_NUM_PROCS = 10
|
|
const DEFAULT_NUM_PROCS = 2
|
|
|
|
type TopProcsCollectorConfig struct {
|
|
Num_procs int `json:"num_procs"`
|
|
}
|
|
|
|
type TopProcsCollector struct {
|
|
metricCollector
|
|
tags map[string]string
|
|
config TopProcsCollectorConfig
|
|
}
|
|
|
|
func (m *TopProcsCollector) Init(config json.RawMessage) error {
|
|
var err error
|
|
m.name = "TopProcsCollector"
|
|
m.parallel = true
|
|
m.tags = map[string]string{"type": "node"}
|
|
m.meta = map[string]string{"source": m.name, "group": "TopProcs"}
|
|
if len(config) > 0 {
|
|
err = json.Unmarshal(config, &m.config)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
} else {
|
|
m.config.Num_procs = int(DEFAULT_NUM_PROCS)
|
|
}
|
|
if m.config.Num_procs <= 0 || m.config.Num_procs > MAX_NUM_PROCS {
|
|
return fmt.Errorf("num_procs option must be set in 'topprocs' config (range: 1-%d)", MAX_NUM_PROCS)
|
|
}
|
|
m.setup()
|
|
command := exec.Command("ps", "-Ao", "comm", "--sort=-pcpu")
|
|
command.Wait()
|
|
_, err = command.Output()
|
|
if err != nil {
|
|
return errors.New("failed to execute command")
|
|
}
|
|
m.init = true
|
|
return nil
|
|
}
|
|
|
|
func (m *TopProcsCollector) Read(interval time.Duration, output chan lp.CCMessage) {
|
|
if !m.init {
|
|
return
|
|
}
|
|
command := exec.Command("ps", "-Ao", "comm", "--sort=-pcpu")
|
|
command.Wait()
|
|
stdout, err := command.Output()
|
|
if err != nil {
|
|
log.Print(m.name, err)
|
|
return
|
|
}
|
|
|
|
lines := strings.Split(string(stdout), "\n")
|
|
for i := 1; i < m.config.Num_procs+1; i++ {
|
|
name := fmt.Sprintf("topproc%d", i)
|
|
y, err := lp.NewMessage(name, m.tags, m.meta, map[string]interface{}{"value": string(lines[i])}, time.Now())
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
}
|
|
|
|
func (m *TopProcsCollector) Close() {
|
|
m.init = false
|
|
}
|