mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-11-10 04:27:25 +01:00
8d85bd53f1
* Cleanup: Remove unused code * Use Golang duration parser for 'interval' and 'duration' in main config * Update handling of LIKWID headers. Download only if not already present in the system. Fixes #73 * Units with cc-units (#64) * Add option to normalize units with cc-unit * Add unit conversion to router * Add option to change unit prefix in the router * Add to MetricRouter README * Add order of operations in router to README * Use second add_tags/del_tags only if metric gets renamed * Skip disks in DiskstatCollector that have size=0 * Check readability of sensor files in TempCollector * Fix for --once option * Rename `cpu` type to `hwthread` (#69) * Rename 'cpu' type to 'hwthread' to avoid naming clashes with MetricStore and CC-Webfrontend * Collectors in parallel (#74) * Provide info to CollectorManager whether the collector can be executed in parallel with others * Split serial and parallel collectors. Read in parallel first * Update NvidiaCollector with new metrics, MIG and NvLink support (#75) * CC topology module update (#76) * Rename CPU to hardware thread, write some comments * Do renaming in other parts * Remove CpuList and SocketList function from metricCollector. Available in ccTopology * Option to use MIG UUID as subtype-id in NvidiaCollector * Option to use MIG slice name as subtype-id in NvidiaCollector * MetricRouter: Fix JSON in README * Fix for Github Action to really use the selected version * Remove Ganglia installation in runonce Action and add Go 1.18 * Fix daemon options in init script * Add separate go.mod files to use it with deprecated 1.16 * Minor updates for Makefiles * fix string comparison * AMD ROCm SMI collector (#77) * Add collector for AMD ROCm SMI metrics * Fix import path * Fix imports * Remove Board Number * store GPU index explicitly * Remove board number from description * Use http instead of ftp to download likwid * Fix serial number in rocmCollector * Improved http sink (#78) * automatic flush in NatsSink * tweak default options of HttpSink * shorter cirt. section and retries for HttpSink * fix error handling * Remove file added by mistake. * Use http instead of ftp to download likwid * Fix serial number in rocmCollector Co-authored-by: Thomas Roehl <thomas.roehl@fau.de> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Lou <lou.knauer@gmx.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-metric-collector/internal/ccMetric"
|
|
)
|
|
|
|
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.CCMetric) {
|
|
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.New(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
|
|
}
|