mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-11-10 12:37:25 +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>
129 lines
2.8 KiB
Go
129 lines
2.8 KiB
Go
package collectors
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"io/ioutil"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
|
|
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
|
|
)
|
|
|
|
//
|
|
// 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.CCMetric) {
|
|
if !m.init {
|
|
return
|
|
}
|
|
buffer, err := ioutil.ReadFile(LOADAVGFILE)
|
|
if err != nil {
|
|
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.New(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.New(name, m.tags, m.meta, map[string]interface{}{"value": x}, now)
|
|
if err == nil {
|
|
output <- y
|
|
}
|
|
|
|
}
|
|
}
|
|
|
|
func (m *LoadavgCollector) Close() {
|
|
m.init = false
|
|
}
|