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>
123 lines
2.7 KiB
Go
123 lines
2.7 KiB
Go
package collectors
|
|
|
|
import (
|
|
"bufio"
|
|
"encoding/json"
|
|
"os"
|
|
"strings"
|
|
"syscall"
|
|
"time"
|
|
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/internal/ccLogger"
|
|
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
|
|
)
|
|
|
|
// "log"
|
|
|
|
const MOUNTFILE = `/proc/self/mounts`
|
|
|
|
type DiskstatCollectorConfig struct {
|
|
ExcludeMetrics []string `json:"exclude_metrics,omitempty"`
|
|
}
|
|
|
|
type DiskstatCollector struct {
|
|
metricCollector
|
|
//matches map[string]int
|
|
config IOstatCollectorConfig
|
|
//devices map[string]IOstatCollectorEntry
|
|
}
|
|
|
|
func (m *DiskstatCollector) Init(config json.RawMessage) error {
|
|
m.name = "DiskstatCollector"
|
|
m.parallel = true
|
|
m.meta = map[string]string{"source": m.name, "group": "Disk"}
|
|
m.setup()
|
|
if len(config) > 0 {
|
|
err := json.Unmarshal(config, &m.config)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
}
|
|
file, err := os.Open(string(MOUNTFILE))
|
|
if err != nil {
|
|
cclog.ComponentError(m.name, err.Error())
|
|
return err
|
|
}
|
|
defer file.Close()
|
|
m.init = true
|
|
return nil
|
|
}
|
|
|
|
func (m *DiskstatCollector) Read(interval time.Duration, output chan lp.CCMetric) {
|
|
if !m.init {
|
|
return
|
|
}
|
|
|
|
file, err := os.Open(string(MOUNTFILE))
|
|
if err != nil {
|
|
cclog.ComponentError(m.name, err.Error())
|
|
return
|
|
}
|
|
defer file.Close()
|
|
|
|
part_max_used := uint64(0)
|
|
scanner := bufio.NewScanner(file)
|
|
for scanner.Scan() {
|
|
line := scanner.Text()
|
|
if len(line) == 0 {
|
|
continue
|
|
}
|
|
if !strings.HasPrefix(line, "/dev") {
|
|
continue
|
|
}
|
|
linefields := strings.Fields(line)
|
|
if strings.Contains(linefields[0], "loop") {
|
|
continue
|
|
}
|
|
if strings.Contains(linefields[1], "boot") {
|
|
continue
|
|
}
|
|
path := strings.Replace(linefields[1], `\040`, " ", -1)
|
|
stat := syscall.Statfs_t{
|
|
Blocks: 0,
|
|
Bsize: 0,
|
|
Bfree: 0,
|
|
}
|
|
err := syscall.Statfs(path, &stat)
|
|
if err != nil {
|
|
continue
|
|
}
|
|
if stat.Blocks == 0 || stat.Bsize == 0 {
|
|
continue
|
|
}
|
|
tags := map[string]string{"type": "node", "device": linefields[0]}
|
|
total := (stat.Blocks * uint64(stat.Bsize)) / uint64(1000000000)
|
|
y, err := lp.New("disk_total", tags, m.meta, map[string]interface{}{"value": total}, time.Now())
|
|
if err == nil {
|
|
y.AddMeta("unit", "GBytes")
|
|
output <- y
|
|
}
|
|
free := (stat.Bfree * uint64(stat.Bsize)) / uint64(1000000000)
|
|
y, err = lp.New("disk_free", tags, m.meta, map[string]interface{}{"value": free}, time.Now())
|
|
if err == nil {
|
|
y.AddMeta("unit", "GBytes")
|
|
output <- y
|
|
}
|
|
if total > 0 {
|
|
perc := (100 * (total - free)) / total
|
|
if perc > part_max_used {
|
|
part_max_used = perc
|
|
}
|
|
}
|
|
}
|
|
y, err := lp.New("part_max_used", map[string]string{"type": "node"}, m.meta, map[string]interface{}{"value": int(part_max_used)}, time.Now())
|
|
if err == nil {
|
|
y.AddMeta("unit", "percent")
|
|
output <- y
|
|
}
|
|
}
|
|
|
|
func (m *DiskstatCollector) Close() {
|
|
m.init = false
|
|
}
|