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>
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/pkg/ccLogger"
|
|
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
|
)
|
|
|
|
// "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.CCMessage) {
|
|
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.NewMessage("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.NewMessage("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.NewMessage("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
|
|
}
|