mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2025-11-04 02:35:07 +01:00
Modularize the whole thing (#16)
* Use channels, add a metric router, split up configuration and use extended version of Influx line protocol internally * Use central timer for collectors and router. Add expressions to router * Add expression to router config * Update entry points * Start with README * Update README for CCMetric * Formatting * Update README.md * Add README for MultiChanTicker * Add README for MultiChanTicker * Update README.md * Add README to metric router * Update main README * Remove SinkEntity type * Update README for sinks * Update go files * Update README for receivers * Update collectors README * Update collectors README * Use seperate page per collector * Fix for tempstat page * Add docs for customcmd collector * Add docs for ipmistat collector * Add docs for topprocs collector * Update customCmdMetric.md * Use seconds when calculating LIKWID metrics * Add IB metrics ib_recv_pkts and ib_xmit_pkts * Drop domain part of host name * Updated to latest stable version of likwid * Define source code dependencies in Makefile * Add GPFS / IBM Spectrum Scale collector * Add vet and staticcheck make targets * Add vet and staticcheck make targets * Avoid go vet warning: struct field tag `json:"..., omitempty"` not compatible with reflect.StructTag.Get: suspicious space in struct tag value struct field tag `json:"...", omitempty` not compatible with reflect.StructTag.Get: key:"value" pairs not separated by spaces * Add sample collector to README.md * Add CPU frequency collector * Avoid staticcheck warning: redundant return statement * Avoid staticcheck warning: unnecessary assignment to the blank identifier * Simplified code * Add CPUFreqCollectorCpuinfo a metric collector to measure the current frequency of the CPUs as obtained from /proc/cpuinfo Only measure on the first hyperthread * Add collector for NFS clients * Move publication of metrics into Flush() for NatsSink * Update GitHub actions * Refactoring * Avoid vet warning: Println arg list ends with redundant newline * Avoid vet warning struct field commands has json tag but is not exported * Avoid vet warning: return copies lock value. * Corrected typo * Refactoring * Add go sources in internal/... * Bad separator in Makefile * Fix Infiniband collector Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com>
This commit is contained in:
Thomas Gruber
GitHub
143
collectors/collectorManager.go
Normal file
143
collectors/collectorManager.go
Normal file
@@ -0,0 +1,143 @@
|
||||
package collectors
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"log"
|
||||
"os"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
|
||||
mct "github.com/ClusterCockpit/cc-metric-collector/internal/multiChanTicker"
|
||||
)
|
||||
|
||||
var AvailableCollectors = map[string]MetricCollector{
|
||||
|
||||
"likwid": &LikwidCollector{},
|
||||
"loadavg": &LoadavgCollector{},
|
||||
"memstat": &MemstatCollector{},
|
||||
"netstat": &NetstatCollector{},
|
||||
"ibstat": &InfinibandCollector{},
|
||||
"lustrestat": &LustreCollector{},
|
||||
"cpustat": &CpustatCollector{},
|
||||
"topprocs": &TopProcsCollector{},
|
||||
"nvidia": &NvidiaCollector{},
|
||||
"customcmd": &CustomCmdCollector{},
|
||||
"diskstat": &DiskstatCollector{},
|
||||
"tempstat": &TempCollector{},
|
||||
"ipmistat": &IpmiCollector{},
|
||||
"gpfs": new(GpfsCollector),
|
||||
"cpufreq": new(CPUFreqCollector),
|
||||
"cpufreq_cpuinfo": new(CPUFreqCpuInfoCollector),
|
||||
"nfsstat": new(NfsCollector),
|
||||
}
|
||||
|
||||
type collectorManager struct {
|
||||
collectors []MetricCollector
|
||||
output chan lp.CCMetric
|
||||
done chan bool
|
||||
ticker mct.MultiChanTicker
|
||||
duration time.Duration
|
||||
wg *sync.WaitGroup
|
||||
config map[string]json.RawMessage
|
||||
}
|
||||
|
||||
type CollectorManager interface {
|
||||
Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error
|
||||
AddOutput(output chan lp.CCMetric)
|
||||
Start()
|
||||
Close()
|
||||
}
|
||||
|
||||
func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) error {
|
||||
cm.collectors = make([]MetricCollector, 0)
|
||||
cm.output = nil
|
||||
cm.done = make(chan bool)
|
||||
cm.wg = wg
|
||||
cm.ticker = ticker
|
||||
cm.duration = duration
|
||||
configFile, err := os.Open(collectConfigFile)
|
||||
if err != nil {
|
||||
log.Print(err.Error())
|
||||
return err
|
||||
}
|
||||
defer configFile.Close()
|
||||
jsonParser := json.NewDecoder(configFile)
|
||||
err = jsonParser.Decode(&cm.config)
|
||||
if err != nil {
|
||||
log.Print(err.Error())
|
||||
return err
|
||||
}
|
||||
for k, cfg := range cm.config {
|
||||
log.Print(k, " ", cfg)
|
||||
if _, found := AvailableCollectors[k]; !found {
|
||||
log.Print("[CollectorManager] SKIP unknown collector ", k)
|
||||
continue
|
||||
}
|
||||
c := AvailableCollectors[k]
|
||||
|
||||
err = c.Init(cfg)
|
||||
if err != nil {
|
||||
log.Print("[CollectorManager] Collector ", k, "initialization failed: ", err.Error())
|
||||
continue
|
||||
}
|
||||
cm.collectors = append(cm.collectors, c)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (cm *collectorManager) Start() {
|
||||
cm.wg.Add(1)
|
||||
tick := make(chan time.Time)
|
||||
cm.ticker.AddChannel(tick)
|
||||
go func() {
|
||||
for {
|
||||
CollectorManagerLoop:
|
||||
select {
|
||||
case <-cm.done:
|
||||
for _, c := range cm.collectors {
|
||||
c.Close()
|
||||
}
|
||||
cm.wg.Done()
|
||||
log.Print("[CollectorManager] DONE\n")
|
||||
break CollectorManagerLoop
|
||||
case t := <-tick:
|
||||
for _, c := range cm.collectors {
|
||||
CollectorManagerInputLoop:
|
||||
select {
|
||||
case <-cm.done:
|
||||
for _, c := range cm.collectors {
|
||||
c.Close()
|
||||
}
|
||||
cm.wg.Done()
|
||||
log.Print("[CollectorManager] DONE\n")
|
||||
break CollectorManagerInputLoop
|
||||
default:
|
||||
log.Print("[CollectorManager] ", c.Name(), " ", t)
|
||||
c.Read(cm.duration, cm.output)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
log.Print("[CollectorManager] EXIT\n")
|
||||
}()
|
||||
log.Print("[CollectorManager] STARTED\n")
|
||||
}
|
||||
|
||||
func (cm *collectorManager) AddOutput(output chan lp.CCMetric) {
|
||||
cm.output = output
|
||||
}
|
||||
|
||||
func (cm *collectorManager) Close() {
|
||||
cm.done <- true
|
||||
log.Print("[CollectorManager] CLOSE")
|
||||
}
|
||||
|
||||
func New(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfigFile string) (CollectorManager, error) {
|
||||
cm := &collectorManager{}
|
||||
err := cm.Init(ticker, duration, wg, collectConfigFile)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return cm, err
|
||||
}
|
||||
Reference in New Issue
Block a user