Compare commits

...

10 Commits

Author SHA1 Message Date
Michael Panzlaff a0aedff202 Merge pull request #235 from ClusterCockpit/marker-commits
Add marker metrics
2026-07-21 12:51:37 +02:00
Michael Panzlaff 6944454592 Update configuration documentation for new marker metrics 2026-07-21 12:47:16 +02:00
Michael Panzlaff 9e773e2e85 Fix marker metric creation 2026-07-20 16:16:10 +02:00
Michael Panzlaff c13bb55735 Actually send the created marker metrics 2026-07-20 15:39:40 +02:00
Michael Panzlaff 6124971b2e collectorManager: Make markers opt-in 2026-07-15 18:04:56 +02:00
Michael Panzlaff cdac3c9163 Add ccmc-{begin,end} markers
These markers are sent out at the beginning and end of a collection run.
This can be used to reconstruct, which metrics belong together and were
obtained during the same tick.
2026-07-15 15:45:15 +02:00
dependabot[bot] 70364d084b Bump golang.org/x/sys from 0.45.0 to 0.47.0
Bumps [golang.org/x/sys](https://github.com/golang/sys) from 0.45.0 to 0.47.0.
- [Commits](https://github.com/golang/sys/compare/v0.45.0...v0.47.0)

---
updated-dependencies:
- dependency-name: golang.org/x/sys
  dependency-version: 0.47.0
  dependency-type: direct:production
  update-type: version-update:semver-minor
...

Signed-off-by: dependabot[bot] <support@github.com>
2026-07-13 12:06:53 +02:00
dependabot[bot] ec0868eba9 Bump github.com/NVIDIA/go-nvml from 0.13.2-0 to 0.13.3-1
Bumps [github.com/NVIDIA/go-nvml](https://github.com/NVIDIA/go-nvml) from 0.13.2-0 to 0.13.3-1.
- [Release notes](https://github.com/NVIDIA/go-nvml/releases)
- [Commits](https://github.com/NVIDIA/go-nvml/compare/v0.13.2-0...v0.13.3-1)

---
updated-dependencies:
- dependency-name: github.com/NVIDIA/go-nvml
  dependency-version: 0.13.3-1
  dependency-type: direct:production
  update-type: version-update:semver-patch
...

Signed-off-by: dependabot[bot] <support@github.com>
2026-07-13 12:06:37 +02:00
Michael Panzlaff b8e76e3bf0 megwareEureka: Fix collector name 2026-07-07 19:03:57 +02:00
Michael Panzlaff f028c83a75 megwareEureka: Remove debug output
This should never have been in the release...
2026-07-07 18:47:02 +02:00
7 changed files with 51 additions and 31 deletions
+1
View File
@@ -33,6 +33,7 @@ There is a main configuration file with basic settings that point to the other c
"receivers-file" : "receivers.json", "receivers-file" : "receivers.json",
"router-file" : "router.json", "router-file" : "router.json",
"main": { "main": {
"enable-markers": false,
"interval": "10s", "interval": "10s",
"duration": "1s" "duration": "1s"
} }
+10 -7
View File
@@ -29,15 +29,17 @@ import (
) )
type CentralConfigFile struct { type CentralConfigFile struct {
Interval string `json:"interval"` Interval string `json:"interval"`
Duration string `json:"duration"` Duration string `json:"duration"`
EnableMarkers bool `json:"enable-markers"`
} }
type RuntimeConfig struct { type RuntimeConfig struct {
Interval time.Duration Interval time.Duration
Duration time.Duration Duration time.Duration
CliArgs map[string]string EnableMarkers bool
ConfigFile CentralConfigFile CliArgs map[string]string
ConfigFile CentralConfigFile
MetricRouter mr.MetricRouter MetricRouter mr.MetricRouter
CollectManager collectors.CollectorManager CollectManager collectors.CollectorManager
@@ -157,6 +159,7 @@ func mainFunc() int {
cclog.Error("The interval should be greater than duration") cclog.Error("The interval should be greater than duration")
return 1 return 1
} }
rcfg.EnableMarkers = rcfg.ConfigFile.EnableMarkers
routerConf := ccconf.GetPackageConfig("router") routerConf := ccconf.GetPackageConfig("router")
if len(routerConf) == 0 { if len(routerConf) == 0 {
@@ -199,7 +202,7 @@ func mainFunc() int {
rcfg.MetricRouter.AddOutput(RouterToSinksChannel) rcfg.MetricRouter.AddOutput(RouterToSinksChannel)
// Create new collector manager // Create new collector manager
rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, &rcfg.Sync, collectorConf) rcfg.CollectManager, err = collectors.New(rcfg.MultiChanTicker, rcfg.Duration, rcfg.EnableMarkers, &rcfg.Sync, collectorConf)
if err != nil { if err != nil {
cclog.Error(err.Error()) cclog.Error(err.Error())
return 1 return 1
+32 -14
View File
@@ -56,21 +56,22 @@ var AvailableCollectors = map[string]MetricCollector{
// Metric collector manager data structure // Metric collector manager data structure
type collectorManager struct { type collectorManager struct {
collectors []MetricCollector // List of metric collectors to read in parallel collectors []MetricCollector // List of metric collectors to read in parallel
serial []MetricCollector // List of metric collectors to read serially serial []MetricCollector // List of metric collectors to read serially
output chan lp.CCMessage // Output channels output chan lp.CCMessage // Output channels
done chan bool // channel to finish / stop metric collector manager done chan bool // channel to finish / stop metric collector manager
ticker mct.MultiChanTicker // periodically ticking once each interval ticker mct.MultiChanTicker // periodically ticking once each interval
duration time.Duration // duration (for metrics that measure over a given duration) duration time.Duration // duration (for metrics that measure over a given duration)
wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector wg *sync.WaitGroup // wait group for all goroutines in cc-metric-collector
config map[string]json.RawMessage // json encoded config for collector manager config map[string]json.RawMessage // json encoded config for collector manager
collector_wg sync.WaitGroup // internally used wait group for the parallel reading of collector collector_wg sync.WaitGroup // internally used wait group for the parallel reading of collector
parallel_run bool // Flag whether the collectors are currently read in parallel parallel_run bool // Flag whether the collectors are currently read in parallel
enableMarkers bool // Send ccmc-{begin,end} metrics
} }
// Metric collector manager access functions // Metric collector manager access functions
type CollectorManager interface { type CollectorManager interface {
Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) error Init(ticker mct.MultiChanTicker, duration time.Duration, enableMarkers bool, wg *sync.WaitGroup, collectConfig json.RawMessage) error
AddOutput(output chan lp.CCMessage) AddOutput(output chan lp.CCMessage)
Start() Start()
Close() Close()
@@ -83,7 +84,7 @@ type CollectorManager interface {
// * ticker (from variable ticker) // * ticker (from variable ticker)
// * configuration (read from config file in variable collectConfigFile) // * configuration (read from config file in variable collectConfigFile)
// Initialization is done for all configured collectors // Initialization is done for all configured collectors
func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) error { func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Duration, enableMarkers bool, wg *sync.WaitGroup, collectConfig json.RawMessage) error {
cm.collectors = make([]MetricCollector, 0) cm.collectors = make([]MetricCollector, 0)
cm.serial = make([]MetricCollector, 0) cm.serial = make([]MetricCollector, 0)
cm.output = nil cm.output = nil
@@ -91,6 +92,7 @@ func (cm *collectorManager) Init(ticker mct.MultiChanTicker, duration time.Durat
cm.wg = wg cm.wg = wg
cm.ticker = ticker cm.ticker = ticker
cm.duration = duration cm.duration = duration
cm.enableMarkers = enableMarkers
d := json.NewDecoder(bytes.NewReader(collectConfig)) d := json.NewDecoder(bytes.NewReader(collectConfig))
d.DisallowUnknownFields() d.DisallowUnknownFields()
@@ -148,6 +150,14 @@ func (cm *collectorManager) Start() {
done() done()
return return
case t := <-tick: case t := <-tick:
if cm.enableMarkers {
m, err := lp.NewMetric("ccmc-begin", map[string]string{"type": "node"}, nil, 0, time.Now())
if err != nil {
cclog.ComponentErrorf("CollectorManager", "Unable to create marker metric: %v", err)
} else {
cm.output <- m
}
}
cm.parallel_run = true cm.parallel_run = true
for _, c := range cm.collectors { for _, c := range cm.collectors {
// Wait for done signal or execute the collector // Wait for done signal or execute the collector
@@ -179,6 +189,14 @@ func (cm *collectorManager) Start() {
c.Read(cm.duration, cm.output) c.Read(cm.duration, cm.output)
} }
} }
if cm.enableMarkers {
m, err := lp.NewMetric("ccmc-end", map[string]string{"type": "node"}, nil, 0, time.Now())
if err != nil {
cclog.ComponentErrorf("CollectorManager", "Unable to create marker metric: %v", err)
} else {
cm.output <- m
}
}
} }
} }
}) })
@@ -201,9 +219,9 @@ func (cm *collectorManager) Close() {
} }
// New creates a new initialized metric collector manager // New creates a new initialized metric collector manager
func New(ticker mct.MultiChanTicker, duration time.Duration, wg *sync.WaitGroup, collectConfig json.RawMessage) (CollectorManager, error) { func New(ticker mct.MultiChanTicker, duration time.Duration, enableMarkers bool, wg *sync.WaitGroup, collectConfig json.RawMessage) (CollectorManager, error) {
cm := new(collectorManager) cm := new(collectorManager)
err := cm.Init(ticker, duration, wg, collectConfig) err := cm.Init(ticker, duration, enableMarkers, wg, collectConfig)
if err != nil { if err != nil {
return nil, err return nil, err
} }
+1 -4
View File
@@ -65,7 +65,7 @@ func (m *MegwareEurekaCollector) Init(config json.RawMessage) error {
return nil return nil
} }
m.name = "MegwareEureka" m.name = "MegwareEurekaCollector"
if err := m.setup(); err != nil { if err := m.setup(); err != nil {
return fmt.Errorf("%s Init(): setup() call failed: %w", m.name, err) return fmt.Errorf("%s Init(): setup() call failed: %w", m.name, err)
} }
@@ -127,9 +127,6 @@ func (m *MegwareEurekaCollector) readMpsData() (*mpsData, error) {
return nil, fmt.Errorf("unable to decode u20 JSON output: %w (stdout=%s)", err, stdout.String()) return nil, fmt.Errorf("unable to decode u20 JSON output: %w (stdout=%s)", err, stdout.String())
} }
fmt.Printf("string: %+v\n", stdout.String())
fmt.Printf("obj: %+v\n", u20output)
u20output.GetMpsPollValues.Timestamp = time.Now() u20output.GetMpsPollValues.Timestamp = time.Now()
return &u20output.GetMpsPollValues, nil return &u20output.GetMpsPollValues, nil
+1
View File
@@ -4,6 +4,7 @@
"receivers-file" : "./receivers.json", "receivers-file" : "./receivers.json",
"router-file" : "./router.json", "router-file" : "./router.json",
"main" : { "main" : {
"enable-markers": false,
"interval": "10s", "interval": "10s",
"duration": "1s" "duration": "1s"
} }
+2 -2
View File
@@ -5,12 +5,12 @@ go 1.25.0
require ( require (
github.com/ClusterCockpit/cc-lib/v2 v2.12.0 github.com/ClusterCockpit/cc-lib/v2 v2.12.0
github.com/ClusterCockpit/go-rocm-smi v0.4.0 github.com/ClusterCockpit/go-rocm-smi v0.4.0
github.com/NVIDIA/go-nvml v0.13.2-0 github.com/NVIDIA/go-nvml v0.13.3-1
github.com/PaesslerAG/gval v1.2.4 github.com/PaesslerAG/gval v1.2.4
github.com/fsnotify/fsnotify v1.10.1 github.com/fsnotify/fsnotify v1.10.1
github.com/tklauser/go-sysconf v0.4.0 github.com/tklauser/go-sysconf v0.4.0
golang.design/x/runtime v0.3.0 golang.design/x/runtime v0.3.0
golang.org/x/sys v0.45.0 golang.org/x/sys v0.47.0
) )
require ( require (
+4 -4
View File
@@ -13,8 +13,8 @@ github.com/Microsoft/go-winio v0.6.1/go.mod h1:LRdKpFKfdobln8UmuiYcKPot9D2v6svN5
github.com/Microsoft/hcsshim v0.11.4 h1:68vKo2VN8DE9AdN4tnkWnmdhqdbpUFM8OF3Airm7fz8= github.com/Microsoft/hcsshim v0.11.4 h1:68vKo2VN8DE9AdN4tnkWnmdhqdbpUFM8OF3Airm7fz8=
github.com/Microsoft/hcsshim v0.11.4/go.mod h1:smjE4dvqPX9Zldna+t5FG3rnoHhaB7QYxPRqGcpAD9w= github.com/Microsoft/hcsshim v0.11.4/go.mod h1:smjE4dvqPX9Zldna+t5FG3rnoHhaB7QYxPRqGcpAD9w=
github.com/NVIDIA/go-nvml v0.13.0-1/go.mod h1:+KNA7c7gIBH7SKSJ1ntlwkfN80zdx8ovl4hrK3LmPt4= github.com/NVIDIA/go-nvml v0.13.0-1/go.mod h1:+KNA7c7gIBH7SKSJ1ntlwkfN80zdx8ovl4hrK3LmPt4=
github.com/NVIDIA/go-nvml v0.13.2-0 h1:7M4cFG62wSUHw8i0XSiNU7ejKODytTS6ZrW/vgB2NSI= github.com/NVIDIA/go-nvml v0.13.3-1 h1:P76U2h88OZSiMtdhRsJjSF5DXyXUqHIXKeDicVAaae0=
github.com/NVIDIA/go-nvml v0.13.2-0/go.mod h1:ahi2psRYoa+wYUBIrZPRO+wJs9lcvMhxSSkjjvsJJNQ= github.com/NVIDIA/go-nvml v0.13.3-1/go.mod h1:ahi2psRYoa+wYUBIrZPRO+wJs9lcvMhxSSkjjvsJJNQ=
github.com/PaesslerAG/gval v1.2.4 h1:rhX7MpjJlcxYwL2eTTYIOBUyEKZ+A96T9vQySWkVUiU= github.com/PaesslerAG/gval v1.2.4 h1:rhX7MpjJlcxYwL2eTTYIOBUyEKZ+A96T9vQySWkVUiU=
github.com/PaesslerAG/gval v1.2.4/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac= github.com/PaesslerAG/gval v1.2.4/go.mod h1:XRFLwvmkTEdYziLdaCeCa5ImcGVrfQbeNUbVR+C6xac=
github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI= github.com/PaesslerAG/jsonpath v0.1.0 h1:gADYeifvlqK3R3i2cR5B4DGgxLXIPb3TRTH1mGi0jPI=
@@ -184,8 +184,8 @@ golang.org/x/mod v0.13.0 h1:I/DsJXRlw/8l/0c24sM9yb0T4z9liZTduXvdAWYiysY=
golang.org/x/mod v0.13.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c= golang.org/x/mod v0.13.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
golang.org/x/net v0.53.0 h1:d+qAbo5L0orcWAr0a9JweQpjXF19LMXJE8Ey7hwOdUA= golang.org/x/net v0.53.0 h1:d+qAbo5L0orcWAr0a9JweQpjXF19LMXJE8Ey7hwOdUA=
golang.org/x/net v0.53.0/go.mod h1:JvMuJH7rrdiCfbeHoo3fCQU24Lf5JJwT9W3sJFulfgs= golang.org/x/net v0.53.0/go.mod h1:JvMuJH7rrdiCfbeHoo3fCQU24Lf5JJwT9W3sJFulfgs=
golang.org/x/sys v0.45.0 h1:dO4czNzziLiiXplLQgBCEpCvXQ3dnkn0SdaZSYdQ+FY= golang.org/x/sys v0.47.0 h1:o7XGOvZQCADBQQ4Y7VNq2dRWQR7JmOUW8Kxx4ZsNgWs=
golang.org/x/sys v0.45.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw= golang.org/x/sys v0.47.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U= golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno= golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
golang.org/x/tools v0.14.0 h1:jvNa2pY0M4r62jkRQ6RwEZZyPcymeL9XZMLBbV7U2nc= golang.org/x/tools v0.14.0 h1:jvNa2pY0M4r62jkRQ6RwEZZyPcymeL9XZMLBbV7U2nc=