ClusterCockpit/cc-metric-collector
1
0
Fork 0
mirror of https://github.com/ClusterCockpit/cc-metric-collector.git synced 2025-07-19 03:11:41 +02:00
Code Issues Packages Projects Releases Wiki Activity

Modularize the whole thing (#16)

Browse Source 
* 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
2022-01-25 15:37:43 +01:00
committed by GitHub
parent 222862af32
commit 200af84c54
60 changed files with 2596 additions and 1105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

62
collectors/likwidMetric.go
View File

@@ -20,16 +20,28 @@ import (
"strings"
"time"
"unsafe"
lp "github.com/influxdata/line-protocol"
lp "github.com/ClusterCockpit/cc-metric-collector/internal/ccMetric"
"gopkg.in/Knetic/govaluate.v2"
)
type MetricScope int
const (
METRIC_SCOPE_HWTHREAD = iota
METRIC_SCOPE_SOCKET
METRIC_SCOPE_NUMA
METRIC_SCOPE_NODE
)
func (ms MetricScope) String() string {
return []string{"Head", "Shoulder", "Knee", "Toe"}[ms]
}
type LikwidCollectorMetricConfig struct {
Name string `json:"name"`
Calc string `json:"calc"`
Socket_scope bool `json:"socket_scope"`
Publish bool `json:"publish"`
Name string `json:"name"`
Calc string `json:"calc"`
Scope MetricScope `json:"socket_scope"`
Publish bool `json:"publish"`
}
type LikwidCollectorEventsetConfig struct {
@@ -45,7 +57,7 @@ type LikwidCollectorConfig struct {
}
type LikwidCollector struct {
MetricCollector
metricCollector
cpulist []C.int
sock2tid map[int]int
metrics map[C.int]map[string]int
@@ -105,7 +117,7 @@ func getSocketCpus() map[C.int]int {
return outmap
}
func (m *LikwidCollector) Init(config []byte) error {
func (m *LikwidCollector) Init(config json.RawMessage) error {
var ret C.int
m.name = "LikwidCollector"
if len(config) > 0 {
@@ -115,11 +127,13 @@ func (m *LikwidCollector) Init(config []byte) error {
}
}
m.setup()
m.meta = map[string]string{"source": m.name, "group": "PerfCounter"}
cpulist := CpuList()
m.cpulist = make([]C.int, len(cpulist))
slist := getSocketCpus()
m.sock2tid = make(map[int]int)
// m.numa2tid = make(map[int]int)
for i, c := range cpulist {
m.cpulist[i] = C.int(c)
if sid, found := slist[m.cpulist[i]]; found {
@@ -169,7 +183,7 @@ func (m *LikwidCollector) Init(config []byte) error {
return nil
}
func (m *LikwidCollector) Read(interval time.Duration, out *[]lp.MutableMetric) {
func (m *LikwidCollector) Read(interval time.Duration, output chan lp.CCMetric) {
if !m.init {
return
}
@@ -246,24 +260,28 @@ func (m *LikwidCollector) Read(interval time.Duration, out *[]lp.MutableMetric)
for _, metric := range evset.Metrics {
_, skip := stringArrayContains(m.config.ExcludeMetrics, metric.Name)
if metric.Publish && !skip {
if metric.Socket_scope {
if metric.Scope.String() == "socket" {
for sid, tid := range m.sock2tid {
y, err := lp.New(metric.Name,
map[string]string{"type": "socket", "type-id": fmt.Sprintf("%d", int(sid))},
map[string]string{"type": "socket",
"type-id": fmt.Sprintf("%d", int(sid))},
m.meta,
map[string]interface{}{"value": m.mresults[i][tid][metric.Name]},
time.Now())
if err == nil {
*out = append(*out, y)
output <- y
}
}
} else {
} else if metric.Scope.String() == "hwthread" {
for tid, cpu := range m.cpulist {
y, err := lp.New(metric.Name,
map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", int(cpu))},
map[string]string{"type": "cpu",
"type-id": fmt.Sprintf("%d", int(cpu))},
m.meta,
map[string]interface{}{"value": m.mresults[i][tid][metric.Name]},
time.Now())
if err == nil {
*out = append(*out, y)
output <- y
}
}
}
@@ -273,24 +291,28 @@ func (m *LikwidCollector) Read(interval time.Duration, out *[]lp.MutableMetric)
for _, metric := range m.config.Metrics {
_, skip := stringArrayContains(m.config.ExcludeMetrics, metric.Name)
if metric.Publish && !skip {
if metric.Socket_scope {
if metric.Scope.String() == "socket" {
for sid, tid := range m.sock2tid {
y, err := lp.New(metric.Name,
map[string]string{"type": "socket", "type-id": fmt.Sprintf("%d", int(sid))},
map[string]string{"type": "socket",
"type-id": fmt.Sprintf("%d", int(sid))},
m.meta,
map[string]interface{}{"value": m.gmresults[tid][metric.Name]},
time.Now())
if err == nil {
*out = append(*out, y)
output <- y
}
}
} else {
for tid, cpu := range m.cpulist {
y, err := lp.New(metric.Name,
map[string]string{"type": "cpu", "type-id": fmt.Sprintf("%d", int(cpu))},
map[string]string{"type": "cpu",
"type-id": fmt.Sprintf("%d", int(cpu))},
m.meta,
map[string]interface{}{"value": m.gmresults[tid][metric.Name]},
time.Now())
if err == nil {
*out = append(*out, y)
output <- y
}
}
}