cc-metric-collector/collectors/customCmdMetric.go

129 lines
2.7 KiB
Go
Raw Normal View History

package collectors
import (
2021-11-25 15:11:39 +01:00
"encoding/json"
"errors"
"log"
2022-10-09 17:03:38 +02:00
"os"
"os/exec"
"strings"
2021-11-25 15:11:39 +01:00
"time"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
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>
2022-01-25 15:37:43 +01:00
influx "github.com/influxdata/line-protocol"
)
const CUSTOMCMDPATH = `/home/unrz139/Work/cc-metric-collector/collectors/custom`
type CustomCmdCollectorConfig struct {
Commands []string `json:"commands"`
Files []string `json:"files"`
2021-11-25 15:11:39 +01:00
ExcludeMetrics []string `json:"exclude_metrics"`
}
type CustomCmdCollector struct {
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>
2022-01-25 15:37:43 +01:00
metricCollector
handler *influx.MetricHandler
parser *influx.Parser
2021-11-25 15:11:39 +01:00
config CustomCmdCollectorConfig
commands []string
2021-11-25 15:11:39 +01:00
files []string
}
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>
2022-01-25 15:37:43 +01:00
func (m *CustomCmdCollector) Init(config json.RawMessage) error {
2021-11-25 15:11:39 +01:00
var err error
m.name = "CustomCmdCollector"
m.parallel = true
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>
2022-01-25 15:37:43 +01:00
m.meta = map[string]string{"source": m.name, "group": "Custom"}
if len(config) > 0 {
2021-11-25 15:11:39 +01:00
err = json.Unmarshal(config, &m.config)
if err != nil {
log.Print(err.Error())
return err
}
}
m.setup()
for _, c := range m.config.Commands {
2021-11-25 15:11:39 +01:00
cmdfields := strings.Fields(c)
command := exec.Command(cmdfields[0], strings.Join(cmdfields[1:], " "))
command.Wait()
_, err = command.Output()
Use customcmd commands if they did not error. (#101) * Merge develop and main (#99) * InfiniBandCollector: Scale raw readings from octets to bytes * Fix clock frequency coming from LikwidCollector and update docs * Build DEB package for Ubuntu 20.04 for releases * Fix memstat collector with numa_stats option * Remove useless prints from MemstatCollector * Replace ioutils with os and io (#87) * Use lower case for error strings in RocmSmiCollector * move maybe-usable-by-other-cc-components to pkg. Fix all files to use the new paths (#88) * Add collector for monitoring the execution of cc-metric-collector itself (#81) * Add collector to monitor execution of cc-metric-collector itself * Register SelfCollector * Fix import paths for moved packages * Check if at least one CPU with frequency information was detected * Correct type: /proc/stats -> /proc/stat * Update README.md * Run ipmitool asynchron. Improved error handling. * Corrected some typos * Add running average power limit (RAPL) metric collector * Add running average power limit (RAPL) metric collector * Do not mess up with the orignal configuration * * Corrected json config in numastatsMetric.md * Added some debug output to numastatsMetric.go * Fixed computing number of physical packages for non continous physical package IDs (e.g. on Ampere Altra Q80-30) * Fix kernel panic for receiver config with missing receiver type * Add receiver to gather remote IPMI sensor metrics * Added config option to add ipmi-sensors command line options * Add documentaion for IPMI receiver * Update to latest version of included go modules * Add go.mod to App dependency * Try to use common metric tags across hardware vendors * Add IPMI metric: current * remove prefix enumeration like 01-... * Add IPMI receiver example configuration to receivers.json * Minimal formating changes * Add hostlist package * Added tests for hostlist Expand() * Use package hostlist to expand a host list * Use package hostlist to expand a host list * Some servers return "ConsumedPowerWatt":65535 instead of "ConsumedPowerWatt":null * Updated to latest package versions * Do not allow unknown fields in JSON configuration file * Add workflow to customize packages to docs * NFS I/O Stats Collector (#91) * Initial version * Delete values for vanished mount points and comments * Fix for Likwid collector (#95) * Run LIKWID in separate thread and check metric type * Change LIKWID collector documentation to use 'type' instead of 'scope' * Re-initialize LIKWID after one read is missing due to lock toggle * Register cc-metric-collector at Zenodo (#93) * Add initial version of Zenodo project file * Orcid ID added * Update .zenodo.json Co-authored-by: Holger Obermaier <holger.obermaier@kit.edu> * Update ipmiMetric.go * Use latest LIKWID version for builds * Update README.md * Remove development stuff from Makefile * Add Requires(pre) to RPM SPEC file * Use curly brackets in packaging make targets * Fix for LIKWID collector with separate measurement thread and inotify watcher on the LIKWID lock (#97) Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> * Update likwid_perfgroup_to_cc_config.py * Use customcmd commands if they did not error. --------- Co-authored-by: Thomas Gruber <Thomas.Roehl@googlemail.com> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu>
2023-02-28 12:02:01 +01:00
if err == nil {
2021-11-25 15:11:39 +01:00
m.commands = append(m.commands, c)
}
}
for _, f := range m.config.Files {
2022-10-09 17:03:38 +02:00
_, err = os.ReadFile(f)
2021-11-25 15:11:39 +01:00
if err == nil {
m.files = append(m.files, f)
} else {
log.Print(err.Error())
continue
}
}
if len(m.files) == 0 && len(m.commands) == 0 {
2022-03-15 16:38:20 +01:00
return errors.New("no metrics to collect")
}
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>
2022-01-25 15:37:43 +01:00
m.handler = influx.NewMetricHandler()
m.parser = influx.NewParser(m.handler)
m.parser.SetTimeFunc(DefaultTime)
m.init = true
return nil
}
var DefaultTime = func() time.Time {
return time.Unix(42, 0)
}
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>
2022-01-25 15:37:43 +01:00
func (m *CustomCmdCollector) Read(interval time.Duration, output chan lp.CCMetric) {
2021-11-25 15:11:39 +01:00
if !m.init {
return
}
for _, cmd := range m.commands {
cmdfields := strings.Fields(cmd)
command := exec.Command(cmdfields[0], strings.Join(cmdfields[1:], " "))
command.Wait()
stdout, err := command.Output()
if err != nil {
log.Print(err)
continue
}
cmdmetrics, err := m.parser.Parse(stdout)
if err != nil {
log.Print(err)
continue
}
2021-11-25 15:11:39 +01:00
for _, c := range cmdmetrics {
_, skip := stringArrayContains(m.config.ExcludeMetrics, c.Name())
if skip {
continue
}
output <- lp.FromInfluxMetric(c)
2021-11-25 15:11:39 +01:00
}
}
for _, file := range m.files {
2022-10-09 17:03:38 +02:00
buffer, err := os.ReadFile(file)
2021-11-25 15:11:39 +01:00
if err != nil {
log.Print(err)
return
}
fmetrics, err := m.parser.Parse(buffer)
if err != nil {
log.Print(err)
continue
}
2021-11-25 15:11:39 +01:00
for _, f := range fmetrics {
_, skip := stringArrayContains(m.config.ExcludeMetrics, f.Name())
if skip {
continue
}
output <- lp.FromInfluxMetric(f)
2021-11-25 15:11:39 +01:00
}
}
}
func (m *CustomCmdCollector) Close() {
m.init = false
}