cc-metric-collector/collectors/sampleMetric.go

102 lines
3.8 KiB
Go
Raw Normal View History

package collectors
import (
"encoding/json"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-metric-collector/pkg/ccMetric"
)
// These are the fields we read from the JSON configuration
type SampleCollectorConfig struct {
Interval string `json:"interval"`
}
// This contains all variables we need during execution and the variables
// defined by metricCollector (name, init, ...)
type SampleCollector struct {
metricCollector
Merge `develop` branch into `main` (#96) * 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 Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu>
2022-12-14 17:02:39 +01:00
config SampleCollectorConfig // the configuration structure
meta map[string]string // default meta information
tags map[string]string // default tags
}
2022-02-28 09:57:26 +01:00
// Functions to implement MetricCollector interface
// Init(...), Read(...), Close()
// See: metricCollector.go
// Init initializes the sample collector
// Called once by the collector manager
// All tags, meta data tags and metrics that do not change over the runtime should be set here
func (m *SampleCollector) Init(config json.RawMessage) error {
var err error = nil
// Always set the name early in Init() to use it in cclog.Component* functions
m.name = "InternalCollector"
// This is for later use, also call it early
m.setup()
Merge latest development changes to main branch (#79) * Cleanup: Remove unused code * Use Golang duration parser for 'interval' and 'duration' in main config * Update handling of LIKWID headers. Download only if not already present in the system. Fixes #73 * Units with cc-units (#64) * Add option to normalize units with cc-unit * Add unit conversion to router * Add option to change unit prefix in the router * Add to MetricRouter README * Add order of operations in router to README * Use second add_tags/del_tags only if metric gets renamed * Skip disks in DiskstatCollector that have size=0 * Check readability of sensor files in TempCollector * Fix for --once option * Rename `cpu` type to `hwthread` (#69) * Rename 'cpu' type to 'hwthread' to avoid naming clashes with MetricStore and CC-Webfrontend * Collectors in parallel (#74) * Provide info to CollectorManager whether the collector can be executed in parallel with others * Split serial and parallel collectors. Read in parallel first * Update NvidiaCollector with new metrics, MIG and NvLink support (#75) * CC topology module update (#76) * Rename CPU to hardware thread, write some comments * Do renaming in other parts * Remove CpuList and SocketList function from metricCollector. Available in ccTopology * Option to use MIG UUID as subtype-id in NvidiaCollector * Option to use MIG slice name as subtype-id in NvidiaCollector * MetricRouter: Fix JSON in README * Fix for Github Action to really use the selected version * Remove Ganglia installation in runonce Action and add Go 1.18 * Fix daemon options in init script * Add separate go.mod files to use it with deprecated 1.16 * Minor updates for Makefiles * fix string comparison * AMD ROCm SMI collector (#77) * Add collector for AMD ROCm SMI metrics * Fix import path * Fix imports * Remove Board Number * store GPU index explicitly * Remove board number from description * Use http instead of ftp to download likwid * Fix serial number in rocmCollector * Improved http sink (#78) * automatic flush in NatsSink * tweak default options of HttpSink * shorter cirt. section and retries for HttpSink * fix error handling * Remove file added by mistake. * Use http instead of ftp to download likwid * Fix serial number in rocmCollector Co-authored-by: Thomas Roehl <thomas.roehl@fau.de> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Lou <lou.knauer@gmx.de>
2022-06-08 15:25:40 +02:00
// Tell whether the collector should be run in parallel with others (reading files, ...)
Merge `develop` branch into `main` (#96) * 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 Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu>
2022-12-14 17:02:39 +01:00
// or it should be run serially, mostly for collectors actually doing measurements
Merge latest development changes to main branch (#79) * Cleanup: Remove unused code * Use Golang duration parser for 'interval' and 'duration' in main config * Update handling of LIKWID headers. Download only if not already present in the system. Fixes #73 * Units with cc-units (#64) * Add option to normalize units with cc-unit * Add unit conversion to router * Add option to change unit prefix in the router * Add to MetricRouter README * Add order of operations in router to README * Use second add_tags/del_tags only if metric gets renamed * Skip disks in DiskstatCollector that have size=0 * Check readability of sensor files in TempCollector * Fix for --once option * Rename `cpu` type to `hwthread` (#69) * Rename 'cpu' type to 'hwthread' to avoid naming clashes with MetricStore and CC-Webfrontend * Collectors in parallel (#74) * Provide info to CollectorManager whether the collector can be executed in parallel with others * Split serial and parallel collectors. Read in parallel first * Update NvidiaCollector with new metrics, MIG and NvLink support (#75) * CC topology module update (#76) * Rename CPU to hardware thread, write some comments * Do renaming in other parts * Remove CpuList and SocketList function from metricCollector. Available in ccTopology * Option to use MIG UUID as subtype-id in NvidiaCollector * Option to use MIG slice name as subtype-id in NvidiaCollector * MetricRouter: Fix JSON in README * Fix for Github Action to really use the selected version * Remove Ganglia installation in runonce Action and add Go 1.18 * Fix daemon options in init script * Add separate go.mod files to use it with deprecated 1.16 * Minor updates for Makefiles * fix string comparison * AMD ROCm SMI collector (#77) * Add collector for AMD ROCm SMI metrics * Fix import path * Fix imports * Remove Board Number * store GPU index explicitly * Remove board number from description * Use http instead of ftp to download likwid * Fix serial number in rocmCollector * Improved http sink (#78) * automatic flush in NatsSink * tweak default options of HttpSink * shorter cirt. section and retries for HttpSink * fix error handling * Remove file added by mistake. * Use http instead of ftp to download likwid * Fix serial number in rocmCollector Co-authored-by: Thomas Roehl <thomas.roehl@fau.de> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Lou <lou.knauer@gmx.de>
2022-06-08 15:25:40 +02:00
// because they should not measure the execution of the other collectors
m.parallel = true
// Define meta information sent with each metric
// (Can also be dynamic or this is the basic set with extension through AddMeta())
m.meta = map[string]string{"source": m.name, "group": "SAMPLE"}
// Define tags sent with each metric
Merge `develop` branch into `main` (#96) * 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 Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu>
2022-12-14 17:02:39 +01:00
// The 'type' tag is always needed, it defines the granularity of the metric
// node -> whole system
// socket -> CPU socket (requires socket ID as 'type-id' tag)
Merge latest development changes to main branch (#79) * Cleanup: Remove unused code * Use Golang duration parser for 'interval' and 'duration' in main config * Update handling of LIKWID headers. Download only if not already present in the system. Fixes #73 * Units with cc-units (#64) * Add option to normalize units with cc-unit * Add unit conversion to router * Add option to change unit prefix in the router * Add to MetricRouter README * Add order of operations in router to README * Use second add_tags/del_tags only if metric gets renamed * Skip disks in DiskstatCollector that have size=0 * Check readability of sensor files in TempCollector * Fix for --once option * Rename `cpu` type to `hwthread` (#69) * Rename 'cpu' type to 'hwthread' to avoid naming clashes with MetricStore and CC-Webfrontend * Collectors in parallel (#74) * Provide info to CollectorManager whether the collector can be executed in parallel with others * Split serial and parallel collectors. Read in parallel first * Update NvidiaCollector with new metrics, MIG and NvLink support (#75) * CC topology module update (#76) * Rename CPU to hardware thread, write some comments * Do renaming in other parts * Remove CpuList and SocketList function from metricCollector. Available in ccTopology * Option to use MIG UUID as subtype-id in NvidiaCollector * Option to use MIG slice name as subtype-id in NvidiaCollector * MetricRouter: Fix JSON in README * Fix for Github Action to really use the selected version * Remove Ganglia installation in runonce Action and add Go 1.18 * Fix daemon options in init script * Add separate go.mod files to use it with deprecated 1.16 * Minor updates for Makefiles * fix string comparison * AMD ROCm SMI collector (#77) * Add collector for AMD ROCm SMI metrics * Fix import path * Fix imports * Remove Board Number * store GPU index explicitly * Remove board number from description * Use http instead of ftp to download likwid * Fix serial number in rocmCollector * Improved http sink (#78) * automatic flush in NatsSink * tweak default options of HttpSink * shorter cirt. section and retries for HttpSink * fix error handling * Remove file added by mistake. * Use http instead of ftp to download likwid * Fix serial number in rocmCollector Co-authored-by: Thomas Roehl <thomas.roehl@fau.de> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Lou <lou.knauer@gmx.de>
2022-06-08 15:25:40 +02:00
// die -> CPU die (requires CPU die ID as 'type-id' tag)
// memoryDomain -> NUMA domain (requires NUMA domain ID as 'type-id' tag)
// llc -> Last level cache (requires last level cache ID as 'type-id' tag)
// core -> single CPU core that may consist of multiple hardware threads (SMT) (requires core ID as 'type-id' tag)
// hwthtread -> single CPU hardware thread (requires hardware thread ID as 'type-id' tag)
// accelerator -> A accelerator device like GPU or FPGA (requires an accelerator ID as 'type-id' tag)
m.tags = map[string]string{"type": "node"}
// Read in the JSON configuration
if len(config) > 0 {
err = json.Unmarshal(config, &m.config)
if err != nil {
cclog.ComponentError(m.name, "Error reading config:", err.Error())
return err
}
}
// Set up everything that the collector requires during the Read() execution
// Check files required, test execution of some commands, create data structure
// for all topological entities (sockets, NUMA domains, ...)
// Return some useful error message in case of any failures
// Set this flag only if everything is initialized properly, all required files exist, ...
m.init = true
return err
}
2022-02-28 09:57:26 +01:00
// Read collects all metrics belonging to the sample collector
// and sends them through the output channel to the collector manager
func (m *SampleCollector) Read(interval time.Duration, output chan lp.CCMetric) {
// Create a sample metric
timestamp := time.Now()
value := 1.0
2022-02-28 09:57:26 +01:00
// If you want to measure something for a specific amount of time, use interval
// start := readState()
// time.Sleep(interval)
// stop := readState()
// value = (stop - start) / interval.Seconds()
y, err := lp.New("sample_metric", m.tags, m.meta, map[string]interface{}{"value": value}, timestamp)
if err == nil {
// Send it to output channel
output <- y
}
}
2022-02-28 09:57:26 +01:00
// Close metric collector: close network connection, close files, close libraries, ...
// Called once by the collector manager
func (m *SampleCollector) Close() {
// Unset flag
m.init = false
}