cc-metric-collector/collectors/netstatMetric.go

243 lines
6.0 KiB
Go
Raw Normal View History

package collectors
import (
"bufio"
2021-11-25 15:11:39 +01:00
"encoding/json"
"errors"
"os"
"strconv"
"strings"
"time"
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
lp "github.com/ClusterCockpit/cc-lib/ccMessage"
)
const NETSTATFILE = "/proc/net/dev"
type NetstatCollectorConfig struct {
IncludeDevices []string `json:"include_devices"`
SendAbsoluteValues bool `json:"send_abs_values"`
SendDerivedValues bool `json:"send_derived_values"`
InterfaceAliases map[string][]string `json:"interface_aliases,omitempty"`
}
type NetstatCollectorMetric struct {
2022-03-11 14:47:18 +01:00
name string
index int
tags map[string]string
meta map[string]string
meta_rates map[string]string
lastValue int64
}
type NetstatCollector 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
config NetstatCollectorConfig
aliasToCanonical map[string]string
matches map[string][]NetstatCollectorMetric
lastTimestamp time.Time
}
func (m *NetstatCollector) buildAliasMapping() {
m.aliasToCanonical = make(map[string]string)
for canon, aliases := range m.config.InterfaceAliases {
for _, alias := range aliases {
m.aliasToCanonical[alias] = canon
}
}
}
func getCanonicalName(raw string, aliasToCanonical map[string]string) string {
if canon, ok := aliasToCanonical[raw]; ok {
return canon
}
return raw
}
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 *NetstatCollector) Init(config json.RawMessage) error {
2021-03-25 17:47:08 +01:00
m.name = "NetstatCollector"
m.parallel = true
m.setup()
m.lastTimestamp = time.Now()
const (
2022-03-11 14:09:22 +01:00
fieldInterface = iota
fieldReceiveBytes
fieldReceivePackets
fieldReceiveErrs
fieldReceiveDrop
fieldReceiveFifo
fieldReceiveFrame
fieldReceiveCompressed
fieldReceiveMulticast
fieldTransmitBytes
fieldTransmitPackets
fieldTransmitErrs
fieldTransmitDrop
fieldTransmitFifo
fieldTransmitColls
fieldTransmitCarrier
fieldTransmitCompressed
)
m.matches = make(map[string][]NetstatCollectorMetric)
// Set default configuration,
m.config.SendAbsoluteValues = true
m.config.SendDerivedValues = false
// Read configuration file, allow overwriting default config
2021-11-26 18:19:45 +01:00
if len(config) > 0 {
2021-11-29 15:32:58 +01:00
err := json.Unmarshal(config, &m.config)
if err != nil {
cclog.ComponentError(m.name, "Error reading config:", err.Error())
2021-11-29 15:32:58 +01:00
return err
}
}
m.buildAliasMapping()
// Check access to net statistic file
file, err := os.Open(NETSTATFILE)
if err != nil {
cclog.ComponentError(m.name, err.Error())
return err
}
defer file.Close()
scanner := bufio.NewScanner(file)
for scanner.Scan() {
l := scanner.Text()
// Skip lines with no net device entry
if !strings.Contains(l, ":") {
continue
}
// Split line into fields
f := strings.Fields(l)
// Get raw and canonical names
raw := strings.Trim(f[0], ": ")
canonical := getCanonicalName(raw, m.aliasToCanonical)
// Check if device is a included device
if _, ok := stringArrayContains(m.config.IncludeDevices, canonical); ok {
// Tag will contain original device name (raw).
tags := map[string]string{"stype": "network", "stype-id": raw, "type": "node"}
2022-03-11 14:47:18 +01:00
meta_unit_byte := map[string]string{"source": m.name, "group": "Network", "unit": "bytes"}
meta_unit_byte_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "bytes/sec"}
meta_unit_pkts := map[string]string{"source": m.name, "group": "Network", "unit": "packets"}
meta_unit_pkts_per_sec := map[string]string{"source": m.name, "group": "Network", "unit": "packets/sec"}
m.matches[canonical] = []NetstatCollectorMetric{
{
2022-03-11 14:47:18 +01:00
name: "net_bytes_in",
index: fieldReceiveBytes,
lastValue: -1,
tags: tags,
meta: meta_unit_byte,
meta_rates: meta_unit_byte_per_sec,
},
{
2022-03-11 14:47:18 +01:00
name: "net_pkts_in",
index: fieldReceivePackets,
lastValue: -1,
tags: tags,
meta: meta_unit_pkts,
meta_rates: meta_unit_pkts_per_sec,
},
{
2022-03-11 14:47:18 +01:00
name: "net_bytes_out",
index: fieldTransmitBytes,
lastValue: -1,
tags: tags,
meta: meta_unit_byte,
meta_rates: meta_unit_byte_per_sec,
},
{
2022-03-11 14:47:18 +01:00
name: "net_pkts_out",
index: fieldTransmitPackets,
lastValue: -1,
tags: tags,
meta: meta_unit_pkts,
meta_rates: meta_unit_pkts_per_sec,
},
}
}
}
if len(m.matches) == 0 {
return errors.New("no devices to collector metrics found")
2021-10-04 15:47:03 +02:00
}
m.init = true
return nil
}
Merge develop branch into main (#123) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Update README.md Use right JSON type in configuration * Update sink's README * Test whether ipmitool or ipmi-sensors can be executed without errors * Little fixes to the prometheus sink (#115) * Add uint64 to float64 cast option * Add prometheus sink to the list of available sinks * Add aggregated counters by gpu for nvlink errors --------- Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de> * Ccmessage migration (#119) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Switch to CCMessage for all files. --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Switch to ccmessage also for latest additions in nvidiaMetric * New Message processor (#118) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * New message processor to check whether a message should be dropped or manipulate it in flight * Create a copy of message before manipulation --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Update collector's Makefile and go.mod/sum files * Use message processor in router, all sinks and all receivers * Add support for credential file (NKEY) to NATS sink and receiver * Fix JSON keys in message processor configuration * Update docs for message processor, router and the default router config file * Add link to expr syntax and fix regex matching docs * Update sample collectors * Minor style change in collector manager * Some helpers for ccTopology * LIKWID collector: write log owner change only once * Fix for metrics without units and reduce debugging messages for messageProcessor * Use shorted hostname for hostname added by router * Define default port for NATS * CPUstat collector: only add unit for applicable metrics * Add precision option to all sinks using Influx's encoder * Add message processor to all sink documentation * Add units to documentation of cpustat collector --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: oscarminus <me@oscarminus.de> Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de>
2024-12-19 23:00:14 +01:00
func (m *NetstatCollector) Read(interval time.Duration, output chan lp.CCMessage) {
if !m.init {
return
}
// Current time stamp
now := time.Now()
// time difference to last time stamp
timeDiff := now.Sub(m.lastTimestamp).Seconds()
// Save current timestamp
m.lastTimestamp = now
file, err := os.Open(NETSTATFILE)
if err != nil {
cclog.ComponentError(m.name, err.Error())
return
}
defer file.Close()
scanner := bufio.NewScanner(file)
for scanner.Scan() {
l := scanner.Text()
// Skip lines with no net device entry
if !strings.Contains(l, ":") {
continue
}
// Split line into fields
f := strings.Fields(l)
// Get raw and canonical names
raw := strings.Trim(f[0], ":")
canonical := getCanonicalName(raw, m.aliasToCanonical)
// Check if device is a included device
if devmetrics, ok := m.matches[canonical]; ok {
for i := range devmetrics {
metric := &devmetrics[i]
// Read value
v, err := strconv.ParseInt(f[metric.index], 10, 64)
if err != nil {
continue
}
if m.config.SendAbsoluteValues {
Merge develop branch into main (#123) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Update README.md Use right JSON type in configuration * Update sink's README * Test whether ipmitool or ipmi-sensors can be executed without errors * Little fixes to the prometheus sink (#115) * Add uint64 to float64 cast option * Add prometheus sink to the list of available sinks * Add aggregated counters by gpu for nvlink errors --------- Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de> * Ccmessage migration (#119) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Switch to CCMessage for all files. --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Switch to ccmessage also for latest additions in nvidiaMetric * New Message processor (#118) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * New message processor to check whether a message should be dropped or manipulate it in flight * Create a copy of message before manipulation --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Update collector's Makefile and go.mod/sum files * Use message processor in router, all sinks and all receivers * Add support for credential file (NKEY) to NATS sink and receiver * Fix JSON keys in message processor configuration * Update docs for message processor, router and the default router config file * Add link to expr syntax and fix regex matching docs * Update sample collectors * Minor style change in collector manager * Some helpers for ccTopology * LIKWID collector: write log owner change only once * Fix for metrics without units and reduce debugging messages for messageProcessor * Use shorted hostname for hostname added by router * Define default port for NATS * CPUstat collector: only add unit for applicable metrics * Add precision option to all sinks using Influx's encoder * Add message processor to all sink documentation * Add units to documentation of cpustat collector --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: oscarminus <me@oscarminus.de> Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de>
2024-12-19 23:00:14 +01:00
if y, err := lp.NewMessage(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
output <- y
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
}
}
if m.config.SendDerivedValues {
if metric.lastValue >= 0 {
rate := float64(v-metric.lastValue) / timeDiff
Merge develop branch into main (#123) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Update README.md Use right JSON type in configuration * Update sink's README * Test whether ipmitool or ipmi-sensors can be executed without errors * Little fixes to the prometheus sink (#115) * Add uint64 to float64 cast option * Add prometheus sink to the list of available sinks * Add aggregated counters by gpu for nvlink errors --------- Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de> * Ccmessage migration (#119) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * Switch to CCMessage for all files. --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Switch to ccmessage also for latest additions in nvidiaMetric * New Message processor (#118) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update cc-metric-collector.init * Allow selection of timestamp precision in HttpSink * Add comment about precision requirement for cc-metric-store * Fix for API changes in gofish@v0.15.0 * Update requirements to latest version * Read sensors through redfish * Update golang toolchain to 1.21 * Remove stray error check * Update main config in configuration.md * Update Release action to use golang 1.22 stable release, no golang RPMs anymore * Update runonce action to use golang 1.22 stable release, no golang RPMs anymore * New message processor to check whether a message should be dropped or manipulate it in flight * Create a copy of message before manipulation --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> * Update collector's Makefile and go.mod/sum files * Use message processor in router, all sinks and all receivers * Add support for credential file (NKEY) to NATS sink and receiver * Fix JSON keys in message processor configuration * Update docs for message processor, router and the default router config file * Add link to expr syntax and fix regex matching docs * Update sample collectors * Minor style change in collector manager * Some helpers for ccTopology * LIKWID collector: write log owner change only once * Fix for metrics without units and reduce debugging messages for messageProcessor * Use shorted hostname for hostname added by router * Define default port for NATS * CPUstat collector: only add unit for applicable metrics * Add precision option to all sinks using Influx's encoder * Add message processor to all sink documentation * Add units to documentation of cpustat collector --------- Co-authored-by: Holger Obermaier <Holger.Obermaier@kit.edu> Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: oscarminus <me@oscarminus.de> Co-authored-by: Michael Schwarz <schwarz@uni-paderborn.de>
2024-12-19 23:00:14 +01:00
if y, err := lp.NewMessage(metric.name+"_bw", metric.tags, metric.meta_rates, map[string]interface{}{"value": rate}, now); err == nil {
output <- y
}
}
metric.lastValue = v
2021-10-04 15:23:43 +02:00
}
}
}
}
}
func (m *NetstatCollector) Close() {
2021-10-04 15:47:03 +02:00
m.init = false
}