cc-metric-collector/collectors/netstatMetric.go

221 lines
5.2 KiB
Go
Raw Permalink 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-metric-collector/pkg/ccMetric"
)
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"`
}
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
matches map[string][]NetstatCollectorMetric
lastTimestamp time.Time
}
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
}
}
// 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 net device entry
dev := strings.Trim(f[0], ": ")
// Check if device is a included device
if _, ok := stringArrayContains(m.config.IncludeDevices, dev); ok {
Merge develop into main (#109) * Add cpu_used (all-cpu_idle) to CpustatCollector * Update to line-protocol/v2 * Update runonce.yml with Golang 1.20 * Update fsnotify in LIKWID Collector * Use not a pointer to line-protocol.Encoder * Simplify Makefile * Use only as many arguments as required * Allow sum function to handle non float types * Allow values to be a slice of type float64, float32, int, int64, int32, bool * Use generic function to simplify code * Add missing case for type []int32 * Use generic function to compute minimum * Use generic function to compute maximum * Use generic function to compute average * Add error value to sumAnyType * Use generic function to compute median * For older versions of go slices is not part of the installation * Remove old entries from go.sum * Use simpler sort function * Compute metrics ib_total and ib_total_pkts * Add aggregated metrics. Add missing units * Update likwidMetric.go Fixes a potential bug when `fsnotify.NewWatcher()` fails with an error * Completly avoid memory allocations in infinibandMetric read() * Fixed initialization: Initalization and measurements should run in the same thread * Add safe.directory to Release action * Fix path after installation to /usr/bin after installation * ioutil.ReadFile is deprecated: As of Go 1.16, this function simply calls os.ReadFile * Switch to package slices from the golang 1.21 default library * Read file line by line * Read file line by line * Read file line by line * Use CamelCase * Use CamelCase * Fix function getNumaDomain, it always returned 0 * Avoid type conversion by using Atoi Avoid copying structs by using pointer access Increase readability with CamelCase variable names * Add caching * Cache CpuData * Cleanup * Use init function to initalize cache structure to avoid multi threading problems * Reuse information from /proc/cpuinfo * Avoid slice cloning. Directly use the cache * Add DieList * Add NumaDomainList and SMTList * Cleanup * Add comment * Lookup core ID from /sys/devices/system/cpu, /proc/cpuinfo is not portable * Lookup all information from /sys/devices/system/cpu, /proc/cpuinfo is not portable * Correctly handle lists from /sys * Add Simultaneous Multithreading siblings * Replace deprecated thread_siblings_list by core_cpus_list * Reduce number of required slices * Allow to send total values per core, socket and node * Send all metrics with same time stamp calcEventsetMetrics does only computiation, counter measurement is done before * Input parameters should be float64 when evaluating to float64 * Send all metrics with same time stamp calcGlobalMetrics does only computiation, counter measurement is done before * Remove unused variable gmresults * Add comments * Updated go packages * Add build with golang 1.21 * Switch to checkout action version 4 * Switch to setup-go action version 4 * Add workflow_dispatch to allow manual run of workflow * Add workflow_dispatch to allow manual run of workflow * Add release build jobs to runonce.yml * Switch to golang 1.20 for RHEL based distributions * Use dnf to download golang * Remove golang versions before 1.20 * Upgrade Ubuntu focal -> jammy * Pipe golang tar package directly to tar * Update golang version * Fix Ubuntu version number * Add links to ipmi and redfish receivers * Fix http server addr format * github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol * Corrected spelling * Add some comments * github.com/influxdata/line-protocol -> github.com/influxdata/line-protocol/v2/lineprotocol * Allow other fields not only field "value" * Add some basic debugging documentation * Add some basic debugging documentation * Use a lock for the flush timer * Add tags in lexical order as required by AddTag() * Only access meta data, when it gets used as tag * Use slice to store lexialicly orderd key value pairs * Increase golang version requirement to 1.20. * Avoid package cmp to allow builds with golang v1.20 * Fix: Error NVML library not found did crash cc-metric-collector with "SIGSEGV: segmentation violation" * Add config option idle_timeout * Add basic authentication support * Add basic authentication support * Avoid unneccessary memory allocations * Add documentation for send_*_total values * Use generic package maps to clone maps * Reuse flush timer * Add Influx client options * Reuse ccTopology functionality * Do not store unused topology information * Add batch_size config * Cleanup * Use stype and stype-id for the NIC in NetstatCollector * Wait for concurrent flush operations to finish * Be more verbose in error messages * Reverted previous changes. Made the code to complex without much advantages * Use line protocol encoder * Go pkg update * Stop flush timer, when immediatelly flushing * Fix: Corrected unlock access to batch slice * Add config option to specify whether to use GZip compression in influx write requests * Add asynchron send of encoder metrics * Use DefaultServeMux instead of github.com/gorilla/mux * Add config option for HTTP keep-alives * Be more strict, when parsing json * Add config option for HTTP request timeout and Retry interval * Allow more then one background send operation * Fix %sysusers_create_package args (#108) %sysusers_create_package requires two arguments. See: https://github.com/systemd/systemd/blob/main/src/rpm/macros.systemd.in#L165 * Add nfsiostat to list of collectors --------- Co-authored-by: Holger Obermaier <40787752+ho-ob@users.noreply.github.com> Co-authored-by: Holger Obermaier <holgerob@gmx.de> Co-authored-by: Obihörnchen <obihoernchende@gmail.com>
2023-12-04 12:21:26 +01:00
tags := map[string]string{"stype": "network", "stype-id": dev, "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[dev] = []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
}
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) Read(interval time.Duration, output chan lp.CCMetric) {
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(string(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 net device entry
dev := strings.Trim(f[0], ":")
// Check if device is a included device
if devmetrics, ok := m.matches[dev]; 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 {
2022-03-11 14:47:18 +01:00
if y, err := lp.New(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
2022-03-11 14:47:18 +01:00
if y, err := lp.New(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
}