mirror of
https://github.com/ClusterCockpit/cc-metric-collector.git
synced 2024-12-27 07:39:05 +01:00
7840de7b82
* 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>
221 lines
5.2 KiB
Go
221 lines
5.2 KiB
Go
package collectors
|
|
|
|
import (
|
|
"bufio"
|
|
"encoding/json"
|
|
"errors"
|
|
"os"
|
|
"strconv"
|
|
"strings"
|
|
"time"
|
|
|
|
cclog "github.com/ClusterCockpit/cc-metric-collector/pkg/ccLogger"
|
|
lp "github.com/ClusterCockpit/cc-energy-manager/pkg/cc-message"
|
|
)
|
|
|
|
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 {
|
|
name string
|
|
index int
|
|
tags map[string]string
|
|
meta map[string]string
|
|
meta_rates map[string]string
|
|
lastValue int64
|
|
}
|
|
|
|
type NetstatCollector struct {
|
|
metricCollector
|
|
config NetstatCollectorConfig
|
|
matches map[string][]NetstatCollectorMetric
|
|
lastTimestamp time.Time
|
|
}
|
|
|
|
func (m *NetstatCollector) Init(config json.RawMessage) error {
|
|
m.name = "NetstatCollector"
|
|
m.parallel = true
|
|
m.setup()
|
|
m.lastTimestamp = time.Now()
|
|
|
|
const (
|
|
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
|
|
if len(config) > 0 {
|
|
err := json.Unmarshal(config, &m.config)
|
|
if err != nil {
|
|
cclog.ComponentError(m.name, "Error reading config:", err.Error())
|
|
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 {
|
|
tags := map[string]string{"stype": "network", "stype-id": dev, "type": "node"}
|
|
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{
|
|
{
|
|
name: "net_bytes_in",
|
|
index: fieldReceiveBytes,
|
|
lastValue: -1,
|
|
tags: tags,
|
|
meta: meta_unit_byte,
|
|
meta_rates: meta_unit_byte_per_sec,
|
|
},
|
|
{
|
|
name: "net_pkts_in",
|
|
index: fieldReceivePackets,
|
|
lastValue: -1,
|
|
tags: tags,
|
|
meta: meta_unit_pkts,
|
|
meta_rates: meta_unit_pkts_per_sec,
|
|
},
|
|
{
|
|
name: "net_bytes_out",
|
|
index: fieldTransmitBytes,
|
|
lastValue: -1,
|
|
tags: tags,
|
|
meta: meta_unit_byte,
|
|
meta_rates: meta_unit_byte_per_sec,
|
|
},
|
|
{
|
|
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")
|
|
}
|
|
m.init = true
|
|
return nil
|
|
}
|
|
|
|
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(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 {
|
|
if y, err := lp.NewMessage(metric.name, metric.tags, metric.meta, map[string]interface{}{"value": v}, now); err == nil {
|
|
output <- y
|
|
}
|
|
}
|
|
if m.config.SendDerivedValues {
|
|
if metric.lastValue >= 0 {
|
|
rate := float64(v-metric.lastValue) / timeDiff
|
|
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
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
func (m *NetstatCollector) Close() {
|
|
m.init = false
|
|
}
|