| 1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261 |
- {
- _config+:: {
- etcd_selector: 'job=~".*etcd.*"',
- },
- prometheusAlerts+:: {
- groups+: [
- {
- name: 'etcd',
- rules: [
- {
- alert: 'EtcdInsufficientMembers',
- expr: |||
- sum(up{%(etcd_selector)s} == bool 1) by (job) < ((count(up{%(etcd_selector)s}) by (job) + 1) / 2)
- ||| % $._config,
- 'for': '3m',
- labels: {
- severity: 'critical',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": insufficient members ({{ $value }}).',
- },
- },
- {
- alert: 'EtcdNoLeader',
- expr: |||
- etcd_server_has_leader{%(etcd_selector)s} == 0
- ||| % $._config,
- 'for': '1m',
- labels: {
- severity: 'critical',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": member {{ $labels.instance }} has no leader.',
- },
- },
- {
- alert: 'EtcdHighNumberOfLeaderChanges',
- expr: |||
- rate(etcd_server_leader_changes_seen_total{%(etcd_selector)s}[15m]) > 3
- ||| % $._config,
- 'for': '15m',
- labels: {
- severity: 'warning',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": instance {{ $labels.instance }} has seen {{ $value }} leader changes within the last hour.',
- },
- },
- {
- alert: 'EtcdHighNumberOfFailedGRPCRequests',
- expr: |||
- 100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
- /
- sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) BY (job, instance, grpc_service, grpc_method)
- > 1
- ||| % $._config,
- 'for': '10m',
- labels: {
- severity: 'warning',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.',
- },
- },
- {
- alert: 'EtcdHighNumberOfFailedGRPCRequests',
- expr: |||
- 100 * sum(rate(grpc_server_handled_total{%(etcd_selector)s, grpc_code!="OK"}[5m])) BY (job, instance, grpc_service, grpc_method)
- /
- sum(rate(grpc_server_handled_total{%(etcd_selector)s}[5m])) BY (job, instance, grpc_service, grpc_method)
- > 5
- ||| % $._config,
- 'for': '5m',
- labels: {
- severity: 'critical',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": {{ $value }}% of requests for {{ $labels.grpc_method }} failed on etcd instance {{ $labels.instance }}.',
- },
- },
- {
- alert: 'EtcdGRPCRequestsSlow',
- expr: |||
- histogram_quantile(0.99, sum(rate(grpc_server_handling_seconds_bucket{%(etcd_selector)s, grpc_type="unary"}[5m])) by (job, instance, grpc_service, grpc_method, le))
- > 0.15
- ||| % $._config,
- 'for': '10m',
- labels: {
- severity: 'critical',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": gRPC requests to {{ $labels.grpc_method }} are taking {{ $value }}s on etcd instance {{ $labels.instance }}.',
- },
- },
- {
- alert: 'EtcdMemberCommunicationSlow',
- expr: |||
- histogram_quantile(0.99, rate(etcd_network_peer_round_trip_time_seconds_bucket{%(etcd_selector)s}[5m]))
- > 0.15
- ||| % $._config,
- 'for': '10m',
- labels: {
- severity: 'warning',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": member communication with {{ $labels.To }} is taking {{ $value }}s on etcd instance {{ $labels.instance }}.',
- },
- },
- {
- alert: 'EtcdHighNumberOfFailedProposals',
- expr: |||
- rate(etcd_server_proposals_failed_total{%(etcd_selector)s}[15m]) > 5
- ||| % $._config,
- 'for': '15m',
- labels: {
- severity: 'warning',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": {{ $value }} proposal failures within the last hour on etcd instance {{ $labels.instance }}.',
- },
- },
- {
- alert: 'EtcdHighFsyncDurations',
- expr: |||
- histogram_quantile(0.99, rate(etcd_disk_wal_fsync_duration_seconds_bucket{%(etcd_selector)s}[5m]))
- > 0.5
- ||| % $._config,
- 'for': '10m',
- labels: {
- severity: 'warning',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": 99th percentile fync durations are {{ $value }}s on etcd instance {{ $labels.instance }}.',
- },
- },
- {
- alert: 'EtcdHighCommitDurations',
- expr: |||
- histogram_quantile(0.99, rate(etcd_disk_backend_commit_duration_seconds_bucket{%(etcd_selector)s}[5m]))
- > 0.25
- ||| % $._config,
- 'for': '10m',
- labels: {
- severity: 'warning',
- },
- annotations: {
- message: 'Etcd cluster "{{ $labels.job }}": 99th percentile commit durations {{ $value }}s on etcd instance {{ $labels.instance }}.',
- },
- },
- {
- record: 'instance:fd_utilization',
- expr: 'process_open_fds / process_max_fds',
- },
- {
- alert: 'FdExhaustionClose',
- expr: |||
- predict_linear(instance:fd_utilization{%(etcd_selector)s}[1h], 3600 * 4) > 1
- ||| % $._config,
- 'for': '10m',
- labels: {
- severity: 'warning',
- },
- annotations: {
- message: '{{ $labels.job }} instance {{ $labels.instance }} will exhaust its file descriptors soon',
- },
- },
- {
- alert: 'FdExhaustionClose',
- expr: |||
- predict_linear(instance:fd_utilization{%(etcd_selector)s}[10m], 3600) > 1
- ||| % $._config,
- 'for': '10m',
- labels: {
- severity: 'critical',
- },
- annotations: {
- description: '{{ $labels.job }} instance {{ $labels.instance }} will exhaust its file descriptors soon',
- },
- },
- ],
- },
- ],
- },
- grafanaDashboards+:: {
- 'etcd.json': {
- id: 6,
- title: 'etcd',
- description: 'etcd sample Grafana dashboard with Prometheus',
- tags: [],
- style: 'dark',
- timezone: 'browser',
- editable: true,
- hideControls: false,
- sharedCrosshair: false,
- rows: [
- {
- collapse: false,
- editable: true,
- height: '250px',
- panels: [
- {
- cacheTimeout: null,
- colorBackground: false,
- colorValue: false,
- colors: [
- 'rgba(245, 54, 54, 0.9)',
- 'rgba(237, 129, 40, 0.89)',
- 'rgba(50, 172, 45, 0.97)',
- ],
- datasource: '$datasource',
- editable: true,
- 'error': false,
- format: 'none',
- gauge: {
- maxValue: 100,
- minValue: 0,
- show: false,
- thresholdLabels: false,
- thresholdMarkers: true,
- },
- id: 28,
- interval: null,
- isNew: true,
- links: [],
- mappingType: 1,
- mappingTypes: [
- {
- name: 'value to text',
- value: 1,
- },
- {
- name: 'range to text',
- value: 2,
- },
- ],
- maxDataPoints: 100,
- nullPointMode: 'connected',
- nullText: null,
- postfix: '',
- postfixFontSize: '50%',
- prefix: '',
- prefixFontSize: '50%',
- rangeMaps: [{
- from: 'null',
- text: 'N/A',
- to: 'null',
- }],
- span: 3,
- sparkline: {
- fillColor: 'rgba(31, 118, 189, 0.18)',
- full: false,
- lineColor: 'rgb(31, 120, 193)',
- show: false,
- },
- targets: [{
- expr: 'sum(etcd_server_has_leader{job="$cluster"})',
- intervalFactor: 2,
- legendFormat: '',
- metric: 'etcd_server_has_leader',
- refId: 'A',
- step: 20,
- }],
- thresholds: '',
- title: 'Up',
- type: 'singlestat',
- valueFontSize: '200%',
- valueMaps: [{
- op: '=',
- text: 'N/A',
- value: 'null',
- }],
- valueName: 'avg',
- },
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- editable: true,
- 'error': false,
- fill: 0,
- id: 23,
- isNew: true,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 5,
- stack: false,
- steppedLine: false,
- targets: [
- {
- expr: 'sum(rate(grpc_server_started_total{job="$cluster",grpc_type="unary"}[5m]))',
- format: 'time_series',
- intervalFactor: 2,
- legendFormat: 'RPC Rate',
- metric: 'grpc_server_started_total',
- refId: 'A',
- step: 2,
- },
- {
- expr: 'sum(rate(grpc_server_handled_total{job="$cluster",grpc_type="unary",grpc_code!="OK"}[5m]))',
- format: 'time_series',
- intervalFactor: 2,
- legendFormat: 'RPC Failed Rate',
- metric: 'grpc_server_handled_total',
- refId: 'B',
- step: 2,
- },
- ],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'RPC Rate',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'individual',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'ops',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- ],
- },
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- editable: true,
- 'error': false,
- fill: 0,
- id: 41,
- isNew: true,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 4,
- stack: true,
- steppedLine: false,
- targets: [
- {
- expr: 'sum(grpc_server_started_total{job="$cluster",grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"}) - sum(grpc_server_handled_total{job="$cluster",grpc_service="etcdserverpb.Watch",grpc_type="bidi_stream"})',
- intervalFactor: 2,
- legendFormat: 'Watch Streams',
- metric: 'grpc_server_handled_total',
- refId: 'A',
- step: 4,
- },
- {
- expr: 'sum(grpc_server_started_total{job="$cluster",grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"}) - sum(grpc_server_handled_total{job="$cluster",grpc_service="etcdserverpb.Lease",grpc_type="bidi_stream"})',
- intervalFactor: 2,
- legendFormat: 'Lease Streams',
- metric: 'grpc_server_handled_total',
- refId: 'B',
- step: 4,
- },
- ],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'Active Streams',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'individual',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'short',
- label: '',
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- ],
- },
- ],
- showTitle: false,
- title: 'Row',
- },
- {
- collapse: false,
- editable: true,
- height: '250px',
- panels: [
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- decimals: null,
- editable: true,
- 'error': false,
- fill: 0,
- grid: {},
- id: 1,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 4,
- stack: false,
- steppedLine: false,
- targets: [{
- expr: 'etcd_debugging_mvcc_db_total_size_in_bytes{job="$cluster"}',
- hide: false,
- interval: '',
- intervalFactor: 2,
- legendFormat: '{{instance}} DB Size',
- metric: '',
- refId: 'A',
- step: 4,
- }],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'DB Size',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'cumulative',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'bytes',
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- logBase: 1,
- max: null,
- min: null,
- show: false,
- },
- ],
- },
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- editable: true,
- 'error': false,
- fill: 0,
- grid: {},
- id: 3,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 1,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 4,
- stack: false,
- steppedLine: true,
- targets: [
- {
- expr: 'histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job="$cluster"}[5m])) by (instance, le))',
- hide: false,
- intervalFactor: 2,
- legendFormat: '{{instance}} WAL fsync',
- metric: 'etcd_disk_wal_fsync_duration_seconds_bucket',
- refId: 'A',
- step: 4,
- },
- {
- expr: 'histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job="$cluster"}[5m])) by (instance, le))',
- intervalFactor: 2,
- legendFormat: '{{instance}} DB fsync',
- metric: 'etcd_disk_backend_commit_duration_seconds_bucket',
- refId: 'B',
- step: 4,
- },
- ],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'Disk Sync Duration',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'cumulative',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 's',
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- logBase: 1,
- max: null,
- min: null,
- show: false,
- },
- ],
- },
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- editable: true,
- 'error': false,
- fill: 0,
- id: 29,
- isNew: true,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 4,
- stack: false,
- steppedLine: false,
- targets: [{
- expr: 'process_resident_memory_bytes{job="$cluster"}',
- intervalFactor: 2,
- legendFormat: '{{instance}} Resident Memory',
- metric: 'process_resident_memory_bytes',
- refId: 'A',
- step: 4,
- }],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'Memory',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'individual',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'bytes',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- ],
- },
- ],
- title: 'New row',
- },
- {
- collapse: false,
- editable: true,
- height: '250px',
- panels: [
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- editable: true,
- 'error': false,
- fill: 5,
- id: 22,
- isNew: true,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 3,
- stack: true,
- steppedLine: false,
- targets: [{
- expr: 'rate(etcd_network_client_grpc_received_bytes_total{job="$cluster"}[5m])',
- intervalFactor: 2,
- legendFormat: '{{instance}} Client Traffic In',
- metric: 'etcd_network_client_grpc_received_bytes_total',
- refId: 'A',
- step: 4,
- }],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'Client Traffic In',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'individual',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'Bps',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- ],
- },
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- editable: true,
- 'error': false,
- fill: 5,
- id: 21,
- isNew: true,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 3,
- stack: true,
- steppedLine: false,
- targets: [{
- expr: 'rate(etcd_network_client_grpc_sent_bytes_total{job="$cluster"}[5m])',
- intervalFactor: 2,
- legendFormat: '{{instance}} Client Traffic Out',
- metric: 'etcd_network_client_grpc_sent_bytes_total',
- refId: 'A',
- step: 4,
- }],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'Client Traffic Out',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'individual',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'Bps',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- ],
- },
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- editable: true,
- 'error': false,
- fill: 0,
- id: 20,
- isNew: true,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 3,
- stack: false,
- steppedLine: false,
- targets: [{
- expr: 'sum(rate(etcd_network_peer_received_bytes_total{job="$cluster"}[5m])) by (instance)',
- intervalFactor: 2,
- legendFormat: '{{instance}} Peer Traffic In',
- metric: 'etcd_network_peer_received_bytes_total',
- refId: 'A',
- step: 4,
- }],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'Peer Traffic In',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'individual',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'Bps',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- ],
- },
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- decimals: null,
- editable: true,
- 'error': false,
- fill: 0,
- grid: {},
- id: 16,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 3,
- stack: false,
- steppedLine: false,
- targets: [{
- expr: 'sum(rate(etcd_network_peer_sent_bytes_total{job="$cluster"}[5m])) by (instance)',
- hide: false,
- interval: '',
- intervalFactor: 2,
- legendFormat: '{{instance}} Peer Traffic Out',
- metric: 'etcd_network_peer_sent_bytes_total',
- refId: 'A',
- step: 4,
- }],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'Peer Traffic Out',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'cumulative',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'Bps',
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- ],
- },
- ],
- title: 'New row',
- },
- {
- collapse: false,
- editable: true,
- height: '250px',
- panels: [
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- editable: true,
- 'error': false,
- fill: 0,
- id: 40,
- isNew: true,
- legend: {
- avg: false,
- current: false,
- max: false,
- min: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 6,
- stack: false,
- steppedLine: false,
- targets: [
- {
- expr: 'sum(rate(etcd_server_proposals_failed_total{job="$cluster"}[5m]))',
- intervalFactor: 2,
- legendFormat: 'Proposal Failure Rate',
- metric: 'etcd_server_proposals_failed_total',
- refId: 'A',
- step: 2,
- },
- {
- expr: 'sum(etcd_server_proposals_pending{job="$cluster"})',
- intervalFactor: 2,
- legendFormat: 'Proposal Pending Total',
- metric: 'etcd_server_proposals_pending',
- refId: 'B',
- step: 2,
- },
- {
- expr: 'sum(rate(etcd_server_proposals_committed_total{job="$cluster"}[5m]))',
- intervalFactor: 2,
- legendFormat: 'Proposal Commit Rate',
- metric: 'etcd_server_proposals_committed_total',
- refId: 'C',
- step: 2,
- },
- {
- expr: 'sum(rate(etcd_server_proposals_applied_total{job="$cluster"}[5m]))',
- intervalFactor: 2,
- legendFormat: 'Proposal Apply Rate',
- refId: 'D',
- step: 2,
- },
- ],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'Raft Proposals',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'individual',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'short',
- label: '',
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- ],
- },
- {
- aliasColors: {},
- bars: false,
- datasource: '$datasource',
- decimals: 0,
- editable: true,
- 'error': false,
- fill: 0,
- id: 19,
- isNew: true,
- legend: {
- alignAsTable: false,
- avg: false,
- current: false,
- max: false,
- min: false,
- rightSide: false,
- show: false,
- total: false,
- values: false,
- },
- lines: true,
- linewidth: 2,
- links: [],
- nullPointMode: 'connected',
- percentage: false,
- pointradius: 5,
- points: false,
- renderer: 'flot',
- seriesOverrides: [],
- span: 6,
- stack: false,
- steppedLine: false,
- targets: [{
- expr: 'changes(etcd_server_leader_changes_seen_total{job="$cluster"}[1d])',
- intervalFactor: 2,
- legendFormat: '{{instance}} Total Leader Elections Per Day',
- metric: 'etcd_server_leader_changes_seen_total',
- refId: 'A',
- step: 2,
- }],
- thresholds: [],
- timeFrom: null,
- timeShift: null,
- title: 'Total Leader Elections Per Day',
- tooltip: {
- msResolution: false,
- shared: true,
- sort: 0,
- value_type: 'individual',
- },
- type: 'graph',
- xaxis: {
- mode: 'time',
- name: null,
- show: true,
- values: [],
- },
- yaxes: [
- {
- format: 'short',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- {
- format: 'short',
- label: null,
- logBase: 1,
- max: null,
- min: null,
- show: true,
- },
- ],
- },
- ],
- title: 'New row',
- },
- ],
- time: {
- from: 'now-15m',
- to: 'now',
- },
- timepicker: {
- now: true,
- refresh_intervals: [
- '5s',
- '10s',
- '30s',
- '1m',
- '5m',
- '15m',
- '30m',
- '1h',
- '2h',
- '1d',
- ],
- time_options: [
- '5m',
- '15m',
- '1h',
- '6h',
- '12h',
- '24h',
- '2d',
- '7d',
- '30d',
- ],
- },
- templating: {
- list: [
- {
- current: {
- text: 'Prometheus',
- value: 'Prometheus',
- },
- hide: 0,
- label: null,
- name: 'datasource',
- options: [],
- query: 'prometheus',
- refresh: 1,
- regex: '',
- type: 'datasource',
- },
- {
- allValue: null,
- current: {
- text: 'prod',
- value: 'prod',
- },
- datasource: '$datasource',
- hide: 0,
- includeAll: false,
- label: 'cluster',
- multi: false,
- name: 'cluster',
- options: [],
- query: 'label_values(etcd_server_has_leader, job)',
- refresh: 1,
- regex: '',
- sort: 2,
- tagValuesQuery: '',
- tags: [],
- tagsQuery: '',
- type: 'query',
- useTags: false,
- },
- ],
- },
- annotations: {
- list: [],
- },
- refresh: false,
- schemaVersion: 13,
- version: 215,
- links: [],
- gnetId: null,
- },
- },
- }
|