Files
terraform-aws-observability…/workloads/infra/dashboards/etcd.json
T
2022-08-26 17:30:03 +02:00

1269 lines
31 KiB
JSON

{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"description": "etcd sample Grafana dashboard with Prometheus",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 14,
"iteration": 1656211137656,
"links": [],
"liveNow": false,
"panels": [
{
"datasource": {
"uid": "$datasource"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"match": "null",
"result": {
"text": "N/A"
}
},
"type": "special"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
},
"unit": "none"
},
"overrides": []
},
"gridPos": {
"h": 7,
"w": 6,
"x": 0,
"y": 0
},
"id": 28,
"links": [],
"maxDataPoints": 100,
"options": {
"colorMode": "none",
"graphMode": "none",
"justifyMode": "auto",
"orientation": "horizontal",
"reduceOptions": {
"calcs": [
"mean"
],
"fields": "",
"values": false
},
"textMode": "auto"
},
"pluginVersion": "9.0.1",
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(etcd_server_has_leader{job=\"$cluster\"})",
"intervalFactor": 2,
"legendFormat": "",
"metric": "etcd_server_has_leader",
"refId": "A",
"step": 20
}
],
"title": "Up",
"type": "stat"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 10,
"x": 6,
"y": 0
},
"hiddenSeries": false,
"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",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(rate(grpc_server_started_total{job=\"$cluster\",grpc_type=\"unary\"}[5m]))",
"format": "time_series",
"intervalFactor": 2,
"legendFormat": "RPC Rate",
"metric": "grpc_server_started_total",
"refId": "A",
"step": 2
},
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(rate(grpc_server_handled_total{job=\"$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": [],
"timeRegions": [],
"title": "RPC Rate",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "ops",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 0
},
"hiddenSeries": false,
"id": 41,
"isNew": true,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"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
},
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(grpc_server_started_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"}) - sum(grpc_server_handled_total{job=\"$cluster\",grpc_service=\"etcdserverpb.Lease\",grpc_type=\"bidi_stream\"})",
"intervalFactor": 2,
"legendFormat": "Lease Streams",
"metric": "grpc_server_handled_total",
"refId": "B",
"step": 4
}
],
"thresholds": [],
"timeRegions": [],
"title": "Active Streams",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": "",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 0,
"fillGradient": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 8,
"x": 0,
"y": 7
},
"hiddenSeries": false,
"id": 1,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "etcd_mvcc_db_total_size_in_bytes{job=\"$cluster\"}",
"hide": false,
"interval": "",
"intervalFactor": 2,
"legendFormat": "{{instance}} DB Size",
"metric": "",
"refId": "A",
"step": 4
}
],
"thresholds": [],
"timeRegions": [],
"title": "DB Size",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": false
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 0,
"fillGradient": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 8,
"x": 8,
"y": 7
},
"hiddenSeries": false,
"id": 3,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 1,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": true,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "histogram_quantile(0.99, sum(rate(etcd_disk_wal_fsync_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))",
"hide": false,
"intervalFactor": 2,
"legendFormat": "{{instance}} WAL fsync",
"metric": "etcd_disk_wal_fsync_duration_seconds_bucket",
"refId": "A",
"step": 4
},
{
"datasource": {
"uid": "$datasource"
},
"expr": "histogram_quantile(0.99, sum(rate(etcd_disk_backend_commit_duration_seconds_bucket{job=\"$cluster\"}[5m])) by (instance, le))",
"intervalFactor": 2,
"legendFormat": "{{instance}} DB fsync",
"metric": "etcd_disk_backend_commit_duration_seconds_bucket",
"refId": "B",
"step": 4
}
],
"thresholds": [],
"timeRegions": [],
"title": "Disk Sync Duration",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "s",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": false
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 8,
"x": 16,
"y": 7
},
"hiddenSeries": false,
"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",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "process_resident_memory_bytes{job=\"$cluster\"}",
"intervalFactor": 2,
"legendFormat": "{{instance}} Resident Memory",
"metric": "process_resident_memory_bytes",
"refId": "A",
"step": 4
}
],
"thresholds": [],
"timeRegions": [],
"title": "Memory",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "bytes",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 5,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 6,
"x": 0,
"y": 14
},
"hiddenSeries": false,
"id": 22,
"isNew": true,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "rate(etcd_network_client_grpc_received_bytes_total{job=\"$cluster\"}[5m])",
"intervalFactor": 2,
"legendFormat": "{{instance}} Client Traffic In",
"metric": "etcd_network_client_grpc_received_bytes_total",
"refId": "A",
"step": 4
}
],
"thresholds": [],
"timeRegions": [],
"title": "Client Traffic In",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "Bps",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 5,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 6,
"x": 6,
"y": 14
},
"hiddenSeries": false,
"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",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "rate(etcd_network_client_grpc_sent_bytes_total{job=\"$cluster\"}[5m])",
"intervalFactor": 2,
"legendFormat": "{{instance}} Client Traffic Out",
"metric": "etcd_network_client_grpc_sent_bytes_total",
"refId": "A",
"step": 4
}
],
"thresholds": [],
"timeRegions": [],
"title": "Client Traffic Out",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "Bps",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 6,
"x": 12,
"y": 14
},
"hiddenSeries": false,
"id": 20,
"isNew": true,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(rate(etcd_network_peer_received_bytes_total{job=\"$cluster\"}[5m])) by (instance)",
"intervalFactor": 2,
"legendFormat": "{{instance}} Peer Traffic In",
"metric": "etcd_network_peer_received_bytes_total",
"refId": "A",
"step": 4
}
],
"thresholds": [],
"timeRegions": [],
"title": "Peer Traffic In",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "Bps",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 0,
"fillGradient": 0,
"grid": {},
"gridPos": {
"h": 7,
"w": 6,
"x": 18,
"y": 14
},
"hiddenSeries": false,
"id": 16,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(rate(etcd_network_peer_sent_bytes_total{job=\"$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": [],
"timeRegions": [],
"title": "Peer Traffic Out",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "cumulative"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "Bps",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"editable": true,
"error": false,
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 0,
"y": 21
},
"hiddenSeries": false,
"id": 40,
"isNew": true,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": false,
"total": false,
"values": false
},
"lines": true,
"linewidth": 2,
"links": [],
"nullPointMode": "connected",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(rate(etcd_server_proposals_failed_total{job=\"$cluster\"}[5m]))",
"intervalFactor": 2,
"legendFormat": "Proposal Failure Rate",
"metric": "etcd_server_proposals_failed_total",
"refId": "A",
"step": 2
},
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(etcd_server_proposals_pending{job=\"$cluster\"})",
"intervalFactor": 2,
"legendFormat": "Proposal Pending Total",
"metric": "etcd_server_proposals_pending",
"refId": "B",
"step": 2
},
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(rate(etcd_server_proposals_committed_total{job=\"$cluster\"}[5m]))",
"intervalFactor": 2,
"legendFormat": "Proposal Commit Rate",
"metric": "etcd_server_proposals_committed_total",
"refId": "C",
"step": 2
},
{
"datasource": {
"uid": "$datasource"
},
"expr": "sum(rate(etcd_server_proposals_applied_total{job=\"$cluster\"}[5m]))",
"intervalFactor": 2,
"legendFormat": "Proposal Apply Rate",
"refId": "D",
"step": 2
}
],
"thresholds": [],
"timeRegions": [],
"title": "Raft Proposals",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"label": "",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": {
"uid": "$datasource"
},
"decimals": 0,
"editable": true,
"error": false,
"fill": 0,
"fillGradient": 0,
"gridPos": {
"h": 7,
"w": 12,
"x": 12,
"y": 21
},
"hiddenSeries": false,
"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",
"options": {
"alertThreshold": true
},
"percentage": false,
"pluginVersion": "9.0.1",
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [
{
"datasource": {
"uid": "$datasource"
},
"expr": "changes(etcd_server_leader_changes_seen_total{job=\"$cluster\"}[1d])",
"intervalFactor": 2,
"legendFormat": "{{instance}} Total Leader Elections Per Day",
"metric": "etcd_server_leader_changes_seen_total",
"refId": "A",
"step": 2
}
],
"thresholds": [],
"timeRegions": [],
"title": "Total Leader Elections Per Day",
"tooltip": {
"msResolution": false,
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"mode": "time",
"show": true,
"values": []
},
"yaxes": [
{
"format": "short",
"logBase": 1,
"show": true
},
{
"format": "short",
"logBase": 1,
"show": true
}
],
"yaxis": {
"align": false
}
}
],
"refresh": "10s",
"schemaVersion": 36,
"style": "dark",
"tags": [],
"templating": {
"list": [
{
"current": {
"selected": false,
"text": "Prometheus",
"value": "Prometheus"
},
"hide": 0,
"includeAll": false,
"multi": false,
"name": "datasource",
"options": [],
"query": "prometheus",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"type": "datasource"
},
{
"current": {
"isNone": true,
"selected": false,
"text": "None",
"value": ""
},
"datasource": {
"type": "prometheus",
"uid": "$datasource"
},
"definition": "",
"hide": 2,
"includeAll": false,
"label": "cluster",
"multi": false,
"name": "cluster",
"options": [],
"query": {
"query": "label_values(etcd_server_has_leader, job)",
"refId": "Prometheus-cluster-Variable-Query"
},
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 2,
"tagValuesQuery": "",
"tagsQuery": "",
"type": "query",
"useTags": false
}
]
},
"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"
]
},
"timezone": "utc",
"title": "etcd",
"uid": "c2f4e12cdf69feb95caa41a5a1b423d9",
"version": 1,
"weekStart": ""
}