Files
zrepl_patched/dist/grafana/grafana-prometheus-zrepl.json
T
Christian Schwarz e391fa94f9 dist/grafana: update grafana dashboard
- uses version metric for 'instances up'
- displays active task count
- displays send abstractions cache entry count
- in general, graphs have a shorter y axis for better overview

fixes #332
2020-06-14 15:26:05 +02:00

1081 lines
32 KiB
JSON

{
"__inputs": [{
"name": "DS_PROMETHEUS",
"label": "prometheus",
"description": "",
"type": "datasource",
"pluginId": "prometheus",
"pluginName": "Prometheus"
}],
"__requires": [{
"type": "grafana",
"id": "grafana",
"name": "Grafana",
"version": "7.0.3"
},
{
"type": "panel",
"id": "graph",
"name": "Graph",
"version": ""
},
{
"type": "datasource",
"id": "prometheus",
"name": "Prometheus",
"version": "1.0.0"
},
{
"type": "panel",
"id": "text",
"name": "Text",
"version": ""
}
],
"annotations": {
"list": [{
"builtIn": 1,
"datasource": "-- Grafana --",
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}]
},
"editable": true,
"gnetId": null,
"graphTooltip": 1,
"id": null,
"iteration": 1591876836041,
"links": [],
"panels": [{
"content": "# zrepl Prometheus Metrics\n\nzrepl exposes Prometheus metrics and ships with this Grafana dashboard.\nThe exported metrics are suitable for health checks:\n\n* The log should generally be warning & error-free\n * The `Log Messages that require attention` graph visualizes log message at levels that generally indicate problems.\n* The number of goroutines should not grow unboundedly over time.\n * During replication, the number of goroutines can be way higher than during idle time.\n * If the goroutine count grows with each replication, there is clearly a goroutine leak. Please open a bug report.\n* Memory consumption should not grow unboundedly over time.\n * Note that the Go runtime pre-allocates some of its heap from the OS.\n * zrepl actually uses much less memory than allocated from the OS.\n * Since Go 1.11, Go pre-allocates more aggressively.\n* Monitor that some data is replicated, although that metric does not guarantee that replication was successful.\n\n**In general, note that the exported metrics are not stable unless declared otherwise.**",
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"gridPos": {
"h": 10,
"w": 24,
"x": 0,
"y": 0
},
"id": 35,
"mode": "markdown",
"title": "Panel Title",
"type": "text"
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 4,
"w": 12,
"x": 0,
"y": 10
},
"hiddenSeries": false,
"id": 48,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": true,
"steppedLine": false,
"targets": [{
"expr": "zrepl_version_daemon{job='$prom_job_name'}",
"format": "time_series",
"interval": "",
"intervalFactor": 1,
"legendFormat": "{{instance}}@version={{raw}}",
"refId": "A"
}],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "zrepl Instances Up",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [{
"format": "short",
"label": null,
"logBase": 1,
"max": "5",
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 5,
"w": 12,
"x": 12,
"y": 10
},
"hiddenSeries": false,
"id": 44,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [{
"expr": "zrepl_trace_active_tasks",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "active tasks tracked by the zrepl trace module (should not grow unboundedly)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"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
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": true,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 5,
"w": 12,
"x": 0,
"y": 14
},
"hiddenSeries": false,
"id": 42,
"legend": {
"alignAsTable": false,
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": false,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [{
"alias": "/replicated bytes in last.*/",
"yaxis": 2
}],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [{
"expr": "sum(increase(zrepl_replication_bytes_replicated{job='$prom_job_name'}[1d])) by (zrepl_job)",
"format": "time_series",
"hide": false,
"instant": false,
"interval": "1d",
"intervalFactor": 1,
"legendFormat": "zrepl_job={{zrepl_job}}",
"refId": "B"
}],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Daily Replication Data Volume",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": false
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 4,
"w": 12,
"x": 12,
"y": 15
},
"hiddenSeries": false,
"id": 22,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [{
"expr": "increase(zrepl_daemon_log_entries{job='$prom_job_name',level=~'warn|error'}[1m])",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Log Messages that require attention",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 5,
"w": 12,
"x": 0,
"y": 19
},
"hiddenSeries": false,
"id": 33,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [{
"alias": "/replicated bytes in last.*/",
"yaxis": 2
}],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [{
"expr": "sum(rate(zrepl_replication_bytes_replicated{job='$prom_job_name'}[10m])) by (zrepl_job)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "replication data ratein last 10min zrepl_job={{zrepl_job}}te zrepl_job={{zrepl_job}}",
"refId": "A"
},
{
"expr": "sum(increase(zrepl_replication_bytes_replicated{job='$prom_job_name'}[10m])) by (zrepl_job)",
"format": "time_series",
"hide": false,
"interval": "",
"intervalFactor": 1,
"legendFormat": "replicated bytes in last 10min zrepl_job={{zrepl_job}}",
"refId": "B"
}
],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Replication Data Rate and Volume(over last 10min)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [{
"format": "Bps",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 5,
"w": 12,
"x": 12,
"y": 19
},
"hiddenSeries": false,
"id": 23,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [{
"expr": "sum(increase(zrepl_daemon_log_entries{job='$prom_job_name',zrepl_job=~\"^[^_].*\"}[1m])) by (instance,zrepl_job)",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Log Activity (without internal jobs)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 5,
"w": 12,
"x": 0,
"y": 24
},
"hiddenSeries": false,
"id": 41,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"rightSide": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [{
"expr": "go_memstats_alloc_bytes{job='$prom_job_name'}",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Go Memory Allocations (should not grow unboundedly)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
},
{
"format": "short",
"label": "",
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 5,
"w": 12,
"x": 12,
"y": 24
},
"hiddenSeries": false,
"id": 47,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [{
"expr": "zrepl_endpoint_send_abstractions_cache_entry_count",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "send abstractions cache entry count (should not be zero and not grow unboundedly)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"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
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 5,
"w": 12,
"x": 0,
"y": 29
},
"hiddenSeries": false,
"id": 17,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [{
"expr": "go_memstats_sys_bytes{job='$prom_job_name'}",
"format": "time_series",
"hide": false,
"intervalFactor": 1,
"refId": "A"
}],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "Memory Allocated by the Go runtime from the OS (should not grow unboundedly)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [{
"format": "bytes",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
},
{
"aliasColors": {},
"bars": false,
"dashLength": 10,
"dashes": false,
"datasource": "${DS_PROMETHEUS}",
"fieldConfig": {
"defaults": {
"custom": {}
},
"overrides": []
},
"fill": 1,
"fillGradient": 0,
"gridPos": {
"h": 5,
"w": 12,
"x": 0,
"y": 34
},
"hiddenSeries": false,
"id": 19,
"legend": {
"avg": false,
"current": false,
"max": false,
"min": false,
"show": true,
"total": false,
"values": false
},
"lines": true,
"linewidth": 1,
"links": [],
"nullPointMode": "null",
"options": {
"dataLinks": []
},
"percentage": false,
"pointradius": 5,
"points": false,
"renderer": "flot",
"seriesOverrides": [],
"spaceLength": 10,
"stack": false,
"steppedLine": false,
"targets": [{
"expr": "go_goroutines{job='$prom_job_name'}",
"format": "time_series",
"intervalFactor": 1,
"refId": "A"
}],
"thresholds": [],
"timeFrom": null,
"timeRegions": [],
"timeShift": null,
"title": "number of goroutines (should not grow unboundedly)",
"tooltip": {
"shared": true,
"sort": 0,
"value_type": "individual"
},
"type": "graph",
"xaxis": {
"buckets": null,
"mode": "time",
"name": null,
"show": true,
"values": []
},
"yaxes": [{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": "0",
"show": true
},
{
"format": "short",
"label": null,
"logBase": 1,
"max": null,
"min": null,
"show": true
}
],
"yaxis": {
"align": false,
"alignLevel": null
}
}
],
"refresh": "5s",
"schemaVersion": 25,
"style": "dark",
"tags": [],
"templating": {
"list": [{
"allValue": null,
"current": {},
"datasource": "${DS_PROMETHEUS}",
"definition": "",
"hide": 0,
"includeAll": false,
"label": "Prometheus Job Name",
"multi": false,
"name": "prom_job_name",
"options": [],
"query": "label_values(up, job)",
"refresh": 1,
"regex": "",
"skipUrlSync": false,
"sort": 1,
"tagValuesQuery": "",
"tags": [],
"tagsQuery": "",
"type": "query",
"useTags": false
}]
},
"time": {
"from": "now-2d",
"to": "now"
},
"timepicker": {
"refresh_intervals": [
"10s",
"30s",
"1m",
"5m",
"15m",
"30m",
"1h",
"2h",
"1d"
],
"time_options": [
"5m",
"15m",
"1h",
"6h",
"12h",
"24h",
"2d",
"7d",
"30d"
]
},
"timezone": "",
"title": "zrepl 0.3",
"uid": "etJuvBmGz",
"version": 6
}