mirror of
https://github.com/ceph/ceph
synced 2024-12-19 01:46:00 +00:00
090b8e17f1
Rendering the dashboards with showMultiCluster=True allows for
them to work with multiple clusters storing their metrics in a single
Prometheus instance. This works via the cluster label and that functionality
already existed. This just fixes some inconsistencies in applying the label
filters.
Additionally this contains updates to the tests to have them succeed with
with both configurations and avoid the introduction of regressions in
regards to multiCluster in the future.
There also are some consistency cleanups here and there:
* `datasource` was not used consistently
* `cluster` label_values are determined from `ceph_health_status`
* `job` template and filters on this label were removed to align multi cluster
support solely via the `cluster` label
* `ceph_hosts` filter now uses label_values from any ceph_metadata metrici
to now show all instance values, but those of hosts with some Ceph
component / daemon.
* Enable showMultiCluster=True since `cluster` label is now always present,
via https://github.com/ceph/ceph/pull/54964
Improves: https://tracker.ceph.com/issues/64321
Signed-off-by: Christian Rohmann <christian.rohmann@inovex.de>
652 lines
19 KiB
JSON
652 lines
19 KiB
JSON
{
|
|
"__inputs": [ ],
|
|
"__requires": [
|
|
{
|
|
"id": "grafana",
|
|
"name": "Grafana",
|
|
"type": "grafana",
|
|
"version": "5.0.0"
|
|
},
|
|
{
|
|
"id": "grafana-piechart-panel",
|
|
"name": "Pie Chart",
|
|
"type": "panel",
|
|
"version": "1.3.3"
|
|
},
|
|
{
|
|
"id": "graph",
|
|
"name": "Graph",
|
|
"type": "panel",
|
|
"version": "5.0.0"
|
|
}
|
|
],
|
|
"annotations": {
|
|
"list": [
|
|
{
|
|
"builtIn": 1,
|
|
"datasource": "-- Grafana --",
|
|
"enable": true,
|
|
"hide": true,
|
|
"iconColor": "rgba(0, 211, 255, 1)",
|
|
"name": "Annotations & Alerts",
|
|
"showIn": 0,
|
|
"tags": [ ],
|
|
"type": "dashboard"
|
|
}
|
|
]
|
|
},
|
|
"description": "",
|
|
"editable": false,
|
|
"gnetId": null,
|
|
"graphTooltip": 0,
|
|
"hideControls": false,
|
|
"id": null,
|
|
"links": [ ],
|
|
"panels": [
|
|
{
|
|
"collapse": false,
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"id": 2,
|
|
"panels": [ ],
|
|
"repeat": null,
|
|
"repeatIteration": null,
|
|
"repeatRowId": null,
|
|
"showTitle": true,
|
|
"title": "RGW Host Detail : $rgw_servers",
|
|
"titleSize": "h6",
|
|
"type": "row"
|
|
},
|
|
{
|
|
"aliasColors": { },
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"description": "",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 8,
|
|
"showPoints": "never"
|
|
},
|
|
"unit": "s"
|
|
}
|
|
},
|
|
"fill": 1,
|
|
"fillGradient": 0,
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"id": 3,
|
|
"legend": {
|
|
"alignAsTable": false,
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"rightSide": false,
|
|
"show": true,
|
|
"sideWidth": null,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"repeat": null,
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (instance_id) (\n rate(ceph_rgw_op_get_obj_lat_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n rate(ceph_rgw_op_get_obj_lat_count{cluster=~\"$cluster\", }[$__rate_interval])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "GET {{ceph_daemon}}",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "sum by (instance_id) (\n rate(ceph_rgw_op_put_obj_lat_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n rate(ceph_rgw_op_put_obj_lat_count{cluster=~\"$cluster\", }[$__rate_interval])\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "PUT {{ceph_daemon}}",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "$rgw_servers GET/PUT Latencies",
|
|
"tooltip": {
|
|
"shared": true,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "timeseries",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "s",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"aliasColors": { },
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"description": "",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 8,
|
|
"showPoints": "never"
|
|
},
|
|
"unit": "bytes"
|
|
}
|
|
},
|
|
"fill": 1,
|
|
"fillGradient": 0,
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 7,
|
|
"x": 6,
|
|
"y": 1
|
|
},
|
|
"id": 4,
|
|
"legend": {
|
|
"alignAsTable": false,
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"rightSide": false,
|
|
"show": true,
|
|
"sideWidth": null,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"repeat": null,
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "rate(ceph_rgw_op_get_obj_bytes{cluster=~\"$cluster\", }[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "GETs {{ceph_daemon}}",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "rate(ceph_rgw_op_put_obj_bytes{cluster=~\"$cluster\", }[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon)\n ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "PUTs {{ceph_daemon}}",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Bandwidth by HTTP Operation",
|
|
"tooltip": {
|
|
"shared": true,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "timeseries",
|
|
"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": 0,
|
|
"show": true
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"aliasColors": {
|
|
"GETs": "#7eb26d",
|
|
"Other": "#447ebc",
|
|
"PUTs": "#eab839",
|
|
"Requests": "#3f2b5b",
|
|
"Requests Failed": "#bf1b00"
|
|
},
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"description": "",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"fillOpacity": 8,
|
|
"showPoints": "never"
|
|
},
|
|
"unit": "short"
|
|
}
|
|
},
|
|
"fill": 1,
|
|
"fillGradient": 0,
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 7,
|
|
"x": 13,
|
|
"y": 1
|
|
},
|
|
"id": 5,
|
|
"legend": {
|
|
"alignAsTable": false,
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"rightSide": false,
|
|
"show": true,
|
|
"sideWidth": null,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"repeat": null,
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "rate(ceph_rgw_failed_req{cluster=~\"$cluster\", }[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "Requests Failed {{ceph_daemon}}",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "rate(ceph_rgw_get{cluster=~\"$cluster\", }[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "GETs {{ceph_daemon}}",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "rate(ceph_rgw_put{cluster=~\"$cluster\", }[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "PUTs {{ceph_daemon}}",
|
|
"refId": "C"
|
|
},
|
|
{
|
|
"expr": "(\n rate(ceph_rgw_req{cluster=~\"$cluster\", }[$__rate_interval]) -\n (\n rate(ceph_rgw_get{cluster=~\"$cluster\", }[$__rate_interval]) +\n rate(ceph_rgw_put{cluster=~\"$cluster\", }[$__rate_interval])\n )\n) * on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "Other {{ceph_daemon}}",
|
|
"refId": "D"
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "HTTP Request Breakdown",
|
|
"tooltip": {
|
|
"shared": true,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "timeseries",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"datasource": "$datasource",
|
|
"description": "",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"hideFrom": {
|
|
"legend": false,
|
|
"tooltip": false,
|
|
"viz": false
|
|
}
|
|
},
|
|
"mappings": [ ]
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "Failures"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#bf1b00",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "GETs"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#7eb26d",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "Other (HEAD,POST,DELETE)"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#447ebc",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "PUTs"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#eab839",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "Requests"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"fixedColor": "#3f2b5b",
|
|
"mode": "fixed"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 4,
|
|
"x": 20,
|
|
"y": 1
|
|
},
|
|
"id": 6,
|
|
"options": {
|
|
"displayLabels": [ ],
|
|
"legend": {
|
|
"calcs": [ ],
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"showLegend": true,
|
|
"values": [
|
|
"percent",
|
|
"value"
|
|
]
|
|
},
|
|
"pieType": "pie",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"expr": "rate(ceph_rgw_failed_req{cluster=~\"$cluster\", }[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "Failures {{ceph_daemon}}",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "rate(ceph_rgw_get{cluster=~\"$cluster\", }[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "GETs {{ceph_daemon}}",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "rate(ceph_rgw_put{cluster=~\"$cluster\", }[$__rate_interval]) *\n on (instance_id) group_left (ceph_daemon) ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "PUTs {{ceph_daemon}}",
|
|
"refId": "C"
|
|
},
|
|
{
|
|
"expr": "(\n rate(ceph_rgw_req{cluster=~\"$cluster\", }[$__rate_interval]) -\n (\n rate(ceph_rgw_get{cluster=~\"$cluster\", }[$__rate_interval]) +\n rate(ceph_rgw_put{cluster=~\"$cluster\", }[$__rate_interval])\n )\n) * on (instance_id) group_left (ceph_daemon)\n ceph_rgw_metadata{ceph_daemon=~\"$rgw_servers\", cluster=~\"$cluster\", }\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 1,
|
|
"legendFormat": "Other (DELETE,LIST) {{ceph_daemon}}",
|
|
"refId": "D"
|
|
}
|
|
],
|
|
"title": "Workload Breakdown",
|
|
"type": "piechart"
|
|
}
|
|
],
|
|
"refresh": "30s",
|
|
"rows": [ ],
|
|
"schemaVersion": 16,
|
|
"style": "dark",
|
|
"tags": [
|
|
"ceph-mixin",
|
|
"overview"
|
|
],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"current": {
|
|
"text": "default",
|
|
"value": "default"
|
|
},
|
|
"hide": 0,
|
|
"label": "Data Source",
|
|
"name": "datasource",
|
|
"options": [ ],
|
|
"query": "prometheus",
|
|
"refresh": 1,
|
|
"regex": "",
|
|
"type": "datasource"
|
|
},
|
|
{
|
|
"allValue": null,
|
|
"current": { },
|
|
"datasource": "$datasource",
|
|
"hide": 0,
|
|
"includeAll": false,
|
|
"label": "cluster",
|
|
"multi": false,
|
|
"name": "cluster",
|
|
"options": [ ],
|
|
"query": "label_values(ceph_health_status, cluster)",
|
|
"refresh": 1,
|
|
"regex": "(.*)",
|
|
"sort": 1,
|
|
"tagValuesQuery": "",
|
|
"tags": [ ],
|
|
"tagsQuery": "",
|
|
"type": "query",
|
|
"useTags": false
|
|
},
|
|
{
|
|
"allValue": null,
|
|
"current": { },
|
|
"datasource": "$datasource",
|
|
"hide": 0,
|
|
"includeAll": true,
|
|
"label": "",
|
|
"multi": false,
|
|
"name": "rgw_servers",
|
|
"options": [ ],
|
|
"query": "label_values(ceph_rgw_metadata{cluster=~\"$cluster\", }, ceph_daemon)",
|
|
"refresh": 1,
|
|
"regex": "",
|
|
"sort": 1,
|
|
"tagValuesQuery": "",
|
|
"tags": [ ],
|
|
"tagsQuery": "",
|
|
"type": "query",
|
|
"useTags": false
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {
|
|
"refresh_intervals": [
|
|
"5s",
|
|
"10s",
|
|
"30s",
|
|
"1m",
|
|
"5m",
|
|
"15m",
|
|
"30m",
|
|
"1h",
|
|
"2h",
|
|
"1d"
|
|
],
|
|
"time_options": [
|
|
"5m",
|
|
"15m",
|
|
"1h",
|
|
"6h",
|
|
"12h",
|
|
"24h",
|
|
"2d",
|
|
"7d",
|
|
"30d"
|
|
]
|
|
},
|
|
"timezone": "",
|
|
"title": "RGW Instance Detail",
|
|
"uid": "x5ARzZtmk",
|
|
"version": 0
|
|
}
|