1177 lines
45 KiB
JSON
1177 lines
45 KiB
JSON
{
|
|
"__requires": [
|
|
{
|
|
"id": "grafana",
|
|
"name": "Grafana",
|
|
"type": "grafana",
|
|
"version": "8.0.0"
|
|
}
|
|
],
|
|
"annotations": {
|
|
"list": [ ]
|
|
},
|
|
"editable": true,
|
|
"gnetId": null,
|
|
"graphTooltip": 1,
|
|
"hideControls": false,
|
|
"links": [
|
|
{
|
|
"asDropdown": true,
|
|
"icon": "external link",
|
|
"includeVars": true,
|
|
"keepTime": true,
|
|
"tags": [
|
|
"mimir"
|
|
],
|
|
"targetBlank": false,
|
|
"title": "Mimir dashboards",
|
|
"type": "dashboards"
|
|
}
|
|
],
|
|
"refresh": "10s",
|
|
"rows": [
|
|
{
|
|
"collapse": false,
|
|
"height": "175px",
|
|
"panels": [
|
|
{
|
|
"content": "<p>\n This dashboard shows health metrics for the ruler read path when remote operational mode is enabled.\n It is broken into sections for each service on the ruler read path, and organized by the order in which the read request flows.\n <br/>\n For each service, there are three panels showing (1) requests per second to that service, (2) average, median, and p99 latency of requests to that service, and (3) p99 latency of requests to each instance of that service.\n</p>\n",
|
|
"datasource": null,
|
|
"description": "",
|
|
"id": 1,
|
|
"mode": "markdown",
|
|
"span": 12,
|
|
"title": "",
|
|
"transparent": true,
|
|
"type": "text"
|
|
}
|
|
],
|
|
"repeat": null,
|
|
"repeatIteration": null,
|
|
"repeatRowId": null,
|
|
"showTitle": false,
|
|
"title": "Remote ruler reads dashboard description",
|
|
"titleSize": "h6"
|
|
},
|
|
{
|
|
"collapse": false,
|
|
"height": "100px",
|
|
"panels": [
|
|
{
|
|
"aliasColors": { },
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"description": "### Evaluations per second\nRate of rule expressions evaluated per second.\n\n",
|
|
"fill": 1,
|
|
"format": "reqps",
|
|
"id": 2,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"span": 12,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "sum(\n rate(\n cortex_request_duration_seconds_count{\n cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\",\n route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"\n }[$__rate_interval]\n )\n)\n",
|
|
"format": "time_series",
|
|
"instant": true,
|
|
"intervalFactor": 2,
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"thresholds": "70,80",
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Evaluations / sec",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "singlestat",
|
|
"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": false
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"repeat": null,
|
|
"repeatIteration": null,
|
|
"repeatRowId": null,
|
|
"showTitle": false,
|
|
"title": "Headlines",
|
|
"titleSize": "h6"
|
|
},
|
|
{
|
|
"collapse": false,
|
|
"height": "250px",
|
|
"panels": [
|
|
{
|
|
"aliasColors": {
|
|
"1xx": "#EAB839",
|
|
"2xx": "#7EB26D",
|
|
"3xx": "#6ED0E0",
|
|
"4xx": "#EF843C",
|
|
"5xx": "#E24D42",
|
|
"cancel": "#A9A9A9",
|
|
"error": "#E24D42",
|
|
"success": "#7EB26D"
|
|
},
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"fill": 10,
|
|
"id": 3,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 0,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"span": 4,
|
|
"stack": true,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "{{status}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Requests / sec",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "graph",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "reqps",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": null,
|
|
"show": false
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"aliasColors": { },
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"fill": 1,
|
|
"id": 4,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"span": 4,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})) * 1e3",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "99th Percentile",
|
|
"refId": "A",
|
|
"step": 10
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})) * 1e3",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "50th Percentile",
|
|
"refId": "B",
|
|
"step": 10
|
|
},
|
|
{
|
|
"expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}) / sum(cluster_job_route:cortex_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "Average",
|
|
"refId": "C",
|
|
"step": 10
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Latency",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "graph",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "ms",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": null,
|
|
"show": false
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"datasource": "$datasource",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"fillOpacity": 0,
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
}
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [ ]
|
|
},
|
|
"unit": "s"
|
|
},
|
|
"overrides": [ ]
|
|
},
|
|
"id": 5,
|
|
"links": [ ],
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"span": 4,
|
|
"targets": [
|
|
{
|
|
"exemplar": true,
|
|
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"}[$__rate_interval])))",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "",
|
|
"legendLink": null
|
|
}
|
|
],
|
|
"title": "Per pod p99 latency",
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"repeat": null,
|
|
"repeatIteration": null,
|
|
"repeatRowId": null,
|
|
"showTitle": true,
|
|
"title": "Query-frontend (dedicated to ruler)",
|
|
"titleSize": "h6"
|
|
},
|
|
{
|
|
"collapse": false,
|
|
"height": "250px",
|
|
"panels": [
|
|
{
|
|
"aliasColors": {
|
|
"1xx": "#EAB839",
|
|
"2xx": "#7EB26D",
|
|
"3xx": "#6ED0E0",
|
|
"4xx": "#EF843C",
|
|
"5xx": "#E24D42",
|
|
"cancel": "#A9A9A9",
|
|
"error": "#E24D42",
|
|
"success": "#7EB26D"
|
|
},
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"fill": 10,
|
|
"id": 6,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 0,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"span": 6,
|
|
"stack": true,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "{{status}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Requests / sec",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "graph",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "reqps",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": null,
|
|
"show": false
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"aliasColors": { },
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"fill": 1,
|
|
"id": 7,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"span": 6,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "99th Percentile",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le)) * 1e3",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "50th Percentile",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"expr": "sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval]))",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "Average",
|
|
"refId": "C"
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Latency (time in queue)",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "graph",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "ms",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": null,
|
|
"show": false
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"repeat": null,
|
|
"repeatIteration": null,
|
|
"repeatRowId": null,
|
|
"showTitle": true,
|
|
"title": "Query-scheduler (dedicated to ruler)",
|
|
"titleSize": "h6"
|
|
},
|
|
{
|
|
"collapse": false,
|
|
"height": "250px",
|
|
"panels": [
|
|
{
|
|
"aliasColors": {
|
|
"1xx": "#EAB839",
|
|
"2xx": "#7EB26D",
|
|
"3xx": "#6ED0E0",
|
|
"4xx": "#EF843C",
|
|
"5xx": "#E24D42",
|
|
"cancel": "#A9A9A9",
|
|
"error": "#E24D42",
|
|
"success": "#7EB26D"
|
|
},
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"fill": 10,
|
|
"id": 8,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 0,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"span": 4,
|
|
"stack": true,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_querier_request_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval]),\n \"status\", \"${1}xx\", \"status_code\", \"([0-9])..\"),\n \"status\", \"${1}\", \"status_code\", \"([a-z]+)\"))\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "{{status}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Requests / sec",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "graph",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "reqps",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": null,
|
|
"show": false
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"aliasColors": { },
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"fill": 1,
|
|
"id": 9,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"span": 4,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "99th Percentile",
|
|
"refId": "A",
|
|
"step": 10
|
|
},
|
|
{
|
|
"expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_querier_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})) * 1e3",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "50th Percentile",
|
|
"refId": "B",
|
|
"step": 10
|
|
},
|
|
{
|
|
"expr": "1e3 * sum(cluster_job_route:cortex_querier_request_duration_seconds_sum:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}) / sum(cluster_job_route:cortex_querier_request_duration_seconds_count:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"})",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "Average",
|
|
"refId": "C",
|
|
"step": 10
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Latency",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "graph",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "ms",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": null,
|
|
"show": false
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"datasource": "$datasource",
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"fillOpacity": 0,
|
|
"lineWidth": 1,
|
|
"pointSize": 5,
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"stacking": {
|
|
"group": "A",
|
|
"mode": "none"
|
|
}
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [ ]
|
|
},
|
|
"unit": "s"
|
|
},
|
|
"overrides": [ ]
|
|
},
|
|
"id": 10,
|
|
"links": [ ],
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "hidden",
|
|
"showLegend": false
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"span": 4,
|
|
"targets": [
|
|
{
|
|
"exemplar": true,
|
|
"expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "",
|
|
"legendLink": null
|
|
}
|
|
],
|
|
"title": "Per pod p99 latency",
|
|
"type": "timeseries"
|
|
}
|
|
],
|
|
"repeat": null,
|
|
"repeatIteration": null,
|
|
"repeatRowId": null,
|
|
"showTitle": true,
|
|
"title": "Querier (dedicated to ruler)",
|
|
"titleSize": "h6"
|
|
},
|
|
{
|
|
"collapse": false,
|
|
"height": "250px",
|
|
"panels": [
|
|
{
|
|
"aliasColors": { },
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"description": "### Replicas\nThe minimum, maximum, and current number of querier replicas.\n\n",
|
|
"fill": 1,
|
|
"id": 11,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"span": 4,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "kube_horizontalpodautoscaler_spec_min_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=\"keda-hpa-ruler-querier\"}",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "Min",
|
|
"legendLink": null
|
|
},
|
|
{
|
|
"expr": "kube_horizontalpodautoscaler_spec_max_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=\"keda-hpa-ruler-querier\"}",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "Max",
|
|
"legendLink": null
|
|
},
|
|
{
|
|
"expr": "kube_horizontalpodautoscaler_status_current_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=\"keda-hpa-ruler-querier\"}",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "Current",
|
|
"legendLink": null
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Replicas",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"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": false
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"aliasColors": { },
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"description": "### Scaling metric\nThis panel shows the result of the query that is used as the scaling metric, and the target and threshold used.\nThe desired number of replicas is computed by HPA as: <scaling metric> / <target per replica>.\n\n",
|
|
"fill": 1,
|
|
"id": 12,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [
|
|
{
|
|
"alias": "Target per replica",
|
|
"yaxis": 2
|
|
}
|
|
],
|
|
"spaceLength": 10,
|
|
"span": 4,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "keda_metrics_adapter_scaler_metrics_value +\non(metric) group_left\nlabel_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n * 0, \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "Scaling metric",
|
|
"legendLink": null
|
|
},
|
|
{
|
|
"expr": "kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=\"keda-hpa-ruler-querier\"}",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "Target per replica",
|
|
"legendLink": null
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Scaling metric",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "graph",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": null,
|
|
"show": true
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"aliasColors": { },
|
|
"bars": false,
|
|
"dashLength": 10,
|
|
"dashes": false,
|
|
"datasource": "$datasource",
|
|
"description": "### Autoscaler failures rate\nThe rate of failures in the KEDA custom metrics API server. Whenever an error occurs, the KEDA custom\nmetrics server is unable to query the scaling metric from Prometheus so the autoscaler does not work properly.\n\n",
|
|
"fill": 1,
|
|
"id": 13,
|
|
"legend": {
|
|
"avg": false,
|
|
"current": false,
|
|
"max": false,
|
|
"min": false,
|
|
"show": true,
|
|
"total": false,
|
|
"values": false
|
|
},
|
|
"lines": true,
|
|
"linewidth": 1,
|
|
"links": [ ],
|
|
"nullPointMode": "null as zero",
|
|
"percentage": false,
|
|
"pointradius": 5,
|
|
"points": false,
|
|
"renderer": "flot",
|
|
"seriesOverrides": [ ],
|
|
"spaceLength": 10,
|
|
"span": 4,
|
|
"stack": false,
|
|
"steppedLine": false,
|
|
"targets": [
|
|
{
|
|
"expr": "sum by(metric) (rate(keda_metrics_adapter_scaler_errors[$__rate_interval])) +\non(metric) group_left\nlabel_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n * 0, \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n",
|
|
"format": "time_series",
|
|
"intervalFactor": 2,
|
|
"legendFormat": "{{metric}} failures",
|
|
"legendLink": null
|
|
}
|
|
],
|
|
"thresholds": [ ],
|
|
"timeFrom": null,
|
|
"timeShift": null,
|
|
"title": "Autoscaler failures rate",
|
|
"tooltip": {
|
|
"shared": false,
|
|
"sort": 0,
|
|
"value_type": "individual"
|
|
},
|
|
"type": "graph",
|
|
"xaxis": {
|
|
"buckets": null,
|
|
"mode": "time",
|
|
"name": null,
|
|
"show": true,
|
|
"values": [ ]
|
|
},
|
|
"yaxes": [
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": 0,
|
|
"show": true
|
|
},
|
|
{
|
|
"format": "short",
|
|
"label": null,
|
|
"logBase": 1,
|
|
"max": null,
|
|
"min": null,
|
|
"show": false
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"repeat": null,
|
|
"repeatIteration": null,
|
|
"repeatRowId": null,
|
|
"showTitle": true,
|
|
"title": "Querier (dedicated to ruler) - autoscaling",
|
|
"titleSize": "h6"
|
|
}
|
|
],
|
|
"schemaVersion": 14,
|
|
"style": "dark",
|
|
"tags": [
|
|
"mimir"
|
|
],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"current": {
|
|
"text": "default",
|
|
"value": "default"
|
|
},
|
|
"hide": 0,
|
|
"label": "Data Source",
|
|
"name": "datasource",
|
|
"options": [ ],
|
|
"query": "prometheus",
|
|
"refresh": 1,
|
|
"regex": "",
|
|
"type": "datasource"
|
|
},
|
|
{
|
|
"allValue": ".+",
|
|
"current": {
|
|
"selected": true,
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"datasource": "$datasource",
|
|
"hide": 0,
|
|
"includeAll": true,
|
|
"label": "cluster",
|
|
"multi": true,
|
|
"name": "cluster",
|
|
"options": [ ],
|
|
"query": "label_values(cortex_build_info, cluster)",
|
|
"refresh": 1,
|
|
"regex": "",
|
|
"sort": 1,
|
|
"tagValuesQuery": "",
|
|
"tags": [ ],
|
|
"tagsQuery": "",
|
|
"type": "query",
|
|
"useTags": false
|
|
},
|
|
{
|
|
"allValue": ".+",
|
|
"current": {
|
|
"selected": true,
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"datasource": "$datasource",
|
|
"hide": 0,
|
|
"includeAll": true,
|
|
"label": "namespace",
|
|
"multi": true,
|
|
"name": "namespace",
|
|
"options": [ ],
|
|
"query": "label_values(cortex_build_info{cluster=~\"$cluster\"}, namespace)",
|
|
"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": "utc",
|
|
"title": "Mimir / Remote ruler reads",
|
|
"uid": "f103238f7f5ab2f1345ce650cbfbfe2f",
|
|
"version": 0
|
|
} |