{ "__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": "

\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
\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

\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, "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": [ { "datasource": "$datasource", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 100, "lineWidth": 0, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "normal" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "reqps" }, "overrides": [ { "matcher": { "id": "byName", "options": "1xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#EAB839", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "2xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#7EB26D", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "3xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#6ED0E0", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "4xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#EF843C", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "5xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#E24D42", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "OK" }, "properties": [ { "id": "color", "value": { "fixedColor": "#7EB26D", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "cancel" }, "properties": [ { "id": "color", "value": { "fixedColor": "#A9A9A9", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "error" }, "properties": [ { "id": "color", "value": { "fixedColor": "#E24D42", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "success" }, "properties": [ { "id": "color", "value": { "fixedColor": "#7EB26D", "mode": "fixed" } } ] } ] }, "id": 3, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "targets": [ { "expr": "sum by (status) (\n label_replace(label_replace(rate(cortex_request_duration_seconds_count{cluster=~\"$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-zA-Z]+)\"))\n", "format": "time_series", "legendFormat": "{{status}}", "refId": "A" } ], "title": "Requests / sec", "type": "timeseries" }, { "datasource": "$datasource", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "ms" }, "overrides": [ ] }, "id": 4, "links": [ ], "nullPointMode": "null as zero", "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "targets": [ { "expr": "histogram_quantile(0.99, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})) * 1e3", "format": "time_series", "legendFormat": "99th percentile", "refId": "A" }, { "expr": "histogram_quantile(0.50, sum by (le) (cluster_job_route:cortex_request_duration_seconds_bucket:sum_rate{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})) * 1e3", "format": "time_series", "legendFormat": "50th percentile", "refId": "B" }, { "expr": "1e3 * sum(cluster_job_route:cortex_request_duration_seconds_sum:sum_rate{cluster=~\"$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=~\"($namespace)/((ruler-query-frontend.*))\", route=~\"/httpgrpc.HTTP/Handle|.*api_v1_query\"})", "format": "time_series", "legendFormat": "Average", "refId": "C" } ], "title": "Latency", "type": "timeseries" }, { "datasource": "$datasource", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 0, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "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\"}[$__rate_interval])))", "format": "time_series", "legendFormat": "", "legendLink": null } ], "title": "Per pod p99 latency", "type": "timeseries" } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Ruler-query-frontend", "titleSize": "h6" }, { "collapse": false, "height": "250px", "panels": [ { "datasource": "$datasource", "description": "### Requests / sec\n

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 100, "lineWidth": 0, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "normal" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "reqps" }, "overrides": [ { "matcher": { "id": "byName", "options": "1xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#EAB839", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "2xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#7EB26D", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "3xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#6ED0E0", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "4xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#EF843C", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "5xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#E24D42", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "OK" }, "properties": [ { "id": "color", "value": { "fixedColor": "#7EB26D", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "cancel" }, "properties": [ { "id": "color", "value": { "fixedColor": "#A9A9A9", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "error" }, "properties": [ { "id": "color", "value": { "fixedColor": "#E24D42", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "success" }, "properties": [ { "id": "color", "value": { "fixedColor": "#7EB26D", "mode": "fixed" } } ] } ] }, "id": 6, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "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\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", "format": "time_series", "legendFormat": "{{status}}", "refId": "A" } ], "title": "Requests / sec", "type": "timeseries" }, { "datasource": "$datasource", "description": "### Latency (Time in Queue)\n

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "ms" }, "overrides": [ ] }, "id": 7, "links": [ ], "nullPointMode": "null as zero", "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "targets": [ { "expr": "histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le)) * 1e3", "format": "time_series", "legendFormat": "99th Percentile", "refId": "A" }, { "expr": "histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le)) * 1e3", "format": "time_series", "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", "legendFormat": "Average", "refId": "C" } ], "title": "Latency (Time in Queue)", "type": "timeseries", "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", "description": "### Queue length\n

\n The query scheduler is an optional service that moves\n the internal queue from the query-frontend into a\n separate component.\n If this service is not deployed,\n these panels will show \"No data.\"\n

\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 0, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "queries" }, "overrides": [ ] }, "id": 8, "links": [ ], "options": { "legend": { "displayMode": "hidden", "showLegend": false }, "tooltip": { "mode": "multi", "sort": "desc" } }, "span": 4, "targets": [ { "exemplar": true, "expr": "sum(min_over_time(cortex_query_scheduler_queue_length{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__interval]))", "format": "time_series", "legendFormat": "Queue length", "legendLink": null } ], "title": "Queue length", "type": "timeseries" } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Ruler-query-scheduler", "titleSize": "h6" }, { "collapse": false, "height": "250px", "panels": [ { "datasource": "$datasource", "description": "### 99th Percentile Latency by Queue Dimension\n

\n The query scheduler can optionally create subqueues\n in order to enforce round-robin query queuing fairness\n across additional queue dimensions beyond the default.\n\n By default, query queuing fairness is only applied by tenant ID.\n Queries without additional queue dimensions are labeled 'none'.\n

\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "noValue": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "ms" }, "overrides": [ ] }, "id": 9, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "targets": [ { "expr": "label_replace(histogram_quantile(0.99, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le, additional_queue_dimensions)) * 1e3, \"additional_queue_dimensions\", \"none\", \"additional_queue_dimensions\", \"^$\")\n", "format": "time_series", "legendFormat": "99th Percentile: {{ additional_queue_dimensions }}", "refId": "A" } ], "title": "99th Percentile Latency by Queue Dimension", "type": "timeseries" }, { "datasource": "$datasource", "description": "### 50th Percentile Latency by Queue Dimension\n

\n The query scheduler can optionally create subqueues\n in order to enforce round-robin query queuing fairness\n across additional queue dimensions beyond the default.\n\n By default, query queuing fairness is only applied by tenant ID.\n Queries without additional queue dimensions are labeled 'none'.\n

\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "noValue": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "ms" }, "overrides": [ ] }, "id": 10, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "targets": [ { "expr": "label_replace(histogram_quantile(0.50, sum(rate(cortex_query_scheduler_queue_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (le, additional_queue_dimensions)) * 1e3, \"additional_queue_dimensions\", \"none\", \"additional_queue_dimensions\", \"^$\")\n", "format": "time_series", "legendFormat": "50th Percentile: {{ additional_queue_dimensions }}", "refId": "A" } ], "title": "50th Percentile Latency by Queue Dimension", "type": "timeseries" }, { "datasource": "$datasource", "description": "### Average Latency by Queue Dimension\n

\n The query scheduler can optionally create subqueues\n in order to enforce round-robin query queuing fairness\n across additional queue dimensions beyond the default.\n\n By default, query queuing fairness is only applied by tenant ID.\n Queries without additional queue dimensions are labeled 'none'.\n

\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "noValue": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "ms" }, "overrides": [ ] }, "id": 11, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "targets": [ { "expr": "label_replace(sum(rate(cortex_query_scheduler_queue_duration_seconds_sum{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (additional_queue_dimensions) * 1e3 / sum(rate(cortex_query_scheduler_queue_duration_seconds_count{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-query-scheduler.*))\"}[$__rate_interval])) by (additional_queue_dimensions), \"additional_queue_dimensions\", \"none\", \"additional_queue_dimensions\", \"^$\")\n", "format": "time_series", "legendFormat": "Average: {{ additional_queue_dimensions }}", "refId": "C" } ], "title": "Average Latency by Queue Dimension", "type": "timeseries" } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Ruler-query-scheduler Latency (Time in Queue) Breakout by Additional Queue Dimensions", "titleSize": "h6" }, { "collapse": false, "height": "250px", "panels": [ { "datasource": "$datasource", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 100, "lineWidth": 0, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "normal" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "reqps" }, "overrides": [ { "matcher": { "id": "byName", "options": "1xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#EAB839", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "2xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#7EB26D", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "3xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#6ED0E0", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "4xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#EF843C", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "5xx" }, "properties": [ { "id": "color", "value": { "fixedColor": "#E24D42", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "OK" }, "properties": [ { "id": "color", "value": { "fixedColor": "#7EB26D", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "cancel" }, "properties": [ { "id": "color", "value": { "fixedColor": "#A9A9A9", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "error" }, "properties": [ { "id": "color", "value": { "fixedColor": "#E24D42", "mode": "fixed" } } ] }, { "matcher": { "id": "byName", "options": "success" }, "properties": [ { "id": "color", "value": { "fixedColor": "#7EB26D", "mode": "fixed" } } ] } ] }, "id": 12, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "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\", \"${1}\", \"status_code\", \"([a-zA-Z]+)\"))\n", "format": "time_series", "legendFormat": "{{status}}", "refId": "A" } ], "title": "Requests / sec", "type": "timeseries" }, { "datasource": "$datasource", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "ms" }, "overrides": [ ] }, "id": 13, "links": [ ], "nullPointMode": "null as zero", "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "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", "legendFormat": "99th percentile", "refId": "A" }, { "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", "legendFormat": "50th percentile", "refId": "B" }, { "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", "legendFormat": "Average", "refId": "C" } ], "title": "Latency", "type": "timeseries" }, { "datasource": "$datasource", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 0, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "s" }, "overrides": [ ] }, "id": 14, "links": [ ], "options": { "legend": { "displayMode": "hidden", "showLegend": false }, "tooltip": { "mode": "multi", "sort": "desc" } }, "span": 4, "targets": [ { "exemplar": true, "expr": "histogram_quantile(0.99, sum by(le, pod) (rate(cortex_querier_request_duration_seconds_bucket{cluster=~\"$cluster\", job=~\"($namespace)/((ruler-querier.*))\", route=~\"(prometheus|api_prom)_api_v1_.+\"}[$__rate_interval])))", "format": "time_series", "legendFormat": "", "legendLink": null } ], "title": "Per pod p99 latency", "type": "timeseries" } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Ruler-querier", "titleSize": "h6" }, { "collapse": false, "height": "250px", "panels": [ { "datasource": "$datasource", "description": "### Replicas\nThe maximum and current number of ruler-querier replicas.

\nNote: The current number of replicas can still show 1 replica even when scaled to 0.\nBecause HPA never reports 0 replicas, the query will report 0 only if the HPA is not active.\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "short" }, "overrides": [ { "matcher": { "id": "byRegexp", "options": "/Max .+/" }, "properties": [ { "id": "custom.fillOpacity", "value": 0 }, { "id": "custom.lineStyle", "value": { "fill": "dash" } } ] }, { "matcher": { "id": "byRegexp", "options": "/Current .+/" }, "properties": [ { "id": "custom.fillOpacity", "value": 0 } ] }, { "matcher": { "id": "byRegexp", "options": "/Min .+/" }, "properties": [ { "id": "custom.fillOpacity", "value": 0 }, { "id": "custom.lineStyle", "value": { "fill": "dash" } } ] } ] }, "id": 15, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 6, "targets": [ { "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_spec_max_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n # Add the scaletargetref_name label for readability\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n)\n", "format": "time_series", "legendFormat": "Max {{ scaletargetref_name }}", "legendLink": null }, { "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_status_current_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n # HPA doesn't go to 0 replicas, so we multiply by 0 if the HPA is not active\n * on (cluster, namespace, horizontalpodautoscaler)\n kube_horizontalpodautoscaler_status_condition{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\", condition=\"ScalingActive\", status=\"true\"}\n # Add the scaletargetref_name label for readability\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n)\n", "format": "time_series", "legendFormat": "Current {{ scaletargetref_name }}", "legendLink": null }, { "expr": "max by (scaletargetref_name) (\n kube_horizontalpodautoscaler_spec_min_replicas{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n # Add the scaletargetref_name label for readability\n + on (cluster, namespace, horizontalpodautoscaler) group_left (scaletargetref_name)\n 0*kube_horizontalpodautoscaler_info{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"}\n)\n", "format": "time_series", "legendFormat": "Min {{ scaletargetref_name }}", "legendLink": null } ], "title": "Replicas", "type": "timeseries" }, { "datasource": "$datasource", "description": "### Autoscaler failures rate\nThe rate of failures in the KEDA custom metrics API server. Whenever an error occurs, the KEDA custom\nmetrics server is unable to query the scaling metric from Prometheus so the autoscaler woudln't work properly.\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "short" }, "overrides": [ ] }, "id": 16, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 6, "targets": [ { "expr": "sum by(cluster, namespace, scaler, metric, scaledObject) (\n label_replace(\n rate(keda_scaler_errors[$__rate_interval]),\n \"namespace\", \"$1\", \"exported_namespace\", \"(.+)\"\n )\n) +\non(cluster, namespace, metric, scaledObject) group_left\nlabel_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"} * 0,\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n ),\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n)\n", "format": "time_series", "legendFormat": "{{scaler}} failures", "legendLink": null } ], "title": "Autoscaler failures rate", "type": "timeseries" } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Ruler-querier - autoscaling", "titleSize": "h6" }, { "collapse": false, "height": "250px", "panels": [ { "datasource": "$datasource", "description": "### Scaling metric (CPU): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "short" }, "overrides": [ ] }, "id": 17, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "targets": [ { "expr": "sum by (scaler) (\n label_replace(\n keda_scaler_metrics_value{cluster=~\"$cluster\", exported_namespace=~\"$namespace\", scaler=~\".*cpu.*\"},\n \"namespace\", \"$1\", \"exported_namespace\", \"(.*)\"\n )\n /\n on(cluster, namespace, scaledObject, metric) group_left label_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n ),\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n )\n)\n", "format": "time_series", "legendFormat": "{{ scaler }}", "legendLink": null } ], "title": "Scaling metric (CPU): Desired replicas", "type": "timeseries" }, { "datasource": "$datasource", "description": "### Scaling metric (memory): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "short" }, "overrides": [ ] }, "id": 18, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "targets": [ { "expr": "sum by (scaler) (\n label_replace(\n keda_scaler_metrics_value{cluster=~\"$cluster\", exported_namespace=~\"$namespace\", scaler=~\".*memory.*\"},\n \"namespace\", \"$1\", \"exported_namespace\", \"(.*)\"\n )\n /\n on(cluster, namespace, scaledObject, metric) group_left label_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n ),\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n )\n)\n", "format": "time_series", "legendFormat": "{{ scaler }}", "legendLink": null } ], "title": "Scaling metric (memory): Desired replicas", "type": "timeseries" }, { "datasource": "$datasource", "description": "### Scaling metric (in-flight queries): Desired replicas\nThis panel shows the scaling metric exposed by KEDA divided by the target/threshold used.\nIt should represent the desired number of replicas, ignoring the min/max constraints applied later.\n\n", "fieldConfig": { "defaults": { "custom": { "drawStyle": "line", "fillOpacity": 1, "lineWidth": 1, "pointSize": 5, "showPoints": "never", "spanNulls": false, "stacking": { "group": "A", "mode": "none" } }, "min": 0, "thresholds": { "mode": "absolute", "steps": [ ] }, "unit": "short" }, "overrides": [ ] }, "id": 19, "links": [ ], "options": { "legend": { "showLegend": true }, "tooltip": { "mode": "single", "sort": "none" } }, "span": 4, "targets": [ { "expr": "sum by (scaler) (\n label_replace(\n keda_scaler_metrics_value{cluster=~\"$cluster\", exported_namespace=~\"$namespace\", scaler=~\".*queries.*\"},\n \"namespace\", \"$1\", \"exported_namespace\", \"(.*)\"\n )\n /\n on(cluster, namespace, scaledObject, metric) group_left label_replace(\n label_replace(\n kube_horizontalpodautoscaler_spec_target_metric{cluster=~\"$cluster\", namespace=~\"$namespace\", horizontalpodautoscaler=~\"keda-hpa-ruler-querier\"},\n \"metric\", \"$1\", \"metric_name\", \"(.+)\"\n ),\n \"scaledObject\", \"$1\", \"horizontalpodautoscaler\", \"keda-hpa-(.*)\"\n )\n)\n", "format": "time_series", "legendFormat": "{{ scaler }}", "legendLink": null } ], "title": "Scaling metric (in-flight queries): Desired replicas", "type": "timeseries" } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "", "titleSize": "h6" } ], "schemaVersion": 14, "style": "dark", "tags": [ "mimir" ], "templating": { "list": [ { "current": { "text": "default", "value": "default" }, "hide": 0, "label": "Data source", "name": "datasource", "options": [ ], "query": "prometheus", "refresh": 1, "regex": "", "type": "datasource" }, { "allValue": ".+", "current": { "selected": true, "text": "All", "value": "$__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 }