Created
December 15, 2021 16:48
-
-
Save rokroskar/54ca45f511e68620a530f9f88e2324e5 to your computer and use it in GitHub Desktop.
Renku grafana dashboards
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "annotations": { | |
| "list": [ | |
| { | |
| "builtIn": 1, | |
| "datasource": "-- Grafana --", | |
| "enable": true, | |
| "hide": true, | |
| "iconColor": "rgba(0, 211, 255, 1)", | |
| "name": "Annotations & Alerts", | |
| "target": { | |
| "limit": 100, | |
| "matchAny": false, | |
| "tags": [], | |
| "type": "dashboard" | |
| }, | |
| "type": "dashboard" | |
| } | |
| ] | |
| }, | |
| "editable": true, | |
| "gnetId": null, | |
| "graphTooltip": 0, | |
| "id": 27, | |
| "links": [], | |
| "panels": [ | |
| { | |
| "datasource": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "mappings": [], | |
| "thresholds": { | |
| "mode": "absolute", | |
| "steps": [ | |
| { | |
| "color": "light-blue", | |
| "value": null | |
| } | |
| ] | |
| } | |
| }, | |
| "overrides": [] | |
| }, | |
| "gridPos": { | |
| "h": 5, | |
| "w": 24, | |
| "x": 0, | |
| "y": 0 | |
| }, | |
| "id": 4, | |
| "options": { | |
| "colorMode": "value", | |
| "graphMode": "none", | |
| "justifyMode": "center", | |
| "orientation": "auto", | |
| "reduceOptions": { | |
| "calcs": [ | |
| "last" | |
| ], | |
| "fields": "", | |
| "values": false | |
| }, | |
| "text": {}, | |
| "textMode": "auto" | |
| }, | |
| "pluginVersion": "8.1.6", | |
| "targets": [ | |
| { | |
| "expr": "entities_count{kubernetes_name=\"renku-knowledge-graph\"}", | |
| "interval": "", | |
| "legendFormat": "{{entities}}", | |
| "refId": "A" | |
| } | |
| ], | |
| "timeFrom": null, | |
| "timeShift": null, | |
| "title": "Number of knowledge graph entities by type", | |
| "type": "stat" | |
| }, | |
| { | |
| "alert": { | |
| "alertRuleTags": {}, | |
| "conditions": [ | |
| { | |
| "evaluator": { | |
| "params": [ | |
| 0.8 | |
| ], | |
| "type": "gt" | |
| }, | |
| "operator": { | |
| "type": "and" | |
| }, | |
| "query": { | |
| "params": [ | |
| "A", | |
| "1m", | |
| "now" | |
| ] | |
| }, | |
| "reducer": { | |
| "params": [], | |
| "type": "avg" | |
| }, | |
| "type": "query" | |
| } | |
| ], | |
| "executionErrorState": "alerting", | |
| "for": "2m", | |
| "frequency": "30s", | |
| "handler": 1, | |
| "message": "Pod CPU utilization approaching the limit.", | |
| "name": "Percentage of cpu limit used alert", | |
| "noDataState": "no_data", | |
| "notifications": [] | |
| }, | |
| "aliasColors": {}, | |
| "bars": false, | |
| "dashLength": 10, | |
| "dashes": false, | |
| "datasource": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 0, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 8, | |
| "w": 12, | |
| "x": 0, | |
| "y": 5 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 15, | |
| "legend": { | |
| "alignAsTable": true, | |
| "avg": false, | |
| "current": false, | |
| "hideEmpty": true, | |
| "hideZero": true, | |
| "max": true, | |
| "min": false, | |
| "rightSide": true, | |
| "show": true, | |
| "sort": "max", | |
| "sortDesc": true, | |
| "total": false, | |
| "values": true | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 2, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "(sum (rate(container_cpu_usage_seconds_total{container!=\"POD\",container!=\"jupyter-server\", container!=\"git-clone\",pod!=\"\",namespace=\"renku\",name=~\"k8s.*\"}[5m])) by (pod)) / (sum (kube_pod_container_resource_limits{namespace=\"renku\", resource=\"cpu\"} > 0) by (pod))", | |
| "hide": false, | |
| "interval": "", | |
| "legendFormat": "{{ pod }}", | |
| "refId": "A" | |
| } | |
| ], | |
| "thresholds": [ | |
| { | |
| "colorMode": "critical", | |
| "fill": true, | |
| "line": true, | |
| "op": "gt", | |
| "value": 0.8, | |
| "visible": true | |
| } | |
| ], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Percentage of cpu limit used", | |
| "tooltip": { | |
| "shared": true, | |
| "sort": 0, | |
| "value_type": "individual" | |
| }, | |
| "type": "graph", | |
| "xaxis": { | |
| "buckets": null, | |
| "mode": "time", | |
| "name": null, | |
| "show": true, | |
| "values": [] | |
| }, | |
| "yaxes": [ | |
| { | |
| "format": "percentunit", | |
| "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 | |
| } | |
| }, | |
| { | |
| "alert": { | |
| "alertRuleTags": {}, | |
| "conditions": [ | |
| { | |
| "evaluator": { | |
| "params": [ | |
| 0.9 | |
| ], | |
| "type": "gt" | |
| }, | |
| "operator": { | |
| "type": "and" | |
| }, | |
| "query": { | |
| "params": [ | |
| "A", | |
| "5m", | |
| "now" | |
| ] | |
| }, | |
| "reducer": { | |
| "params": [], | |
| "type": "avg" | |
| }, | |
| "type": "query" | |
| }, | |
| { | |
| "evaluator": { | |
| "params": [ | |
| 0.995 | |
| ], | |
| "type": "gt" | |
| }, | |
| "operator": { | |
| "type": "or" | |
| }, | |
| "query": { | |
| "params": [ | |
| "B", | |
| "5m", | |
| "now" | |
| ] | |
| }, | |
| "reducer": { | |
| "params": [], | |
| "type": "avg" | |
| }, | |
| "type": "query" | |
| } | |
| ], | |
| "executionErrorState": "alerting", | |
| "for": "5m", | |
| "frequency": "1m", | |
| "handler": 1, | |
| "message": "Pod approaching memory limit.", | |
| "name": "Percentage of memory limit used alert", | |
| "noDataState": "no_data", | |
| "notifications": [] | |
| }, | |
| "aliasColors": {}, | |
| "bars": false, | |
| "dashLength": 10, | |
| "dashes": false, | |
| "datasource": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 0, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 8, | |
| "w": 12, | |
| "x": 12, | |
| "y": 5 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 16, | |
| "legend": { | |
| "alignAsTable": true, | |
| "avg": false, | |
| "current": false, | |
| "hideEmpty": true, | |
| "max": true, | |
| "min": false, | |
| "rightSide": true, | |
| "show": true, | |
| "sort": "max", | |
| "sortDesc": true, | |
| "total": false, | |
| "values": true | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 2, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "container_memory_working_set_bytes{container!=\"POD\",container!=\"jupyter-server\", container!=\"git-clone\", namespace=\"renku\", pod!~\"renku-triples-generator.*\"} / (container_spec_memory_limit_bytes > 0)", | |
| "interval": "", | |
| "legendFormat": "{{ pod }}", | |
| "refId": "A" | |
| }, | |
| { | |
| "expr": "container_memory_working_set_bytes{container!=\"POD\", namespace=\"renku\", pod=~\"renku-triples-generator.*\"} / (container_spec_memory_limit_bytes > 0)", | |
| "hide": false, | |
| "interval": "", | |
| "legendFormat": "{{ pod }}", | |
| "refId": "B" | |
| } | |
| ], | |
| "thresholds": [ | |
| { | |
| "colorMode": "critical", | |
| "fill": true, | |
| "line": true, | |
| "op": "gt", | |
| "value": 0.9, | |
| "visible": true | |
| } | |
| ], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Percentage of memory limit used", | |
| "tooltip": { | |
| "shared": true, | |
| "sort": 0, | |
| "value_type": "individual" | |
| }, | |
| "type": "graph", | |
| "xaxis": { | |
| "buckets": null, | |
| "mode": "time", | |
| "name": null, | |
| "show": true, | |
| "values": [] | |
| }, | |
| "yaxes": [ | |
| { | |
| "format": "percentunit", | |
| "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": "Prometheus", | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 1, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 8, | |
| "w": 12, | |
| "x": 0, | |
| "y": 13 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 13, | |
| "legend": { | |
| "avg": false, | |
| "current": false, | |
| "max": false, | |
| "min": false, | |
| "show": true, | |
| "total": false, | |
| "values": false | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "links": [], | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "paceLength": 10, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 5, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "sum(kube_pod_status_phase{pod!~\"^renku-.*\",namespace=\"renku\"}) by (phase)", | |
| "format": "time_series", | |
| "interval": "", | |
| "intervalFactor": 2, | |
| "legendFormat": "{{phase}}", | |
| "refId": "A" | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "User pods running over time", | |
| "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 | |
| } | |
| }, | |
| { | |
| "alert": { | |
| "alertRuleTags": {}, | |
| "conditions": [ | |
| { | |
| "evaluator": { | |
| "params": [ | |
| 90 | |
| ], | |
| "type": "gt" | |
| }, | |
| "operator": { | |
| "type": "and" | |
| }, | |
| "query": { | |
| "params": [ | |
| "A", | |
| "5m", | |
| "now" | |
| ] | |
| }, | |
| "reducer": { | |
| "params": [], | |
| "type": "last" | |
| }, | |
| "type": "query" | |
| } | |
| ], | |
| "executionErrorState": "alerting", | |
| "for": "5m", | |
| "frequency": "1m", | |
| "handler": 1, | |
| "message": "Persistent volume pressure on renkulab.", | |
| "name": "Persistent Volume capacity alert", | |
| "noDataState": "no_data", | |
| "notifications": [] | |
| }, | |
| "aliasColors": {}, | |
| "bars": false, | |
| "dashLength": 10, | |
| "dashes": false, | |
| "datasource": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [], | |
| "unit": "percent" | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 1, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 8, | |
| "w": 12, | |
| "x": 12, | |
| "y": 13 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 2, | |
| "legend": { | |
| "alignAsTable": true, | |
| "avg": false, | |
| "current": true, | |
| "hideEmpty": false, | |
| "hideZero": false, | |
| "max": false, | |
| "min": false, | |
| "rightSide": true, | |
| "show": true, | |
| "sideWidth": null, | |
| "sort": "current", | |
| "sortDesc": true, | |
| "total": false, | |
| "values": true | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 2, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "100 * (kubelet_volume_stats_used_bytes{renku_io_node_purpose=\"\"} / kubelet_volume_stats_capacity_bytes{renku_io_node_purpose=\"\"})", | |
| "interval": "", | |
| "legendFormat": "{{persistentvolumeclaim}}", | |
| "refId": "A" | |
| }, | |
| { | |
| "exemplar": true, | |
| "expr": "100 * (kubelet_volume_stats_used_bytes{renku_io_node_purpose=\"user\"} / kubelet_volume_stats_capacity_bytes{renku_io_node_purpose=\"user\"})", | |
| "hide": false, | |
| "interval": "", | |
| "legendFormat": "{{persistentvolumeclaim}}", | |
| "refId": "B" | |
| } | |
| ], | |
| "thresholds": [ | |
| { | |
| "colorMode": "critical", | |
| "fill": true, | |
| "line": true, | |
| "op": "gt", | |
| "value": 90, | |
| "visible": true | |
| } | |
| ], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Persistent Volume capacity", | |
| "tooltip": { | |
| "shared": true, | |
| "sort": 2, | |
| "value_type": "individual" | |
| }, | |
| "type": "graph", | |
| "xaxis": { | |
| "buckets": null, | |
| "mode": "time", | |
| "name": null, | |
| "show": true, | |
| "values": [] | |
| }, | |
| "yaxes": [ | |
| { | |
| "$$hashKey": "object:91", | |
| "format": "percent", | |
| "label": null, | |
| "logBase": 1, | |
| "max": null, | |
| "min": null, | |
| "show": true | |
| }, | |
| { | |
| "$$hashKey": "object:92", | |
| "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": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 0, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 8, | |
| "w": 12, | |
| "x": 0, | |
| "y": 21 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 10, | |
| "legend": { | |
| "avg": false, | |
| "current": true, | |
| "max": true, | |
| "min": false, | |
| "rightSide": false, | |
| "show": true, | |
| "total": false, | |
| "values": true | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 2, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "rate(container_cpu_usage_seconds_total{container=\"notebooks\", namespace=\"renku\"}[5m]) ", | |
| "interval": "", | |
| "legendFormat": "{{ pod }}", | |
| "refId": "A" | |
| }, | |
| { | |
| "exemplar": true, | |
| "expr": "kube_pod_container_resource_limits{resource=\"cpu\", container=\"notebooks\", namespace=\"renku\"}", | |
| "hide": true, | |
| "interval": "", | |
| "legendFormat": "limit", | |
| "refId": "B" | |
| }, | |
| { | |
| "exemplar": true, | |
| "expr": "kube_pod_container_resource_requests{resource=\"cpu\", container=\"notebooks\", namespace=\"renku\"}", | |
| "hide": true, | |
| "interval": "", | |
| "legendFormat": "request", | |
| "refId": "C" | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Notebooks Service CPU usage", | |
| "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": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 0, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 8, | |
| "w": 12, | |
| "x": 12, | |
| "y": 21 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 11, | |
| "legend": { | |
| "avg": false, | |
| "current": true, | |
| "max": true, | |
| "min": false, | |
| "show": false, | |
| "total": false, | |
| "values": true | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 2, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "container_memory_usage_bytes{container=\"notebooks\", namespace=\"renku\"} ", | |
| "interval": "", | |
| "legendFormat": "{{pod}}", | |
| "refId": "A" | |
| }, | |
| { | |
| "exemplar": true, | |
| "expr": "kube_pod_container_resource_limits{resource=\"memory\", container=\"notebooks\", namespace=\"renku\"}", | |
| "interval": "", | |
| "legendFormat": "limit", | |
| "refId": "C" | |
| }, | |
| { | |
| "exemplar": true, | |
| "expr": "kube_pod_container_resource_requests{resource=\"memory\",container=\"notebooks\", namespace=\"renku\"}", | |
| "interval": "", | |
| "legendFormat": "request", | |
| "refId": "B" | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Notebooks Service memory usage", | |
| "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": null, | |
| "logBase": 1, | |
| "max": null, | |
| "min": null, | |
| "show": true | |
| } | |
| ], | |
| "yaxis": { | |
| "align": false, | |
| "alignLevel": null | |
| } | |
| } | |
| ], | |
| "refresh": "", | |
| "schemaVersion": 30, | |
| "style": "dark", | |
| "tags": [], | |
| "templating": { | |
| "list": [] | |
| }, | |
| "time": { | |
| "from": "now-3h", | |
| "to": "now" | |
| }, | |
| "timepicker": { | |
| "refresh_intervals": [ | |
| "10s", | |
| "30s", | |
| "1m", | |
| "5m", | |
| "15m", | |
| "30m", | |
| "1h", | |
| "2h", | |
| "1d" | |
| ] | |
| }, | |
| "timezone": "", | |
| "title": "Renku health", | |
| "uid": "fW_Ip_NMz", | |
| "version": 52 | |
| } |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| { | |
| "annotations": { | |
| "list": [ | |
| { | |
| "builtIn": 1, | |
| "datasource": "-- Grafana --", | |
| "enable": true, | |
| "hide": true, | |
| "iconColor": "rgba(0, 211, 255, 1)", | |
| "name": "Annotations & Alerts", | |
| "target": { | |
| "limit": 100, | |
| "matchAny": false, | |
| "tags": [], | |
| "type": "dashboard" | |
| }, | |
| "type": "dashboard" | |
| } | |
| ] | |
| }, | |
| "description": "Overview of running user pods", | |
| "editable": true, | |
| "gnetId": null, | |
| "graphTooltip": 0, | |
| "id": 56, | |
| "links": [], | |
| "panels": [ | |
| { | |
| "aliasColors": {}, | |
| "bars": false, | |
| "dashLength": 10, | |
| "dashes": false, | |
| "datasource": "Prometheus", | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 1, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 7, | |
| "w": 24, | |
| "x": 0, | |
| "y": 0 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 2, | |
| "legend": { | |
| "avg": false, | |
| "current": false, | |
| "max": false, | |
| "min": false, | |
| "show": true, | |
| "total": false, | |
| "values": false | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "links": [], | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "paceLength": 10, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 5, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "sum(kube_pod_status_phase{pod!~\"^renku-.*\",namespace=\"renku\"}) by (phase)", | |
| "format": "time_series", | |
| "interval": "", | |
| "intervalFactor": 2, | |
| "legendFormat": "{{phase}}", | |
| "refId": "A" | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "User pods running over time", | |
| "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": null, | |
| "decimals": 3, | |
| "editable": true, | |
| "error": false, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 0, | |
| "fillGradient": 0, | |
| "grid": {}, | |
| "gridPos": { | |
| "h": 9, | |
| "w": 24, | |
| "x": 0, | |
| "y": 7 | |
| }, | |
| "height": "", | |
| "hiddenSeries": false, | |
| "id": 6, | |
| "legend": { | |
| "alignAsTable": true, | |
| "avg": true, | |
| "current": true, | |
| "max": false, | |
| "min": false, | |
| "rightSide": true, | |
| "show": true, | |
| "sort": "avg", | |
| "sortDesc": true, | |
| "total": false, | |
| "values": true | |
| }, | |
| "lines": true, | |
| "linewidth": 2, | |
| "links": [], | |
| "nullPointMode": "connected", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "paceLength": 10, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 5, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": true, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "topk(5, sum(rate(container_cpu_usage_seconds_total{container=\"jupyter-server\"}[2m])) by (pod))", | |
| "format": "time_series", | |
| "hide": false, | |
| "instant": false, | |
| "interval": "", | |
| "intervalFactor": 1, | |
| "legendFormat": "{{ pod }}", | |
| "metric": "container_cpu", | |
| "refId": "A", | |
| "step": 10 | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Top 5 Pods CPU usage (2m avg)", | |
| "tooltip": { | |
| "msResolution": true, | |
| "shared": false, | |
| "sort": 2, | |
| "value_type": "cumulative" | |
| }, | |
| "type": "graph", | |
| "xaxis": { | |
| "buckets": null, | |
| "mode": "time", | |
| "name": null, | |
| "show": true, | |
| "values": [] | |
| }, | |
| "yaxes": [ | |
| { | |
| "$$hashKey": "object:46", | |
| "format": "none", | |
| "label": "cores", | |
| "logBase": 1, | |
| "max": null, | |
| "min": "0", | |
| "show": true | |
| }, | |
| { | |
| "$$hashKey": "object:47", | |
| "format": "short", | |
| "label": null, | |
| "logBase": 1, | |
| "max": null, | |
| "min": null, | |
| "show": false | |
| } | |
| ], | |
| "yaxis": { | |
| "align": false, | |
| "alignLevel": null | |
| } | |
| }, | |
| { | |
| "aliasColors": {}, | |
| "bars": false, | |
| "dashLength": 10, | |
| "dashes": false, | |
| "datasource": null, | |
| "decimals": 3, | |
| "editable": true, | |
| "error": false, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 0, | |
| "fillGradient": 0, | |
| "grid": {}, | |
| "gridPos": { | |
| "h": 8, | |
| "w": 24, | |
| "x": 0, | |
| "y": 16 | |
| }, | |
| "height": "", | |
| "hiddenSeries": false, | |
| "id": 4, | |
| "legend": { | |
| "alignAsTable": true, | |
| "avg": true, | |
| "current": true, | |
| "max": false, | |
| "min": false, | |
| "rightSide": true, | |
| "show": true, | |
| "sort": "avg", | |
| "sortDesc": true, | |
| "total": false, | |
| "values": true | |
| }, | |
| "lines": true, | |
| "linewidth": 2, | |
| "links": [], | |
| "nullPointMode": "connected", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "paceLength": 10, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 5, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": true, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "topk(5, sum(container_memory_usage_bytes{namespace=\"renku\",pod!~\"^renku.*\"}) by (pod))", | |
| "format": "time_series", | |
| "interval": "", | |
| "intervalFactor": 1, | |
| "legendFormat": "{{ pod_name }}", | |
| "metric": "container_cpu", | |
| "refId": "A", | |
| "step": 10 | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Top 5 Pods memory usage", | |
| "tooltip": { | |
| "msResolution": true, | |
| "shared": false, | |
| "sort": 2, | |
| "value_type": "cumulative" | |
| }, | |
| "type": "graph", | |
| "xaxis": { | |
| "buckets": null, | |
| "mode": "time", | |
| "name": null, | |
| "show": true, | |
| "values": [] | |
| }, | |
| "yaxes": [ | |
| { | |
| "$$hashKey": "object:71", | |
| "format": "decbytes", | |
| "label": "RAM", | |
| "logBase": 1, | |
| "max": null, | |
| "min": "0", | |
| "show": true | |
| }, | |
| { | |
| "$$hashKey": "object:72", | |
| "format": "short", | |
| "label": null, | |
| "logBase": 1, | |
| "max": null, | |
| "min": null, | |
| "show": false | |
| } | |
| ], | |
| "yaxis": { | |
| "align": false, | |
| "alignLevel": null | |
| } | |
| }, | |
| { | |
| "aliasColors": {}, | |
| "bars": false, | |
| "dashLength": 10, | |
| "dashes": false, | |
| "datasource": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 1, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 7, | |
| "w": 24, | |
| "x": 0, | |
| "y": 24 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 8, | |
| "legend": { | |
| "avg": false, | |
| "current": false, | |
| "max": false, | |
| "min": false, | |
| "show": true, | |
| "total": false, | |
| "values": false | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "links": [], | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "paceLength": 10, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 5, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "sum (container_memory_usage_bytes{namespace=\"renku\",pod!~\"^renku.*\"})", | |
| "format": "time_series", | |
| "interval": "", | |
| "intervalFactor": 1, | |
| "legendFormat": "total memory", | |
| "refId": "A" | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Total user pod memory consumption", | |
| "tooltip": { | |
| "shared": true, | |
| "sort": 0, | |
| "value_type": "individual" | |
| }, | |
| "type": "graph", | |
| "xaxis": { | |
| "buckets": null, | |
| "mode": "time", | |
| "name": null, | |
| "show": true, | |
| "values": [] | |
| }, | |
| "yaxes": [ | |
| { | |
| "format": "decbytes", | |
| "label": null, | |
| "logBase": 1, | |
| "max": null, | |
| "min": null, | |
| "show": true | |
| }, | |
| { | |
| "format": "decgbytes", | |
| "label": null, | |
| "logBase": 1, | |
| "max": null, | |
| "min": null, | |
| "show": false | |
| } | |
| ], | |
| "yaxis": { | |
| "align": false, | |
| "alignLevel": null | |
| } | |
| }, | |
| { | |
| "aliasColors": {}, | |
| "bars": false, | |
| "dashLength": 10, | |
| "dashes": false, | |
| "datasource": null, | |
| "description": "Number of user pods running grouped by their memory limit", | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 1, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 9, | |
| "w": 12, | |
| "x": 0, | |
| "y": 31 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 12, | |
| "legend": { | |
| "avg": false, | |
| "current": false, | |
| "max": false, | |
| "min": false, | |
| "show": true, | |
| "total": false, | |
| "values": false | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 2, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "count_values (\"Mem_limit_GB\", container_spec_memory_limit_bytes{container=\"jupyter-server\"}/1024/1024/1024)", | |
| "interval": "", | |
| "legendFormat": "", | |
| "refId": "A" | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "User pods per memory limit", | |
| "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": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 1, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 9, | |
| "w": 12, | |
| "x": 12, | |
| "y": 31 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 18, | |
| "legend": { | |
| "avg": false, | |
| "current": false, | |
| "max": false, | |
| "min": false, | |
| "show": true, | |
| "total": false, | |
| "values": false | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 2, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "count_values (\"CPU_requests\", container_spec_cpu_shares{container=\"jupyter-server\"}/1024)", | |
| "interval": "", | |
| "legendFormat": "", | |
| "refId": "A" | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "User pods per CPU requests", | |
| "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": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 1, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 7, | |
| "w": 12, | |
| "x": 0, | |
| "y": 40 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 14, | |
| "legend": { | |
| "avg": false, | |
| "current": false, | |
| "max": false, | |
| "min": false, | |
| "show": true, | |
| "total": false, | |
| "values": false | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 2, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "exemplar": true, | |
| "expr": "sum (container_spec_memory_limit_bytes{container=\"jupyter-server\",name=~\".*bio.*\"}/1024/1024/1024)", | |
| "interval": "", | |
| "legendFormat": "Total mem (GB) bio344", | |
| "refId": "A" | |
| }, | |
| { | |
| "exemplar": true, | |
| "expr": "sum (container_spec_memory_limit_bytes{container=\"jupyter-server\",name=~\".*crnaseq.*\"}/1024/1024/1024)", | |
| "interval": "", | |
| "legendFormat": "Total mem (GB) SIB", | |
| "refId": "B" | |
| }, | |
| { | |
| "exemplar": true, | |
| "expr": "sum (container_spec_memory_limit_bytes{container=\"jupyter-server\",name=~\".*wsbim.*\"}/1024/1024/1024)", | |
| "interval": "", | |
| "legendFormat": "Total mem (GB) WSbim", | |
| "refId": "C" | |
| }, | |
| { | |
| "exemplar": true, | |
| "expr": "sum (container_spec_memory_limit_bytes{container=\"jupyter-server\",name=~\".*e-2drum.*\"}/1024/1024/1024)", | |
| "interval": "", | |
| "legendFormat": "Total mem (GB) e-rum", | |
| "refId": "D" | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Total memory used for courses", | |
| "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": null, | |
| "fieldConfig": { | |
| "defaults": { | |
| "links": [] | |
| }, | |
| "overrides": [] | |
| }, | |
| "fill": 1, | |
| "fillGradient": 0, | |
| "gridPos": { | |
| "h": 7, | |
| "w": 12, | |
| "x": 12, | |
| "y": 40 | |
| }, | |
| "hiddenSeries": false, | |
| "id": 16, | |
| "legend": { | |
| "avg": false, | |
| "current": false, | |
| "max": false, | |
| "min": false, | |
| "show": true, | |
| "total": false, | |
| "values": false | |
| }, | |
| "lines": true, | |
| "linewidth": 1, | |
| "nullPointMode": "null", | |
| "options": { | |
| "alertThreshold": true | |
| }, | |
| "percentage": false, | |
| "pluginVersion": "8.1.6", | |
| "pointradius": 2, | |
| "points": false, | |
| "renderer": "flot", | |
| "seriesOverrides": [], | |
| "spaceLength": 10, | |
| "stack": false, | |
| "steppedLine": false, | |
| "targets": [ | |
| { | |
| "expr": "count(kube_pod_container_info{image=~\".*wsbim.*\"})", | |
| "legendFormat": "Pods for WSbim", | |
| "refId": "A" | |
| }, | |
| { | |
| "expr": "count(kube_pod_container_info{image=~\".*crnaseq.*\"})", | |
| "legendFormat": "Pods for SIB", | |
| "refId": "B" | |
| }, | |
| { | |
| "expr": "count(kube_pod_container_info{image=~\".*bio.*\"})", | |
| "legendFormat": "Pods for bio344", | |
| "refId": "C" | |
| }, | |
| { | |
| "expr": "count(kube_pod_container_info{image=~\".*e-2drum.*\"})", | |
| "legendFormat": "Pods for e-rum", | |
| "refId": "D" | |
| } | |
| ], | |
| "thresholds": [], | |
| "timeFrom": null, | |
| "timeRegions": [], | |
| "timeShift": null, | |
| "title": "Number of user pods per course", | |
| "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 | |
| } | |
| } | |
| ], | |
| "refresh": "10s", | |
| "schemaVersion": 30, | |
| "style": "dark", | |
| "tags": [], | |
| "templating": { | |
| "list": [] | |
| }, | |
| "time": { | |
| "from": "now-7d", | |
| "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": "User pod stats", | |
| "uid": "xRxoj9jiz", | |
| "version": 5 | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment