apiVersion: v1 kind: ConfigMap metadata: name: k8ssandra-cassandra-condensed-dashboard namespace: k8ssandra-operator labels: grafana_dashboard: "1" data: cassandra-condensed.json: | { "__inputs": [ ], "__requires": [ ], "annotations": { "list": [ ] }, "description": "Single pane of glass for most important Cassandra metrics", "editable": true, "gnetId": null, "graphTooltip": 0, "hideControls": false, "id": null, "links": [ ], "refresh": "30s", "rows": [ { "collapse": false, "collapsed": false, "height": 100, "panels": [ { "cacheTimeout": null, "colorBackground": false, "colorValue": true, "colors": [ "#d44a3a", "#299c46", "#299c46" ], "datasource": "Prometheus", "decimals": 0, "description": "Nodes that are currently running in this time window", "format": "none", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 2, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": false }, "tableColumn": "", "targets": [ { "expr": "count(mcac_compaction_completed_tasks{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"} >= 0) or vector(0)", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "0.1,1000", "title": "Nodes Up", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": true, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "decimals": 0, "description": "Nodes that are currently not running in this time window", "format": "none", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 3, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": false }, "tableColumn": "", "targets": [ { "expr": "count(absent(sum(rate(mcac_compaction_completed_tasks{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[5m])))) OR vector(0)", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "1,2", "title": "Nodes Down", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": false, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "decimals": 0, "description": "Rate of compactions during this window", "format": "none", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 4, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": true }, "tableColumn": "", "targets": [ { "expr": "sum(rate(mcac_compaction_completed_tasks{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "", "title": "Compactions / $rate", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": false, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "decimals": 0, "description": "Rate of CQL requests during this window", "format": "none", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 5, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": true }, "tableColumn": "", "targets": [ { "expr": "sum(irate(dse_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "", "title": "CQL Requests / $rate", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": true, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "decimals": 0, "description": "Rate of Dropped requests during this window", "format": "none", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 6, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": true }, "tableColumn": "", "targets": [ { "expr": "sum(irate(mcac_table_dropped_mutations_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "30,300", "title": "Dropped Messages / $rate", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "content": "", "datasource": "Prometheus", "gridPos": { }, "id": 7, "mode": "html", "span": 2, "title": "", "transparent": true, "type": "text" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": true, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "decimals": 0, "description": "Number of connected clients during this time window", "format": "none", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 8, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": true }, "tableColumn": "", "targets": [ { "expr": "sum(mcac_client_connected_native_clients{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "100,1000", "title": "CQL Clients", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": true, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "description": "Client timeouts over the last $rate", "format": "none", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 9, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": true }, "tableColumn": "", "targets": [ { "expr": "sum(irate(mcac_client_request_timeouts_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "100,300", "title": "Timeouts / $rate", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": true, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "description": "Hints stored over the last $rate", "format": "none", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 10, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": true }, "tableColumn": "", "targets": [ { "expr": "sum(irate(mcac_storage_hints_on_disk_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "1000,30000", "title": "Hints / $rate", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": false, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "description": "Data", "format": "bytes", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 11, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": true }, "tableColumn": "", "targets": [ { "expr": "sum(mcac_table_live_disk_space_used_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "", "title": "Data Size", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": false, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "decimals": 1, "description": "Data", "format": "ms", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 12, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 1, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": true }, "tableColumn": "", "targets": [ { "expr": "sum(rate(mcac_jvm_gc_time{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "", "title": "GC Time / $rate", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Cluster Overview", "titleSize": "h6", "type": "row" }, { "collapse": false, "collapsed": false, "height": 300, "panels": [ { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "(no keyspace/table filters apply)", "fill": 1, "fillGradient": 0, "gridPos": { }, "id": 13, "legend": { "alignAsTable": false, "avg": false, "current": false, "hideEmpty": true, "hideZero": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "/.*Connected/", "yaxis": 2 } ], "spaceLength": 10, "span": 4, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum(irate(mcac_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate])) by ($by, request_type)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{$by}}:{{request_type}}", "refId": "A" }, { "expr": "sum(mcac_client_connected_native_clients{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{$by}}:Clients Connected", "refId": "B" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Requests Served / $by / $rate", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "short", "label": null, "logBase": 1, "max": null, "min": null, "show": true }, { "format": "short", "label": "Clients Connected", "logBase": 1, "max": null, "min": null, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "(no keyspace/table filters apply)", "fill": 1, "fillGradient": 0, "gridPos": { }, "id": 14, "legend": { "alignAsTable": false, "avg": false, "current": false, "hideEmpty": true, "hideZero": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "span": 4, "stack": false, "steppedLine": false, "targets": [ { "expr": "histogram_quantile($latency, sum(rate(mcac_client_request_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate])) by (le, request_type, $by))", "format": "time_series", "intervalFactor": 2, "legendFormat": "$by:{{$by}} {{$latency}} {{request_type}}", "refId": "A" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Coordinator $latency Latency / $by", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "fill": 1, "fillGradient": 0, "gridPos": { }, "id": 15, "legend": { "alignAsTable": false, "avg": false, "current": false, "hideEmpty": true, "hideZero": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "/.*Flushes/", "bars": true, "lines": false, "yaxis": 2, "zindex": -3 } ], "spaceLength": 10, "span": 4, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum(mcac_table_memtable_off_heap_size{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{$by}} : Off Heap", "refId": "A" }, { "expr": "sum(mcac_table_memtable_on_heap_size{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{$by}} : On Heap", "refId": "B" }, { "expr": "sum(idelta(mcac_table_memtable_switch_count_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}[$rate])) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{$by}} : Flushes", "refId": "C" }, { "expr": "sum(idelta(mcac_table_pending_flushes_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}[$rate])) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{$by}} : Pending Flushes", "refId": "D" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Memtable Space $keyspace.$table / $by", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "bytes", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "short", "label": "Flush", "logBase": 1, "max": null, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "fill": 1, "fillGradient": 0, "gridPos": { }, "id": 16, "legend": { "alignAsTable": false, "avg": false, "current": false, "hideEmpty": true, "hideZero": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "/.*Compactions/", "bars": true, "lines": false, "yaxis": 2, "zindex": -3 } ], "spaceLength": 10, "span": 4, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum(irate(mcac_table_compaction_bytes_written_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}[$rate])) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{by}} : Bytes Compacted", "refId": "A" }, { "expr": "sum(irate(mcac_table_pending_compactions{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}[$rate])) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{by}} : Pending Compactions", "refId": "B" }, { "expr": "sum(irate(mcac_compaction_completed_tasks{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate])) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{by}} : Completed Compactions", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Compactions $keyspace.$table / $by", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "bps", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "short", "label": "Count", "logBase": 1, "max": null, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "", "fill": 1, "fillGradient": 0, "gridPos": { }, "id": 17, "legend": { "alignAsTable": false, "avg": false, "current": false, "hideEmpty": true, "hideZero": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "span": 4, "stack": false, "steppedLine": false, "targets": [ { "expr": "histogram_quantile($latency, sum(irate(mcac_table_range_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}[$rate])) by (le, $by))", "format": "time_series", "intervalFactor": 2, "legendFormat": "$by:{{$by}} Local Range Scan", "refId": "A" }, { "expr": "histogram_quantile($latency, sum(irate(mcac_table_read_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}[$rate])) by (le, $by))", "format": "time_series", "intervalFactor": 2, "legendFormat": "$by:{{$by}} Local Read", "refId": "B" }, { "expr": "histogram_quantile($latency, sum(irate(mcac_table_write_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}[$rate])) by (le, $by))", "format": "time_series", "intervalFactor": 2, "legendFormat": "$by:{{$by}} Local Write", "refId": "C" }, { "expr": "histogram_quantile($latency, sum(irate(mcac_table_coordinator_read_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\"}[$rate])) by (le, $by))", "format": "time_series", "intervalFactor": 2, "legendFormat": "$by:{{$by}} Coordinator Read", "refId": "D" }, { "expr": "histogram_quantile($latency, sum(irate(mcac_table_coordinator_scan_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", keyspace=~\"$keyspace\", table=~\"$table\", instance=~\"$host\"}[$rate])) by (le, $by))", "format": "time_series", "intervalFactor": 2, "legendFormat": "$by:{{$by}} Coordinator Range Scan", "refId": "E" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Table $latency Latency / $by", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "", "fill": 1, "fillGradient": 0, "gridPos": { }, "id": 18, "legend": { "alignAsTable": false, "avg": false, "current": false, "hideEmpty": true, "hideZero": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "span": 4, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum(irate(mcac_streaming_total_incoming_bytes_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate])) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{$by}}: Incoming Stream", "refId": "A" }, { "expr": "sum(irate(mcac_streaming_total_outgoing_bytes_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$host\"}[$rate])) by ($by)", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{$by}}: Outgoing Stream", "refId": "B" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Streaming / $by / $rate", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "Bps", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "Bps", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Condensed Metrics", "titleSize": "h6", "type": "row" } ], "schemaVersion": 14, "style": "dark", "tags": [ "os" ], "templating": { "list": [ { "current": { "text": "Prometheus", "value": "Prometheus" }, "hide": 2, "label": null, "name": "PROMETHEUS_DS", "options": [ ], "query": "Prometheus", "refresh": 1, "regex": "", "type": "datasource" }, { "allValue": null, "current": { "text": "Cluster", "value": "cluster" }, "hide": 0, "includeAll": false, "label": "Group By", "multi": false, "name": "by", "options": [ { "text": "Cluster", "value": "cluster" }, { "text": "Datacenter", "value": "dc" }, { "text": "Rack", "value": "rack" }, { "text": "Host", "value": "instance" } ], "query": "cluster,dc,rack,instance", "refresh": 0, "type": "custom" }, { "auto": false, "auto_count": 300, "auto_min": "10s", "current": { "text": "5m", "value": "5m" }, "hide": 0, "label": "Rate", "name": "rate", "query": "1m,5m,10m,30m,1h,6h,12h,1d,7d,14d,30d", "refresh": 2, "type": "interval" }, { "allValue": ".*", "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": true, "label": "Cluster", "multi": false, "name": "cluster", "options": [ ], "query": "label_values(collectd_collectd_queue_length{}, cluster)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false }, { "allValue": ".*", "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": true, "label": "DataCenter", "multi": false, "name": "dc", "options": [ ], "query": "label_values(collectd_collectd_queue_length{cluster=~\"$cluster\"}, dc)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false }, { "allValue": ".*", "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": true, "label": "Rack", "multi": false, "name": "rack", "options": [ ], "query": "label_values(collectd_collectd_queue_length{cluster=~\"$cluster\", dc=~\"$dc\"}, rack)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false }, { "allValue": ".*", "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": true, "label": "Keyspace", "multi": false, "name": "keyspace", "options": [ ], "query": "label_values(mcac_table_read_latency_total{cluster=~\"$cluster\", dc=~\"$dc\"}, keyspace)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false }, { "allValue": ".*", "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": true, "label": "Table", "multi": false, "name": "table", "options": [ ], "query": "label_values(mcac_table_read_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", keyspace=~\"$keyspace\"}, table)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false }, { "allValue": ".*", "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": true, "label": "Host", "multi": false, "name": "host", "options": [ ], "query": "label_values(collectd_collectd_queue_length{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\"}, instance)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false }, { "allValue": null, "current": { "text": "P95", "value": "0.95" }, "hide": 0, "includeAll": false, "label": "Percentile", "multi": false, "name": "latency", "options": [ { "text": "P999", "value": "0.999" }, { "text": "P99", "value": "0.99" }, { "text": "P98", "value": "0.98" }, { "text": "P95", "value": "0.95" }, { "text": "P90", "value": "0.90" }, { "text": "P75", "value": "0.75" }, { "text": "P50", "value": "0.50" } ], "query": "0.999,0.99,0.98,0.95,0.90,0.75,0.50", "refresh": 0, "type": "custom" } ] }, "time": { "from": "now-30m", "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": "browser", "title": "Cassandra Cluster Condensed", "version": 0 } --- apiVersion: v1 kind: ConfigMap metadata: name: k8ssandra-cassandra-overview-dashboard namespace: k8ssandra-operator labels: grafana_dashboard: "1" data: cassandra-overview.json: | { "__inputs": [ ], "__requires": [ ], "annotations": { "list": [ ] }, "editable": true, "gnetId": null, "graphTooltip": 0, "hideControls": false, "id": null, "links": [ ], "refresh": "30s", "rows": [ { "collapse": false, "collapsed": false, "panels": [ { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Total Requests Per Cluster, by Request Type", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 5, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "Stargate write", "color": "#8F3BB8" }, { "alias": "Stargate read", "color": "#C4162A" }, { "alias": "Stargate cas_read", "color": "#FA6400" }, { "alias": "Stargate cas_write", "color": "#E0B400" }, { "alias": "Stargate range_slice", "color": "#1F60C4" }, { "alias": "Stargate view_write", "color": "#37872D" }, { "alias": "write", "color": "#96D98D" }, { "alias": "read", "color": "#8AB8FF" }, { "alias": "cas_read", "color": "#FFF899" }, { "alias": "cas_write", "color": "#FFB357" }, { "alias": "range_slice", "color": "#FF7383" }, { "alias": "view_write", "color": "#DEB6F2" } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum by (cluster, request_type) (rate(mcac_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{request_type}}", "refId": "A" }, { "expr": "sum by (cluster, request_type) (rate(stargate_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate {{request_type}}", "refId": "B" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Request Throughputs", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "rps", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "rps", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Total Timeouts, Failures, Unavailable Rates for each cluster", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 6, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum by (cluster, request_type) (rate(mcac_client_request_failures_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{request_type}} failures", "refId": "A" }, { "expr": "sum by (cluster, request_type) (rate(mcac_client_request_timeouts_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{request_type}} timeouts", "refId": "B" }, { "expr": "sum by (cluster, request_type) (rate(mcac_client_request_unavailables_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{request_type}} unavailable errors", "refId": "C" }, { "expr": "sum by (cluster, request_type) (rate(mcac_client_request_unfinished_commit_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{request_type}} unfinished commit errors", "refId": "D" }, { "expr": "sum by (cluster, request_type) (rate(mcac_client_request_condition_not_met_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{request_type}} condition not met errors", "refId": "E" }, { "expr": "sum by (cluster, request_type) (rate(mcac_client_request_contention_histogram_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{request_type}} contention histogram errors", "refId": "F" }, { "expr": "sum by (cluster, request_type) (rate(stargate_client_request_failures_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate {{request_type}} failures", "refId": "G" }, { "expr": "sum by (cluster, request_type) (rate(stargate_client_request_timeouts_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate {{request_type}} timeouts", "refId": "H" }, { "expr": "sum by (cluster, request_type) (rate(stargate_client_request_unavailables_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate {{request_type}} unavailable errors", "refId": "I" }, { "expr": "sum by (cluster, request_type) (rate(stargate_client_request_unfinished_commit_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate {{request_type}} unfinished commit errors", "refId": "J" }, { "expr": "sum by (cluster, request_type) (rate(stargate_client_request_condition_not_met_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate {{request_type}} condition not met errors", "refId": "K" }, { "expr": "sum by (cluster, request_type) (rate(stargate_client_request_contention_histogram_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate {{request_type}} contention histogram errors", "refId": "L" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Error throughputs", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "rps", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "rps", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] }, { "cacheTimeout": null, "colorBackground": false, "colorValue": false, "colors": [ "#DEB6F2", "#CA95E5", "#8F3BB8" ], "datasource": "Prometheus", "decimals": 2, "description": "Part of reads in the total of standard requests (Reads+Writes). CAS, Views, ... operations are ignored.", "format": "percentunit", "gauge": { "maxValue": 1, "minValue": 0, "show": true, "thresholdLabels": true, "thresholdMarkers": false }, "gridPos": { }, "id": 7, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": " Reads", "postfixFontSize": "30%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "#FFB357", "show": false }, "tableColumn": "", "targets": [ { "expr": "( sum by (cluster, request_type) (rate(mcac_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"read\"}[1m:30s])) + sum by (cluster, request_type) (rate(stargate_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"read\"}[1m:30s])) ) / ignoring (request_type) (sum by (cluster, request_type) (rate(mcac_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"read\"}[1m:30s])) + ignoring (request_type) sum by (cluster, request_type) (rate(mcac_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"write\"}[1m:30s])) + ignoring (request_type) sum by (cluster, request_type) (rate(stargate_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"read\"}[1m:30s])) + ignoring (request_type) sum by (cluster, request_type) (rate(stargate_client_request_latency_total{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"write\"}[1m:30s])))", "format": "time_series", "intervalFactor": 2, "legendFormat": "", "refId": "A" } ], "thresholds": "0.25,0.5,0.75", "timeFrom": "", "title": "Read / Write Distribution", "transparent": true, "type": "singlestat", "valueFontSize": "30%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "current" }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Read latency for coordinated reads", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 8, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "p999", "fillBelowTo": "p98", "lines": false }, { "alias": "p98", "lines": false }, { "alias": "Stargate p999", "fillBelowTo": "Stargate p98", "lines": false }, { "alias": "Stargate p98", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "histogram_quantile(0.98, sum(rate(mcac_client_request_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"read\"}[5m])) by (le, cluster))", "format": "time_series", "intervalFactor": 2, "legendFormat": "p98", "refId": "A" }, { "expr": "histogram_quantile(0.99, sum(rate(mcac_client_request_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"read\"}[5m])) by (le, cluster))", "format": "time_series", "intervalFactor": 2, "legendFormat": "p99", "refId": "B" }, { "expr": "histogram_quantile(0.999, sum(rate(mcac_client_request_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"read\"}[5m])) by (le, cluster))", "format": "time_series", "intervalFactor": 2, "legendFormat": "p999", "refId": "C" }, { "expr": "stargate_client_request_latency_quantile{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", quantile=~\"0.98\", request_type=\"read\"}*1000000", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate p98", "refId": "D" }, { "expr": "stargate_client_request_latency_quantile{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", quantile=~\"0.99\", request_type=\"read\"}*1000000", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate p99", "refId": "E" }, { "expr": "stargate_client_request_latency_quantile{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", quantile=~\"0.999\", request_type=\"read\"}*1000000", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate p999", "refId": "F" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Read Latency (98 - 999th percentile)", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Write latency for coordinated writes", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 9, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "p999", "fillBelowTo": "p98", "lines": false }, { "alias": "p98", "lines": false }, { "alias": "Stargate p999", "fillBelowTo": "Stargate p98", "lines": false }, { "alias": "Stargate p98", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "histogram_quantile(0.98, sum(rate(mcac_client_request_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"write\"}[5m])) by (le, cluster))", "format": "time_series", "intervalFactor": 2, "legendFormat": "p98", "refId": "A" }, { "expr": "histogram_quantile(0.99, sum(rate(mcac_client_request_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"write\"}[5m])) by (le, cluster))", "format": "time_series", "intervalFactor": 2, "legendFormat": "p99", "refId": "B" }, { "expr": "histogram_quantile(0.999, sum(rate(mcac_client_request_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type=\"write\"}[5m])) by (le, cluster))", "format": "time_series", "intervalFactor": 2, "legendFormat": "p999", "refId": "C" }, { "expr": "stargate_client_request_latency_quantile{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", quantile=~\"0.98\", request_type=\"write\"}*1000000", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate p98", "refId": "D" }, { "expr": "stargate_client_request_latency_quantile{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", quantile=~\"0.99\", request_type=\"write\"}*1000000", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate p99", "refId": "E" }, { "expr": "stargate_client_request_latency_quantile{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", quantile=~\"0.999\", request_type=\"write\"}*1000000", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate p999", "refId": "F" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Write Latency (98th - p999 Percentile)", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Other p99 latencies for coordinated requests", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 10, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "histogram_quantile(0.99, sum(rate(mcac_client_request_latency_bucket{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", request_type!~\"write|read|.*-.*\"}[1m:30s])) by (le, request_type, cluster))", "format": "time_series", "intervalFactor": 2, "legendFormat": "p99 {{request_type}}", "refId": "A" }, { "expr": "stargate_client_request_latency_quantile{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", quantile=~\"0.99\", request_type!~\"write|read|.*-.*\"}*1000000", "format": "time_series", "intervalFactor": 2, "legendFormat": "Stargate p99 {{request_type}}", "refId": "B" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Other Latencies", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "format": "µs", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Request Throughputs (Coordinator Perspective)", "titleSize": "h6", "type": "row" }, { "collapse": false, "collapsed": false, "panels": [ { "datasource": "Prometheus", "description": "Nodes Status uses Internal/Gossip activity. Be mindful that if Native or Thrift protocol are disabled, the nodes won't be reachable, and still marked up", "gridPos": { }, "id": 11, "mappingType": 2, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "polystat": { "globalOperatorName": "current", "globalThresholds": [ { "color": "#d44a3a", "state": 2, "value": 0 }, { "color": "#299c46", "state": 0, "value": 1 } ], "globalUnitFormat": "none", "valueEnabled": true }, "rangeMaps": [ { "from": "0", "text": "DOWN", "to": "0.9999" }, { "from": "1", "text": "UP", "to": "1" } ], "span": 12, "targets": [ { "expr": "max by (cluster, dc, rack, instance) (changes(mcac_thread_pools_completed_tasks{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", pool_name=\"gossip_stage\"}[2m:30s])) > bool 0", "format": "time_series", "instant": true, "intervalFactor": 2, "legendFormat": "{{instance}}", "refId": "A" } ], "title": "Nodes Status", "transparent": true, "type": "grafana-polystat-panel" }, { "cacheTimeout": null, "colorBackground": false, "colorValue": false, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "Prometheus", "decimals": 0, "description": "Nodes up and down in the cluster", "format": "short", "gauge": { "maxValue": 100, "minValue": 0, "show": false, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { }, "id": 12, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": " Nodes", "postfixFontSize": "80%", "prefix": "Total:", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "span": 4, "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": false }, "tableColumn": "", "targets": [ { "expr": "count by (cluster) (max by (cluster, dc, rack, instance) (collectd_collectd_queue_length{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Total Number Of Nodes", "refId": "A" } ], "thresholds": "", "title": "Nodes Count", "transparent": true, "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "avg" }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "decimals": 0, "description": "Nodes up and down in the cluster per protocol/activity", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 13, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": false, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "span": 8, "stack": false, "steppedLine": false, "targets": [ { "expr": "count by (cluster) (max by (cluster, dc, rack, instance) (collectd_collectd_queue_length{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}))", "format": "time_series", "intervalFactor": 2, "legendFormat": "Total Number Of Nodes", "refId": "A" }, { "expr": "sum by (cluster) (max by (cluster, datacenter, rack, instance) (changes(mcac_thread_pools_completed_tasks{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", pool_name=\"native\"}[2m:30s])) > bool 0)", "format": "time_series", "intervalFactor": 2, "legendFormat": "Nodes Coordinating Requests (Native protocol)", "refId": "B" }, { "expr": "sum by (cluster) (max by (cluster, datacenter, rack, instance) (changes(mcac_thread_pools_completed_tasks{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", pool_name=\"gossip_stage\"}[2m:30s])) > bool 0)", "format": "time_series", "intervalFactor": 2, "legendFormat": "Nodes With Internal Activity (Gossip protocol)", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Nodes Status History", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "decimals": 0, "format": "short", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "decimals": 0, "format": "short", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Nodes Status", "titleSize": "h6", "type": "row" }, { "collapse": false, "collapsed": false, "panels": [ { "columns": [ { "text": "Current", "value": "current" } ], "datasource": "Prometheus", "description": "Disk space used ordered (fullest disks first)", "gridPos": { }, "id": 14, "links": [ ], "sort": { "col": 1, "desc": true }, "styles": [ { "alias": "Node --> Mounting Point", "colorMode": null, "colors": [ "rgba(245, 54, 54, 0.9)", "rgba(237, 129, 40, 0.89)", "rgba(50, 172, 45, 0.97)" ], "dateFormat": "YYYY-MM-DD HH:mm:ss", "decimals": 2, "mappingType": 1, "pattern": "Metric", "preserveFormat": true, "sanitize": true, "thresholds": [ ], "type": "string", "unit": "short" }, { "alias": "% Disk Space Used", "colorMode": "row", "colors": [ "rgba(50, 172, 45, 0.97)", "rgba(237, 129, 40, 0.89)", "rgba(245, 54, 54, 0.9)" ], "dateFormat": "YYYY-MM-DD HH:mm:ss", "decimals": 2, "link": false, "mappingType": 1, "pattern": "Current", "thresholds": [ "0.5", "0.75" ], "type": "number", "unit": "percentunit" } ], "targets": [ { "expr": "min by (instance, df) (1-(collectd_df_df_complex{df!~\".*lxcfs.*\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", type=\"free\"}\n / ignoring (type) (collectd_df_df_complex{df!~\".*lxcfs.*\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", type=\"used\"}\n + ignoring (type) collectd_df_df_complex{df!~\".*lxcfs.*\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", type=\"reserved\"}\n + ignoring (type) collectd_df_df_complex{df!~\".*lxcfs.*\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\", type=\"free\"}))\n )", "format": "time_series", "instant": true, "intervalFactor": 2, "legendFormat": "{{cluster}}-{{instance}} --> {{df}}", "refId": "A" } ], "timeFrom": null, "timeShift": null, "title": "Disk Space Usage", "transform": "timeseries_aggregations", "transparent": true, "type": "table" }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Total sizes of the data on distinct nodes", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 15, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum by (cluster) (mcac_table_live_disk_space_used_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "Live space - {{cluster}}", "refId": "A" }, { "expr": "sum by (cluster) (mcac_table_total_disk_space_used_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "Total space - {{cluster}}", "refId": "B" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Cassandra cluster Data Size", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": "bytes", "label": null, "logBase": 1, "max": null, "min": null, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "SSTable Count Max and Average per table", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 16, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "max by (cluster, keyspace, table) (mcac_table_live_ss_table_count{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "Table - {{keyspace}}.{{table}}", "refId": "A" }, { "expr": "max by (cluster) (mcac_table_live_ss_table_count{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "Max in cluster - {{cluster}}", "refId": "B" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "SSTable Count", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "decimals": 0, "description": "Maximum pending compactions on any node in the cluster", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 17, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "max", "fillBelowTo": "min", "lines": false }, { "alias": "min", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "max by (cluster) (mcac_table_pending_compactions{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "max", "refId": "A" }, { "expr": "min by (cluster) (mcac_table_pending_compactions{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "min", "refId": "B" }, { "expr": "avg by (cluster) (mcac_table_pending_compactions{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "avg", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Pending Compactions", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "decimals": 0, "format": "short", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "decimals": 0, "format": "short", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "decimals": 0, "description": "Maximum pending compactions per table", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 18, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": true, "steppedLine": false, "targets": [ { "expr": "max by (cluster, keyspace, table) (mcac_table_pending_compactions{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "max for {{keyspace}}.{{table}}", "refId": "A" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Pending Compactions per Table", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "decimals": 0, "format": "short", "label": null, "logBase": 1, "max": null, "min": 0, "show": true }, { "decimals": 0, "format": "short", "label": null, "logBase": 1, "max": null, "min": 0, "show": true } ] } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Data Status", "titleSize": "h6", "type": "row" }, { "collapse": false, "collapsed": false, "panels": [ { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Cluster wide pending threads, by thread pool name", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 19, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum by (cluster, pool_name) (mcac_thread_pools_pending_tasks{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}} - pending {{pool_name}}", "refId": "A" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Pending Tasks", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Cluster wide blocked threads, by thread pool name", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 20, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum by (cluster, pool_name) (rate(mcac_thread_pools_total_blocked_tasks_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}} - blocked {{pool_name}}", "refId": "A" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Blocked Tasks", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Dropped messages rate summed by message type and cluster", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 21, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum by (cluster, message_type) (rate(mcac_dropped_message_dropped_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}} - dropped {{message_type}}", "refId": "A" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Dropped Messages", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "active threads summed per cluster", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 22, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum by (cluster, pool_name) (mcac_thread_pools_active_tasks{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "{{cluster}} - active {{pool_name}}", "refId": "A" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Active Tasks", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Sum of hints being handed off per cluster.", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 23, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum by (cluster) (mcac_storage_total_hints_in_progress_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "count", "refId": "A" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Hinted Handoff", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": 0, "show": true } ] } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Cassandra Internals", "titleSize": "h6", "type": "row" }, { "collapse": false, "collapsed": false, "panels": [ { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "decimals": 1, "description": "Maximum CPU utilisation (max 100%)", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 24, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": true, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "max", "fillBelowTo": "min", "lines": false }, { "alias": "min", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "max by (cluster) (1 - (sum by (cluster, dc, rack, instance) (rate(collectd_cpu_total{type=\"idle\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s])) / sum by (cluster, dc, rack, instance) (rate(collectd_cpu_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))))", "format": "time_series", "intervalFactor": 2, "legendFormat": "max", "refId": "A" }, { "expr": "min by (cluster) (1 - (sum by (cluster, dc, rack, instance) (rate(collectd_cpu_total{type=\"idle\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s])) / sum by (cluster, dc, rack, instance) (rate(collectd_cpu_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))))", "format": "time_series", "intervalFactor": 2, "legendFormat": "min", "refId": "B" }, { "expr": "avg by (cluster) (1 - (sum by (cluster, dc, rack, instance) (rate(collectd_cpu_total{type=\"idle\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s])) / sum by (cluster, dc, rack, instance) (rate(collectd_cpu_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))))", "format": "time_series", "intervalFactor": 2, "legendFormat": "avg", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "CPU Utilization", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "decimals": 1, "format": "percentunit", "label": null, "logBase": 1, "max": 1, "min": 0, "show": true }, { "decimals": 1, "format": "percentunit", "label": null, "logBase": 1, "max": 1, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Max Unix load on a node for a cluster", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 25, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "max", "fillBelowTo": "min", "lines": false }, { "alias": "min", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "max by (cluster) (collectd_load_shortterm{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "max", "refId": "A" }, { "expr": "min by (cluster) (collectd_load_shortterm{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "min", "refId": "B" }, { "expr": "avg by (cluster) (collectd_load_shortterm{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "avg", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Unix Load (1m rate)", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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 } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Maximum Memory allocated per usage (worst node) - excludes caches, buffers, etc", "fill": 1, "fillGradient": 0, "gridPos": { }, "id": 26, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 2, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "min by (cluster) (sum by (cluster, dc, rack, instance) (collectd_memory{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}))", "format": "time_series", "intervalFactor": 2, "legendFormat": "min memory available", "refId": "A" }, { "expr": "max by (cluster, memory) (sum by (cluster, dc, rack, instance, memory) (collectd_memory{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}))", "format": "time_series", "intervalFactor": 2, "legendFormat": "max memory {{memory}}", "refId": "B" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Memory Utilisation", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": "bytes", "label": null, "logBase": 1, "max": null, "min": null, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Disk read throughput", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 27, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "max", "fillBelowTo": "min", "lines": false }, { "alias": "min", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "max by (cluster) (rate(collectd_processes_disk_octets_read_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "max", "refId": "A" }, { "expr": "min by (cluster) (rate(collectd_processes_disk_octets_read_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "min", "refId": "B" }, { "expr": "avg by (cluster) (rate(collectd_processes_disk_octets_read_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "avg", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Disk Read Thoughput", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "bps", "label": null, "logBase": 1, "max": null, "min": null, "show": true }, { "format": "bps", "label": null, "logBase": 1, "max": null, "min": null, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Disk write throughput", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 28, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "max", "fillBelowTo": "min", "lines": false }, { "alias": "min", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "max by (cluster) (rate(collectd_processes_disk_octets_write_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "max", "refId": "A" }, { "expr": "min by (cluster) (rate(collectd_processes_disk_octets_write_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "min", "refId": "B" }, { "expr": "avg by (cluster) (rate(collectd_processes_disk_octets_write_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "avg", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Disk Write Thoughput", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "bps", "label": null, "logBase": 1, "max": null, "min": null, "show": true }, { "format": "bps", "label": null, "logBase": 1, "max": null, "min": null, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Network In and Out per cluster", "fill": 1, "fillGradient": 0, "gridPos": { }, "id": 29, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "incoming", "transform": "negative-Y" } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "sum by (cluster) (rate(collectd_interface_if_octets_rx_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "outgoing", "refId": "A" }, { "expr": "sum by (cluster) (rate(collectd_interface_if_octets_rx_total{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "incoming", "refId": "B" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Network I/O", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": "bytes", "label": null, "logBase": 1, "max": null, "min": null, "show": true } ] } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "Hardware / Operating System", "titleSize": "h6", "type": "row" }, { "collapse": false, "collapsed": false, "panels": [ { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "decimals": 2, "description": "Percentage of the time the node is *not* doing a GC, thus Cassandra is not stopped for GC", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 30, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "max", "fillBelowTo": "min", "lines": false }, { "alias": "min", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "max by (cluster) (1 - (sum by (cluster, dc, rack, instance) (rate(mcac_jvm_gc_time{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s])) / 1000))", "format": "time_series", "intervalFactor": 2, "legendFormat": "max", "refId": "A" }, { "expr": "min by (cluster) (1 - (sum by (cluster, dc, rack, instance) (rate(mcac_jvm_gc_time{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s])) / 1000))", "format": "time_series", "intervalFactor": 2, "legendFormat": "min", "refId": "B" }, { "expr": "avg by (cluster) (1 - (sum by (cluster, dc, rack, instance) (rate(mcac_jvm_gc_time{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s])) / 1000))", "format": "time_series", "intervalFactor": 2, "legendFormat": "avg", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Application Throughput (% time NOT doing GC)", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "decimals": 2, "format": "percentunit", "label": null, "logBase": 1, "max": 1, "min": 0, "show": true }, { "decimals": 2, "format": "percentunit", "label": null, "logBase": 1, "max": 1, "min": 0, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Garbage collection duration", "fill": 0, "fillGradient": 0, "gridPos": { }, "id": 31, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "max", "fillBelowTo": "min", "lines": false }, { "alias": "min", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "max by (cluster) (rate(mcac_jvm_gc_time{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "max", "refId": "A" }, { "expr": "min by (cluster) (rate(mcac_jvm_gc_time{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "min", "refId": "B" }, { "expr": "avg by (cluster) (rate(mcac_jvm_gc_time{cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"}[1m:30s]))", "format": "time_series", "intervalFactor": 2, "legendFormat": "avg", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Garbage Collection Time", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "ms", "label": null, "logBase": 1, "max": null, "min": null, "show": true }, { "format": "ms", "label": null, "logBase": 1, "max": null, "min": null, "show": true } ] }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "Maximum JVM Heap Memory size (worst node) and minimum available heap size", "fill": 1, "fillGradient": 0, "gridPos": { }, "id": 32, "legend": { "alignAsTable": true, "avg": false, "current": true, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "sort": "current", "sortDesc": true, "total": false, "values": true }, "lines": true, "linewidth": 2, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ { "alias": "max", "fillBelowTo": "min", "lines": false }, { "alias": "min", "lines": false } ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "max by (cluster)\n (mcac_jvm_memory_used{memory_type=\"heap\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "max", "refId": "A" }, { "expr": "min by (cluster)\n (mcac_jvm_memory_used{memory_type=\"heap\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "min", "refId": "B" }, { "expr": "avg by (cluster)\n (mcac_jvm_memory_used{memory_type=\"heap\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "avg", "refId": "C" }, { "expr": "min by ( cluster)\n (mcac_jvm_memory_max{memory_type=\"heap\", cluster=\"$cluster\", dc=~\"$dc\", rack=~\"$rack\", instance=~\"$node\"})", "format": "time_series", "intervalFactor": 2, "legendFormat": "Heap memory available", "refId": "D" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "JVM Heap Memory Utilisation", "tooltip": { "shared": false, "sort": 0, "value_type": "individual" }, "transparent": true, "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": "bytes", "label": null, "logBase": 1, "max": null, "min": null, "show": true } ] } ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "JVM / Garbage Collection", "titleSize": "h6", "type": "row" } ], "schemaVersion": 14, "style": "dark", "tags": [ "Cassandra", "Overview" ], "templating": { "list": [ { "current": { "text": "Prometheus", "value": "Prometheus" }, "hide": 2, "label": null, "name": "PROMETHEUS_DS", "options": [ ], "query": "Prometheus", "refresh": 1, "regex": "", "type": "datasource" }, { "allValue": null, "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": false, "label": "Cluster", "multi": false, "name": "cluster", "options": [ ], "query": "label_values(collectd_collectd_queue_length{}, cluster)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false }, { "allValue": ".*", "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": true, "label": "DataCenter", "multi": false, "name": "dc", "options": [ ], "query": "label_values(collectd_collectd_queue_length{cluster=~\"$cluster\"}, dc)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false }, { "allValue": ".*", "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": true, "label": "Rack", "multi": false, "name": "rack", "options": [ ], "query": "label_values(collectd_collectd_queue_length{cluster=~\"$cluster\", dc=~\"$dc\"}, rack)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false }, { "allValue": ".*", "current": { }, "datasource": "Prometheus", "hide": 0, "includeAll": true, "label": "Node", "multi": false, "name": "node", "options": [ ], "query": "label_values(collectd_collectd_queue_length{cluster=~\"$cluster\", dc=~\"$dc\", rack=~\"$rack\"}, instance)", "refresh": 2, "regex": "", "sort": 0, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false } ] }, "time": { "from": "now-30m", "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": "browser", "title": "Cassandra Overview", "version": 0 } --- apiVersion: v1 kind: ConfigMap metadata: name: k8ssandra-stargate-dashboard namespace: k8ssandra-operator labels: grafana_dashboard: "1" data: stargate.json: | { "annotations": { "list": [ { "builtIn": 1, "datasource": "-- Grafana --", "enable": true, "hide": true, "iconColor": "rgba(0, 211, 255, 1)", "name": "Annotations & Alerts", "type": "dashboard" } ] }, "editable": true, "gnetId": null, "graphTooltip": 0, "id": 3, "links": [], "panels": [ { "aliasColors": {}, "bars": false, "dashLength": 10, "dashes": false, "datasource": "Prometheus", "description": "", "fieldConfig": { "defaults": { "custom": {} }, "overrides": [] }, "fill": 1, "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 }, "hiddenSeries": false, "id": 8, "legend": { "alignAsTable": true, "avg": false, "current": false, "max": true, "min": false, "rightSide": true, "show": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "nullPointMode": "null as zero", "options": { "alertThreshold": true }, "percentage": false, "pluginVersion": "7.3.5", "pointradius": 2, "points": false, "renderer": "flot", "seriesOverrides": [], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "restapi_io_dropwizard_jetty_MutableServletContextHandler_percent_4xx_1m", "interval": "1m", "legendFormat": "{{pod}}", "refId": "A" } ], "thresholds": [], "timeFrom": null, "timeRegions": [], "timeShift": null, "title": "4xx Errors", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [] }, "yaxes": [ { "$$hashKey": "object:143", "decimals": null, "format": "percentunit", "label": "", "logBase": 1, "max": "1", "min": "0", "show": true }, { "$$hashKey": "object:144", "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": "Prometheus", "description": "", "fieldConfig": { "defaults": { "custom": {} }, "overrides": [] }, "fill": 1, "fillGradient": 0, "gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 }, "hiddenSeries": false, "id": 5, "legend": { "alignAsTable": true, "avg": false, "current": false, "max": true, "min": false, "rightSide": true, "show": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "nullPointMode": "null as zero", "options": { "alertThreshold": true }, "percentage": false, "pluginVersion": "7.3.5", "pointradius": 2, "points": false, "renderer": "flot", "seriesOverrides": [], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "restapi_io_dropwizard_jetty_MutableServletContextHandler_percent_5xx_1m", "interval": "1m", "legendFormat": "{{pod}}", "refId": "A" } ], "thresholds": [], "timeFrom": null, "timeRegions": [], "timeShift": null, "title": "5xx Errors", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [] }, "yaxes": [ { "$$hashKey": "object:143", "decimals": null, "format": "percentunit", "label": "", "logBase": 1, "max": "1", "min": "0", "show": true }, { "$$hashKey": "object:144", "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": "Prometheus", "fieldConfig": { "defaults": { "custom": {} }, "overrides": [] }, "fill": 1, "fillGradient": 0, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 8 }, "hiddenSeries": false, "id": 7, "legend": { "alignAsTable": true, "avg": true, "current": false, "hideEmpty": true, "hideZero": true, "max": true, "min": false, "rightSide": true, "show": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "nullPointMode": "null as zero", "options": { "alertThreshold": true }, "percentage": false, "pluginVersion": "7.3.5", "pointradius": 2, "points": false, "renderer": "flot", "seriesOverrides": [], "spaceLength": 10, "stack": true, "steppedLine": false, "targets": [ { "expr": "rate(restapi_io_dropwizard_jetty_MutableServletContextHandler_requests_count[1m])", "interval": "15s", "legendFormat": "{{pod}}", "refId": "A" } ], "thresholds": [], "timeFrom": null, "timeRegions": [], "timeShift": null, "title": "HTTP Requests per Second", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [] }, "yaxes": [ { "$$hashKey": "object:315", "format": "short", "label": null, "logBase": 1, "max": null, "min": "0", "show": true }, { "$$hashKey": "object:316", "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": { "custom": {}, "mappings": [], "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [] }, "fill": 1, "fillGradient": 0, "gridPos": { "h": 13, "w": 24, "x": 0, "y": 16 }, "hiddenSeries": false, "id": 2, "legend": { "alignAsTable": true, "avg": true, "current": false, "hideEmpty": true, "hideZero": true, "max": true, "min": false, "rightSide": true, "show": true, "total": false, "values": true }, "lines": true, "linewidth": 1, "nullPointMode": "connected", "options": { "alertThreshold": true }, "percentage": false, "pluginVersion": "7.3.5", "pointradius": 2, "points": false, "renderer": "flot", "seriesOverrides": [], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "jvm_memory_heap_used", "instant": false, "interval": "15s", "legendFormat": "{{pod}} Usage", "refId": "A" }, { "expr": "jvm_memory_heap_max", "interval": "15s", "legendFormat": "{{pod}} Max", "refId": "B" } ], "thresholds": [], "timeFrom": null, "timeRegions": [], "timeShift": null, "title": "JVM Heap Usage", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "graph", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [] }, "yaxes": [ { "$$hashKey": "object:61", "format": "bytes", "label": null, "logBase": 1, "max": null, "min": "0", "show": true }, { "$$hashKey": "object:62", "format": "short", "label": null, "logBase": 1, "max": null, "min": null, "show": false } ], "yaxis": { "align": false, "alignLevel": null } } ], "refresh": false, "schemaVersion": 26, "style": "dark", "tags": [], "templating": { "list": [] }, "time": { "from": "now-1h", "to": "now" }, "timepicker": {}, "timezone": "", "title": "Stargate", "uid": "YnvTjHYGk", "version": 1 }