apiVersion: v1 data: osds-overview.json: |- { "__inputs": [ ], "__requires": [ { "id": "grafana", "name": "Grafana", "type": "grafana", "version": "5.0.0" }, { "id": "grafana-piechart-panel", "name": "Pie Chart", "type": "panel", "version": "1.3.3" }, { "id": "graph", "name": "Graph", "type": "panel", "version": "5.0.0" }, { "id": "table", "name": "Table", "type": "panel", "version": "5.0.0" } ], "annotations": { "list": [ { "builtIn": 1, "datasource": "-- Grafana --", "enable": true, "hide": true, "iconColor": "rgba(0, 211, 255, 1)", "name": "Annotations & Alerts", "showIn": 0, "tags": [ ], "type": "dashboard" } ] }, "description": "", "editable": false, "gnetId": null, "graphTooltip": 0, "hideControls": false, "id": null, "links": [ ], "panels": [ { "aliasColors": { "@95%ile": "#e0752d" }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "$datasource", "description": "", "fieldConfig": { "defaults": { "custom": { "fillOpacity": 8, "showPoints": "never" }, "unit": "ms" } }, "fill": 1, "fillGradient": 0, "gridPos": { "h": 8, "w": 8, "x": 0, "y": 0 }, "id": 2, "legend": { "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "avg (\n rate(ceph_osd_op_r_latency_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_r_latency_count{cluster=~\"$cluster\", }[$__rate_interval]) * 1000\n)\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "AVG read", "refId": "A" }, { "expr": "max(\n rate(ceph_osd_op_r_latency_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_r_latency_count{cluster=~\"$cluster\", }[$__rate_interval]) * 1000\n)\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "MAX read", "refId": "B" }, { "expr": "quantile(0.95,\n (\n rate(ceph_osd_op_r_latency_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_r_latency_count{cluster=~\"$cluster\", }[$__rate_interval])\n * 1000\n )\n)\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "@95%ile", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "OSD Read Latencies", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "timeseries", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "ms", "label": null, "logBase": 1, "max": null, "min": "0", "show": true }, { "format": "short", "label": null, "logBase": 1, "max": null, "min": "0", "show": true } ] }, { "columns": [ ], "datasource": "${datasource}", "fieldConfig": { "defaults": { "custom": { "align": "null", "cellOptions": { "type": "auto" }, "filterable": true, "inspect": false }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [ { "matcher": { "id": "byName", "options": "ceph_daemon" }, "properties": [ { "id": "displayName", "value": "OSD ID" }, { "id": "unit", "value": "short" }, { "id": "decimals", "value": 2 }, { "id": "custom.align", "value": null } ] }, { "matcher": { "id": "byName", "options": "Value" }, "properties": [ { "id": "displayName", "value": "Latency (ms)" }, { "id": "unit", "value": "none" }, { "id": "decimals", "value": 2 }, { "id": "custom.align", "value": null } ] } ] }, "gridPos": { "h": 8, "w": 4, "x": 8, "y": 0 }, "id": 3, "links": [ ], "options": { "footer": { "countRows": false, "enablePagination": false, "fields": "", "reducer": [ "sum" ], "show": false }, "frameIndex": 1, "showHeader": true }, "pluginVersion": "10.4.0", "styles": "", "targets": [ { "expr": "topk(10,\n (sort(\n (\n rate(ceph_osd_op_r_latency_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_r_latency_count{cluster=~\"$cluster\", }[$__rate_interval]) *\n 1000\n )\n ))\n)\n", "format": "table", "instant": true, "intervalFactor": 1, "legendFormat": "", "refId": "A" } ], "timeFrom": null, "timeShift": null, "title": "Highest READ Latencies", "transformations": [ { "id": "merge", "options": { "reducers": [ ] } }, { "id": "organize", "options": { "excludeByName": { "Time": true, "cluster": true }, "includeByName": { }, "indexByName": { }, "renameByName": { } } } ], "type": "table" }, { "aliasColors": { "@95%ile write": "#e0752d" }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "$datasource", "description": "", "fieldConfig": { "defaults": { "custom": { "fillOpacity": 8, "showPoints": "never" }, "unit": "ms" } }, "fill": 1, "fillGradient": 0, "gridPos": { "h": 8, "w": 8, "x": 12, "y": 0 }, "id": 4, "legend": { "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "avg(\n rate(ceph_osd_op_w_latency_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_w_latency_count{cluster=~\"$cluster\", }[$__rate_interval])\n * 1000\n)\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "AVG write", "refId": "A" }, { "expr": "max(\n rate(ceph_osd_op_w_latency_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_w_latency_count{cluster=~\"$cluster\", }[$__rate_interval]) *\n 1000\n)\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "MAX write", "refId": "B" }, { "expr": "quantile(0.95, (\n rate(ceph_osd_op_w_latency_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_w_latency_count{cluster=~\"$cluster\", }[$__rate_interval]) *\n 1000\n))\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "@95%ile write", "refId": "C" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "OSD Write Latencies", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "timeseries", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "ms", "label": null, "logBase": 1, "max": null, "min": "0", "show": true }, { "format": "short", "label": null, "logBase": 1, "max": null, "min": "0", "show": true } ] }, { "columns": [ ], "datasource": "${datasource}", "description": "This table shows the osd's that are delivering the 10 highest write latencies within the cluster", "fieldConfig": { "defaults": { "custom": { "align": "null", "cellOptions": { "type": "auto" }, "filterable": true, "inspect": false }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [ { "matcher": { "id": "byName", "options": "ceph_daemon" }, "properties": [ { "id": "displayName", "value": "OSD ID" }, { "id": "unit", "value": "short" }, { "id": "decimals", "value": 2 }, { "id": "custom.align", "value": null } ] }, { "matcher": { "id": "byName", "options": "Value" }, "properties": [ { "id": "displayName", "value": "Latency (ms)" }, { "id": "unit", "value": "none" }, { "id": "decimals", "value": 2 }, { "id": "custom.align", "value": null } ] }, { "matcher": { "id": "byName", "options": "Value" }, "properties": [ { "id": "mappings", "value": [ { "options": { "NaN": { "index": 0, "text": "0.00" } }, "type": "value" } ] }, { "id": "unit", "value": "none" }, { "id": "decimals", "value": 2 }, { "id": "custom.align", "value": null } ] } ] }, "gridPos": { "h": 8, "w": 4, "x": 20, "y": 0 }, "id": 5, "links": [ ], "options": { "footer": { "countRows": false, "enablePagination": false, "fields": "", "reducer": [ "sum" ], "show": false }, "frameIndex": 1, "showHeader": true }, "pluginVersion": "10.4.0", "styles": "", "targets": [ { "expr": "topk(10,\n (sort(\n (rate(ceph_osd_op_w_latency_sum{cluster=~\"$cluster\", }[$__rate_interval]) /\n on (ceph_daemon) rate(ceph_osd_op_w_latency_count{cluster=~\"$cluster\", }[$__rate_interval]) *\n 1000)\n ))\n)\n", "format": "table", "instant": true, "intervalFactor": 1, "legendFormat": "", "refId": "A" } ], "timeFrom": null, "timeShift": null, "title": "Highest WRITE Latencies", "transformations": [ { "id": "merge", "options": { "reducers": [ ] } }, { "id": "organize", "options": { "excludeByName": { "Time": true, "cluster": true }, "includeByName": { }, "indexByName": { }, "renameByName": { } } } ], "type": "table" }, { "datasource": "$datasource", "description": "", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } }, "mappings": [ ] }, "overrides": [ ] }, "gridPos": { "h": 8, "w": 4, "x": 0, "y": 8 }, "id": 6, "options": { "displayLabels": [ "percent" ], "legend": { "calcs": [ ], "displayMode": "table", "placement": "bottom", "showLegend": true, "values": [ "percent", "value" ] }, "pieType": "pie", "reduceOptions": { }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "expr": "count by (device_class) (ceph_osd_metadata{cluster=~\"$cluster\", })", "format": "time_series", "intervalFactor": 1, "legendFormat": "{{device_class}}", "refId": "A" } ], "title": "OSD Types Summary", "type": "piechart" }, { "datasource": "$datasource", "description": "", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } }, "mappings": [ ] }, "overrides": [ ] }, "gridPos": { "h": 8, "w": 4, "x": 4, "y": 8 }, "id": 7, "options": { "displayLabels": [ "percent" ], "legend": { "calcs": [ ], "displayMode": "table", "placement": "bottom", "showLegend": true, "values": [ "percent", "value" ] }, "pieType": "pie", "reduceOptions": { }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "expr": "count(ceph_bluefs_wal_total_bytes{cluster=~\"$cluster\", })", "format": "time_series", "intervalFactor": 2, "legendFormat": "bluestore", "refId": "A" }, { "expr": "absent(ceph_bluefs_wal_total_bytes{cluster=~\"$cluster\", }) * count(ceph_osd_metadata{cluster=~\"$cluster\", })", "format": "time_series", "intervalFactor": 2, "legendFormat": "filestore", "refId": "B" } ], "title": "OSD Objectstore Types", "type": "piechart" }, { "datasource": "$datasource", "description": "The pie chart shows the various OSD sizes used within the cluster", "fieldConfig": { "defaults": { "color": { "mode": "palette-classic" }, "custom": { "hideFrom": { "legend": false, "tooltip": false, "viz": false } }, "mappings": [ ] }, "overrides": [ ] }, "gridPos": { "h": 8, "w": 4, "x": 8, "y": 8 }, "id": 8, "options": { "displayLabels": [ "percent" ], "legend": { "calcs": [ ], "displayMode": "table", "placement": "bottom", "showLegend": true, "values": [ "percent", "value" ] }, "pieType": "pie", "reduceOptions": { }, "tooltip": { "mode": "single", "sort": "none" } }, "targets": [ { "expr": "count(ceph_osd_stat_bytes{cluster=~\"$cluster\", } < 1099511627776)", "format": "time_series", "intervalFactor": 2, "legendFormat": "<1TB", "refId": "A" }, { "expr": "count(ceph_osd_stat_bytes{cluster=~\"$cluster\", } >= 1099511627776 < 2199023255552)", "format": "time_series", "intervalFactor": 2, "legendFormat": "<2TB", "refId": "B" }, { "expr": "count(ceph_osd_stat_bytes{cluster=~\"$cluster\", } >= 2199023255552 < 3298534883328)", "format": "time_series", "intervalFactor": 2, "legendFormat": "<3TB", "refId": "C" }, { "expr": "count(ceph_osd_stat_bytes{cluster=~\"$cluster\", } >= 3298534883328 < 4398046511104)", "format": "time_series", "intervalFactor": 2, "legendFormat": "<4TB", "refId": "D" }, { "expr": "count(ceph_osd_stat_bytes{cluster=~\"$cluster\", } >= 4398046511104 < 6597069766656)", "format": "time_series", "intervalFactor": 2, "legendFormat": "<6TB", "refId": "E" }, { "expr": "count(ceph_osd_stat_bytes{cluster=~\"$cluster\", } >= 6597069766656 < 8796093022208)", "format": "time_series", "intervalFactor": 2, "legendFormat": "<8TB", "refId": "F" }, { "expr": "count(ceph_osd_stat_bytes{cluster=~\"$cluster\", } >= 8796093022208 < 10995116277760)", "format": "time_series", "intervalFactor": 2, "legendFormat": "<10TB", "refId": "G" }, { "expr": "count(ceph_osd_stat_bytes{cluster=~\"$cluster\", } >= 10995116277760 < 13194139533312)", "format": "time_series", "intervalFactor": 2, "legendFormat": "<12TB", "refId": "H" }, { "expr": "count(ceph_osd_stat_bytes{cluster=~\"$cluster\", } >= 13194139533312)", "format": "time_series", "intervalFactor": 2, "legendFormat": "<12TB+", "refId": "I" } ], "title": "OSD Size Summary", "type": "piechart" }, { "aliasColors": { }, "bars": true, "dashLength": 10, "dashes": false, "datasource": "$datasource", "fieldConfig": { "defaults": { "custom": { "fillOpacity": 8, "showPoints": "never" }, "unit": "short" } }, "fill": 1, "fillGradient": 0, "gridPos": { "h": 8, "w": 8, "x": 12, "y": 8 }, "id": 9, "legend": { "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "ceph_osd_numpg{cluster=~\"$cluster\", }", "format": "time_series", "instant": true, "intervalFactor": 1, "legendFormat": "PGs per OSD", "refId": "A" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Distribution of PGs per OSD", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "timeseries", "xaxis": { "buckets": 20, "mode": "histogram", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "short", "label": "# of OSDs", "logBase": 1, "max": null, "min": "0", "show": true }, { "format": "short", "label": null, "logBase": 1, "max": null, "min": "0", "show": true } ] }, { "cacheTimeout": null, "colorBackground": false, "colorValue": true, "colors": [ "#299c46", "rgba(237, 129, 40, 0.89)", "#d44a3a" ], "datasource": "$datasource", "description": "This gauge panel shows onode Hits ratio to help determine if increasing RAM per OSD could help improve the performance of the cluster", "format": "percentunit", "gauge": { "maxValue": 1, "minValue": 0, "show": true, "thresholdLabels": false, "thresholdMarkers": true }, "gridPos": { "h": 8, "w": 4, "x": 20, "y": 8 }, "id": 10, "interval": null, "links": [ ], "mappingType": 1, "mappingTypes": [ { "name": "value to text", "value": 1 }, { "name": "range to text", "value": 2 } ], "maxDataPoints": 100, "nullPointMode": "connected", "nullText": null, "postfix": "", "postfixFontSize": "50%", "prefix": "", "prefixFontSize": "50%", "rangeMaps": [ { "from": "null", "text": "N/A", "to": "null" } ], "sparkline": { "fillColor": "rgba(31, 118, 189, 0.18)", "full": false, "lineColor": "rgb(31, 120, 193)", "show": false }, "tableColumn": "", "targets": [ { "expr": "sum(ceph_bluestore_onode_hits{cluster=~\"$cluster\", }) / (\n sum(ceph_bluestore_onode_hits{cluster=~\"$cluster\", }) +\n sum(ceph_bluestore_onode_misses{cluster=~\"$cluster\", })\n)\n", "format": "time_series", "intervalFactor": 1, "legendFormat": "", "refId": "A" } ], "thresholds": ".75", "title": "OSD onode Hits Ratio", "type": "singlestat", "valueFontSize": "80%", "valueMaps": [ { "op": "=", "text": "N/A", "value": "null" } ], "valueName": "current" }, { "collapse": false, "collapsed": false, "gridPos": { "h": 1, "w": 24, "x": 0, "y": 16 }, "id": 11, "panels": [ ], "repeat": null, "repeatIteration": null, "repeatRowId": null, "showTitle": true, "title": "R/W Profile", "titleSize": "h6", "type": "row" }, { "aliasColors": { }, "bars": false, "dashLength": 10, "dashes": false, "datasource": "$datasource", "description": "Show the read/write workload profile overtime", "fieldConfig": { "defaults": { "custom": { "fillOpacity": 8, "showPoints": "never" }, "unit": "short" } }, "fill": 1, "fillGradient": 0, "gridPos": { "h": 8, "w": 24, "x": 0, "y": 17 }, "id": 12, "legend": { "alignAsTable": false, "avg": false, "current": false, "max": false, "min": false, "rightSide": false, "show": true, "sideWidth": null, "total": false, "values": false }, "lines": true, "linewidth": 1, "links": [ ], "nullPointMode": "null", "percentage": false, "pointradius": 5, "points": false, "renderer": "flot", "repeat": null, "seriesOverrides": [ ], "spaceLength": 10, "stack": false, "steppedLine": false, "targets": [ { "expr": "round(sum(rate(ceph_pool_rd{cluster=~\"$cluster\", }[$__rate_interval])))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Reads", "refId": "A" }, { "expr": "round(sum(rate(ceph_pool_wr{cluster=~\"$cluster\", }[$__rate_interval])))", "format": "time_series", "intervalFactor": 1, "legendFormat": "Writes", "refId": "B" } ], "thresholds": [ ], "timeFrom": null, "timeShift": null, "title": "Read/Write Profile", "tooltip": { "shared": true, "sort": 0, "value_type": "individual" }, "type": "timeseries", "xaxis": { "buckets": null, "mode": "time", "name": null, "show": true, "values": [ ] }, "yaxes": [ { "format": "short", "label": null, "logBase": 1, "max": null, "min": null, "show": true }, { "format": "short", "label": null, "logBase": 1, "max": null, "min": null, "show": true } ] }, { "columns": [ ], "datasource": "${datasource}", "description": "This table shows the 10 OSDs with the highest number of slow ops", "fieldConfig": { "defaults": { "custom": { "align": "null", "cellOptions": { "type": "auto" }, "filterable": true, "inspect": false }, "thresholds": { "mode": "absolute", "steps": [ { "color": "green", "value": null }, { "color": "red", "value": 80 } ] } }, "overrides": [ { "matcher": { "id": "byName", "options": "ceph_daemon" }, "properties": [ { "id": "displayName", "value": "OSD ID" }, { "id": "unit", "value": "short" }, { "id": "decimals", "value": 2 }, { "id": "custom.align", "value": null } ] }, { "matcher": { "id": "byName", "options": "Value" }, "properties": [ { "id": "displayName", "value": "Slow Ops" }, { "id": "unit", "value": "none" }, { "id": "decimals", "value": 2 }, { "id": "custom.align", "value": null } ] } ] }, "gridPos": { "h": 8, "w": 5, "x": 0, "y": 25 }, "id": 13, "links": [ ], "options": { "footer": { "countRows": false, "enablePagination": false, "fields": "", "reducer": [ "sum" ], "show": false }, "frameIndex": 1, "showHeader": true }, "pluginVersion": "10.4.0", "styles": "", "targets": [ { "expr": "topk(10,\n (ceph_daemon_health_metrics{type=\"SLOW_OPS\", ceph_daemon=~\"osd.*\"})\n)\n", "format": "table", "instant": true, "intervalFactor": 1, "legendFormat": "", "refId": "A" } ], "timeFrom": null, "timeShift": null, "title": "Top Slow Ops", "transformations": [ { "id": "merge", "options": { "reducers": [ ] } }, { "id": "organize", "options": { "excludeByName": { "Time": true, "__name__": true, "cluster": true, "instance": true, "job": true, "type": true }, "includeByName": { }, "indexByName": { }, "renameByName": { } } } ], "type": "table" } ], "refresh": "30s", "rows": [ ], "schemaVersion": 16, "style": "dark", "tags": [ "ceph-mixin" ], "templating": { "list": [ { "current": { "text": "default", "value": "default" }, "hide": 0, "label": "Data Source", "name": "datasource", "options": [ ], "query": "prometheus", "refresh": 1, "regex": "", "type": "datasource" }, { "allValue": null, "current": { }, "datasource": "$datasource", "hide": 0, "includeAll": false, "label": "cluster", "multi": false, "name": "cluster", "options": [ ], "query": "label_values(ceph_health_status, cluster)", "refresh": 1, "regex": "(.*)", "sort": 1, "tagValuesQuery": "", "tags": [ ], "tagsQuery": "", "type": "query", "useTags": false } ] }, "time": { "from": "now-1h", "to": "now" }, "timepicker": { "refresh_intervals": [ "5s", "10s", "30s", "1m", "5m", "15m", "30m", "1h", "2h", "1d" ], "time_options": [ "5m", "15m", "1h", "6h", "12h", "24h", "2d", "7d", "30d" ] }, "timezone": "", "title": "OSD Overview", "uid": "lo02I1Aiz", "version": 0 } kind: ConfigMap metadata: creationTimestamp: "2026-04-20T10:18:11Z" labels: grafana_dashboard: "1" name: kube-prometheus-stack-dashboard-osds-overview namespace: monitoring resourceVersion: "4085" uid: ab7f8b72-09c2-46c3-9c8a-7b6cd4cd45c6