Merge PR #67592 into tentacle

* refs/pull/67592/head:
	mgt/dashboard: Add the CPU, Memory to CephFS dashboard
	Fixes for subvolume overview in grafana
	mgr/dashboard: Fix unit tests
	mgr/dashboard: Added capacity metrics
	monitoring: Add subvolume dashboard

Reviewed-by: Afreen Misbah <afreen@ibm.com>
This commit is contained in:
Patrick Donnelly 2026-07-18 19:35:44 -04:00
commit 6034ccd68b
No known key found for this signature in database
GPG Key ID: 053758C0A8A3CE2F
2 changed files with 5586 additions and 4429 deletions

View File

@ -0,0 +1,916 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"target": {
"limit": 100,
"matchAny": false,
"tags": [],
"type": "dashboard"
},
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 0,
"id": 40,
"links": [],
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "A view that displays the current space used by the subvolume path along with its configured quota. If no quota is set, the quota is shown as Unlimited, giving a clear snapshot of usage versus available capacity.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [
{
"options": {
"0": {
"index": 0,
"text": "Unlimited"
}
},
"type": "value"
}
],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 0,
"y": 0
},
"id": 7,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.3.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_used_bytes{cluster=\"$cluster\",fs_name=\"$filesystem\", subvolume_path=\"$subvolume\"})",
"instant": false,
"legendFormat": "Used",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_quota_bytes{cluster=\"$cluster\",fs_name=\"$filesystem\", subvolume_path=\"$subvolume\"})",
"hide": false,
"instant": false,
"legendFormat": "Quota",
"range": true,
"refId": "B"
}
],
"title": "Capacity Usage",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Displays the current IOPS for the subvolume, giving a quick view of live I/O activity.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 6,
"y": 0
},
"id": 1,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.3.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_read_iops{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"instant": false,
"legendFormat": "Read",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_write_iops{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"hide": false,
"instant": false,
"legendFormat": "Write",
"range": true,
"refId": "B"
}
],
"title": "I/O Operations",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Shows the current throughput for the subvolume (read/write), providing a quick view of data transfer rate.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "binBps"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 12,
"y": 0
},
"id": 2,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.3.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_read_tp_Bps{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"instant": false,
"legendFormat": "Read",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_write_tp_Bps{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"hide": false,
"instant": false,
"legendFormat": "Write",
"range": true,
"refId": "B"
}
],
"title": "Throughput",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "Displays the current average latency for the subvolume, indicating how responsive I/O operations are.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "thresholds"
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "ms"
},
"overrides": []
},
"gridPos": {
"h": 6,
"w": 6,
"x": 18,
"y": 0
},
"id": 3,
"options": {
"colorMode": "value",
"graphMode": "area",
"justifyMode": "auto",
"orientation": "auto",
"percentChangeColorMode": "standard",
"reduceOptions": {
"calcs": [
"lastNotNull"
],
"fields": "",
"values": false
},
"showPercentChange": false,
"textMode": "auto",
"wideLayout": true
},
"pluginVersion": "12.3.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_read_lat_msec{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"instant": false,
"legendFormat": "Read",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_write_lat_msec{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"hide": false,
"instant": false,
"legendFormat": "Write",
"range": true,
"refId": "B"
}
],
"title": "Latency",
"type": "stat"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "A time-series graph that shows the used capacity of the subvolume over time, helping track growth trends and understand how storage consumption changes.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showValues": false,
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "bytes"
},
"overrides": []
},
"gridPos": {
"h": 10,
"w": 6,
"x": 0,
"y": 6
},
"id": 8,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.3.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_used_bytes{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"instant": true,
"legendFormat": "Used",
"range": true,
"refId": "A"
}
],
"title": "Used Capacity",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "A time-series chart showing IOPS over time, useful for spotting spikes, drops, and overall I/O patterns.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineStyle": {
"fill": "solid"
},
"lineWidth": 1,
"pointSize": 1,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showValues": false,
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "short"
},
"overrides": []
},
"gridPos": {
"h": 10,
"w": 6,
"x": 6,
"y": 6
},
"id": 4,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.3.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_read_iops{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"instant": false,
"legendFormat": "Read",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_write_iops{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"hide": false,
"instant": false,
"legendFormat": "Write",
"range": true,
"refId": "B"
}
],
"title": "IOPS graph",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "A time-series chart displaying throughput over time, helping identify bandwidth usage patterns and bursts.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showValues": false,
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
}
]
},
"unit": "binBps"
},
"overrides": []
},
"gridPos": {
"h": 10,
"w": 6,
"x": 12,
"y": 6
},
"id": 5,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.3.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_read_tp_Bps{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"instant": false,
"legendFormat": "Read",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_write_tp_Bps{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"hide": false,
"instant": false,
"legendFormat": "Write",
"range": true,
"refId": "B"
}
],
"title": "Throughput graph",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"description": "A time-series chart showing latency over time, useful for detecting performance degradation and intermittent delays.",
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"barWidthFactor": 0.6,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"showValues": false,
"spanNulls": true,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": 0
},
{
"color": "red",
"value": 80
}
]
},
"unit": "ms"
},
"overrides": []
},
"gridPos": {
"h": 10,
"w": 6,
"x": 18,
"y": 6
},
"id": 6,
"options": {
"legend": {
"calcs": [
"lastNotNull"
],
"displayMode": "table",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"hideZeros": false,
"mode": "single",
"sort": "none"
}
},
"pluginVersion": "12.3.1",
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "P43CA22E17D0F9596"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_read_lat_msec{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"instant": false,
"legendFormat": "Read",
"range": true,
"refId": "A"
},
{
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"editorMode": "code",
"exemplar": false,
"expr": "sum(ceph_mds_subvolume_metrics_avg_write_lat_msec{cluster=~\"$cluster\",fs_name=~\"$filesystem\", subvolume_path=~\"$subvolume\"})",
"hide": false,
"instant": false,
"legendFormat": "Write",
"range": true,
"refId": "B"
}
],
"title": "Latency Graph",
"type": "timeseries"
}
],
"preload": false,
"refresh": "10s",
"schemaVersion": 42,
"tags": [
"overview"
],
"templating": {
"list": [
{
"current": {
"text": "Dashboard",
"value": "Dashboard"
},
"includeAll": false,
"label": "Data Source",
"name": "datasource",
"options": [],
"query": "prometheus",
"refresh": 1,
"regex": "",
"type": "datasource"
},
{
"current": {
"text": "cluster1",
"value": "cluster1"
},
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"definition": "label_values(ceph_health_status, cluster)",
"description": "",
"includeAll": false,
"label": "Cluster",
"name": "cluster",
"options": [],
"query": {
"query": "label_values(ceph_health_status, cluster)",
"refId": "StandardVariableQuery"
},
"refresh": 1,
"regex": "",
"type": "query"
},
{
"current": {
"text": "a",
"value": "a"
},
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"definition": "label_values(ceph_fs_metadata{cluster=~\"$cluster\"},name)",
"includeAll": false,
"label": "Filesystem",
"name": "filesystem",
"options": [],
"query": {
"query": "label_values(ceph_fs_metadata{cluster=~\"$cluster\"},name)",
"refId": "StandardVariableQuery"
},
"refresh": 2,
"regex": "",
"type": "query"
},
{
"current": {
},
"datasource": {
"type": "prometheus",
"uid": "${datasource}"
},
"definition": "label_values(ceph_mds_subvolume_metrics_avg_read_iops{cluster=~\"$cluster\", fs_name=~\"$filesystem\"},subvolume_path)",
"includeAll": false,
"label": "Subvolume path",
"name": "subvolume",
"options": [],
"query": {
"query": "label_values(ceph_mds_subvolume_metrics_avg_read_iops{cluster=~\"$cluster\", fs_name=~\"$filesystem\"},subvolume_path)",
"refId": "StandardVariableQuery"
},
"refresh": 2,
"regex": "",
"type": "query"
}
]
},
"time": {
"from": "now-6h",
"to": "now"
},
"timepicker": {},
"timezone": "browser",
"title": "Ceph - Filesystem Subvolume Overview",
"uid": "af0wifl5kbda8d",
"version": 1
}

File diff suppressed because it is too large Load Diff