This is an automated email from the ASF dual-hosted git repository.
Gargi-jais11 pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/ozone.git
The following commit(s) were added to refs/heads/master by this push:
new 0110ff57df4 HDDS-15396. Grafana dashboard for disk balancer (#10609).
0110ff57df4 is described below
commit 0110ff57df479f1b5da1e7004ec8ddd3f99091b6
Author: Navink <[email protected]>
AuthorDate: Tue Aug 11 17:03:44 2026 +0530
HDDS-15396. Grafana dashboard for disk balancer (#10609).
---
.../grafana/dashboards/Ozone - Disk Balancer.json | 1096 ++++++++++++++++++++
1 file changed, 1096 insertions(+)
diff --git a/hadoop-ozone/dist/src/main/compose/common/grafana/dashboards/Ozone
- Disk Balancer.json
b/hadoop-ozone/dist/src/main/compose/common/grafana/dashboards/Ozone - Disk
Balancer.json
new file mode 100644
index 00000000000..2c79cbacb9a
--- /dev/null
+++ b/hadoop-ozone/dist/src/main/compose/common/grafana/dashboards/Ozone - Disk
Balancer.json
@@ -0,0 +1,1096 @@
+{
+ "__inputs": [
+ {
+ "name": "DS_PROMETHEUS",
+ "label": "prometheus",
+ "description": "",
+ "type": "datasource",
+ "pluginId": "prometheus",
+ "pluginName": "Prometheus"
+ }
+ ],
+ "__elements": {},
+ "__requires": [
+ {
+ "type": "panel",
+ "id": "bargauge",
+ "name": "Bar gauge",
+ "version": ""
+ },
+ {
+ "type": "panel",
+ "id": "gauge",
+ "name": "Gauge",
+ "version": ""
+ },
+ {
+ "type": "grafana",
+ "id": "grafana",
+ "name": "Grafana",
+ "version": "13.0.2"
+ },
+ {
+ "type": "panel",
+ "id": "piechart",
+ "name": "Pie chart",
+ "version": ""
+ },
+ {
+ "type": "datasource",
+ "id": "prometheus",
+ "name": "Prometheus",
+ "version": "1.0.0"
+ },
+ {
+ "type": "panel",
+ "id": "stat",
+ "name": "Stat",
+ "version": ""
+ },
+ {
+ "type": "panel",
+ "id": "timeseries",
+ "name": "Time series",
+ "version": ""
+ }
+ ],
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": {
+ "type": "grafana",
+ "uid": "-- Grafana --"
+ },
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "type": "dashboard"
+ },
+ {
+ "builtIn": 1,
+ "enable": true,
+ "hide": true,
+ "iconColor": "",
+ "name": "Annotations & Alerts",
+ "type": "dashboard"
+ }
+ ]
+ },
+ "description": "Monitors Ozone Disk Balancer progress, throughput, and idle
state per datanode.",
+ "editable": true,
+ "fiscalYearStartMonth": 0,
+ "graphTooltip": 1,
+ "links": [],
+ "liveNow": false,
+ "panels": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "Shows how full each disk is over time. When the balancer
is running, you should see these lines slowly move closer together until they
meet in the middle.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "showValues": false,
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 12,
+ "x": 0,
+ "y": 0
+ },
+ "id": 2,
+ "options": {
+ "annotations": {
+ "clustering": -1,
+ "multiLane": false
+ },
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr": "sum({__name__=~\"volume_info_metrics_.*_ozone_used\",
instance=~\"$datanode\"}) by (instance, storagedirectory)",
+ "legendFormat": "{{instance}} {{storagedirectory}}",
+ "refId": "A"
+ }
+ ],
+ "title": "Disk Space Convergence Profile (Historical Before vs After)",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "The exact size of the data gap between your most full
disk and your emptiest disk right now. The balancer's goal is to shrink this
number down to zero.",
+ "fieldConfig": {
+ "defaults": {
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 4,
+ "w": 12,
+ "x": 12,
+ "y": 0
+ },
+ "id": 3,
+ "options": {
+ "displayMode": "lcd",
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": false
+ },
+ "maxVizHeight": 300,
+ "minVizHeight": 16,
+ "minVizWidth": 8,
+ "namePlacement": "auto",
+ "orientation": "horizontal",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showUnfilled": true,
+ "sizing": "auto",
+ "valueMode": "color"
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr": "max(sum({__name__=~\"volume_info_metrics_.*_ozone_used\",
instance=~\"$datanode\"}) by (instance, storagedirectory)) by (instance) -
min(sum({__name__=~\"volume_info_metrics_.*_ozone_used\",
instance=~\"$datanode\"}) by (instance, storagedirectory)) by (instance)",
+ "instant": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Current Disk Space Allocation Skew (Max - Min Volume Gap)",
+ "type": "bargauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "How much time it takes the system to successfully copy,
verify, and finalize a single container.",
+ "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": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 24,
+ "x": 0,
+ "y": 4
+ },
+ "id": 6,
+ "options": {
+ "annotations": {
+ "clustering": -1,
+ "multiLane": false
+ },
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"disk_balancer_service_metrics_move_success_time_avg_time{instance=~\"$datanode\"}",
+ "legendFormat": "{{instance}} success avg latency",
+ "refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"disk_balancer_service_metrics_move_failure_time_avg_time{instance=~\"$datanode\"}",
+ "legendFormat": "{{instance}} failure avg latency",
+ "refId": "B"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"disk_balancer_service_metrics_move_success_time_num_ops{instance=~\"$datanode\"}",
+ "legendFormat": "{{instance}} moves/interval",
+ "refId": "C"
+ }
+ ],
+ "title": "Container Migration Latency Profile (Processing Duration)",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "The live speedometer. This shows exactly how fast data
is physically copying from one disk to another across the node.",
+ "fieldConfig": {
+ "defaults": {
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "Bps"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 6,
+ "x": 0,
+ "y": 9
+ },
+ "id": 5,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "value",
+ "wideLayout": true
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"rate(disk_balancer_service_metrics_success_bytes{instance=~\"$datanode\"}[$__rate_interval])",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Active Balancing Throughput Speed",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "The remaining amount of data the balancer still needs to
queue up to reach perfect balance.",
+ "fieldConfig": {
+ "defaults": {
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 8,
+ "x": 6,
+ "y": 9
+ },
+ "id": 7,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "value",
+ "wideLayout": true
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr": "sum by (instance) (clamp_min(sum by (instance,
storagedirectory) ({__name__=~\"volume_info_metrics_.*_ozone_used\",
instance=~\"$datanode\"}) - on(instance) group_left avg by (instance) (sum by
(instance, storagedirectory) ({__name__=~\"volume_info_metrics_.*_ozone_used\",
instance=~\"$datanode\"})), 0))",
+ "instant": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Unscheduled Target Backlog",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "A rough estimate of how many minutes are left before the
balancer finishes balancing.",
+ "fieldConfig": {
+ "defaults": {
+ "noValue": "N/A",
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "m"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 10,
+ "x": 14,
+ "y": 9
+ },
+ "id": 8,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "value",
+ "wideLayout": true
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr": "(sum by (instance) (clamp_min(sum by (instance,
storagedirectory) ({__name__=~\"volume_info_metrics_.*_ozone_used\",
instance=~\"$datanode\"}) - on(instance) group_left avg by (instance) (sum by
(instance, storagedirectory) ({__name__=~\"volume_info_metrics_.*_ozone_used\",
instance=~\"$datanode\"})), 0)) /
clamp_min(sum(rate(disk_balancer_service_metrics_success_bytes{instance=~\"$datanode\"}[5m])),
1)) / 60",
+ "instant": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Est. Time for Unscheduled Backlog",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "The percentage of container moves that finished
perfectly.",
+ "fieldConfig": {
+ "defaults": {
+ "max": 100,
+ "min": 0,
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "percent"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 6,
+ "w": 5,
+ "x": 0,
+ "y": 14
+ },
+ "id": 11,
+ "options": {
+ "barShape": "flat",
+ "barWidthFactor": 0.5,
+ "effects": {
+ "barGlow": false,
+ "centerGlow": false,
+ "gradient": true
+ },
+ "endpointMarker": "point",
+ "minVizHeight": 75,
+ "minVizWidth": 75,
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "segmentCount": 1,
+ "segmentSpacing": 0.3,
+ "shape": "gauge",
+ "showThresholdLabels": false,
+ "showThresholdMarkers": true,
+ "sizing": "auto",
+ "sparkline": true,
+ "textMode": "auto"
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"(sum(disk_balancer_service_metrics_success_count{instance=~\"$datanode\"}) /
(sum(disk_balancer_service_metrics_success_count{instance=~\"$datanode\"}) +
sum(disk_balancer_service_metrics_failure_count{instance=~\"$datanode\"}) +
0.00001)) * 100",
+ "instant": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Overall Move Success Rate",
+ "type": "gauge"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "The total number of individual data blocks (containers)
successfully relocated by the balancer.",
+ "fieldConfig": {
+ "defaults": {
+ "noValue": "0",
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 6,
+ "w": 4,
+ "x": 5,
+ "y": 14
+ },
+ "id": 12,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "value",
+ "wideLayout": true
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"sum(disk_balancer_service_metrics_success_count{instance=~\"$datanode\"})",
+ "instant": false,
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Total Lifetime Container Moves",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "The total physical weight of all the data successfully
shifted across the disks since the balancer started.",
+ "fieldConfig": {
+ "defaults": {
+ "noValue": "0",
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "decbytes"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 6,
+ "w": 5,
+ "x": 9,
+ "y": 14
+ },
+ "id": 14,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"sum(disk_balancer_service_metrics_success_bytes{instance=~\"$datanode\"})",
+ "instant": false,
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Total Lifetime Data Balanced",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "The number of times a move was aborted due to error.
This should ideally stay at 0.",
+ "fieldConfig": {
+ "defaults": {
+ "noValue": "0",
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 1
+ }
+ ]
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 6,
+ "w": 4,
+ "x": 14,
+ "y": 14
+ },
+ "id": 15,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"sum(disk_balancer_service_metrics_failure_count{instance=~\"$datanode\"})",
+ "instant": false,
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Failed Container Moves",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "Counts scheduler loops where DiskBalancer is still
running but did not queue any container move. 'No Suitable Volume/Container'
increments when the policy cannot find a valid source/destination volume pair
with a movable container (for example, disks are already even, density is below
threshold, or no container matches the allowed states). 'Throttled' increments
when the scheduler deliberately waits because the configured bandwidth limit
was reached.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ }
+ }
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 6,
+ "w": 6,
+ "x": 18,
+ "y": 14
+ },
+ "id": 13,
+ "options": {
+ "legend": {
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "pieType": "donut",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "sort": "desc",
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"sum(increase(disk_balancer_service_metrics_idle_loop_no_available_volume_pair_count{instance=~\"$datanode\"}[$__range]))",
+ "instant": false,
+ "legendFormat": "No Suitable Volume/Container",
+ "refId": "A"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"sum(increase(disk_balancer_service_metrics_idle_loop_exceeds_bandwidth_count{instance=~\"$datanode\"}[$__range]))",
+ "instant": false,
+ "legendFormat": "Throttled",
+ "refId": "B"
+ }
+ ],
+ "title": "Balancer Idle Reason",
+ "type": "piechart"
+ },
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "description": "Rate of disk balancer scheduler loop iterations per
second. A non-zero value confirms the balancer process is alive and iterating.
If this drops to zero while the balancer is expected to run, the service may
have stalled or been stopped.",
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "lineWidth": 1,
+ "pointSize": 5,
+ "scaleDistribution": {
+ "type": "linear"
+ },
+ "showPoints": "auto",
+ "showValues": false,
+ "spanNulls": false,
+ "stacking": {
+ "group": "A",
+ "mode": "none"
+ },
+ "thresholdsStyle": {
+ "mode": "off"
+ }
+ },
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "loops/sec"
+ },
+ "overrides": []
+ },
+ "gridPos": {
+ "h": 5,
+ "w": 24,
+ "x": 0,
+ "y": 20
+ },
+ "id": 16,
+ "options": {
+ "annotations": {
+ "clustering": -1,
+ "multiLane": false
+ },
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "pluginVersion": "13.0.2",
+ "targets": [
+ {
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "expr":
"rate(disk_balancer_service_metrics_running_loop_count{instance=~\"$datanode\"}[$__rate_interval])",
+ "legendFormat": "{{instance}} loop rate",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Balancer Heartbeat — Scheduler Loop Rate",
+ "type": "timeseries"
+ }
+ ],
+ "preload": false,
+ "refresh": "5s",
+ "schemaVersion": 42,
+ "tags": [
+ "ozone",
+ "datanode",
+ "disk-balancer"
+ ],
+ "templating": {
+ "list": [
+ {
+ "allowCustomValue": true,
+ "current": {
+ "text": "",
+ "value": "${DS_PROMETHEUS}",
+ "selected": true
+ },
+ "includeAll": false,
+ "label": "Data Source",
+ "name": "datasource",
+ "options": [],
+ "query": "prometheus",
+ "refresh": 1,
+ "regex": "",
+ "type": "datasource"
+ },
+ {
+ "allowCustomValue": true,
+ "current": {},
+ "datasource": {
+ "type": "prometheus",
+ "uid": "${datasource}"
+ },
+ "definition":
"label_values(disk_balancer_service_metrics_success_count, instance)",
+ "includeAll": true,
+ "multi": true,
+ "name": "datanode",
+ "options": [],
+ "query": {
+ "query": "label_values(disk_balancer_service_metrics_success_count,
instance)",
+ "refId": "StandardVariableQuery"
+ },
+ "refresh": 1,
+ "regex": "",
+ "regexApplyTo": "value",
+ "sort": 1,
+ "type": "query"
+ }
+ ]
+ },
+ "time": {
+ "from": "now-5m",
+ "to": "now"
+ },
+ "timepicker": {
+ "refresh_intervals": [
+ "5s",
+ "10s",
+ "30s",
+ "1m",
+ "5m",
+ "15m",
+ "30m",
+ "1h",
+ "2h",
+ "1d"
+ ]
+ },
+ "timezone": "browser",
+ "title": "Ozone Disk Balancer Operations",
+ "uid": "ad6cf2f",
+ "version": 1,
+ "weekStart": ""
+}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
