sreejasahithi commented on code in PR #10398:
URL: https://github.com/apache/ozone/pull/10398#discussion_r3332340615
##########
hadoop-ozone/dist/src/main/compose/common/grafana/dashboards/Ozone - Container
Balancer Metrics.json:
##########
@@ -0,0 +1,1379 @@
+{
+ "annotations": [
+ {
+ "kind": "AnnotationQuery",
+ "spec": {
+ "builtIn": true,
+ "enable": true,
+ "hide": true,
+ "iconColor": "",
+ "name": "Annotations & Alerts",
+ "query": {
+ "group": "grafana",
+ "kind": "DataQuery",
+ "spec": {},
+ "version": "v0"
+ }
+ }
+ }
+ ],
+ "cursorSync": "Crosshair",
+ "description": "Comprehensive tracking of Ozone cluster balancing
operations. Monitors real-time DataNode capacity convergence, current iteration
health (Scheduled vs Completed), and lifetime data movement metrics.",
+ "editable": true,
+ "elements": {
+ "panel-1": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_datanodes_unbalanced)",
+ "legendFormat": "Unbalanced DataNodes",
+ "range": false
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "Tracks the total number of DataNodes whose capacity
usage falls outside the configured cluster balance threshold. A healthy, fully
balanced cluster should ideally maintain a value of 0.",
+ "id": 1,
+ "links": [],
+ "title": "Unbalanced DataNodes",
+ "vizConfig": {
+ "group": "stat",
+ "kind": "VizConfig",
+ "spec": {
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "orange",
+ "value": 1
+ },
+ {
+ "color": "red",
+ "value": 5
+ }
+ ]
+ },
+ "unit": "none"
+ },
+ "overrides": []
+ },
+ "options": {
+ "colorMode": "value",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-2": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_data_size_unbalanced_gb * 1024 * 1024 * 1024)",
+ "legendFormat": "Total Unbalanced Data Size",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "Represents the total volume of data in gigabytes
currently residing on over-utilized nodes that must be shifted to
under-utilized nodes to satisfy your configured container balancing
thresholds.",
+ "id": 2,
+ "links": [],
+ "title": "Cluster Unbalanced Data Size Over Time",
+ "vizConfig": {
+ "group": "timeseries",
+ "kind": "VizConfig",
+ "spec": {
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "left",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "smooth",
+ "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": "decbytes"
+ },
+ "overrides": []
+ },
+ "options": {
+ "annotations": {
+ "clustering": -1,
+ "multiLane": false
+ },
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-3": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(increase(container_balancer_metrics_data_size_moved_gb[$__range]))",
+ "legendFormat": "Moved Data Size (GB)",
+ "range": true
Review Comment:
should this be
`sum(container_balancer_metrics_data_size_moved_gb_in_latest_iteration)`
instead?
since the title of this panel says 'Size Moved (Latest)'
##########
hadoop-ozone/dist/src/main/compose/common/grafana/dashboards/Ozone - Container
Balancer Metrics.json:
##########
@@ -0,0 +1,1379 @@
+{
+ "annotations": [
+ {
+ "kind": "AnnotationQuery",
+ "spec": {
+ "builtIn": true,
+ "enable": true,
+ "hide": true,
+ "iconColor": "",
+ "name": "Annotations & Alerts",
+ "query": {
+ "group": "grafana",
+ "kind": "DataQuery",
+ "spec": {},
+ "version": "v0"
+ }
+ }
+ }
+ ],
+ "cursorSync": "Crosshair",
+ "description": "Comprehensive tracking of Ozone cluster balancing
operations. Monitors real-time DataNode capacity convergence, current iteration
health (Scheduled vs Completed), and lifetime data movement metrics.",
+ "editable": true,
+ "elements": {
+ "panel-1": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_datanodes_unbalanced)",
+ "legendFormat": "Unbalanced DataNodes",
+ "range": false
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "Tracks the total number of DataNodes whose capacity
usage falls outside the configured cluster balance threshold. A healthy, fully
balanced cluster should ideally maintain a value of 0.",
+ "id": 1,
+ "links": [],
+ "title": "Unbalanced DataNodes",
+ "vizConfig": {
+ "group": "stat",
+ "kind": "VizConfig",
+ "spec": {
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "orange",
+ "value": 1
+ },
+ {
+ "color": "red",
+ "value": 5
+ }
+ ]
+ },
+ "unit": "none"
+ },
+ "overrides": []
+ },
+ "options": {
+ "colorMode": "value",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-2": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_data_size_unbalanced_gb * 1024 * 1024 * 1024)",
+ "legendFormat": "Total Unbalanced Data Size",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "Represents the total volume of data in gigabytes
currently residing on over-utilized nodes that must be shifted to
under-utilized nodes to satisfy your configured container balancing
thresholds.",
+ "id": 2,
+ "links": [],
+ "title": "Cluster Unbalanced Data Size Over Time",
+ "vizConfig": {
+ "group": "timeseries",
+ "kind": "VizConfig",
+ "spec": {
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "left",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "smooth",
+ "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": "decbytes"
+ },
+ "overrides": []
+ },
+ "options": {
+ "annotations": {
+ "clustering": -1,
+ "multiLane": false
+ },
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-3": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(increase(container_balancer_metrics_data_size_moved_gb[$__range]))",
+ "legendFormat": "Moved Data Size (GB)",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "Measures the total volume of data in gigabytes
successfully transferred between source and target DataNodes during the most
recently executed balancer iteration loop.",
+ "id": 3,
+ "links": [],
+ "title": "Size Moved (Latest)",
+ "vizConfig": {
+ "group": "stat",
+ "kind": "VizConfig",
+ "spec": {
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 1000
+ }
+ ]
+ },
+ "unit": "decgbytes"
+ },
+ "overrides": []
+ },
+ "options": {
+ "colorMode": "value",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-4": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_datanodes_involved_in_latest_iteration)",
+ "legendFormat": "Datanode Involved",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "The count of unique DataNode hosts that actively
participated as either a source (sender) or target (receiver) of data blocks in
the latest iteration.",
+ "id": 4,
+ "links": [],
+ "title": "Nodes Involved (Latest)",
+ "vizConfig": {
+ "group": "stat",
+ "kind": "VizConfig",
+ "spec": {
+ "fieldConfig": {
+ "defaults": {
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ {
+ "color": "green",
+ "value": 0
+ },
+ {
+ "color": "red",
+ "value": 80
+ }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "options": {
+ "colorMode": "value",
+ "graphMode": "none",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "percentChangeColorMode": "standard",
+ "reduceOptions": {
+ "calcs": [
+ "lastNotNull"
+ ],
+ "fields": "",
+ "values": false
+ },
+ "showPercentChange": false,
+ "textMode": "auto",
+ "wideLayout": true
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-5": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_container_moves_scheduled_in_latest_iteration)",
+ "legendFormat": "Scheduled",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ },
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_container_moves_completed_in_latest_iteration)",
+ "legendFormat": "Completed",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "B"
+ }
+ },
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_container_moves_failed_in_latest_iteration)",
+ "legendFormat": "Failed",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "C"
+ }
+ },
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_container_moves_timeout_in_latest_iteration)",
+ "legendFormat": "Timeout",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "D"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "A real-time status breakdown of individual container
transfers during the current or latest iteration. Displays the exact counts of
Scheduled, Completed, Failed, and Timeout movements.",
+ "id": 5,
+ "links": [],
+ "title": "Container Move Operations Breakdown (Latest Iteration)",
+ "vizConfig": {
+ "group": "timeseries",
+ "kind": "VizConfig",
+ "spec": {
+ "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": "none"
+ },
+ "overrides": []
+ },
+ "options": {
+ "annotations": {
+ "clustering": -1,
+ "multiLane": false
+ },
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-6": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "expr": "container_balancer_metrics_data_size_moved_gb *
1024 * 1024 * 1024",
+ "legendFormat": "Total Data Moved"
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "An accumulating historical counter showing the total
volume of data moved across the cluster since tracking began. This acts as a
lifetime indicator of balancer workload.",
+ "id": 6,
+ "links": [],
+ "title": "Cumulative Data Volume Moved",
+ "vizConfig": {
+ "group": "timeseries",
+ "kind": "VizConfig",
+ "spec": {
+ "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": "decbytes"
+ },
+ "overrides": []
+ },
+ "options": {
+ "annotations": {
+ "clustering": -1,
+ "multiLane": false
+ },
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-7": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_container_moves_completed)",
+ "legendFormat": "Completed",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ },
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_container_moves_failed)",
+ "instant": false,
+ "legendFormat": "Failed",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "B"
+ }
+ },
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_container_moves_scheduled)",
+ "instant": false,
+ "legendFormat": "Scheduled",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "C"
+ }
+ },
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "editorMode": "code",
+ "expr":
"sum(container_balancer_metrics_num_container_moves_timeout)",
+ "instant": false,
+ "legendFormat": "Timeout",
+ "range": true
+ },
+ "version": "v0"
+ },
+ "refId": "D"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "Cluster-wide historical aggregation of all attempted
container migrations since inception. Compares total Scheduled vs Completed
moves alongside long-term Failed and Timeout counts to assess network and disk
reliability.",
+ "id": 7,
+ "links": [],
+ "title": "Cumulative Executed Container Moves",
+ "vizConfig": {
+ "group": "timeseries",
+ "kind": "VizConfig",
+ "spec": {
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "axisBorderShow": false,
+ "axisCenteredZero": false,
+ "axisColorMode": "text",
+ "axisLabel": "",
+ "axisPlacement": "auto",
+ "barAlignment": 0,
+ "barWidthFactor": 0.6,
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "gradientMode": "none",
+ "hideFrom": {
+ "legend": false,
+ "tooltip": false,
+ "viz": false
+ },
+ "insertNulls": false,
+ "lineInterpolation": "linear",
+ "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": "none"
+ },
+ "overrides": [
+ {
+ "__systemRef": "hideSeriesFrom",
+ "matcher": {
+ "id": "byNames",
+ "options": {
+ "mode": "exclude",
+ "names": [
+ "Completed"
+ ],
+ "prefix": "All except:",
+ "readOnly": true
+ }
+ },
+ "properties": [
+ {
+ "id": "custom.hideFrom",
+ "value": {
+ "legend": false,
+ "tooltip": true,
+ "viz": true
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "options": {
+ "annotations": {
+ "clustering": -1,
+ "multiLane": false
+ },
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-8": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "${datasource}"
+ },
+ "group": "prometheus",
+ "kind": "DataQuery",
+ "spec": {
+ "expr": "container_balancer_metrics_num_iterations",
+ "legendFormat": "Completed Iterations"
+ },
+ "version": "v0"
+ },
+ "refId": "A"
+ }
+ }
+ ],
+ "queryOptions": {},
+ "transformations": []
+ }
+ },
+ "description": "The lifetime count of fully executed, successful
balancing loops completed by the Storage Container Manager (SCM). If the
balancer exits during initialization due to an already balanced cluster, this
counter does not increment.",
+ "id": 8,
+ "links": [],
+ "title": "Total Balancer Iterations Completed",
+ "vizConfig": {
+ "group": "timeseries",
+ "kind": "VizConfig",
+ "spec": {
+ "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": "none"
+ },
+ "overrides": [
+ {
+ "__systemRef": "hideSeriesFrom",
+ "matcher": {
+ "id": "byNames",
+ "options": {
+ "mode": "exclude",
+ "names": [
+ "Completed Iterations"
+ ],
+ "prefix": "All except:",
+ "readOnly": true
+ }
+ },
+ "properties": [
+ {
+ "id": "custom.hideFrom",
+ "value": {
+ "legend": false,
+ "tooltip": true,
+ "viz": true
+ }
+ }
+ ]
+ }
+ ]
+ },
+ "options": {
+ "annotations": {
+ "clustering": -1,
+ "multiLane": false
+ },
+ "legend": {
+ "calcs": [],
+ "displayMode": "list",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "hideZeros": false,
+ "mode": "single",
+ "sort": "none"
+ }
+ }
+ },
+ "version": "13.0.1+security-01"
+ }
+ }
+ },
+ "panel-9": {
+ "kind": "Panel",
+ "spec": {
+ "data": {
+ "kind": "QueryGroup",
+ "spec": {
+ "queries": [
+ {
+ "kind": "PanelQuery",
+ "spec": {
+ "hidden": false,
+ "query": {
+ "datasource": {
+ "name": "dfm13nk97y9kwf"
Review Comment:
Don’t hardcode dfm13nk97y9kwf. Use ${datasource} like the other panels.
Remove the hardcoded UID from the variable default too.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
