This is an automated email from the ASF dual-hosted git repository.
smengcl 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 fb4d3ccf7d4 HDDS-15352. Add Datanode Decommission and Maintenance
Grafana dashboard (#10337)
fb4d3ccf7d4 is described below
commit fb4d3ccf7d48ac4408106a9b13f9aea22031d63d
Author: Wei-Chiu Chuang <[email protected]>
AuthorDate: Wed May 27 17:27:33 2026 -0700
HDDS-15352. Add Datanode Decommission and Maintenance Grafana dashboard
(#10337)
---
...ne - Datanode Decommission and Maintenance.json | 1243 ++++++++++++++++++++
1 file changed, 1243 insertions(+)
diff --git a/hadoop-ozone/dist/src/main/compose/common/grafana/dashboards/Ozone
- Datanode Decommission and Maintenance.json
b/hadoop-ozone/dist/src/main/compose/common/grafana/dashboards/Ozone - Datanode
Decommission and Maintenance.json
new file mode 100644
index 00000000000..1cc6b26391a
--- /dev/null
+++ b/hadoop-ozone/dist/src/main/compose/common/grafana/dashboards/Ozone -
Datanode Decommission and Maintenance.json
@@ -0,0 +1,1243 @@
+{
+ "annotations": {
+ "list": [
+ {
+ "builtIn": 1,
+ "datasource": {
+ "type": "grafana",
+ "uid": "-- Grafana --"
+ },
+ "enable": true,
+ "hide": true,
+ "iconColor": "rgba(0, 211, 255, 1)",
+ "name": "Annotations & Alerts",
+ "type": "dashboard"
+ }
+ ]
+ },
+ "editable": true,
+ "fiscalYearStartMonth": 0,
+ "graphTooltip": 0,
+ "id": null,
+ "links": [],
+ "panels": [
+ {
+ "collapsed": false,
+ "gridPos": { "h": 1, "w": 24, "x": 0, "y": 0 },
+ "id": 1,
+ "panels": [],
+ "title": "SCM Node Decommission Overview",
+ "type": "row"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ { "color": "blue", "value": null },
+ { "color": "orange", "value": 1 }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 4, "w": 4, "x": 0, "y": 1 },
+ "id": 11,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [ "lastNotNull" ],
+ "fields": "",
+ "values": false
+ },
+ "textMode": "auto"
+ },
+ "pluginVersion": "11.4.0",
+ "targets": [
+ {
+ "expr":
"node_decommission_metrics_decommissioning_maintenance_nodes_total",
+ "instant": false,
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Nodes Decommissioning/Maintenance",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ { "color": "green", "value": null },
+ { "color": "blue", "value": 1 }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 4, "w": 4, "x": 4, "y": 1 },
+ "id": 12,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [ "lastNotNull" ],
+ "fields": "",
+ "values": false
+ },
+ "textMode": "auto"
+ },
+ "pluginVersion": "11.4.0",
+ "targets": [
+ {
+ "expr": "node_decommission_metrics_recommission_nodes_total",
+ "instant": false,
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Nodes Recommissioning",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ { "color": "green", "value": null },
+ { "color": "red", "value": 1 }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 4, "w": 4, "x": 8, "y": 1 },
+ "id": 13,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [ "lastNotNull" ],
+ "fields": "",
+ "values": false
+ },
+ "textMode": "auto"
+ },
+ "pluginVersion": "11.4.0",
+ "targets": [
+ {
+ "expr": "node_decommission_metrics_pipelines_waiting_to_close_total",
+ "instant": false,
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Pipelines Waiting to Close",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ { "color": "green", "value": null },
+ { "color": "red", "value": 1 }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 4, "w": 4, "x": 12, "y": 1 },
+ "id": 14,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [ "lastNotNull" ],
+ "fields": "",
+ "values": false
+ },
+ "textMode": "auto"
+ },
+ "pluginVersion": "11.4.0",
+ "targets": [
+ {
+ "expr":
"node_decommission_metrics_containers_under_replicated_total",
+ "instant": false,
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Containers Under-Replicated",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ { "color": "green", "value": null },
+ { "color": "orange", "value": 1 }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 4, "w": 4, "x": 16, "y": 1 },
+ "id": 15,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [ "lastNotNull" ],
+ "fields": "",
+ "values": false
+ },
+ "textMode": "auto"
+ },
+ "pluginVersion": "11.4.0",
+ "targets": [
+ {
+ "expr": "node_decommission_metrics_containers_un_closed_total",
+ "instant": false,
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Containers Unclosed",
+ "type": "stat"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "thresholds"
+ },
+ "decimals": 0,
+ "mappings": [],
+ "thresholds": {
+ "mode": "absolute",
+ "steps": [
+ { "color": "green", "value": null }
+ ]
+ },
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 4, "w": 4, "x": 20, "y": 1 },
+ "id": 16,
+ "options": {
+ "colorMode": "value",
+ "graphMode": "area",
+ "justifyMode": "auto",
+ "orientation": "auto",
+ "reduceOptions": {
+ "calcs": [ "lastNotNull" ],
+ "fields": "",
+ "values": false
+ },
+ "textMode": "auto"
+ },
+ "pluginVersion": "11.4.0",
+ "targets": [
+ {
+ "expr":
"node_decommission_metrics_containers_sufficiently_replicated_total",
+ "instant": false,
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Containers Suff. Replicated",
+ "type": "stat"
+ },
+ {
+ "collapsed": false,
+ "gridPos": { "h": 1, "w": 24, "x": 0, "y": 5 },
+ "id": 2,
+ "panels": [],
+ "title": "Decommission Progress by Host",
+ "type": "row"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 0, "y": 6 },
+ "id": 21,
+ "options": {
+ "legend": {
+ "calcs": [ "mean", "max", "last" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "descending"
+ }
+ },
+ "targets": [
+ {
+ "expr": "node_decommission_metrics_under_replicated_dn",
+ "legendFormat": "{{datanode}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Under-Replicated Containers by Host",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 12, "y": 6 },
+ "id": 22,
+ "options": {
+ "legend": {
+ "calcs": [ "mean", "max", "last" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "descending"
+ }
+ },
+ "targets": [
+ {
+ "expr": "node_decommission_metrics_pipelines_waiting_to_close_dn",
+ "legendFormat": "{{datanode}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Pipelines Waiting to Close by Host",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 0, "y": 14 },
+ "id": 23,
+ "options": {
+ "legend": {
+ "calcs": [ "mean", "max", "last" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "descending"
+ }
+ },
+ "targets": [
+ {
+ "expr": "node_decommission_metrics_unclosed_containers_dn",
+ "legendFormat": "{{datanode}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Unclosed Containers by Host",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 12, "y": 14 },
+ "id": 24,
+ "options": {
+ "legend": {
+ "calcs": [ "mean", "max", "last" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "descending"
+ }
+ },
+ "targets": [
+ {
+ "expr": "node_decommission_metrics_sufficiently_replicated_dn",
+ "legendFormat": "{{datanode}}",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Sufficiently Replicated Containers by Host",
+ "type": "timeseries"
+ },
+ {
+ "collapsed": false,
+ "gridPos": { "h": 1, "w": 24, "x": 0, "y": 22 },
+ "id": 3,
+ "panels": [],
+ "title": "SCM Replication Manager Metrics",
+ "type": "row"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 0, "y": 23 },
+ "id": 31,
+ "options": {
+ "legend": {
+ "calcs": [ "mean", "max", "last" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr": "replication_manager_metrics_under_replicated_queue_size",
+ "legendFormat": "Under Replicated Queue",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr": "replication_manager_metrics_over_replicated_queue_size",
+ "legendFormat": "Over Replicated Queue",
+ "range": true,
+ "refId": "B"
+ }
+ ],
+ "title": "Replication Manager Queue Sizes",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 12, "y": 23 },
+ "id": 32,
+ "options": {
+ "legend": {
+ "calcs": [ "mean", "max", "last" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr": "replication_manager_metrics_inflight_replication",
+ "legendFormat": "Inflight Replication",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr": "replication_manager_metrics_inflight_ec_replication",
+ "legendFormat": "Inflight EC Replication",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "expr": "replication_manager_metrics_inflight_deletion",
+ "legendFormat": "Inflight Deletion",
+ "range": true,
+ "refId": "C"
+ },
+ {
+ "expr": "replication_manager_metrics_inflight_ec_deletion",
+ "legendFormat": "Inflight EC Deletion",
+ "range": true,
+ "refId": "D"
+ }
+ ],
+ "title": "Inflight Container Replication & Deletion Tasks",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 0, "y": 31 },
+ "id": 33,
+ "options": {
+ "legend": {
+ "calcs": [ "sum", "max" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr":
"rate(replication_manager_metrics_replication_cmds_sent_total[$__rate_interval])",
+ "legendFormat": "Replication Cmds Sent/sec",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_replicas_created_total[$__rate_interval])",
+ "legendFormat": "Replicas Created/sec",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_replica_create_timeout_total[$__rate_interval])",
+ "legendFormat": "Replica Create Timeouts/sec",
+ "range": true,
+ "refId": "C"
+ }
+ ],
+ "title": "Replication Command Rates",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 12, "y": 31 },
+ "id": 34,
+ "options": {
+ "legend": {
+ "calcs": [ "sum", "max" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr":
"rate(replication_manager_metrics_replicate_container_cmds_deferred_total[$__rate_interval])",
+ "legendFormat": "Replicate Cmds Deferred/sec",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_delete_container_cmds_deferred_total[$__rate_interval])",
+ "legendFormat": "Delete Cmds Deferred/sec",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_ec_reconstruction_cmds_deferred_total[$__rate_interval])",
+ "legendFormat": "EC Reconstruction Deferred/sec",
+ "range": true,
+ "refId": "C"
+ }
+ ],
+ "title": "Deferred Commands Rates (Overloaded Nodes)",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 0, "y": 39 },
+ "id": 35,
+ "options": {
+ "legend": {
+ "calcs": [ "sum", "max" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr":
"rate(replication_manager_metrics_ec_reconstruction_cmds_sent_total[$__rate_interval])",
+ "legendFormat": "EC Reconstruction Cmds Sent/sec",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_ec_replicas_created_total[$__rate_interval])",
+ "legendFormat": "EC Replicas Created/sec",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_ec_partial_reconstruction_skipped_total[$__rate_interval])",
+ "legendFormat": "EC Partial Recon Skipped/sec",
+ "range": true,
+ "refId": "C"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_ec_partial_reconstruction_critical_total[$__rate_interval])",
+ "legendFormat": "EC Partial Recon Critical/sec",
+ "range": true,
+ "refId": "D"
+ }
+ ],
+ "title": "EC Reconstruction Command Rates",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 12, "y": 39 },
+ "id": 36,
+ "options": {
+ "legend": {
+ "calcs": [ "sum", "max" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr":
"rate(replication_manager_metrics_ec_partial_replication_for_out_of_service_replicas_total[$__rate_interval])",
+ "legendFormat": "EC Out-Of-Service Partial Repl/sec",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_partial_replication_total[$__rate_interval])",
+ "legendFormat": "Ratis Partial Repl/sec",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_ec_partial_replication_for_mis_replication_total[$__rate_interval])",
+ "legendFormat": "EC Mis-Repl Partial/sec",
+ "range": true,
+ "refId": "C"
+ },
+ {
+ "expr":
"rate(replication_manager_metrics_partial_replication_for_mis_replication_total[$__rate_interval])",
+ "legendFormat": "Ratis Mis-Repl Partial/sec",
+ "range": true,
+ "refId": "D"
+ }
+ ],
+ "title": "Partial Replication Rates (Decommission/Maintenance)",
+ "type": "timeseries"
+ },
+ {
+ "collapsed": false,
+ "gridPos": { "h": 1, "w": 24, "x": 0, "y": 47 },
+ "id": 4,
+ "panels": [],
+ "title": "DataNode Replication Supervisor",
+ "type": "row"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 10,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 0, "y": 48 },
+ "id": 41,
+ "options": {
+ "legend": {
+ "calcs": [ "mean", "max", "last" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr": "replication_supervisor_metrics_num_in_flight_replications",
+ "legendFormat": "Inflight Replications ({{hostname}})",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr": "replication_supervisor_metrics_num_queued_replications",
+ "legendFormat": "Queued Replications ({{hostname}})",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "expr": "replication_supervisor_metrics_num_requested_replications",
+ "legendFormat": "Requested Replications ({{hostname}})",
+ "range": true,
+ "refId": "C"
+ }
+ ],
+ "title": "Supervisor Task Status",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 12, "y": 48 },
+ "id": 42,
+ "options": {
+ "legend": {
+ "calcs": [ "sum", "max" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr":
"rate(replication_supervisor_metrics_num_success_replications[$__rate_interval])",
+ "legendFormat": "Success Repl/sec ({{hostname}})",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr":
"rate(replication_supervisor_metrics_num_failure_replications[$__rate_interval])",
+ "legendFormat": "Failure Repl/sec ({{hostname}})",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "expr":
"rate(replication_supervisor_metrics_num_timeout_replications[$__rate_interval])",
+ "legendFormat": "Timeout Repl/sec ({{hostname}})",
+ "range": true,
+ "refId": "C"
+ },
+ {
+ "expr":
"rate(replication_supervisor_metrics_num_skipped_replications[$__rate_interval])",
+ "legendFormat": "Skipped Repl/sec ({{hostname}})",
+ "range": true,
+ "refId": "D"
+ }
+ ],
+ "title": "Supervisor Replication Completion Rates",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "lineInterpolation": "stepAfter",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "short"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 6, "w": 24, "x": 0, "y": 56 },
+ "id": 43,
+ "options": {
+ "legend": {
+ "calcs": [ "max", "last" ],
+ "displayMode": "table",
+ "placement": "right",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "single",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr": "replication_supervisor_metrics_max_replication_streams",
+ "legendFormat": "Max streams ({{hostname}})",
+ "range": true,
+ "refId": "A"
+ }
+ ],
+ "title": "Max Concurrent Replication Streams Limit per Host",
+ "type": "timeseries"
+ },
+ {
+ "collapsed": false,
+ "gridPos": { "h": 1, "w": 24, "x": 0, "y": 62 },
+ "id": 5,
+ "panels": [],
+ "title": "DataNode Replicator Performance (MeasuredReplicator)",
+ "type": "row"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 0,
+ "mappings": [],
+ "unit": "ops"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 0, "y": 63 },
+ "id": 51,
+ "options": {
+ "legend": {
+ "calcs": [ "sum", "max" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr": "rate(measured_replicator_success[$__rate_interval])",
+ "legendFormat": "Success/sec ({{hostname}})",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr": "rate(measured_replicator_failure[$__rate_interval])",
+ "legendFormat": "Failure/sec ({{hostname}})",
+ "range": true,
+ "refId": "B"
+ }
+ ],
+ "title": "Replicator Operations Rate",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 1,
+ "mappings": [],
+ "unit": "Bps"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 12, "x": 12, "y": 63 },
+ "id": 52,
+ "options": {
+ "legend": {
+ "calcs": [ "sum", "max" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr":
"rate(measured_replicator_transferred_bytes[$__rate_interval])",
+ "legendFormat": "Transferred Bytes/sec ({{hostname}})",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr": "rate(measured_replicator_failure_bytes[$__rate_interval])",
+ "legendFormat": "Failure Bytes/sec ({{hostname}})",
+ "range": true,
+ "refId": "B"
+ }
+ ],
+ "title": "Replicator Byte Transfer Rates",
+ "type": "timeseries"
+ },
+ {
+ "datasource": {
+ "type": "prometheus"
+ },
+ "fieldConfig": {
+ "defaults": {
+ "color": {
+ "mode": "palette-classic"
+ },
+ "custom": {
+ "drawStyle": "line",
+ "fillOpacity": 0,
+ "lineInterpolation": "smooth",
+ "lineWidth": 2
+ },
+ "decimals": 1,
+ "mappings": [],
+ "unit": "ms"
+ },
+ "overrides": []
+ },
+ "gridPos": { "h": 8, "w": 24, "x": 0, "y": 71 },
+ "id": 53,
+ "options": {
+ "legend": {
+ "calcs": [ "mean", "max" ],
+ "displayMode": "table",
+ "placement": "bottom",
+ "showLegend": true
+ },
+ "tooltip": {
+ "mode": "multi",
+ "sort": "none"
+ }
+ },
+ "targets": [
+ {
+ "expr": "rate(measured_replicator_queue_time[$__rate_interval]) /
rate(measured_replicator_success[$__rate_interval])",
+ "legendFormat": "Avg Queue Delay (ms) ({{hostname}})",
+ "range": true,
+ "refId": "A"
+ },
+ {
+ "expr": "rate(measured_replicator_success_time[$__rate_interval]) /
rate(measured_replicator_success[$__rate_interval])",
+ "legendFormat": "Avg Success Exec Time (ms) ({{hostname}})",
+ "range": true,
+ "refId": "B"
+ },
+ {
+ "expr": "rate(measured_replicator_failure_time[$__rate_interval]) /
rate(measured_replicator_failure[$__rate_interval])",
+ "legendFormat": "Avg Failure Exec Time (ms) ({{hostname}})",
+ "range": true,
+ "refId": "C"
+ }
+ ],
+ "title": "Avg Queue Delay and Execution Latency",
+ "type": "timeseries"
+ }
+ ],
+ "preload": false,
+ "refresh": "10s",
+ "schemaVersion": 40,
+ "tags": [ "ozone", "decommission", "maintenance" ],
+ "templating": {
+ "list": []
+ },
+ "time": {
+ "from": "now-15m",
+ "to": "now"
+ },
+ "timepicker": {},
+ "timezone": "browser",
+ "title": "Ozone - Datanode Decommission and Maintenance",
+ "uid": "ozone_dn_decommission",
+ "version": 1,
+ "weekStart": ""
+}
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
