diff --git a/docker/telemetry/grafana/dashboards/consensus-health.json b/docker/telemetry/grafana/dashboards/consensus-health.json index 1f562e5802..d9bbcaeb67 100644 --- a/docker/telemetry/grafana/dashboards/consensus-health.json +++ b/docker/telemetry/grafana/dashboards/consensus-health.json @@ -743,88 +743,6 @@ "overrides": [] } }, - { - "title": "Consensus Outcome Distribution", - "description": "Distribution of consensus.accept outcomes: yes (normal), moved_on (without full agreement), expired (timeout). Non-yes outcomes indicate network stress.", - "type": "piechart", - "gridPos": { - "h": 8, - "w": 8, - "x": 0, - "y": 72 - }, - "options": { - "legend": { - "displayMode": "table", - "placement": "right", - "values": ["value", "percent"] - }, - "tooltip": { - "mode": "multi" - } - }, - "targets": [ - { - "datasource": { - "type": "prometheus" - }, - "expr": "sum by (consensus_state) (increase(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.accept\", consensus_state!=\"\"}[5m]))", - "legendFormat": "{{consensus_state}}" - } - ], - "fieldConfig": { - "defaults": { - "unit": "short" - }, - "overrides": [] - } - }, - { - "title": "Consensus Failures Over Time", - "description": "Rate of non-normal consensus outcomes (moved_on + expired). Spikes indicate consensus instability.", - "type": "timeseries", - "gridPos": { - "h": 8, - "w": 16, - "x": 8, - "y": 72 - }, - "options": { - "tooltip": { - "mode": "multi", - "sort": "desc" - } - }, - "targets": [ - { - "datasource": { - "type": "prometheus" - }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.accept\", consensus_state=\"moved_on\"}[5m]))", - "legendFormat": "moved_on [{{exported_instance}}]" - }, - { - "datasource": { - "type": "prometheus" - }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.accept\", consensus_state=\"expired\"}[5m]))", - "legendFormat": "expired [{{exported_instance}}]" - } - ], - "fieldConfig": { - "defaults": { - "unit": "ops", - "custom": { - "axisLabel": "Failures / Sec", - "spanNulls": true, - "insertNulls": false, - "showPoints": "auto", - "pointSize": 3 - } - }, - "overrides": [] - } - }, { "title": "Consensus Round Duration (Full Round)", "description": "p95/p50 duration of the full consensus round. The consensus.round span (RCLConsensus.cpp startRound) wraps an entire round end-to-end. Filterable by consensus mode. This is the single most important consensus-health signal; rising round time precedes ledger-age alarms.", @@ -833,7 +751,7 @@ "h": 8, "w": 12, "x": 0, - "y": 80 + "y": 72 }, "options": { "tooltip": { @@ -879,7 +797,7 @@ "h": 8, "w": 12, "x": 12, - "y": 80 + "y": 72 }, "options": { "tooltip": { @@ -925,7 +843,7 @@ "h": 8, "w": 12, "x": 0, - "y": 88 + "y": 80 }, "options": { "tooltip": { @@ -971,7 +889,7 @@ "h": 8, "w": 12, "x": 12, - "y": 88 + "y": 80 }, "options": { "tooltip": { @@ -1017,7 +935,7 @@ "h": 8, "w": 24, "x": 0, - "y": 96 + "y": 88 }, "options": { "tooltip": {