ARCHIVE/rippled
1
0
Fork 0
mirror of https://github.com/XRPLF/rippled.git synced 2026-04-29 15:37:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

docs(telemetry): sync runbook, dashboards, and configs with code

Browse Source 
- Add 14 missing spans to runbook (6 TxQ + 8 consensus)
- Fix tx.receive attributes and config table in runbook
- Document dispute.resolve and tx.included span events
- Add spanmetrics dimensions for close_time_correct and tx.suppressed
- Fix Close Time Agreement and TX Receive vs Suppressed panel PromQL
- Wire $consensus_mode template variable to all consensus panels
- Add 10 Tempo search filters for operational attributes
- Apply rename script artifacts

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Pratik Mankawde
2026-04-29 12:29:53 +01:00
parent c5a59645d9
commit 21dad9a17d
9 changed files with 160 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
docker/telemetry/grafana/dashboards/consensus-health.json
View File

@@ -22,14 +22,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m])))",
"expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", xrpl_consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept\"}[5m])))",
"legendFormat": "P95 Round Duration"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept\"}[5m])))",
"expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", xrpl_consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept\"}[5m])))",
"legendFormat": "P50 Round Duration"
}
],
@@ -54,7 +54,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.proposal.send\"}[5m]))",
"expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_consensus_mode=~\"$consensus_mode\", span_name=\"consensus.proposal.send\"}[5m]))",
"legendFormat": "Proposals / Sec"
}
],
@@ -79,7 +79,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m])))",
"expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", xrpl_consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[5m])))",
"legendFormat": "P95 Close Duration"
}
],
@@ -104,7 +104,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.validation.send\"}[5m]))",
"expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", xrpl_consensus_mode=~\"$consensus_mode\", span_name=\"consensus.validation.send\"}[5m]))",
"legendFormat": "Validations / Sec"
}
],
@@ -130,14 +130,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept.apply\"}[5m])))",
"expr": "histogram_quantile(0.95, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", xrpl_consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept.apply\"}[5m])))",
"legendFormat": "P95 Apply Duration"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.accept.apply\"}[5m])))",
"expr": "histogram_quantile(0.50, sum by (le) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", xrpl_consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept.apply\"}[5m])))",
"legendFormat": "P50 Apply Duration"
}
],
@@ -170,8 +170,8 @@
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"consensus.accept.apply\"}[5m]))",
"legendFormat": "Total Rounds / Sec"
"expr": "sum by (xrpl_consensus_close_time_correct, exported_instance) (rate(traces_span_metrics_calls_total{span_name=\"consensus.accept.apply\", xrpl_consensus_mode=~\"$consensus_mode\", exported_instance=~\"$node\"}[$__rate_interval]))",
"legendFormat": "close_time_correct={{xrpl_consensus_close_time_correct}}"
}
],
"fieldConfig": {

4
docker/telemetry/grafana/dashboards/transaction-overview.json
View File

@@ -105,8 +105,8 @@
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.receive\"}[5m]))",
"legendFormat": "total received"
"expr": "sum by (xrpl_tx_suppressed, exported_instance) (rate(traces_span_metrics_calls_total{span_name=\"tx.receive\", exported_instance=~\"$node\"}[$__rate_interval]))",
"legendFormat": "suppressed={{xrpl_tx_suppressed}}"
}
],
"fieldConfig": {

51
docker/telemetry/grafana/provisioning/datasources/tempo.yaml
View File

@@ -166,3 +166,54 @@ datasources:
operator: "="
scope: span
type: dynamic
- id: consensus-proposers
tag: xrpl.consensus.proposers
operator: "="
scope: span
type: dynamic
- id: consensus-result
tag: xrpl.consensus.result
operator: "="
scope: span
type: dynamic
- id: consensus-mode-old
tag: xrpl.consensus.mode.old
operator: "="
scope: span
type: dynamic
- id: consensus-mode-new
tag: xrpl.consensus.mode.new
operator: "="
scope: span
type: dynamic
- id: consensus-ledger-id
tag: xrpl.consensus.ledger_id
operator: "="
scope: span
type: static
# Phase 3/4: Additional transaction and queue filters
- id: tx-path
tag: xrpl.tx.path
operator: "="
scope: span
type: dynamic
- id: tx-suppressed
tag: xrpl.tx.suppressed
operator: "="
scope: span
type: dynamic
- id: peer-version
tag: xrpl.peer.version
operator: "="
scope: span
type: dynamic
- id: txq-status
tag: xrpl.txq.status
operator: "="
scope: span
type: dynamic
- id: txq-ter-code
tag: xrpl.txq.ter_code
operator: "="
scope: span
type: dynamic

2
docker/telemetry/otel-collector-config.yaml
View File

@@ -34,7 +34,9 @@ connectors:
- name: xrpl.rpc.command
- name: xrpl.rpc.status
- name: xrpl.consensus.mode
- name: xrpl.consensus.close_time_correct
- name: xrpl.tx.local
- name: xrpl.tx.suppressed
exporters:
debug: