mirror of
https://github.com/XRPLF/rippled.git
synced 2026-06-05 17:56:49 +00:00
9e27120a15
- Add canonical ledgerHash (xrpl.ledger.hash) to SpanNames.h. - LedgerSpanNames: reuse shared canonicals (ledgerSeq, closeTime, closeTimeCorrect, closeResolutionMs, ledgerHash); bare names for tx_count, tx_failed, validations. - PeerSpanNames: reuse shared canonicals (peerId, ledgerHash); bare names for proposal_trusted, validation_full, validation_trusted. - Update call sites in BuildLedger.cpp, LedgerMaster.cpp, PeerImp.cpp. - Update 5 Grafana dashboards: strip xrpl.<domain>. prefix from per-span attr refs in PromQL/TraceQL queries. Keep rule-5 entries. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
354 lines
11 KiB
JSON
354 lines
11 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Ledger Build Rate",
|
|
"description": "Rate at which new ledgers are being built. The ledger.build span (BuildLedger.cpp:31) wraps the entire buildLedgerImpl() function which creates a new ledger from a parent, applies transactions, flushes SHAMap nodes, and sets the accepted state. Should match the consensus close rate (~0.25/sec on mainnet with ~4s rounds).",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m]))",
|
|
"legendFormat": "Builds / Sec [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Ledger Build Duration",
|
|
"description": "p95 and p50 duration of ledger builds. Measures the full buildLedgerImpl() call including transaction application, SHAMap flushing, and ledger acceptance. The span records xrpl.ledger.seq as an attribute. Long build times indicate expensive transaction sets or I/O pressure from SHAMap flushes.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])))",
|
|
"legendFormat": "P95 Build Duration [{{exported_instance}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])))",
|
|
"legendFormat": "P50 Build Duration [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Ledger Validation Rate",
|
|
"description": "Rate at which ledgers pass the validation threshold and are accepted as fully validated. The ledger.validate span (LedgerMaster.cpp:915) fires in checkAccept() only after the ledger receives sufficient trusted validations (>= quorum). Records xrpl.ledger.seq and validations (the number of validations received).",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"ledger.validate\"}[5m]))",
|
|
"legendFormat": "Validations / Sec [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Ledger Build Duration Heatmap",
|
|
"description": "Heatmap showing the distribution of ledger.build durations across histogram buckets over time. Each cell represents the count of ledger builds that fell into that duration bucket in a 5m window. Useful for spotting occasional slow ledger builds that may not appear in percentile charts.",
|
|
"type": "heatmap",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"yAxis": {
|
|
"axisLabel": "Duration (ms)"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])) by (le)",
|
|
"legendFormat": "{{le}}",
|
|
"format": "heatmap"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms"
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Transaction Apply Duration",
|
|
"description": "p95 and p50 duration of applying the consensus transaction set during ledger building. The tx.apply span (BuildLedger.cpp:88) wraps applyTransactions() which iterates through the CanonicalTXSet with multiple retry passes. Records tx_count (successful) and tx_failed (failed) as attributes.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m])))",
|
|
"legendFormat": "P95 tx.apply [{{exported_instance}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m])))",
|
|
"legendFormat": "P50 tx.apply [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Transaction Apply Rate",
|
|
"description": "Rate of tx.apply span invocations, reflecting how frequently the transaction application phase runs during ledger building. Each ledger build triggers one tx.apply call. Should closely match the ledger build rate.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"tx.apply\"}[5m]))",
|
|
"legendFormat": "tx.apply / Sec [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Operations / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Ledger Store Rate",
|
|
"description": "Rate at which ledgers are stored into the ledger history. The ledger.store span (LedgerMaster.cpp:409) wraps storeLedger() which inserts the ledger into the LedgerHistory cache. Records xrpl.ledger.seq. Should match the ledger build rate under normal operation.",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"ledger.store\"}[5m]))",
|
|
"legendFormat": "Stores / Sec [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Build vs Close Duration",
|
|
"description": "Compares p95 durations of ledger.build (the actual ledger construction in BuildLedger.cpp) vs consensus.ledger_close (the consensus close event in RCLConsensus.cpp). Build time is a subset of close time. A large gap between them indicates overhead in the consensus pipeline outside of ledger construction itself.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 24
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"ledger.build\"}[5m])))",
|
|
"legendFormat": "P95 ledger.build [{{exported_instance}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=\"consensus.ledger_close\"}[5m])))",
|
|
"legendFormat": "P95 consensus.ledger_close [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["rippled", "ledger", "telemetry"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "node",
|
|
"label": "Node",
|
|
"description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
|
|
"type": "query",
|
|
"query": "label_values(traces_span_metrics_calls_total, exported_instance)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "Ledger Operations",
|
|
"uid": "rippled-ledger-ops"
|
|
}
|