mirror of
https://github.com/XRPLF/rippled.git
synced 2026-06-05 17:56:49 +00:00
5601615952
MetricsRegistry emits OTel SDK metrics with the xrpld_ prefix
(MetricsRegistry.cpp defines "xrpld_nodestore_state",
"xrpld_cache_metrics", etc.), but the Phase 9 dashboards and the
Step 10c integration-test assertions introduced in 892fee638a
queried the rippled_ prefix. Every Phase 9 panel and assertion
therefore rendered "No data" or failed on a live run, even though
the underlying series were being exported correctly.
Rename the rippled_ prefix to xrpld_ for every MetricsRegistry
metric in dashboards and the integration test:
- nodestore_state, cache_metrics, txq_metrics, load_factor_metrics,
object_count
- rpc_method_started_total / _finished_total / _errored_total /
_duration_us_bucket
- job_queued_total / _started_total / _finished_total /
_queued_duration_us_bucket / _running_duration_us_bucket
- peer_quality, server_info, validator_health, ledger_economy,
db_metrics, complete_ledgers, build_info, state_tracking
- ledgers_closed_total, validations_sent_total,
validations_checked_total, state_changes_total
- validation_agreement (ValidationTracker 1h/24h/7d windows)
Also add ValidationTracker window-gauge assertions to Step 10c of
integration-test.sh so the 1h/24h/7d agreement and miss counts are
checked alongside the other Phase 9 gauges.
The rippled_ prefix is preserved for beast::insight metrics
(rippled_LedgerMaster_*, rippled_Peer_Finder_*, rippled_total_*,
rippled_Overlay_*, rippled_State_Accounting_*, rippled_transactions_*,
rippled_proposals_*, rippled_validations_Messages_*) because those
flow through the StatsD-style OTelCollector configured with
`[insight] prefix=rippled` and remain on that prefix by design.
Verified against a live 6-node consensus network: all 22 Phase 9 +
ValidationTracker assertions now report 6+ series per metric.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
392 lines
9.8 KiB
JSON
392 lines
9.8 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"description": "Peer network quality metrics: latency, divergence, version distribution, upgrade recommendations, disconnects, and connection direction balance. Requires push_metrics.py or equivalent OTel metric source.",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "P90 Peer Latency",
|
|
"description": "90th percentile peer-to-peer latency in milliseconds over time. High latency indicates network congestion or geographically distant peers.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "xrpld_peer_quality{metric=\"peer_latency_p90_ms\",exported_instance=~\"$node\"}",
|
|
"legendFormat": "P90 Latency [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Latency (ms)",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 200
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 500
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Insane/Diverged Peers",
|
|
"description": "Count of peers whose ledger state is considered insane or diverged from the network. Non-zero values suggest those peers are misbehaving or on a fork.",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "xrpld_peer_quality{metric=\"peers_insane_count\",exported_instance=~\"$node\"}",
|
|
"legendFormat": "Insane Peers [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 3
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Higher Version Peers %",
|
|
"description": "Percentage of connected peers running a higher rippled version. A high percentage suggests this node should be upgraded.",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "xrpld_peer_quality{metric=\"peers_higher_version_pct\",exported_instance=~\"$node\"}",
|
|
"legendFormat": "Higher Version % [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100,
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 30
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 60
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Upgrade Recommended",
|
|
"description": "Whether an upgrade is recommended based on peer version analysis (1=recommended, 0=not needed). Triggered when a majority of peers run a newer version.",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "xrpld_peer_quality{metric=\"upgrade_recommended\",exported_instance=~\"$node\"}",
|
|
"legendFormat": "Upgrade [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": { "text": "No", "color": "green" }
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"1": { "text": "Yes", "color": "red" }
|
|
}
|
|
}
|
|
],
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Resource Disconnects",
|
|
"description": "Cumulative peer disconnections due to resource limit violations over time. Rising values indicate aggressive or misbehaving peers being dropped.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 10,
|
|
"x": 6,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "xrpld_server_info{metric=\"peer_disconnects_resources\",exported_instance=~\"$node\"}",
|
|
"legendFormat": "Disconnects [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"custom": {
|
|
"axisLabel": "Disconnects",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Inbound vs Outbound Peers",
|
|
"description": "Comparison of active inbound and outbound peer connections. A healthy node should have a balanced mix. All-inbound may indicate NAT/firewall issues preventing outbound connections.",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 8,
|
|
"x": 16,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"orientation": "horizontal",
|
|
"displayMode": "gradient",
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "rippled_Peer_Finder_Active_Inbound_Peers{exported_instance=~\"$node\"}",
|
|
"legendFormat": "Inbound [{{exported_instance}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "rippled_Peer_Finder_Active_Outbound_Peers{exported_instance=~\"$node\"}",
|
|
"legendFormat": "Outbound [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "Inbound.*"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"mode": "fixed",
|
|
"fixedColor": "blue"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "Outbound.*"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"mode": "fixed",
|
|
"fixedColor": "orange"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["rippled", "otel", "peer", "network", "telemetry"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "node",
|
|
"label": "Node",
|
|
"description": "Filter by rippled node (service.instance.id)",
|
|
"type": "query",
|
|
"query": "label_values(xrpld_peer_quality, exported_instance)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "Peer Quality",
|
|
"uid": "rippled-peer-quality"
|
|
}
|