Files
rippled/docker/telemetry/grafanacloud/peer-quality.json
Pratik Mankawde cb1ca17442 feat(telemetry): add Grafana Cloud dashboard copies
Grafana Cloud variants of the 14 xrpld dashboards. Identical to the local
grafana/dashboards/ originals except the DS_PROMETHEUS / DS_TEMPO datasource
template variables have their `current` value pinned to the Grafana Cloud
datasource UIDs (grafanacloud-ripplex-prometheus / -traces).

Includes the ledger-data-sync data-type split and node-health mixed-unit
split + Cache Hit Ratio fix merged forward from phases 7 and 9.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-07-13 21:12:54 +01:00

542 lines
18 KiB
JSON

{
"annotations": {
"list": []
},
"description": "What this shows: Peer connection quality: latency, divergence, version distribution and upgrade guidance, resource disconnects, and inbound/outbound balance.\nUse it to: Assess how good this node's peer set is and whether connectivity or an upgrade needs attention.",
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"id": null,
"links": [],
"panels": [
{
"title": "P90 Peer Latency",
"description": "###### What this is:\n*90th-percentile round-trip latency to connected peers, in milliseconds.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the p90 peer latency.*\n\n###### Reading it:\n*Lower is better; green under 200ms, yellow to 500ms, red above.*\n\n###### Healthy range:\n*Under 200ms.*\n\n###### Watch for:\n*Rising latency, which points to network congestion or geographically distant, poorly performing peers.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerPeerQualityGauge`",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 0
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "peer_quality{metric=\"peer_latency_p90_ms\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
"legendFormat": "P90 Latency [{{service_instance_id}}]"
}
],
"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": "###### What this is:\n*Count of connected peers whose ledger state has diverged from the network.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the diverged-peer count.*\n\n###### Reading it:\n*Zero is healthy; any count means those peers disagree on ledger state.*\n\n###### Healthy range:\n*0 diverged peers.*\n\n###### Watch for:\n*A persistent non-zero count, which can indicate peers on a fork or misbehaving peers.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerPeerQualityGauge`",
"type": "stat",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 8
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "peer_quality{metric=\"peers_insane_count\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
"legendFormat": "Insane Peers [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"thresholds": {
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 1
},
{
"color": "red",
"value": 3
}
]
},
"custom": {}
},
"overrides": []
}
},
{
"title": "Higher Version Peers %",
"description": "###### What this is:\n*Percentage of connected peers running a newer rippled version than this node.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the higher-version peer percentage.*\n\n###### Reading it:\n*A high percentage suggests this node is behind and should be upgraded.*\n\n###### Healthy range:\n*Under 30%.*\n\n###### Watch for:\n*A majority of peers on a newer version, a strong upgrade signal.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerPeerQualityGauge`",
"type": "stat",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 16
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "peer_quality{metric=\"peers_higher_version_pct\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
"legendFormat": "Higher Version % [{{service_instance_id}}]"
}
],
"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": "###### What this is:\n*A flag indicating whether an upgrade is advised based on peer version analysis (Yes/No).*\n\n###### How it's computed:\n*Instantaneous gauge reading of the upgrade-recommended flag.*\n\n###### Reading it:\n*No is healthy; Yes means most peers run a newer version.*\n\n###### Healthy range:\n*No.*\n\n###### Watch for:\n*A Yes state, indicating the node risks falling out of step with the network.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerPeerQualityGauge`",
"type": "stat",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 24
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "peer_quality{metric=\"upgrade_recommended\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
"legendFormat": "Upgrade [{{service_instance_id}}]"
}
],
"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": "###### What this is:\n*Cumulative count of peers dropped for exceeding resource (load) limits.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the resource-disconnect total over time.*\n\n###### Reading it:\n*A flat line is healthy; a rising line means peers are being dropped for overuse.*\n\n###### Healthy range:\n*Flat / near constant.*\n\n###### Watch for:\n*A steep climb, which flags aggressive or misbehaving peers being shed as backpressure.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 32
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "server_info{metric=\"peer_disconnects_resources\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
"legendFormat": "Disconnects [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"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": "###### What this is:\n*Active inbound versus outbound peer connection counts.*\n\n###### How it's computed:\n*Instantaneous gauge readings of active inbound and outbound peer counts.*\n\n###### Reading it:\n*A balanced mix is healthy for connectivity and resilience.*\n\n###### Healthy range:\n*A mix of both; some outbound connections present.*\n\n###### Watch for:\n*All-inbound with no outbound, which usually means NAT or firewall issues block outbound peering.*\n\n###### Source:\n[PeerfinderManager.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/peerfinder/detail/PeerfinderManager.cpp)\n\n###### Function:\n`Logic Stats ctor`",
"type": "bargauge",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 40
},
"options": {
"orientation": "horizontal",
"displayMode": "gradient",
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "peer_finder_active_inbound_peers{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
"legendFormat": "Inbound [{{service_instance_id}}]"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "peer_finder_active_outbound_peers{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}",
"legendFormat": "Outbound [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"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": ["network", "peer"],
"templating": {
"list": [
{
"name": "DS_PROMETHEUS",
"type": "datasource",
"label": "Prometheus",
"query": "prometheus",
"regex": "",
"current": {
"text": "grafanacloud-ripplex-prometheus",
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
},
"hide": 0,
"refresh": 1,
"includeAll": false,
"multi": false,
"options": []
},
{
"name": "service_name",
"label": "Service Name",
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
"type": "query",
"query": "label_values(service_name)",
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "xrpld",
"value": "xrpld"
},
"multi": true,
"refresh": 2,
"sort": 1
},
{
"name": "deployment_environment",
"label": "Environment",
"description": "Filter by deployment tier [local / ci / test / prod]",
"type": "query",
"query": "label_values(deployment_environment)",
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
},
{
"name": "xrpl_network_type",
"label": "Network",
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
"type": "query",
"query": "label_values(xrpl_network_type)",
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
},
{
"name": "xrpl_work_item",
"label": "Work Item",
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
"type": "query",
"query": "label_values(xrpl_work_item)",
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
},
{
"name": "xrpl_branch",
"label": "Branch",
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
"type": "query",
"query": "label_values(xrpl_branch)",
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
},
{
"name": "xrpl_node_role",
"label": "Node Role",
"description": "Filter by node role (validator / peer)",
"type": "query",
"query": "label_values(xrpl_node_role)",
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
},
{
"name": "node",
"label": "Node",
"description": "Filter by rippled node (service.instance.id)",
"type": "query",
"query": "label_values(target_info, service_instance_id)",
"datasource": {
"type": "prometheus",
"uid": "${DS_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": "peer-quality",
"refresh": "10s"
}