mirror of
https://github.com/XRPLF/rippled.git
synced 2026-07-24 07:30:30 +00:00
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>
1109 lines
41 KiB
JSON
1109 lines
41 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"description": "What this shows: Validator agreement rates, validation counts, amendment and UNL status, server state tracking, and ledger close rate.\nUse it to: Confirm the validator is participating, agreeing with the network, and closing ledgers at the expected cadence.",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Validation Agreement",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Agreement % (1h)",
|
|
"description": "###### What this is:\n*Share of ledgers over the last hour where this validator agreed with the network consensus.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the 1-hour agreement percentage.*\n\n###### Reading it:\n*Higher is better; green at 95%+, yellow from 80%, red below.*\n\n###### Healthy range:\n*95-100%.*\n\n###### Watch for:\n*Values below 80%, meaning the validator frequently disagrees with consensus.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidationAgreementGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validation_agreement{metric=\"agreement_pct_1h\",service_instance_id=~\"$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": "Agreement 1h [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100,
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 80
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 95
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Agreement % (24h)",
|
|
"description": "###### What this is:\n*Share of ledgers over the last 24 hours where this validator agreed with consensus.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the 24-hour agreement percentage.*\n\n###### Reading it:\n*Higher is better; a smoother, longer-term view than the 1h stat.*\n\n###### Healthy range:\n*95-100%.*\n\n###### Watch for:\n*A sustained dip below 90%, which can indicate configuration drift or a network partition.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidationAgreementGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 9
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validation_agreement{metric=\"agreement_pct_24h\",service_instance_id=~\"$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": "Agreement 24h [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100,
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 80
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 95
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Agreements vs Missed (1h)",
|
|
"description": "###### What this is:\n*Counts of agreed versus missed validations over the last hour.*\n\n###### How it's computed:\n*Instantaneous gauge readings of the 1-hour agreed and missed counts.*\n\n###### Reading it:\n*Agreements should dominate; missed should be small.*\n\n###### Healthy range:\n*Missed near 0.*\n\n###### Watch for:\n*A high missed count, meaning the validator is skipping consensus rounds.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidationAgreementGauge`",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 17
|
|
},
|
|
"options": {
|
|
"orientation": "horizontal",
|
|
"displayMode": "gradient",
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validation_agreement{metric=\"agreements_1h\",service_instance_id=~\"$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": "Agreements 1h [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validation_agreement{metric=\"missed_1h\",service_instance_id=~\"$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": "Missed 1h [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "Missed.*"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"mode": "fixed",
|
|
"fixedColor": "red"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"title": "Agreements vs Missed (24h)",
|
|
"description": "###### What this is:\n*Counts of agreed versus missed validations over the last 24 hours.*\n\n###### How it's computed:\n*Instantaneous gauge readings of the 24-hour agreed and missed counts.*\n\n###### Reading it:\n*Agreements should dominate over the full day.*\n\n###### Healthy range:\n*Missed a small fraction of agreements.*\n\n###### Watch for:\n*A growing missed share, signalling longer-term reliability problems.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidationAgreementGauge`",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 25
|
|
},
|
|
"options": {
|
|
"orientation": "horizontal",
|
|
"displayMode": "gradient",
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validation_agreement{metric=\"agreements_24h\",service_instance_id=~\"$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": "Agreements 24h [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validation_agreement{metric=\"missed_24h\",service_instance_id=~\"$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": "Missed 24h [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "Missed.*"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"mode": "fixed",
|
|
"fixedColor": "red"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"title": "Validation Rates",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 33
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Validation Rate",
|
|
"description": "###### What this is:\n*Validations this node sends per minute.*\n\n###### How it's computed:\n*Per-second rate of the sent-validations counter over 5 minutes, scaled to per minute.*\n\n###### Reading it:\n*Should track the ledger close cadence; roughly one validation per closed ledger.*\n\n###### Healthy range:\n*About 12-20 per minute (one per closed ledger, ~3-5s close).*\n\n###### Watch for:\n*A drop toward zero, meaning the validator has stopped participating.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementValidationsSent (caller RCLConsensus.cpp)`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 34
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "rate(validations_sent_total{service_instance_id=~\"$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\"}[$__rate_interval]) * 60",
|
|
"legendFormat": "Sent/min [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "cpm",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 5
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 8
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Validations Checked Rate",
|
|
"description": "###### What this is:\n*Validations received from peers and checked per minute.*\n\n###### How it's computed:\n*Per-second rate of the checked-validations counter over 5 minutes, scaled to per minute.*\n\n###### Reading it:\n*Reflects how much validation traffic the network is delivering to this node.*\n\n###### Healthy range:\n*Workload-dependent; scales with trusted validator count.*\n\n###### Watch for:\n*A sudden collapse, which suggests peer connectivity loss or network isolation.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementValidationsChecked (caller NetworkOPs.cpp)`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 42
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "rate(validations_checked_total{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=~\"$xrpl_node_role\"}[$__rate_interval]) * 60",
|
|
"legendFormat": "Checked/min [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "cpm",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Amendment Blocked",
|
|
"description": "###### What this is:\n*Whether the node is amendment-blocked (OK/BLOCKED).*\n\n###### How it's computed:\n*Instantaneous gauge reading of the amendment-blocked flag.*\n\n###### Reading it:\n*OK is healthy; BLOCKED means an enabled amendment is unsupported by this build.*\n\n###### Healthy range:\n*OK.*\n\n###### Watch for:\n*A BLOCKED state, which halts validation and requires a software upgrade.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidatorHealthGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 50
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validator_health{metric=\"amendment_blocked\",service_instance_id=~\"$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": "Blocked [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": {
|
|
"text": "OK",
|
|
"color": "green"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"1": {
|
|
"text": "BLOCKED",
|
|
"color": "red"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "UNL Expiry (days)",
|
|
"description": "###### What this is:\n*Days remaining until the current UNL (trusted validator list) expires.*\n\n###### How it's computed:\n*Instantaneous gauge reading of days-to-expiry.*\n\n###### Reading it:\n*Higher is safer; green at 30+, yellow under 7, red at expiry.*\n\n###### Healthy range:\n*30+ days.*\n\n###### Watch for:\n*Fewer than 7 days, after which the node loses its trusted validator set if not renewed.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidatorHealthGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 58
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validator_health{metric=\"unl_expiry_days\",service_instance_id=~\"$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": "UNL Expiry [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "d",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 7
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 30
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "UNL Blocked",
|
|
"description": "###### What this is:\n*Whether the node's UNL is blocked (OK/BLOCKED).*\n\n###### How it's computed:\n*Instantaneous gauge reading of the UNL-blocked flag.*\n\n###### Reading it:\n*OK is healthy; BLOCKED means validator trust cannot be established.*\n\n###### Healthy range:\n*OK.*\n\n###### Watch for:\n*A BLOCKED state, which can stop the node participating in consensus.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidatorHealthGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 66
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validator_health{metric=\"unl_blocked\",service_instance_id=~\"$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": "UNL Blocked [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": {
|
|
"text": "OK",
|
|
"color": "green"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"1": {
|
|
"text": "BLOCKED",
|
|
"color": "red"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Agreement/Missed Counters (Rate)",
|
|
"description": "###### What this is:\n*Rate of cumulative agreement and missed-validation counters per minute.*\n\n###### How it's computed:\n*Per-second rate of each monotonic counter over 5 minutes, scaled to per minute.*\n\n###### Reading it:\n*Agreements should dominate; the missed line should stay low.*\n\n###### Healthy range:\n*Missed rate near 0.*\n\n###### Watch for:\n*A rising missed rate, complementing the windowed agreement percentages above.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidationTotalsCounters`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 74
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "rate(validation_agreements_total{service_instance_id=~\"$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\"}[$__rate_interval]) * 60",
|
|
"legendFormat": "Agreements/min [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "rate(validation_missed_total{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=~\"$xrpl_node_role\"}[$__rate_interval]) * 60",
|
|
"legendFormat": "Missed/min [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "cpm",
|
|
"custom": {
|
|
"axisLabel": "Per Minute",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "Missed.*"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "color",
|
|
"value": {
|
|
"mode": "fixed",
|
|
"fixedColor": "red"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"title": "Server State & Consensus",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 82
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Validation Quorum",
|
|
"description": "###### What this is:\n*Minimum number of trusted validations required to declare a ledger fully validated.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the current quorum requirement.*\n\n###### Reading it:\n*Tracks the quorum derived from the active validator list; changes when the list changes.*\n\n###### Healthy range:\n*Stable at the network-appropriate value.*\n\n###### Watch for:\n*An unexpected drop, which can weaken consensus safety guarantees.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidatorHealthGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 83
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validator_health{metric=\"validation_quorum\",service_instance_id=~\"$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": "Quorum [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "State Value Timeline",
|
|
"description": "###### What this is:\n*Numeric encoding of the server operating state (disconnected, connected, syncing, tracking, full, validating, proposing) over time.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the encoded state value.*\n\n###### Reading it:\n*A flat line at the full-operation state is healthy; steps show transitions.*\n\n###### Healthy range:\n*Steady at the highest (full) state.*\n\n###### Watch for:\n*Frequent transitions, useful for correlating state flapping with other metrics.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerStateTrackingGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 91
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "state_tracking{metric=\"state_value\",service_instance_id=~\"$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": "State [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "State",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Time in Current State",
|
|
"description": "###### What this is:\n*How long the server has held its current operating state, in seconds.*\n\n###### How it's computed:\n*Current value of the time-in-state gauge.*\n\n###### Reading it:\n*Not yet wired in the code; the value currently always reads 0.*\n\n###### Healthy range:\n*Not applicable; the value is always 0 today.*\n\n###### Watch for:\n*n/a until implemented.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerStateTrackingGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 99
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "state_tracking{metric=\"time_in_current_state_seconds\",service_instance_id=~\"$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": "Time in State [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "State Changes Rate",
|
|
"description": "###### What this is:\n*Rate of server operating-state changes per hour.*\n\n###### How it's computed:\n*Per-hour rate of the state-change counter, averaged over a 1-hour window.*\n\n###### Reading it:\n*Near zero is healthy; each increment is one state transition.*\n\n###### Healthy range:\n*Near 0 changes per hour.*\n\n###### Watch for:\n*Frequent transitions, which point to network instability or configuration problems.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementStateChanges (caller NetworkOPs.cpp)`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 107
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "3600 * sum by (service_instance_id) (rate(state_changes_total{service_instance_id=~\"$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\"}[$__rate_interval]))",
|
|
"legendFormat": "Changes/hr [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "suffix:/hr",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 5
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Ledgers Closed Rate",
|
|
"description": "###### What this is:\n*Ledgers closed per minute by this node.*\n\n###### How it's computed:\n*Per-second rate of the ledgers-closed counter over 5 minutes, scaled to per minute.*\n\n###### Reading it:\n*Should match the network's steady close cadence.*\n\n###### Healthy range:\n*About 12-20 per minute (one per closed ledger, ~3-5s close).*\n\n###### Watch for:\n*Deviation from the expected cadence, which indicates consensus timing trouble or the node falling behind.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementLedgersClosed (caller RCLConsensus.cpp)`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 115
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "rate(ledgers_closed_total{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=~\"$xrpl_node_role\"}[$__rate_interval]) * 60",
|
|
"legendFormat": "Closed/min [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "cpm",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 5
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 8
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Agreement % (7d)",
|
|
"description": "###### What this is:\n*Share of ledgers over the trailing 7 days where this validator agreed with consensus.*\n\n###### How it's computed:\n*Instantaneous gauge reading of the 7-day agreement percentage.*\n\n###### Reading it:\n*The long-term reliability window; higher is better.*\n\n###### Healthy range:\n*95-100%.*\n\n###### Watch for:\n*A gradual decline, which reflects chronic rather than transient disagreement.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidationAgreementGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 123
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validation_agreement{metric=\"agreement_pct_7d\",service_instance_id=~\"$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": "Agreement 7d [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100,
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 80
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 95
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Agreements vs Missed (7d)",
|
|
"description": "###### What this is:\n*Agreed versus missed validation counts over the trailing 7 days.*\n\n###### How it's computed:\n*Instantaneous gauge readings of the 7-day agreed and missed counts.*\n\n###### Reading it:\n*Agreements should dominate across the week.*\n\n###### Healthy range:\n*Missed a small fraction of agreements.*\n\n###### Watch for:\n*A rising missed trend, signalling sustained validator unreliability.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerValidationAgreementGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 131
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validation_agreement{metric=\"agreements_7d\",service_instance_id=~\"$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": "Agreements 7d [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "validation_agreement{metric=\"missed_7d\",service_instance_id=~\"$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": "Missed 7d [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Count",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["validator", "health"],
|
|
"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": "Validator Health",
|
|
"uid": "validator-health",
|
|
"refresh": "10s"
|
|
}
|