mirror of
https://github.com/XRPLF/rippled.git
synced 2026-07-24 07:30:30 +00:00
cb1ca17442
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>
1351 lines
55 KiB
JSON
1351 lines
55 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Validation Send Rate",
|
|
"description": "###### What this is:\n*How often this node issues a ledger validation to the network. Each validation asserts the node fully validated one ledger.*\n\n###### How it's computed:\n*Per-second rate of validation events sent, summed per node over a 5-minute window.*\n\n###### Reading it:\n*A flat line at the network's ledger cadence is normal; higher is not better and lower means the node is validating less often.*\n\n###### Healthy range:\n*Roughly one validation per closed ledger (about 0.2-0.3/s on a healthy chain).*\n\n###### Watch for:\n*A drop to zero on a validator means it stopped validating; a value well below the close rate means validation is lagging.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::createValidationSpan`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$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\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.validation.send\"}[$__rate_interval]))",
|
|
"legendFormat": "Validations / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 1
|
|
},
|
|
{
|
|
"title": "Consensus Mode Over Time",
|
|
"description": "###### What this is:\n*Ledger-close activity split by the node's consensus mode (Proposing, Observing, Wrong Ledger, Switched Ledger).*\n\n###### How it's computed:\n*Per-second rate of ledger-close events grouped by consensus mode, per node, over a 5-minute window.*\n\n###### Reading it:\n*One dominant band is normal; a validator should sit almost entirely in Proposing, a stock node in Observing.*\n\n###### Healthy range:\n*Nearly all activity in a single expected mode.*\n\n###### Watch for:\n*Sustained time in Wrong Ledger or Switched Ledger indicates the node is out of sync or flapping between chains.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::onClose`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (consensus_mode, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$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\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[$__rate_interval]))",
|
|
"legendFormat": "{{consensus_mode}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Events / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 2
|
|
},
|
|
{
|
|
"title": "Consensus Proposals Sent Rate",
|
|
"description": "###### What this is:\n*How often this node proposes its candidate transaction set to peers during consensus.*\n\n###### How it's computed:\n*Per-second rate of proposal-send events, summed per node over a 5-minute window.*\n\n###### Reading it:\n*A steady line tracking the ledger cadence is healthy; only proposing (validator) nodes show activity.*\n\n###### Healthy range:\n*Steady output in step with the close rate for a proposing node; zero for a non-proposing node.*\n\n###### Watch for:\n*A proposing validator dropping to zero, or erratic spikes suggesting repeated re-proposals within rounds.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::propose`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$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\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.proposal.send\"}[$__rate_interval]))",
|
|
"legendFormat": "Proposals / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Proposals / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 3
|
|
},
|
|
{
|
|
"title": "Accept vs Close Rate",
|
|
"description": "###### What this is:\n*Two rates side by side: ledgers accepted after consensus versus ledger closes initiated.*\n\n###### How it's computed:\n*Per-second rate of accept events and of close events, each summed per node over a 5-minute window.*\n\n###### Reading it:\n*The two lines should overlap; read any gap between them as closes that did not finish accepting.*\n\n###### Healthy range:\n*Both lines equal and tracking the network close cadence.*\n\n###### Watch for:\n*A persistent gap where closes exceed accepts points to consensus rounds failing or timing out before acceptance.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::makeAcceptSpan / RCLConsensus::Adaptor::onClose`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$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\", span_name=\"consensus.accept\"}[$__rate_interval]))",
|
|
"legendFormat": "Accepts / Sec [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_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=~\"$xrpl_node_role\", span_name=\"consensus.ledger_close\"}[$__rate_interval]))",
|
|
"legendFormat": "Closes / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Events / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 4
|
|
},
|
|
{
|
|
"title": "Validation vs Close Rate",
|
|
"description": "###### What this is:\n*Two rates side by side: validations sent versus ledger closes, so you can see whether every closed ledger gets validated.*\n\n###### How it's computed:\n*Per-second rate of validation-send events and of close events, each summed per node over a 5-minute window.*\n\n###### Reading it:\n*The lines should overlap; a validation line below the close line means validation is falling behind.*\n\n###### Healthy range:\n*Both lines equal at the network close cadence.*\n\n###### Watch for:\n*Validations persistently trailing closes, which means the node validates fewer ledgers than it closes.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::createValidationSpan / RCLConsensus::Adaptor::onClose`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$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\", span_name=\"consensus.validation.send\"}[$__rate_interval]))",
|
|
"legendFormat": "Validations / Sec [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_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=~\"$xrpl_node_role\", span_name=\"consensus.ledger_close\"}[$__rate_interval]))",
|
|
"legendFormat": "Closes / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Events / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 5
|
|
},
|
|
{
|
|
"title": "Time to Reach Consensus (p50/p95)",
|
|
"description": "###### What this is:\n*Wall-clock time for the network to agree a ledger, at the median and 95th percentile.*\n\n###### How it's computed:\n*The recorded per-round agreement time is aggregated to its 50th and 95th percentile over the window.*\n\n###### Reading it:\n*Lower is better; the p95 line shows the worst typical rounds while p50 shows the common case.*\n\n###### Healthy range:\n*Roughly 2-4 seconds on mainnet; workload- and network-dependent.*\n\n###### Watch for:\n*Rising percentiles, or a p95 that pulls far above p50, signal slow or contentious rounds under load or poor peer connectivity.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::makeAcceptSpan`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "${DS_TEMPO}"
|
|
},
|
|
"queryType": "traceql",
|
|
"query": "{name=\"consensus.accept\" && resource.service.instance.id=~\"$node\"} | quantile_over_time(span.round_time_ms, .5)",
|
|
"legendFormat": "P50 Time to Consensus [{{resource.service.instance.id}}]",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "${DS_TEMPO}"
|
|
},
|
|
"queryType": "traceql",
|
|
"refId": "B",
|
|
"query": "{name=\"consensus.accept\" && resource.service.instance.id=~\"$node\"} | quantile_over_time(span.round_time_ms, .95)",
|
|
"legendFormat": "P95 Time to Consensus [{{resource.service.instance.id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Time to Consensus (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 6
|
|
},
|
|
{
|
|
"title": "Average Time to Reach Consensus",
|
|
"description": "###### What this is:\n*Mean wall-clock time for the network to agree a ledger.*\n\n###### How it's computed:\n*The recorded per-round agreement time averaged over the window.*\n\n###### Reading it:\n*Lower is better; watch the trend rather than any single point.*\n\n###### Healthy range:\n*Roughly 2-4 seconds on mainnet; workload-dependent.*\n\n###### Watch for:\n*A steady upward drift indicates the network is taking longer to converge, often from load or connectivity problems.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::makeAcceptSpan`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "${DS_TEMPO}"
|
|
},
|
|
"queryType": "traceql",
|
|
"query": "{name=\"consensus.accept\" && resource.service.instance.id=~\"$node\"} | avg_over_time(span.round_time_ms)",
|
|
"legendFormat": "Avg Time to Consensus [{{resource.service.instance.id}}]",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Time to Consensus (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 7
|
|
},
|
|
{
|
|
"title": "Consensus Rounds per Ledger (Establish Count)",
|
|
"description": "###### What this is:\n*How many establish-phase iterations each ledger needed before validators converged.*\n\n###### How it's computed:\n*Ledgers are counted over the window and grouped by their iteration count; each series is one count value.*\n\n###### Reading it:\n*Most weight on the '1' series is ideal; weight shifting to 2, 3 or more shows harder convergence.*\n\n###### Healthy range:\n*The large majority of ledgers converging in one iteration.*\n\n###### Watch for:\n*A growing share of ledgers needing several iterations, indicating disagreement or network stress.*\n\n###### Source:\n[Consensus.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/consensus/Consensus.h)\n\n###### Function:\n`Consensus::startEstablishTracing`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 32
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc",
|
|
"maxHeight": 500
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["mean", "max", "lastNotNull"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "${DS_TEMPO}"
|
|
},
|
|
"queryType": "traceql",
|
|
"refId": "A",
|
|
"query": "{name=\"consensus.establish\" && resource.service.instance.id=~\"$node\"} | count_over_time() by (span.establish_count)",
|
|
"legendFormat": "{{span.establish_count}} Rounds"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Ledgers in Window",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"decimals": 0
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 8
|
|
},
|
|
{
|
|
"title": "Previous Round Time per Ledger",
|
|
"description": "###### What this is:\n*Duration of the immediately preceding consensus round, at the 95th percentile.*\n\n###### How it's computed:\n*The prior round's recorded duration is aggregated to its 95th percentile over the window.*\n\n###### Reading it:\n*Lower is better; complements the time-to-consensus panels with the previous round's cost.*\n\n###### Healthy range:\n*Comparable to the current time-to-consensus, roughly a few seconds.*\n\n###### Watch for:\n*A rising p95 means recent rounds have been expensive, often preceding a slowdown in ledger cadence.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::startRoundTracing`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 40
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "${DS_TEMPO}"
|
|
},
|
|
"queryType": "traceql",
|
|
"query": "{name=\"consensus.round\" && resource.service.instance.id=~\"$node\"} | quantile_over_time(span.previous_round_time_ms, .95)",
|
|
"legendFormat": "P95 Previous Round [{{resource.service.instance.id}}]",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Round Time (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 9
|
|
},
|
|
{
|
|
"title": "Position Update Duration",
|
|
"description": "###### What this is:\n*Time this node spends each round tallying disputes and updating its consensus position, at the 95th percentile.*\n\n###### How it's computed:\n*Per-round position-update durations are aggregated to their 95th percentile over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; short, flat durations are normal.*\n\n###### Healthy range:\n*A few milliseconds under normal load.*\n\n###### Watch for:\n*Sustained high durations point to heavy dispute resolution or slow convergence on close time.*\n\n###### Source:\n[Consensus.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/consensus/Consensus.h)\n\n###### Function:\n`Consensus::updateOurPositions`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 40
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$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\", span_name=\"consensus.update_positions\"}[5m])))",
|
|
"legendFormat": "P95 Update [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 10
|
|
},
|
|
{
|
|
"title": "Ledger Close Duration",
|
|
"description": "###### What this is:\n*Time from when consensus triggers a ledger close to when the close completes, at the 95th percentile.*\n\n###### How it's computed:\n*Per-close durations are aggregated to their 95th percentile per node over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; compare against the round time to see how much of it the close accounts for.*\n\n###### Healthy range:\n*A few to tens of milliseconds; workload-dependent.*\n\n###### Watch for:\n*A rising p95 indicates the close step is becoming a bottleneck, often under heavy transaction volume.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::onClose`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 48
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$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\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[5m])))",
|
|
"legendFormat": "P95 Close Duration [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 11
|
|
},
|
|
{
|
|
"title": "Ledger Apply Duration (doAccept)",
|
|
"description": "###### What this is:\n*Time spent applying the agreed transaction set to build the new ledger, at the 95th percentile.*\n\n###### How it's computed:\n*Per-apply durations are aggregated to their 95th percentile per node over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; this is the cost of executing the ledger's transactions.*\n\n###### Healthy range:\n*A few to tens of milliseconds, scaling with the number of transactions in the ledger.*\n\n###### Watch for:\n*A rising p95 alongside high transaction counts signals apply-stage load, whether organic or from a flood of transactions.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::doAccept`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 48
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(span_duration_milliseconds_bucket{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=~\"$xrpl_node_role\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept.apply\"}[5m])))",
|
|
"legendFormat": "P95 Apply Duration [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 12
|
|
},
|
|
{
|
|
"title": "Consensus Accept Duration Heatmap",
|
|
"description": "###### What this is:\n*Distribution of how long the accept step takes across rounds, over time.*\n\n###### How it's computed:\n*Accept durations are bucketed by duration band and counted per 5-minute window, drawn as a heatmap.*\n\n###### Reading it:\n*A tight low band is healthy; brighter cells higher up mean more slow rounds.*\n\n###### Healthy range:\n*Most rounds concentrated in the lowest duration bands.*\n\n###### Watch for:\n*A widening or upward-drifting hot band flags outlier rounds that take abnormally long.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::makeAcceptSpan`",
|
|
"type": "heatmap",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 56
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"yAxis": {
|
|
"axisLabel": "Duration (ms)",
|
|
"unit": "ms"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum(increase(span_duration_milliseconds_bucket{service_instance_id=~\"$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\", span_name=\"consensus.accept\"}[5m])) by (le)",
|
|
"legendFormat": "{{le}}",
|
|
"format": "heatmap"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms"
|
|
}
|
|
},
|
|
"id": 13
|
|
},
|
|
{
|
|
"title": "Close-Time Agreement Rate (Agreed vs Disagreed)",
|
|
"description": "###### What this is:\n*How often validators agreed on the ledger close time versus agreed to disagree.*\n\n###### How it's computed:\n*Per-second rate of rounds split into Agreed and Disagreed, per node, over the rate interval.*\n\n###### Reading it:\n*Mostly Agreed is healthy; occasional Disagreed is normal when validator clocks differ slightly.*\n\n###### Healthy range:\n*Overwhelmingly Agreed.*\n\n###### Watch for:\n*A sustained rise in Disagreed points to clock drift or latency spread across the validator set.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::doAccept`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 56
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (close_time_correct, service_instance_id) (rate(span_calls_total{span_name=\"consensus.accept.apply\", consensus_mode=~\"$consensus_mode\", 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": "{{close_time_correct}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Rounds / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 14,
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": ".*true.*",
|
|
"renamePattern": "Agreed"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": ".*false.*",
|
|
"renamePattern": "Disagreed"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Close Time Vote Bins & Resolution",
|
|
"description": "###### What this is:\n*Two related values: how many distinct close-time votes were seen, and the current close-time rounding granularity in ms.*\n\n###### How it's computed:\n*Both values are averaged over the window and plotted on dual axes.*\n\n###### Reading it:\n*Fewer vote bins and a fine resolution mean tight agreement; more bins and a coarse resolution mean disagreement.*\n\n###### Healthy range:\n*Few bins with a fine (about 10s) resolution.*\n\n###### Watch for:\n*Rising bins with the resolution widening (toward 120s) shows validators struggling to agree on close time.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::doAccept`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 64
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineInterpolation": "stepAfter",
|
|
"pointSize": 5,
|
|
"showPoints": "auto",
|
|
"axisLabel": "Count / Milliseconds"
|
|
},
|
|
"unit": "short"
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "Vote Bins"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "unit",
|
|
"value": "short"
|
|
},
|
|
{
|
|
"id": "custom.axisPlacement",
|
|
"value": "left"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byName",
|
|
"options": "Resolution"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "unit",
|
|
"value": "ms"
|
|
},
|
|
{
|
|
"id": "custom.axisPlacement",
|
|
"value": "right"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "bottom",
|
|
"calcs": ["mean", "max"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "${DS_TEMPO}"
|
|
},
|
|
"queryType": "traceql",
|
|
"query": "{name=\"consensus.accept.apply\" && resource.service.instance.id=~\"$node\"} | avg_over_time(span.close_time_vote_bins)",
|
|
"legendFormat": "Avg Vote Bins",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "${DS_TEMPO}"
|
|
},
|
|
"queryType": "traceql",
|
|
"query": "{name=\"consensus.accept.apply\" && resource.service.instance.id=~\"$node\"} | avg_over_time(span.close_resolution_ms)",
|
|
"legendFormat": "Avg Resolution (ms)",
|
|
"refId": "B"
|
|
}
|
|
],
|
|
"id": 15
|
|
},
|
|
{
|
|
"title": "Close-Time Resolution Change (per Round)",
|
|
"description": "###### What this is:\n*Whether the close-time rounding granularity moved Coarser, Finer, or stayed Steady versus the previous round.*\n\n###### How it's computed:\n*Rounds are counted over the window and grouped by direction of change.*\n\n###### Reading it:\n*Mostly Steady is healthy; Coarser means widening bins (more disagreement), Finer means tightening.*\n\n###### Healthy range:\n*Predominantly Steady.*\n\n###### Watch for:\n*Frequent Coarser shifts indicate the network is repeatedly failing to agree on close time.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::doAccept`",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 64
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 0,
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "blue"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"orientation": "horizontal",
|
|
"displayMode": "gradient",
|
|
"showUnfilled": true,
|
|
"reduceOptions": {
|
|
"calcs": ["sum"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"legend": {
|
|
"showLegend": false
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "${DS_TEMPO}"
|
|
},
|
|
"queryType": "traceql",
|
|
"query": "{name=\"consensus.accept.apply\" && resource.service.instance.id=~\"$node\" && span.resolution_direction=~\"$resolution_direction\"} | count_over_time() by (span.resolution_direction)",
|
|
"legendFormat": "{{span.resolution_direction}}",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"id": 16,
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "increased",
|
|
"renamePattern": "Coarser (more disagreement)"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "decreased",
|
|
"renamePattern": "Finer (better agreement)"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "unchanged",
|
|
"renamePattern": "Steady"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Close-Time Proposal Spread (Distinct Positions per Round)",
|
|
"description": "###### What this is:\n*How spread out validators' proposed close times were, as the number of distinct positions per round.*\n\n###### How it's computed:\n*Rounds are counted over the window and grouped by their distinct-position count; each bar is one count value.*\n\n###### Reading it:\n*Weight on '1 distinct position' means everyone agreed; weight on 2 or more means the proposals split.*\n\n###### Healthy range:\n*Most rounds at a single distinct position.*\n\n###### Watch for:\n*A shift toward two or more distinct positions signals growing clock drift or latency across validators.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::doAccept`",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 72
|
|
},
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 0,
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "blue"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"orientation": "horizontal",
|
|
"displayMode": "gradient",
|
|
"showUnfilled": true,
|
|
"reduceOptions": {
|
|
"calcs": ["sum"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"legend": {
|
|
"showLegend": false
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "tempo",
|
|
"uid": "${DS_TEMPO}"
|
|
},
|
|
"queryType": "traceql",
|
|
"query": "{name=\"consensus.accept.apply\" && resource.service.instance.id=~\"$node\"} | count_over_time() by (span.close_time_vote_bins)",
|
|
"legendFormat": "{{span.close_time_vote_bins}} Distinct Position(s)",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"id": 17
|
|
},
|
|
{
|
|
"title": "Consensus Outcome Distribution (per Round)",
|
|
"description": "###### What this is:\n*How consensus rounds concluded: Agreed, Moved On (partial), Expired (timeout), or No Consensus.*\n\n###### How it's computed:\n*Rounds over the window are counted and grouped by outcome, shown as shares of a pie.*\n\n###### Reading it:\n*An almost fully Agreed pie is healthy; other slices represent degraded outcomes.*\n\n###### Healthy range:\n*Nearly 100 percent Agreed.*\n\n###### Watch for:\n*A growing Moved On or Expired share signals network stress, disagreement, or connectivity loss.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::makeAcceptSpan`",
|
|
"type": "piechart",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 80
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"values": ["value", "percent"]
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (consensus_state) (increase(span_calls_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=~\"$xrpl_node_role\", span_name=\"consensus.accept\", consensus_state!=\"\"}[$__rate_interval]))",
|
|
"legendFormat": "{{consensus_state}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 18,
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "yes",
|
|
"renamePattern": "Agreed"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "moved_on",
|
|
"renamePattern": "Moved On (partial)"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "expired",
|
|
"renamePattern": "Expired (timeout)"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "^no$",
|
|
"renamePattern": "No Consensus"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Consensus Failures Over Time",
|
|
"description": "###### What this is:\n*Rate of non-normal consensus outcomes (moved-on plus expired) over time.*\n\n###### How it's computed:\n*Per-second rate of the moved-on and expired outcomes, summed per node over a 5-minute window.*\n\n###### Reading it:\n*Flat at zero is healthy; any sustained line is a concern.*\n\n###### Healthy range:\n*Zero under normal operation.*\n\n###### Watch for:\n*Spikes or a persistent nonzero rate indicate consensus instability that can precede ledger stalls or forks.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::makeAcceptSpan`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 88
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_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=~\"$xrpl_node_role\", span_name=\"consensus.accept\", consensus_state=\"moved_on\"}[$__rate_interval]))",
|
|
"legendFormat": "moved_on [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$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\", span_name=\"consensus.accept\", consensus_state=\"expired\"}[$__rate_interval]))",
|
|
"legendFormat": "expired [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Failures / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 19
|
|
},
|
|
{
|
|
"title": "Consensus Stall Rate",
|
|
"description": "###### What this is:\n*Rate at which consensus health checks report a stalled condition versus not stalled.*\n\n###### How it's computed:\n*Per-second rate of consensus checks split by stalled flag, summed per node over a 5-minute window.*\n\n###### Reading it:\n*The Not Stalled line should carry all the weight; any Stalled line is an early warning.*\n\n###### Healthy range:\n*Stalled at zero.*\n\n###### Watch for:\n*A nonzero stalled rate surfaces stalls before they show up as validated-ledger-age alarms.*\n\n###### Source:\n[Consensus.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/consensus/Consensus.h)\n\n###### Function:\n`Consensus::haveConsensus`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 88
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_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=~\"$xrpl_node_role\", span_name=\"consensus.check\", consensus_stalled=\"true\"}[$__rate_interval]))",
|
|
"legendFormat": "Stalled [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$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\", span_name=\"consensus.check\", consensus_stalled=\"false\"}[$__rate_interval]))",
|
|
"legendFormat": "Not Stalled [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Checks / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 20
|
|
},
|
|
{
|
|
"title": "Consensus Mode-Change Rate by Target Mode",
|
|
"description": "###### What this is:\n*How often the node switches consensus mode, broken down by the mode it switched into.*\n\n###### How it's computed:\n*Per-second rate of mode-change events grouped by target mode, per node, over a 5-minute window.*\n\n###### Reading it:\n*Near-zero is healthy; a stable node rarely changes mode.*\n\n###### Healthy range:\n*Essentially zero mode changes in steady state.*\n\n###### Watch for:\n*Frequent switches into Wrong Ledger or Switched Ledger mark an unstable node at risk of forking.*\n\n###### Source:\n[RCLConsensus.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/consensus/RCLConsensus.cpp)\n\n###### Function:\n`RCLConsensus::Adaptor::onModeChange`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 96
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (mode_new, service_instance_id) (rate(span_calls_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=~\"$xrpl_node_role\", span_name=\"consensus.mode_change\"}[$__rate_interval]))",
|
|
"legendFormat": "{{mode_new}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Mode Changes / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 21
|
|
},
|
|
{
|
|
"title": "Ledger History Mismatch Rate by Reason",
|
|
"description": "###### What this is:\n*Rate of built-versus-validated ledger mismatches, broken down by why they diverged.*\n\n###### How it's computed:\n*Per-second rate of mismatch events grouped by reason, per node, over a 5-minute window.*\n\n###### Reading it:\n*Flat at zero is healthy; the reason label tells you the nature of any divergence.*\n\n###### Healthy range:\n*Zero under normal operation.*\n\n###### Watch for:\n*Any sustained rate marks a fork; the reason distinguishes close-time disagreement, sync drift, and transaction-processing differences.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementLedgerHistoryMismatch`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 96
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (reason, service_instance_id) (rate(ledger_history_mismatch_total{service_instance_id=~\"$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\"}[$__rate_interval]))",
|
|
"legendFormat": "{{reason}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Mismatches / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 22
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["consensus"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "DS_PROMETHEUS",
|
|
"type": "datasource",
|
|
"label": "Prometheus",
|
|
"query": "prometheus",
|
|
"regex": "",
|
|
"current": {
|
|
"text": "grafanacloud-ripplex-prometheus",
|
|
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
|
},
|
|
"hide": 0,
|
|
"refresh": 1,
|
|
"includeAll": false,
|
|
"multi": false,
|
|
"options": []
|
|
},
|
|
{
|
|
"name": "DS_TEMPO",
|
|
"type": "datasource",
|
|
"label": "Tempo",
|
|
"query": "tempo",
|
|
"regex": "",
|
|
"current": {
|
|
"text": "grafanacloud-ripplex-traces",
|
|
"value": "grafanacloud-traces"
|
|
},
|
|
"hide": 0,
|
|
"refresh": 1,
|
|
"includeAll": false,
|
|
"multi": false,
|
|
"options": []
|
|
},
|
|
{
|
|
"name": "service_name",
|
|
"label": "Service Name",
|
|
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
|
"type": "query",
|
|
"query": "label_values(service_name)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${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 — e.g. Node-1)",
|
|
"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
|
|
},
|
|
{
|
|
"name": "consensus_mode",
|
|
"label": "Consensus Mode",
|
|
"description": "Filter by consensus mode (Proposing, Observing, Wrong Ledger, Switched Ledger)",
|
|
"type": "query",
|
|
"query": "label_values(span_calls_total{span_name=\"consensus.ledger_close\"}, consensus_mode)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "close_time_correct",
|
|
"label": "Close Time Agreed",
|
|
"type": "custom",
|
|
"query": "true,false",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"multi": true,
|
|
"options": [
|
|
{
|
|
"text": "All",
|
|
"value": "$__all",
|
|
"selected": true
|
|
},
|
|
{
|
|
"text": "true",
|
|
"value": "true",
|
|
"selected": false
|
|
},
|
|
{
|
|
"text": "false",
|
|
"value": "false",
|
|
"selected": false
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"name": "resolution_direction",
|
|
"label": "Resolution Direction",
|
|
"type": "custom",
|
|
"query": "increased,decreased,unchanged",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"multi": true,
|
|
"options": [
|
|
{
|
|
"text": "All",
|
|
"value": "$__all",
|
|
"selected": true
|
|
},
|
|
{
|
|
"text": "increased",
|
|
"value": "increased",
|
|
"selected": false
|
|
},
|
|
{
|
|
"text": "decreased",
|
|
"value": "decreased",
|
|
"selected": false
|
|
},
|
|
{
|
|
"text": "unchanged",
|
|
"value": "unchanged",
|
|
"selected": false
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "Consensus Health",
|
|
"uid": "consensus-health",
|
|
"description": "What this shows: Consensus health for XRPL nodes: how reliably and quickly the network agrees each ledger, and where agreement breaks down.\nUse it to: Spot stalled or slow consensus rounds and pinpoint the phase where agreement is failing.",
|
|
"refresh": "10s"
|
|
}
|