mirror of
https://github.com/XRPLF/rippled.git
synced 2026-06-06 18:26:51 +00:00
7d8e908879
Visualise the metrics added in this series: - consensus-health: "Ledger History Mismatch Rate by Reason" (xrpld_ledger_history_mismatch_total by reason — fork diagnostics) - fee-market: "Queue Abandonment Rate (Expired)" and "Queue Admission Rejections (Dropped)" (xrpld_txq_expired_total / dropped_total) - peer-network: "Reduce-Relay Peer Selection" and "Reduce-Relay Missing-Tx Frequency" (xrpld_reduce_relay_metrics) - system-node-health: "Ledger Acquire Duration" and "Ledger Acquire Rate by Outcome" (ledger.acquire span) otel-collector-config.yaml: add outcome and acquire_reason spanmetrics dimensions so the ledger.acquire outcome breakdown populates. All panels follow the existing template: $node filter, exported_instance in legends, Title Case, axis labels. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
321 lines
9.9 KiB
JSON
321 lines
9.9 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"description": "Requires trace_peer=1 in the [telemetry] config section.",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Peer Proposal Receive Rate",
|
|
"description": "Rate of consensus proposals received from network peers. The peer.proposal.receive span (PeerImp.cpp) fires in onMessage(TMProposeSet) for each incoming proposal. Records xrpl.peer.id (sending peer) and proposal_trusted (whether the proposer is in our UNL). Requires trace_peer=1 in the telemetry config.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"peer.proposal.receive\"}[5m]))",
|
|
"legendFormat": "Proposals Received / Sec [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Proposals / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Peer Validation Receive Rate",
|
|
"description": "Rate of ledger validations received from network peers. The peer.validation.receive span (PeerImp.cpp) fires in onMessage(TMValidation) for each incoming validation message. Records xrpl.peer.id (sending peer) and validation_trusted (whether the validator is trusted). Requires trace_peer=1 in the telemetry config.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", span_name=\"peer.validation.receive\"}[5m]))",
|
|
"legendFormat": "Validations Received / Sec [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Validations / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Proposals Trusted vs Untrusted",
|
|
"description": "Pie chart showing the ratio of proposals received from trusted validators (in our UNL) vs untrusted validators. Grouped by the proposal_trusted span attribute (true/false). A healthy node connected to a well-configured UNL should see a significant portion of trusted proposals. Note: proposals that fail early validation may not have the trusted attribute set.",
|
|
"type": "piechart",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (proposal_trusted, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", proposal_trusted=~\"$proposal_trusted\", span_name=\"peer.proposal.receive\"}[5m]))",
|
|
"legendFormat": "Trusted = {{proposal_trusted}} [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Validations Trusted vs Untrusted",
|
|
"description": "Pie chart showing the ratio of validations received from trusted validators (in our UNL) vs untrusted validators. Grouped by the validation_trusted span attribute (true/false). Monitoring this helps detect if the node is receiving validations from the expected set of trusted validators. Note: validations that fail early checks may not have the trusted attribute set.",
|
|
"type": "piechart",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (validation_trusted, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", validation_trusted=~\"$validation_trusted\", span_name=\"peer.validation.receive\"}[5m]))",
|
|
"legendFormat": "Trusted = {{validation_trusted}} [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Reduce-Relay Peer Selection",
|
|
"description": "Transaction reduce-relay efficiency: peers selected as relay sources vs suppressed, plus peers with the feature disabled. A high suppressed:selected ratio proves reduce-relay is saving bandwidth; a high not_enabled count means stale peers force full relay.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "xrpld_reduce_relay_metrics{metric=\"selected_peers\",exported_instance=~\"$node\"}",
|
|
"legendFormat": "Selected [{{exported_instance}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "xrpld_reduce_relay_metrics{metric=\"suppressed_peers\",exported_instance=~\"$node\"}",
|
|
"legendFormat": "Suppressed [{{exported_instance}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "xrpld_reduce_relay_metrics{metric=\"not_enabled_peers\",exported_instance=~\"$node\"}",
|
|
"legendFormat": "Not Enabled [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"custom": {
|
|
"axisLabel": "Peer Count",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Reduce-Relay Missing-Tx Frequency",
|
|
"description": "Frequency of on-demand transaction fetches triggered when a peer is missing a relayed transaction. A rising value means the suppression is too aggressive and the on-demand fetch path is growing.",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "xrpld_reduce_relay_metrics{metric=\"missing_tx_freq\",exported_instance=~\"$node\"}",
|
|
"legendFormat": "Missing Tx Freq [{{exported_instance}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"custom": {
|
|
"axisLabel": "Frequency",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["xrpld", "peer"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "node",
|
|
"label": "Node",
|
|
"description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
|
|
"type": "query",
|
|
"query": "label_values(traces_span_metrics_calls_total, exported_instance)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "proposal_trusted",
|
|
"label": "Proposal Trusted",
|
|
"description": "Filter by proposal trust status (true = from trusted validator)",
|
|
"type": "query",
|
|
"query": "label_values(traces_span_metrics_calls_total{span_name=\"peer.proposal.receive\"}, proposal_trusted)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "validation_trusted",
|
|
"label": "Validation Trusted",
|
|
"description": "Filter by validation trust status (true = from trusted validator)",
|
|
"type": "query",
|
|
"query": "label_values(traces_span_metrics_calls_total{span_name=\"peer.validation.receive\"}, validation_trusted)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "Peer Network",
|
|
"uid": "xrpld-peer-net",
|
|
"refresh": "5s"
|
|
}
|