mirror of
https://github.com/XRPLF/rippled.git
synced 2026-07-23 15:10:34 +00:00
Panel legends only showed the node (service_instance_id); the perf-iac
filter dimensions (xrpl_branch, xrpl_node_role) never appeared, so
baseline-vs-test series were indistinguishable.
Each node-referencing target now injects its curated name via
label_replace(...,"series",...) and uses the Prometheus "__auto" legend,
which shows only labels that vary across the displayed series. A
renameByRegex chain reshapes the auto output into
"Name [node, role]-[branch, work_item]", collapsing empty groups so a
dimension appears only when the filter widens it. Aggregating queries gain
xrpl_branch/xrpl_node_role in their by() so those labels survive; multi-
dimension legends keep their rich label set and append branch/role.
Quantile panels surfaced the quantile via the panel title (q$quantile),
since {{quantile}} is a dashboard variable, not a series label.
Timeseries panels now connect only null gaps shorter than 30m
(spanNulls=1800000): brief scrape gaps bridge, genuine outages stay broken.
Non-node panels (heatmaps, rows, tables, state timelines, category/bucket
series) are left unchanged. Applied to all 14 dashboards.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
936 lines
31 KiB
JSON
936 lines
31 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"description": "What this shows: Consensus proposals and validations received from peers, and transaction relay efficiency for this node.\nUse it to: Check that peers are feeding this node proposals, validations, and transactions, and gauge relay overhead.",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Peer Proposal Receive Rate",
|
|
"description": "###### What this is:\n*How many consensus proposals this node receives from peers per second.*\n\n###### How it's computed:\n*Per-second rate of received proposals over 5 minutes, per node.*\n\n###### Reading it:\n*A steady rate roughly proportional to the number of proposing validators.*\n\n###### Healthy range:\n*Workload-dependent; scales with validator count and connectivity.*\n\n###### Watch for:\n*A drop toward zero (isolation from the network) or a sudden flood far above baseline (proposal spam).*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::onMessage(TMProposeSet)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (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=~\"$xrpl_node_role\", span_name=\"peer.proposal.receive\"}[$__rate_interval])), \"series\", \"Proposals Received / Sec\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Proposals / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/(?:__name__|job|metric|service_name|service_version|deployment_environment|instance|xrpl_network_type|le)=\"[^\"]*\",?\\s*/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\{(?:series=\"([^\"]*)\",?\\s*)?(?:service_instance_id=\"([^\"]*)\",?\\s*)?(?:xrpl_branch=\"([^\"]*)\",?\\s*)?(?:xrpl_node_role=\"([^\"]*)\",?\\s*)?(?:xrpl_work_item=\"([^\"]*)\",?\\s*)?\\}/g",
|
|
"renamePattern": "$1 [$2, $4]-[$3, $5]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/,\\s*\\]/g",
|
|
"renamePattern": "]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[,\\s*/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]-\\[/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/-\\[\\]/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]\\s*$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s*\\[\\]\\s*$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\s{2,}/g",
|
|
"renamePattern": " "
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s+|\\s+$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Peer Validation Receive Rate",
|
|
"description": "###### What this is:\n*How many ledger validations this node receives from peers per second.*\n\n###### How it's computed:\n*Per-second rate of received validations over 5 minutes, per node.*\n\n###### Reading it:\n*Steady and proportional to the number of validators the node hears from.*\n\n###### Healthy range:\n*Workload-dependent; roughly one burst per validator per closed ledger.*\n\n###### Watch for:\n*A fall toward zero (loss of validator connectivity) or an abnormal surge from untrusted sources.*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::onMessage(TMValidation)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (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=~\"$xrpl_node_role\", span_name=\"peer.validation.receive\"}[$__rate_interval])), \"series\", \"Validations Received / Sec\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Validations / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/(?:__name__|job|metric|service_name|service_version|deployment_environment|instance|xrpl_network_type|le)=\"[^\"]*\",?\\s*/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\{(?:series=\"([^\"]*)\",?\\s*)?(?:service_instance_id=\"([^\"]*)\",?\\s*)?(?:xrpl_branch=\"([^\"]*)\",?\\s*)?(?:xrpl_node_role=\"([^\"]*)\",?\\s*)?(?:xrpl_work_item=\"([^\"]*)\",?\\s*)?\\}/g",
|
|
"renamePattern": "$1 [$2, $4]-[$3, $5]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/,\\s*\\]/g",
|
|
"renamePattern": "]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[,\\s*/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]-\\[/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/-\\[\\]/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]\\s*$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s*\\[\\]\\s*$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\s{2,}/g",
|
|
"renamePattern": " "
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s+|\\s+$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Proposals Trusted vs Untrusted",
|
|
"description": "###### What this is:\n*The share of received proposals that come from trusted (UNL) validators versus everyone else.*\n\n###### How it's computed:\n*Received-proposal rate split by trust status over 5 minutes, shown as proportions.*\n\n###### Reading it:\n*A healthy node with a good UNL shows a solid trusted slice.*\n\n###### Healthy range:\n*Workload-dependent; a meaningful trusted fraction is expected.*\n\n###### Watch for:\n*A collapsing trusted share or a large untrusted volume, consistent with proposal flooding from non-UNL peers.*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::onMessage(TMProposeSet)`",
|
|
"type": "piechart",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(sum by (proposal_trusted, service_instance_id, xrpl_branch, xrpl_node_role) (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=~\"$xrpl_node_role\", proposal_trusted=~\"$proposal_trusted\", span_name=\"peer.proposal.receive\"}[$__rate_interval])), \"series\", \"Trusted = $1\", \"proposal_trusted\", \"(.*)\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/(?:__name__|job|metric|service_name|service_version|deployment_environment|instance|xrpl_network_type|le|proposal_trusted)=\"[^\"]*\",?\\s*/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\{(?:series=\"([^\"]*)\",?\\s*)?(?:service_instance_id=\"([^\"]*)\",?\\s*)?(?:xrpl_branch=\"([^\"]*)\",?\\s*)?(?:xrpl_node_role=\"([^\"]*)\",?\\s*)?(?:xrpl_work_item=\"([^\"]*)\",?\\s*)?\\}/g",
|
|
"renamePattern": "$1 [$2, $4]-[$3, $5]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/,\\s*\\]/g",
|
|
"renamePattern": "]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[,\\s*/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]-\\[/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/-\\[\\]/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]\\s*$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s*\\[\\]\\s*$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\s{2,}/g",
|
|
"renamePattern": " "
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s+|\\s+$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Validations Trusted vs Untrusted",
|
|
"description": "###### What this is:\n*The share of received validations from trusted (UNL) validators versus untrusted sources.*\n\n###### How it's computed:\n*Received-validation rate split by trust status over 5 minutes, shown as proportions.*\n\n###### Reading it:\n*The trusted slice should dominate for a well-configured node.*\n\n###### Healthy range:\n*Workload-dependent; trusted validations expected to be the majority.*\n\n###### Watch for:\n*A shrinking trusted share or a spike of untrusted validations, which can indicate misconfiguration or abuse.*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::onMessage(TMValidation)`",
|
|
"type": "piechart",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(sum by (validation_trusted, service_instance_id, xrpl_branch, xrpl_node_role) (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=~\"$xrpl_node_role\", validation_trusted=~\"$validation_trusted\", span_name=\"peer.validation.receive\"}[$__rate_interval])), \"series\", \"Trusted = $1\", \"validation_trusted\", \"(.*)\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/(?:__name__|job|metric|service_name|service_version|deployment_environment|instance|xrpl_network_type|le|validation_trusted)=\"[^\"]*\",?\\s*/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\{(?:series=\"([^\"]*)\",?\\s*)?(?:service_instance_id=\"([^\"]*)\",?\\s*)?(?:xrpl_branch=\"([^\"]*)\",?\\s*)?(?:xrpl_node_role=\"([^\"]*)\",?\\s*)?(?:xrpl_work_item=\"([^\"]*)\",?\\s*)?\\}/g",
|
|
"renamePattern": "$1 [$2, $4]-[$3, $5]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/,\\s*\\]/g",
|
|
"renamePattern": "]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[,\\s*/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]-\\[/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/-\\[\\]/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]\\s*$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s*\\[\\]\\s*$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\s{2,}/g",
|
|
"renamePattern": " "
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s+|\\s+$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Reduce-Relay Peer Selection",
|
|
"description": "###### What this is:\n*How transaction relay picks peers: chosen relay sources, suppressed peers, and peers with the feature off.*\n\n###### How it's computed:\n*Current peer counts in each category (selected, suppressed, not-enabled), per node.*\n\n###### Reading it:\n*A high suppressed-to-selected ratio means relay is saving bandwidth as intended.*\n\n###### Healthy range:\n*Workload-dependent; suppressed should exceed selected in a well-connected mesh.*\n\n###### Watch for:\n*A large not-enabled count (older peers forcing full relay) or selected climbing while suppressed falls.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerReduceRelayGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(reduce_relay_metrics{metric=\"selected_peers\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Selected\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(reduce_relay_metrics{metric=\"suppressed_peers\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Suppressed\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(reduce_relay_metrics{metric=\"not_enabled_peers\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Not Enabled\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Peer Count",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/(?:__name__|job|metric|service_name|service_version|deployment_environment|instance|xrpl_network_type|le)=\"[^\"]*\",?\\s*/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\{(?:series=\"([^\"]*)\",?\\s*)?(?:service_instance_id=\"([^\"]*)\",?\\s*)?(?:xrpl_branch=\"([^\"]*)\",?\\s*)?(?:xrpl_node_role=\"([^\"]*)\",?\\s*)?(?:xrpl_work_item=\"([^\"]*)\",?\\s*)?\\}/g",
|
|
"renamePattern": "$1 [$2, $4]-[$3, $5]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/,\\s*\\]/g",
|
|
"renamePattern": "]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[,\\s*/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]-\\[/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/-\\[\\]/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]\\s*$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s*\\[\\]\\s*$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\s{2,}/g",
|
|
"renamePattern": " "
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s+|\\s+$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Reduce-Relay Missing-Tx Frequency",
|
|
"description": "###### What this is:\n*How often a peer has to fetch a transaction it missed because relay suppressed it.*\n\n###### How it's computed:\n*The reported frequency of on-demand missing-transaction fetches, per node.*\n\n###### Reading it:\n*Lower is better; near-flat means suppression is well tuned.*\n\n###### Healthy range:\n*Workload-dependent; a low, stable value is expected.*\n\n###### Watch for:\n*A rising trend, meaning suppression is too aggressive and the on-demand fetch path is growing.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerReduceRelayGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(reduce_relay_metrics{metric=\"missing_tx_freq\",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\"}, \"series\", \"Missing Tx Freq\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Frequency",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/(?:__name__|job|metric|service_name|service_version|deployment_environment|instance|xrpl_network_type|le)=\"[^\"]*\",?\\s*/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\{(?:series=\"([^\"]*)\",?\\s*)?(?:service_instance_id=\"([^\"]*)\",?\\s*)?(?:xrpl_branch=\"([^\"]*)\",?\\s*)?(?:xrpl_node_role=\"([^\"]*)\",?\\s*)?(?:xrpl_work_item=\"([^\"]*)\",?\\s*)?\\}/g",
|
|
"renamePattern": "$1 [$2, $4]-[$3, $5]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/,\\s*\\]/g",
|
|
"renamePattern": "]"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[,\\s*/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]-\\[/g",
|
|
"renamePattern": "["
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/-\\[\\]/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\[\\]\\s*$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s*\\[\\]\\s*$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/\\s{2,}/g",
|
|
"renamePattern": " "
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^\\s+|\\s+$/g",
|
|
"renamePattern": ""
|
|
}
|
|
},
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["network", "peer"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "DS_PROMETHEUS",
|
|
"type": "datasource",
|
|
"label": "Prometheus",
|
|
"query": "prometheus",
|
|
"regex": "",
|
|
"current": {},
|
|
"hide": 0,
|
|
"refresh": 1,
|
|
"includeAll": false,
|
|
"multi": false,
|
|
"options": []
|
|
},
|
|
{
|
|
"name": "service_name",
|
|
"label": "Service Name",
|
|
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
|
"type": "query",
|
|
"query": "label_values(service_name)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${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 \u2014 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": "proposal_trusted",
|
|
"label": "Proposal Trusted",
|
|
"description": "Filter by proposal trust status (true = from trusted validator)",
|
|
"type": "query",
|
|
"query": "label_values(span_calls_total{span_name=\"peer.proposal.receive\"}, proposal_trusted)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__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(span_calls_total{span_name=\"peer.validation.receive\"}, validation_trusted)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "Peer Network",
|
|
"uid": "peer-network",
|
|
"refresh": "10s"
|
|
}
|