mirror of
https://github.com/XRPLF/rippled.git
synced 2026-07-27 17:10:46 +00:00
cc4104b565
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$quantile),
since {{quantile}} is a dashboard variable, not a series label.
Timeseries panels now connect only null gaps shorter than 30m
(spanNulls=1800000): brief scrape gaps bridge, genuine outages stay broken.
Non-node panels (heatmaps, rows, tables, state timelines, category/bucket
series) are left unchanged. Applied to all 14 dashboards.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
6207 lines
223 KiB
JSON
6207 lines
223 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"description": "What this shows: Operational health of an XRPL node: sync state, ledger progress, caches, storage, job queue, and network economy.\nUse it to: Get an at-a-glance read on whether the node is healthy, synced, and keeping up with the network.",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Validated Ledger Age",
|
|
"description": "###### What this is:\n*How old the most recently validated ledger is, in seconds.*\n\n###### How it's computed:\n*Current value of the validated-ledger-age gauge, refreshed each collection interval.*\n\n###### Reading it:\n*Lower is better; it should stay near the network close interval.*\n\n###### Healthy range:\n*Under about 7 seconds on a healthy node.*\n\n###### Watch for:\n*Values above 20 seconds mean the node is falling behind the network.*\n\n###### Source:\n[LedgerMaster.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/LedgerMaster.h)\n\n###### Function:\n`LedgerMaster::Stats::collectMetrics`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(ledgermaster_validated_ledger_age{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\", \"Validated Age\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 10
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 20
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Published Ledger Age",
|
|
"description": "###### What this is:\n*How old the most recently published ledger is, in seconds.*\n\n###### How it's computed:\n*Current value of the published-ledger-age gauge, refreshed each collection interval.*\n\n###### Reading it:\n*Lower is better; should track close to the validated ledger age.*\n\n###### Healthy range:\n*Under about 7 seconds on a healthy node.*\n\n###### Watch for:\n*A growing gap above the validated age indicates the publish pipeline is backing up.*\n\n###### Source:\n[LedgerMaster.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/LedgerMaster.h)\n\n###### Function:\n`LedgerMaster::Stats::collectMetrics`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(ledgermaster_published_ledger_age{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\", \"Published Age\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 10
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 20
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Operating Mode (Time Share)",
|
|
"description": "###### What this is:\n*Fraction of recent wall-clock time the node spent in each operating mode (Disconnected, Connected, Syncing, Tracking, Full).*\n\n###### How it's computed:\n*Per-second rate of each per-mode duration counter divided by the sum of all five mode rates, giving each mode's time share.*\n\n###### Reading it:\n*The Full share should sit at or near 1.0 and dominate; other shares should be near 0.*\n\n###### Healthy range:\n*Full share close to 1.0.*\n\n###### Watch for:\n*Share accumulating in Syncing, Connected, or Disconnected means the node is not staying fully synced.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(state_accounting_full_duration{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]) / (rate(state_accounting_disconnected_duration{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]) + rate(state_accounting_connected_duration{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]) + rate(state_accounting_syncing_duration{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]) + rate(state_accounting_tracking_duration{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]) + rate(state_accounting_full_duration{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])), \"series\", \"Full\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(state_accounting_tracking_duration{service_instance_id=~\"$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\"}[$__rate_interval]) / (rate(state_accounting_disconnected_duration{service_instance_id=~\"$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\"}[$__rate_interval]) + rate(state_accounting_connected_duration{service_instance_id=~\"$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\"}[$__rate_interval]) + rate(state_accounting_syncing_duration{service_instance_id=~\"$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\"}[$__rate_interval]) + rate(state_accounting_tracking_duration{service_instance_id=~\"$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\"}[$__rate_interval]) + rate(state_accounting_full_duration{service_instance_id=~\"$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\"}[$__rate_interval])), \"series\", \"Tracking\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(state_accounting_syncing_duration{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]) / (rate(state_accounting_disconnected_duration{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]) + rate(state_accounting_connected_duration{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]) + rate(state_accounting_syncing_duration{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]) + rate(state_accounting_tracking_duration{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]) + rate(state_accounting_full_duration{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])), \"series\", \"Syncing\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(state_accounting_connected_duration{service_instance_id=~\"$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\"}[$__rate_interval]) / (rate(state_accounting_disconnected_duration{service_instance_id=~\"$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\"}[$__rate_interval]) + rate(state_accounting_connected_duration{service_instance_id=~\"$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\"}[$__rate_interval]) + rate(state_accounting_syncing_duration{service_instance_id=~\"$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\"}[$__rate_interval]) + rate(state_accounting_tracking_duration{service_instance_id=~\"$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\"}[$__rate_interval]) + rate(state_accounting_full_duration{service_instance_id=~\"$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\"}[$__rate_interval])), \"series\", \"Connected\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(state_accounting_disconnected_duration{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]) / (rate(state_accounting_disconnected_duration{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]) + rate(state_accounting_connected_duration{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]) + rate(state_accounting_syncing_duration{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]) + rate(state_accounting_tracking_duration{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]) + rate(state_accounting_full_duration{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])), \"series\", \"Disconnected\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"min": 0,
|
|
"max": 1,
|
|
"custom": {
|
|
"axisLabel": "Time Share",
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Operating Mode Transitions",
|
|
"description": "###### What this is:\n*Cumulative count of transitions into each operating mode.*\n\n###### How it's computed:\n*Current value of each per-mode transition counter, plotted as lines.*\n\n###### Reading it:\n*Flat lines are healthy; steps up mean the node changed mode.*\n\n###### Healthy range:\n*Few transitions once the node is stable in Full mode.*\n\n###### Watch for:\n*Frequent transitions out of Full, or into Disconnected or Syncing, indicate instability.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(state_accounting_full_transitions{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=~\"$xrpl_node_role\"}, \"series\", \"Full\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(state_accounting_tracking_transitions{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=~\"$xrpl_node_role\"}, \"series\", \"Tracking\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(state_accounting_syncing_transitions{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=~\"$xrpl_node_role\"}, \"series\", \"Syncing\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(state_accounting_connected_transitions{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=~\"$xrpl_node_role\"}, \"series\", \"Connected\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(state_accounting_disconnected_transitions{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\", \"Disconnected\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Transitions",
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "I/O Latency",
|
|
"description": "###### What this is:\n*Latency of the I/O service loop, at the 95th percentile in milliseconds.*\n\n###### How it's computed:\n*I/O loop latency samples aggregated to their 95th percentile per node over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; it reflects how promptly queued I/O work runs.*\n\n###### Healthy range:\n*A few milliseconds; brief spikes are tolerable.*\n\n###### Watch for:\n*Sustained values above a few hundred ms indicate thread-pool saturation or blocking operations.*\n\n###### Source:\n[Application.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/main/Application.cpp)\n\n###### Function:\n`ApplicationImp`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(ios_latency_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\"}[5m]))), \"series\", \"P95 I/O Latency\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Latency (ms)",
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Job Queue Depth",
|
|
"description": "###### What this is:\n*Number of jobs currently waiting in the internal work queue.*\n\n###### How it's computed:\n*Current value of the job-count gauge, plotted over time.*\n\n###### Reading it:\n*Lower is better; a near-flat low line means the node keeps up with its workload.*\n\n###### Healthy range:\n*Low single digits at idle, brief bumps under load.*\n\n###### Watch for:\n*A sustained high depth means the node cannot process work fast enough, common during replay, heavy RPC, or a request flood.*\n\n###### Source:\n[JobQueue.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/core/detail/JobQueue.cpp)\n\n###### Function:\n`JobQueue`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(jobq_job_count{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Job Queue Depth\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Jobs",
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Ledger Fetch Rate",
|
|
"description": "###### What this is:\n*How often the node requests a ledger from its peers.*\n\n###### How it's computed:\n*Per-second rate of ledger-fetch requests over a 5-minute window.*\n\n###### Reading it:\n*Near zero in steady state; elevated while catching up.*\n\n###### Healthy range:\n*Close to zero once fully synced.*\n\n###### Watch for:\n*A sustained high rate means the node is repeatedly missing ledgers and back-filling from peers.*\n\n###### Source:\n[InboundLedgers.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/InboundLedgers.cpp)\n\n###### Function:\n`InboundLedgersImp`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(ledger_fetches_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]), \"series\", \"Fetches / Sec\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Ledger History Mismatches",
|
|
"description": "###### What this is:\n*Rate at which a locally built ledger hash fails to match the network-validated hash.*\n\n###### How it's computed:\n*Per-second rate of history-mismatch events over a 5-minute window.*\n\n###### Reading it:\n*Flat at zero is the only healthy reading.*\n\n###### Healthy range:\n*Zero.*\n\n###### Watch for:\n*Any nonzero value indicates consensus divergence or database corruption and warrants immediate investigation.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementLedgerHistoryMismatch`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 24
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(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]), \"series\", \"Mismatches / Sec\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.01
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "NodeStore I/O",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 32
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "NodeStore Throughput",
|
|
"description": "###### What this is:\n*Cumulative object-store read, cache-hit, and write operation counts.*\n\n###### How it's computed:\n*Current values of the read, cache-hit, and write counters, plotted as lines.*\n\n###### Reading it:\n*Steadily rising lines are normal; the slope reflects store activity.*\n\n###### Healthy range:\n*Reads and writes rising smoothly, with cache-hits tracking a good fraction of reads.*\n\n###### Watch for:\n*A sudden surge in reads or writes signals heavy back-end I/O, from sync, replay, or query load.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerNodeStoreGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"x": 0,
|
|
"y": 33,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(nodestore_state{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=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval]), \"series\", \"Reads Total\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(nodestore_state{service_instance_id=~\"$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\", metric=\"node_reads_hit\"}[$__rate_interval]), \"series\", \"Reads Hit (cache)\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(nodestore_state{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=~\"$xrpl_node_role\", metric=\"node_writes\"}[$__rate_interval]), \"series\", \"Writes Total\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "C"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Operations / Sec",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "NodeStore Cache Hit Ratio",
|
|
"description": "###### What this is:\n*Cumulative object-store read, cache-hit, and write operation counts.*\n\n###### How it's computed:\n*Current values of the read, cache-hit, and write counters, plotted as lines.*\n\n###### Reading it:\n*Steadily rising lines are normal; the slope reflects store activity.*\n\n###### Healthy range:\n*Reads and writes rising smoothly, with cache-hits tracking a good fraction of reads.*\n\n###### Watch for:\n*A sudden surge in reads or writes signals heavy back-end I/O, from sync, replay, or query load.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerNodeStoreGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"x": 12,
|
|
"y": 33,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(nodestore_state{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=~\"$xrpl_node_role\", metric=\"node_reads_hit\"}[$__rate_interval]) / ignoring(metric) rate(nodestore_state{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=~\"$xrpl_node_role\", metric=\"node_reads_total\"}[$__rate_interval]), \"series\", \"Cache Hit Ratio\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"custom": {
|
|
"axisLabel": "Operations / Sec",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "NodeStore Write Load & Read Queue",
|
|
"description": "###### What this is:\n*Instantaneous write-load score and read-queue depth of the object store.*\n\n###### How it's computed:\n*Current values of the write-load and read-queue gauges, plotted over time.*\n\n###### Reading it:\n*Lower is better for both; short, flat lines are healthy.*\n\n###### Healthy range:\n*Write load near zero and read queue in low double digits or less.*\n\n###### Watch for:\n*High write load means back-end pressure; a high read queue means the prefetch threads are saturated.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerNodeStoreGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"x": 0,
|
|
"y": 41,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(nodestore_state{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=~\"$xrpl_node_role\", metric=\"write_load\"}, \"series\", \"Write Load\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(nodestore_state{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\", metric=\"read_queue\"}, \"series\", \"Read Queue\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Count",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 100
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1000
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "NodeStore Bytes Read/Written",
|
|
"description": "###### What this is:\n*Cumulative bytes read from and written to the object-store back end.*\n\n###### How it's computed:\n*Current values of the bytes-read and bytes-written counters, plotted as lines.*\n\n###### Reading it:\n*Steadily rising lines are normal; the slope shows throughput.*\n\n###### Healthy range:\n*Smooth growth consistent with ledger and query activity.*\n\n###### Watch for:\n*A sharp acceleration indicates a heavy I/O phase such as sync, replay, or large queries.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerNodeStoreGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"x": 12,
|
|
"y": 41,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(nodestore_state{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=~\"$xrpl_node_role\", metric=\"node_read_bytes\"}[$__rate_interval]), \"series\", \"Bytes Read\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(nodestore_state{service_instance_id=~\"$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\", metric=\"node_written_bytes\"}[$__rate_interval]), \"series\", \"Bytes Written\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Throughput",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "NodeStore Read Threads",
|
|
"description": "###### What this is:\n*Read-thread utilization, bundled read count, and cumulative read time for the object store.*\n\n###### How it's computed:\n*Current values of the running/total read-thread gauges, read-bundle gauge, and cumulative read-duration counter, plotted as lines.*\n\n###### Reading it:\n*Running threads well below total means spare capacity; a rising duration line reflects time spent in read I/O.*\n\n###### Healthy range:\n*Running threads below the total count most of the time.*\n\n###### Watch for:\n*Running threads pinned at the total for long periods means read I/O is saturated.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerNodeStoreGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"x": 0,
|
|
"y": 49,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(nodestore_state{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=~\"$xrpl_node_role\", metric=\"read_threads_running\"}, \"series\", \"Read Threads Running\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "A"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(nodestore_state{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=~\"$xrpl_node_role\", metric=\"read_threads_total\"}, \"series\", \"Read Threads Total\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "B"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(nodestore_state{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\", metric=\"read_request_bundle\"}, \"series\", \"Read Request Bundle\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "C"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Threads / Bundle",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "NodeStore Read Busy Ratio",
|
|
"description": "###### What this is:\n*Read-thread utilization, bundled read count, and cumulative read time for the object store.*\n\n###### How it's computed:\n*Current values of the running/total read-thread gauges, read-bundle gauge, and cumulative read-duration counter, plotted as lines.*\n\n###### Reading it:\n*Running threads well below total means spare capacity; a rising duration line reflects time spent in read I/O.*\n\n###### Healthy range:\n*Running threads below the total count most of the time.*\n\n###### Watch for:\n*Running threads pinned at the total for long periods means read I/O is saturated.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerNodeStoreGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"x": 12,
|
|
"y": 49,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(nodestore_state{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=~\"$xrpl_node_role\", metric=\"node_reads_duration_us\"}[$__rate_interval]) / 1e6, \"series\", \"Read Busy Ratio\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"custom": {
|
|
"axisLabel": "Threads / Bundle",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Cache Hit Rates",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 57
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Cache Hit Rates",
|
|
"description": "###### What this is:\n*Hit rates for the SLE, Ledger, and AcceptedLedger caches, from 0 to 1.*\n\n###### How it's computed:\n*Current values of the per-cache hit-rate gauges, plotted as lines.*\n\n###### Reading it:\n*Higher is better; each line is the fraction of lookups served from cache.*\n\n###### Healthy range:\n*Above roughly 0.8 in steady state.*\n\n###### Watch for:\n*Low or falling hit rates indicate cache thrashing and extra back-end reads.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerCacheHitRateGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 58
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(cache_metrics{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=~\"$xrpl_node_role\", metric=\"SLE_hit_rate\"}, \"series\", \"SLE Hit Rate\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(cache_metrics{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=~\"$xrpl_node_role\", metric=\"ledger_hit_rate\"}, \"series\", \"Ledger Hit Rate\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(cache_metrics{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\", metric=\"AL_hit_rate\"}, \"series\", \"AcceptedLedger Hit Rate\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"min": 0,
|
|
"max": 1,
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"axisLabel": "Hit Rate",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Cache Sizes",
|
|
"description": "###### What this is:\n*Entry counts for the TreeNode cache and track set, the FullBelow cache, and the AcceptedLedger cache.*\n\n###### How it's computed:\n*Current values of the per-cache size gauges, plotted as lines.*\n\n###### Reading it:\n*Stable lines are normal; sizes grow with working set and shrink after sweeps.*\n\n###### Healthy range:\n*Stable within configured limits.*\n\n###### Watch for:\n*Unbounded growth suggests memory pressure or a cache not being swept.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerCacheHitRateGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 58
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(cache_metrics{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=~\"$xrpl_node_role\", metric=\"treenode_cache_size\"}, \"series\", \"TreeNode Cache\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(cache_metrics{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=~\"$xrpl_node_role\", metric=\"treenode_track_size\"}, \"series\", \"TreeNode Track\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(cache_metrics{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=~\"$xrpl_node_role\", metric=\"fullbelow_size\"}, \"series\", \"FullBelow\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(cache_metrics{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\", metric=\"AL_size\"}, \"series\", \"AcceptedLedger Size\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Entries",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Object Instance Counts",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 66
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Object Instance Counts",
|
|
"description": "###### What this is:\n*Live instance counts for the busiest internal object types.*\n\n###### How it's computed:\n*Current per-type instance counts, showing the top 15 types over time.*\n\n###### Reading it:\n*Stable lines are healthy; each line is one object type's live count.*\n\n###### Healthy range:\n*Steady counts that rise and fall with load.*\n\n###### Watch for:\n*A single type climbing without bound suggests memory pressure or a leak.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerObjectCountGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 67
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["last", "max"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(topk(15, object_count{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", type=~\"$type\"}), \"series\", \"$1\", \"type\", \"(.*)\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Instances",
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 5,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"transformations": [
|
|
{
|
|
"id": "renameByRegex",
|
|
"options": {
|
|
"regex": "/(?:__name__|job|metric|service_name|service_version|deployment_environment|instance|xrpl_network_type|le|type)=\"[^\"]*\",?\\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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Server Info",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 75
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Server State",
|
|
"description": "###### What this is:\n*The node's current operating mode, shown as a labeled state.*\n\n###### How it's computed:\n*Current value of the server-state gauge mapped to a mode name.*\n\n###### Reading it:\n*FULL (green) is the goal; lower states mean the node is not fully participating.*\n\n###### Healthy range:\n*FULL.*\n\n###### Watch for:\n*Sitting in SYNCING, CONNECTED, or DISCONNECTED means the node is not caught up to the network.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 76
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(server_info{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\", metric=\"server_state\"}, \"series\", \"State\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": {
|
|
"text": "DISCONNECTED",
|
|
"color": "red"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"1": {
|
|
"text": "CONNECTED",
|
|
"color": "orange"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"2": {
|
|
"text": "SYNCING",
|
|
"color": "yellow"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"3": {
|
|
"text": "TRACKING",
|
|
"color": "blue"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"4": {
|
|
"text": "FULL",
|
|
"color": "green"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Uptime",
|
|
"description": "###### What this is:\n*How long the server process has been running, in seconds.*\n\n###### How it's computed:\n*Current value of the uptime gauge.*\n\n###### Reading it:\n*Higher is generally better; a reset to a small value means the process restarted.*\n\n###### Healthy range:\n*Continuously increasing.*\n\n###### Watch for:\n*An unexpected drop to near zero indicates a restart or crash.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 76
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(server_info{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\", metric=\"uptime\"}, \"series\", \"Uptime\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Peer Count",
|
|
"description": "###### What this is:\n*Total connected peers, inbound plus outbound.*\n\n###### How it's computed:\n*Current value of the peer-count gauge.*\n\n###### Reading it:\n*A stable count in the healthy range is good; too few limits connectivity.*\n\n###### Healthy range:\n*Workload- and config-dependent, typically 10 or more.*\n\n###### Watch for:\n*A sudden drop points to network or connectivity problems; an unusually high inbound count can indicate connection-flood pressure.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 76
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(server_info{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\", metric=\"peers\"}, \"series\", \"Peers\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Validated Ledger Seq",
|
|
"description": "###### What this is:\n*Sequence number of the most recently validated ledger.*\n\n###### How it's computed:\n*Current value of the validated-ledger-sequence gauge.*\n\n###### Reading it:\n*Should climb steadily; reads 0 before the first validation.*\n\n###### Healthy range:\n*Continuously increasing at the network close cadence.*\n\n###### Watch for:\n*A flat sequence means the node has stopped validating new ledgers.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 76
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(server_info{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\", metric=\"validated_ledger_seq\"}, \"series\", \"Seq\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Last Close \u2014 Proposers",
|
|
"description": "###### What this is:\n*Proposer count and convergence time from the last closed consensus round.*\n\n###### How it's computed:\n*Current values of the last-close proposer-count and convergence-time gauges, plotted as lines.*\n\n###### Reading it:\n*A healthy proposer count with a low convergence time is good.*\n\n###### Healthy range:\n*Convergence time of a few seconds with the expected number of proposers.*\n\n###### Watch for:\n*A falling proposer count or rising convergence time signals degrading consensus conditions.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"x": 0,
|
|
"y": 84,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(server_info{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\", metric=\"last_close_proposers\"}, \"series\", \"Proposers\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Proposers",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Last Close \u2014 Converge Time",
|
|
"description": "###### What this is:\n*Proposer count and convergence time from the last closed consensus round.*\n\n###### How it's computed:\n*Current values of the last-close proposer-count and convergence-time gauges, plotted as lines.*\n\n###### Reading it:\n*A healthy proposer count with a low convergence time is good.*\n\n###### Healthy range:\n*Convergence time of a few seconds with the expected number of proposers.*\n\n###### Watch for:\n*A falling proposer count or rising convergence time signals degrading consensus conditions.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"x": 12,
|
|
"y": 84,
|
|
"w": 12,
|
|
"h": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(server_info{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\", metric=\"last_close_converge_time_ms\"}, \"series\", \"Converge Time ms\", \"\", \"\")",
|
|
"legendFormat": "__auto",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Proposers",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Build Version",
|
|
"description": "###### What this is:\n*The running server's build version string.*\n\n###### How it's computed:\n*Read from the version label of the build-info metric (its value is always 1).*\n\n###### Reading it:\n*Confirms which version each node is running.*\n\n###### Healthy range:\n*The expected release version across all nodes.*\n\n###### Watch for:\n*A node on an unexpected or mismatched version in a fleet.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerBuildInfoGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 92
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"textMode": "name"
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "build_info{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=~\"$xrpl_node_role\"}",
|
|
"legendFormat": "v{{version}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Current Ledger Index",
|
|
"description": "###### What this is:\n*Sequence number of the current open ledger.*\n\n###### How it's computed:\n*Current value of the open-ledger index gauge.*\n\n###### Reading it:\n*Should climb steadily; the gap above the validated sequence is the ledgers in flight.*\n\n###### Healthy range:\n*One or two ahead of the validated sequence.*\n\n###### Watch for:\n*A large or growing gap above the validated sequence means validation is lagging behind ledger creation.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 100
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(server_info{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\", metric=\"ledger_current_index\"}, \"series\", \"Current Ledger\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "NuDB Storage Size",
|
|
"description": "###### What this is:\n*On-disk size of the NuDB object-store back end, in bytes.*\n\n###### How it's computed:\n*Current value of the NuDB storage-size gauge, plotted over time.*\n\n###### Reading it:\n*A smoothly growing line is normal; the slope is the data growth rate.*\n\n###### Healthy range:\n*Gradual growth consistent with retained ledger history.*\n\n###### Watch for:\n*A sudden jump in growth rate can indicate runaway storage or an unexpected back-fill.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerStorageDetailGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 100
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(storage_detail{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\", metric=\"nudb_bytes\"}, \"series\", \"NuDB Size\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "decbytes",
|
|
"custom": {
|
|
"axisLabel": "Size",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Complete Ledgers & DB",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 108
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Complete Ledger Ranges",
|
|
"description": "###### What this is:\n*The contiguous ranges of ledgers the node holds locally.*\n\n###### How it's computed:\n*Current start and end bounds of each complete range, listed as table rows.*\n\n###### Reading it:\n*Fewer ranges is better; one continuous range means an unbroken history.*\n\n###### Healthy range:\n*A single range covering the configured retention window.*\n\n###### Watch for:\n*Many fragmented ranges indicate gaps in stored history from missed or failed fetches.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerCompleteLedgersGauge`",
|
|
"type": "table",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 109
|
|
},
|
|
"options": {
|
|
"showHeader": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "complete_ledgers{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=~\"$xrpl_node_role\"}",
|
|
"legendFormat": "{{bound}} [range {{index}}] [{{service_instance_id}}]",
|
|
"format": "table",
|
|
"instant": true
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"custom": {}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "Database Sizes",
|
|
"description": "###### What this is:\n*Sizes of the relational databases in KB (total, ledger, transaction).*\n\n###### How it's computed:\n*Current values of the per-database size gauges, plotted as lines.*\n\n###### Reading it:\n*Smoothly growing lines are normal; the split shows where storage is used.*\n\n###### Healthy range:\n*Gradual growth consistent with retained history.*\n\n###### Watch for:\n*An abrupt change in growth rate can indicate storage pressure or a pruning issue.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerDbMetricsGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 109
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(db_metrics{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=~\"$xrpl_node_role\", metric=\"db_kb_total\"}, \"series\", \"Total KB\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(db_metrics{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=~\"$xrpl_node_role\", metric=\"db_kb_ledger\"}, \"series\", \"Ledger KB\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(db_metrics{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\", metric=\"db_kb_transaction\"}, \"series\", \"Transaction KB\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "deckbytes",
|
|
"custom": {
|
|
"axisLabel": "Size (KB)",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Historical Fetch Rate",
|
|
"description": "###### What this is:\n*How many historical ledgers the node is back-filling per minute.*\n\n###### How it's computed:\n*Current value of the historical-fetch-per-minute gauge.*\n\n###### Reading it:\n*Near zero once history is complete; elevated while back-filling.*\n\n###### Healthy range:\n*Close to zero in steady state.*\n\n###### Watch for:\n*A sustained high rate means the node is still filling gaps in its stored history.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerDbMetricsGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 117
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(db_metrics{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\", metric=\"historical_perminute\"}, \"series\", \"Fetches/min\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "cpm",
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Peer Disconnects (Resources)",
|
|
"description": "###### What this is:\n*Cumulative count of peers disconnected for exceeding resource limits.*\n\n###### How it's computed:\n*Current value of the resource-disconnect gauge, plotted over time.*\n\n###### Reading it:\n*A flat line is healthy; steps up mean peers were dropped for overuse.*\n\n###### Healthy range:\n*Flat or very slowly rising.*\n\n###### Watch for:\n*A rising line indicates peers are being throttled off, consistent with abusive or misbehaving peers.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 117
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(server_info{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\", metric=\"peer_disconnects_resources\"}, \"series\", \"Resource Disconnects\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Ledger Economy",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 125
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Base Fee (drops)",
|
|
"description": "###### What this is:\n*The node's local load-based fee factor that scales its minimum transaction cost; baseline 256 at idle.*\n\n###### How it's computed:\n*Current value of the local load-fee economy gauge.*\n\n###### Reading it:\n*Steady at the baseline (256) is normal; higher values mean the node is raising its fee in response to load.*\n\n###### Healthy range:\n*Around 256 (the normal baseline) when idle.*\n\n###### Watch for:\n*A climbing factor, which indicates the node is under transaction load pressure.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLedgerEconomyGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 126
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(ledger_economy{metric=\"base_fee_xrp\",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\", \"Base Fee\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "si:drops",
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Reserve Base (drops)",
|
|
"description": "###### What this is:\n*The minimum XRP balance required to keep an account on the ledger, in drops.*\n\n###### How it's computed:\n*Current value of the reserve-base economy gauge.*\n\n###### Reading it:\n*A stable value is expected; it changes only via network amendment or vote.*\n\n###### Healthy range:\n*The configured network reserve base.*\n\n###### Watch for:\n*An unexpected change outside a known amendment or fee vote.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLedgerEconomyGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 126
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(ledger_economy{metric=\"reserve_base_xrp\",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\", \"Reserve Base\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "si:drops",
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Reserve Inc (drops)",
|
|
"description": "###### What this is:\n*The additional XRP reserve required per owned ledger object, in drops.*\n\n###### How it's computed:\n*Current value of the reserve-increment economy gauge.*\n\n###### Reading it:\n*A stable value is expected; it changes only via network amendment or vote.*\n\n###### Healthy range:\n*The configured network owner reserve increment.*\n\n###### Watch for:\n*An unexpected change outside a known amendment or fee vote.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLedgerEconomyGauge`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 126
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(ledger_economy{metric=\"reserve_inc_xrp\",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\", \"Reserve Inc\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "si:drops",
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Ledger Age",
|
|
"description": "###### What this is:\n*Seconds since the last validated ledger closed, plotted over time.*\n\n###### How it's computed:\n*Current value of the ledger-age economy gauge, sampled each interval.*\n\n###### Reading it:\n*Lower is better; it should stay near the ledger close interval. Mirrors the Validated Ledger Age panel.*\n\n###### Healthy range:\n*Under about 10 seconds.*\n\n###### Watch for:\n*Growth beyond the expected close interval, meaning the node is not keeping up with validated ledgers.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLedgerEconomyGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 126
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(ledger_economy{metric=\"ledger_age_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\"}, \"series\", \"Ledger Age\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 10
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 20
|
|
}
|
|
]
|
|
},
|
|
"custom": {
|
|
"axisLabel": "Ledger Age (s)",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3,
|
|
"thresholdsStyle": {
|
|
"mode": "line"
|
|
}
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Transaction Rate",
|
|
"description": "###### What this is:\n*The network transaction throughput reported by the ledger economy metrics.*\n\n###### How it's computed:\n*Current value of the transaction-rate economy gauge, plotted over time.*\n\n###### Reading it:\n*Reflects how many transactions are being processed; higher means busier.*\n\n###### Healthy range:\n*Workload-dependent.*\n\n###### Watch for:\n*A sudden sustained surge can indicate a transaction flood; a drop to zero can indicate the node stopped processing.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLedgerEconomyGauge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 134
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(ledger_economy{metric=\"transaction_rate\",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\", \"Tx Rate\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "cps",
|
|
"custom": {
|
|
"axisLabel": "Transactions",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Extended Metrics",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 32
|
|
},
|
|
"collapsed": false,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Key Jobs Execution Time (q$quantile)",
|
|
"description": "###### What this is:\n*Execution time for the most critical job types at the selected quantile.*\n\n###### How it's computed:\n*Per-job-type execution durations aggregated to the chosen quantile per node over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; each line is one job type's run time.*\n\n###### Healthy range:\n*A few to tens of milliseconds for most jobs; workload-dependent.*\n\n###### Watch for:\n*Spikes on key jobs (accept, transaction, write) indicate processing bottlenecks.*\n\n###### Source:\n[JobTypeData.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/core/JobTypeData.h)\n\n###### Function:\n`JobTypeData`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 33
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"acceptLedger\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Accept Ledger\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"advanceLedger\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Advance Ledger\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"transaction\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Transaction\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"writeObjects\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Write Objects\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"heartbeat\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Heartbeat\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"sweep\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Sweep\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"trustedValidation\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Validation\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"trustedProposal\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Trusted Proposal\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"publishNewLedger\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Publish New Ledger\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"clientRPC\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Client RPC\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{job_type=\"ledgerData\", 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\"}[5m]))), \"series\", \"Ledger Data\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Key Jobs Dequeue Wait Time (q$quantile)",
|
|
"description": "###### What this is:\n*Time critical jobs wait in the queue before running, at the selected quantile.*\n\n###### How it's computed:\n*Per-job-type queue-wait durations aggregated to the chosen quantile per node over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; each line is one job type's wait time.*\n\n###### Healthy range:\n*Near zero to a few milliseconds when the queue is keeping up.*\n\n###### Watch for:\n*High waits mean the queue is backlogged and jobs are scheduled late.*\n\n###### Source:\n[JobTypeData.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/core/JobTypeData.h)\n\n###### Function:\n`JobTypeData`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 33
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"acceptLedger\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Accept Ledger\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"advanceLedger\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Advance Ledger\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"transaction\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Transaction\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"writeObjects\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Write Objects\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"heartbeat\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Heartbeat\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"sweep\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Sweep\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"trustedValidation\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Trusted Validation\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"trustedProposal\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Trusted Proposal\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"publishNewLedger\", 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=~\"$xrpl_node_role\"}[5m]))), \"series\", \"Publish New Ledger\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"clientRPC\", service_instance_id=~\"$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\"}[5m]))), \"series\", \"Client RPC\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"ledgerData\", 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\"}[5m]))), \"series\", \"Ledger Data\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Wait Time (ms)",
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "FullBelowCache Size",
|
|
"description": "###### What this is:\n*Number of entries in the FullBelowCache, which tracks subtrees known to be fully present locally.*\n\n###### How it's computed:\n*Current value of the cache size gauge, plotted over time.*\n\n###### Reading it:\n*A stable size is normal; it grows during acquisition and is trimmed by sweeps.*\n\n###### Healthy range:\n*Stable within its configured bound.*\n\n###### Watch for:\n*Unbounded growth suggests the cache is not being swept.*\n\n###### Source:\n[TaggedCache.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/basics/TaggedCache.h)\n\n###### Function:\n`TaggedCache::Stats`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 41
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(node_family_full_below_cache_size{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\", \"FullBelowCache Size\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Entries",
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "FullBelowCache Hit Rate",
|
|
"description": "###### What this is:\n*Hit-rate percentage for the FullBelowCache.*\n\n###### How it's computed:\n*Current value of the cache hit-rate gauge.*\n\n###### Reading it:\n*Higher is better; it shows how often cached subtree knowledge is reused.*\n\n###### Healthy range:\n*Above roughly 50 percent in steady state.*\n\n###### Watch for:\n*A low hit rate during steady state means redundant subtree work and warrants investigation.*\n\n###### Source:\n[TaggedCache.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/basics/TaggedCache.h)\n\n###### Function:\n`TaggedCache::Stats`",
|
|
"type": "gauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 41
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(node_family_full_below_cache_hit_rate{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\", \"Hit Rate\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"min": 0,
|
|
"max": 100,
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 25
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 50
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Ledger Publish Gap",
|
|
"description": "###### What this is:\n*The lag between published and validated ledger ages, in seconds.*\n\n###### How it's computed:\n*Published ledger age minus validated ledger age, as a single derived value.*\n\n###### Reading it:\n*Near zero is healthy; a positive value is how far publishing trails validation.*\n\n###### Healthy range:\n*Close to zero.*\n\n###### Watch for:\n*A growing gap means the publish pipeline is falling behind and subscribers may see stale data.*\n\n###### Source:\n[LedgerMaster.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/LedgerMaster.h)\n\n###### Function:\n`LedgerMaster::Stats::collectMetrics`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 49
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(ledgermaster_published_ledger_age{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=~\"$xrpl_node_role\"} - ledgermaster_validated_ledger_age{service_instance_id=~\"$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\", \"Publish Gap\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 5
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 10
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "State Duration Rate (Full vs Tracking)",
|
|
"description": "###### What this is:\n*Rate of change of time spent in Full and Tracking modes, normalized to seconds per second.*\n\n###### How it's computed:\n*Per-second rate of the Full and Tracking duration counters, scaled to seconds.*\n\n###### Reading it:\n*The Full line near 1.0 means the node gains a second of Full-mode time each wall-clock second.*\n\n###### Healthy range:\n*Full rate close to 1.0, Tracking near 0.*\n\n###### Watch for:\n*A Full rate below 1.0 means the node is spending time in other modes.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 49
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(state_accounting_full_duration{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]) / 1000000, \"series\", \"Full Mode Rate\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(state_accounting_tracking_duration{service_instance_id=~\"$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]) / 1000000, \"series\", \"Tracking Mode Rate\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Rate (s/s)",
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "All Jobs Execution Time (Detail)",
|
|
"description": "###### What this is:\n*Execution time for every non-special job type at the selected quantile.*\n\n###### How it's computed:\n*Per-job-type execution durations aggregated to the chosen quantile per node over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; this is the full picture behind the Key Jobs view.*\n\n###### Healthy range:\n*A few to tens of milliseconds for most jobs.*\n\n###### Watch for:\n*Broad elevation across many job types indicates systemic processing load.*\n\n###### Source:\n[JobTypeData.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/core/JobTypeData.h)\n\n###### Function:\n`JobTypeData`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 57
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, job_type, xrpl_branch, xrpl_node_role) (rate(job_running_us_bucket{service_instance_id=~\"$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\"}[5m]))), \"series\", \"$1\", \"job_type\", \"(.*)\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"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|job_type)=\"[^\"]*\",?\\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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "All Jobs Dequeue Wait (Detail)",
|
|
"description": "###### What this is:\n*Queue wait time for every non-special job type at the selected quantile.*\n\n###### How it's computed:\n*Per-job-type queue-wait durations aggregated to the chosen quantile per node over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; this is the full picture behind the Key Jobs wait view.*\n\n###### Healthy range:\n*Near zero to a few milliseconds when the queue keeps up.*\n\n###### Watch for:\n*High waits across many job types indicate systemic queue congestion.*\n\n###### Source:\n[JobTypeData.h](https://github.com/XRPLF/rippled/blob/develop/include/xrpl/core/JobTypeData.h)\n\n###### Function:\n`JobTypeData`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 65
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile($quantile, sum by (le, job_type, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{service_instance_id=~\"$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\"}[5m]))), \"series\", \"$1\", \"job_type\", \"(.*)\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Wait Time (ms)",
|
|
"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|job_type)=\"[^\"]*\",?\\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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Ledger Acquire Duration (Inbound Fetch)",
|
|
"description": "###### What this is:\n*Time to fetch a missing ledger from peers, at the 95th percentile.*\n\n###### How it's computed:\n*Per-acquire durations aggregated to their 95th percentile per node over a 5-minute window.*\n\n###### Reading it:\n*Lower is better; populated mainly during sync or back-fill.*\n\n###### Healthy range:\n*Low when synced; higher and more active while catching up.*\n\n###### Watch for:\n*A spike signals the node is falling behind or recovering from a fork.*\n\n###### Source:\n[InboundLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/InboundLedger.cpp)\n\n###### Function:\n`InboundLedger::init`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 126
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (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=\"ledger.acquire\"}[5m]))), \"series\", \"P95 Acquire\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Ledger Acquire Rate by Outcome",
|
|
"description": "###### What this is:\n*Rate of completed ledger fetches split by outcome (complete or failed).*\n\n###### How it's computed:\n*Per-second rate of finished acquisitions grouped by outcome, per node, over a 5-minute window.*\n\n###### Reading it:\n*Complete should dominate; the failed line should stay near zero.*\n\n###### Healthy range:\n*Complete tracking fetch demand, failed near zero.*\n\n###### Watch for:\n*A rising failed rate means the node cannot fetch needed ledgers from its peers.*\n\n###### Source:\n[InboundLedger.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/InboundLedger.cpp)\n\n###### Function:\n`InboundLedger::init`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 126
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(sum by (outcome, 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=~\"$xrpl_node_role\", span_name=\"ledger.acquire\"}[$__rate_interval])), \"series\", \"$1\", \"outcome\", \"(.*)\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Acquisitions / 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|outcome)=\"[^\"]*\",?\\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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Operating Mode (State Timeline)",
|
|
"description": "###### What this is:\n*The node's operating mode over time as a colored timeline (Disconnected, Connected, Syncing, Tracking, Full).*\n\n###### How it's computed:\n*Current value of the server-state gauge mapped to a mode name; equal consecutive samples are merged into a single band.*\n\n###### Reading it:\n*A solid green Full band across the window is the goal; other colors mark periods the node was not fully synced.*\n\n###### Healthy range:\n*Continuously Full (green).*\n\n###### Watch for:\n*Bands of Syncing, Connected, or Disconnected, which pinpoint exactly when the node dropped out of Full.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
|
|
"type": "state-timeline",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 18,
|
|
"x": 0,
|
|
"y": 134
|
|
},
|
|
"options": {
|
|
"mergeValues": true,
|
|
"showValue": "auto",
|
|
"alignValue": "left",
|
|
"rowHeight": 0.9,
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "server_info{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\", metric=\"server_state\"}",
|
|
"legendFormat": "State [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "none",
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": {
|
|
"text": "Disconnected",
|
|
"color": "red"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"1": {
|
|
"text": "Connected",
|
|
"color": "orange"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"2": {
|
|
"text": "Syncing",
|
|
"color": "yellow"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"3": {
|
|
"text": "Tracking",
|
|
"color": "blue"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"4": {
|
|
"text": "Full",
|
|
"color": "green"
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"custom": {
|
|
"fillOpacity": 80,
|
|
"lineWidth": 0
|
|
}
|
|
},
|
|
"overrides": []
|
|
}
|
|
},
|
|
{
|
|
"title": "% Time in Full",
|
|
"description": "###### What this is:\n*The share of recent wall-clock time the node spent in Full mode.*\n\n###### How it's computed:\n*Per-second rate of the Full-mode duration counter divided by the sum of the per-second rates of all five mode duration counters.*\n\n###### Reading it:\n*Higher is better; 1.0 means the node was fully synced for the entire window.*\n\n###### Healthy range:\n*At or above 0.99.*\n\n###### Watch for:\n*Values dropping below 0.9, meaning the node spent meaningful time outside Full mode.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 134
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"orientation": "auto",
|
|
"textMode": "auto",
|
|
"colorMode": "value",
|
|
"tooltip": {
|
|
"mode": "single",
|
|
"sort": "none"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(rate(state_accounting_full_duration{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]) / (rate(state_accounting_disconnected_duration{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]) + rate(state_accounting_connected_duration{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]) + rate(state_accounting_syncing_duration{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]) + rate(state_accounting_tracking_duration{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]) + rate(state_accounting_full_duration{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])), \"series\", \"% Time in Full\", \"\", \"\")",
|
|
"legendFormat": "__auto"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"min": 0,
|
|
"max": 1,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.9
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 0.99
|
|
}
|
|
]
|
|
},
|
|
"custom": {}
|
|
},
|
|
"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": "/^$/g",
|
|
"renamePattern": "all"
|
|
}
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["node", "health"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "DS_PROMETHEUS",
|
|
"type": "datasource",
|
|
"label": "Prometheus",
|
|
"query": "prometheus",
|
|
"regex": "",
|
|
"current": {},
|
|
"hide": 0,
|
|
"refresh": 1,
|
|
"includeAll": false,
|
|
"multi": false,
|
|
"options": []
|
|
},
|
|
{
|
|
"name": "service_name",
|
|
"label": "Service Name",
|
|
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
|
"type": "query",
|
|
"query": "label_values(service_name)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${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)",
|
|
"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": "type",
|
|
"label": "Object Type",
|
|
"description": "Filter by internal object type (CountedObject<T> class name)",
|
|
"type": "query",
|
|
"query": "label_values(object_count, type)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "quantile",
|
|
"label": "Quantile",
|
|
"type": "custom",
|
|
"query": "0.5,0.75,0.95,0.99",
|
|
"current": {
|
|
"text": "0.95",
|
|
"value": "0.95"
|
|
},
|
|
"options": [
|
|
{
|
|
"text": "0.5",
|
|
"value": "0.5",
|
|
"selected": false
|
|
},
|
|
{
|
|
"text": "0.75",
|
|
"value": "0.75",
|
|
"selected": false
|
|
},
|
|
{
|
|
"text": "0.95",
|
|
"value": "0.95",
|
|
"selected": true
|
|
},
|
|
{
|
|
"text": "0.99",
|
|
"value": "0.99",
|
|
"selected": false
|
|
}
|
|
],
|
|
"includeAll": false,
|
|
"multi": false
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "Node Health",
|
|
"uid": "node-health",
|
|
"refresh": "10s"
|
|
}
|