mirror of
https://github.com/XRPLF/rippled.git
synced 2026-08-23 15:20:54 +00:00
371f10934e
Found by reviewing what each metric actually measures, with attention to the derived and bucketed ones. All five could report healthy while the node was not, or the reverse. - The nodestore latency panel took rate() of a mean. The gauge already divides duration by count in code, so rating it produced a figure with no unit, and Prometheus discards a gauge's decreases, so a heavy back-fill read as roughly zero microseconds per operation. The cumulative duration totals are now exported alongside the means, and the panel divides the rate of the total by the rate of the count, which is the latency over the panel's own window rather than a since-boot average that flattens with uptime. - The DNS-resolve and outbound-dial histograms had no explicit buckets, so they inherited a ladder that stops at ten seconds while the dial timer is fifteen. Every timed-out dial fell in the overflow bucket and p95 read exactly ten seconds however bad it got. Both now have a ladder reaching thirty seconds with fifteen on its own boundary, so a timeout is distinguishable from merely slow. - The missing-node counts only cleared when a tree completed, so a timed-out or failed acquire left its last count latched. Since the gauge reports the maximum across everything still in the collection, and eviction waits on a grace period plus the sweep interval, a finished node reported as stuck for minutes. That inverts the one signal that separates stuck from slow. Cleared unconditionally on the terminal path instead. - A disabled quorum published a sentinel so large that, on a timeseries axis shared with the trusted-key count, it flattened the key line to the baseline and hid the outage it was meant to mark. The series is now omitted and a quorum_disabled flag carries the state. - Two panel descriptions claimed a one-second export cycle. The reader is configured for ten. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
1638 lines
94 KiB
JSON
1638 lines
94 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"description": "What this shows: Ledger data exchange and object-fetch traffic between this node and its peers: ledger sync, tree-node retrieval, and transaction-set exchange.\nUse it to: See how much ledger data the node is pulling or serving and spot catch-up activity.",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Ledger Data — Ledger",
|
|
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_get_bytes_in{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\", \"Ledger Data Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_share_bytes_in{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\", \"Ledger Data Share\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 1
|
|
},
|
|
{
|
|
"title": "Ledger Data — Transaction",
|
|
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Set Candidate Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Set Candidate Share\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_transaction_node_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Node Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Node Share\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 2
|
|
},
|
|
{
|
|
"title": "Ledger Data — Account State",
|
|
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_account_state_node_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Account State Node Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Account State Node Share\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 3
|
|
},
|
|
{
|
|
"title": "Ledger Traffic — Ledger",
|
|
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Ledger Get In\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Ledger Share In\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 4
|
|
},
|
|
{
|
|
"title": "Ledger Traffic — Transaction",
|
|
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Set Candidate Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Set Candidate Share\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_transaction_node_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Node Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_transaction_node_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Node Share\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 5
|
|
},
|
|
{
|
|
"title": "Ledger Traffic — Account State",
|
|
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_account_state_node_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Account State Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_account_state_node_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Account State Share\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 6
|
|
},
|
|
{
|
|
"title": "GetObject — Ledger",
|
|
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_ledger_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Ledger Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_ledger_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Ledger Share\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 7
|
|
},
|
|
{
|
|
"title": "GetObject — Transaction",
|
|
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 24
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transaction_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Transaction Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transaction_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Transaction Share\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transaction_node_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Node Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transaction_node_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Node Share\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 8
|
|
},
|
|
{
|
|
"title": "GetObject — Account State",
|
|
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 32
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_account_state_node_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Account State Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_account_state_node_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Account State Share\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 9
|
|
},
|
|
{
|
|
"title": "GetObject Messages — Ledger",
|
|
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 32
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_ledger_get_messages_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Ledger Get\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "cps",
|
|
"custom": {
|
|
"axisLabel": "Messages In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 10
|
|
},
|
|
{
|
|
"title": "GetObject Messages — Transaction",
|
|
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 40
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transaction_get_messages_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Transaction Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transaction_node_get_messages_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"TX Node Get\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "cps",
|
|
"custom": {
|
|
"axisLabel": "Messages In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 11
|
|
},
|
|
{
|
|
"title": "GetObject Messages — Account State",
|
|
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 40
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_account_state_node_get_messages_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Account State Get\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "cps",
|
|
"custom": {
|
|
"axisLabel": "Messages In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 12
|
|
},
|
|
{
|
|
"title": "GetObject Messages — Specials",
|
|
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 48
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_cas_get_messages_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"CAS Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_fetch_pack_get_messages_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Fetch Pack Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transactions_get_messages_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Transactions Get\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "cps",
|
|
"custom": {
|
|
"axisLabel": "Messages In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 13
|
|
},
|
|
{
|
|
"title": "GetObject — Specials",
|
|
"description": "###### What this is:\n*Aggregate object-fetch inbound bytes plus special buckets: content-addressed storage fetches, bulk fetch-pack downloads used during catch-up, and bulk transaction fetches.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Fetch-pack rises sharply while catching up a range of ledgers; near zero when fully synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous fetch-pack traffic (node never fully catches up) or unexpectedly high content-store volume.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 48
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_cas_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"CAS Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_cas_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"CAS Share\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_fetch_pack_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Fetch Pack Share\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_fetch_pack_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Fetch Pack Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transactions_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Transactions Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_get_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Aggregate Get\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_share_bytes_in{service_instance_id=~\"$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\"}[$__rate_interval]), \"series\", \"Aggregate Share\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 14
|
|
},
|
|
{
|
|
"title": "Overlay Traffic Heatmap (All Categories, Bytes In)",
|
|
"description": "###### What this is:\n*All overlay traffic categories ranked by inbound bytes, giving an at-a-glance view of which message types consume the most receive bandwidth.*\n\n###### How it's computed:\n*Top categories by latest inbound byte value across all traffic categories. Each bar is labelled with its traffic category followed by the node identity; the shared `_bytes_in` suffix is dropped from the category name because the panel already reports inbound bytes.*\n\n###### Reading it:\n*The longest bars are the biggest bandwidth consumers; on a synced node transactions, proposals, and validations usually lead.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*A single ledger-data or fetch category dominating (ongoing sync) or an unexpected category topping the list.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 18,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 56
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"displayMode": "gradient",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(topk(20, {service_instance_id=~\"$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\", __name__=~\".*_bytes_in\", __name__!~\"total_.*\"}), \"series\", \"$1\", \"__name__\", \"(.*)_bytes_in\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "decbytes",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 1048576
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 104857600
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 15
|
|
},
|
|
{
|
|
"title": "Sync Diagnostics",
|
|
"type": "row",
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 74
|
|
},
|
|
"id": 16,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Sync State",
|
|
"description": "###### What this is:\n*Current server operating state as a numeric code: 0 disconnected, 1 connected, 2 syncing, 3 tracking, 4 full. A healthy synced node sits at 4.*\n\n###### How it's computed:\n*state_tracking{metric=\"state_value\"} (gauge). Companion time_in_current_state_seconds shows how long it has been stuck there.*\n\n###### Reading it:\n*Flat at 4 = full/healthy. Dropping to 1-2 and staying = the node fell out of sync and is re-acquiring (the primary red flag this row explains).*\n\n###### Healthy range:\n*4 (full), briefly 2-3 right after restart.*\n\n###### Watch for:\n*A node stuck below 4 for more than a few minutes, or oscillating - read the lower panels for the cause.*\n\n###### Source:\n[app/misc/NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::setMode`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 75
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(state_tracking{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=\"state_value\"}, \"series\", \"Server State\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Server State",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": {
|
|
"text": "Disconnected",
|
|
"color": "red",
|
|
"index": 0
|
|
},
|
|
"1": {
|
|
"text": "Connected",
|
|
"color": "orange",
|
|
"index": 1
|
|
},
|
|
"2": {
|
|
"text": "Syncing",
|
|
"color": "yellow",
|
|
"index": 2
|
|
},
|
|
"3": {
|
|
"text": "Tracking",
|
|
"color": "blue",
|
|
"index": 3
|
|
},
|
|
"4": {
|
|
"text": "Full",
|
|
"color": "green",
|
|
"index": 4
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 2
|
|
},
|
|
{
|
|
"color": "blue",
|
|
"value": 3
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 4
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"min": 0,
|
|
"max": 4
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 17
|
|
},
|
|
{
|
|
"title": "Validated Ledger Age",
|
|
"description": "###### What this is:\n*Seconds since this node last had a freshly validated ledger. The single clearest 'am I keeping up with the network' signal.*\n\n###### How it's computed:\n*ledgermaster_validated_ledger_age gauge (seconds), per node.*\n\n###### Reading it:\n*Should hover at the network close interval (~3-5s). A rising sawtooth or a high plateau means the node is falling behind or not validating.*\n\n###### Healthy range:\n*<= ~6s on a synced node.*\n\n###### Watch for:\n*Sustained climb above ~15s, or a monotonic ramp = the node is not keeping up; correlate with job-queue wait and NuDB read latency below.*\n\n###### Source:\n[app/ledger/LedgerMaster.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/LedgerMaster.cpp)\n\n###### Function:\n`LedgerMaster::getValidatedLedgerAge`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 75
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(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\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(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\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "s",
|
|
"custom": {
|
|
"axisLabel": "Age (seconds)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 18
|
|
},
|
|
{
|
|
"title": "Ledger Close Rate",
|
|
"description": "###### What this is:\n*Rate at which the node closes ledgers, versus the ~0.25/s network cadence. A throughput deficit means it is not advancing in step with the network.*\n\n###### How it's computed:\n*rate(ledgers_closed_total[$__rate_interval]) per node.*\n\n###### Reading it:\n*Should track ~0.22-0.25 ledgers/s (one every ~4s). Near-zero while behind = stalled; a burst above network rate = catching up.*\n\n###### Healthy range:\n*~0.25/s steady on a synced node.*\n\n###### Watch for:\n*Near-zero close rate while Validated Ledger Age climbs = hard stall (e.g. genesis-flapping or disk-bound acquisition).*\n\n###### Source:\n[app/ledger/LedgerMaster.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/ledger/detail/LedgerMaster.cpp)\n\n###### Function:\n`LedgerMaster::closeLedger`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 83
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(rate(ledgers_closed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}[$__rate_interval]), \"series\", \"Ledgers Closed\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(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\", \"Ledger Fetches\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "reqps",
|
|
"custom": {
|
|
"axisLabel": "Rate (per second)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 19
|
|
},
|
|
{
|
|
"title": "Job Queue Wait p95 By Type",
|
|
"description": "###### What this is:\n*95th-percentile time a job waits in the queue before a worker thread picks it up, for the sync-critical job types. This is the metric form of the 'ProcessLData wait: NNNNms' warnings in the debug log.*\n\n###### How it's computed:\n*histogram_quantile(0.95, rate(jobq_<type>_q_milliseconds_bucket[$__rate_interval])) for ledgerdata, acceptledger, fetchtxndata, transaction, advanceledger, ledgerrequest.*\n\n###### Reading it:\n*Queue wait should be single-digit to low-tens of ms. High ledgerdata/fetchtxndata wait = the node cannot process inbound ledger data fast enough.*\n\n###### Healthy range:\n*< ~50ms p95 per type on a healthy node.*\n\n###### Watch for:\n*ledgerdata or fetchtxndata q-wait spiking to seconds = worker threads are blocked (usually on NuDB reads - see the cause tier).*\n\n###### Source:\n[core/JobQueue.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/core/detail/JobQueue.cpp)\n\n###### Function:\n`JobQueue::getJson (per-type queue timing)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 83
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_ledgerdata_q_milliseconds_bucket{service_instance_id=~\"$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\"}[$__rate_interval]))), \"series\", \"ledgerdata q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_acceptledger_q_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=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"acceptledger q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_fetchtxndata_q_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=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"fetchtxndata q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_transaction_q_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=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"transaction q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_advanceledger_q_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=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"advanceledger q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(jobq_ledgerrequest_q_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=~\"$xrpl_node_role\"}[$__rate_interval]))), \"series\", \"ledgerrequest q-wait p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "p95 Wait (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 20
|
|
},
|
|
{
|
|
"title": "NuDB Read Latency",
|
|
"description": "###### What this is:\n*Average nodestore (NuDB) read latency: how long each on-disk object read takes. The direct disk-layer cost that backs up the job queue.*\n\n###### How it's computed:\n*rate(nodestore_state{metric=\"node_reads_duration_us\"}[$__rate_interval]) / rate(nodestore_state{metric=\"node_reads_total\"}[$__rate_interval]), in us.*\n\n###### Reading it:\n*Low single-digit us when the OS page cache is warm; tens-to-hundreds of us when reads hit the disk. Rises sharply during cold-cache catch-up.*\n\n###### Healthy range:\n*< ~10us/read warm; higher is expected briefly after a wipe/restart.*\n\n###### Watch for:\n*Sustained high us/read together with low cache hit % (below) = disk-bound reads are the bottleneck; check EBS IOPS / io scheduler latency.*\n\n###### Source:\n[nodestore/backend/NuDBFactory.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/nodestore/backend/NuDBFactory.cpp)\n\n###### Function:\n`NuDB backend read path`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 91
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (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])) / clamp_min(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (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])), 1), \"series\", \"NuDB us/read\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "µs",
|
|
"custom": {
|
|
"axisLabel": "Latency (µs/read)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 21
|
|
},
|
|
{
|
|
"title": "I/O Scheduler Latency p95",
|
|
"description": "###### What this is:\n*95th-percentile latency of the node's internal I/O service queue - the async task scheduler that dispatches network and disk callbacks.*\n\n###### How it's computed:\n*histogram_quantile(0.95, rate(ios_latency_milliseconds_bucket[$__rate_interval])).*\n\n###### Reading it:\n*Low and flat when the event loop is responsive. Rising p95 means callbacks are queuing behind long-running work (often blocking disk reads).*\n\n###### Healthy range:\n*< ~10ms p95.*\n\n###### Watch for:\n*p95 climbing into hundreds of ms = the I/O service is saturated; the node cannot service network/disk events promptly, stalling sync.*\n\n###### Source:\n[core/impl/Workers.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/core/detail/Workers.cpp)\n\n###### Function:\n`io_service latency histogram`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 91
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role) (rate(ios_latency_milliseconds_bucket{service_instance_id=~\"$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\"}[$__rate_interval]))), \"series\", \"IO Service p95\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "p95 Latency (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 22
|
|
},
|
|
{
|
|
"title": "NuDB Cache Hit Ratio",
|
|
"description": "###### What this is:\n*Fraction of nodestore reads served from cache rather than disk. A cold cache (fresh NuDB after a wipe) forces almost every read to disk - the root cause of high read latency during catch-up.*\n\n###### How it's computed:\n*rate(nodestore_state{metric=\"node_reads_hit\"}[$__rate_interval]) / rate(nodestore_state{metric=\"node_reads_total\"}[$__rate_interval]).*\n\n###### Reading it:\n*Near 1.0 (100%) on a warm node. Near 0 right after a wipe/restart, climbing as the working set warms.*\n\n###### Healthy range:\n*> ~0.9 warm; near 0 briefly after a cold start.*\n\n###### Watch for:\n*Persistently low hit ratio on a node that should be warm = working set does not fit cache, or continuous re-acquisition churning the cache.*\n\n###### Source:\n[nodestore/backend/NuDBFactory.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/nodestore/backend/NuDBFactory.cpp)\n\n###### Function:\n`TaggedCache hit accounting`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 99
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (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])) / clamp_min(sum by (service_instance_id, xrpl_branch, xrpl_node_role) (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])), 1), \"series\", \"NuDB Hit Ratio\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "percentunit",
|
|
"custom": {
|
|
"axisLabel": "Hit Ratio",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 23
|
|
},
|
|
{
|
|
"title": "NuDB Read Pressure",
|
|
"description": "###### What this is:\n*Nodestore read throughput and backlog: reads per second, the pending read queue depth, and how many read threads are active. Shows disk saturation depth.*\n\n###### How it's computed:\n*rate(node_reads_total), and gauges read_queue / read_threads_running from nodestore_state.*\n\n###### Reading it:\n*reads/s spikes during catch-up. A growing read_queue with all read threads busy = disk cannot keep up with demand.*\n\n###### Healthy range:\n*read_queue ~0 and reads/s low on a warm synced node.*\n\n###### Watch for:\n*read_queue climbing while read_threads_running is pinned at read_threads_total = disk-bound; the IOPS ceiling is the limiter.*\n\n###### Source:\n[nodestore/backend/NuDBFactory.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/nodestore/backend/NuDBFactory.cpp)\n\n###### Function:\n`NuDB read scheduler`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 99
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(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/s\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(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\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(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\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Reads/s & Depth",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 24
|
|
},
|
|
{
|
|
"title": "Job Queue Depth",
|
|
"description": "###### What this is:\n*Total number of jobs currently queued across the JobQueue. A backlog means work is arriving faster than worker threads can drain it.*\n\n###### How it's computed:\n*jobq_job_count gauge (total queued jobs), per node.*\n\n###### Reading it:\n*Near 0 when keeping up. Sustained positive depth = the node is overloaded or blocked on a downstream resource (usually disk reads).*\n\n###### Healthy range:\n*~0 on a healthy node.*\n\n###### Watch for:\n*Depth climbing in step with Validated Ledger Age = the queue backlog is why the node is falling behind.*\n\n###### Source:\n[core/JobQueue.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/core/detail/JobQueue.cpp)\n\n###### Function:\n`JobQueue::getJobCountTotal`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 107
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(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\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Queued Jobs",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 25
|
|
},
|
|
{
|
|
"title": "Load Factor & Peers",
|
|
"description": "###### What this is:\n*Server load factor (fee/throttle multiplier; 1 = unloaded) alongside active inbound/outbound peer counts. Rules out overload and insufficient fetch sources as causes.*\n\n###### How it's computed:\n*load_factor_metrics{metric=\"load_factor\"}, and peer_finder_active_inbound_peers / _outbound_peers gauges.*\n\n###### Reading it:\n*load_factor at 1 = no local overload. Outbound peers should be healthy (~10+); too few peers limits how fast the node can fetch ledger data.*\n\n###### Healthy range:\n*load_factor = 1; outbound peers >= ~8.*\n\n###### Watch for:\n*load_factor > 1 = local overload throttling; very low peer count = not enough sources to acquire history from (a distinct sync bottleneck).*\n\n###### Source:\n[overlay/detail/OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl load / PeerFinder counts`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 107
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(load_factor_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=\"load_factor\"}, \"series\", \"Load Factor\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(peer_finder_active_outbound_peers{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Outbound Peers\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(peer_finder_active_inbound_peers{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\"}, \"series\", \"Inbound Peers\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Factor / Peer Count",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 26
|
|
},
|
|
{
|
|
"title": "Job Queue Saturation",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 115
|
|
},
|
|
"collapsed": false,
|
|
"panels": [],
|
|
"id": 27
|
|
},
|
|
{
|
|
"title": "Job Queue Backlog and Deferred by Type",
|
|
"description": "###### What this is:\n*Per-job-type queue depth, two series per type. Waiting is the whole backlog: every job enqueued for that type that has not started yet. Deferred is the subset of that backlog that is blocked specifically because the type is already running at its concurrency limit. Deferred is the leading indicator of backpressure, because JobQueue::addJob never rejects a job for queue pressure -- it returns success and defers instead, so a capped type under pressure produces no error and no dropped work. Without these the only evidence is latency, which appears after the harm is already done.*\n\n###### How it's computed:\n*Two targets, each the top 10 gauges by current value: jobq_<jobtype>_waiting and jobq_<jobtype>_deferred. JobQueue::collect snapshots both counters under the one lock that guards them, so the pair is read at the same instant and is directly comparable, then publishes them on the 10-second export cycle. Gauges exist only for non-special job types, so the 11 special types -- the ones declared with a limit of 0, which bypass the limit logic entirely and therefore never defer -- do not appear on either series.*\n\n###### Reading it:\n*Read the two together; the ratio is the diagnostic, not either value alone. Deferred is always a subset of waiting, because addRefCountedJob increments waiting for every job and deferred only for the ones that arrive while the type is at its limit. Waiting high with deferred at zero means the type has spare slots and the backlog is just arrival burstiness -- it will drain without intervention. Waiting high with deferred also high means the concurrency limit is the binding constraint, not the work. Both near zero is the normal state. These are depths, not rates: the value is how many jobs are queued right now. finishJob drains deferred one per completion, so a deferred line that stays elevated means arrivals are outpacing completions rather than one isolated burst. Only the 10 highest series per state are drawn, which on an idle node is arbitrary among the zeros and under load is exactly the types under pressure.*\n\n###### Healthy range:\n*Deferred zero on all types. Waiting near zero, with brief spikes during ledger close.*\n\n###### Watch for:\n*ledgerrequest deferred above zero: the 3-slot ledgerRequest queue is full, so TMGetLedger service to syncing peers is being delayed. Use LedgerReq Wait by Handler next to see which of its two producers is responsible. ledgerdata or fetchtxndata deferred: inbound ledger data cannot be absorbed fast enough, which is what makes validated ledger age grow. A waiting line that climbs steadily while deferred stays flat points at the worker pool or at slow jobs rather than at the limit. Note both are sampled once per export cycle, so a sub-second spike can be missed; a reading of zero is not proof that nothing was ever queued or deferred.*\n\n###### Keywords:\n- **Deferred job** *(per node)* — a job held back because its type is already at its concurrency limit; the leading indicator of queue backpressure.\n- **Concurrency limit** *(per node)* — the cap on how many jobs of one type may run at once; a type at its cap cannot start more work.\n- **Job queue / job type** *(per node)* — xrpld's worker-thread pool; every unit of background work is enqueued under a named job type.\n\n###### Computation boundary:\n*Result: Per node — each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[core/JobQueue.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/core/detail/JobQueue.cpp)\n\n###### Function:\n`JobQueue::addRefCountedJob / JobQueue::collect`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#deferred-job)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 116
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(topk(10, {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\", __name__=~\"jobq_.*_deferred\"}), \"series\", \"$1 Deferred\", \"__name__\", \"jobq_(.*)_deferred\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(topk(10, {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\", __name__=~\"jobq_.*_waiting\"}), \"series\", \"$1 Waiting\", \"__name__\", \"jobq_(.*)_waiting\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Queued Jobs (Waiting / Deferred)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 28
|
|
},
|
|
{
|
|
"title": "LedgerReq Wait by Handler",
|
|
"description": "###### What this is:\n*Queue wait for the ledgerRequest job type, split by which handler enqueued the job. The type has a concurrency limit of 3 and two producers that compete for those slots: RcvGetLedger, which serves TMGetLedger to syncing peers, and RcvGetObjByHash, which serves TMGetObjectByHash. Both report the same job_type, so without the handler split a wait spike cannot be attributed to either.*\n\n###### How it's computed:\n*p99 of job_queued_us for job_type=\"ledgerRequest\", grouped by the handler label. JobQueue::processTask measures the wait, then PerfLog hands it to MetricsRegistry::recordJobStarted, which is where the histogram is recorded. The handler value is the addJob name passed through a sanitizer that keeps letters-only names and folds everything else to \"other\", which bounds the label domain to 43 names plus \"other\". Both producers here are letters-only, so both appear under their own names; \"other\" is a mixed bucket and never means one specific caller.*\n\n###### Reading it:\n*This is the panel that answers which producer is starving the 3-slot queue. Both lines high together means the queue is genuinely oversubscribed and both kinds of peer request are being delayed. One line high while the other is flat means that producer is arriving faster than 3 concurrent slots can absorb, and it is the one delaying the other. Wait is queue time only, so a high line here is contention, not slow work; the work itself is on the GetObject Handler Latency Breakdown panel.*\n\n###### Healthy range:\n*Single-digit to low-tens of milliseconds p99 for both handlers, matching the wider Job Queue Wait p95 By Type panel.*\n\n###### Watch for:\n*RcvGetObjByHash wait climbing: one in-bounds TMGetObjectByHash request can perform thousands of NodeStore lookups, so a few concurrent ones occupy every slot and delay TMGetLedger to peers that are themselves syncing. Cross-check Job Queue Backlog and Deferred by Type for jobq_ledgerrequest_deferred above zero to confirm the limit, not the work, is the binding constraint.*\n\n###### Keywords:\n- **Handler label** *(per node)* — the addJob call-site name attached to job metrics, so producers sharing one job type stay separable.\n- **Concurrency limit** *(per node)* — the cap on how many jobs of one type may run at once; a type at its cap cannot start more work.\n- **Job queue / job type** *(per node)* — xrpld's worker-thread pool; every unit of background work is enqueued under a named job type.\n\n###### Computation boundary:\n*Result: Per node — each series is one server's own value.*\n*Computed in xrpld code (MetricsRegistry, OpenTelemetry SDK) and exported as a metric; the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`MetricsRegistry::recordJobStarted`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#handler-label)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 116
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.99, sum by (le, handler, service_instance_id, xrpl_branch, xrpl_node_role) (rate(job_queued_us_bucket{job_type=\"ledgerRequest\", handler=~\"$handler\", service_instance_id=~\"$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\", \"$1 q-wait p99\", \"handler\", \"(.*)\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "µs",
|
|
"custom": {
|
|
"axisLabel": "p99 Wait (μs)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 29
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["ledger", "sync"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "service_name",
|
|
"label": "Service Name",
|
|
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
|
"type": "query",
|
|
"query": "label_values(service_name)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "xrpld",
|
|
"value": "xrpld"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "deployment_environment",
|
|
"label": "Environment",
|
|
"description": "Filter by deployment tier [local / ci / test / prod]",
|
|
"type": "query",
|
|
"query": "label_values(deployment_environment)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__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": "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": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "node",
|
|
"label": "Node",
|
|
"description": "Filter by rippled node (service.instance.id)",
|
|
"type": "query",
|
|
"query": "label_values(target_info, service_instance_id)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "handler",
|
|
"label": "Handler",
|
|
"description": "Filter by enqueueing handler (sanitised addJob name, e.g. RcvGetLedger)",
|
|
"type": "query",
|
|
"query": "label_values(job_queued_total, handler)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "Ledger Data & Sync",
|
|
"uid": "ledger-data-sync"
|
|
}
|