mirror of
https://github.com/XRPLF/rippled.git
synced 2026-08-22 14:50:54 +00:00
004b8e92ab
Nine targets across four panels filtered on xrpl_work_item while leaving it out of their sum by() grouping. PromQL keeps only the labels listed in by(), so the label was dropped from the result and the xrpl_ident legend these panels build from it lost that segment. Perf-iac runs stamp xrpl_work_item and give each work item its own set of nodes, so service_instance_id already separates the runs; the visible effect is the legend rather than merged series. Adding the label makes the work item identifiable, which is the comparison these panels exist for. NuDB Read Latency and NuDB Read Found Ratio each divide two aggregations. Both sides get the label so their label sets stay equal and vector matching still works.
1785 lines
91 KiB
JSON
1785 lines
91 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": "Overlay Traffic Heatmap (All Categories, Bytes In) [$xrpl_network_type]",
|
|
"description": "###### What this is:\n*All overlay traffic categories ranked by inbound bytes, giving an at-a-glance view of which message types consume the most receive bandwidth.*\n\n###### How it's computed:\n*Top categories by latest inbound byte value across all traffic categories. Each bar is labelled with its traffic category followed by the node identity; the shared `_bytes_in` suffix is dropped from the category name because the panel already reports inbound bytes.*\n\n###### Reading it:\n*The longest bars are the biggest bandwidth consumers; on a synced node transactions, proposals, and validations usually lead.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*A single ledger-data or fetch category dominating (ongoing sync) or an unexpected category topping the list.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"displayMode": "gradient",
|
|
"orientation": "horizontal",
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(topk(20, {service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "decbytes",
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 1048576
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 104857600
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 1,
|
|
"repeat": "xrpl_network_type",
|
|
"repeatDirection": "h",
|
|
"maxPerRow": 2
|
|
},
|
|
{
|
|
"title": "Ledger Data \u2014 Ledger",
|
|
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 10
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 2
|
|
},
|
|
{
|
|
"title": "Ledger Data \u2014 Transaction",
|
|
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 10
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 3
|
|
},
|
|
{
|
|
"title": "Ledger Data \u2014 Account State",
|
|
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 20
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_data_account_state_node_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 4
|
|
},
|
|
{
|
|
"title": "Ledger Traffic \u2014 Ledger",
|
|
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 20
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 5
|
|
},
|
|
{
|
|
"title": "Ledger Traffic \u2014 Transaction",
|
|
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 30
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 6
|
|
},
|
|
{
|
|
"title": "Ledger Traffic \u2014 Account State",
|
|
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 30
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(ledger_account_state_node_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 7
|
|
},
|
|
{
|
|
"title": "GetObject \u2014 Ledger",
|
|
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 40
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_ledger_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 8
|
|
},
|
|
{
|
|
"title": "GetObject \u2014 Transaction",
|
|
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 40
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transaction_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 9
|
|
},
|
|
{
|
|
"title": "GetObject \u2014 Account State",
|
|
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 50
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_account_state_node_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 10
|
|
},
|
|
{
|
|
"title": "GetObject Messages \u2014 Ledger",
|
|
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 50
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_ledger_get_messages_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "suffix: messages/s",
|
|
"custom": {
|
|
"axisLabel": "Messages / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 11
|
|
},
|
|
{
|
|
"title": "GetObject Messages \u2014 Transaction",
|
|
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 60
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_transaction_get_messages_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "suffix: messages/s",
|
|
"custom": {
|
|
"axisLabel": "Messages / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 12
|
|
},
|
|
{
|
|
"title": "GetObject Messages \u2014 Account State",
|
|
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 60
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_account_state_node_get_messages_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "suffix: messages/s",
|
|
"custom": {
|
|
"axisLabel": "Messages / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 13
|
|
},
|
|
{
|
|
"title": "GetObject Messages \u2014 Specials",
|
|
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 70
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_cas_get_messages_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "suffix: messages/s",
|
|
"custom": {
|
|
"axisLabel": "Messages / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 14
|
|
},
|
|
{
|
|
"title": "GetObject \u2014 Specials",
|
|
"description": "###### What this is:\n*Aggregate object-fetch inbound bytes plus special buckets: content-addressed storage fetches, bulk fetch-pack downloads used during catch-up, and bulk transaction fetches.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Fetch-pack rises sharply while catching up a range of ledgers; near zero when fully synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous fetch-pack traffic (node never fully catches up) or unexpectedly high content-store volume.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 70
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(getobject_cas_get_bytes_in{service_instance_id=~\"$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} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "Bps",
|
|
"custom": {
|
|
"axisLabel": "Bytes In",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 15
|
|
},
|
|
{
|
|
"title": "Sync Diagnostics",
|
|
"type": "row",
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 80
|
|
},
|
|
"id": 16,
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "Sync State",
|
|
"description": "###### What this is:\n*Current server operating state as a numeric code: 0 disconnected, 1 connected, 2 syncing, 3 tracking, 4 full, 5 validating, 6 proposing. A healthy validator sits at 6, a healthy non-validating node at 4.*\n\n###### How it's computed:\n*state_tracking{metric=\"state_value\"} (gauge). Companion time_in_current_state_seconds shows how long it has been stuck there.*\n\n###### Reading it:\n*Flat at 4-6 = full/healthy. Dropping to 1-2 and staying = the node fell out of sync and is re-acquiring (the primary red flag this row explains).*\n\n###### Healthy range:\n*4-6 steady, briefly 2-3 right after restart.*\n\n###### Watch for:\n*A node stuck below 4 for more than a few minutes, or oscillating - read the lower panels for the cause.*\n\n###### Source:\n[app/misc/NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::setMode`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 81
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${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": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
},
|
|
"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
|
|
},
|
|
"5": {
|
|
"text": "Validating",
|
|
"color": "super-light-green",
|
|
"index": 5
|
|
},
|
|
"6": {
|
|
"text": "Proposing",
|
|
"color": "dark-green",
|
|
"index": 6
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"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": "super-light-green",
|
|
"value": 5
|
|
},
|
|
{
|
|
"color": "dark-green",
|
|
"value": 6
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"min": 0,
|
|
"max": 6
|
|
},
|
|
"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": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 81
|
|
},
|
|
"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} ${__field.labels.xrpl_ident}",
|
|
"unit": "s",
|
|
"custom": {
|
|
"axisLabel": "Age (seconds)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 18
|
|
},
|
|
{
|
|
"title": "Time Spent Per State",
|
|
"description": "###### What this is:\n*Operating mode as a colour-coded timeline. Each band's width is the time spent in that state, so short-lived states show as thin slivers instead of vanishing.*\n\n###### How it's computed:\n*server_info{metric=\"server_state\"} (gauge), the raw OperatingMode 0-4. Uses server_state rather than state_value because state_value folds 5 and 6 onto FULL, which would split one Full band into three colours.*\n\n###### Reading it:\n*One green band across the window = healthy. Red/orange/yellow bands show when and for how long the node was degraded.*\n\n###### Healthy range:\n*Continuously green (Full), brief orange/yellow/blue only after a restart.*\n\n###### Watch for:\n*Repeated thin bands = the node is oscillating. This is sampled every 10s, so a state shorter than one sample can still be missed.*\n\n###### Source:\n[app/misc/NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::setMode`",
|
|
"type": "state-timeline",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 91
|
|
},
|
|
"options": {
|
|
"mergeValues": true,
|
|
"showValue": "auto",
|
|
"alignValue": "left",
|
|
"rowHeight": 0.9,
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(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\"}, \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")",
|
|
"refId": "A"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "State ${__field.labels.xrpl_ident}",
|
|
"unit": "none",
|
|
"custom": {
|
|
"fillOpacity": 80,
|
|
"lineWidth": 0,
|
|
"insertNulls": false,
|
|
"spanNulls": 1800000
|
|
},
|
|
"mappings": [
|
|
{
|
|
"type": "value",
|
|
"options": {
|
|
"0": {
|
|
"text": "Disconnected",
|
|
"color": "red",
|
|
"index": 0
|
|
},
|
|
"1": {
|
|
"text": "Connected",
|
|
"color": "orange",
|
|
"index": 1
|
|
},
|
|
"2": {
|
|
"text": "Syncing",
|
|
"color": "yellow",
|
|
"index": 2
|
|
},
|
|
"3": {
|
|
"text": "Tracking",
|
|
"color": "blue",
|
|
"index": 3
|
|
},
|
|
"4": {
|
|
"text": "Full",
|
|
"color": "green",
|
|
"index": 4
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "red",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "orange",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 2
|
|
},
|
|
{
|
|
"color": "blue",
|
|
"value": 3
|
|
},
|
|
{
|
|
"color": "green",
|
|
"value": 4
|
|
}
|
|
]
|
|
},
|
|
"color": {
|
|
"mode": "thresholds"
|
|
},
|
|
"min": 0,
|
|
"max": 4
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 19
|
|
},
|
|
{
|
|
"title": "Ledger Close Rate",
|
|
"description": "###### What this is:\n*Rate at which the node closes ledgers, versus the ~0.25/s network cadence. A throughput deficit means it is not advancing in step with the network.*\n\n###### How it's computed:\n*rate(ledgers_closed_total[$__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": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 91
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(rate(ledgers_closed_total{service_instance_id=~\"$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} ${__field.labels.xrpl_ident}",
|
|
"unit": "suffix: ledgers/s",
|
|
"custom": {
|
|
"axisLabel": "Ledgers / Sec & Fetches / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "/^Ledger Fetches/"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "unit",
|
|
"value": "suffix: fetches/s"
|
|
},
|
|
{
|
|
"id": "custom.axisPlacement",
|
|
"value": "right"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"id": 20
|
|
},
|
|
{
|
|
"title": "Job Queue Wait p95 By Type",
|
|
"description": "###### What this is:\n*95th-percentile time a job waits in the queue before a worker thread picks it up, for the sync-critical job types. This is the metric form of the 'ProcessLData wait: NNNNms' warnings in the debug log.*\n\n###### How it's computed:\n*histogram_quantile(0.95, rate(jobq_<type>_q_milliseconds_bucket[$__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": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 101
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(jobq_ledgerdata_q_milliseconds_bucket{service_instance_id=~\"$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, xrpl_work_item) (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, xrpl_work_item) (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, xrpl_work_item) (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, xrpl_work_item) (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, xrpl_work_item) (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} ${__field.labels.xrpl_ident}",
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "p95 Wait (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 21
|
|
},
|
|
{
|
|
"title": "NuDB Read Latency",
|
|
"description": "###### What this is:\n*Average nodestore (NuDB) read latency: how long each on-disk object read takes. The direct disk-layer cost that backs up the job queue.*\n\n###### How it's computed:\n*rate(nodestore_state{metric=\"node_reads_duration_us\"}[$__rate_interval]) / rate(nodestore_state{metric=\"node_reads_total\"}[$__rate_interval]), in us.*\n\n###### Reading it:\n*Low single-digit us when the OS page cache is warm; tens-to-hundreds of us when reads hit the disk. Rises sharply during cold-cache catch-up.*\n\n###### Healthy range:\n*< ~10us/read warm; higher is expected briefly after a wipe/restart.*\n\n###### Watch for:\n*Sustained high us/read is the disk-bound signal on its own; the found ratio below stays near 100% even then, so do not wait for it to drop. Check EBS IOPS / io scheduler latency.*\n\n###### Source:\n[nodestore/backend/NuDBFactory.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/nodestore/backend/NuDBFactory.cpp)\n\n###### Function:\n`NuDB backend read path`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 101
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (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])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (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])) > 0), \"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} ${__field.labels.xrpl_ident}",
|
|
"unit": "\u00b5s",
|
|
"custom": {
|
|
"axisLabel": "Latency (\u00b5s/read)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 22
|
|
},
|
|
{
|
|
"title": "I/O Scheduler Latency p95",
|
|
"description": "###### What this is:\n*95th-percentile latency of the node's internal I/O service queue - the async task scheduler that dispatches network and disk callbacks.*\n\n###### How it's computed:\n*histogram_quantile(0.95, rate(ios_latency_milliseconds_bucket[$__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": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 111
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(histogram_quantile(0.95, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(ios_latency_milliseconds_bucket{service_instance_id=~\"$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} ${__field.labels.xrpl_ident}",
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "p95 Latency (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 23
|
|
},
|
|
{
|
|
"title": "NuDB Read Found Ratio",
|
|
"description": "###### What this is:\n*Fraction of nodestore fetches that found the object they asked for. This is not a cache hit ratio: `node_reads_hit` counts every fetch that returned an object, whatever served it, so a fetch that went all the way to disk still counts here.*\n\n###### How it's computed:\n*rate(nodestore_state{metric=\"node_reads_hit\"}[$__rate_interval]) / rate(nodestore_state{metric=\"node_reads_total\"}[$__rate_interval]).*\n\n###### Reading it:\n*Normally sits near 1.0 (100%) on any node that has the data, warm or cold, because a synced node almost always finds what it asks for. It does not fall when the page cache goes cold.*\n\n###### Healthy range:\n*Near 1.0. A ratio well below 1.0 means fetches are missing, which points at a gap in local history rather than at cache pressure.*\n\n###### Watch for:\n*Never read this panel on its own. A ~100% found ratio at over 100 microseconds per read is the cold-read signature, not a healthy cache: the data is found every time and paid for every time. Always pair it with NuDB Read Latency.*\n\n###### Source:\n[nodestore/Database.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/nodestore/Database.cpp)\n\n###### Function:\n`Database::fetchNodeObject`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 111
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "label_replace(label_join(label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (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])) / (sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (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])) > 0), \"series\", \"NuDB Found Ratio\", \"\", \"\"), \"xrpl_ident\", \", \", \"service_instance_id\", \"xrpl_branch\", \"xrpl_work_item\"), \"xrpl_ident\", \"[$1]\", \"xrpl_ident\", \"(?:, )*(.*[^, ])(?:, )*\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} ${__field.labels.xrpl_ident}",
|
|
"unit": "percentunit",
|
|
"custom": {
|
|
"axisLabel": "Found Ratio",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 24
|
|
},
|
|
{
|
|
"title": "NuDB Read Pressure",
|
|
"description": "###### What this is:\n*Nodestore read throughput and backlog: reads per second, the pending read queue depth, and how many read threads are active. Shows disk saturation depth.*\n\n###### How it's computed:\n*rate(node_reads_total), and gauges read_queue / read_threads_running from nodestore_state.*\n\n###### Reading it:\n*reads/s spikes during catch-up. A growing read_queue with all read threads busy = disk cannot keep up with demand.*\n\n###### Healthy range:\n*read_queue ~0 and reads/s low on a warm synced node.*\n\n###### Watch for:\n*read_queue climbing while read_threads_running is pinned at read_threads_total = disk-bound; the IOPS ceiling is the limiter.*\n\n###### Source:\n[nodestore/backend/NuDBFactory.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/nodestore/backend/NuDBFactory.cpp)\n\n###### Function:\n`NuDB read scheduler`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 121
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${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} ${__field.labels.xrpl_ident}",
|
|
"unit": "suffix: reads/s",
|
|
"custom": {
|
|
"axisLabel": "Reads / Sec & Depth",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": [
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "/^Read Queue/"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "unit",
|
|
"value": "short"
|
|
},
|
|
{
|
|
"id": "custom.axisPlacement",
|
|
"value": "right"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"matcher": {
|
|
"id": "byRegexp",
|
|
"options": "/^Read Threads Running/"
|
|
},
|
|
"properties": [
|
|
{
|
|
"id": "unit",
|
|
"value": "short"
|
|
},
|
|
{
|
|
"id": "custom.axisPlacement",
|
|
"value": "right"
|
|
}
|
|
]
|
|
}
|
|
]
|
|
},
|
|
"id": 25
|
|
},
|
|
{
|
|
"title": "Job Queue Depth",
|
|
"description": "###### What this is:\n*Total number of jobs currently queued across the JobQueue. A backlog means work is arriving faster than worker threads can drain it.*\n\n###### How it's computed:\n*jobq_job_count gauge (total queued jobs), per node.*\n\n###### Reading it:\n*Near 0 when keeping up. Sustained positive depth = the node is overloaded or blocked on a downstream resource (usually disk reads).*\n\n###### Healthy range:\n*~0 on a healthy node.*\n\n###### Watch for:\n*Depth climbing in step with Validated Ledger Age = the queue backlog is why the node is falling behind.*\n\n###### Source:\n[core/JobQueue.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/core/detail/JobQueue.cpp)\n\n###### Function:\n`JobQueue::getJobCountTotal`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 121
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${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} ${__field.labels.xrpl_ident}",
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Queued Jobs",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
},
|
|
"decimals": 0
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 26
|
|
},
|
|
{
|
|
"title": "Load Factor & Peers",
|
|
"description": "###### What this is:\n*Server load factor (fee/throttle multiplier; 1 = unloaded) alongside active inbound/outbound peer counts. Rules out overload and insufficient fetch sources as causes.*\n\n###### How it's computed:\n*load_factor_metrics{metric=\"load_factor\"}, and peer_finder_active_inbound_peers / _outbound_peers gauges.*\n\n###### Reading it:\n*load_factor at 1 = no local overload. Outbound peers should be healthy (~10+); too few peers limits how fast the node can fetch ledger data.*\n\n###### Healthy range:\n*load_factor = 1; outbound peers >= ~8.*\n\n###### Watch for:\n*load_factor > 1 = local overload throttling; very low peer count = not enough sources to acquire history from (a distinct sync bottleneck).*\n\n###### Source:\n[overlay/detail/OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl load / PeerFinder counts`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 131
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${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} ${__field.labels.xrpl_ident}",
|
|
"unit": "short",
|
|
"custom": {
|
|
"axisLabel": "Factor / Peer Count",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
},
|
|
"decimals": 0
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 27
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["ledger", "sync"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "DS_PROMETHEUS",
|
|
"type": "datasource",
|
|
"label": "Prometheus",
|
|
"query": "prometheus",
|
|
"regex": "",
|
|
"current": {},
|
|
"hide": 0,
|
|
"refresh": 1,
|
|
"includeAll": false,
|
|
"multi": false,
|
|
"options": []
|
|
},
|
|
{
|
|
"name": "service_name",
|
|
"label": "Service Name",
|
|
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
|
"type": "query",
|
|
"query": "label_values(service_name)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "xrpld",
|
|
"value": "xrpld"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "deployment_environment",
|
|
"label": "Environment",
|
|
"description": "Filter by deployment tier [local / ci / test / prod]",
|
|
"type": "query",
|
|
"query": "label_values(deployment_environment)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__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
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "Ledger Data & Sync",
|
|
"uid": "ledger-data-sync"
|
|
}
|