mirror of
https://github.com/XRPLF/rippled.git
synced 2026-07-23 07:00:21 +00:00
cb1ca17442
Grafana Cloud variants of the 14 xrpld dashboards. Identical to the local grafana/dashboards/ originals except the DS_PROMETHEUS / DS_TEMPO datasource template variables have their `current` value pinned to the Grafana Cloud datasource UIDs (grafanacloud-ripplex-prometheus / -traces). Includes the ledger-data-sync data-type split and node-health mixed-unit split + Cache Hit Ratio fix merged forward from phases 7 and 9. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
1080 lines
44 KiB
JSON
1080 lines
44 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"id": 11,
|
|
"type": "row",
|
|
"title": "Aggregate RPC (all commands)",
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "RPC Request Rate by Command",
|
|
"description": "###### What this is:\n*How many times each RPC command runs per second.*\n\n###### How it's computed:\n*Per-second rate of command executions over 5 minutes, grouped by command name and node.*\n\n###### Reading it:\n*Compare bars/lines across commands to see which endpoints drive load.*\n\n###### Healthy range:\n*Workload-dependent; dominated by whichever commands clients call most.*\n\n###### Watch for:\n*A single command spiking far above its norm, consistent with a client hammering one endpoint.*\n\n###### Source:\n[RPCHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/RPCHandler.cpp)\n\n###### Function:\n`callMethod`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 1
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (command, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval]))",
|
|
"legendFormat": "{{command}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps",
|
|
"custom": {
|
|
"axisLabel": "Requests / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 1
|
|
},
|
|
{
|
|
"title": "RPC Latency P95 by Command",
|
|
"description": "###### What this is:\n*The 95th-percentile response time for each RPC command.*\n\n###### How it's computed:\n*95th-percentile of per-command execution durations over 5 minutes, grouped by command and node.*\n\n###### Reading it:\n*Lower is better; watch the slowest commands.*\n\n###### Healthy range:\n*Fast lookups a few ms; heavy queries tens to hundreds of ms. Workload-dependent.*\n\n###### Watch for:\n*A command whose latency climbs steadily, pointing to an expensive or degrading query path.*\n\n###### Source:\n[RPCHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/RPCHandler.cpp)\n\n###### Function:\n`callMethod`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 1
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, command, service_instance_id) (rate(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])))",
|
|
"legendFormat": "P95 {{command}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Latency (ms)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 2
|
|
},
|
|
{
|
|
"title": "RPC Error Rate",
|
|
"description": "###### What this is:\n*The percentage of each command's calls that finished with an error.*\n\n###### How it's computed:\n*Error calls divided by total calls per command over 5 minutes, expressed as a percent.*\n\n###### Reading it:\n*Green under 1%, yellow 1-5%, red above 5%.*\n\n###### Healthy range:\n*Below 1% per command in normal operation.*\n\n###### Watch for:\n*A command sitting red, indicating malformed input, overload, or a broken handler.*\n\n###### Source:\n[RPCHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/RPCHandler.cpp)\n\n###### Function:\n`callMethod`",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 9
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (command, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[$__rate_interval])) / sum by (command, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval])) * 100",
|
|
"legendFormat": "{{command}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 5
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 3
|
|
},
|
|
{
|
|
"title": "RPC Latency Heatmap",
|
|
"description": "###### What this is:\n*The full distribution of RPC response times over the window.*\n\n###### How it's computed:\n*Counts of requests in each latency band per 5-minute window, shown as color density.*\n\n###### Reading it:\n*A tight low band is healthy; multiple bands mean mixed fast/slow requests.*\n\n###### Healthy range:\n*Most mass in the low-latency bands; workload-dependent.*\n\n###### Watch for:\n*A distinct high-latency cluster (bimodal behavior) that percentiles alone would hide.*\n\n###### Source:\n[RPCHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/RPCHandler.cpp)\n\n###### Function:\n`callMethod`",
|
|
"type": "heatmap",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 9
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"yAxis": {
|
|
"axisLabel": "Duration (ms)",
|
|
"unit": "ms"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum(increase(span_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])) by (le)",
|
|
"legendFormat": "{{le}}",
|
|
"format": "heatmap"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms"
|
|
}
|
|
},
|
|
"id": 4
|
|
},
|
|
{
|
|
"title": "Overall RPC Throughput",
|
|
"description": "###### What this is:\n*Two layers of the request pipeline: connections accepted by the HTTP handler versus requests parsed and dispatched.*\n\n###### How it's computed:\n*Per-second rates of the outer request-accept layer and the inner processing layer over 5 minutes, per node.*\n\n###### Reading it:\n*The two lines should track each other closely.*\n\n###### Healthy range:\n*Workload-dependent; both lines roughly equal.*\n\n###### Watch for:\n*A gap between accept and process, meaning requests are queued or rejected before dispatch.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler::processSession ; ServerHandler::processRequest`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 17
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=\"rpc.http_request\"}[$__rate_interval]))",
|
|
"legendFormat": "rpc.http_request / Sec [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=\"rpc.process\"}[$__rate_interval]))",
|
|
"legendFormat": "rpc.process / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps",
|
|
"custom": {
|
|
"axisLabel": "Requests / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 5
|
|
},
|
|
{
|
|
"title": "RPC Success vs Error",
|
|
"description": "###### What this is:\n*Aggregate rate of successful versus failed RPC commands across all command types.*\n\n###### How it's computed:\n*Per-second rates of ok-status and error-status command completions over 5 minutes, per node.*\n\n###### Reading it:\n*Successful commands report an ok status and should dominate; the error line should stay near the floor.*\n\n###### Healthy range:\n*Error line near zero relative to success; workload-dependent.*\n\n###### Watch for:\n*A sustained error line, which warrants drilling into the per-command breakdown.*\n\n###### Source:\n[RPCHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/RPCHandler.cpp)\n\n###### Function:\n`callMethod`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 17
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_OK\"}[$__rate_interval]))",
|
|
"legendFormat": "Success [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[$__rate_interval]))",
|
|
"legendFormat": "Error [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Commands / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 6
|
|
},
|
|
{
|
|
"title": "Top Commands by Volume",
|
|
"description": "###### What this is:\n*The ten most-called RPC commands over the recent window.*\n\n###### How it's computed:\n*Total invocation counts per command over the last 5 minutes, ranked and capped at ten.*\n\n###### Reading it:\n*The top bars are the hottest endpoints driving node load.*\n\n###### Healthy range:\n*Workload-dependent; typically led by lightweight status queries.*\n\n###### Watch for:\n*An unexpected command dominating the ranking, consistent with automated abuse.*\n\n###### Source:\n[RPCHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/RPCHandler.cpp)\n\n###### Function:\n`callMethod`",
|
|
"type": "bargauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 25
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "topk(10, sum by (command, service_instance_id) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval])))",
|
|
"legendFormat": "{{command}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 7
|
|
},
|
|
{
|
|
"title": "WebSocket Message Rate",
|
|
"description": "###### What this is:\n*How many RPC messages arrive over WebSocket connections per second.*\n\n###### How it's computed:\n*Per-second rate of processed WebSocket RPC messages over 5 minutes, per node.*\n\n###### Reading it:\n*Non-zero only when clients use WebSocket; zero is normal for HTTP-only nodes.*\n\n###### Healthy range:\n*Workload-dependent; zero if no WebSocket clients.*\n\n###### Watch for:\n*A sudden surge from a single source, consistent with a chatty or abusive subscription client.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler::processSession`",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 25
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", command=~\"$command\", span_name=\"rpc.ws_message\"}[$__rate_interval]))",
|
|
"legendFormat": "WS Messages / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 8
|
|
},
|
|
{
|
|
"title": "RPC Resource Cost by Command",
|
|
"description": "###### What this is:\n*RPC traffic grouped by resource-cost category rather than by command name.*\n\n###### How it's computed:\n*Per-second rate of commands over 5 minutes, grouped by load/cost category.*\n\n###### Reading it:\n*Cheap categories should dominate; costly ones should be a small slice.*\n\n###### Healthy range:\n*Workload-dependent; low-cost categories carry most traffic.*\n\n###### Watch for:\n*Growth in high-cost categories such as exception or malformed requests, which point to problematic clients.*\n\n###### Source:\n[RPCHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/RPCHandler.cpp)\n\n###### Function:\n`callMethod`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 33
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["mean", "lastNotNull"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (load_type) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=~\"rpc.command.*\", load_type!=\"\"}[$__rate_interval]))",
|
|
"legendFormat": "{{load_type}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Requests / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 9
|
|
},
|
|
{
|
|
"title": "Batch vs Single RPC Requests",
|
|
"description": "###### What this is:\n*The rate of batched RPC requests versus single-command requests.*\n\n###### How it's computed:\n*Per-second rates of batch and single requests over 5 minutes, per node.*\n\n###### Reading it:\n*Single requests usually dominate; batch is used by bulk clients.*\n\n###### Healthy range:\n*Workload-dependent; batch typically a minority.*\n\n###### Watch for:\n*A batch rate climbing sharply, consistent with bulk automation or amplification attempts.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler::processRequest`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 41
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"rpc.process\", is_batch=\"true\"}[$__rate_interval]))",
|
|
"legendFormat": "Batch [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", span_name=\"rpc.process\", is_batch=\"false\"}[$__rate_interval]))",
|
|
"legendFormat": "Single [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"axisLabel": "Requests / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 10
|
|
},
|
|
{
|
|
"id": 12,
|
|
"type": "row",
|
|
"title": "Per-Method Detail",
|
|
"collapsed": false,
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 50
|
|
},
|
|
"panels": []
|
|
},
|
|
{
|
|
"title": "RPC Call Rate (All Methods)",
|
|
"description": "###### What this is:\n*Overall rate of RPC method calls that started, finished, and errored, across all methods.*\n\n###### How it's computed:\n*Per-second rate of each counter over a 5-minute window, summed per node.*\n\n###### Reading it:\n*Started should closely track finished; errored should be a small fraction.*\n\n###### Healthy range:\n*Workload-dependent; started ≈ finished, errored near zero.*\n\n###### Watch for:\n*A growing gap between started and finished (calls hanging), or an errored line that rises with load.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordRpcStarted / recordRpcFinished / recordRpcErrored`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 51
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(rpc_method_started_total{service_instance_id=~\"$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\", method=~\"$method\"}[$__rate_interval]))",
|
|
"legendFormat": "Started/s [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(rpc_method_finished_total{service_instance_id=~\"$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\", method=~\"$method\"}[$__rate_interval]))",
|
|
"legendFormat": "Finished/s [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(rpc_method_errored_total{service_instance_id=~\"$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\", method=~\"$method\"}[$__rate_interval]))",
|
|
"legendFormat": "Errored/s [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"axisLabel": "Operations / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 13
|
|
},
|
|
{
|
|
"title": "Per-Method Call Rate (Top 10)",
|
|
"description": "###### What this is:\n*The ten busiest RPC methods by call rate.*\n\n###### How it's computed:\n*Per-second start rate over 5 minutes, per method, showing the top ten.*\n\n###### Reading it:\n*Identifies which methods dominate load; the mix shifts with client behaviour.*\n\n###### Healthy range:\n*Workload-dependent.*\n\n###### Watch for:\n*A single method suddenly dominating, which can signal a runaway client or abusive query pattern.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordRpcStarted`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 59
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["mean", "max"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "topk(10, rate(rpc_method_started_total{service_instance_id=~\"$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\", method=~\"$method\"}[$__rate_interval]))",
|
|
"legendFormat": "{{method}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Operations / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 14
|
|
},
|
|
{
|
|
"title": "Per-Method Error Rate (Top 10)",
|
|
"description": "###### What this is:\n*The ten RPC methods producing the most errors.*\n\n###### How it's computed:\n*Per-second error rate over 5 minutes, per method, top ten.*\n\n###### Reading it:\n*Normally near zero; persistent errors point to a specific failing method.*\n\n###### Healthy range:\n*Near zero for well-behaved traffic.*\n\n###### Watch for:\n*Sustained errors concentrated on one method — a broken client, a bad input, or probing.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordRpcErrored`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 67
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["mean", "max"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "topk(10, rate(rpc_method_errored_total{service_instance_id=~\"$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\", method=~\"$method\"}[$__rate_interval]))",
|
|
"legendFormat": "{{method}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ops",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Operations / Sec",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 15
|
|
},
|
|
{
|
|
"title": "RPC Latency - All Methods",
|
|
"description": "###### What this is:\n*Aggregate RPC handler latency across all methods (p75 and p99).*\n\n###### How it's computed:\n*Percentiles of the method-duration histogram over a 5-minute window.*\n\n###### Reading it:\n*p75 reflects typical responsiveness; p99 captures the slow tail.*\n\n###### Healthy range:\n*Sub-millisecond to low-millisecond for light commands; heavier commands run longer.*\n\n###### Watch for:\n*A rising p99 while p75 stays flat — a subset of calls degrading, often from expensive queries.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordRpcFinished`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 75
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "histogram_quantile(0.75, sum by (le, service_instance_id) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m])))",
|
|
"legendFormat": "p75 [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "histogram_quantile(0.99, sum by (le, service_instance_id) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m])))",
|
|
"legendFormat": "p99 [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "µs",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Duration (μs)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 16
|
|
},
|
|
{
|
|
"title": "Per-Method Latency (p99, Top 10 Slowest)",
|
|
"description": "###### What this is:\n*The ten slowest RPC methods by tail latency.*\n\n###### How it's computed:\n*p99 of each method's duration histogram over 5 minutes, top ten.*\n\n###### Reading it:\n*Surfaces which specific methods are expensive.*\n\n###### Healthy range:\n*Method-dependent; ledger/account queries are heavier than status calls.*\n\n###### Watch for:\n*A method whose p99 climbs over time, or an unexpectedly cheap method appearing here.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordRpcFinished`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 83
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["mean", "max"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "topk(10, histogram_quantile(0.99, sum by (le, method, service_instance_id) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m]))))",
|
|
"legendFormat": "{{method}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "µs",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Duration (μs)",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 17
|
|
},
|
|
{
|
|
"title": "RPC Error Ratio by Method",
|
|
"description": "###### What this is:\n*The methods with the highest error rates, for spotting failure hotspots.*\n\n###### How it's computed:\n*Per-second error rate over 5 minutes, per method, top ten.*\n\n###### Reading it:\n*Highlights where failures concentrate.*\n\n###### Healthy range:\n*Near zero.*\n\n###### Watch for:\n*One method with a persistently high error rate — malformed requests or targeted probing.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordRpcErrored`",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 91
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["mean", "max"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "topk(10, rate(rpc_method_errored_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=~\"$xrpl_node_role\", method=~\"$method\"}[$__rate_interval]) / (rate(rpc_method_started_total{service_instance_id=~\"$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\", method=~\"$method\"}[$__rate_interval]) > 0))",
|
|
"legendFormat": "{{method}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percentunit",
|
|
"min": 0,
|
|
"max": 1,
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Error Ratio",
|
|
"spanNulls": true,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.05
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.25
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 18
|
|
},
|
|
{
|
|
"title": "Current RPC Latency (p99 Gauge)",
|
|
"description": "###### What this is:\n*Current tail latency (p99) of RPC handling across all methods, as a live gauge.*\n\n###### How it's computed:\n*p99 of the method-duration histogram over the recent window.*\n\n###### Reading it:\n*A single at-a-glance number for current RPC responsiveness.*\n\n###### Healthy range:\n*Low-millisecond under normal load.*\n\n###### Watch for:\n*Sustained elevation, indicating the node is under query pressure.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordRpcFinished`",
|
|
"type": "gauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 99
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"orientation": "auto",
|
|
"showThresholdLabels": false,
|
|
"showThresholdMarkers": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"expr": "histogram_quantile(0.99, sum by (le) (rate(rpc_method_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", method=~\"$method\"}[5m])))",
|
|
"legendFormat": "p99 Latency"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "µs",
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 100000
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1000000
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 19
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["rpc"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "DS_PROMETHEUS",
|
|
"type": "datasource",
|
|
"label": "Prometheus",
|
|
"query": "prometheus",
|
|
"regex": "",
|
|
"current": {
|
|
"text": "grafanacloud-ripplex-prometheus",
|
|
"value": "dab0b23c-3010-43d0-be90-40a77dfe95cf"
|
|
},
|
|
"hide": 0,
|
|
"refresh": 1,
|
|
"includeAll": false,
|
|
"multi": false,
|
|
"options": []
|
|
},
|
|
{
|
|
"name": "service_name",
|
|
"label": "Service Name",
|
|
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
|
"type": "query",
|
|
"query": "label_values(service_name)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "xrpld",
|
|
"value": "xrpld"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "deployment_environment",
|
|
"label": "Environment",
|
|
"description": "Filter by deployment tier [local / ci / test / prod]",
|
|
"type": "query",
|
|
"query": "label_values(deployment_environment)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "xrpl_network_type",
|
|
"label": "Network",
|
|
"description": "Filter by XRPL network [mainnet / testnet / devnet / perf / unknown]",
|
|
"type": "query",
|
|
"query": "label_values(xrpl_network_type)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "xrpl_work_item",
|
|
"label": "Work Item",
|
|
"description": "Filter by perf-iac work item / ticket (e.g. RIPD-7455)",
|
|
"type": "query",
|
|
"query": "label_values(xrpl_work_item)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "xrpl_branch",
|
|
"label": "Branch",
|
|
"description": "Filter by comparison side (baseline:<ref>:<commit> / test:<ref>:<commit>)",
|
|
"type": "query",
|
|
"query": "label_values(xrpl_branch)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "xrpl_node_role",
|
|
"label": "Node Role",
|
|
"description": "Filter by node role (validator / peer)",
|
|
"type": "query",
|
|
"query": "label_values(xrpl_node_role)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "node",
|
|
"label": "Node",
|
|
"description": "Filter by rippled node (service.instance.id — e.g. Node-1)",
|
|
"type": "query",
|
|
"query": "label_values(target_info, service_instance_id)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "command",
|
|
"label": "RPC Command",
|
|
"description": "Filter by RPC command name (e.g., server_info, submit)",
|
|
"type": "query",
|
|
"query": "label_values(span_calls_total{span_name=~\"rpc.command.*\"}, command)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "method",
|
|
"label": "RPC Method",
|
|
"description": "Filter by RPC method",
|
|
"type": "query",
|
|
"query": "label_values(rpc_method_started_total, method)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "${DS_PROMETHEUS}"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "RPC Performance",
|
|
"uid": "rpc-performance",
|
|
"refresh": "10s",
|
|
"description": "What this shows: Per-command and per-method RPC performance: call rates, error rates, and latency distributions.\nUse it to: Identify slow or failing RPC commands and track client-facing request latency."
|
|
}
|