mirror of
https://github.com/XRPLF/rippled.git
synced 2026-08-22 23:00:55 +00:00
fd006ec3ac
Four defects found by a query-correctness audit of all 16 dashboards, all scoped to panels this branch owns. job-queue "Current Job Latency (p99 Gauge)": the histogram by-clause dropped service_instance_id, collapsing every node into one fleet-wide p99 and hiding a slow node. Measured: gauge read 1325us while the worst node was 1868us. The panel's displayName already referenced service_instance_id, so it was also rendering an empty label. Now groups by service_instance_id and xrpl_work_item, matching sibling panels 5, 6 and 7. ledger-data-sync "NodeStore Read Latency (Bottleneck Discriminator)": replaced clamp_min(<denominator>, 1) with (<denominator> > 0). clamp_min clamps the value, not just the zero case, so any node reading below 1/s got a fabricated denominator. Demonstrated with a zero-rate denominator: clamp_min invents 40.2/40.3/11.2/9.2 where the > 0 guard correctly returns no data. This panel is the bottleneck discriminator, read during a stall, which is exactly when the read rate collapses and the clamp is most wrong. Panels 21 and 23 carry the same defect but originate on phase-7 and are fixed there. node-health thresholds: percentunit fields are compared against the raw value, so a step of 80 needed 8000% and could never fire. Rescaled panels 74, 81 and 85 to 0.8. Panel 81 is a found-ratio where high is healthy, so its bands were also inverted. Note these three panels use palette-classic with thresholdsStyle off, so the steps are currently dormant rather than visibly wrong. node-health panels 81 and 85 descriptions: both described the multi-series panels they were split from. Panel 81 carried a byte-identical copy of panel 80's text, promising three plotted rate lines where it draws a single bounded ratio; panel 85's text described read-thread gauges absent from its expression. Rewritten to match the actual queries.
668 lines
34 KiB
JSON
668 lines
34 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"description": "What this shows: Per-job-type throughput, queue wait times, and execution times for the node's internal worker job queue.\nUse it to: Find job types that are backing up or running slowly and causing internal processing delays.",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Current Job Latency (p99 Gauge)",
|
|
"description": "###### What this is:\n*At-a-glance p99 of how long jobs wait in the queue and how long they run once started.*\n\n###### How it's computed:\n*99th percentile derived from the job wait-time and run-time histograms over the last 5 minutes.*\n\n###### Reading it:\n*Lower is better; green under 100ms, yellow to 1s, red beyond 1s.*\n\n###### Healthy range:\n*Wait and exec p99 under 100ms.*\n\n###### Watch for:\n*p99 wait climbing into the red, meaning worker threads are saturated and jobs are backing up.*\n\n###### Keywords:\n- **Job queue / job type** *(per node)* \u2014 xrpld's worker-thread pool; every unit of background work is enqueued under a named job type.\n- **Deferred job** *(per node)* \u2014 a job held back because its type is already at its concurrency limit; the leading indicator of queue backpressure.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobStarted / recordJobFinished`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#job-queue-job-type)",
|
|
"type": "gauge",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"reduceOptions": {
|
|
"calcs": ["lastNotNull"],
|
|
"fields": "",
|
|
"values": false
|
|
},
|
|
"orientation": "auto",
|
|
"showThresholdLabels": false,
|
|
"showThresholdMarkers": true
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\", handler=~\"$handler\"}[5m]))), \"series\", \"p99 Wait\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(histogram_quantile(0.99, sum by (le, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\", handler=~\"$handler\"}[5m]))), \"series\", \"p99 Exec\", \"\", \"\")"
|
|
}
|
|
],
|
|
"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": "\u00b5s",
|
|
"min": 0,
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 100000
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1000000
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 1
|
|
},
|
|
{
|
|
"title": "Job Throughput Rate (Per Second)",
|
|
"description": "###### What this is:\n*Rate of jobs queued, started, and finished across all job types.*\n\n###### How it's computed:\n*Per-second rate of each cumulative job counter over a 5-minute window.*\n\n###### Reading it:\n*Queued, started, and finished tracking together means the queue keeps up.*\n\n###### Healthy range:\n*Workload-dependent; the three rates should stay roughly equal.*\n\n###### Watch for:\n*Queued rate persistently above finished rate, which indicates a growing backlog.*\n\n###### Keywords:\n- **Job queue / job type** *(per node)* \u2014 xrpld's worker-thread pool; every unit of background work is enqueued under a named job type.\n- **Deferred job** *(per node)* \u2014 a job held back because its type is already at its concurrency limit; the leading indicator of queue backpressure.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobQueued / recordJobStarted / recordJobFinished`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#job-queue-job-type)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 8
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_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\", job_type=~\"$job_type\", handler=~\"$handler\"}[$__rate_interval])), \"series\", \"Queued/s\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_started_total{service_instance_id=~\"$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\", job_type=~\"$job_type\", handler=~\"$handler\"}[$__rate_interval])), \"series\", \"Started/s\", \"\", \"\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(sum by (service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_finished_total{service_instance_id=~\"$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\", job_type=~\"$job_type\", handler=~\"$handler\"}[$__rate_interval])), \"series\", \"Finished/s\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "suffix: jobs/s",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"axisLabel": "Jobs / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 2
|
|
},
|
|
{
|
|
"title": "Per-Job-Type Queued Rate",
|
|
"description": "###### What this is:\n*Rate of jobs entering the queue, broken down by job type (top 10).*\n\n###### How it's computed:\n*Per-second rate of the queued-job counter per job_type over a 5-minute window.*\n\n###### Reading it:\n*Identifies which job types generate the most queue activity.*\n\n###### Healthy range:\n*Workload-dependent.*\n\n###### Watch for:\n*A single job type surging unexpectedly, which can point to a flood of a particular request or peer message.*\n\n###### Keywords:\n- **Job queue / job type** *(per node)* \u2014 xrpld's worker-thread pool; every unit of background work is enqueued under a named job type.\n- **Deferred job** *(per node)* \u2014 a job held back because its type is already at its concurrency limit; the leading indicator of queue backpressure.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobQueued`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#job-queue-job-type)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 16
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["mean", "max"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(topk(10, sum by (job_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_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\", job_type=~\"$job_type\", handler=~\"$handler\"}[$__rate_interval]))), \"series\", \"$1\", \"job_type\", \"(.*)\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "suffix: jobs/s",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Jobs / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 3
|
|
},
|
|
{
|
|
"title": "Per-Job-Type Finish Rate",
|
|
"description": "###### What this is:\n*Rate of jobs completing, broken down by job type (top 10).*\n\n###### How it's computed:\n*Per-second rate of the finished-job counter per job_type over a 5-minute window.*\n\n###### Reading it:\n*Compare against the queued rate per type to spot which types are falling behind.*\n\n###### Healthy range:\n*Workload-dependent; should match the per-type queued rate.*\n\n###### Watch for:\n*A type whose finish rate lags its queued rate, revealing where the backlog concentrates.*\n\n###### Keywords:\n- **Job queue / job type** *(per node)* \u2014 xrpld's worker-thread pool; every unit of background work is enqueued under a named job type.\n- **Deferred job** *(per node)* \u2014 a job held back because its type is already at its concurrency limit; the leading indicator of queue backpressure.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobFinished`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#job-queue-job-type)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 24
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["mean", "max"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(topk(10, sum by (job_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_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\", job_type=~\"$job_type\", handler=~\"$handler\"}[$__rate_interval]))), \"series\", \"$1\", \"job_type\", \"(.*)\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "suffix: jobs/s",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Jobs / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 4
|
|
},
|
|
{
|
|
"title": "Job Queue Wait Time",
|
|
"description": "###### What this is:\n*How long jobs sit in the queue before a worker picks them up, split by job type (p75 typical, p99 tail).*\n\n###### How it's computed:\n*Percentiles derived from the job wait-time histogram over a 5-minute window, kept per job type. Limited to the ten types with the highest wait so the legend stays readable.*\n\n###### Reading it:\n*Lower is better. The legend names the job type, so a single slow queue is identifiable rather than hidden in an all-types average. A widening p75-to-p99 gap on one type signals occasional stalls there.*\n\n###### Healthy range:\n*Sub-millisecond to low-millisecond waits on an unloaded node.*\n\n###### Watch for:\n*Rising p99 wait on a capped type -- ledgerRequest, ledgerData and makeFetchPack have small concurrency limits, so they queue first. Cross-check the deferred gauge for that type.*\n\n###### Keywords:\n- **Job queue** *(per node)* \u2014 the worker pool that runs xrpld's background work; each unit of work is a job with a type.\n- **Dequeue wait** *(per node)* \u2014 time a job sits enqueued before a worker starts it, as distinct from how long it then runs.\n- **Concurrency limit** *(per node)* \u2014 the maximum number of jobs of one type allowed to run at once; work beyond it is deferred, not rejected.\n\n###### Computation boundary:\n*Result: Per node and job type \u2014 each series is one server's own value for one job type.*\n*Recorded in code as an OTel SDK histogram, then aggregated to percentiles by the Grafana query.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobStarted`\n\n###### References:\n[Job queue](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#job-queue-job-type) \u00b7 [Concurrency limit](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#concurrency-limit)\n",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 32
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(topk(10, histogram_quantile(0.75, sum by (le, job_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\", handler=~\"$handler\"}[5m])))), \"series\", \"p75 Wait $1\", \"job_type\", \"(.*)\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(topk(10, histogram_quantile(0.99, sum by (le, job_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_queued_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\", handler=~\"$handler\"}[5m])))), \"series\", \"p99 Wait $1\", \"job_type\", \"(.*)\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "\u00b5s",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Duration (\u00b5s)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 5
|
|
},
|
|
{
|
|
"title": "Job Execution Time",
|
|
"description": "###### What this is:\n*How long jobs run once started, split by job type (p75 typical, p99 tail).*\n\n###### How it's computed:\n*Percentiles derived from the job run-time histogram over a 5-minute window, kept per job type. Limited to the ten slowest types so the legend stays readable.*\n\n###### Reading it:\n*Lower is better. The legend names the job type, so an expensive job type is identifiable rather than averaged away. Stable p75 with a controlled p99 is healthy.*\n\n###### Healthy range:\n*Workload-dependent, but stable over time.*\n\n###### Watch for:\n*Growing execution times, which point to CPU pressure or expensive individual jobs.*\n\n###### Keywords:\n- **Job queue** *(per node)* \u2014 the worker pool that runs xrpld's background work; each unit of work is a job with a type.\n- **Execution time** *(per node)* \u2014 time a job spends running after a worker picks it up, excluding its queue wait.\n\n###### Computation boundary:\n*Result: Per node and job type \u2014 each series is one server's own value for one job type.*\n*Recorded in code as an OTel SDK histogram, then aggregated to percentiles by the Grafana query.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobFinished`\n\n###### References:\n[Job queue](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#job-queue-job-type)\n",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 32
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(topk(10, histogram_quantile(0.75, sum by (le, job_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\", handler=~\"$handler\"}[5m])))), \"series\", \"p75 Exec $1\", \"job_type\", \"(.*)\")"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(topk(10, histogram_quantile(0.99, sum by (le, job_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\", handler=~\"$handler\"}[5m])))), \"series\", \"p99 Exec $1\", \"job_type\", \"(.*)\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "\u00b5s",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Duration (\u00b5s)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 6
|
|
},
|
|
{
|
|
"title": "Per-Job-Type Execution Time (p99)",
|
|
"description": "###### What this is:\n*The 10 slowest job types ranked by p99 execution time.*\n\n###### How it's computed:\n*p99 derived from the run-time histogram per job_type over a 5-minute window, top 10 selected.*\n\n###### Reading it:\n*Highlights which job types cost the most CPU time at the tail.*\n\n###### Healthy range:\n*Workload-dependent.*\n\n###### Watch for:\n*A job type whose p99 grows over time, indicating a slow or degrading operation.*\n\n###### Keywords:\n- **Job queue / job type** *(per node)* \u2014 xrpld's worker-thread pool; every unit of background work is enqueued under a named job type.\n- **Deferred job** *(per node)* \u2014 a job held back because its type is already at its concurrency limit; the leading indicator of queue backpressure.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`recordJobFinished`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#job-queue-job-type)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 40
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
},
|
|
"legend": {
|
|
"displayMode": "table",
|
|
"placement": "right",
|
|
"calcs": ["mean", "max"]
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(topk(10, histogram_quantile(0.99, sum by (le, job_type, service_instance_id, xrpl_branch, xrpl_node_role, xrpl_work_item) (rate(job_running_us_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", xrpl_work_item=~\"$xrpl_work_item\", xrpl_branch=~\"$xrpl_branch\", xrpl_node_role=~\"$xrpl_node_role\", job_type=~\"$job_type\", handler=~\"$handler\"}[5m])))), \"series\", \"$1\", \"job_type\", \"(.*)\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "\u00b5s",
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 5,
|
|
"axisLabel": "Duration (\u00b5s)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 7
|
|
},
|
|
{
|
|
"title": "Transaction Overflow Rate",
|
|
"description": "###### What this is:\n*Rate at which transaction jobs are shed when the queue's transaction limit is exceeded.*\n\n###### How it's computed:\n*Per-second rate of the overflow counter over the dashboard's rate interval, scaled to per minute. The counter is observed from the overlay's cumulative overflow tally.*\n\n###### Reading it:\n*Near zero is healthy; a rising rate means the job queue is shedding transaction work under load.*\n\n###### Healthy range:\n*0 overflows per minute.*\n\n###### Watch for:\n*Any sustained non-zero rate \u2014 the node is dropping transaction jobs because the queue is saturated.*\n\n###### Keywords:\n- **Job queue / job type** *(per node)* \u2014 xrpld's worker-thread pool; every unit of background work is enqueued under a named job type.\n- **Transaction queue (TxQ)** *(per node)* \u2014 holds transactions that cannot enter the open ledger yet, ordered by fee level.\n\n###### Computation boundary:\n*Result: Per node \u2014 each series is one server's own value.*\n*Recorded in xrpld code as a native metric (beast::insight); the collector only forwards it; the Grafana query selects and aggregates it.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerParityCounters (observed from Overlay::getJqTransOverflow)`\n\n###### References:\n[Telemetry glossary](https://github.com/XRPLF/rippled/blob/develop/docs/telemetry-glossary.md#job-queue-job-type)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 48
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "label_replace(rate(jq_trans_overflow_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\"}[$__rate_interval]) * 60, \"series\", \"Overflows/min\", \"\", \"\")"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"displayName": "${__field.labels.series} [${__field.labels.service_instance_id} ${__field.labels.xrpl_branch} ${__field.labels.xrpl_node_role} ${__field.labels.xrpl_work_item}]",
|
|
"unit": "suffix: overflows/min",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 10
|
|
}
|
|
]
|
|
},
|
|
"custom": {
|
|
"axisLabel": "Overflows / Min",
|
|
"drawStyle": "line",
|
|
"lineWidth": 2,
|
|
"fillOpacity": 10,
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 3
|
|
},
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 8
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["node", "jobqueue"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "DS_PROMETHEUS",
|
|
"type": "datasource",
|
|
"label": "Prometheus",
|
|
"query": "prometheus",
|
|
"regex": "",
|
|
"current": {},
|
|
"hide": 0,
|
|
"refresh": 1,
|
|
"includeAll": false,
|
|
"multi": false,
|
|
"options": []
|
|
},
|
|
{
|
|
"name": "service_name",
|
|
"label": "Service Name",
|
|
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
|
"type": "query",
|
|
"query": "label_values(service_name)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "xrpld",
|
|
"value": "xrpld"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "deployment_environment",
|
|
"label": "Environment",
|
|
"description": "Filter by deployment tier [local / ci / test / prod]",
|
|
"type": "query",
|
|
"query": "label_values(deployment_environment)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__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
|
|
},
|
|
{
|
|
"name": "job_type",
|
|
"label": "Job Type",
|
|
"description": "Filter by job type",
|
|
"type": "query",
|
|
"query": "label_values(job_queued_total, job_type)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "handler",
|
|
"label": "Handler",
|
|
"description": "Filter by enqueueing handler (sanitised addJob name, e.g. RcvGetLedger)",
|
|
"type": "query",
|
|
"query": "label_values(job_queued_total, handler)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"timepicker": {},
|
|
"timezone": "browser",
|
|
"title": "Job Queue Analysis",
|
|
"uid": "job-queue",
|
|
"version": 1,
|
|
"refresh": "5s"
|
|
}
|