mirror of
https://github.com/XRPLF/rippled.git
synced 2026-08-22 06:40:53 +00:00
97089a3b6f
A repeating panel expands into one copy per network at view time and, with
maxPerRow=2, claims the whole row. The non-repeating panel paired beside it was
pushed to the next line but kept its stored x=12, so it rendered on the right
against an empty gap.
Two changes to how the layout is planned:
- a repeating panel gets a row to itself. It keeps w=12, so its copies still
tile two across inside that row.
- single-value panels are grouped to the top of each row section, so the
charts that follow pair with each other instead of being split up by an
interleaved repeat. Without this the gaps just become wasted half-rows.
Verified per dashboard: no panel lost, every targets block byte-identical, ids
1..N, no overlaps, and no row left with a gap on its left.
830 lines
30 KiB
JSON
830 lines
30 KiB
JSON
{
|
|
"annotations": {
|
|
"list": []
|
|
},
|
|
"description": "Client-facing RPC behavior and payment pathfinding cost on this node: request rates, response times and sizes, resource-limit warnings and drops, gRPC read-path load, and pathfinding request, compute, and discovery activity.",
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 1,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "RPC Request Rate [$xrpl_network_type]",
|
|
"description": "**What:** Rate of RPC requests handled, counting every HTTP and WebSocket call.\n**How it's computed:** Per-second rate of the RPC-requests counter over 5 minutes.\n**Reading it:** Tracks client demand on the node.\n**Healthy range:** workload-dependent.\n**Watch for:** Sudden sustained spikes (client surge or abusive polling) or a drop to zero (endpoint unavailable).\n**Source:** src/xrpld/rpc/detail/ServerHandler.cpp ServerHandler ctor",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "rate(rpc_requests_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
|
|
"interval": "15s",
|
|
"legendFormat": "Requests / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "reqps"
|
|
},
|
|
"overrides": []
|
|
},
|
|
"repeat": "xrpl_network_type",
|
|
"repeatDirection": "h",
|
|
"maxPerRow": 2,
|
|
"id": 1
|
|
},
|
|
{
|
|
"title": "RPC Response",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 10
|
|
},
|
|
"collapsed": false,
|
|
"panels": [],
|
|
"id": 2
|
|
},
|
|
{
|
|
"title": "RPC Response Time",
|
|
"description": "**What:** P95 and P50 of end-to-end RPC handler time (full HTTP handling, not just command execution).\n**How it's computed:** 95th and 50th percentiles over a 5-minute window.\n**Reading it:** Lower is better; P95 shows the slow tail.\n**Healthy range:** workload-dependent; most methods well under a second.\n**Watch for:** Rising P95 while request rate is flat (expensive queries or contention).\n**Source:** src/xrpld/rpc/detail/ServerHandler.cpp ServerHandler ctor",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 11
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P95 Response Time [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.5, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P50 Response Time [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Latency (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 3
|
|
},
|
|
{
|
|
"title": "RPC Response Size",
|
|
"description": "**⚠ Instrument mismatch — values unreliable.** Response size is recorded through the millisecond-scaled event histogram (rpc_size_milliseconds_bucket), so byte values saturate at the top time bucket (5000) and the percentiles are not true byte sizes. A dedicated byte-unit histogram is needed to fix this; tracked separately. Treat this panel as indicative only until then.\n\n**What:** P95 and P50 of RPC response payload size in bytes.\n**How it's computed:** 95th and 50th percentiles over the dashboard rate interval.\n**Reading it:** Larger responses cost more bandwidth and CPU to build.\n**Healthy range:** workload-dependent.\n**Watch for:** Large P95 (result-heavy queries such as broad account_tx, or API misuse).\n**Source:** src/xrpld/rpc/detail/ServerHandler.cpp ServerHandler ctor",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 11
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(rpc_size_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P95 Response Size [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.5, sum by (le, service_instance_id) (rate(rpc_size_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P50 Response Size [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "decbytes",
|
|
"custom": {
|
|
"axisLabel": "Size (Bytes)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 4
|
|
},
|
|
{
|
|
"title": "RPC Response Time Distribution",
|
|
"description": "**What:** RPC response-time spread shown as P50, P90, P95, and P99.\n**How it's computed:** Four quantiles of response time over a 5-minute window.\n**Reading it:** A wide gap between P50 and P99 signals a long latency tail.\n**Healthy range:** workload-dependent; quantiles clustered together.\n**Watch for:** P99 pulling far above P50 (bimodal latency or occasional very slow requests).\n**Source:** src/xrpld/rpc/detail/ServerHandler.cpp ServerHandler ctor",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 21
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.5, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P50 [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.9, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P90 [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P95 [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.99, sum by (le, service_instance_id) (rate(rpc_time_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P99 [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Latency (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 5
|
|
},
|
|
{
|
|
"title": "Pathfinding",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 31
|
|
},
|
|
"collapsed": false,
|
|
"panels": [],
|
|
"id": 6
|
|
},
|
|
{
|
|
"title": "Resource Warnings Rate [$xrpl_network_type]",
|
|
"description": "**What:** Rate of resource-limit warnings raised when a peer or client exceeds its usage warning threshold.\n**How it's computed:** Per-second rate of the warn counter over 5 minutes.\n**Reading it:** Occasional warnings are normal under load; a rising rate flags aggressive clients.\n**Healthy range:** workload-dependent; low.\n**Watch for:** A climbing warning rate (clients approaching limits, a precursor to drops).\n**Source:** include/xrpl/resource/detail/Logic.h Logic::Stats ctor",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 32
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "rate(warn_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
|
|
"interval": "15s",
|
|
"legendFormat": "Warnings / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "suffix: warnings/s",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.1
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 1
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"repeat": "xrpl_network_type",
|
|
"repeatDirection": "h",
|
|
"maxPerRow": 2,
|
|
"id": 7
|
|
},
|
|
{
|
|
"title": "Resource Drops Rate [$xrpl_network_type]",
|
|
"description": "**What:** Rate of resource drops: consumers disconnected or blocked for excessive usage.\n**How it's computed:** Per-second rate of the drop counter over 5 minutes.\n**Reading it:** Non-zero means the node is actively rejecting abusive connections.\n**Healthy range:** at or near zero.\n**Watch for:** Sustained non-zero drops (ongoing abuse or a misbehaving client/peer being throttled).\n**Source:** include/xrpl/resource/detail/Logic.h Logic::Stats ctor",
|
|
"type": "stat",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 42
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "rate(drop_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
|
|
"interval": "15s",
|
|
"legendFormat": "Drops / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "suffix: drops/s",
|
|
"thresholds": {
|
|
"steps": [
|
|
{
|
|
"color": "green",
|
|
"value": null
|
|
},
|
|
{
|
|
"color": "yellow",
|
|
"value": 0.01
|
|
},
|
|
{
|
|
"color": "red",
|
|
"value": 0.1
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"repeat": "xrpl_network_type",
|
|
"repeatDirection": "h",
|
|
"maxPerRow": 2,
|
|
"id": 8
|
|
},
|
|
{
|
|
"title": "Pathfinding Fast Duration",
|
|
"description": "**What:** P95 and P50 execution time of the fast pathfinding search (simplified, favoring speed over completeness).\n**How it's computed:** 95th and 50th percentiles over a 5-minute window.\n**Reading it:** Lower is better; fast pathfinding should stay quick.\n**Healthy range:** workload-dependent; typically well below full pathfinding.\n**Watch for:** Rising fast-path latency (pathfinding load or complex order books).\n**Source:** src/xrpld/rpc/detail/PathRequestManager.h ctor",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 52
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(pathfind_fast_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P95 Fast Pathfind [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.5, sum by (le, service_instance_id) (rate(pathfind_fast_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P50 Fast Pathfind [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 9
|
|
},
|
|
{
|
|
"title": "Pathfinding Full Duration",
|
|
"description": "**What:** P95 and P50 execution time of the full, exhaustive pathfinding search.\n**How it's computed:** 95th and 50th percentiles over a 5-minute window.\n**Reading it:** Full pathfinding is heavier and slower than fast mode.\n**Healthy range:** workload-dependent.\n**Watch for:** High or rising full-path latency (expensive path computation under subscription load).\n**Source:** src/xrpld/rpc/detail/PathRequestManager.h ctor",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 52
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(pathfind_full_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P95 Full Pathfind [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.5, sum by (le, service_instance_id) (rate(pathfind_full_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P50 Full Pathfind [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 10
|
|
},
|
|
{
|
|
"title": "gRPC (Spans)",
|
|
"type": "row",
|
|
"gridPos": {
|
|
"h": 1,
|
|
"w": 24,
|
|
"x": 0,
|
|
"y": 62
|
|
},
|
|
"collapsed": false,
|
|
"panels": [],
|
|
"id": 11
|
|
},
|
|
{
|
|
"title": "gRPC Request Rate by Method (Spans)",
|
|
"description": "**What:** Per-method gRPC call rate for the gRPC read API used by reporting and Clio.\n**How it's computed:** Per-second count of gRPC calls grouped by method.\n**Reading it:** Shows which gRPC methods are called and how often; only populated when the node serves gRPC.\n**Healthy range:** workload-dependent.\n**Watch for:** A single method spiking (heavy reporting load) or unexpected methods appearing.\n**Source:** src/xrpld/rpc/GRPCServer.cpp (gRPC method handlers)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 63
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (method, 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\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[$__rate_interval]))",
|
|
"interval": "15s",
|
|
"legendFormat": "{{method}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "suffix: calls/s",
|
|
"custom": {
|
|
"axisLabel": "Calls / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 12
|
|
},
|
|
{
|
|
"title": "gRPC Latency P95 by Method (Spans)",
|
|
"description": "**What:** P95 latency per gRPC method.\n**How it's computed:** 95th percentile of gRPC call duration per method over 5 minutes.\n**Reading it:** Identifies slow gRPC read paths.\n**Healthy range:** workload-dependent.\n**Watch for:** One method's P95 rising (expensive ledger reads or backend pressure).\n**Source:** src/xrpld/rpc/GRPCServer.cpp (gRPC method handlers)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 63
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, method, 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\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "{{method}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 13
|
|
},
|
|
{
|
|
"title": "gRPC Error Rate by Status (Spans)",
|
|
"description": "**What:** Rate of gRPC calls broken down by result status: success, error, resource-exhausted, failed-precondition.\n**How it's computed:** Per-second count of gRPC calls grouped by status.\n**Reading it:** Errors and resource-exhausted should be a small share.\n**Healthy range:** workload-dependent; mostly success.\n**Watch for:** Rising error or resource-exhausted rate (clients hitting limits or failing reads).\n**Source:** src/xrpld/rpc/GRPCServer.cpp (gRPC method handlers)",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 73
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (grpc_status, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"grpc\\\\..*\", grpc_status!=\"\"}[$__rate_interval]))",
|
|
"interval": "15s",
|
|
"legendFormat": "{{grpc_status}} [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "suffix: calls/s",
|
|
"custom": {
|
|
"axisLabel": "Calls / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 14
|
|
},
|
|
{
|
|
"title": "Pathfinding Compute Duration (Spans)",
|
|
"description": "**What:** P95 and P50 of per-request path computation time.\n**How it's computed:** 95th and 50th percentiles of path-computation duration over 5 minutes.\n**Reading it:** Complements the fast/full timers with per-request visibility; populated under book/path RPC load.\n**Healthy range:** workload-dependent.\n**Watch for:** Rising compute time (complex paths or heavy pathfinding demand).\n**Source:** src/xrpld/rpc/detail/PathRequest.cpp PathRequest::doUpdate",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 73
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.95, sum by (le, 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\", span_name=\"pathfind.compute\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P95 Compute [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "histogram_quantile(0.50, sum by (le, 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\", span_name=\"pathfind.compute\"}[5m])))",
|
|
"interval": "15s",
|
|
"legendFormat": "P50 Compute [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "ms",
|
|
"custom": {
|
|
"axisLabel": "Duration (ms)",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 15
|
|
},
|
|
{
|
|
"title": "Pathfinding Request & Discovery Rate (Spans)",
|
|
"description": "**What:** Rate of client path requests and of path-discovery passes.\n**How it's computed:** Per-second count of path-request and path-discovery operations.\n**Reading it:** Shows pathfinding demand and the discovery cost driver for subscription-heavy nodes.\n**Healthy range:** workload-dependent.\n**Watch for:** Discovery rate climbing (subscription load driving repeated path discovery).\n**Source:** src/xrpld/rpc/handlers/orderbook/PathFind.cpp doPathFind; src/xrpld/rpc/detail/PathRequest.cpp PathRequest::findPaths",
|
|
"type": "timeseries",
|
|
"gridPos": {
|
|
"h": 10,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 83
|
|
},
|
|
"options": {
|
|
"tooltip": {
|
|
"maxHeight": 600,
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
},
|
|
"targets": [
|
|
{
|
|
"datasource": {
|
|
"type": "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\", span_name=\"pathfind.request\"}[$__rate_interval]))",
|
|
"interval": "15s",
|
|
"legendFormat": "Requests / Sec [{{service_instance_id}}]"
|
|
},
|
|
{
|
|
"datasource": {
|
|
"type": "prometheus"
|
|
},
|
|
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"pathfind.discover\"}[$__rate_interval]))",
|
|
"interval": "15s",
|
|
"legendFormat": "Discoveries / Sec [{{service_instance_id}}]"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "suffix: operations/s",
|
|
"custom": {
|
|
"axisLabel": "Operations / Sec",
|
|
"spanNulls": 1800000,
|
|
"insertNulls": false,
|
|
"showPoints": "auto",
|
|
"pointSize": 5,
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"gradientMode": "none"
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"id": 16
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["rpc", "pathfinding"],
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "service_name",
|
|
"label": "Service Name",
|
|
"description": "Filter by service.name (e.g. xrpld, xrpld-validator)",
|
|
"type": "query",
|
|
"query": "label_values(service_name)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "xrpld",
|
|
"value": "xrpld"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "deployment_environment",
|
|
"label": "Environment",
|
|
"description": "Filter by deployment tier (local/ci/test/prod)",
|
|
"type": "query",
|
|
"query": "label_values(deployment_environment)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "xrpl_network_type",
|
|
"label": "Network",
|
|
"description": "Filter by XRPL network (mainnet/testnet/devnet)",
|
|
"type": "query",
|
|
"query": "label_values(xrpl_network_type)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "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": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "grpc_method",
|
|
"label": "gRPC Method",
|
|
"description": "Filter by gRPC method (GetLedger, GetLedgerData, GetLedgerDiff, GetLedgerEntry)",
|
|
"type": "query",
|
|
"query": "label_values(span_calls_total{span_name=~\"grpc\\\\..*\"}, method)",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "prometheus"
|
|
},
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"multi": true,
|
|
"refresh": 2,
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"time": {
|
|
"from": "now-1h",
|
|
"to": "now"
|
|
},
|
|
"title": "RPC & Pathfinding",
|
|
"uid": "rpc-pathfinding"
|
|
}
|