merge: pratik/otel-phase9-metric-gap-fill fix(SpanKind) into pratik/otel-phase10-workload-validation

# Conflicts:
#	docker/telemetry/otel-collector-config.yaml
#	docker/telemetry/xrpld-telemetry.cfg
This commit is contained in:
Pratik Mankawde
2026-05-14 15:59:39 +01:00
20 changed files with 1241 additions and 94 deletions

View File

@@ -772,5 +772,6 @@
"to": "now"
},
"title": "Consensus Health",
"uid": "rippled-consensus"
"uid": "rippled-consensus",
"refresh": "5s"
}

View File

@@ -349,5 +349,6 @@
"to": "now"
},
"title": "Ledger Operations",
"uid": "rippled-ledger-ops"
"uid": "rippled-ledger-ops",
"refresh": "5s"
}

View File

@@ -223,5 +223,6 @@
"to": "now"
},
"title": "Peer Network",
"uid": "rippled-peer-net"
"uid": "rippled-peer-net",
"refresh": "5s"
}

View File

@@ -339,5 +339,6 @@
"timezone": "browser",
"title": "Fee Market & TxQ",
"uid": "rippled-fee-market",
"version": 1
"version": 1,
"refresh": "5s"
}

View File

@@ -214,7 +214,7 @@
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 5,
"axisLabel": "Duration (μs)",
"axisLabel": "Duration (\u03bcs)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
@@ -273,7 +273,7 @@
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 5,
"axisLabel": "Duration (μs)",
"axisLabel": "Duration (\u03bcs)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
@@ -323,7 +323,68 @@
"drawStyle": "line",
"lineWidth": 1,
"fillOpacity": 5,
"axisLabel": "Duration (μs)",
"axisLabel": "Duration (\u03bcs)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
},
"color": {
"mode": "palette-classic"
}
},
"overrides": []
}
},
{
"title": "Transaction Overflow Rate",
"description": "Rate of job queue transaction overflows per minute. Overflows occur when the job queue's transaction limit is exceeded, causing transactions to be dropped. Non-zero values indicate the node is under heavy transaction load.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 32
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(xrpld_jq_trans_overflow_total{exported_instance=~\"$node\"}[5m]) * 60",
"legendFormat": "Overflows/min [{{exported_instance}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"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": true,
"insertNulls": false,
"showPoints": "auto",
@@ -391,5 +452,6 @@
"timezone": "browser",
"title": "Job Queue Analysis",
"uid": "rippled-job-queue",
"version": 1
"version": 1,
"refresh": "5s"
}

View File

@@ -202,13 +202,19 @@
{
"type": "value",
"options": {
"0": { "text": "No", "color": "green" }
"0": {
"text": "No",
"color": "green"
}
}
},
{
"type": "value",
"options": {
"1": { "text": "Yes", "color": "red" }
"1": {
"text": "Yes",
"color": "red"
}
}
}
],
@@ -387,5 +393,6 @@
"to": "now"
},
"title": "Peer Quality",
"uid": "rippled-peer-quality"
"uid": "rippled-peer-quality",
"refresh": "5s"
}

View File

@@ -214,7 +214,7 @@
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 5,
"axisLabel": "Duration (μs)",
"axisLabel": "Duration (\u03bcs)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
@@ -264,7 +264,7 @@
"drawStyle": "line",
"lineWidth": 1,
"fillOpacity": 5,
"axisLabel": "Duration (μs)",
"axisLabel": "Duration (\u03bcs)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
@@ -400,5 +400,6 @@
"timezone": "browser",
"title": "RPC Performance (OTel)",
"uid": "rippled-rpc-perf",
"version": 1
"version": 1,
"refresh": "5s"
}

View File

@@ -381,13 +381,19 @@
{
"type": "value",
"options": {
"0": { "text": "OK", "color": "green" }
"0": {
"text": "OK",
"color": "green"
}
}
},
{
"type": "value",
"options": {
"1": { "text": "BLOCKED", "color": "red" }
"1": {
"text": "BLOCKED",
"color": "red"
}
}
}
],
@@ -457,6 +463,139 @@
"overrides": []
}
},
{
"title": "UNL Blocked",
"description": "Whether the node's UNL (Unique Node List) is blocked (1=blocked, 0=normal). A UNL-blocked node cannot determine validator trust and may stop participating in consensus.",
"type": "stat",
"gridPos": {
"h": 8,
"w": 6,
"x": 0,
"y": 18
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_validator_health{metric=\"unl_blocked\",exported_instance=~\"$node\"}",
"legendFormat": "UNL Blocked [{{exported_instance}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"mappings": [
{
"type": "value",
"options": {
"0": {
"text": "OK",
"color": "green"
}
}
},
{
"type": "value",
"options": {
"1": {
"text": "BLOCKED",
"color": "red"
}
}
}
],
"thresholds": {
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 1
}
]
},
"custom": {}
},
"overrides": []
}
},
{
"title": "Agreement/Missed Counters (Rate)",
"description": "Rate of cumulative validation agreements and misses per minute. These monotonic counters complement the rolling window percentages above.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 18,
"x": 6,
"y": 18
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(xrpld_validation_agreements_total{exported_instance=~\"$node\"}[5m]) * 60",
"legendFormat": "Agreements/min [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(xrpld_validation_missed_total{exported_instance=~\"$node\"}[5m]) * 60",
"legendFormat": "Missed/min [{{exported_instance}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"custom": {
"axisLabel": "Per Minute",
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 10,
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
},
"color": {
"mode": "palette-classic"
}
},
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "Missed.*"
},
"properties": [
{
"id": "color",
"value": {
"mode": "fixed",
"fixedColor": "red"
}
}
]
}
]
}
},
{
"title": "--- Server State & Consensus ---",
"type": "row",
@@ -464,7 +603,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 18
"y": 26
},
"collapsed": false,
"panels": []
@@ -477,7 +616,7 @@
"h": 8,
"w": 6,
"x": 0,
"y": 19
"y": 27
},
"options": {
"tooltip": {
@@ -510,7 +649,7 @@
"h": 8,
"w": 18,
"x": 6,
"y": 19
"y": 27
},
"options": {
"tooltip": {
@@ -555,7 +694,7 @@
"h": 8,
"w": 8,
"x": 0,
"y": 27
"y": 35
},
"options": {
"tooltip": {
@@ -588,7 +727,7 @@
"h": 8,
"w": 8,
"x": 8,
"y": 27
"y": 35
},
"options": {
"tooltip": {
@@ -637,7 +776,7 @@
"h": 8,
"w": 8,
"x": 16,
"y": 27
"y": 35
},
"options": {
"tooltip": {
@@ -710,5 +849,6 @@
"to": "now"
},
"title": "Validator Health",
"uid": "rippled-validator-health"
"uid": "rippled-validator-health",
"refresh": "5s"
}

View File

@@ -328,7 +328,7 @@
{
"name": "node",
"label": "Node",
"description": "Filter by rippled node (service.instance.id e.g. Node-1)",
"description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
"type": "query",
"query": "label_values(traces_span_metrics_calls_total, exported_instance)",
"datasource": {
@@ -372,5 +372,6 @@
"to": "now"
},
"title": "RPC Performance",
"uid": "rippled-rpc-perf"
"uid": "rippled-rpc-perf",
"refresh": "5s"
}

View File

@@ -523,5 +523,6 @@
"to": "now"
},
"title": "Ledger Data & Sync (System Metrics)",
"uid": "rippled-system-ledger-sync"
"uid": "rippled-system-ledger-sync",
"refresh": "5s"
}

View File

@@ -655,6 +655,119 @@
}
]
}
},
{
"title": "Duplicate Traffic (Wasted Bandwidth)",
"description": "Rate of duplicate overlay traffic across transaction, proposal, and validation categories. Duplicate messages are messages the node has already seen and discards. High duplicate rates indicate inefficient message routing or network topology issues causing redundant relays.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 32
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_transactions_duplicate_Bytes_In{exported_instance=~\"$node\"}[5m])",
"legendFormat": "TX Duplicate In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_transactions_duplicate_Bytes_Out{exported_instance=~\"$node\"}[5m])",
"legendFormat": "TX Duplicate Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_proposals_duplicate_Bytes_In{exported_instance=~\"$node\"}[5m])",
"legendFormat": "Proposals Duplicate In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_proposals_duplicate_Bytes_Out{exported_instance=~\"$node\"}[5m])",
"legendFormat": "Proposals Duplicate Out"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_validations_duplicate_Bytes_In{exported_instance=~\"$node\"}[5m])",
"legendFormat": "Validations Duplicate In"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_validations_duplicate_Bytes_Out{exported_instance=~\"$node\"}[5m])",
"legendFormat": "Validations Duplicate Out"
}
],
"fieldConfig": {
"defaults": {
"unit": "Bps",
"custom": {
"axisLabel": "Throughput",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "All Traffic Categories (Detail)",
"description": "Top 15 traffic categories by inbound byte rate, excluding the total aggregate. Provides a detailed timeseries view of which overlay message types are consuming the most bandwidth over time. Complements the bar gauge snapshot view in the Overlay Traffic panel.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 32
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "topk(15, rate({__name__=~\"rippled_.*_Bytes_In\", __name__!~\"rippled_total_{exported_instance=~\"$node\"}.*\"}[5m]))",
"legendFormat": "{{__name__}}"
}
],
"fieldConfig": {
"defaults": {
"unit": "Bps",
"custom": {
"axisLabel": "Throughput",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
}
],
"schemaVersion": 39,
@@ -688,5 +801,6 @@
"to": "now"
},
"title": "Network Traffic (System Metrics)",
"uid": "rippled-system-network"
"uid": "rippled-system-network",
"refresh": "5s"
}

View File

@@ -162,7 +162,7 @@
],
"fieldConfig": {
"defaults": {
"unit": "µs",
"unit": "\u00b5s",
"custom": {
"axisLabel": "Duration",
"spanNulls": true,
@@ -289,7 +289,7 @@
},
{
"title": "Job Queue Depth",
"description": "Current number of jobs waiting in the job queue. Sourced from the job_count gauge (JobQueue.cpp:26). A sustained high value indicates the node cannot process work fast enough common during ledger replay or heavy RPC load.",
"description": "Current number of jobs waiting in the job queue. Sourced from the job_count gauge (JobQueue.cpp:26). A sustained high value indicates the node cannot process work fast enough \u2014 common during ledger replay or heavy RPC load.",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -535,6 +535,116 @@
"overrides": []
}
},
{
"title": "NodeStore Bytes Read/Written",
"description": "Cumulative bytes read and written by the NodeStore backend. Sourced from MetricsRegistry nodestore_state observable gauge with metric=node_written_bytes, node_read_bytes.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 41
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"node_read_bytes\"}",
"legendFormat": "Bytes Read [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"node_written_bytes\"}",
"legendFormat": "Bytes Written [{{exported_instance}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Bytes",
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 10
},
"color": {
"mode": "palette-classic"
}
},
"overrides": []
}
},
{
"title": "NodeStore Read Threads & Duration",
"description": "Read thread utilization and cumulative read duration. read_threads_running/read_threads_total shows thread saturation. node_reads_duration_us tracks cumulative time spent in read I/O. read_request_bundle tracks bundled read operations.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 41
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"read_threads_running\"}",
"legendFormat": "Read Threads Running [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"read_threads_total\"}",
"legendFormat": "Read Threads Total [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"read_request_bundle\"}",
"legendFormat": "Read Request Bundle [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"node_reads_duration_us\"}",
"legendFormat": "Read Duration (\u00b5s) [{{exported_instance}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"custom": {
"axisLabel": "Count / \u00b5s",
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 10
},
"color": {
"mode": "palette-classic"
}
},
"overrides": []
}
},
{
"title": "--- OTel: Cache Hit Rates ---",
"type": "row",
@@ -542,7 +652,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 41
"y": 49
},
"collapsed": false,
"panels": []
@@ -555,7 +665,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 42
"y": 50
},
"options": {
"tooltip": {
@@ -610,13 +720,13 @@
},
{
"title": "Cache Sizes",
"description": "TreeNode cache size, TreeNode track size, and FullBelow cache size. Sourced from MetricsRegistry cache_metrics observable gauge.",
"description": "TreeNode cache size, TreeNode track size, and FullBelow cache size. Sourced from MetricsRegistry cache_metrics observable gauge. Also includes AcceptedLedger (AL) cache size.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 42
"y": 50
},
"options": {
"tooltip": {
@@ -645,6 +755,13 @@
},
"expr": "xrpld_cache_metrics{exported_instance=~\"$node\", metric=\"fullbelow_size\"}",
"legendFormat": "FullBelow [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_cache_metrics{exported_instance=~\"$node\", metric=\"AL_size\"}",
"legendFormat": "AcceptedLedger Size [{{exported_instance}}]"
}
],
"fieldConfig": {
@@ -670,7 +787,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 50
"y": 58
},
"collapsed": false,
"panels": []
@@ -683,7 +800,7 @@
"h": 8,
"w": 24,
"x": 0,
"y": 51
"y": 59
},
"options": {
"tooltip": {
@@ -728,7 +845,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 59
"y": 67
},
"collapsed": false,
"panels": []
@@ -741,7 +858,7 @@
"h": 8,
"w": 6,
"x": 0,
"y": 60
"y": 68
},
"options": {
"tooltip": {
@@ -764,23 +881,48 @@
"mappings": [
{
"type": "value",
"options": { "0": { "text": "DISCONNECTED", "color": "red" } }
"options": {
"0": {
"text": "DISCONNECTED",
"color": "red"
}
}
},
{
"type": "value",
"options": { "1": { "text": "CONNECTED", "color": "orange" } }
"options": {
"1": {
"text": "CONNECTED",
"color": "orange"
}
}
},
{
"type": "value",
"options": { "2": { "text": "SYNCING", "color": "yellow" } }
"options": {
"2": {
"text": "SYNCING",
"color": "yellow"
}
}
},
{
"type": "value",
"options": { "3": { "text": "TRACKING", "color": "blue" } }
"options": {
"3": {
"text": "TRACKING",
"color": "blue"
}
}
},
{
"type": "value",
"options": { "4": { "text": "FULL", "color": "green" } }
"options": {
"4": {
"text": "FULL",
"color": "green"
}
}
}
],
"custom": {}
@@ -796,7 +938,7 @@
"h": 8,
"w": 6,
"x": 6,
"y": 60
"y": 68
},
"options": {
"tooltip": {
@@ -829,7 +971,7 @@
"h": 8,
"w": 6,
"x": 12,
"y": 60
"y": 68
},
"options": {
"tooltip": {
@@ -862,7 +1004,7 @@
"h": 8,
"w": 6,
"x": 18,
"y": 60
"y": 68
},
"options": {
"tooltip": {
@@ -895,7 +1037,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 68
"y": 76
},
"options": {
"tooltip": {
@@ -942,7 +1084,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 68
"y": 76
},
"options": {
"tooltip": {
@@ -968,6 +1110,80 @@
"overrides": []
}
},
{
"title": "Current Ledger Index",
"description": "Current open ledger sequence number. The gap between this and validated_ledger_seq represents ledgers in flight.",
"type": "stat",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 84
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_server_info{exported_instance=~\"$node\", metric=\"ledger_current_index\"}",
"legendFormat": "Current Ledger [{{exported_instance}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"custom": {}
},
"overrides": []
}
},
{
"title": "NuDB Storage Size",
"description": "NuDB backend file size in bytes. Sourced from MetricsRegistry storage_detail observable gauge. Tracks database growth over time.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 84
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "xrpld_storage_detail{exported_instance=~\"$node\", metric=\"nudb_bytes\"}",
"legendFormat": "NuDB Size [{{exported_instance}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"custom": {
"axisLabel": "Size",
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 10
},
"color": {
"mode": "palette-classic"
}
},
"overrides": []
}
},
{
"title": "--- OTel: Complete Ledgers & DB ---",
"type": "row",
@@ -975,7 +1191,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 76
"y": 92
},
"collapsed": false,
"panels": []
@@ -988,7 +1204,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 77
"y": 93
},
"options": {
"showHeader": true
@@ -1020,7 +1236,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 77
"y": 93
},
"options": {
"tooltip": {
@@ -1075,7 +1291,7 @@
"h": 8,
"w": 12,
"x": 0,
"y": 85
"y": 101
},
"options": {
"tooltip": {
@@ -1108,7 +1324,7 @@
"h": 8,
"w": 12,
"x": 12,
"y": 85
"y": 101
},
"options": {
"tooltip": {
@@ -1147,7 +1363,7 @@
"h": 1,
"w": 24,
"x": 0,
"y": 93
"y": 109
},
"collapsed": false,
"panels": []
@@ -1160,7 +1376,7 @@
"h": 8,
"w": 6,
"x": 0,
"y": 94
"y": 110
},
"options": {
"tooltip": {
@@ -1193,7 +1409,7 @@
"h": 8,
"w": 6,
"x": 6,
"y": 94
"y": 110
},
"options": {
"tooltip": {
@@ -1226,7 +1442,7 @@
"h": 8,
"w": 6,
"x": 12,
"y": 94
"y": 110
},
"options": {
"tooltip": {
@@ -1259,7 +1475,7 @@
"h": 8,
"w": 6,
"x": 18,
"y": 94
"y": 110
},
"options": {
"tooltip": {
@@ -1308,7 +1524,7 @@
"h": 8,
"w": 24,
"x": 0,
"y": 102
"y": 118
},
"options": {
"tooltip": {
@@ -1344,6 +1560,497 @@
},
"overrides": []
}
},
{
"title": "--- Extended Metrics (Recovered from Phase 6) ---",
"type": "row",
"gridPos": {
"h": 1,
"w": 24,
"x": 0,
"y": 32
},
"collapsed": false,
"panels": []
},
{
"title": "Key Jobs Execution Time",
"description": "Execution time for critical job types at the selected quantile. Sourced from per-job-type events in JobTypeData (JobTypeData.h:48). Shows how long key consensus, transaction, and maintenance jobs take to execute. Spikes indicate processing bottlenecks.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 33
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_acceptLedger{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Accept Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_advanceLedger{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Advance Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_transaction{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Transaction [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_writeObjects{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Write Objects [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_heartbeat{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Heartbeat [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_sweep{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Sweep [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_trustedValidation{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Trusted Validation [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_trustedProposal{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Trusted Proposal [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_publishNewLedger{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Publish New Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_clientRPC{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Client RPC [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledgerData{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Ledger Data [{{quantile}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"axisLabel": "Duration (ms)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "Key Jobs Dequeue Wait Time",
"description": "Time spent waiting in the job queue before execution for critical job types. Sourced from per-job-type dequeue events (JobTypeData.h:47). High dequeue times indicate the job queue is backlogged and jobs are waiting too long to be scheduled.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 33
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_acceptLedger_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Accept Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_advanceLedger_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Advance Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_transaction_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Transaction [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_writeObjects_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Write Objects [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_heartbeat_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Heartbeat [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_sweep_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Sweep [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_trustedValidation_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Trusted Validation [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_trustedProposal_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Trusted Proposal [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_publishNewLedger_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Publish New Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_clientRPC_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Client RPC [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledgerData_q{quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "Ledger Data [{{quantile}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"axisLabel": "Wait Time (ms)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "FullBelowCache Size",
"description": "Number of entries in the FullBelowCache. Sourced from the TaggedCache size gauge (TaggedCache.h:183) for the Node family full below cache (NodeFamily.cpp:29). This cache tracks which SHAMap nodes have all children present locally, avoiding redundant fetches during ledger acquisition.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 41
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_Node_family_full_below_cache_size{exported_instance=~\"$node\"}",
"legendFormat": "FullBelowCache Size"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Entries",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "FullBelowCache Hit Rate",
"description": "Hit rate percentage for the FullBelowCache. Sourced from the TaggedCache hit_rate gauge (TaggedCache.h:184). A high hit rate means the node is efficiently reusing cached knowledge about complete SHAMap subtrees. Low hit rates during steady state warrant investigation.",
"type": "gauge",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 41
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_Node_family_full_below_cache_hit_rate{exported_instance=~\"$node\"}",
"legendFormat": "Hit Rate"
}
],
"fieldConfig": {
"defaults": {
"unit": "percent",
"min": 0,
"max": 100,
"thresholds": {
"steps": [
{
"color": "red",
"value": null
},
{
"color": "yellow",
"value": 25
},
{
"color": "green",
"value": 50
}
]
}
},
"overrides": []
}
},
{
"title": "Ledger Publish Gap",
"description": "Difference between published and validated ledger ages. Computed as Published_Ledger_Age minus Validated_Ledger_Age. A value near zero means the publish pipeline keeps up with validation. A growing gap indicates the publish pipeline is falling behind, potentially causing stale data for subscribers.",
"type": "stat",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 49
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_LedgerMaster_Published_Ledger_Age{exported_instance=~\"$node\"} - rippled_LedgerMaster_Validated_Ledger_Age{exported_instance=~\"$node\"}",
"legendFormat": "Publish Gap"
}
],
"fieldConfig": {
"defaults": {
"unit": "s",
"thresholds": {
"steps": [
{
"color": "green",
"value": null
},
{
"color": "yellow",
"value": 5
},
{
"color": "red",
"value": 10
}
]
}
},
"overrides": []
}
},
{
"title": "State Duration Rate (Full vs Tracking)",
"description": "Rate of change of time spent in Full and Tracking operating modes, normalized to seconds. Sourced from State_Accounting duration gauges (NetworkOPs.cpp:774-778). In steady state the Full duration rate should be close to 1.0 (gaining one second of Full-mode time per wall-clock second). A drop below 1.0 means the node is spending time in other modes.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 49
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_State_Accounting_Full_duration{exported_instance=~\"$node\"}[5m]) / 1000000",
"legendFormat": "Full Mode Rate"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_State_Accounting_Tracking_duration{exported_instance=~\"$node\"}[5m]) / 1000000",
"legendFormat": "Tracking Mode Rate"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Rate (s/s)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "All Jobs Execution Time (Detail)",
"description": "Execution time for ALL non-special job types at the selected quantile. Shows the complete picture of job execution performance. Use the Key Jobs panel for a focused view of the most critical jobs.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 57
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "{__name__=~\"rippled_(makeFetchPack|publishAcqLedger|untrustedValidation|manifest|localTransaction|ledgerReplayRequest|ledgerRequest|untrustedProposal|ledgerReplayTask|ledgerData|clientCommand|clientSubscribe|clientFeeChange|clientConsensus|clientAccountHistory|clientRPC|clientWebsocket|RPC|updatePaths|transaction|batch|advanceLedger|publishNewLedger|fetchTxnData|writeAhead|trustedValidation|writeObjects|acceptLedger|trustedProposal|sweep|clusterReport|heartbeat|administration|handleHaveTransactions|doTransactions)\", quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "{{__name__}} [{{quantile}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"axisLabel": "Duration (ms)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
},
{
"title": "All Jobs Dequeue Wait (Detail)",
"description": "Dequeue wait time for ALL non-special job types at the selected quantile. Shows the complete picture of job queue waiting times. High wait times across many job types indicate systemic job queue congestion.",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 24,
"x": 0,
"y": 65
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus"
},
"expr": "{__name__=~\"rippled_(makeFetchPack_q|publishAcqLedger_q|untrustedValidation_q|manifest_q|localTransaction_q|ledgerReplayRequest_q|ledgerRequest_q|untrustedProposal_q|ledgerReplayTask_q|ledgerData_q|clientCommand_q|clientSubscribe_q|clientFeeChange_q|clientConsensus_q|clientAccountHistory_q|clientRPC_q|clientWebsocket_q|RPC_q|updatePaths_q|transaction_q|batch_q|advanceLedger_q|publishNewLedger_q|fetchTxnData_q|writeAhead_q|trustedValidation_q|writeObjects_q|acceptLedger_q|trustedProposal_q|sweep_q|clusterReport_q|heartbeat_q|administration_q|handleHaveTransactions_q|doTransactions_q)\", quantile=\"$quantile\", exported_instance=~\"$node\"}",
"legendFormat": "{{__name__}} [{{quantile}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "ms",
"custom": {
"axisLabel": "Wait Time (ms)",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
}
}
],
"schemaVersion": 39,
@@ -1397,5 +2104,6 @@
"to": "now"
},
"title": "Node Health (System Metrics)",
"uid": "rippled-system-node-health"
"uid": "rippled-system-node-health",
"refresh": "5s"
}

View File

@@ -583,5 +583,6 @@
"to": "now"
},
"title": "Overlay Traffic Detail (System Metrics)",
"uid": "rippled-system-overlay-detail"
"uid": "rippled-system-overlay-detail",
"refresh": "5s"
}

View File

@@ -413,5 +413,6 @@
"to": "now"
},
"title": "RPC & Pathfinding (System Metrics)",
"uid": "rippled-system-rpc"
"uid": "rippled-system-rpc",
"refresh": "5s"
}

View File

@@ -147,8 +147,8 @@
"datasource": {
"type": "prometheus"
},
"expr": "sum by (xrpl_tx_suppressed, exported_instance) (rate(traces_span_metrics_calls_total{span_name=\"tx.receive\", exported_instance=~\"$node\"}[$__rate_interval]))",
"legendFormat": "Suppressed={{xrpl_tx_suppressed}} [{{exported_instance}}]"
"expr": "sum by (suppressed, exported_instance) (rate(traces_span_metrics_calls_total{span_name=\"tx.receive\", exported_instance=~\"$node\"}[$__rate_interval]))",
"legendFormat": "Suppressed={{suppressed}} [{{exported_instance}}]"
}
],
"fieldConfig": {
@@ -336,7 +336,7 @@
{
"name": "node",
"label": "Node",
"description": "Filter by rippled node (service.instance.id e.g. Node-1)",
"description": "Filter by rippled node (service.instance.id \u2014 e.g. Node-1)",
"type": "query",
"query": "label_values(traces_span_metrics_calls_total, exported_instance)",
"datasource": {
@@ -380,5 +380,6 @@
"to": "now"
},
"title": "Transaction Overview",
"uid": "rippled-transactions"
"uid": "rippled-transactions",
"refresh": "5s"
}

View File

@@ -116,16 +116,16 @@ datasources:
operator: "="
scope: span
type: dynamic
# Phase 2: Node health filters (Task 2.8)
# Phase 2: Node health filters (Task 2.8) — resource attributes
- id: node-amendment-blocked
tag: xrpl.node.amendment_blocked
operator: "="
scope: span
scope: resource
type: static
- id: node-server-state
tag: xrpl.node.server_state
operator: "="
scope: span
scope: resource
type: dynamic
# Phase 3: Transaction tracing filters
- id: tx-hash
@@ -134,12 +134,12 @@ datasources:
scope: span
type: static
- id: tx-origin
tag: xrpl.tx.local
tag: local
operator: "="
scope: span
type: dynamic
- id: tx-status
tag: xrpl.tx.status
tag: tx_status
operator: "="
scope: span
type: dynamic
@@ -155,42 +155,42 @@ datasources:
scope: span
type: dynamic
- id: consensus-ledger-seq
tag: xrpl.consensus.ledger.seq
tag: xrpl.ledger.seq
operator: "="
scope: span
type: static
- id: consensus-close-time-correct
tag: xrpl.consensus.close_time_correct
tag: close_time_correct
operator: "="
scope: span
type: dynamic
- id: consensus-state
tag: xrpl.consensus.state
tag: consensus_state
operator: "="
scope: span
type: dynamic
- id: consensus-close-resolution
tag: xrpl.consensus.close_resolution_ms
tag: close_resolution_ms
operator: "="
scope: span
type: dynamic
- id: consensus-proposers
tag: xrpl.consensus.proposers
tag: proposers
operator: "="
scope: span
type: dynamic
- id: consensus-result
tag: xrpl.consensus.result
tag: consensus_result
operator: "="
scope: span
type: dynamic
- id: consensus-mode-old
tag: xrpl.consensus.mode.old
tag: mode_old
operator: "="
scope: span
type: dynamic
- id: consensus-mode-new
tag: xrpl.consensus.mode.new
tag: mode_new
operator: "="
scope: span
type: dynamic
@@ -201,17 +201,17 @@ datasources:
type: static
# Phase 3/4: Additional transaction and queue filters
- id: tx-path
tag: xrpl.tx.path
tag: path
operator: "="
scope: span
type: dynamic
- id: tx-suppressed
tag: xrpl.tx.suppressed
tag: suppressed
operator: "="
scope: span
type: dynamic
- id: peer-version
tag: xrpl.peer.version
tag: peer_version
operator: "="
scope: span
type: dynamic

View File

@@ -69,9 +69,9 @@ connectors:
- name: xrpl.consensus.mode
- name: close_time_correct
- name: local
- name: xrpl.tx.suppressed
- name: xrpl.peer.proposal.trusted
- name: xrpl.peer.validation.trusted
- name: suppressed
- name: proposal_trusted
- name: validation_trusted
exporters:
debug:

View File

@@ -0,0 +1,11 @@
# Devnet validator list configuration.
#
# Uses the Devnet validator list publisher operated by Ripple.
# This fetches the current set of trusted validators for the
# XRP Ledger Devnet automatically.
[validator_list_sites]
https://vl.devnet.rippletest.net
[validator_list_keys]
EDBB54B0D9AEE071BB37784AF5A9E7CC49AC7A0EFCE868C54532BCB966B9CFC13B

View File

@@ -1,17 +1,25 @@
# Standalone xrpld configuration with OpenTelemetry enabled.
# xrpld configuration for Devnet with full OpenTelemetry tracing.
#
# Connects to the XRP Ledger Devnet and exercises ALL instrumented
# workflows: RPC, transactions, consensus, peer overlay, ledger ops,
# and pathfinding.
#
# Usage:
# 1. Start the observability stack:
# docker compose -f docker/telemetry/docker-compose.yml up -d
# 2. Run xrpld in standalone mode:
# ./xrpld --conf docker/telemetry/xrpld-telemetry.cfg -a --start
# 3. Send RPC commands to exercise tracing:
# 2. Run xrpld:
# ./xrpld --conf docker/telemetry/xrpld-telemetry.cfg
# 3. Wait for sync (server_state=full), then exercise workflows:
# curl -s http://localhost:5005 -d '{"method":"server_info"}'
# 4. View traces in Grafana Explore -> Tempo: http://localhost:3000
# --- Server ports -----------------------------------------------------------
[server]
port_rpc_admin_local
port_ws_admin_local
port_ws_public
port_peer
[port_rpc_admin_local]
port = 5005
@@ -25,29 +33,90 @@ ip = 127.0.0.1
admin = 127.0.0.1
protocol = ws
[port_ws_public]
port = 6005
ip = 0.0.0.0
protocol = ws
[port_peer]
port = 51235
ip = 0.0.0.0
protocol = peer
# --- Network ----------------------------------------------------------------
[network_id]
devnet
[ips]
s.devnet.rippletest.net 51235
[validators_file]
validators-devnet.txt
[peer_private]
0
[peers_max]
21
# --- Pathfinding (exercises ripple_path_find / path_find workflows) ---------
[path_search]
7
[path_search_fast]
2
[path_search_max]
10
# --- Signing (allows sign/sign_for RPC for test tx submission) --------------
[signing_support]
true
# --- Database ---------------------------------------------------------------
[node_db]
type=NuDB
path=docker/telemetry/data/nudb
online_delete=256
online_delete=2000
advisory_delete=0
[database_path]
docker/telemetry/data
[ledger_history]
1000
# --- Logging ----------------------------------------------------------------
[debug_logfile]
docker/telemetry/data/debug.log
/tmp/xrpld-integration/devnet/debug.log
[rpc_startup]
{ "command": "log_level", "severity": "debug" }
# --- SSL --------------------------------------------------------------------
[ssl_verify]
0
# --- OpenTelemetry tracing ---
# --- Insight (native OTel metrics via beast::insight) -----------------------
[insight]
server=otel
endpoint=http://localhost:4318/v1/metrics
prefix=rippled
# --- OpenTelemetry tracing --------------------------------------------------
[telemetry]
enabled=1
service_instance_id=xrpld-standalone
service_instance_id=xrpld-devnet
endpoint=http://localhost:4318/v1/traces
metrics_endpoint=http://localhost:4318/v1/metrics
exporter=otlp_http
sampling_ratio=1.0
batch_size=512
@@ -56,5 +125,5 @@ max_queue_size=2048
trace_rpc=1
trace_transactions=1
trace_consensus=1
trace_peer=0
trace_peer=1
trace_ledger=1

View File

@@ -142,6 +142,32 @@ isCategoryEnabled(Telemetry const& tel, TraceCategory cat)
return false; // unreachable, silences compiler warning
}
namespace {
// Map a TraceCategory to an OTel SpanKind so Tempo's service-graph /
// RED metrics see the correct direction. RPC spans are emitted at the
// server entry point (handler dispatch), Peer spans at inbound-message
// receipt. Transactions / Consensus / Ledger are internal processing
// and keep the default kInternal.
otel_trace::SpanKind
categoryToSpanKind(TraceCategory cat)
{
switch (cat)
{
case TraceCategory::Rpc:
return otel_trace::SpanKind::kServer;
case TraceCategory::Peer:
return otel_trace::SpanKind::kConsumer;
case TraceCategory::Transactions:
case TraceCategory::Consensus:
case TraceCategory::Ledger:
return otel_trace::SpanKind::kInternal;
}
return otel_trace::SpanKind::kInternal; // unreachable
}
} // namespace
SpanGuard
SpanGuard::span(TraceCategory cat, std::string_view prefix, std::string_view name)
{
@@ -149,7 +175,7 @@ SpanGuard::span(TraceCategory cat, std::string_view prefix, std::string_view nam
if (!tel || !tel->isEnabled() || !isCategoryEnabled(*tel, cat))
return {};
auto fullName = std::string(prefix) + "." + std::string(name);
return SpanGuard(std::make_unique<Impl>(tel->startSpan(fullName)));
return SpanGuard(std::make_unique<Impl>(tel->startSpan(fullName, categoryToSpanKind(cat))));
}
// ===== Child / linked span creation ========================================