ARCHIVE/rippled
1
0
Fork 0
mirror of https://github.com/XRPLF/rippled.git synced 2026-07-23 15:10:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'pratik/otel-phase9-metric-gap-fill' into pratik/otel-phase10-workload-validation

Browse Source 
# Conflicts:
#	docker/telemetry/grafana/dashboards/fee-market.json
#	docker/telemetry/grafana/dashboards/transaction-overview.json
#	src/xrpld/telemetry/MetricsRegistry.h
This commit is contained in:
Pratik Mankawde
2026-07-10 17:31:39 +01:00
parent e6946d525e eb502d6eea
commit 945aba0388
16 changed files with 553 additions and 442 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
docker/telemetry/grafana/dashboards/consensus-health.json
View File

@@ -30,7 +30,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.validation.send\"}[5m]))",
"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\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.validation.send\"}[$__rate_interval]))",
"legendFormat": "Validations / Sec [{{service_instance_id}}]"
}
],
@@ -64,7 +64,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (consensus_mode, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[5m]))",
"expr": "sum by (consensus_mode, 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\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[$__rate_interval]))",
"legendFormat": "{{consensus_mode}} [{{service_instance_id}}]"
}
],
@@ -105,7 +105,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.proposal.send\"}[5m]))",
"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\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.proposal.send\"}[$__rate_interval]))",
"legendFormat": "Proposals / Sec [{{service_instance_id}}]"
}
],
@@ -146,7 +146,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\"}[$__rate_interval]))",
"legendFormat": "Accepts / Sec [{{service_instance_id}}]"
},
{
@@ -154,7 +154,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.ledger_close\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.ledger_close\"}[$__rate_interval]))",
"legendFormat": "Closes / Sec [{{service_instance_id}}]"
}
],
@@ -195,7 +195,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.validation.send\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.validation.send\"}[$__rate_interval]))",
"legendFormat": "Validations / Sec [{{service_instance_id}}]"
},
{
@@ -203,7 +203,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.ledger_close\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.ledger_close\"}[$__rate_interval]))",
"legendFormat": "Closes / Sec [{{service_instance_id}}]"
}
],
@@ -853,7 +853,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (consensus_state) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\", consensus_state!=\"\"}[5m]))",
"expr": "sum by (consensus_state) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\", consensus_state!=\"\"}[$__rate_interval]))",
"legendFormat": "{{consensus_state}}"
}
],
@@ -917,7 +917,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\", consensus_state=\"moved_on\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\", consensus_state=\"moved_on\"}[$__rate_interval]))",
"legendFormat": "moved_on [{{service_instance_id}}]"
},
{
@@ -925,7 +925,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\", consensus_state=\"expired\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\", consensus_state=\"expired\"}[$__rate_interval]))",
"legendFormat": "expired [{{service_instance_id}}]"
}
],
@@ -966,7 +966,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.check\", consensus_stalled=\"true\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.check\", consensus_stalled=\"true\"}[$__rate_interval]))",
"legendFormat": "Stalled [{{service_instance_id}}]"
},
{
@@ -974,7 +974,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.check\", consensus_stalled=\"false\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.check\", consensus_stalled=\"false\"}[$__rate_interval]))",
"legendFormat": "Not Stalled [{{service_instance_id}}]"
}
],
@@ -1015,7 +1015,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (mode_new, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.mode_change\"}[5m]))",
"expr": "sum by (mode_new, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.mode_change\"}[$__rate_interval]))",
"legendFormat": "{{mode_new}} [{{service_instance_id}}]"
}
],
@@ -1056,7 +1056,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (reason, service_instance_id) (rate(ledger_history_mismatch_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]))",
"expr": "sum by (reason, service_instance_id) (rate(ledger_history_mismatch_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "{{reason}} [{{service_instance_id}}]"
}
],

91
docker/telemetry/grafana/dashboards/fee-market.json
View File

@@ -320,12 +320,12 @@
}
},
{
"title": "Load Factor Attribution (Stacked Components)",
"description": "###### What this is:\n*The stacked contribution of each load-factor component (fee escalation, queue, local, net, cluster) to the effective transaction cost.*\n\n###### How it's computed:\n*Instantaneous gauge readings of each component stacked to show relative share.*\n\n###### Reading it:\n*The tallest band identifies which component is driving the fee, detail the aggregate load factor hides.*\n\n###### Healthy range:\n*Thin bands near 1.0 total under normal traffic.*\n\n###### Watch for:\n*One band dominating during a fee spike, revealing the specific driver of elevated cost.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLoadFactorGauge`",
"title": "Queue Abandonment Rate (Expired)",
"description": "###### What this is:\n*Transactions dropped from the queue because their last-ledger deadline passed before they could be included.*\n\n###### How it's computed:\n*Per-second rate of the cumulative expired-transaction counter over the dashboard's rate interval.*\n\n###### Reading it:\n*Near zero is healthy; a rising rate means submitters under-bid the escalating fee and their transactions timed out.*\n\n###### Healthy range:\n*Near 0 expirations per second.*\n\n###### Watch for:\n*Sustained expiry rate, a demand-frustration signal often coinciding with fee spikes or spam that crowds out honest traffic.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementTxqExpired (caller TxQ.cpp)`",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 24,
"w": 12,
"x": 0,
"y": 24
},
@@ -341,84 +341,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "load_factor_metrics{metric=\"load_factor_fee_escalation\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"legendFormat": "Fee Escalation [{{service_instance_id}}]"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "load_factor_metrics{metric=\"load_factor_fee_queue\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"legendFormat": "Fee Queue [{{service_instance_id}}]"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "load_factor_metrics{metric=\"load_factor_local\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"legendFormat": "Local [{{service_instance_id}}]"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "load_factor_metrics{metric=\"load_factor_net\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"legendFormat": "Net [{{service_instance_id}}]"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "load_factor_metrics{metric=\"load_factor_cluster\",service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"legendFormat": "Cluster [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"custom": {
"axisLabel": "Load Factor Multiplier",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3,
"stacking": {
"mode": "normal",
"group": "A"
},
"fillOpacity": 30
}
},
"overrides": []
}
},
{
"title": "Queue Abandonment Rate (Expired)",
"description": "###### What this is:\n*Transactions dropped from the queue because their last-ledger deadline passed before they could be included.*\n\n###### How it's computed:\n*Per-second rate of the cumulative expired-transaction counter over a 5-minute window.*\n\n###### Reading it:\n*Near zero is healthy; a rising rate means submitters under-bid the escalating fee and their transactions timed out.*\n\n###### Healthy range:\n*Near 0 expirations per second.*\n\n###### Watch for:\n*Sustained expiry rate, a demand-frustration signal often coinciding with fee spikes or spam that crowds out honest traffic.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementTxqExpired (caller TxQ.cpp)`",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 32
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(txq_expired_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(txq_expired_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "Expired / Sec [{{service_instance_id}}]"
}
],
@@ -438,13 +361,13 @@
},
{
"title": "Queue Admission Rejections (Dropped)",
"description": "###### What this is:\n*Transactions refused entry to the queue, broken down by reason such as queue_full.*\n\n###### How it's computed:\n*Per-second rate of the cumulative dropped-transaction counter over a 5-minute window, split by reason.*\n\n###### Reading it:\n*Near zero is healthy; queue_full rejections mean the queue is at capacity and applying backpressure.*\n\n###### Healthy range:\n*Near 0 rejections per second.*\n\n###### Watch for:\n*A burst of queue_full drops, distinct from expiry, indicating the node is being flooded faster than it can drain.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementTxqDropped (caller TxQ.cpp)`",
"description": "###### What this is:\n*Transactions refused entry to the queue, broken down by reason such as queue_full.*\n\n###### How it's computed:\n*Per-second rate of the cumulative dropped-transaction counter over the dashboard's rate interval, split by reason.*\n\n###### Reading it:\n*Near zero is healthy; queue_full rejections mean the queue is at capacity and applying backpressure.*\n\n###### Healthy range:\n*Near 0 rejections per second.*\n\n###### Watch for:\n*A burst of queue_full drops, distinct from expiry, indicating the node is being flooded faster than it can drain.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`incrementTxqDropped (caller TxQ.cpp)`",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 32
"y": 24
},
"options": {
"tooltip": {
@@ -458,7 +381,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (reason, service_instance_id) (rate(txq_dropped_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]))",
"expr": "sum by (reason, service_instance_id) (rate(txq_dropped_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "{{reason}} [{{service_instance_id}}]"
}
],

14
docker/telemetry/grafana/dashboards/job-queue.json
View File

@@ -95,7 +95,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(job_queued_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(job_queued_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[$__rate_interval]))",
"legendFormat": "Queued/s [{{service_instance_id}}]"
},
{
@@ -103,7 +103,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(job_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(job_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[$__rate_interval]))",
"legendFormat": "Started/s [{{service_instance_id}}]"
},
{
@@ -111,7 +111,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(job_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(job_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[$__rate_interval]))",
"legendFormat": "Finished/s [{{service_instance_id}}]"
}
],
@@ -163,7 +163,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "topk(10, rate(job_queued_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[5m]))",
"expr": "topk(10, rate(job_queued_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[$__rate_interval]))",
"legendFormat": "{{job_type}} [{{service_instance_id}}]"
}
],
@@ -215,7 +215,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "topk(10, rate(job_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[5m]))",
"expr": "topk(10, rate(job_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", job_type=~\"$job_type\"}[$__rate_interval]))",
"legendFormat": "{{job_type}} [{{service_instance_id}}]"
}
],
@@ -404,7 +404,7 @@
},
{
"title": "Transaction Overflow Rate",
"description": "###### What this is:\n*Rate at which transaction jobs would be shed when the queue's transaction limit is exceeded.*\n\n###### How it's computed:\n*Per-second rate of the overflow counter over 5 minutes, scaled to per minute.*\n\n###### Reading it:\n*This counter is not currently wired up in the code, so the panel reads empty or zero regardless of load.*\n\n###### Healthy range:\n*Not applicable until wired; currently always empty or zero.*\n\n###### Watch for:\n*n/a until wired — this counter does not rise under load today.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`(job-queue transaction overflow counter)`",
"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 — the node is dropping transaction jobs because the queue is saturated.*\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)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -424,7 +424,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(jq_trans_overflow_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) * 60",
"expr": "rate(jq_trans_overflow_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) * 60",
"legendFormat": "Overflows/min [{{service_instance_id}}]"
}
],

96
docker/telemetry/grafana/dashboards/ledger-data-sync.json
View File

@@ -11,7 +11,7 @@
"panels": [
{
"title": "Ledger Data Exchange (Bytes In)",
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte counters, shown at their latest cumulative value per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Inbound bytes for ledger-data message categories, split into aggregate get/share plus the transaction-set, transaction-node, and account-state-node sub-types the node receives from peers.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Normally low and flat once synced. Account-state-node traffic dominates during state sync; transaction-set-candidate traffic dominates during consensus catch-up.*\n\n###### Healthy range:\n*workload-dependent; low and steady on a synced node.*\n\n###### Watch for:\n*Sustained high account-state or tx-node inbound bytes on a node that should be caught up (repeated re-sync, missing history), or a single peer driving all traffic.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -31,7 +31,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_data_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_data_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Ledger Data Get [{{service_instance_id}}]"
},
{
@@ -39,7 +39,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_data_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_data_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Ledger Data Share [{{service_instance_id}}]"
},
{
@@ -47,7 +47,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_data_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_data_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Set Candidate Get [{{service_instance_id}}]"
},
{
@@ -55,7 +55,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_data_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_data_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Set Candidate Share [{{service_instance_id}}]"
},
{
@@ -63,7 +63,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_data_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_data_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Node Get [{{service_instance_id}}]"
},
{
@@ -71,7 +71,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_data_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Node Share [{{service_instance_id}}]"
},
{
@@ -79,7 +79,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_data_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_data_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Account State Node Get [{{service_instance_id}}]"
},
{
@@ -87,13 +87,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_data_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Account State Node Share [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes In",
"spanNulls": true,
@@ -107,7 +107,7 @@
},
{
"title": "Ledger Share/Get Traffic (Bytes)",
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte counters at their latest value per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Inbound bytes for the older ledger share/get message categories and their tx-set, tx-node, and account-state sub-types.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Usually small; these legacy categories carry ledger-fetch traffic for peers using the older protocol.*\n\n###### Healthy range:\n*workload-dependent; low on a synced node.*\n\n###### Watch for:\n*Large sustained volumes indicating heavy fetch load or a peer repeatedly requesting the same data.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -127,7 +127,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Ledger Share In [{{service_instance_id}}]"
},
{
@@ -135,7 +135,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Ledger Get In [{{service_instance_id}}]"
},
{
@@ -143,7 +143,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_transaction_set_candidate_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Set Candidate Share [{{service_instance_id}}]"
},
{
@@ -151,7 +151,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_transaction_set_candidate_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Set Candidate Get [{{service_instance_id}}]"
},
{
@@ -159,7 +159,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Node Share [{{service_instance_id}}]"
},
{
@@ -167,7 +167,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Node Get [{{service_instance_id}}]"
},
{
@@ -175,7 +175,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Account State Share [{{service_instance_id}}]"
},
{
@@ -183,13 +183,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "ledger_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(ledger_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Account State Get [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes In",
"spanNulls": true,
@@ -203,7 +203,7 @@
},
{
"title": "GetObject Traffic by Type (Bytes In)",
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte counters at their latest value per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Inbound bytes for object-fetch traffic broken down by object type: ledger headers, individual transactions, transaction-tree nodes, and state-tree nodes.*\n\n###### How it's computed:\n*Per-type inbound byte rate per node.*\n\n###### Reading it:\n*Small during steady state; grows when the node fetches missing tree nodes.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*A large share on state/tx nodes for long periods (persistent gap-filling), meaning the node keeps catching up.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -223,7 +223,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_ledger_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Ledger Get [{{service_instance_id}}]"
},
{
@@ -231,7 +231,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_ledger_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Ledger Share [{{service_instance_id}}]"
},
{
@@ -239,7 +239,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_transaction_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_transaction_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Transaction Get [{{service_instance_id}}]"
},
{
@@ -247,7 +247,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_transaction_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_transaction_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Transaction Share [{{service_instance_id}}]"
},
{
@@ -255,7 +255,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_transaction_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Node Get [{{service_instance_id}}]"
},
{
@@ -263,7 +263,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_transaction_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Node Share [{{service_instance_id}}]"
},
{
@@ -271,7 +271,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_account_state_node_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Account State Get [{{service_instance_id}}]"
},
{
@@ -279,13 +279,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_account_state_node_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Account State Share [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes In",
"spanNulls": true,
@@ -299,7 +299,7 @@
},
{
"title": "GetObject Aggregate & Special Types (Bytes In)",
"description": "###### What this is:\n*Aggregate object-fetch inbound bytes plus special buckets: content-addressed storage fetches, bulk fetch-pack downloads used during catch-up, and bulk transaction fetches.*\n\n###### How it's computed:\n*Per-category inbound byte counters at their latest value per node.*\n\n###### Reading it:\n*Fetch-pack rises sharply while catching up a range of ledgers; near zero when fully synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous fetch-pack traffic (node never fully catches up) or unexpectedly high content-store volume.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Aggregate object-fetch inbound bytes plus special buckets: content-addressed storage fetches, bulk fetch-pack downloads used during catch-up, and bulk transaction fetches.*\n\n###### How it's computed:\n*Per-category inbound byte rate per node.*\n\n###### Reading it:\n*Fetch-pack rises sharply while catching up a range of ledgers; near zero when fully synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous fetch-pack traffic (node never fully catches up) or unexpectedly high content-store volume.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -319,7 +319,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_cas_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_cas_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "CAS Get [{{service_instance_id}}]"
},
{
@@ -327,7 +327,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_cas_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_cas_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "CAS Share [{{service_instance_id}}]"
},
{
@@ -335,7 +335,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_fetch_pack_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_fetch_pack_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Fetch Pack Share [{{service_instance_id}}]"
},
{
@@ -343,7 +343,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_fetch_pack_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_fetch_pack_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Fetch Pack Get [{{service_instance_id}}]"
},
{
@@ -351,7 +351,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_transactions_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_transactions_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Transactions Get [{{service_instance_id}}]"
},
{
@@ -359,7 +359,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Aggregate Get [{{service_instance_id}}]"
},
{
@@ -367,13 +367,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Aggregate Share [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes In",
"spanNulls": true,
@@ -387,7 +387,7 @@
},
{
"title": "GetObject Messages by Type",
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message counters at their latest value per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Count of individual object-fetch request/response messages per object type.*\n\n###### How it's computed:\n*Per-type inbound message rate per node.*\n\n###### Reading it:\n*Many messages with few bytes means small piecemeal fetches; few messages with many bytes means large batch transfers.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High message counts with tiny payloads sustained over time (inefficient per-node fetching).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -407,7 +407,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_ledger_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_ledger_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Ledger Get [{{service_instance_id}}]"
},
{
@@ -415,7 +415,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_transaction_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_transaction_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Transaction Get [{{service_instance_id}}]"
},
{
@@ -423,7 +423,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_transaction_node_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_transaction_node_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Node Get [{{service_instance_id}}]"
},
{
@@ -431,7 +431,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_account_state_node_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_account_state_node_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Account State Get [{{service_instance_id}}]"
},
{
@@ -439,7 +439,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_cas_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_cas_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "CAS Get [{{service_instance_id}}]"
},
{
@@ -447,7 +447,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_fetch_pack_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_fetch_pack_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Fetch Pack Get [{{service_instance_id}}]"
},
{
@@ -455,13 +455,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "getobject_transactions_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(getobject_transactions_get_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Transactions Get [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"unit": "cps",
"custom": {
"axisLabel": "Messages In",
"spanNulls": true,

8
docker/telemetry/grafana/dashboards/ledger-operations.json
View File

@@ -30,7 +30,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[$__rate_interval]))",
"legendFormat": "Builds / Sec [{{service_instance_id}}]"
}
],
@@ -103,7 +103,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.validate\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.validate\"}[$__rate_interval]))",
"legendFormat": "Validations / Sec [{{service_instance_id}}]"
}
],
@@ -213,7 +213,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[$__rate_interval]))",
"legendFormat": "tx.apply / Sec [{{service_instance_id}}]"
}
],
@@ -253,7 +253,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.store\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.store\"}[$__rate_interval]))",
"legendFormat": "Stores / Sec [{{service_instance_id}}]"
}
],

76
docker/telemetry/grafana/dashboards/network-traffic.json
View File

@@ -59,7 +59,7 @@
},
{
"title": "Peer Disconnects",
"description": "###### What this is:\n*Cumulative count of peer connections that have dropped.*\n\n###### How it's computed:\n*Running total of disconnect events per node.*\n\n###### Reading it:\n*A flat or slowly rising line is normal; the slope matters more than the absolute value.*\n\n###### Healthy range:\n*workload-dependent; slow, steady growth.*\n\n###### Watch for:\n*Sharp step-ups in the slope (network instability, resource exhaustion, or many peers dropping the node at once).*\n\n###### Source:\n[OverlayImpl.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.h)\n\n###### Function:\n`OverlayImpl::Stats ctor`",
"description": "###### What this is:\n*Peer connections that dropped, as a per-interval increase.*\n\n###### How it's computed:\n*Disconnect events per rate-interval, per node.*\n\n###### Reading it:\n*A flat or slowly rising line is normal; the slope matters more than the absolute value.*\n\n###### Healthy range:\n*workload-dependent; slow, steady growth.*\n\n###### Watch for:\n*Sharp step-ups in the slope (network instability, resource exhaustion, or many peers dropping the node at once).*\n\n###### Source:\n[OverlayImpl.h](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.h)\n\n###### Function:\n`OverlayImpl::Stats ctor`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -79,7 +79,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "overlay_peer_disconnects{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "increase(overlay_peer_disconnects{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Disconnects [{{service_instance_id}}]"
}
],
@@ -87,7 +87,7 @@
"defaults": {
"unit": "none",
"custom": {
"axisLabel": "Disconnects",
"axisLabel": "Disconnects per interval",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
@@ -99,7 +99,7 @@
},
{
"title": "Total Network Bytes",
"description": "###### What this is:\n*Total bytes received and sent across all peer connections.*\n\n###### How it's computed:\n*Current cumulative in/out byte totals per node.*\n\n###### Reading it:\n*Overall bandwidth footprint; in and out usually track network activity together.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Sudden sustained jumps not matched by ledger or transaction activity (relay storms or a noisy peer).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Total bytes received and sent across all peer connections.*\n\n###### How it's computed:\n*Per-second in/out byte rate per node.*\n\n###### Reading it:\n*Overall bandwidth footprint; in and out usually track network activity together.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Sudden sustained jumps not matched by ledger or transaction activity (relay storms or a noisy peer).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -119,7 +119,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "total_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(total_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Bytes In [{{service_instance_id}}]"
},
{
@@ -127,13 +127,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "total_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(total_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Bytes Out [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,
@@ -147,7 +147,7 @@
},
{
"title": "Total Network Messages",
"description": "###### What this is:\n*Total messages received and sent across all peer connections.*\n\n###### How it's computed:\n*Current cumulative in/out message totals per node.*\n\n###### Reading it:\n*Overall message throughput of the overlay; complements the byte totals.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Message count climbing far faster than bytes (many tiny messages, possible flooding).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Total messages received and sent across all peer connections.*\n\n###### How it's computed:\n*Per-second in/out message rate per node.*\n\n###### Reading it:\n*Overall message throughput of the overlay; complements the byte totals.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Message count climbing far faster than bytes (many tiny messages, possible flooding).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -167,7 +167,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "total_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(total_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Messages In [{{service_instance_id}}]"
},
{
@@ -175,13 +175,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "total_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(total_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Messages Out [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"unit": "cps",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
@@ -195,7 +195,7 @@
},
{
"title": "Transaction Traffic",
"description": "###### What this is:\n*Transaction relay messages in and out, plus duplicate transaction messages received.*\n\n###### How it's computed:\n*Current message counts for the transaction and transaction-duplicate categories.*\n\n###### Reading it:\n*In/out rise with network transaction volume; duplicates are transactions the node already had.*\n\n###### Healthy range:\n*workload-dependent; duplicates a modest fraction of inbound.*\n\n###### Watch for:\n*Duplicate inbound approaching or exceeding unique inbound (redundant relay), or a sharp spike suggesting transaction flooding.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Transaction relay messages in and out, plus duplicate transaction messages received.*\n\n###### How it's computed:\n*Per-second message rate for the transaction and transaction-duplicate categories.*\n\n###### Reading it:\n*In/out rise with network transaction volume; duplicates are transactions the node already had.*\n\n###### Healthy range:\n*workload-dependent; duplicates a modest fraction of inbound.*\n\n###### Watch for:\n*Duplicate inbound approaching or exceeding unique inbound (redundant relay), or a sharp spike suggesting transaction flooding.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -215,7 +215,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Messages In [{{service_instance_id}}]"
},
{
@@ -223,7 +223,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Messages Out [{{service_instance_id}}]"
},
{
@@ -231,13 +231,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "transactions_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(transactions_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Duplicate In [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"unit": "cps",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
@@ -251,7 +251,7 @@
},
{
"title": "Proposal Traffic",
"description": "###### What this is:\n*Consensus proposal messages in/out, plus untrusted and duplicate proposal messages received.*\n\n###### How it's computed:\n*Current message counts for the proposal, proposal-untrusted, and proposal-duplicate categories.*\n\n###### Reading it:\n*Trusted in/out track consensus rounds; untrusted come from validators not on this node's trusted list.*\n\n###### Healthy range:\n*workload-dependent; untrusted and duplicates low relative to trusted.*\n\n###### Watch for:\n*High untrusted (trusted-list misconfiguration) or high duplicates (inefficient relay or proposal spam).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Consensus proposal messages in/out, plus untrusted and duplicate proposal messages received.*\n\n###### How it's computed:\n*Per-second message rate for the proposal, proposal-untrusted, and proposal-duplicate categories.*\n\n###### Reading it:\n*Trusted in/out track consensus rounds; untrusted come from validators not on this node's trusted list.*\n\n###### Healthy range:\n*workload-dependent; untrusted and duplicates low relative to trusted.*\n\n###### Watch for:\n*High untrusted (trusted-list misconfiguration) or high duplicates (inefficient relay or proposal spam).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -271,7 +271,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "proposals_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(proposals_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Proposals In [{{service_instance_id}}]"
},
{
@@ -279,7 +279,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "proposals_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(proposals_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Proposals Out [{{service_instance_id}}]"
},
{
@@ -287,7 +287,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "proposals_untrusted_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(proposals_untrusted_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Untrusted In [{{service_instance_id}}]"
},
{
@@ -295,13 +295,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "proposals_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(proposals_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Duplicate In [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"unit": "cps",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
@@ -315,7 +315,7 @@
},
{
"title": "Validation Traffic",
"description": "###### What this is:\n*Validation messages in/out, plus untrusted and duplicate validation messages received.*\n\n###### How it's computed:\n*Current message counts for the validation, validation-untrusted, and validation-duplicate categories.*\n\n###### Reading it:\n*Trusted validations should arrive steadily each ledger; untrusted come from non-trusted validators.*\n\n###### Healthy range:\n*workload-dependent; untrusted and duplicates low relative to trusted.*\n\n###### Watch for:\n*Rising untrusted or duplicate validations (trusted-list health issues or validation spam).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Validation messages in/out, plus untrusted and duplicate validation messages received.*\n\n###### How it's computed:\n*Per-second message rate for the validation, validation-untrusted, and validation-duplicate categories.*\n\n###### Reading it:\n*Trusted validations should arrive steadily each ledger; untrusted come from non-trusted validators.*\n\n###### Healthy range:\n*workload-dependent; untrusted and duplicates low relative to trusted.*\n\n###### Watch for:\n*Rising untrusted or duplicate validations (trusted-list health issues or validation spam).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -335,7 +335,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "validations_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(validations_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Validations In [{{service_instance_id}}]"
},
{
@@ -343,7 +343,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "validations_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(validations_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Validations Out [{{service_instance_id}}]"
},
{
@@ -351,7 +351,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "validations_untrusted_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(validations_untrusted_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Untrusted In [{{service_instance_id}}]"
},
{
@@ -359,13 +359,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "validations_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(validations_duplicate_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Duplicate In [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"unit": "cps",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
@@ -379,7 +379,7 @@
},
{
"title": "Overlay Traffic by Category (Bytes In)",
"description": "###### What this is:\n*Top overlay traffic categories ranked by inbound bytes, excluding the all-traffic total.*\n\n###### How it's computed:\n*Top categories by latest inbound byte value per node.*\n\n###### Reading it:\n*Shows which message types dominate receive bandwidth right now.*\n\n###### Healthy range:\n*workload-dependent; transactions, proposals, and validations typically lead on a synced node.*\n\n###### Watch for:\n*A fetch or ledger-data category topping the list (sync activity) or an unexpected category dominating.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Top overlay traffic categories ranked by inbound bytes, excluding the all-traffic total.*\n\n###### How it's computed:\n*Top categories by inbound byte rate per node.*\n\n###### Reading it:\n*Shows which message types dominate receive bandwidth right now.*\n\n###### Healthy range:\n*workload-dependent; transactions, proposals, and validations typically lead on a synced node.*\n\n###### Watch for:\n*A fetch or ledger-data category topping the list (sync activity) or an unexpected category dominating.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "bargauge",
"gridPos": {
"h": 8,
@@ -399,13 +399,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "topk(10, {service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", __name__=~\".*_bytes_in\", __name__!~\"total_.*\"})",
"expr": "topk(10, rate({service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", __name__=~\".*_bytes_in\", __name__!~\"total_.*\"}[$__rate_interval]))",
"legendFormat": "{{__name__}} [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes"
"unit": "Bps"
},
"overrides": [
{
@@ -697,7 +697,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(transactions_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(transactions_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Duplicate In"
},
{
@@ -705,7 +705,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(transactions_duplicate_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(transactions_duplicate_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "TX Duplicate Out"
},
{
@@ -713,7 +713,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(proposals_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(proposals_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Proposals Duplicate In"
},
{
@@ -721,7 +721,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(proposals_duplicate_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(proposals_duplicate_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Proposals Duplicate Out"
},
{
@@ -729,7 +729,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(validations_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(validations_duplicate_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Validations Duplicate In"
},
{
@@ -737,7 +737,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(validations_duplicate_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(validations_duplicate_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Validations Duplicate Out"
}
],
@@ -777,7 +777,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "topk(15, rate({__name__=~\".*_bytes_in\", __name__!~\"total_.*\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]))",
"expr": "topk(15, rate({__name__=~\".*_bytes_in\", __name__!~\"total_.*\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "{{__name__}}"
}
],

291
docker/telemetry/grafana/dashboards/node-health.json
View File

@@ -110,8 +110,8 @@
}
},
{
"title": "Operating Mode Duration",
"description": "###### What this is:\n*Cumulative time the node has spent in each operating mode (Disconnected, Connected, Syncing, Tracking, Full).*\n\n###### How it's computed:\n*Current value of each per-mode duration counter, plotted as lines.*\n\n###### Reading it:\n*The Full line should climb steadily and dominate; other lines should be flat.*\n\n###### Healthy range:\n*Almost all accumulated time in Full mode.*\n\n###### Watch for:\n*Time accumulating in Syncing, Connected, or Disconnected means the node is not staying fully synced.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`",
"title": "Operating Mode (Time Share)",
"description": "###### What this is:\n*Fraction of recent wall-clock time the node spent in each operating mode (Disconnected, Connected, Syncing, Tracking, Full).*\n\n###### How it's computed:\n*Per-second rate of each per-mode duration counter divided by the sum of all five mode rates, giving each mode's time share.*\n\n###### Reading it:\n*The Full share should sit at or near 1.0 and dominate; other shares should be near 0.*\n\n###### Healthy range:\n*Full share close to 1.0.*\n\n###### Watch for:\n*Share accumulating in Syncing, Connected, or Disconnected means the node is not staying fully synced.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -131,7 +131,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) / (rate(state_accounting_disconnected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_connected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_syncing_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "Full [{{service_instance_id}}]"
},
{
@@ -139,7 +139,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) / (rate(state_accounting_disconnected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_connected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_syncing_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "Tracking [{{service_instance_id}}]"
},
{
@@ -147,7 +147,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "state_accounting_syncing_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(state_accounting_syncing_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) / (rate(state_accounting_disconnected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_connected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_syncing_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "Syncing [{{service_instance_id}}]"
},
{
@@ -155,7 +155,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "state_accounting_connected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(state_accounting_connected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) / (rate(state_accounting_disconnected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_connected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_syncing_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "Connected [{{service_instance_id}}]"
},
{
@@ -163,15 +163,17 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "state_accounting_disconnected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(state_accounting_disconnected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) / (rate(state_accounting_disconnected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_connected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_syncing_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "Disconnected [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "µs",
"unit": "percentunit",
"min": 0,
"max": 1,
"custom": {
"axisLabel": "Duration",
"axisLabel": "Time Share",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
@@ -355,7 +357,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(ledger_fetches_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(ledger_fetches_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Fetches / Sec [{{service_instance_id}}]"
}
],
@@ -389,7 +391,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(ledger_history_mismatch_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(ledger_history_mismatch_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Mismatches / Sec [{{service_instance_id}}]"
}
],
@@ -447,7 +449,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_reads_total\"}",
"expr": "rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_reads_total\"}[$__rate_interval])",
"legendFormat": "Reads Total [{{service_instance_id}}]"
},
{
@@ -455,7 +457,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_reads_hit\"}",
"expr": "rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_reads_hit\"}[$__rate_interval])",
"legendFormat": "Reads Hit (cache) [{{service_instance_id}}]"
},
{
@@ -463,15 +465,23 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_writes\"}",
"expr": "rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_writes\"}[$__rate_interval])",
"legendFormat": "Writes Total [{{service_instance_id}}]"
},
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_reads_hit\"}[$__rate_interval]) / rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_reads_total\"}[$__rate_interval])",
"legendFormat": "Cache Hit Ratio [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"unit": "ops",
"custom": {
"axisLabel": "Operations",
"axisLabel": "Operations / Sec",
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 10
@@ -480,7 +490,24 @@
"mode": "palette-classic"
}
},
"overrides": []
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "/Cache Hit Ratio/"
},
"properties": [
{
"id": "unit",
"value": "percentunit"
},
{
"id": "custom.axisPlacement",
"value": "right"
}
]
}
]
}
},
{
@@ -571,7 +598,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_read_bytes\"}",
"expr": "rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_read_bytes\"}[$__rate_interval])",
"legendFormat": "Bytes Read [{{service_instance_id}}]"
},
{
@@ -579,15 +606,15 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_written_bytes\"}",
"expr": "rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_written_bytes\"}[$__rate_interval])",
"legendFormat": "Bytes Written [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes",
"axisLabel": "Throughput",
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 10
@@ -645,15 +672,15 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_reads_duration_us\"}",
"legendFormat": "Read Duration (µs) [{{service_instance_id}}]"
"expr": "rate(nodestore_state{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"node_reads_duration_us\"}[$__rate_interval]) / 1e6",
"legendFormat": "Read Busy Ratio [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"custom": {
"axisLabel": "Count / µs",
"axisLabel": "Threads / Bundle",
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 10
@@ -662,7 +689,24 @@
"mode": "palette-classic"
}
},
"overrides": []
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "/Read Busy Ratio/"
},
"properties": [
{
"id": "unit",
"value": "percentunit"
},
{
"id": "custom.axisPlacement",
"value": "right"
}
]
}
]
}
},
{
@@ -1097,8 +1141,9 @@
],
"fieldConfig": {
"defaults": {
"unit": "none",
"unit": "short",
"custom": {
"axisLabel": "Proposers",
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 10
@@ -1107,7 +1152,24 @@
"mode": "palette-classic"
}
},
"overrides": []
"overrides": [
{
"matcher": {
"id": "byRegexp",
"options": "/Converge Time ms/"
},
"properties": [
{
"id": "unit",
"value": "ms"
},
{
"id": "custom.axisPlacement",
"value": "right"
}
]
}
]
}
},
{
@@ -1515,8 +1577,8 @@
},
{
"title": "Ledger Age",
"description": "###### What this is:\n*Seconds since the last validated ledger closed.*\n\n###### How it's computed:\n*Current value of the ledger-age economy gauge.*\n\n###### Reading it:\n*Lower is better; it should stay near the ledger close interval. Mirrors the Validated Ledger Age panel.*\n\n###### Healthy range:\n*Under about 8 seconds.*\n\n###### Watch for:\n*Growth beyond the expected close interval, meaning the node is not keeping up with validated ledgers.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLedgerEconomyGauge`",
"type": "stat",
"description": "###### What this is:\n*Seconds since the last validated ledger closed, plotted over time.*\n\n###### How it's computed:\n*Current value of the ledger-age economy gauge, sampled each interval.*\n\n###### Reading it:\n*Lower is better; it should stay near the ledger close interval. Mirrors the Validated Ledger Age panel.*\n\n###### Healthy range:\n*Under about 10 seconds.*\n\n###### Watch for:\n*Growth beyond the expected close interval, meaning the node is not keeping up with validated ledgers.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerLedgerEconomyGauge`",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 6,
@@ -1550,7 +1612,7 @@
},
{
"color": "yellow",
"value": 8
"value": 10
},
{
"color": "red",
@@ -1558,7 +1620,19 @@
}
]
},
"custom": {}
"custom": {
"axisLabel": "Ledger Age (s)",
"drawStyle": "line",
"lineWidth": 2,
"fillOpacity": 10,
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3,
"thresholdsStyle": {
"mode": "line"
}
}
},
"overrides": []
}
@@ -2023,7 +2097,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) / 1000000",
"expr": "rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) / 1000000",
"legendFormat": "Full Mode Rate"
},
{
@@ -2031,7 +2105,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) / 1000000",
"expr": "rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) / 1000000",
"legendFormat": "Tracking Mode Rate"
}
],
@@ -2191,7 +2265,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (outcome, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.acquire\"}[5m]))",
"expr": "sum by (outcome, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.acquire\"}[$__rate_interval]))",
"legendFormat": "{{outcome}} [{{service_instance_id}}]"
}
],
@@ -2208,6 +2282,155 @@
},
"overrides": []
}
},
{
"title": "Operating Mode (State Timeline)",
"description": "###### What this is:\n*The node's operating mode over time as a colored timeline (Disconnected, Connected, Syncing, Tracking, Full).*\n\n###### How it's computed:\n*Current value of the server-state gauge mapped to a mode name; equal consecutive samples are merged into a single band.*\n\n###### Reading it:\n*A solid green Full band across the window is the goal; other colors mark periods the node was not fully synced.*\n\n###### Healthy range:\n*Continuously Full (green).*\n\n###### Watch for:\n*Bands of Syncing, Connected, or Disconnected, which pinpoint exactly when the node dropped out of Full.*\n\n###### Source:\n[MetricsRegistry.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/telemetry/MetricsRegistry.cpp)\n\n###### Function:\n`registerServerInfoGauge`",
"type": "state-timeline",
"gridPos": {
"h": 8,
"w": 18,
"x": 0,
"y": 134
},
"options": {
"mergeValues": true,
"showValue": "auto",
"alignValue": "left",
"rowHeight": 0.9,
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "server_info{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", metric=\"server_state\"}",
"legendFormat": "State [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "none",
"mappings": [
{
"type": "value",
"options": {
"0": {
"text": "Disconnected",
"color": "red"
}
}
},
{
"type": "value",
"options": {
"1": {
"text": "Connected",
"color": "orange"
}
}
},
{
"type": "value",
"options": {
"2": {
"text": "Syncing",
"color": "yellow"
}
}
},
{
"type": "value",
"options": {
"3": {
"text": "Tracking",
"color": "blue"
}
}
},
{
"type": "value",
"options": {
"4": {
"text": "Full",
"color": "green"
}
}
}
],
"custom": {
"fillOpacity": 80,
"lineWidth": 0
}
},
"overrides": []
}
},
{
"title": "% Time in Full",
"description": "###### What this is:\n*The share of recent wall-clock time the node spent in Full mode.*\n\n###### How it's computed:\n*Per-second rate of the Full-mode duration counter divided by the sum of the per-second rates of all five mode duration counters.*\n\n###### Reading it:\n*Higher is better; 1.0 means the node was fully synced for the entire window.*\n\n###### Healthy range:\n*At or above 0.99.*\n\n###### Watch for:\n*Values dropping below 0.9, meaning the node spent meaningful time outside Full mode.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp)\n\n###### Function:\n`NetworkOPsImp::Stats`",
"type": "stat",
"gridPos": {
"h": 8,
"w": 6,
"x": 18,
"y": 134
},
"options": {
"reduceOptions": {
"calcs": ["lastNotNull"],
"fields": "",
"values": false
},
"orientation": "auto",
"textMode": "auto",
"colorMode": "value",
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) / (rate(state_accounting_disconnected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_connected_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_syncing_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_tracking_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) + rate(state_accounting_full_duration{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "% Time in Full [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "percentunit",
"min": 0,
"max": 1,
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "red",
"value": null
},
{
"color": "yellow",
"value": 0.9
},
{
"color": "green",
"value": 0.99
}
]
},
"custom": {}
},
"overrides": []
}
}
],
"schemaVersion": 39,

94
docker/telemetry/grafana/dashboards/overlay-traffic-detail.json
View File

@@ -11,7 +11,7 @@
"panels": [
{
"title": "Squelch Traffic (Messages)",
"description": "###### What this is:\n*Squelch relay-control messages in/out, plus messages suppressed by squelch and squelch directives that were ignored. Squelch reduces redundant message forwarding between peers.*\n\n###### How it's computed:\n*Current message counts for the squelch, squelch-suppressed, and squelch-ignored categories, in and out.*\n\n###### Reading it:\n*High suppressed counts mean squelch is saving bandwidth; ignored should stay low.*\n\n###### Healthy range:\n*workload-dependent; suppressed far above ignored.*\n\n###### Watch for:\n*High ignored counts (peers not honoring squelch) or squelch traffic itself dominating.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Squelch relay-control messages in/out, plus messages suppressed by squelch and squelch directives that were ignored. Squelch reduces redundant message forwarding between peers.*\n\n###### How it's computed:\n*Per-second message rate for the squelch, squelch-suppressed, and squelch-ignored categories, in and out.*\n\n###### Reading it:\n*High suppressed counts mean squelch is saving bandwidth; ignored should stay low.*\n\n###### Healthy range:\n*workload-dependent; suppressed far above ignored.*\n\n###### Watch for:\n*High ignored counts (peers not honoring squelch) or squelch traffic itself dominating.*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -31,7 +31,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "squelch_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(squelch_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Squelch In [{{service_instance_id}}]"
},
{
@@ -39,7 +39,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "squelch_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(squelch_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Squelch Out [{{service_instance_id}}]"
},
{
@@ -47,7 +47,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "squelch_suppressed_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(squelch_suppressed_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Suppressed In [{{service_instance_id}}]"
},
{
@@ -55,7 +55,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "squelch_suppressed_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(squelch_suppressed_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Suppressed Out [{{service_instance_id}}]"
},
{
@@ -63,7 +63,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "squelch_ignored_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(squelch_ignored_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Ignored In [{{service_instance_id}}]"
},
{
@@ -71,13 +71,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "squelch_ignored_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(squelch_ignored_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Ignored Out [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"unit": "cps",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
@@ -91,7 +91,7 @@
},
{
"title": "Overhead Traffic Breakdown (Bytes)",
"description": "###### What this is:\n*Overlay protocol overhead bytes split into base overhead, intra-cluster overhead, and validator-manifest distribution overhead.*\n\n###### How it's computed:\n*Current in/out byte counts for the overhead, overhead-cluster, and overhead-manifest categories.*\n\n###### Reading it:\n*Base overhead is routine; cluster and manifest rise around cluster syncs and manifest changes.*\n\n###### Healthy range:\n*workload-dependent; low and stable.*\n\n###### Watch for:\n*Sustained high cluster or manifest overhead (frequent cluster state churn or manifest reissue).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Overlay protocol overhead bytes split into base overhead, intra-cluster overhead, and validator-manifest distribution overhead.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the overhead, overhead-cluster, and overhead-manifest categories.*\n\n###### Reading it:\n*Base overhead is routine; cluster and manifest rise around cluster syncs and manifest changes.*\n\n###### Healthy range:\n*workload-dependent; low and stable.*\n\n###### Watch for:\n*Sustained high cluster or manifest overhead (frequent cluster state churn or manifest reissue).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -111,7 +111,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "overhead_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(overhead_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Base Overhead In [{{service_instance_id}}]"
},
{
@@ -119,7 +119,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "overhead_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(overhead_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Base Overhead Out [{{service_instance_id}}]"
},
{
@@ -127,7 +127,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "overhead_cluster_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(overhead_cluster_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Cluster In [{{service_instance_id}}]"
},
{
@@ -135,7 +135,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "overhead_cluster_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(overhead_cluster_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Cluster Out [{{service_instance_id}}]"
},
{
@@ -143,7 +143,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "overhead_manifest_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(overhead_manifest_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Manifest In [{{service_instance_id}}]"
},
{
@@ -151,13 +151,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "overhead_manifest_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(overhead_manifest_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Manifest Out [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,
@@ -171,7 +171,7 @@
},
{
"title": "Validator List Traffic",
"description": "###### What this is:\n*Bytes and messages exchanged distributing validator lists (trusted-list configuration) between peers.*\n\n###### How it's computed:\n*Current in/out byte and message counts for the validator-lists category.*\n\n###### Reading it:\n*Bursts when lists update or new peers connect; quiet otherwise.*\n\n###### Healthy range:\n*workload-dependent; occasional bursts.*\n\n###### Watch for:\n*Continuous high volume (repeated list re-fetching or churn).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Bytes and messages exchanged distributing validator lists (trusted-list configuration) between peers.*\n\n###### How it's computed:\n*Per-second in/out byte and message rate for the validator-lists category.*\n\n###### Reading it:\n*Bursts when lists update or new peers connect; quiet otherwise.*\n\n###### Healthy range:\n*workload-dependent; occasional bursts.*\n\n###### Watch for:\n*Continuous high volume (repeated list re-fetching or churn).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -191,7 +191,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "validator_lists_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(validator_lists_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Bytes In [{{service_instance_id}}]"
},
{
@@ -199,7 +199,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "validator_lists_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(validator_lists_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Bytes Out [{{service_instance_id}}]"
},
{
@@ -207,7 +207,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "validator_lists_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(validator_lists_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Messages In [{{service_instance_id}}]"
},
{
@@ -215,13 +215,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "validator_lists_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(validator_lists_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Messages Out [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"unit": "cps",
"custom": {
"axisLabel": "Count",
"spanNulls": true,
@@ -243,7 +243,7 @@
},
{
"id": "unit",
"value": "decbytes"
"value": "binBps"
}
]
}
@@ -252,7 +252,7 @@
},
{
"title": "Set Get/Share Traffic (Bytes)",
"description": "###### What this is:\n*Transaction-set fetch (get) and share bytes exchanged during ledger close.*\n\n###### How it's computed:\n*Current in/out byte counts for the set-get and set-share categories.*\n\n###### Reading it:\n*Some exchange each ledger is normal as peers reconcile transaction sets.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High set-get (peers frequently missing transaction sets: possible sync delays).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Transaction-set fetch (get) and share bytes exchanged during ledger close.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the set-get and set-share categories.*\n\n###### Reading it:\n*Some exchange each ledger is normal as peers reconcile transaction sets.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High set-get (peers frequently missing transaction sets: possible sync delays).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -272,7 +272,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "set_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(set_get_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Set Get In [{{service_instance_id}}]"
},
{
@@ -280,7 +280,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "set_get_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(set_get_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Set Get Out [{{service_instance_id}}]"
},
{
@@ -288,7 +288,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "set_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(set_share_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Set Share In [{{service_instance_id}}]"
},
{
@@ -296,13 +296,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "set_share_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(set_share_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Set Share Out [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,
@@ -316,7 +316,7 @@
},
{
"title": "Have/Requested Transactions (Messages)",
"description": "###### What this is:\n*Transaction-availability messages: advertisements that a peer has certain transactions, and explicit requests for transaction data.*\n\n###### How it's computed:\n*Current in/out message counts for the have-transactions and requested-transactions categories.*\n\n###### Reading it:\n*Compare requested versus have to gauge how well transactions are propagating.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Requested far exceeding have (peers behind on transaction propagation).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Transaction-availability messages: advertisements that a peer has certain transactions, and explicit requests for transaction data.*\n\n###### How it's computed:\n*Per-second in/out message rate for the have-transactions and requested-transactions categories.*\n\n###### Reading it:\n*Compare requested versus have to gauge how well transactions are propagating.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*Requested far exceeding have (peers behind on transaction propagation).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -336,7 +336,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "have_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(have_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Have TX In [{{service_instance_id}}]"
},
{
@@ -344,7 +344,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "have_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(have_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Have TX Out [{{service_instance_id}}]"
},
{
@@ -352,7 +352,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "requested_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(requested_transactions_messages_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Requested TX In [{{service_instance_id}}]"
},
{
@@ -360,13 +360,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "requested_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(requested_transactions_messages_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Requested TX Out [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "short",
"unit": "cps",
"custom": {
"axisLabel": "Messages",
"spanNulls": true,
@@ -461,7 +461,7 @@
},
{
"title": "Proof Path Traffic",
"description": "###### What this is:\n*Proof-path request/response bytes used to verify individual ledger entries without downloading the whole ledger.*\n\n###### How it's computed:\n*Current in/out byte counts for the proof-path request and response categories.*\n\n###### Reading it:\n*Rises when peers verify specific state, often during catch-up.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High sustained request volume (heavy state-verification load).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Proof-path request/response bytes used to verify individual ledger entries without downloading the whole ledger.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the proof-path request and response categories.*\n\n###### Reading it:\n*Rises when peers verify specific state, often during catch-up.*\n\n###### Healthy range:\n*workload-dependent.*\n\n###### Watch for:\n*High sustained request volume (heavy state-verification load).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -481,7 +481,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "proof_path_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(proof_path_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Request Bytes In [{{service_instance_id}}]"
},
{
@@ -489,7 +489,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "proof_path_request_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(proof_path_request_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Request Bytes Out [{{service_instance_id}}]"
},
{
@@ -497,7 +497,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "proof_path_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(proof_path_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Response Bytes In [{{service_instance_id}}]"
},
{
@@ -505,13 +505,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "proof_path_response_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(proof_path_response_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Response Bytes Out [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,
@@ -525,7 +525,7 @@
},
{
"title": "Replay Delta Traffic",
"description": "###### What this is:\n*Replay-delta request/response bytes used to efficiently replay ledger state changes during catch-up.*\n\n###### How it's computed:\n*Current in/out byte counts for the replay-delta request and response categories.*\n\n###### Reading it:\n*Active during catch-up and replay; quiet when synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous replay traffic (node repeatedly replaying rather than staying current).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"description": "###### What this is:\n*Replay-delta request/response bytes used to efficiently replay ledger state changes during catch-up.*\n\n###### How it's computed:\n*Per-second in/out byte rate for the replay-delta request and response categories.*\n\n###### Reading it:\n*Active during catch-up and replay; quiet when synced.*\n\n###### Healthy range:\n*workload-dependent; low when synced.*\n\n###### Watch for:\n*Continuous replay traffic (node repeatedly replaying rather than staying current).*\n\n###### Source:\n[OverlayImpl.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/OverlayImpl.cpp)\n\n###### Function:\n`OverlayImpl ctor (TrafficGauges)`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -545,7 +545,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "replay_delta_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(replay_delta_request_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Request Bytes In [{{service_instance_id}}]"
},
{
@@ -553,7 +553,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "replay_delta_request_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(replay_delta_request_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Request Bytes Out [{{service_instance_id}}]"
},
{
@@ -561,7 +561,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "replay_delta_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(replay_delta_response_bytes_in{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Response Bytes In [{{service_instance_id}}]"
},
{
@@ -569,13 +569,13 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "replay_delta_response_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}",
"expr": "rate(replay_delta_response_bytes_out{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Response Bytes Out [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "decbytes",
"unit": "Bps",
"custom": {
"axisLabel": "Bytes",
"spanNulls": true,

8
docker/telemetry/grafana/dashboards/peer-network.json
View File

@@ -31,7 +31,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"peer.proposal.receive\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"peer.proposal.receive\"}[$__rate_interval]))",
"legendFormat": "Proposals Received / Sec [{{service_instance_id}}]"
}
],
@@ -71,7 +71,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"peer.validation.receive\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"peer.validation.receive\"}[$__rate_interval]))",
"legendFormat": "Validations Received / Sec [{{service_instance_id}}]"
}
],
@@ -111,7 +111,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (proposal_trusted, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", proposal_trusted=~\"$proposal_trusted\", span_name=\"peer.proposal.receive\"}[5m]))",
"expr": "sum by (proposal_trusted, 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\", proposal_trusted=~\"$proposal_trusted\", span_name=\"peer.proposal.receive\"}[$__rate_interval]))",
"legendFormat": "Trusted = {{proposal_trusted}} [{{service_instance_id}}]"
}
],
@@ -144,7 +144,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (validation_trusted, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", validation_trusted=~\"$validation_trusted\", span_name=\"peer.validation.receive\"}[5m]))",
"expr": "sum by (validation_trusted, 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\", validation_trusted=~\"$validation_trusted\", span_name=\"peer.validation.receive\"}[$__rate_interval]))",
"legendFormat": "Trusted = {{validation_trusted}} [{{service_instance_id}}]"
}
],

16
docker/telemetry/grafana/dashboards/rpc-pathfinding.json
View File

@@ -31,7 +31,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(rpc_requests_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(rpc_requests_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Requests / Sec [{{service_instance_id}}]"
}
],
@@ -84,7 +84,7 @@
},
{
"title": "RPC Response Size",
"description": "###### What this is:\n*The 95th-percentile size of RPC response payloads in bytes.*\n\n###### How it's computed:\n*95th-percentile of response payload sizes over 5 minutes, per node.*\n\n###### Reading it:\n*Smaller is cheaper; large responses cost bandwidth and memory.*\n\n###### Healthy range:\n*Workload-dependent; small for status queries, large for bulk data queries.*\n\n###### Watch for:\n*Growth in large responses, consistent with expensive queries or API misuse.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler ctor`",
"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 this is:\n*The 95th-percentile size of RPC response payloads in bytes.*\n\n###### How it's computed:\n*95th-percentile of response payload sizes over the dashboard rate interval, per node.*\n\n###### Reading it:\n*Smaller is cheaper; large responses cost bandwidth and memory.*\n\n###### Healthy range:\n*Workload-dependent; small for status queries, large for bulk data queries.*\n\n###### Watch for:\n*Growth in large responses, consistent with expensive queries or API misuse.*\n\n###### Source:\n[ServerHandler.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/rpc/detail/ServerHandler.cpp)\n\n###### Function:\n`ServerHandler ctor`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -280,7 +280,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(warn_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(warn_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Warnings / Sec [{{service_instance_id}}]"
}
],
@@ -329,7 +329,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(drop_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])",
"expr": "rate(drop_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval])",
"legendFormat": "Drops / Sec [{{service_instance_id}}]"
}
],
@@ -378,7 +378,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (method, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$grpc_method\", span_name=~\"grpc\\\\..*\"}[5m]))",
"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]))",
"legendFormat": "{{method}} [{{service_instance_id}}]"
}
],
@@ -458,7 +458,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (grpc_status, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"grpc\\\\..*\", grpc_status!=\"\"}[5m]))",
"expr": "sum by (grpc_status, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"grpc\\\\..*\", grpc_status!=\"\"}[$__rate_interval]))",
"legendFormat": "{{grpc_status}} [{{service_instance_id}}]"
}
],
@@ -538,7 +538,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"pathfind.request\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"pathfind.request\"}[$__rate_interval]))",
"legendFormat": "Requests / Sec [{{service_instance_id}}]"
},
{
@@ -546,7 +546,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"pathfind.discover\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"pathfind.discover\"}[$__rate_interval]))",
"legendFormat": "Discoveries / Sec [{{service_instance_id}}]"
}
],

34
docker/telemetry/grafana/dashboards/rpc-performance.json
View File

@@ -43,7 +43,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (command, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m]))",
"expr": "sum by (command, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval]))",
"legendFormat": "{{command}} [{{service_instance_id}}]"
}
],
@@ -125,7 +125,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (command, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[5m])) / sum by (command, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])) * 100",
"expr": "sum by (command, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[$__rate_interval])) / sum by (command, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval])) * 100",
"legendFormat": "{{command}} [{{service_instance_id}}]"
}
],
@@ -213,7 +213,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.http_request\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.http_request\"}[$__rate_interval]))",
"legendFormat": "rpc.http_request / Sec [{{service_instance_id}}]"
},
{
@@ -221,7 +221,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.process\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.process\"}[$__rate_interval]))",
"legendFormat": "rpc.process / Sec [{{service_instance_id}}]"
}
],
@@ -262,7 +262,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_OK\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_OK\"}[$__rate_interval]))",
"legendFormat": "Success [{{service_instance_id}}]"
},
{
@@ -270,7 +270,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[$__rate_interval]))",
"legendFormat": "Error [{{service_instance_id}}]"
}
],
@@ -311,7 +311,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "topk(10, sum by (command, service_instance_id) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])))",
"expr": "topk(10, sum by (command, service_instance_id) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[$__rate_interval])))",
"legendFormat": "{{command}} [{{service_instance_id}}]"
}
],
@@ -345,7 +345,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.ws_message\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.ws_message\"}[$__rate_interval]))",
"legendFormat": "WS Messages / Sec [{{service_instance_id}}]"
}
],
@@ -384,7 +384,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (load_type) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"rpc.command.*\", load_type!=\"\"}[5m]))",
"expr": "sum by (load_type) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"rpc.command.*\", load_type!=\"\"}[$__rate_interval]))",
"legendFormat": "{{load_type}}"
}
],
@@ -425,7 +425,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"rpc.process\", is_batch=\"true\"}[5m]))",
"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=\"rpc.process\", is_batch=\"true\"}[$__rate_interval]))",
"legendFormat": "Batch [{{service_instance_id}}]"
},
{
@@ -433,7 +433,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"rpc.process\", is_batch=\"false\"}[5m]))",
"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=\"rpc.process\", is_batch=\"false\"}[$__rate_interval]))",
"legendFormat": "Single [{{service_instance_id}}]"
}
],
@@ -487,7 +487,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(rpc_method_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(rpc_method_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[$__rate_interval]))",
"legendFormat": "Started/s [{{service_instance_id}}]"
},
{
@@ -495,7 +495,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(rpc_method_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(rpc_method_finished_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[$__rate_interval]))",
"legendFormat": "Finished/s [{{service_instance_id}}]"
},
{
@@ -503,7 +503,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(rpc_method_errored_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(rpc_method_errored_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[$__rate_interval]))",
"legendFormat": "Errored/s [{{service_instance_id}}]"
}
],
@@ -555,7 +555,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "topk(10, rate(rpc_method_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[5m]))",
"expr": "topk(10, rate(rpc_method_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[$__rate_interval]))",
"legendFormat": "{{method}} [{{service_instance_id}}]"
}
],
@@ -607,7 +607,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "topk(10, rate(rpc_method_errored_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[5m]))",
"expr": "topk(10, rate(rpc_method_errored_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[$__rate_interval]))",
"legendFormat": "{{method}} [{{service_instance_id}}]"
}
],
@@ -766,7 +766,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "topk(10, rate(rpc_method_errored_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[5m]) / (rate(rpc_method_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[5m]) > 0))",
"expr": "topk(10, rate(rpc_method_errored_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[$__rate_interval]) / (rate(rpc_method_started_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", method=~\"$method\"}[$__rate_interval]) > 0))",
"legendFormat": "{{method}} [{{service_instance_id}}]"
}
],

78
docker/telemetry/grafana/dashboards/transaction-overview.json
View File

@@ -31,7 +31,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\", status_code=\"STATUS_CODE_ERROR\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\", status_code=\"STATUS_CODE_ERROR\"}[$__rate_interval]))",
"legendFormat": "Failed / Sec [{{service_instance_id}}]"
}
],
@@ -134,7 +134,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (tx_type, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))",
"expr": "sum by (tx_type, 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=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval]))",
"legendFormat": "{{tx_type}} [{{service_instance_id}}]"
}
],
@@ -181,7 +181,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (tx_type, ter_result, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\", ter_result=~\"$ter_result\", ter_result!=\"tesSUCCESS\"}[5m]))",
"expr": "sum by (tx_type, ter_result, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\", ter_result=~\"$ter_result\", ter_result!=\"tesSUCCESS\"}[$__rate_interval]))",
"legendFormat": "{{tx_type}} [{{ter_result}}, {{service_instance_id}}]"
}
],
@@ -244,7 +244,7 @@
},
{
"title": "Transaction Processing Rate",
"description": "###### What this is:\n*Transactions entering the processing pipeline versus raw transactions arriving from peers.*\n\n###### How it's computed:\n*Per-second rates of processed transactions and received peer transactions over 5 minutes, per node.*\n\n###### Reading it:\n*Received sits above processed; the difference is deduplicated relay traffic.*\n\n###### Healthy range:\n*Workload-dependent; both scale with network volume.*\n\n###### Watch for:\n*A receive rate spiking well above processing, consistent with relay flooding.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp) · [PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`NetworkOPsImp::processTransaction ; PeerImp::handleTransaction`",
"description": "###### What this is:\n*Transactions entering the processing pipeline versus raw transactions arriving from peers.*\n\n###### How it's computed:\n*Per-second rates of processed transactions and received peer transactions over 5 minutes, per node.*\n\n###### Reading it:\n*Received sits above processed; the difference is deduplicated relay traffic.*\n\n###### Healthy range:\n*Workload-dependent; both scale with network volume.*\n\n###### Watch for:\n*A receive rate spiking well above processing, consistent with relay flooding.*\n\n###### Source:\n[NetworkOPs.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/app/misc/NetworkOPs.cpp) \u00b7 [PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`NetworkOPsImp::processTransaction ; PeerImp::handleTransaction`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -265,7 +265,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))",
"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=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval]))",
"legendFormat": "tx.process / Sec [{{service_instance_id}}]"
},
{
@@ -273,7 +273,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.receive\", tx_type=~\"$tx_type\"}[5m]))",
"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=\"tx.receive\", tx_type=~\"$tx_type\"}[$__rate_interval]))",
"legendFormat": "tx.receive / Sec [{{service_instance_id}}]"
}
],
@@ -315,7 +315,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (local, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", local=~\"$tx_origin\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))",
"expr": "sum by (local, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", local=~\"$tx_origin\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[$__rate_interval]))",
"legendFormat": "Local [{{local}}, {{service_instance_id}}]"
}
],
@@ -360,48 +360,6 @@
},
"id": 8
},
{
"title": "Peer Transaction Receive Rate",
"description": "###### What this is:\n*How many transaction messages arrive from network peers per second.*\n\n###### How it's computed:\n*Per-second rate of received peer transactions over 5 minutes, per node.*\n\n###### Reading it:\n*Reflects network-wide transaction volume reaching this node.*\n\n###### Healthy range:\n*Workload-dependent; tracks overall network activity.*\n\n###### Watch for:\n*A sharp spike above baseline, consistent with network-wide volume surges or peer flooding.*\n\n###### Source:\n[PeerImp.cpp](https://github.com/XRPLF/rippled/blob/develop/src/xrpld/overlay/detail/PeerImp.cpp)\n\n###### Function:\n`PeerImp::handleTransaction`",
"type": "timeseries",
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 44
},
"options": {
"tooltip": {
"mode": "multi",
"sort": "desc",
"maxHeight": 500
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.receive\", tx_type=~\"$tx_type\"}[5m]))",
"legendFormat": "tx.receive / Sec [{{service_instance_id}}]"
}
],
"fieldConfig": {
"defaults": {
"unit": "ops",
"custom": {
"axisLabel": "Transactions / Sec",
"spanNulls": true,
"insertNulls": false,
"showPoints": "auto",
"pointSize": 3
}
},
"overrides": []
},
"id": 9
},
{
"title": "Transactor Duration by Type (p95)",
"description": "###### What this is:\n*The 95th-percentile execution time of the core transactor step, by transaction type.*\n\n###### How it's computed:\n*95th-percentile of transactor durations over 5 minutes, grouped by type and node.*\n\n###### Reading it:\n*Lower is better; reveals which types are most expensive to execute.*\n\n###### Healthy range:\n*Sub-millisecond to a few ms for most types; workload-dependent.*\n\n###### Watch for:\n*A type whose execution time grows, indicating expensive logic or ledger contention.*\n\n###### Source:\n[Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`Transactor::operator()`",
@@ -451,7 +409,7 @@
},
{
"title": "Tx Apply Pipeline Rate by Stage",
"description": "###### What this is:\n*How many transactions pass through each apply-pipeline stage (preflight, preclaim, apply) per second.*\n\n###### How it's computed:\n*Per-second rate over 5 minutes, grouped by pipeline stage and node.*\n\n###### Reading it:\n*Stages should step down slightly as invalid transactions are filtered out.*\n\n###### Healthy range:\n*Workload-dependent; preflight highest, apply lowest.*\n\n###### Watch for:\n*A large drop between stages, showing where most transactions are being rejected.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) · [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`",
"description": "###### What this is:\n*How many transactions pass through each apply-pipeline stage (preflight, preclaim, apply) per second.*\n\n###### How it's computed:\n*Per-second rate over 5 minutes, grouped by pipeline stage and node.*\n\n###### Reading it:\n*Stages should step down slightly as invalid transactions are filtered out.*\n\n###### Healthy range:\n*Workload-dependent; preflight highest, apply lowest.*\n\n###### Watch for:\n*A large drop between stages, showing where most transactions are being rejected.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -477,7 +435,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "label_replace(label_replace(label_replace(sum by (stage, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\"}[5m])), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\")",
"expr": "label_replace(label_replace(label_replace(sum by (stage, 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=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\"}[$__rate_interval])), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\")",
"legendFormat": "{{stage}} [{{service_instance_id}}]"
}
],
@@ -498,7 +456,7 @@
},
{
"title": "Tx Apply Pipeline Latency by Stage (p95)",
"description": "###### What this is:\n*The 95th-percentile duration of each apply-pipeline stage.*\n\n###### How it's computed:\n*95th-percentile of per-stage durations over 5 minutes, grouped by stage and node.*\n\n###### Reading it:\n*Lower is better; isolates which stage dominates processing time.*\n\n###### Healthy range:\n*Each stage typically sub-millisecond to a few ms; workload-dependent.*\n\n###### Watch for:\n*One stage's latency rising, pinpointing the bottleneck in transaction handling.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) · [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`",
"description": "###### What this is:\n*The 95th-percentile duration of each apply-pipeline stage.*\n\n###### How it's computed:\n*95th-percentile of per-stage durations over 5 minutes, grouped by stage and node.*\n\n###### Reading it:\n*Lower is better; isolates which stage dominates processing time.*\n\n###### Healthy range:\n*Each stage typically sub-millisecond to a few ms; workload-dependent.*\n\n###### Watch for:\n*One stage's latency rising, pinpointing the bottleneck in transaction handling.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -545,7 +503,7 @@
},
{
"title": "Tx Apply Pipeline Failure Rate by Stage",
"description": "###### What this is:\n*How many transactions fail at each apply-pipeline stage per second.*\n\n###### How it's computed:\n*Per-second rate of non-success outcomes over 5 minutes, grouped by stage and node.*\n\n###### Reading it:\n*Shows whether rejections concentrate in preflight, preclaim, or apply.*\n\n###### Healthy range:\n*Workload-dependent; a modest background of expected rejections is normal.*\n\n###### Watch for:\n*A failure spike concentrated in one stage, consistent with malformed or spam submissions.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) · [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`",
"description": "###### What this is:\n*How many transactions fail at each apply-pipeline stage per second.*\n\n###### How it's computed:\n*Per-second rate of non-success outcomes over 5 minutes, grouped by stage and node.*\n\n###### Reading it:\n*Shows whether rejections concentrate in preflight, preclaim, or apply.*\n\n###### Healthy range:\n*Workload-dependent; a modest background of expected rejections is normal.*\n\n###### Watch for:\n*A failure spike concentrated in one stage, consistent with malformed or spam submissions.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -571,7 +529,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "label_replace(label_replace(label_replace(sum by (stage, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\", ter_result!~\"tesSUCCESS|\"}[5m])), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\")",
"expr": "label_replace(label_replace(label_replace(sum by (stage, 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=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\", ter_result!~\"tesSUCCESS|\"}[$__rate_interval])), \"stage\", \"Preflight\", \"stage\", \"preflight\"), \"stage\", \"Preclaim\", \"stage\", \"preclaim\"), \"stage\", \"Apply\", \"stage\", \"apply\")",
"legendFormat": "{{stage}} [{{service_instance_id}}]"
}
],
@@ -592,7 +550,7 @@
},
{
"title": "Tx Apply Pipeline Latency by Type and Stage (p95)",
"description": "###### What this is:\n*The 95th-percentile stage duration broken down by both transaction type and pipeline stage.*\n\n###### How it's computed:\n*95th-percentile durations over 5 minutes, grouped by type and stage; higher cardinality than the by-stage view.*\n\n###### Reading it:\n*Lower is better; shows which stage dominates each type's latency.*\n\n###### Healthy range:\n*Workload-dependent; most type/stage pairs sub-millisecond to a few ms.*\n\n###### Watch for:\n*A specific type/stage combination rising sharply, pinpointing a costly path.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) · [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`",
"description": "###### What this is:\n*The 95th-percentile stage duration broken down by both transaction type and pipeline stage.*\n\n###### How it's computed:\n*95th-percentile durations over 5 minutes, grouped by type and stage; higher cardinality than the by-stage view.*\n\n###### Reading it:\n*Lower is better; shows which stage dominates each type's latency.*\n\n###### Healthy range:\n*Workload-dependent; most type/stage pairs sub-millisecond to a few ms.*\n\n###### Watch for:\n*A specific type/stage combination rising sharply, pinpointing a costly path.*\n\n###### Source:\n[applySteps.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/applySteps.cpp) \u00b7 [Transactor.cpp](https://github.com/XRPLF/rippled/blob/develop/src/libxrpl/tx/Transactor.cpp)\n\n###### Function:\n`makeStageSpan ; Transactor::operator()`",
"type": "timeseries",
"gridPos": {
"h": 8,
@@ -702,7 +660,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (tx_type, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.enqueue\"}[5m]))",
"expr": "sum by (tx_type, service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.enqueue\"}[$__rate_interval]))",
"legendFormat": "{{tx_type}} [{{service_instance_id}}]"
}
],
@@ -748,7 +706,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (txq_status, service_instance_id) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.accept_tx\", txq_status=~\"$txq_status\"}[5m]))",
"expr": "sum by (txq_status, service_instance_id) (increase(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.accept_tx\", txq_status=~\"$txq_status\"}[$__rate_interval]))",
"legendFormat": "{{txq_status}} [{{service_instance_id}}]"
}
],
@@ -783,7 +741,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.apply_direct\"}[5m])) / clamp_min(sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.apply_direct\"}[5m])) + sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.enqueue\"}[5m])), 1)",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.apply_direct\"}[$__rate_interval])) / clamp_min(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=\"txq.apply_direct\"}[$__rate_interval])) + sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.enqueue\"}[$__rate_interval])), 1)",
"legendFormat": "Direct-Apply Fraction [{{service_instance_id}}]"
}
],
@@ -867,7 +825,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.cleanup\"}[5m]))",
"expr": "sum by (service_instance_id) (rate(span_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.cleanup\"}[$__rate_interval]))",
"legendFormat": "Cleanups / Sec [{{service_instance_id}}]"
}
],
@@ -967,7 +925,7 @@
{
"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(span_calls_total, service_instance_id)",
"datasource": {

12
docker/telemetry/grafana/dashboards/validator-health.json
View File

@@ -295,7 +295,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(validations_sent_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) * 60",
"expr": "rate(validations_sent_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) * 60",
"legendFormat": "Sent/min [{{service_instance_id}}]"
}
],
@@ -345,7 +345,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(validations_checked_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) * 60",
"expr": "rate(validations_checked_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) * 60",
"legendFormat": "Checked/min [{{service_instance_id}}]"
}
],
@@ -561,7 +561,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(validation_agreements_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) * 60",
"expr": "rate(validation_agreements_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) * 60",
"legendFormat": "Agreements/min [{{service_instance_id}}]"
},
{
@@ -569,7 +569,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(validation_missed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) * 60",
"expr": "rate(validation_missed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) * 60",
"legendFormat": "Missed/min [{{service_instance_id}}]"
}
],
@@ -757,7 +757,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "3600 * sum by (service_instance_id) (rate(state_changes_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[1h]))",
"expr": "3600 * sum by (service_instance_id) (rate(state_changes_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))",
"legendFormat": "Changes/hr [{{service_instance_id}}]"
}
],
@@ -807,7 +807,7 @@
"type": "prometheus",
"uid": "${DS_PROMETHEUS}"
},
"expr": "rate(ledgers_closed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m]) * 60",
"expr": "rate(ledgers_closed_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]) * 60",
"legendFormat": "Closed/min [{{service_instance_id}}]"
}
],

100
docs/telemetry-runbook.md
View File

@@ -748,8 +748,8 @@ The `OTelCollector` implementation exports metrics via OTLP/HTTP to the same OTe
| `peer_finder_active_outbound_peers` | PeerfinderManager.cpp:215 | Active outbound peer connections |
| `overlay_peer_disconnects` | OverlayImpl.h:557 | Peer disconnect count |
| `job_count` | JobQueue.cpp:26 | Current job queue depth |
| `{category}_bytes_in/Out` | OverlayImpl.h:535 | Overlay traffic bytes per category (57 categories) |
| `{category}_messages_in/Out` | OverlayImpl.h:535 | Overlay traffic messages per category |
| `{category}_bytes_in/out` | OverlayImpl.h:535 | Overlay traffic bytes per category (57 categories) |
| `{category}_messages_in/out` | OverlayImpl.h:535 | Overlay traffic messages per category |
#### OTel MetricsRegistry Gauges
@@ -900,16 +900,16 @@ Ten dashboards are pre-provisioned in `docker/telemetry/grafana/dashboards/`:
### Transaction Overview (`transaction-overview`)
| Panel | Type | PromQL | Labels Used |
| --------------------------------- | ---------- | --------------------------------------------------------------------- | ------------- |
| Transaction Processing Rate | timeseries | `rate(span_calls_total{span_name="tx.process"}[5m])` and `tx.receive` | `span_name` |
| Transaction Processing Latency | timeseries | `histogram_quantile(0.95 / 0.50, ... {span_name="tx.process"})` | — |
| Transaction Path Distribution | piechart | `sum by (local) (rate(span_calls_total{span_name="tx.process"}[5m]))` | `local` |
| Transaction Receive vs Suppressed | timeseries | `rate(span_calls_total{span_name="tx.receive"}[5m])` | — |
| TX Processing Duration Heatmap | heatmap | `tx.process` histogram buckets | `le` |
| TX Apply Duration per Ledger | timeseries | p95/p50 of `tx.apply` | — |
| Peer TX Receive Rate | timeseries | `tx.receive` rate | — |
| TX Apply Failed Rate | stat | `tx.apply` with `STATUS_CODE_ERROR` | `status_code` |
| Panel | Type | PromQL | Labels Used |
| --------------------------------- | ---------- | -------------------------------------------------------------------------------------------- | --------------------- |
| Transaction Processing Rate | timeseries | `rate(span_calls_total{span_name="tx.process"}[5m])` and `tx.receive` | `span_name` |
| Transaction Processing Latency | timeseries | `histogram_quantile(0.95 / 0.50, ... {span_name="tx.process"})` | — |
| Transaction Path Distribution | piechart | `sum by (local) (rate(span_calls_total{span_name="tx.process"}[5m]))` | `local` |
| Transaction Receive vs Suppressed | timeseries | `rate(span_calls_total{span_name="tx.receive"}[5m])` | — |
| TX Processing Duration Heatmap | heatmap | `tx.process` histogram buckets | `le` |
| TX Apply Duration per Ledger | timeseries | p95/p50 of `tx.apply` | — |
| Peer TX Receive Rate | timeseries | `tx.receive` rate | — |
| TX Apply Failed Rate | stat | `rate(span_calls_total{span_name="tx.transactor",stage="apply",ter_result!~"tesSUCCESS\|"})` | `stage`, `ter_result` |
### Consensus Health (`consensus-health`)
@@ -952,47 +952,47 @@ Requires `trace_peer=1` in the `[telemetry]` config section.
### Node Health -- System Metrics (`node-health`)
| Panel | Type | PromQL | Labels Used |
| -------------------------------------- | ---------- | --------------------------------------------------------- | ---------------- |
| Validated Ledger Age | stat | `ledgermaster_validated_ledger_age` | — |
| Published Ledger Age | stat | `ledgermaster_published_ledger_age` | — |
| Operating Mode Duration | timeseries | `state_accounting_*_duration` | — |
| Operating Mode Transitions | timeseries | `state_accounting_*_transitions` | — |
| I/O Latency | timeseries | `histogram_quantile(0.95, ios_latency_bucket)` | — |
| Job Queue Depth | timeseries | `job_count` | — |
| Ledger Fetch Rate | stat | `rate(ledger_fetches[5m])` | — |
| Ledger History Mismatches | stat | `rate(ledger_history_mismatch[5m])` | — |
| Key Jobs Execution Time | timeseries | `acceptledger{quantile="$quantile"}` (+ 10 more key jobs) | `quantile` |
| Key Jobs Dequeue Wait Time | timeseries | `acceptledger_q{quantile="$quantile"}` (+ 10 more) | `quantile` |
| FullBelowCache Size | timeseries | `node_family_full_below_cache_size` | — |
| FullBelowCache Hit Rate | gauge | `node_family_full_below_cache_hit_rate` | — |
| Ledger Publish Gap | stat | `Published_Ledger_Age - Validated_Ledger_Age` | — |
| State Duration Rate (Full vs Tracking) | timeseries | `rate(state_accounting_full_duration[5m]) / 1000000` | — |
| All Jobs Execution Time (Detail) | timeseries | `{__name__=~"<all_jobs>", quantile="$quantile"}` | `quantile` |
| All Jobs Dequeue Wait (Detail) | timeseries | `{__name__=~"<all_jobs>_q", quantile="$quantile"}` | `quantile` |
| Server State | stat | `server_info{metric="server_state"}` | `metric` |
| Uptime | stat | `server_info{metric="uptime"}` | `metric` |
| Peer Count | stat | `server_info{metric="peers"}` | `metric` |
| Validated Ledger Seq | stat | `server_info{metric="validated_ledger_seq"}` | `metric` |
| Build Version | stat | `build_info` | `version` |
| Complete Ledger Ranges | table | `complete_ledgers` | `bound`, `index` |
| Database Sizes | timeseries | `db_metrics{metric=~"db_kb_.*"}` | `metric` |
| Historical Fetch Rate | stat | `db_metrics{metric="historical_perminute"}` | `metric` |
| Panel | Type | PromQL | Labels Used |
| -------------------------------------- | ---------- | ---------------------------------------------------------- | ---------------- |
| Validated Ledger Age | stat | `ledgermaster_validated_ledger_age` | — |
| Published Ledger Age | stat | `ledgermaster_published_ledger_age` | — |
| Operating Mode (Time Share) | timeseries | `rate(state_accounting_X_duration) / sum(rate(all modes))` | — |
| Operating Mode Transitions | timeseries | `state_accounting_*_transitions` | — |
| I/O Latency | timeseries | `histogram_quantile(0.95, ios_latency_bucket)` | — |
| Job Queue Depth | timeseries | `job_count` | — |
| Ledger Fetch Rate | stat | `rate(ledger_fetches[5m])` | — |
| Ledger History Mismatches | stat | `rate(ledger_history_mismatch[5m])` | — |
| Key Jobs Execution Time | timeseries | `acceptledger{quantile="$quantile"}` (+ 10 more key jobs) | `quantile` |
| Key Jobs Dequeue Wait Time | timeseries | `acceptledger_q{quantile="$quantile"}` (+ 10 more) | `quantile` |
| FullBelowCache Size | timeseries | `node_family_full_below_cache_size` | — |
| FullBelowCache Hit Rate | gauge | `node_family_full_below_cache_hit_rate` | — |
| Ledger Publish Gap | stat | `Published_Ledger_Age - Validated_Ledger_Age` | — |
| State Duration Rate (Full vs Tracking) | timeseries | `rate(state_accounting_full_duration[5m]) / 1000000` | — |
| All Jobs Execution Time (Detail) | timeseries | `{__name__=~"<all_jobs>", quantile="$quantile"}` | `quantile` |
| All Jobs Dequeue Wait (Detail) | timeseries | `{__name__=~"<all_jobs>_q", quantile="$quantile"}` | `quantile` |
| Server State | stat | `server_info{metric="server_state"}` | `metric` |
| Uptime | stat | `server_info{metric="uptime"}` | `metric` |
| Peer Count | stat | `server_info{metric="peers"}` | `metric` |
| Validated Ledger Seq | stat | `server_info{metric="validated_ledger_seq"}` | `metric` |
| Build Version | stat | `build_info` | `version` |
| Complete Ledger Ranges | table | `complete_ledgers` | `bound`, `index` |
| Database Sizes | timeseries | `db_metrics{metric=~"db_kb_.*"}` | `metric` |
| Historical Fetch Rate | stat | `db_metrics{metric="historical_perminute"}` | `metric` |
### Network Traffic -- System Metrics (`network-traffic`)
| Panel | Type | PromQL | Labels Used |
| ------------------------------------ | ---------- | ------------------------------------ | ----------- |
| Active Peers | timeseries | `peer_finder_active_*_Peers` | — |
| Peer Disconnects | timeseries | `overlay_peer_disconnects` | — |
| Total Network Bytes | timeseries | `rate(total_bytes_in/Out[5m])` | — |
| Total Network Messages | timeseries | `total_messages_in/Out` | — |
| Transaction Traffic | timeseries | `transactions_messages_in/Out` | — |
| Proposal Traffic | timeseries | `proposals_messages_in/Out` | — |
| Validation Traffic | timeseries | `validations_messages_in/Out` | — |
| Traffic by Category | bargauge | `topk(10, *_bytes_in)` | — |
| Duplicate Traffic (Wasted Bandwidth) | timeseries | `rate(*_duplicate_bytes_in/out[5m])` | — |
| All Traffic Categories (Detail) | timeseries | `topk(15, rate(*_bytes_in[5m]))` | — |
| Panel | Type | PromQL | Labels Used |
| ------------------------------------ | ---------- | ------------------------------------------------------ | ----------- |
| Active Peers | timeseries | `peer_finder_active_*_peers` | — |
| Peer Disconnects | timeseries | `increase(overlay_peer_disconnects[$__rate_interval])` | — |
| Total Network Bytes | timeseries | `rate(total_bytes_in/out[$__rate_interval])` | — |
| Total Network Messages | timeseries | `rate(total_messages_in/out[$__rate_interval])` | — |
| Transaction Traffic | timeseries | `rate(transactions_messages_in/out[$__rate_interval])` | — |
| Proposal Traffic | timeseries | `rate(proposals_messages_in/out[$__rate_interval])` | — |
| Validation Traffic | timeseries | `rate(validations_messages_in/out[$__rate_interval])` | — |
| Traffic by Category | bargauge | `topk(10, rate(*_bytes_in[$__rate_interval]))` | — |
| Duplicate Traffic (Wasted Bandwidth) | timeseries | `rate(*_duplicate_bytes_in/out[$__rate_interval])` | — |
| All Traffic Categories (Detail) | timeseries | `topk(15, rate(*_bytes_in[$__rate_interval]))` | — |
### RPC & Pathfinding -- System Metrics (`rpc-pathfinding`)

33
src/xrpld/telemetry/MetricsRegistry.cpp
View File

@@ -254,8 +254,30 @@ MetricsRegistry::initSyncInstruments()
"validations_checked_total", "Total network validations received and checked");
stateChangesCounter_ =
meter_->CreateUInt64Counter("state_changes_total", "Total operating mode changes");
jqTransOverflowCounter_ = meter_->CreateUInt64Counter(
// jq_trans_overflow_total is observed from Overlay's existing cumulative
// atomic (Overlay::getJqTransOverflow()) rather than pushed. The overlay
// owns the only increment site (PeerImp), so an ObservableCounter reads the
// live total each collection cycle without threading a push path through
// develop-owned overlay code.
jqTransOverflowObservable_ = meter_->CreateInt64ObservableCounter(
"jq_trans_overflow_total", "Total job queue transaction overflows");
jqTransOverflowObservable_->AddCallback(
[](opentelemetry::metrics::ObserverResult result, void* state) {
auto* self = static_cast<MetricsRegistry*>(state);
if (self->callbacksDetached_.load(std::memory_order_acquire))
return;
try
{
opentelemetry::nostd::get<opentelemetry::nostd::shared_ptr<
opentelemetry::metrics::ObserverResultT<int64_t>>>(result)
->Observe(static_cast<int64_t>(self->app_.getOverlay().getJqTransOverflow()));
}
catch (...) // NOLINT(bugprone-empty-catch)
{
// Silently skip on error.
}
},
this);
ledgerHistoryMismatchCounter_ = meter_->CreateUInt64Counter(
"ledger_history_mismatch_total", "Total built-vs-validated ledger mismatches by reason");
txqExpiredCounter_ = meter_->CreateUInt64Counter(
@@ -1458,15 +1480,6 @@ MetricsRegistry::incrementStateChanges()
#endif
}
void
MetricsRegistry::incrementJqTransOverflow()
{
#ifdef XRPL_ENABLE_TELEMETRY
if (enabled_ && jqTransOverflowCounter_)
jqTransOverflowCounter_->Add(1);
#endif
}
void
MetricsRegistry::incrementLedgerHistoryMismatch(std::string_view reason)
{

16
src/xrpld/telemetry/MetricsRegistry.h
View File

@@ -36,7 +36,6 @@
| +-- validations_sent_total
| +-- validations_checked_total
| +-- state_changes_total
| +-- jq_trans_overflow_total
| +-- ledger_history_mismatch_total{reason}
| +-- txq_expired_total
| +-- txq_dropped_total{reason}
@@ -61,6 +60,7 @@
+-- State tracking (mode value, time in state)
+-- Storage detail (NuDB sizes)
+-- Validation agreement (1h/24h pct, counts)
+-- jq_trans_overflow_total (observed from Overlay)
Control-flow for async gauges:
@@ -347,13 +347,6 @@ public:
void
incrementStateChanges();
/** Increment the jq_trans_overflow_total counter.
Called when the job queue transaction limit overflows (mirrors
Overlay::incJqTransOverflow()).
*/
void
incrementJqTransOverflow();
/** Increment the ledger_history_mismatch_total counter for a reason.
Called from LedgerHistory::handleMismatch() once the mismatch has
been classified. The reason label turns fork diagnosis from a
@@ -517,9 +510,10 @@ private:
/// Counter: state_changes_total — incremented on operating mode transitions.
opentelemetry::nostd::unique_ptr<opentelemetry::metrics::Counter<uint64_t>>
stateChangesCounter_;
/// Counter: jq_trans_overflow_total — incremented on job queue transaction overflows.
opentelemetry::nostd::unique_ptr<opentelemetry::metrics::Counter<uint64_t>>
jqTransOverflowCounter_;
/// ObservableCounter: jq_trans_overflow_total — observed from
/// Overlay::getJqTransOverflow() (cumulative overflow tally owned by the overlay).
opentelemetry::nostd::shared_ptr<opentelemetry::metrics::ObservableInstrument>
jqTransOverflowObservable_;
/// Counter: ledger_history_mismatch_total{reason} — incremented per classified
/// built-vs-validated ledger mismatch.
opentelemetry::nostd::unique_ptr<opentelemetry::metrics::Counter<uint64_t>>