ARCHIVE/rippled
1
0
Fork 0
mirror of https://github.com/XRPLF/rippled.git synced 2026-06-02 16:26:48 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(telemetry): align Phase 9 dashboards and integration-test with xrpld_ metric prefix

Browse Source 
MetricsRegistry emits OTel SDK metrics with the xrpld_ prefix
(MetricsRegistry.cpp defines "xrpld_nodestore_state",
"xrpld_cache_metrics", etc.), but the Phase 9 dashboards and the
Step 10c integration-test assertions introduced in 892fee638a
queried the rippled_ prefix. Every Phase 9 panel and assertion
therefore rendered "No data" or failed on a live run, even though
the underlying series were being exported correctly.

Rename the rippled_ prefix to xrpld_ for every MetricsRegistry
metric in dashboards and the integration test:

- nodestore_state, cache_metrics, txq_metrics, load_factor_metrics,
  object_count
- rpc_method_started_total / _finished_total / _errored_total /
  _duration_us_bucket
- job_queued_total / _started_total / _finished_total /
  _queued_duration_us_bucket / _running_duration_us_bucket
- peer_quality, server_info, validator_health, ledger_economy,
  db_metrics, complete_ledgers, build_info, state_tracking
- ledgers_closed_total, validations_sent_total,
  validations_checked_total, state_changes_total
- validation_agreement (ValidationTracker 1h/24h/7d windows)

Also add ValidationTracker window-gauge assertions to Step 10c of
integration-test.sh so the 1h/24h/7d agreement and miss counts are
checked alongside the other Phase 9 gauges.

The rippled_ prefix is preserved for beast::insight metrics
(rippled_LedgerMaster_*, rippled_Peer_Finder_*, rippled_total_*,
rippled_Overlay_*, rippled_State_Accounting_*, rippled_transactions_*,
rippled_proposals_*, rippled_validations_Messages_*) because those
flow through the StatsD-style OTelCollector configured with
`[insight] prefix=rippled` and remain on that prefix by design.

Verified against a live 6-node consensus network: all 22 Phase 9 +
ValidationTracker assertions now report 6+ series per metric.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
Pratik Mankawde
2026-05-13 14:59:00 +01:00
parent 4cbb1be5b4
commit 5601615952
7 changed files with 120 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
docker/telemetry/grafana/dashboards/rippled-fee-market.json
View File

@@ -30,14 +30,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_count\"}",
"expr": "xrpld_txq_metrics{exported_instance=~\"$node\", metric=\"txq_count\"}",
"legendFormat": "Queue Depth [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_max_size\"}",
"expr": "xrpld_txq_metrics{exported_instance=~\"$node\", metric=\"txq_max_size\"}",
"legendFormat": "Max Capacity [{{exported_instance}}]"
}
],
@@ -78,14 +78,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_in_ledger\"}",
"expr": "xrpld_txq_metrics{exported_instance=~\"$node\", metric=\"txq_in_ledger\"}",
"legendFormat": "In Ledger [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_per_ledger\"}",
"expr": "xrpld_txq_metrics{exported_instance=~\"$node\", metric=\"txq_per_ledger\"}",
"legendFormat": "Expected Per Ledger [{{exported_instance}}]"
}
],
@@ -126,28 +126,28 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_reference_fee_level\"}",
"expr": "xrpld_txq_metrics{exported_instance=~\"$node\", metric=\"txq_reference_fee_level\"}",
"legendFormat": "Reference Fee Level [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_min_processing_fee_level\"}",
"expr": "xrpld_txq_metrics{exported_instance=~\"$node\", metric=\"txq_min_processing_fee_level\"}",
"legendFormat": "Min Processing Fee Level [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_med_fee_level\"}",
"expr": "xrpld_txq_metrics{exported_instance=~\"$node\", metric=\"txq_med_fee_level\"}",
"legendFormat": "Median Fee Level [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_open_ledger_fee_level\"}",
"expr": "xrpld_txq_metrics{exported_instance=~\"$node\", metric=\"txq_open_ledger_fee_level\"}",
"legendFormat": "Open Ledger Fee Level [{{exported_instance}}]"
}
],
@@ -192,28 +192,28 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor\"}",
"expr": "xrpld_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor\"}",
"legendFormat": "Combined Load Factor [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_server\"}",
"expr": "xrpld_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_server\"}",
"legendFormat": "Server [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_fee_escalation\"}",
"expr": "xrpld_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_fee_escalation\"}",
"legendFormat": "Fee Escalation [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_fee_queue\"}",
"expr": "xrpld_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_fee_queue\"}",
"legendFormat": "Fee Queue [{{exported_instance}}]"
}
],
@@ -270,21 +270,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_local\"}",
"expr": "xrpld_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_local\"}",
"legendFormat": "Local [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_net\"}",
"expr": "xrpld_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_net\"}",
"legendFormat": "Network [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_cluster\"}",
"expr": "xrpld_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_cluster\"}",
"legendFormat": "Cluster [{{exported_instance}}]"
}
],

26
docker/telemetry/grafana/dashboards/rippled-job-queue.json
View File

@@ -30,21 +30,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "sum by (exported_instance) (rate(rippled_job_queued_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"expr": "sum by (exported_instance) (rate(xrpld_job_queued_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"legendFormat": "Queued/s [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "sum by (exported_instance) (rate(rippled_job_started_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"expr": "sum by (exported_instance) (rate(xrpld_job_started_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"legendFormat": "Started/s [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "sum by (exported_instance) (rate(rippled_job_finished_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"expr": "sum by (exported_instance) (rate(xrpld_job_finished_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"legendFormat": "Finished/s [{{exported_instance}}]"
}
],
@@ -94,7 +94,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_job_queued_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"expr": "topk(10, rate(xrpld_job_queued_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"legendFormat": "{{job_type}} [{{exported_instance}}]"
}
],
@@ -144,7 +144,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_job_finished_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"expr": "topk(10, rate(xrpld_job_finished_total{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))",
"legendFormat": "{{job_type}} [{{exported_instance}}]"
}
],
@@ -189,21 +189,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(rippled_job_queued_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"legendFormat": "P50 [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(rippled_job_queued_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"legendFormat": "P95 [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.99, sum by (le, exported_instance) (rate(rippled_job_queued_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"expr": "histogram_quantile(0.99, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"legendFormat": "P99 [{{exported_instance}}]"
}
],
@@ -248,21 +248,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"legendFormat": "P50 [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"legendFormat": "P95 [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.99, sum by (le, exported_instance) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"expr": "histogram_quantile(0.99, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m])))",
"legendFormat": "P99 [{{exported_instance}}]"
}
],
@@ -312,7 +312,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, histogram_quantile(0.95, sum by (le, job_type, exported_instance) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))))",
"expr": "topk(10, histogram_quantile(0.95, sum by (le, job_type, exported_instance) (rate(xrpld_job_running_duration_us_bucket{exported_instance=~\"$node\", job_type=~\"$job_type\"}[5m]))))",
"legendFormat": "{{job_type}} [{{exported_instance}}]"
}
],
@@ -366,7 +366,7 @@
"label": "Job Type",
"description": "Filter by job type",
"type": "query",
"query": "label_values(rippled_job_queued_total, job_type)",
"query": "label_values(xrpld_job_queued_total, job_type)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"

12
docker/telemetry/grafana/dashboards/rippled-peer-quality.json
View File

@@ -30,7 +30,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_peer_quality{metric=\"peer_latency_p90_ms\",exported_instance=~\"$node\"}",
"expr": "xrpld_peer_quality{metric=\"peer_latency_p90_ms\",exported_instance=~\"$node\"}",
"legendFormat": "P90 Latency [{{exported_instance}}]"
}
],
@@ -91,7 +91,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_peer_quality{metric=\"peers_insane_count\",exported_instance=~\"$node\"}",
"expr": "xrpld_peer_quality{metric=\"peers_insane_count\",exported_instance=~\"$node\"}",
"legendFormat": "Insane Peers [{{exported_instance}}]"
}
],
@@ -140,7 +140,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_peer_quality{metric=\"peers_higher_version_pct\",exported_instance=~\"$node\"}",
"expr": "xrpld_peer_quality{metric=\"peers_higher_version_pct\",exported_instance=~\"$node\"}",
"legendFormat": "Higher Version % [{{exported_instance}}]"
}
],
@@ -191,7 +191,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_peer_quality{metric=\"upgrade_recommended\",exported_instance=~\"$node\"}",
"expr": "xrpld_peer_quality{metric=\"upgrade_recommended\",exported_instance=~\"$node\"}",
"legendFormat": "Upgrade [{{exported_instance}}]"
}
],
@@ -250,7 +250,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_server_info{metric=\"peer_disconnects_resources\",exported_instance=~\"$node\"}",
"expr": "xrpld_server_info{metric=\"peer_disconnects_resources\",exported_instance=~\"$node\"}",
"legendFormat": "Disconnects [{{exported_instance}}]"
}
],
@@ -365,7 +365,7 @@
"label": "Node",
"description": "Filter by rippled node (service.instance.id)",
"type": "query",
"query": "label_values(rippled_peer_quality, exported_instance)",
"query": "label_values(xrpld_peer_quality, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"

22
docker/telemetry/grafana/dashboards/rippled-rpc-perf.json
View File

@@ -30,21 +30,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "sum by (exported_instance) (rate(rippled_rpc_method_started_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"expr": "sum by (exported_instance) (rate(xrpld_rpc_method_started_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"legendFormat": "Started/s [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "sum by (exported_instance) (rate(rippled_rpc_method_finished_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"expr": "sum by (exported_instance) (rate(xrpld_rpc_method_finished_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"legendFormat": "Finished/s [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "sum by (exported_instance) (rate(rippled_rpc_method_errored_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"expr": "sum by (exported_instance) (rate(xrpld_rpc_method_errored_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"legendFormat": "Errored/s [{{exported_instance}}]"
}
],
@@ -94,7 +94,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_rpc_method_started_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"expr": "topk(10, rate(xrpld_rpc_method_started_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"legendFormat": "{{method}} [{{exported_instance}}]"
}
],
@@ -144,7 +144,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_rpc_method_errored_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"expr": "topk(10, rate(xrpld_rpc_method_errored_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]))",
"legendFormat": "{{method}} [{{exported_instance}}]"
}
],
@@ -189,21 +189,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\", method=~\"$method\"}[5m])))",
"expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(xrpld_rpc_method_duration_us_bucket{exported_instance=~\"$node\", method=~\"$method\"}[5m])))",
"legendFormat": "P50 [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\", method=~\"$method\"}[5m])))",
"expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(xrpld_rpc_method_duration_us_bucket{exported_instance=~\"$node\", method=~\"$method\"}[5m])))",
"legendFormat": "P95 [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.99, sum by (le, exported_instance) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\", method=~\"$method\"}[5m])))",
"expr": "histogram_quantile(0.99, sum by (le, exported_instance) (rate(xrpld_rpc_method_duration_us_bucket{exported_instance=~\"$node\", method=~\"$method\"}[5m])))",
"legendFormat": "P99 [{{exported_instance}}]"
}
],
@@ -253,7 +253,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, histogram_quantile(0.95, sum by (le, method, exported_instance) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\", method=~\"$method\"}[5m]))))",
"expr": "topk(10, histogram_quantile(0.95, sum by (le, method, exported_instance) (rate(xrpld_rpc_method_duration_us_bucket{exported_instance=~\"$node\", method=~\"$method\"}[5m]))))",
"legendFormat": "{{method}} [{{exported_instance}}]"
}
],
@@ -303,7 +303,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_rpc_method_errored_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]) / (rate(rippled_rpc_method_started_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]) > 0))",
"expr": "topk(10, rate(xrpld_rpc_method_errored_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]) / (rate(xrpld_rpc_method_started_total{exported_instance=~\"$node\", method=~\"$method\"}[5m]) > 0))",
"legendFormat": "{{method}} [{{exported_instance}}]"
}
],
@@ -375,7 +375,7 @@
"label": "RPC Method",
"description": "Filter by RPC method",
"type": "query",
"query": "label_values(rippled_rpc_method_started_total, method)",
"query": "label_values(xrpld_rpc_method_started_total, method)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"

32
docker/telemetry/grafana/dashboards/rippled-validator-health.json
View File

@@ -42,7 +42,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validation_agreement{metric=\"agreement_pct_1h\",exported_instance=~\"$node\"}",
"expr": "xrpld_validation_agreement{metric=\"agreement_pct_1h\",exported_instance=~\"$node\"}",
"legendFormat": "Agreement 1h [{{exported_instance}}]"
}
],
@@ -93,7 +93,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validation_agreement{metric=\"agreement_pct_24h\",exported_instance=~\"$node\"}",
"expr": "xrpld_validation_agreement{metric=\"agreement_pct_24h\",exported_instance=~\"$node\"}",
"legendFormat": "Agreement 24h [{{exported_instance}}]"
}
],
@@ -146,14 +146,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validation_agreement{metric=\"agreements_1h\",exported_instance=~\"$node\"}",
"expr": "xrpld_validation_agreement{metric=\"agreements_1h\",exported_instance=~\"$node\"}",
"legendFormat": "Agreements 1h [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validation_agreement{metric=\"missed_1h\",exported_instance=~\"$node\"}",
"expr": "xrpld_validation_agreement{metric=\"missed_1h\",exported_instance=~\"$node\"}",
"legendFormat": "Missed 1h [{{exported_instance}}]"
}
],
@@ -212,14 +212,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validation_agreement{metric=\"agreements_24h\",exported_instance=~\"$node\"}",
"expr": "xrpld_validation_agreement{metric=\"agreements_24h\",exported_instance=~\"$node\"}",
"legendFormat": "Agreements 24h [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validation_agreement{metric=\"missed_24h\",exported_instance=~\"$node\"}",
"expr": "xrpld_validation_agreement{metric=\"missed_24h\",exported_instance=~\"$node\"}",
"legendFormat": "Missed 24h [{{exported_instance}}]"
}
],
@@ -288,7 +288,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_validations_sent_total{exported_instance=~\"$node\"}[5m]) * 60",
"expr": "rate(xrpld_validations_sent_total{exported_instance=~\"$node\"}[5m]) * 60",
"legendFormat": "Sent/min [{{exported_instance}}]"
}
],
@@ -337,7 +337,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_validations_checked_total{exported_instance=~\"$node\"}[5m]) * 60",
"expr": "rate(xrpld_validations_checked_total{exported_instance=~\"$node\"}[5m]) * 60",
"legendFormat": "Checked/min [{{exported_instance}}]"
}
],
@@ -370,7 +370,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validator_health{metric=\"amendment_blocked\",exported_instance=~\"$node\"}",
"expr": "xrpld_validator_health{metric=\"amendment_blocked\",exported_instance=~\"$node\"}",
"legendFormat": "Blocked [{{exported_instance}}]"
}
],
@@ -429,7 +429,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validator_health{metric=\"unl_expiry_days\",exported_instance=~\"$node\"}",
"expr": "xrpld_validator_health{metric=\"unl_expiry_days\",exported_instance=~\"$node\"}",
"legendFormat": "UNL Expiry [{{exported_instance}}]"
}
],
@@ -490,7 +490,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_validator_health{metric=\"validation_quorum\",exported_instance=~\"$node\"}",
"expr": "xrpld_validator_health{metric=\"validation_quorum\",exported_instance=~\"$node\"}",
"legendFormat": "Quorum [{{exported_instance}}]"
}
],
@@ -523,7 +523,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_state_tracking{metric=\"state_value\",exported_instance=~\"$node\"}",
"expr": "xrpld_state_tracking{metric=\"state_value\",exported_instance=~\"$node\"}",
"legendFormat": "State [{{exported_instance}}]"
}
],
@@ -568,7 +568,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_state_tracking{metric=\"time_in_current_state_seconds\",exported_instance=~\"$node\"}",
"expr": "xrpld_state_tracking{metric=\"time_in_current_state_seconds\",exported_instance=~\"$node\"}",
"legendFormat": "Time in State [{{exported_instance}}]"
}
],
@@ -601,7 +601,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_state_changes_total{exported_instance=~\"$node\"}[1h])",
"expr": "rate(xrpld_state_changes_total{exported_instance=~\"$node\"}[1h])",
"legendFormat": "Changes/hr [{{exported_instance}}]"
}
],
@@ -650,7 +650,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rate(rippled_ledgers_closed_total{exported_instance=~\"$node\"}[5m]) * 60",
"expr": "rate(xrpld_ledgers_closed_total{exported_instance=~\"$node\"}[5m]) * 60",
"legendFormat": "Closed/min [{{exported_instance}}]"
}
],
@@ -688,7 +688,7 @@
"label": "Node",
"description": "Filter by rippled node (service.instance.id)",
"type": "query",
"query": "label_values(rippled_validation_agreement, exported_instance)",
"query": "label_values(xrpld_validation_agreement, exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"

62
docker/telemetry/grafana/dashboards/system-node-health.json
View File

@@ -437,21 +437,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"node_reads_total\"}",
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"node_reads_total\"}",
"legendFormat": "Reads Total [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"node_reads_hit\"}",
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"node_reads_hit\"}",
"legendFormat": "Reads Hit (cache) [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"node_writes\"}",
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"node_writes\"}",
"legendFormat": "Writes Total [{{exported_instance}}]"
}
],
@@ -492,14 +492,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"write_load\"}",
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"write_load\"}",
"legendFormat": "Write Load [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"read_queue\"}",
"expr": "xrpld_nodestore_state{exported_instance=~\"$node\", metric=\"read_queue\"}",
"legendFormat": "Read Queue [{{exported_instance}}]"
}
],
@@ -568,21 +568,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"SLE_hit_rate\"}",
"expr": "xrpld_cache_metrics{exported_instance=~\"$node\", metric=\"SLE_hit_rate\"}",
"legendFormat": "SLE Hit Rate [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"ledger_hit_rate\"}",
"expr": "xrpld_cache_metrics{exported_instance=~\"$node\", metric=\"ledger_hit_rate\"}",
"legendFormat": "Ledger Hit Rate [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"AL_hit_rate\"}",
"expr": "xrpld_cache_metrics{exported_instance=~\"$node\", metric=\"AL_hit_rate\"}",
"legendFormat": "AcceptedLedger Hit Rate [{{exported_instance}}]"
}
],
@@ -629,21 +629,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"treenode_cache_size\"}",
"expr": "xrpld_cache_metrics{exported_instance=~\"$node\", metric=\"treenode_cache_size\"}",
"legendFormat": "TreeNode Cache [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"treenode_track_size\"}",
"expr": "xrpld_cache_metrics{exported_instance=~\"$node\", metric=\"treenode_track_size\"}",
"legendFormat": "TreeNode Track [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"fullbelow_size\"}",
"expr": "xrpld_cache_metrics{exported_instance=~\"$node\", metric=\"fullbelow_size\"}",
"legendFormat": "FullBelow [{{exported_instance}}]"
}
],
@@ -701,7 +701,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(15, rippled_object_count{exported_instance=~\"$node\", type=~\"$type\"})",
"expr": "topk(15, xrpld_object_count{exported_instance=~\"$node\", type=~\"$type\"})",
"legendFormat": "{{type}} [{{exported_instance}}]"
}
],
@@ -754,7 +754,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_server_info{exported_instance=~\"$node\", metric=\"server_state\"}",
"expr": "xrpld_server_info{exported_instance=~\"$node\", metric=\"server_state\"}",
"legendFormat": "State [{{exported_instance}}]"
}
],
@@ -809,7 +809,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_server_info{exported_instance=~\"$node\", metric=\"uptime\"}",
"expr": "xrpld_server_info{exported_instance=~\"$node\", metric=\"uptime\"}",
"legendFormat": "Uptime [{{exported_instance}}]"
}
],
@@ -842,7 +842,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_server_info{exported_instance=~\"$node\", metric=\"peers\"}",
"expr": "xrpld_server_info{exported_instance=~\"$node\", metric=\"peers\"}",
"legendFormat": "Peers [{{exported_instance}}]"
}
],
@@ -875,7 +875,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_server_info{exported_instance=~\"$node\", metric=\"validated_ledger_seq\"}",
"expr": "xrpld_server_info{exported_instance=~\"$node\", metric=\"validated_ledger_seq\"}",
"legendFormat": "Seq [{{exported_instance}}]"
}
],
@@ -908,14 +908,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_server_info{exported_instance=~\"$node\", metric=\"last_close_proposers\"}",
"expr": "xrpld_server_info{exported_instance=~\"$node\", metric=\"last_close_proposers\"}",
"legendFormat": "Proposers [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_server_info{exported_instance=~\"$node\", metric=\"last_close_converge_time_ms\"}",
"expr": "xrpld_server_info{exported_instance=~\"$node\", metric=\"last_close_converge_time_ms\"}",
"legendFormat": "Converge Time ms [{{exported_instance}}]"
}
],
@@ -956,7 +956,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_build_info{exported_instance=~\"$node\"}",
"expr": "xrpld_build_info{exported_instance=~\"$node\"}",
"legendFormat": "v{{version}} [{{exported_instance}}]"
}
],
@@ -998,7 +998,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_complete_ledgers{exported_instance=~\"$node\"}",
"expr": "xrpld_complete_ledgers{exported_instance=~\"$node\"}",
"legendFormat": "{{bound}} [range {{index}}] [{{exported_instance}}]",
"format": "table",
"instant": true
@@ -1033,21 +1033,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_db_metrics{exported_instance=~\"$node\", metric=\"db_kb_total\"}",
"expr": "xrpld_db_metrics{exported_instance=~\"$node\", metric=\"db_kb_total\"}",
"legendFormat": "Total KB [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_db_metrics{exported_instance=~\"$node\", metric=\"db_kb_ledger\"}",
"expr": "xrpld_db_metrics{exported_instance=~\"$node\", metric=\"db_kb_ledger\"}",
"legendFormat": "Ledger KB [{{exported_instance}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_db_metrics{exported_instance=~\"$node\", metric=\"db_kb_transaction\"}",
"expr": "xrpld_db_metrics{exported_instance=~\"$node\", metric=\"db_kb_transaction\"}",
"legendFormat": "Transaction KB [{{exported_instance}}]"
}
],
@@ -1088,7 +1088,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_db_metrics{exported_instance=~\"$node\", metric=\"historical_perminute\"}",
"expr": "xrpld_db_metrics{exported_instance=~\"$node\", metric=\"historical_perminute\"}",
"legendFormat": "Fetches/min [{{exported_instance}}]"
}
],
@@ -1121,7 +1121,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_server_info{exported_instance=~\"$node\", metric=\"peer_disconnects_resources\"}",
"expr": "xrpld_server_info{exported_instance=~\"$node\", metric=\"peer_disconnects_resources\"}",
"legendFormat": "Resource Disconnects [{{exported_instance}}]"
}
],
@@ -1173,7 +1173,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_economy{metric=\"base_fee_xrp\",exported_instance=~\"$node\"}",
"expr": "xrpld_ledger_economy{metric=\"base_fee_xrp\",exported_instance=~\"$node\"}",
"legendFormat": "Base Fee [{{exported_instance}}]"
}
],
@@ -1206,7 +1206,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_economy{metric=\"reserve_base_xrp\",exported_instance=~\"$node\"}",
"expr": "xrpld_ledger_economy{metric=\"reserve_base_xrp\",exported_instance=~\"$node\"}",
"legendFormat": "Reserve Base [{{exported_instance}}]"
}
],
@@ -1239,7 +1239,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_economy{metric=\"reserve_inc_xrp\",exported_instance=~\"$node\"}",
"expr": "xrpld_ledger_economy{metric=\"reserve_inc_xrp\",exported_instance=~\"$node\"}",
"legendFormat": "Reserve Inc [{{exported_instance}}]"
}
],
@@ -1272,7 +1272,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_economy{metric=\"ledger_age_seconds\",exported_instance=~\"$node\"}",
"expr": "xrpld_ledger_economy{metric=\"ledger_age_seconds\",exported_instance=~\"$node\"}",
"legendFormat": "Ledger Age [{{exported_instance}}]"
}
],
@@ -1321,7 +1321,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_ledger_economy{metric=\"transaction_rate\",exported_instance=~\"$node\"}",
"expr": "xrpld_ledger_economy{metric=\"transaction_rate\",exported_instance=~\"$node\"}",
"legendFormat": "Tx Rate [{{exported_instance}}]"
}
],
@@ -1375,7 +1375,7 @@
"label": "Object Type",
"description": "Filter by internal object type (CountedObject<T> class name)",
"type": "query",
"query": "label_values(rippled_object_count, type)",
"query": "label_values(xrpld_object_count, type)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"

41
docker/telemetry/integration-test.sh
View File

@@ -658,31 +658,46 @@ check_otel_metric() {
}
# Task 9.1: NodeStore I/O
check_otel_metric 'rippled_nodestore_state{metric="node_reads_total"}'
check_otel_metric 'rippled_nodestore_state{metric="write_load"}'
check_otel_metric 'xrpld_nodestore_state{metric="node_reads_total"}'
check_otel_metric 'xrpld_nodestore_state{metric="write_load"}'
# Task 9.2: Cache hit rates
check_otel_metric 'rippled_cache_metrics{metric="SLE_hit_rate"}'
check_otel_metric 'rippled_cache_metrics{metric="treenode_cache_size"}'
check_otel_metric 'xrpld_cache_metrics{metric="SLE_hit_rate"}'
check_otel_metric 'xrpld_cache_metrics{metric="treenode_cache_size"}'
# Task 9.3: TxQ metrics
check_otel_metric 'rippled_txq_metrics{metric="txq_count"}'
check_otel_metric 'rippled_txq_metrics{metric="txq_reference_fee_level"}'
check_otel_metric 'xrpld_txq_metrics{metric="txq_count"}'
check_otel_metric 'xrpld_txq_metrics{metric="txq_reference_fee_level"}'
# Task 9.4: Per-RPC metrics
check_otel_metric "rippled_rpc_method_started_total"
check_otel_metric "rippled_rpc_method_finished_total"
check_otel_metric "xrpld_rpc_method_started_total"
check_otel_metric "xrpld_rpc_method_finished_total"
# Task 9.5: Per-job metrics
check_otel_metric "rippled_job_queued_total"
check_otel_metric "rippled_job_finished_total"
check_otel_metric "xrpld_job_queued_total"
check_otel_metric "xrpld_job_finished_total"
# Task 9.6: Counted object instances
check_otel_metric "rippled_object_count"
check_otel_metric "xrpld_object_count"
# Task 9.7: Load factor breakdown
check_otel_metric 'rippled_load_factor_metrics{metric="load_factor"}'
check_otel_metric 'rippled_load_factor_metrics{metric="load_factor_server"}'
check_otel_metric 'xrpld_load_factor_metrics{metric="load_factor"}'
check_otel_metric 'xrpld_load_factor_metrics{metric="load_factor_server"}'
# Task 7.15 / Phase 9: ValidationTracker rolling-window agreement gauge.
# MetricsRegistry::registerValidationAgreementGauge() publishes
# xrpld_validation_agreement with a `metric` label for each window
# (1h / 24h / 7d) plus the matching agreement/miss counts. The 7-day
# window matches the external xrpl-validator-dashboard parity target.
check_otel_metric 'xrpld_validation_agreement{metric="agreement_pct_1h"}'
check_otel_metric 'xrpld_validation_agreement{metric="agreement_pct_24h"}'
check_otel_metric 'xrpld_validation_agreement{metric="agreement_pct_7d"}'
check_otel_metric 'xrpld_validation_agreement{metric="agreements_1h"}'
check_otel_metric 'xrpld_validation_agreement{metric="missed_1h"}'
check_otel_metric 'xrpld_validation_agreement{metric="agreements_24h"}'
check_otel_metric 'xrpld_validation_agreement{metric="missed_24h"}'
check_otel_metric 'xrpld_validation_agreement{metric="agreements_7d"}'
check_otel_metric 'xrpld_validation_agreement{metric="missed_7d"}'
# ---------------------------------------------------------------------------
# Step 11: Summary