ARCHIVE/rippled
1
0
Fork 0
mirror of https://github.com/XRPLF/rippled.git synced 2026-03-13 00:02:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Phase 9: Add node template variable and instance filters to Grafana dashboards

Browse Source 
Add $node template variable (exported_instance) to rippled-fee-market,
rippled-job-queue, and rippled-rpc-perf dashboards enabling multi-node
filtering. Add $job_type variable to job-queue and $method variable to
rpc-perf dashboards. Inject exported_instance=~"$node" filter into all
PromQL queries across these dashboards including rate(), histogram_quantile(),
topk(), and sum() expressions. Also add the instance filter to Phase 9
panels (NodeStore, Cache, CountedObjects) in system-node-health dashboard.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Pratik Mankawde
2026-03-10 18:52:45 +00:00
parent 055b88687a
commit dfd052a87e
4 changed files with 155 additions and 52 deletions
Download Patch File Download Diff File Expand all files Collapse all files

53
docker/telemetry/grafana/dashboards/rippled-fee-market.json
View File

@@ -30,14 +30,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{metric=\"txq_count\"}",
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_count\"}",
"legendFormat": "Queue Depth"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{metric=\"txq_max_size\"}",
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_max_size\"}",
"legendFormat": "Max Capacity"
}
],
@@ -77,14 +77,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{metric=\"txq_in_ledger\"}",
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_in_ledger\"}",
"legendFormat": "In Ledger"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{metric=\"txq_per_ledger\"}",
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_per_ledger\"}",
"legendFormat": "Expected Per Ledger"
}
],
@@ -124,28 +124,28 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{metric=\"txq_reference_fee_level\"}",
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_reference_fee_level\"}",
"legendFormat": "Reference Fee Level"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{metric=\"txq_min_processing_fee_level\"}",
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_min_processing_fee_level\"}",
"legendFormat": "Min Processing Fee Level"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{metric=\"txq_med_fee_level\"}",
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_med_fee_level\"}",
"legendFormat": "Median Fee Level"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_txq_metrics{metric=\"txq_open_ledger_fee_level\"}",
"expr": "rippled_txq_metrics{exported_instance=~\"$node\", metric=\"txq_open_ledger_fee_level\"}",
"legendFormat": "Open Ledger Fee Level"
}
],
@@ -189,28 +189,28 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{metric=\"load_factor\"}",
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor\"}",
"legendFormat": "Combined Load Factor"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{metric=\"load_factor_server\"}",
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_server\"}",
"legendFormat": "Server"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{metric=\"load_factor_fee_escalation\"}",
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_fee_escalation\"}",
"legendFormat": "Fee Escalation"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{metric=\"load_factor_fee_queue\"}",
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_fee_queue\"}",
"legendFormat": "Fee Queue"
}
],
@@ -266,21 +266,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{metric=\"load_factor_local\"}",
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_local\"}",
"legendFormat": "Local"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{metric=\"load_factor_net\"}",
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_net\"}",
"legendFormat": "Network"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_load_factor_metrics{metric=\"load_factor_cluster\"}",
"expr": "rippled_load_factor_metrics{exported_instance=~\"$node\", metric=\"load_factor_cluster\"}",
"legendFormat": "Cluster"
}
],
@@ -303,7 +303,28 @@
"schemaVersion": 39,
"tags": ["rippled", "otel", "fee-market"],
"templating": {
"list": []
"list": [
{
"name": "node",
"label": "Node",
"description": "Filter by rippled node (service.instance.id)",
"type": "query",
"query": "label_values(exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
}
]
},
"time": {
"from": "now-1h",

67
docker/telemetry/grafana/dashboards/rippled-job-queue.json
View File

@@ -30,21 +30,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(rippled_job_queued_total[5m]))",
"expr": "sum(rate(rippled_job_queued_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "Queued/s"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(rippled_job_started_total[5m]))",
"expr": "sum(rate(rippled_job_started_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "Started/s"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(rippled_job_finished_total[5m]))",
"expr": "sum(rate(rippled_job_finished_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "Finished/s"
}
],
@@ -89,7 +89,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_job_queued_total[5m]))",
"expr": "topk(10, rate(rippled_job_queued_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "{{job_type}}"
}
],
@@ -134,7 +134,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_job_finished_total[5m]))",
"expr": "topk(10, rate(rippled_job_finished_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "{{job_type}}"
}
],
@@ -174,21 +174,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.50, sum by (le) (rate(rippled_job_queued_duration_us_bucket[5m])))",
"expr": "histogram_quantile(0.50, sum by (le) (rate(rippled_job_queued_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
"legendFormat": "p50"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le) (rate(rippled_job_queued_duration_us_bucket[5m])))",
"expr": "histogram_quantile(0.95, sum by (le) (rate(rippled_job_queued_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
"legendFormat": "p95"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.99, sum by (le) (rate(rippled_job_queued_duration_us_bucket[5m])))",
"expr": "histogram_quantile(0.99, sum by (le) (rate(rippled_job_queued_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
"legendFormat": "p99"
}
],
@@ -228,21 +228,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.50, sum by (le) (rate(rippled_job_running_duration_us_bucket[5m])))",
"expr": "histogram_quantile(0.50, sum by (le) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
"legendFormat": "p50"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le) (rate(rippled_job_running_duration_us_bucket[5m])))",
"expr": "histogram_quantile(0.95, sum by (le) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
"legendFormat": "p95"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.99, sum by (le) (rate(rippled_job_running_duration_us_bucket[5m])))",
"expr": "histogram_quantile(0.99, sum by (le) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
"legendFormat": "p99"
}
],
@@ -287,7 +287,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, histogram_quantile(0.95, sum by (le, job_type) (rate(rippled_job_running_duration_us_bucket[5m]))))",
"expr": "topk(10, histogram_quantile(0.95, sum by (le, job_type) (rate(rippled_job_running_duration_us_bucket{exported_instance=~\"$node\"}[5m]))))",
"legendFormat": "{{job_type}}"
}
],
@@ -310,7 +310,48 @@
"schemaVersion": 39,
"tags": ["rippled", "otel", "job-queue"],
"templating": {
"list": []
"list": [
{
"name": "node",
"label": "Node",
"description": "Filter by rippled node (service.instance.id)",
"type": "query",
"query": "label_values(exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
},
{
"name": "job_type",
"label": "Job Type",
"description": "Filter by job type",
"type": "query",
"query": "label_values(rippled_job_queued_total, job_type)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
}
]
},
"time": {
"from": "now-1h",

63
docker/telemetry/grafana/dashboards/rippled-rpc-perf.json
View File

@@ -30,21 +30,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(rippled_rpc_method_started_total[5m]))",
"expr": "sum(rate(rippled_rpc_method_started_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "Started/s"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(rippled_rpc_method_finished_total[5m]))",
"expr": "sum(rate(rippled_rpc_method_finished_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "Finished/s"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "sum(rate(rippled_rpc_method_errored_total[5m]))",
"expr": "sum(rate(rippled_rpc_method_errored_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "Errored/s"
}
],
@@ -89,7 +89,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_rpc_method_started_total[5m]))",
"expr": "topk(10, rate(rippled_rpc_method_started_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "{{method}}"
}
],
@@ -134,7 +134,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_rpc_method_errored_total[5m]))",
"expr": "topk(10, rate(rippled_rpc_method_errored_total{exported_instance=~\"$node\"}[5m]))",
"legendFormat": "{{method}}"
}
],
@@ -174,21 +174,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.50, sum by (le) (rate(rippled_rpc_method_duration_us_bucket[5m])))",
"expr": "histogram_quantile(0.50, sum by (le) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
"legendFormat": "p50"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.95, sum by (le) (rate(rippled_rpc_method_duration_us_bucket[5m])))",
"expr": "histogram_quantile(0.95, sum by (le) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
"legendFormat": "p95"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile(0.99, sum by (le) (rate(rippled_rpc_method_duration_us_bucket[5m])))",
"expr": "histogram_quantile(0.99, sum by (le) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\"}[5m])))",
"legendFormat": "p99"
}
],
@@ -233,7 +233,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, histogram_quantile(0.95, sum by (le, method) (rate(rippled_rpc_method_duration_us_bucket[5m]))))",
"expr": "topk(10, histogram_quantile(0.95, sum by (le, method) (rate(rippled_rpc_method_duration_us_bucket{exported_instance=~\"$node\"}[5m]))))",
"legendFormat": "{{method}}"
}
],
@@ -278,7 +278,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(10, rate(rippled_rpc_method_errored_total[5m]) / (rate(rippled_rpc_method_started_total[5m]) > 0))",
"expr": "topk(10, rate(rippled_rpc_method_errored_total{exported_instance=~\"$node\"}[5m]) / (rate(rippled_rpc_method_started_total{exported_instance=~\"$node\"}[5m]) > 0))",
"legendFormat": "{{method}}"
}
],
@@ -319,7 +319,48 @@
"schemaVersion": 39,
"tags": ["rippled", "otel", "rpc"],
"templating": {
"list": []
"list": [
{
"name": "node",
"label": "Node",
"description": "Filter by rippled node (service.instance.id)",
"type": "query",
"query": "label_values(exported_instance)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
},
{
"name": "method",
"label": "RPC Method",
"description": "Filter by RPC method",
"type": "query",
"query": "label_values(rippled_rpc_method_started_total, method)",
"datasource": {
"type": "prometheus",
"uid": "prometheus"
},
"includeAll": true,
"allValue": ".*",
"current": {
"text": "All",
"value": "$__all"
},
"multi": true,
"refresh": 2,
"sort": 1
}
]
},
"time": {
"from": "now-1h",

24
docker/telemetry/grafana/dashboards/system-node-health.json
View File

@@ -433,21 +433,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{metric=\"node_reads_total\"}",
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"node_reads_total\"}",
"legendFormat": "Reads Total"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{metric=\"node_reads_hit\"}",
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"node_reads_hit\"}",
"legendFormat": "Reads Hit (cache)"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{metric=\"node_writes\"}",
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"node_writes\"}",
"legendFormat": "Writes Total"
}
],
@@ -487,14 +487,14 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{metric=\"write_load\"}",
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"write_load\"}",
"legendFormat": "Write Load"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_nodestore_state{metric=\"read_queue\"}",
"expr": "rippled_nodestore_state{exported_instance=~\"$node\", metric=\"read_queue\"}",
"legendFormat": "Read Queue"
}
],
@@ -562,21 +562,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{metric=\"SLE_hit_rate\"}",
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"SLE_hit_rate\"}",
"legendFormat": "SLE Hit Rate"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{metric=\"ledger_hit_rate\"}",
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"ledger_hit_rate\"}",
"legendFormat": "Ledger Hit Rate"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{metric=\"AL_hit_rate\"}",
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"AL_hit_rate\"}",
"legendFormat": "AcceptedLedger Hit Rate"
}
],
@@ -618,21 +618,21 @@
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{metric=\"treenode_cache_size\"}",
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"treenode_cache_size\"}",
"legendFormat": "TreeNode Cache"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{metric=\"treenode_track_size\"}",
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"treenode_track_size\"}",
"legendFormat": "TreeNode Track"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "rippled_cache_metrics{metric=\"fullbelow_size\"}",
"expr": "rippled_cache_metrics{exported_instance=~\"$node\", metric=\"fullbelow_size\"}",
"legendFormat": "FullBelow"
}
],
@@ -689,7 +689,7 @@
"datasource": {
"type": "prometheus"
},
"expr": "topk(15, rippled_object_count)",
"expr": "topk(15, rippled_object_count{exported_instance=~\"$node\"})",
"legendFormat": "{{type}}"
}
],