fix(telemetry): repoint node-health job panels to native job-duration metrics

The Key Jobs execution/dequeue panels queried StatsD-era per-job metric
names (xrpld_<job>_milliseconds_bucket, xrpld_<job>_q_milliseconds_bucket)
that the native OTel path no longer emits. Phase 9's MetricsRegistry emits
job timings as two label-dimensioned histograms instead:
  xrpld_job_running_duration_us_bucket{job_type="<job>"}
  xrpld_job_queued_duration_us_bucket{job_type="<job>"}

Rewrite the 22 affected panel queries (11 job types x running/queued) to
the label-dimensioned form, preserving the histogram_quantile / rate /
sum-by structure and all template-variable filters.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
Pratik Mankawde
2026-07-07 18:54:01 +01:00
parent 04f351f3b7
commit bc140d9e96

View File

@@ -433,77 +433,77 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_acceptLedger_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"acceptLedger\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Accept Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_advanceLedger_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"advanceLedger\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Advance Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_transaction_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"transaction\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Transaction [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_writeObjects_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"writeObjects\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Write Objects [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_heartbeat_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"heartbeat\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Heartbeat [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_sweep_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"sweep\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Sweep [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedValidation_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"trustedValidation\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Trusted Validation [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedProposal_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"trustedProposal\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Trusted Proposal [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_publishNewLedger_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"publishNewLedger\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Publish New Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_clientRPC_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"clientRPC\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Client RPC [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_ledgerData_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_running_duration_us_bucket{job_type=\"ledgerData\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Ledger Data [{{quantile}}]"
}
],
@@ -542,77 +542,77 @@
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_acceptLedger_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"acceptLedger\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Accept Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_advanceLedger_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"advanceLedger\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Advance Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_transaction_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"transaction\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Transaction [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_writeObjects_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"writeObjects\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Write Objects [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_heartbeat_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"heartbeat\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Heartbeat [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_sweep_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"sweep\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Sweep [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedValidation_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"trustedValidation\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Trusted Validation [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_trustedProposal_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"trustedProposal\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Trusted Proposal [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_publishNewLedger_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"publishNewLedger\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Publish New Ledger [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_clientRPC_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"clientRPC\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Client RPC [{{quantile}}]"
},
{
"datasource": {
"type": "prometheus"
},
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_ledgerData_q_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"expr": "histogram_quantile($quantile, sum by (le, exported_instance) (rate(xrpld_job_queued_duration_us_bucket{job_type=\"ledgerData\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[5m])))",
"legendFormat": "Ledger Data [{{quantile}}]"
}
],