From 1eb44689d083fb6f75f64742f37e16f7aa720d91 Mon Sep 17 00:00:00 2001 From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com> Date: Wed, 8 Jul 2026 14:51:26 +0100 Subject: [PATCH] fix(telemetry): use service_instance_id label instead of exported_instance exported_instance is a Prometheus scrape artifact that only exists when Prometheus scrapes a target with a conflicting instance label. Users running push-based pipelines (remote_write, OTLP) never get this label. service_instance_id is always present via resource_to_telemetry_conversion regardless of ingestion path. Co-Authored-By: Claude Opus 4.6 --- .../grafana/dashboards/consensus-health.json | 102 +++++++++--------- .../grafana/dashboards/ledger-operations.json | 44 ++++---- .../grafana/dashboards/peer-network.json | 18 ++-- .../grafana/dashboards/rpc-performance.json | 50 ++++----- .../dashboards/transaction-overview.json | 90 ++++++++-------- 5 files changed, 152 insertions(+), 152 deletions(-) diff --git a/docker/telemetry/grafana/dashboards/consensus-health.json b/docker/telemetry/grafana/dashboards/consensus-health.json index 5971b6a69e..36c84d3196 100644 --- a/docker/telemetry/grafana/dashboards/consensus-health.json +++ b/docker/telemetry/grafana/dashboards/consensus-health.json @@ -29,15 +29,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept\"}[5m])))", - "legendFormat": "P95 Round Duration [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept\"}[5m])))", + "legendFormat": "P95 Round Duration [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept\"}[5m])))", - "legendFormat": "P50 Round Duration [{{exported_instance}}]" + "expr": "histogram_quantile(0.50, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept\"}[5m])))", + "legendFormat": "P50 Round Duration [{{service_instance_id}}]" } ], "fieldConfig": { @@ -75,8 +75,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.proposal.send\"}[5m]))", - "legendFormat": "Proposals / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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]))", + "legendFormat": "Proposals / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -114,8 +114,8 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[5m])))", - "legendFormat": "P95 Close Duration [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$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])))", + "legendFormat": "P95 Close Duration [{{service_instance_id}}]" } ], "fieldConfig": { @@ -153,8 +153,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.validation.send\"}[5m]))", - "legendFormat": "Validations / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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]))", + "legendFormat": "Validations / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -179,15 +179,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept.apply\"}[5m])))", - "legendFormat": "P95 Apply Duration [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept.apply\"}[5m])))", + "legendFormat": "P95 Apply Duration [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept.apply\"}[5m])))", - "legendFormat": "P50 Apply Duration [{{exported_instance}}]" + "expr": "histogram_quantile(0.50, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.accept.apply\"}[5m])))", + "legendFormat": "P50 Apply Duration [{{service_instance_id}}]" } ], "fieldConfig": { @@ -219,8 +219,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (close_time_correct, exported_instance) (rate(traces_span_metrics_calls_total{span_name=\"consensus.accept.apply\", consensus_mode=~\"$consensus_mode\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))", - "legendFormat": "Close Time Correct={{close_time_correct}} [{{exported_instance}}]" + "expr": "sum by (close_time_correct, service_instance_id) (rate(traces_span_metrics_calls_total{span_name=\"consensus.accept.apply\", consensus_mode=~\"$consensus_mode\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))", + "legendFormat": "Close Time Correct={{close_time_correct}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -258,8 +258,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (consensus_mode, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.ledger_close\"}[5m]))", - "legendFormat": "{{consensus_mode}} [{{exported_instance}}]" + "expr": "sum by (consensus_mode, service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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]))", + "legendFormat": "{{consensus_mode}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -297,15 +297,15 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\"}[5m]))", - "legendFormat": "Accepts / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Accepts / Sec [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.ledger_close\"}[5m]))", - "legendFormat": "Closes / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Closes / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -343,15 +343,15 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.validation.send\"}[5m]))", - "legendFormat": "Validations / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Validations / Sec [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.ledger_close\"}[5m]))", - "legendFormat": "Closes / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Closes / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -393,7 +393,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\"}[5m])) by (le)", + "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\"}[5m])) by (le)", "legendFormat": "{{le}}", "format": "heatmap" } @@ -686,7 +686,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (consensus_state) (increase(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$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(traces_span_metrics_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]))", "legendFormat": "{{consensus_state}}" } ], @@ -718,15 +718,15 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\", consensus_state=\"moved_on\"}[5m]))", - "legendFormat": "moved_on [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "moved_on [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.accept\", consensus_state=\"expired\"}[5m]))", - "legendFormat": "expired [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "expired [{{service_instance_id}}]" } ], "fieldConfig": { @@ -764,15 +764,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.round\"}[5m])))", - "legendFormat": "P95 Round [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.round\"}[5m])))", + "legendFormat": "P95 Round [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.round\"}[5m])))", - "legendFormat": "P50 Round [{{exported_instance}}]" + "expr": "histogram_quantile(0.50, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", consensus_mode=~\"$consensus_mode\", span_name=\"consensus.round\"}[5m])))", + "legendFormat": "P50 Round [{{service_instance_id}}]" } ], "fieldConfig": { @@ -810,15 +810,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.phase.open\"}[5m])))", - "legendFormat": "P95 Open Phase [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.phase.open\"}[5m])))", + "legendFormat": "P95 Open Phase [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.establish\"}[5m])))", - "legendFormat": "P95 Establish Phase [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.establish\"}[5m])))", + "legendFormat": "P95 Establish Phase [{{service_instance_id}}]" } ], "fieldConfig": { @@ -856,15 +856,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.update_positions\"}[5m])))", - "legendFormat": "P95 Update [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.update_positions\"}[5m])))", + "legendFormat": "P95 Update [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.5, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.update_positions\"}[5m])))", - "legendFormat": "P50 Update [{{exported_instance}}]" + "expr": "histogram_quantile(0.5, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.update_positions\"}[5m])))", + "legendFormat": "P50 Update [{{service_instance_id}}]" } ], "fieldConfig": { @@ -902,15 +902,15 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.check\", consensus_stalled=\"true\"}[5m]))", - "legendFormat": "Stalled [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Stalled [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.check\", consensus_stalled=\"false\"}[5m]))", - "legendFormat": "Not Stalled [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Not Stalled [{{service_instance_id}}]" } ], "fieldConfig": { @@ -948,8 +948,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (mode_new, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.mode_change\"}[5m]))", - "legendFormat": "{{mode_new}} [{{exported_instance}}]" + "expr": "sum by (mode_new, service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "{{mode_new}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -1036,7 +1036,7 @@ "label": "Node", "description": "Filter by rippled node (service.instance.id — e.g. Node-1)", "type": "query", - "query": "label_values(traces_span_metrics_calls_total, exported_instance)", + "query": "label_values(traces_span_metrics_calls_total, service_instance_id)", "datasource": { "type": "prometheus", "uid": "prometheus" diff --git a/docker/telemetry/grafana/dashboards/ledger-operations.json b/docker/telemetry/grafana/dashboards/ledger-operations.json index 6a00c51158..70f99707d7 100644 --- a/docker/telemetry/grafana/dashboards/ledger-operations.json +++ b/docker/telemetry/grafana/dashboards/ledger-operations.json @@ -29,8 +29,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m]))", - "legendFormat": "Builds / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Builds / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -61,15 +61,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m])))", - "legendFormat": "P95 Build Duration [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m])))", + "legendFormat": "P95 Build Duration [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m])))", - "legendFormat": "P50 Build Duration [{{exported_instance}}]" + "expr": "histogram_quantile(0.50, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m])))", + "legendFormat": "P50 Build Duration [{{service_instance_id}}]" } ], "fieldConfig": { @@ -107,8 +107,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.validate\"}[5m]))", - "legendFormat": "Validations / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Validations / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -142,7 +142,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m])) by (le)", + "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m])) by (le)", "legendFormat": "{{le}}", "format": "heatmap" } @@ -175,15 +175,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m])))", - "legendFormat": "P95 tx.apply [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m])))", + "legendFormat": "P95 tx.apply [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m])))", - "legendFormat": "P50 tx.apply [{{exported_instance}}]" + "expr": "histogram_quantile(0.50, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m])))", + "legendFormat": "P50 tx.apply [{{service_instance_id}}]" } ], "fieldConfig": { @@ -221,8 +221,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m]))", - "legendFormat": "tx.apply / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "tx.apply / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -260,8 +260,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.store\"}[5m]))", - "legendFormat": "Stores / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Stores / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -292,15 +292,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m])))", - "legendFormat": "P95 ledger.build [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"ledger.build\"}[5m])))", + "legendFormat": "P95 ledger.build [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.ledger_close\"}[5m])))", - "legendFormat": "P95 consensus.ledger_close [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"consensus.ledger_close\"}[5m])))", + "legendFormat": "P95 consensus.ledger_close [{{service_instance_id}}]" } ], "fieldConfig": { @@ -387,7 +387,7 @@ "label": "Node", "description": "Filter by rippled node (service.instance.id — e.g. Node-1)", "type": "query", - "query": "label_values(traces_span_metrics_calls_total, exported_instance)", + "query": "label_values(traces_span_metrics_calls_total, service_instance_id)", "datasource": { "type": "prometheus", "uid": "prometheus" diff --git a/docker/telemetry/grafana/dashboards/peer-network.json b/docker/telemetry/grafana/dashboards/peer-network.json index 715616b424..2493b31179 100644 --- a/docker/telemetry/grafana/dashboards/peer-network.json +++ b/docker/telemetry/grafana/dashboards/peer-network.json @@ -30,8 +30,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"peer.proposal.receive\"}[5m]))", - "legendFormat": "Proposals Received / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Proposals Received / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -69,8 +69,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"peer.validation.receive\"}[5m]))", - "legendFormat": "Validations Received / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Validations Received / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -108,8 +108,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (proposal_trusted, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", proposal_trusted=~\"$proposal_trusted\", span_name=\"peer.proposal.receive\"}[5m]))", - "legendFormat": "Trusted = {{proposal_trusted}} [{{exported_instance}}]" + "expr": "sum by (proposal_trusted, service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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]))", + "legendFormat": "Trusted = {{proposal_trusted}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -140,8 +140,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (validation_trusted, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", validation_trusted=~\"$validation_trusted\", span_name=\"peer.validation.receive\"}[5m]))", - "legendFormat": "Trusted = {{validation_trusted}} [{{exported_instance}}]" + "expr": "sum by (validation_trusted, service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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]))", + "legendFormat": "Trusted = {{validation_trusted}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -221,7 +221,7 @@ "label": "Node", "description": "Filter by rippled node (service.instance.id — e.g. Node-1)", "type": "query", - "query": "label_values(traces_span_metrics_calls_total, exported_instance)", + "query": "label_values(traces_span_metrics_calls_total, service_instance_id)", "datasource": { "type": "prometheus", "uid": "prometheus" diff --git a/docker/telemetry/grafana/dashboards/rpc-performance.json b/docker/telemetry/grafana/dashboards/rpc-performance.json index ce43229fa7..2a11175807 100644 --- a/docker/telemetry/grafana/dashboards/rpc-performance.json +++ b/docker/telemetry/grafana/dashboards/rpc-performance.json @@ -29,8 +29,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (command, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m]))", - "legendFormat": "{{command}} [{{exported_instance}}]" + "expr": "sum by (command, service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m]))", + "legendFormat": "{{command}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -68,8 +68,8 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, command, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])))", - "legendFormat": "P95 {{command}} [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, command, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])))", + "legendFormat": "P95 {{command}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -107,8 +107,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (command, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[5m])) / sum by (command, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])) * 100", - "legendFormat": "{{command}} [{{exported_instance}}]" + "expr": "sum by (command, service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[5m])) / sum by (command, service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])) * 100", + "legendFormat": "{{command}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -159,7 +159,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])) by (le)", + "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])) by (le)", "legendFormat": "{{le}}", "format": "heatmap" } @@ -191,15 +191,15 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.http_request\"}[5m]))", - "legendFormat": "rpc.http_request / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.http_request\"}[5m]))", + "legendFormat": "rpc.http_request / Sec [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.process\"}[5m]))", - "legendFormat": "rpc.process / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.process\"}[5m]))", + "legendFormat": "rpc.process / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -237,15 +237,15 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_UNSET\"}[5m]))", - "legendFormat": "Success [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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_UNSET\"}[5m]))", + "legendFormat": "Success [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\", status_code=\"STATUS_CODE_ERROR\"}[5m]))", - "legendFormat": "Error [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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]))", + "legendFormat": "Error [{{service_instance_id}}]" } ], "fieldConfig": { @@ -283,8 +283,8 @@ "datasource": { "type": "prometheus" }, - "expr": "topk(10, sum by (command, exported_instance) (increase(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])))", - "legendFormat": "{{command}} [{{exported_instance}}]" + "expr": "topk(10, sum by (command, service_instance_id) (increase(traces_span_metrics_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=~\"rpc.command.*\"}[5m])))", + "legendFormat": "{{command}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -315,8 +315,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.ws_message\"}[5m]))", - "legendFormat": "WS Messages / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", command=~\"$command\", span_name=\"rpc.ws_message\"}[5m]))", + "legendFormat": "WS Messages / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -352,7 +352,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (load_type) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$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(traces_span_metrics_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]))", "legendFormat": "{{load_type}}" } ], @@ -391,15 +391,15 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"rpc.process\", is_batch=\"true\"}[5m]))", - "legendFormat": "Batch [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Batch [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"rpc.process\", is_batch=\"false\"}[5m]))", - "legendFormat": "Single [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Single [{{service_instance_id}}]" } ], "fieldConfig": { @@ -486,7 +486,7 @@ "label": "Node", "description": "Filter by rippled node (service.instance.id — e.g. Node-1)", "type": "query", - "query": "label_values(traces_span_metrics_calls_total, exported_instance)", + "query": "label_values(traces_span_metrics_calls_total, service_instance_id)", "datasource": { "type": "prometheus", "uid": "prometheus" diff --git a/docker/telemetry/grafana/dashboards/transaction-overview.json b/docker/telemetry/grafana/dashboards/transaction-overview.json index 0fe0a1ccd1..6aa4b8d9aa 100644 --- a/docker/telemetry/grafana/dashboards/transaction-overview.json +++ b/docker/telemetry/grafana/dashboards/transaction-overview.json @@ -29,15 +29,15 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))", - "legendFormat": "tx.process / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))", + "legendFormat": "tx.process / Sec [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.receive\", tx_type=~\"$tx_type\"}[5m]))", - "legendFormat": "tx.receive / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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": { @@ -80,15 +80,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, tx_type, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m])))", - "legendFormat": "P95 {{tx_type}} [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, tx_type, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m])))", + "legendFormat": "P95 {{tx_type}} [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, tx_type, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m])))", - "legendFormat": "P50 {{tx_type}} [{{exported_instance}}]" + "expr": "histogram_quantile(0.50, sum by (le, tx_type, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m])))", + "legendFormat": "P50 {{tx_type}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -126,8 +126,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (local, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", local=~\"$tx_origin\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))", - "legendFormat": "Local = {{local}} [{{exported_instance}}]" + "expr": "sum by (local, service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Local = {{local}} [{{service_instance_id}}]" } ] }, @@ -152,8 +152,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (suppressed, exported_instance) (rate(traces_span_metrics_calls_total{span_name=\"tx.receive\", tx_type=~\"$tx_type\", exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))", - "legendFormat": "Suppressed={{suppressed}} [{{exported_instance}}]" + "expr": "sum by (suppressed, service_instance_id) (rate(traces_span_metrics_calls_total{span_name=\"tx.receive\", tx_type=~\"$tx_type\", service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\"}[$__rate_interval]))", + "legendFormat": "Suppressed={{suppressed}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -195,7 +195,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m])) by (le)", + "expr": "sum(increase(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m])) by (le)", "legendFormat": "{{le}}", "format": "heatmap" } @@ -227,15 +227,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m])))", - "legendFormat": "P95 tx.apply [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m])))", + "legendFormat": "P95 tx.apply [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m])))", - "legendFormat": "P50 tx.apply [{{exported_instance}}]" + "expr": "histogram_quantile(0.50, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\"}[5m])))", + "legendFormat": "P50 tx.apply [{{service_instance_id}}]" } ], "fieldConfig": { @@ -273,8 +273,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.receive\", tx_type=~\"$tx_type\"}[5m]))", - "legendFormat": "tx.receive / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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": { @@ -312,8 +312,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.apply\", status_code=\"STATUS_CODE_ERROR\"}[5m]))", - "legendFormat": "Failed / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Failed / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -365,7 +365,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (tx_type) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))", + "expr": "sum by (tx_type) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.process\", tx_type=~\"$tx_type\"}[5m]))", "legendFormat": "{{tx_type}}" } ], @@ -409,7 +409,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (tx_type, ter_result) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$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) (rate(traces_span_metrics_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]))", "legendFormat": "{{tx_type}}: {{ter_result}}" } ], @@ -452,7 +452,7 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (txq_status) (increase(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.accept_tx\", txq_status=~\"$txq_status\"}[5m]))", + "expr": "sum by (txq_status) (increase(traces_span_metrics_calls_total{service_instance_id=~\"$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]))", "legendFormat": "{{txq_status}}" } ], @@ -489,8 +489,8 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, tx_type, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.transactor\", tx_type=~\"$tx_type\"}[5m])))", - "legendFormat": "P95 {{tx_type}} [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, tx_type, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"tx.transactor\", tx_type=~\"$tx_type\"}[5m])))", + "legendFormat": "P95 {{tx_type}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -528,8 +528,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (tx_type, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.enqueue\"}[5m]))", - "legendFormat": "{{tx_type}} [{{exported_instance}}]" + "expr": "sum by (tx_type, service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "{{tx_type}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -567,8 +567,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.apply_direct\"}[5m])) / clamp_min(sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.apply_direct\"}[5m])) + sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.enqueue\"}[5m])), 1)", - "legendFormat": "Direct-Apply Fraction [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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(traces_span_metrics_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(traces_span_metrics_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)", + "legendFormat": "Direct-Apply Fraction [{{service_instance_id}}]" } ], "fieldConfig": { @@ -606,15 +606,15 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.accept\"}[5m])))", - "legendFormat": "P95 Drain [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.accept\"}[5m])))", + "legendFormat": "P95 Drain [{{service_instance_id}}]" }, { "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.50, sum by (le, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.accept\"}[5m])))", - "legendFormat": "P50 Drain [{{exported_instance}}]" + "expr": "histogram_quantile(0.50, sum by (le, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.accept\"}[5m])))", + "legendFormat": "P50 Drain [{{service_instance_id}}]" } ], "fieldConfig": { @@ -652,8 +652,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=\"txq.cleanup\"}[5m]))", - "legendFormat": "Cleanups / Sec [{{exported_instance}}]" + "expr": "sum by (service_instance_id) (rate(traces_span_metrics_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]))", + "legendFormat": "Cleanups / Sec [{{service_instance_id}}]" } ], "fieldConfig": { @@ -696,8 +696,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (stage, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\"}[5m]))", - "legendFormat": "{{stage}} [{{exported_instance}}]" + "expr": "sum by (stage, service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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]))", + "legendFormat": "{{stage}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -740,8 +740,8 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, stage, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\"}[5m])))", - "legendFormat": "P95 {{stage}} [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, stage, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{service_instance_id=~\"$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])))", + "legendFormat": "P95 {{stage}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -784,8 +784,8 @@ "datasource": { "type": "prometheus" }, - "expr": "sum by (stage, exported_instance) (rate(traces_span_metrics_calls_total{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", stage=~\"$stage\", ter_result!~\"tesSUCCESS|\"}[5m]))", - "legendFormat": "{{stage}} [{{exported_instance}}]" + "expr": "sum by (stage, service_instance_id) (rate(traces_span_metrics_calls_total{service_instance_id=~\"$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]))", + "legendFormat": "{{stage}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -828,8 +828,8 @@ "datasource": { "type": "prometheus" }, - "expr": "histogram_quantile(0.95, sum by (le, tx_type, stage, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", deployment_environment=~\"$deployment_environment\", xrpl_network_type=~\"$xrpl_network_type\", service_name=~\"$service_name\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", tx_type=~\"$tx_type\", stage=~\"$stage\"}[5m])))", - "legendFormat": "P95 {{tx_type}} {{stage}} [{{exported_instance}}]" + "expr": "histogram_quantile(0.95, sum by (le, tx_type, stage, service_instance_id) (rate(traces_span_metrics_duration_milliseconds_bucket{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\", tx_type=~\"$tx_type\", stage=~\"$stage\"}[5m])))", + "legendFormat": "P95 {{tx_type}} {{stage}} [{{service_instance_id}}]" } ], "fieldConfig": { @@ -916,7 +916,7 @@ "label": "Node", "description": "Filter by rippled node (service.instance.id — e.g. Node-1)", "type": "query", - "query": "label_values(traces_span_metrics_calls_total, exported_instance)", + "query": "label_values(traces_span_metrics_calls_total, service_instance_id)", "datasource": { "type": "prometheus", "uid": "prometheus"