From 72642b5dc6b4c9226707cf553d5a3746cbd56642 Mon Sep 17 00:00:00 2001
From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com>
Date: Fri, 5 Jun 2026 13:39:59 +0100
Subject: [PATCH] feat(telemetry): add tx apply latency panel by type and stage

The existing apply-pipeline panels show latency by stage (all types
combined) or by type (single span). Neither answers "for a given
transaction type, which stage dominates its latency". Add a p95 panel
grouped by both tx_type and stage, filterable via the $tx_type and
$stage variables. Both dimensions already exist in spanmetrics, so no
collector change is needed. Reflow the section so the full-width
failure panel sits below the new full-width panel.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 .../dashboards/transaction-overview.json      | 46 ++++++++++++++++++-
 1 file changed, 45 insertions(+), 1 deletion(-)

diff --git a/docker/telemetry/grafana/dashboards/transaction-overview.json b/docker/telemetry/grafana/dashboards/transaction-overview.json
index 5423a8e4fb..405e1564e8 100644
--- a/docker/telemetry/grafana/dashboards/transaction-overview.json
+++ b/docker/telemetry/grafana/dashboards/transaction-overview.json
@@ -766,7 +766,7 @@
         "h": 8,
         "w": 24,
         "x": 0,
-        "y": 72
+        "y": 80
       },
       "options": {
         "tooltip": {
@@ -801,6 +801,50 @@
         },
         "overrides": []
       }
+    },
+    {
+      "title": "Tx Apply Pipeline Latency by Type and Stage (p95)",
+      "description": "95th-percentile duration broken down by both transaction type and apply-pipeline stage. Shows, for each transaction type, which stage (preflight, preclaim, apply) dominates its latency. Higher cardinality than the by-stage view; filter with the $tx_type and $stage variables.",
+      "type": "timeseries",
+      "gridPos": {
+        "h": 8,
+        "w": 24,
+        "x": 0,
+        "y": 72
+      },
+      "options": {
+        "tooltip": {
+          "mode": "multi",
+          "sort": "desc"
+        },
+        "legend": {
+          "displayMode": "table",
+          "placement": "right",
+          "calcs": ["mean", "max"]
+        }
+      },
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus"
+          },
+          "expr": "histogram_quantile(0.95, sum by (le, tx_type, stage, exported_instance) (rate(traces_span_metrics_duration_milliseconds_bucket{exported_instance=~\"$node\", span_name=~\"tx.preflight|tx.preclaim|tx.transactor\", tx_type=~\"$tx_type\", stage=~\"$stage\"}[5m])))",
+          "legendFormat": "P95 {{tx_type}} {{stage}} [{{exported_instance}}]"
+        }
+      ],
+      "fieldConfig": {
+        "defaults": {
+          "unit": "ms",
+          "custom": {
+            "axisLabel": "Duration (ms)",
+            "spanNulls": true,
+            "insertNulls": false,
+            "showPoints": "auto",
+            "pointSize": 3
+          }
+        },
+        "overrides": []
+      }
     }
   ],
   "schemaVersion": 39,