Imporve monitoring 4

2026-01-09 14:48:44 +01:00
parent 7ef85c1188
commit 22dab143ba
21 changed files with 1911 additions and 202 deletions
--- a/infrastructure/signoz/dashboards/api-performance.json
+++ b/infrastructure/signoz/dashboards/api-performance.json
@@ -0,0 +1,102 @@
+{
+  "dashboard": {
+    "title": "Bakery IA - API Performance",
+    "description": "Comprehensive API performance monitoring for Bakery IA REST and GraphQL endpoints",
+    "tags": ["api", "performance", "rest", "graphql"],
+    "panels": [
+      {
+        "title": "Request Volume",
+        "type": "timeseries",
+        "query": {
+          "metric": "http_server_requests_seconds_count",
+          "aggregate": "sum",
+          "groupBy": ["api"],
+          "filters": [
+            {
+              "key": "api",
+              "operator": "=",
+              "value": "${api}"
+            }
+          ]
+        },
+        "unit": "req/s"
+      },
+      {
+        "title": "Error Rate",
+        "type": "timeseries",
+        "query": {
+          "metric": "http_server_requests_seconds_count",
+          "aggregate": "sum",
+          "groupBy": ["api", "status"],
+          "filters": [
+            {
+              "key": "api",
+              "operator": "=",
+              "value": "${api}"
+            },
+            {
+              "key": "status",
+              "operator": "=~",
+              "value": "5.."
+            }
+          ]
+        },
+        "unit": "req/s"
+      },
+      {
+        "title": "Average Response Time",
+        "type": "timeseries",
+        "query": {
+          "metric": "http_server_requests_seconds_sum",
+          "aggregate": "avg",
+          "groupBy": ["api", "endpoint"],
+          "filters": [
+            {
+              "key": "api",
+              "operator": "=",
+              "value": "${api}"
+            }
+          ]
+        },
+        "unit": "seconds"
+      },
+      {
+        "title": "P95 Latency",
+        "type": "timeseries",
+        "query": {
+          "metric": "http_server_requests_seconds_bucket",
+          "aggregate": "histogram_quantile",
+          "quantile": 0.95,
+          "groupBy": ["api", "endpoint"],
+          "filters": [
+            {
+              "key": "api",
+              "operator": "=",
+              "value": "${api}"
+            }
+          ]
+        },
+        "unit": "seconds"
+      }
+    ],
+    "variables": [
+      {
+        "name": "api",
+        "label": "API Service",
+        "type": "dropdown",
+        "default": "*",
+        "values": ["*", "gateway-api", "auth-api", "inventory-api", "production-api", "forecasting-api", "procurement-api"]
+      }
+    ],
+    "layout": {
+      "type": "grid",
+      "columns": 12,
+      "gap": [16, 16]
+    },
+    "refresh": "15s",
+    "time": {
+      "from": "now-1h",
+      "to": "now"
+    }
+  }
+}