Imporve monitoring 4

infrastructure/signoz/dashboards/error-tracking.json

@@ -0,0 +1,105 @@
+{
+  "dashboard": {
+    "title": "Bakery IA - Error Tracking",
+    "description": "Comprehensive error tracking and analysis dashboard",
+    "tags": ["errors", "exceptions", "tracking"],
+    "panels": [
+      {
+        "title": "Total Errors",
+        "type": "stat",
+        "query": {
+          "metric": "error_total",
+          "aggregate": "sum",
+          "filters": [
+            {
+              "key": "service",
+              "operator": "=",
+              "value": "${service}"
+            }
+          ]
+        },
+        "unit": "number"
+      },
+      {
+        "title": "Error Rate",
+        "type": "timeseries",
+        "query": {
+          "metric": "error_total",
+          "aggregate": "rate",
+          "groupBy": ["service"],
+          "filters": [
+            {
+              "key": "service",
+              "operator": "=",
+              "value": "${service}"
+            }
+          ]
+        },
+        "unit": "errors/s"
+      },
+      {
+        "title": "HTTP 5xx Errors",
+        "type": "timeseries",
+        "query": {
+          "metric": "http_server_requests_seconds_count",
+          "aggregate": "sum",
+          "groupBy": ["service", "status"],
+          "filters": [
+            {
+              "key": "service",
+              "operator": "=",
+              "value": "${service}"
+            },
+            {
+              "key": "status",
+              "operator": "=~",
+              "value": "5.."
+            }
+          ]
+        },
+        "unit": "number"
+      },
+      {
+        "title": "HTTP 4xx Errors",
+        "type": "timeseries",
+        "query": {
+          "metric": "http_server_requests_seconds_count",
+          "aggregate": "sum",
+          "groupBy": ["service", "status"],
+          "filters": [
+            {
+              "key": "service",
+              "operator": "=",
+              "value": "${service}"
+            },
+            {
+              "key": "status",
+              "operator": "=~",
+              "value": "4.."
+            }
+          ]
+        },
+        "unit": "number"
+      }
+    ],
+    "variables": [
+      {
+        "name": "service",
+        "label": "Service",
+        "type": "dropdown",
+        "default": "*",
+        "values": ["*", "auth-service", "gateway-service", "inventory-service", "production-service", "forecasting-service"]
+      }
+    ],
+    "layout": {
+      "type": "grid",
+      "columns": 12,
+      "gap": [16, 16]
+    },
+    "refresh": "15s",
+    "time": {
+      "from": "now-1h",
+      "to": "now"
+    }
+  }
+}