InfiniBand recommended monitors (#20159)

* ib recommended monitors

* manifest

* Update manifest.json

* path change

* path change

* Update manifest.json

Author: steveny91

infiniband/assets/monitors/physical_state.json

@@ -0,0 +1,34 @@
+{
+    "version": 2,
+    "created_at": "2025-04-27",
+    "last_updated_at": "2025-04-27",
+    "title": "InfiniBand Port Physical State Alert",
+    "description": "Alerts when an InfiniBand port reports a disabled or link error recovery physical state for 5 minutes or longer",
+    "definition": {
+        "id": 170517673,
+        "name": "[InfiniBand] Port Physical State Alert",
+        "type": "query alert",
+        "query": "min(last_5m):avg:infiniband.port_phys_state{port_phys_state:disabled OR port_phys_state:link_error_recovery} by {port,device,host,port_state} >= 1",
+        "message": "{{#is_alert}}\nPort:{{port.name}} of device:{{device.name}} on host:{{host.name}} is reporting a {{port_state.name}} physical state.\n{{/is_alert}}",
+        "tags": [
+            "integration:infiniband"
+        ],
+        "options": {
+            "thresholds": {
+                "critical": 1
+            },
+            "notify_audit": false,
+            "on_missing_data": "resolve",
+            "include_tags": true,
+            "new_group_delay": 60,
+            "silenced": {}
+        },
+        "priority": null,
+        "restriction_policy": {
+            "bindings": []
+        }
+    },
+    "tags": [
+        "integration:infiniband"
+    ]
+}

infiniband/assets/monitors/port_state.json

@@ -0,0 +1,34 @@
+{
+    "version": 2,
+    "created_at": "2025-04-27",
+    "last_updated_at": "2025-04-27",
+    "title": "InfiniBand Port State Alert",
+    "description": "Alerts when an InfiniBand port reports a down state for 5 minutes or longer",
+    "definition": {
+        "id": 170517681,
+        "name": "[InfiniBand] Port State Alert",
+        "type": "query alert",
+        "query": "min(last_5m):count:infiniband.port_state{port_state:down} by {port,device,host,port_state} >= 1",
+        "message": "{{#is_alert}}\nPort:{{port.name}} of device:{{device.name}} on host:{{host.name}} is reporting a {{port_state.name}} state.\n{{/is_alert}}",
+        "tags": [
+            "integration:infiniband"
+        ],
+        "options": {
+            "thresholds": {
+                "critical": 1
+            },
+            "notify_audit": false,
+            "on_missing_data": "resolve",
+            "include_tags": true,
+            "new_group_delay": 60,
+            "silenced": {}
+        },
+        "priority": null,
+        "restriction_policy": {
+            "bindings": []
+        }
+    },
+    "tags": [
+        "integration:infiniband"
+    ]
+}

infiniband/manifest.json

@@ -36,6 +36,10 @@
         "metadata_path": "metadata.csv"
       }
     },
+    "monitors": {
+      "port_state": "assets/monitors/port_state.json",
+      "physical_state": "assets/monitors/physical_state.json"
+    },
     "dashboards": {
       "InfiniBand Overview": "assets/dashboards/infiniband_overview.json"
     }