Enhance Grafana dashboard with new Prometheus datasource configurations and additional metrics for improved monitoring of OCI GPU Scanner health checks.

Author: jolettacheungoracle

grafana_dashboards/oke-workloads-to-gpuscanner-nodename-dashboard.json

@@ -1964,6 +1964,22 @@
                 "value": "Node"
               }
             ]
+          },
+          {
+            "matcher": {
+              "id": "byName",
+              "options": "Time Last Run"
+            },
+            "properties": [
+              {
+                "id": "unit",
+                "value": "dateTimeAsIso"
+              },
+              {
+                "id": "custom.align",
+                "value": "auto"
+              }
+            ]
           }
         ]
       },
@@ -2157,6 +2173,21 @@
           "legendFormat": "__auto",
           "range": false,
           "refId": "K"
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "{{DATASOURCE_PROMETHEUS}}"
+          },
+          "editorMode": "code",
+          "exemplar": false,
+          "expr": "max by (instance) (push_time_seconds{job=\"oci_lens_healthchecks\"}) * 1000",
+          "format": "table",
+          "instant": true,
+          "legendFormat": "__auto",
+          "range": false,
+          "refId": "L",
+          "hide": false
         }
       ],
       "title": "OCI GPU Scanner - ACTIVE health check summary",
@@ -2391,12 +2422,48 @@
               "test 6": true,
               "test 7": true,
               "test 8": true,
-              "test 9": true
+              "test 9": true,
+              "Time 1": true,
+              "Value #L": false,
+              "dtype 11": true,
+              "dtype 12": true,
+              "dtype 13": true,
+              "dtype 14": true,
+              "dtype 15": true,
+              "dtype 16": true,
+              "dtype 17": true,
+              "dtype 18": true,
+              "dtype 19": true,
+              "dtype 20": true,
+              "dtype": true,
+              "tensor_parallel_size 11": true,
+              "tensor_parallel_size 12": true,
+              "tensor_parallel_size 13": true,
+              "tensor_parallel_size 14": true
             },
             "includeByName": {},
-            "indexByName": {},
+            "indexByName": {
+              "instance": 0,
+              "Value #L": 1,
+              "hostGPU 1": 2,
+              "hostIP 1": 3,
+              "hostRegion 1": 4,
+              "tensor_parallel_size 1": 5,
+              "Value #A": 6,
+              "Value #B": 7,
+              "Value #C": 8,
+              "Value #D": 9,
+              "Value #E": 10,
+              "Value #F": 11,
+              "Value #G": 12,
+              "Value #H": 13,
+              "Value #I": 14,
+              "Value #J": 15,
+              "Value #K": 16
+            },
             "renameByName": {
-              "Time 1": "Time Last Run",
+              "Time 1": "",
+              "tensor_parallel_size 1": "Tensor Parallel Size",
               "Value #A": "Compute Throughput",
               "Value #B": "Memory Bandwidth",
               "Value #C": "Error Detection",
@@ -2408,7 +2475,7 @@
               "Value #I": "GPU Temperature Check",
               "Value #J": "GPU Power Check",
               "Value #K": "GPU Utilization Check",
-              "Value #L": "",
+              "Value #L": "Time Last Run",
               "__name__ 1": "",
               "gpu 1": "GPU",
               "hostGPU 1": "GPU Shape",