Merge pull request GoogleCloudPlatform#671 from huygaa11/master

Add NVIDIA DCGM prometheus sample dashboard
observIQ · Jan 9, 2024 · 7b5a9e2 · 7b5a9e2
2 parents 1ddeb34 + 5754207
commit 7b5a9e2
Show file tree

Hide file tree

Showing 6 changed files with 607 additions and 0 deletions.
diff --git a/dashboards/nvidia-gpu/README.md b/dashboards/nvidia-gpu/README.md
@@ -16,3 +16,8 @@
 |:------------------|
 |Filename: [nvidia-dcgm.json](nvidia-dcgm.json)|
 |Displays Advanced GPU metrics from NVIDIA Datacenter GPU Manager (DCGM).  This requires a specific setup (e.g. installing DCGM, installing the Ops Agent, and configuring it to receive DCGM metrics).|
+
+|NVIDIA GPU Monitoring Advanced DCGM Metrics (GKE Only)|
+|:------------------|
+|Filename: [nvidia-dcgm-prometheus.json](nvidia-dcgm-prometheus.json)|
+|Displays Advanced GPU metrics from NVIDIA Datacenter GPU Manager (DCGM).  This requires a specific setup (e.g. installing DCGM and DCGM exporter).|
diff --git a/dashboards/nvidia-gpu/metadata.yaml b/dashboards/nvidia-gpu/metadata.yaml
@@ -14,3 +14,12 @@ sample_dashboards:
     related_integrations:
       - id: dcgm
         platform: GCE
+  -
+    category: NVIDIA GPUs
+    id: nvidia-dcgm-prometheus
+    display_name: NVIDIA GPU Monitoring Advanced DCGM Metrics (GKE Only)
+    description: |-
+      Displays Advanced GPU metrics from NVIDIA Datacenter GPU Manager (DCGM).  This requires a specific setup (e.g. installing DCGM and DCGM exporter).
+    related_integrations:
+      - id: dcgm
+        platform: GKE
diff --git a/dashboards/nvidia-gpu/nvidia-dcgm-prometheus.01.png b/dashboards/nvidia-gpu/nvidia-dcgm-prometheus.01.png
diff --git a/dashboards/nvidia-gpu/nvidia-dcgm-prometheus.02.png b/dashboards/nvidia-gpu/nvidia-dcgm-prometheus.02.png
diff --git a/dashboards/nvidia-gpu/nvidia-dcgm-prometheus.03.png b/dashboards/nvidia-gpu/nvidia-dcgm-prometheus.03.png