diff --git a/artifacthub-pkg.yml b/artifacthub-pkg.yml index 3437ac9..c77db0a 100644 --- a/artifacthub-pkg.yml +++ b/artifacthub-pkg.yml @@ -90,6 +90,14 @@ changes: - kind: fixed description: "Resolve ESLint/Prettier indent conflict by disabling ESLint indent rule (Prettier is formatting authority)" +screenshots: + - title: Overview — cluster GPU summary, operator status, and active workloads + url: https://raw.githubusercontent.com/privilegedescalation/headlamp-intel-gpu-plugin/main/docs/screenshots/01-overview.svg + - title: GPU Nodes — per-node GPU type, capacity, and allocation bars + url: https://raw.githubusercontent.com/privilegedescalation/headlamp-intel-gpu-plugin/main/docs/screenshots/02-nodes.svg + - title: Metrics — real-time GPU power draw and TDP utilization (discrete GPUs) + url: https://raw.githubusercontent.com/privilegedescalation/headlamp-intel-gpu-plugin/main/docs/screenshots/03-metrics.svg + annotations: headlamp/plugin/archive-url: "https://github.com/privilegedescalation/headlamp-intel-gpu-plugin/releases/download/v0.4.3/intel-gpu-0.4.3.tar.gz" headlamp/plugin/archive-checksum: sha256:d9c78b3d678d3e6b92c81315bfed88bd22ec4f5cd63578467206727244db7dab diff --git a/docs/screenshots/01-overview.svg b/docs/screenshots/01-overview.svg new file mode 100644 index 0000000..947dbdb --- /dev/null +++ b/docs/screenshots/01-overview.svg @@ -0,0 +1,123 @@ + + + + + + + ⚡ Headlamp + Intel GPU + / + Overview + + + + + Overview + Device Plugins + GPU Nodes + GPU Pods + Metrics + + + Intel GPU Overview + Cluster-wide GPU device plugin status and workload summary + + + + + + GPU Nodes + 6 + / 12 total + + + + + Active GPU Pods + 14 + running + + + + + Device Plugins + 2 + healthy + + + + + Cluster GPU Allocation + 58% + + + + + + + GPU Type Distribution + + + + + + + Discrete (i915/Xe) + 4 nodes · 67% + + Integrated + 2 nodes · 33% + + + + Operator Status + + + + gpu-device-plugin + Running + 6/6 + + + node-feature-discovery + Running + 1/1 + + + prometheus / node-exporter + Available + 6/6 + + + + Active GPU Pods + + + NAME + NAMESPACE + NODE + GPU REQUEST + STATUS + + + gpu-inference-7d9c4f + ml-workloads + gpu-node-01 + 2 + + Running + + training-job-abc12 + training + gpu-node-03 + 4 + + Running + + render-worker-9xk2p + rendering + gpu-node-02 + 1 + + Pending + diff --git a/docs/screenshots/02-nodes.svg b/docs/screenshots/02-nodes.svg new file mode 100644 index 0000000..49680f4 --- /dev/null +++ b/docs/screenshots/02-nodes.svg @@ -0,0 +1,142 @@ + + + + + + + ⚡ Headlamp + Intel GPU + / + GPU Nodes + + + + Overview + Device Plugins + + GPU Nodes + GPU Pods + Metrics + + + GPU Nodes + Per-node GPU capacity, allocatable, allocation, and active workloads + + + + + gpu-node-01 + + Ready + Type + Discrete (i915) + Capacity + 4 GPUs + Allocatable + 4 GPUs + + Allocation + 75% (3/4) + + + Active Pods: + gpu-inference-7d9c4f, render-worker-9xk2p + + + + + gpu-node-02 + + Ready + Type + Discrete (Xe) + Capacity + 2 GPUs + Allocatable + 2 GPUs + + Allocation + 50% (1/2) + + + Active Pods: + render-worker-9xk2p + + + + + gpu-node-03 + + Ready + Type + Discrete (i915) + Capacity + 8 GPUs + Allocatable + 8 GPUs + + Allocation + 100% (8/8) + + + Active Pods: + training-job-abc12 (+3 more) + + + + + worker-node-05 + + Ready + Type + Integrated + Capacity + 1 GPU + Allocatable + 1 GPU + + Allocation + 0% (0/1) + + Active Pods: + none + + + + + gpu-node-04 + + Ready + Type + Discrete (i915) + Capacity + 2 GPUs + Allocatable + 2 GPUs + + Allocation + 25% (0.5/2) + + + Active Pods: + light-inference-pod + + + + + worker-node-07 + + NotReady + Type + Integrated + Capacity + 1 GPU + Allocatable + — + + Allocation + — + + Active Pods: + node unavailable + diff --git a/docs/screenshots/03-metrics.svg b/docs/screenshots/03-metrics.svg new file mode 100644 index 0000000..3e1524b --- /dev/null +++ b/docs/screenshots/03-metrics.svg @@ -0,0 +1,117 @@ + + + + + + + ⚡ Headlamp + Intel GPU + / + Metrics + + + + Overview + Device Plugins + GPU Nodes + GPU Pods + + Metrics + + + GPU Metrics + Real-time GPU power draw from node-exporter i915 hwmon (discrete GPU nodes only) + + + + Last 30 min ▾ + + + + Peak Power Draw + 186 W + gpu-node-03 + + + Avg Power (cluster) + 124 W + 3 nodes + + + Avg TDP Utilization + 68% + of 250W TDP + + + Nodes Reporting + 3 + / 4 discrete + + + + GPU Power Draw (W) — Last 30 Minutes + + + + 0 + 50 + 100 + 150 + 200 + + + + + + + + -30m + -22m + -15m + -7m + now + + + + + + + + + + + + + gpu-node-01 (i915, 4x GPU, avg 186W) + + gpu-node-03 (i915, 8x GPU, avg 124W) + + gpu-node-02 (Xe, 2x GPU, avg 80W) + + + + TDP Utilization — Current + + + gpu-node-01 + 186W / 250W TDP + + + 74% + + gpu-node-03 + 124W / 250W TDP + + + 50% + + gpu-node-02 + 80W / 150W TDP + + + 53% + + gpu-node-04 + No hwmon data — integrated GPU + n/a +