From 455603bc9f13f2ead715190213d943648b85b72a Mon Sep 17 00:00:00 2001 From: Joji Mekkattuparamban Date: Fri, 30 Jan 2026 08:29:14 -0800 Subject: [PATCH 1/2] Enable cc manager by default on all kata nodes Signed-off-by: Joji Mekkattuparamban --- assets/state-cc-manager/0500_daemonset.yaml | 1 - deployments/gpu-operator/values.yaml | 4 ++-- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/assets/state-cc-manager/0500_daemonset.yaml b/assets/state-cc-manager/0500_daemonset.yaml index fa234b253..85fb9f9ca 100644 --- a/assets/state-cc-manager/0500_daemonset.yaml +++ b/assets/state-cc-manager/0500_daemonset.yaml @@ -20,7 +20,6 @@ spec: effect: NoSchedule nodeSelector: nvidia.com/gpu.deploy.cc-manager: "true" - nvidia.com/cc.capable: "true" priorityClassName: system-node-critical serviceAccountName: nvidia-cc-manager containers: diff --git a/deployments/gpu-operator/values.yaml b/deployments/gpu-operator/values.yaml index c501a5fce..a4d51904f 100644 --- a/deployments/gpu-operator/values.yaml +++ b/deployments/gpu-operator/values.yaml @@ -503,8 +503,8 @@ sandboxDevicePlugin: resources: {} ccManager: - enabled: false - defaultMode: "off" + enabled: true + defaultMode: "on" repository: nvcr.io/nvidia/cloud-native image: k8s-cc-manager version: v0.1.1 From bd954f7ce25707d33519862f3a22b7d15b942078 Mon Sep 17 00:00:00 2001 From: Joji Mekkattuparamban Date: Fri, 30 Jan 2026 08:44:56 -0800 Subject: [PATCH 2/2] Eliminate cc specific nfd rules, handled elsewhere Signed-off-by: Joji Mekkattuparamban --- .../templates/nodefeaturerules.yaml | 105 ------------------ 1 file changed, 105 deletions(-) diff --git a/deployments/gpu-operator/templates/nodefeaturerules.yaml b/deployments/gpu-operator/templates/nodefeaturerules.yaml index b8c3a6cd8..4584cffc1 100644 --- a/deployments/gpu-operator/templates/nodefeaturerules.yaml +++ b/deployments/gpu-operator/templates/nodefeaturerules.yaml @@ -1,111 +1,6 @@ {{- if .Values.nfd.nodefeaturerules }} apiVersion: nfd.k8s-sigs.io/v1alpha1 kind: NodeFeatureRule -metadata: - name: nvidia-nfd-nodefeaturerules -spec: - rules: - - name: "TDX rule" - labels: - tdx.enabled: "true" - matchFeatures: - - feature: cpu.security - matchExpressions: - tdx.enabled: {op: IsTrue} - - name: "TDX total keys rule" - extendedResources: - tdx.total_keys: "@cpu.security.tdx.total_keys" - matchFeatures: - - feature: cpu.security - matchExpressions: - tdx.enabled: {op: IsTrue} - - name: "SEV-SNP rule" - labels: - sev.snp.enabled: "true" - matchFeatures: - - feature: cpu.security - matchExpressions: - sev.snp.enabled: - op: IsTrue - - name: "SEV-ES rule" - labels: - sev.es.enabled: "true" - matchFeatures: - - feature: cpu.security - matchExpressions: - sev.es.enabled: - op: IsTrue - - name: SEV system capacities - extendedResources: - sev_asids: '@cpu.security.sev.asids' - sev_es: '@cpu.security.sev.encrypted_state_ids' - matchFeatures: - - feature: cpu.security - matchExpressions: - sev.enabled: - op: Exists - - name: "NVIDIA H100" - labels: - "nvidia.com/gpu.H100": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device - matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2339"]} - - name: "NVIDIA H100 PCIe" - labels: - "nvidia.com/gpu.H100.pcie": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device - matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2331"]} - - name: "NVIDIA H100 80GB HBM3" - labels: - "nvidia.com/gpu.H100.HBM3": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device - matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2330"]} - - name: "NVIDIA H800" - labels: - "nvidia.com/gpu.H800": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device - matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2324"]} - - name: "NVIDIA H800 PCIE" - labels: - "nvidia.com/gpu.H800.pcie": "true" - "nvidia.com/gpu.family": "hopper" - matchFeatures: - - feature: pci.device - matchExpressions: - vendor: {op: In, value: ["10de"]} - device: {op: In, value: ["2322"]} - - name: "NVIDIA CC Enabled" - labels: - "nvidia.com/cc.capable": "true" - matchAny: # TDX/SEV + Hopper GPU - - matchFeatures: - - feature: rule.matched - matchExpressions: - nvidia.com/gpu.family: {op: In, value: ["hopper"]} - sev.snp.enabled: {op: IsTrue} - - matchFeatures: - - feature: rule.matched - matchExpressions: - nvidia.com/gpu.family: {op: In, value: ["hopper"]} - tdx.enabled: {op: IsTrue} ---- -apiVersion: nfd.k8s-sigs.io/v1alpha1 -kind: NodeFeatureRule metadata: name: nvidia-kernel-modules spec: