From d7341749ff26a071b0971dba3f779277b93d76df Mon Sep 17 00:00:00 2001 From: Rohit Agarwal Date: Wed, 29 Nov 2017 11:31:39 -0800 Subject: [PATCH] nvidia-gpu-device-plugin daemonset should tolerate nvidia.com/gpu taint. It is expected that nodes with extended resources attached will be tainted with the resouce name, so that we can create dedicated nodes. If ExtendedResourceToleration admission controller is enabled, pods requesting such resources will automatically tolerate such taints. nvidia-gpu-device-plugin daemonset doesn't request such resources but still needs to run on such nodes, so it needs this toleration. --- cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml b/cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml index 6b5edbf733d..de66faecb30 100644 --- a/cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml +++ b/cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml @@ -22,6 +22,10 @@ spec: - matchExpressions: - key: cloud.google.com/gke-accelerator operator: Exists + tolerations: + - key: "nvidia.com/gpu" + effect: "NoSchedule" + operator: "Exists" hostNetwork: true hostPID: true volumes: