From cf292754ba423aa6782564ea83fe48cc1ed677d4 Mon Sep 17 00:00:00 2001
From: Rohit Agarwal <agarwalrohit@google.com>
Date: Mon, 30 Oct 2017 15:50:08 -0700
Subject: [PATCH] Run nvidia-gpu device-plugin daemonset as an addon on GCE
 nodes that have nvidia GPUs attached.

---
 .../device-plugins/nvidia-gpu/daemonset.yaml  | 45 +++++++++++++++++++
 cluster/common.sh                             |  5 +++
 cluster/gce/gci/configure-helper.sh           |  3 ++
 3 files changed, 53 insertions(+)
 create mode 100644 cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml

diff --git a/cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml b/cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml
new file mode 100644
index 0000000000..a5eaf1da76
--- /dev/null
+++ b/cluster/addons/device-plugins/nvidia-gpu/daemonset.yaml
@@ -0,0 +1,45 @@
+apiVersion: extensions/v1beta1
+kind: DaemonSet
+metadata:
+  name: nvidia-gpu-device-plugin
+  namespace: kube-system
+  labels:
+    k8s-app: nvidia-gpu-device-plugin
+    addonmanager.kubernetes.io/mode: Reconcile
+spec:
+  template:
+    metadata:
+      labels:
+        k8s-app: nvidia-gpu-device-plugin
+    spec:
+      affinity:
+        nodeAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            nodeSelectorTerms:
+            - matchExpressions:
+              - key: cloud.google.com/gke-accelerator
+                operator: Exists
+      hostNetwork: true
+      hostPID: true
+      volumes:
+      - name: device-plugin
+        hostPath:
+          path: /var/lib/kubelet/device-plugins
+      - name: dev
+        hostPath:
+          path: /dev
+      containers:
+      - image: "gcr.io/google-containers/nvidia-gpu-device-plugin@sha256:943a62949cd80c26e7371d4e123dac61b4cc7281390721aaa95f265171094842"
+        command: ["/usr/bin/nvidia-gpu-device-plugin", "-logtostderr"]
+        name: nvidia-gpu-device-plugin
+        resources:
+          requests:
+            cpu: 10m
+            memory: 10Mi
+        securityContext:
+          privileged: true
+        volumeMounts:
+        - name: device-plugin
+          mountPath: /device-plugin
+        - name: dev
+          mountPath: /dev
diff --git a/cluster/common.sh b/cluster/common.sh
index 2b11917d77..dc0107f027 100755
--- a/cluster/common.sh
+++ b/cluster/common.sh
@@ -873,6 +873,11 @@ EOF
     if [ -n "${CLUSTER_SIGNING_DURATION:-}" ]; then
       cat >>$file <<EOF
 CLUSTER_SIGNING_DURATION: $(yaml-quote ${CLUSTER_SIGNING_DURATION})
+EOF
+    fi
+    if [[ "${NODE_ACCELERATORS:-}" == *"type=nvidia"* ]]; then
+      cat >>$file <<EOF
+ENABLE_NVIDIA_GPU_DEVICE_PLUGIN: $(yaml-quote "true")
 EOF
     fi
 
diff --git a/cluster/gce/gci/configure-helper.sh b/cluster/gce/gci/configure-helper.sh
index 99a563c081..e4f618f392 100644
--- a/cluster/gce/gci/configure-helper.sh
+++ b/cluster/gce/gci/configure-helper.sh
@@ -1796,6 +1796,9 @@ function start-kube-addons {
   if [[ "${ENABLE_METRICS_SERVER:-}" == "true" ]]; then
     setup-addon-manifests "addons" "metrics-server"
   fi
+  if [[ "${ENABLE_NVIDIA_GPU_DEVICE_PLUGIN:-}" == "true" ]]; then
+    setup-addon-manifests "addons" "device-plugins/nvidia-gpu"
+  fi
   if [[ "${ENABLE_CLUSTER_DNS:-}" == "true" ]]; then
     setup-addon-manifests "addons" "dns"
     local -r kubedns_file="${dst_dir}/dns/kube-dns.yaml"