GKE DWS examples (#127)

gke-dws-examples/README.md

@@ -0,0 +1,11 @@
+# Dynamic Workload Scheduler examples
+
+The repository contains examples on how to use DWS in GKE. More information about DWS is 
+available [here](https://cloud.google.com/kubernetes-engine/docs/how-to/provisioningrequest).
+
+Files included:
+
+* kueue-manifests.yaml - [Kueue](https://kueue.sigs.k8s.io/) configuration files with ProvisioningRequest and DWS support enabled.
+* dws-queue.yaml - Kueue's Cluster and Local queues with ProvisioningRequest and DWS support enabled.
+* job.yaml - Sample job that requires GPU and uses DWS-enabled queue.
+

gke-dws-examples/dws-queues.yaml

@@ -0,0 +1,53 @@
+apiVersion: kueue.x-k8s.io/v1beta1
+kind: ResourceFlavor
+metadata:
+  name: "default-flavor"
+---
+apiVersion: kueue.x-k8s.io/v1beta1
+kind: AdmissionCheck
+metadata:
+  name: dws-prov
+spec:
+  controllerName: kueue.x-k8s.io/provisioning-request
+  parameters:
+    apiGroup: kueue.x-k8s.io
+    kind: ProvisioningRequestConfig
+    name: dws-config
+---
+apiVersion: kueue.x-k8s.io/v1beta1
+kind: ProvisioningRequestConfig
+metadata:
+  name: dws-config
+spec:
+  provisioningClassName: queued-provisioning.gke.io
+  managedResources:
+  - nvidia.com/gpu
+---
+apiVersion: kueue.x-k8s.io/v1beta1
+kind: ClusterQueue
+metadata:
+  name: "dws-cluster-queue"
+spec:
+  namespaceSelector: {} 
+  resourceGroups:
+  - coveredResources: ["cpu", "memory", "nvidia.com/gpu"]
+    flavors:
+    - name: "default-flavor"
+      resources:
+      - name: "cpu"
+        nominalQuota: 10000  # Infinite quota.
+      - name: "memory"
+        nominalQuota: 10000Gi # Infinite quota.
+      - name: "nvidia.com/gpu"
+        nominalQuota: 10000  # Infinite quota.
+  admissionChecks:
+  - dws-prov
+---
+apiVersion: kueue.x-k8s.io/v1beta1
+kind: LocalQueue
+metadata:
+  namespace: "default"
+  name: "dws-local-queue"
+spec:
+  clusterQueue: "dws-cluster-queue"
+---

gke-dws-examples/job.yaml

@@ -0,0 +1,33 @@
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: sample-job
+  namespace: default
+  labels:
+    kueue.x-k8s.io/queue-name: dws-local-queue
+spec:
+  parallelism: 1
+  completions: 1
+  suspend: true
+  template:
+    spec:
+      nodeSelector:
+        cloud.google.com/gke-nodepool: dws-nodepool
+      tolerations:
+      - key: "nvidia.com/gpu"
+        operator: "Exists"
+        effect: "NoSchedule"
+      containers:
+      - name: dummy-job
+        image: gcr.io/k8s-staging-perf-tests/sleep:v0.0.3
+        args: ["120s"]
+        resources:
+          requests:
+            cpu: "100m"
+            memory: "100Mi"
+            nvidia.com/gpu: 1
+          limits:
+            cpu: "100m"
+            memory: "100Mi"
+            nvidia.com/gpu: 1
+      restartPolicy: Never