wip

Author: iamvigneshwars

mpi.yaml

@@ -0,0 +1,60 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Workflow
+metadata:
+  generateName: mpi-kueue-test-
+spec:
+  entrypoint: mpi-job
+  podSpecPatch: |
+    {"initContainers":[{"name":"init","volumeMounts":[{"name":"init-temp-dir","mountPath":"/tmp"}]}],"volumes":[{"name":"init-temp-dir","emptyDir":{}}]}
+  templates:
+  - name: mpi-job
+    resource:
+      action: create
+      manifest: |
+        apiVersion: kubeflow.org/v2beta1
+        kind: MPIJob
+        metadata:
+          name: pi
+          labels:
+            kueue.x-k8s.io/queue-name: default-queue
+        spec:
+          slotsPerWorker: 1
+          runPolicy:
+            cleanPodPolicy: Running
+            ttlSecondsAfterFinished: 60
+          sshAuthMountPath: /home/mpiuser/.ssh
+          mpiReplicaSpecs:
+            Launcher:
+              replicas: 1
+              template:
+                spec:
+                  containers:
+                  - image: mpioperator/mpi-pi:openmpi
+                    name: mpi-launcher
+                    command:
+                    - mpirun
+                    args:
+                    - -n
+                    - "2"
+                    - /home/mpiuser/pi
+                    resources:
+                      limits:
+                        cpu: 1
+                        memory: 1Gi
+            Worker:
+              replicas: 2
+              template:
+                spec:
+                  containers:
+                  - image: mpioperator/mpi-pi:openmpi
+                    name: mpi-worker
+                    command:
+                    - /usr/sbin/sshd
+                    args:
+                    - -De
+                    - -f
+                    - /home/mpiuser/.sshd_config
+                    resources:
+                      limits:
+                        cpu: 1
+                        memory: 1Gi

offline.yaml

@@ -0,0 +1,16 @@
+apiVersion: argoproj.io/v1alpha1
+kind: Workflow
+metadata:
+  name: offline-test
+spec:
+  entrypoint: process-data
+  templates:
+  - name: process-data
+    container:
+      image: busybox
+      command: ["/bin/sh", "-c"]
+      args: ["echo 'Processing offline data (low priority)'; sleep 300"]
+      resources:
+        limits:
+          cpu: "2"
+          memory: "2Gi"