diff --git a/.github/workflows/integration-test.yml b/.github/workflows/integration-test.yml index 6ad082a8a3..18936b8eb5 100644 --- a/.github/workflows/integration-test.yml +++ b/.github/workflows/integration-test.yml @@ -1303,10 +1303,11 @@ jobs: echo "Cluster name is ${EKS_CLUSTER_NAME}" kubectl create -f https://raw.githubusercontent.com/NVIDIA/k8s-device-plugin/v0.17.0/deployments/static/nvidia-device-plugin.yml kubectl patch amazoncloudwatchagents -n amazon-cloudwatch cloudwatch-agent --type='json' -p='[{"op": "replace", "path": "/spec/image", "value": ${{ secrets.AWS_ECR_PRIVATE_REGISTRY }}/${{ env.ECR_INTEGRATION_TEST_REPO }}:${{ github.sha }}}]' - kubectl rollout status daemonset nvidia-device-plugin-daemonset -n kube-system --timeout 10s + # wait nvidia device plugin to be ready + sleep 10 kubectl apply -f ./gpuBurner.yaml else - terraform destroy -var="beta=${{ github.event.inputs.run_in_beta }}" -auto-approve && exit 1 + terraform destroy -auto-approve && exit 1 fi - name: Run Go tests with retry @@ -1345,4 +1346,4 @@ jobs: else cd terraform/eks/addon/gpu fi - terraform destroy -var="beta=${{ github.event.inputs.run_in_beta }}" -auto-approve + terraform destroy -auto-approve