Merge remote-tracking branch 'upstream/master'

johnugeorge · Apr 28, 2024 · 3b64a8c · 3b64a8c
2 parents e8dea4c + f8f7363
commit 3b64a8c
Show file tree

Hide file tree

Showing 128 changed files with 23,220 additions and 24,073 deletions.
diff --git a/.github/workflows/build-and-publish-images.yaml b/.github/workflows/build-and-publish-images.yaml
@@ -31,6 +31,9 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v3
 
+      - name: Free-Up Disk Space
+        uses: ./.github/workflows/free-up-disk-space
+
       - name: Docker Login
         # Trigger workflow only for kubeflow/training-operator repository with specific branch (master, v.*-branch) or tag (v.*).
         if: >-

diff --git a/.github/workflows/free-up-disk-space/action.yaml b/.github/workflows/free-up-disk-space/action.yaml
@@ -0,0 +1,49 @@
+name: Free-Up Disk Space
+description: Remove Non-Essential Tools And Move Docker Data Directory to /mnt/docker
+
+runs:
+  using: composite
+  steps:
+    # This step is a Workaround to avoid the "No space left on device" error.
+    # ref: https://github.com/actions/runner-images/issues/2840
+    - name: Remove unnecessary files
+      shell: bash
+      run: |
+        echo "Disk usage before cleanup:"
+        df -hT
+
+        sudo rm -rf /usr/share/dotnet
+        sudo rm -rf /opt/ghc
+        sudo rm -rf /usr/local/share/boost
+        sudo rm -rf "$AGENT_TOOLSDIRECTORY"
+        sudo rm -rf /usr/local/lib/android
+        sudo rm -rf /usr/local/share/powershell
+        sudo rm -rf /usr/share/swift
+
+        echo "Disk usage after cleanup:"
+        df -hT
+
+    - name: Prune docker images
+      shell: bash
+      run: |
+        docker image prune -a -f
+        docker system df
+        df -hT
+
+    - name: Move docker data directory
+      shell: bash
+      run: |
+        echo "Stopping docker service ..."
+        sudo systemctl stop docker
+        DOCKER_DEFAULT_ROOT_DIR=/var/lib/docker
+        DOCKER_ROOT_DIR=/mnt/docker
+        echo "Moving ${DOCKER_DEFAULT_ROOT_DIR} -> ${DOCKER_ROOT_DIR}"
+        sudo mv ${DOCKER_DEFAULT_ROOT_DIR} ${DOCKER_ROOT_DIR}
+        echo "Creating symlink ${DOCKER_DEFAULT_ROOT_DIR} -> ${DOCKER_ROOT_DIR}"
+        sudo ln -s ${DOCKER_ROOT_DIR} ${DOCKER_DEFAULT_ROOT_DIR}
+        echo "$(sudo ls -l ${DOCKER_DEFAULT_ROOT_DIR})"
+        echo "Starting docker service ..."
+        sudo systemctl daemon-reload
+        sudo systemctl start docker
+        echo "Docker service status:"
+        sudo systemctl --no-pager -l -o short status docker
diff --git a/.github/workflows/integration-tests.yaml b/.github/workflows/integration-tests.yaml
@@ -16,7 +16,7 @@ jobs:
     # strategy:
     #   fail-fast: false
     #   matrix:
-    #     kubernetes-version: [""v1.25.11", "v1.26.6", "v1.27.3"]
+    #     kubernetes-version: ["v1.27.11", "v1.28.7", "v1.29.2"]
     #     gang-scheduler-name: ["none", "scheduler-plugins", "volcano"]
     # ```
     # The difference is that each combination is randomly assigned various Python versions
@@ -26,54 +26,41 @@ jobs:
       matrix:
         # TODO (tenzen-y): Add volcano.
         include:
-          - kubernetes-version: v1.26.6
+          - kubernetes-version: v1.29.2
             gang-scheduler-name: "none"
             python-version: "3.10"
-          - kubernetes-version: v1.27.3
+          - kubernetes-version: v1.27.11
             gang-scheduler-name: "none"
             python-version: "3.7"
-          - kubernetes-version: v1.25.11
+          - kubernetes-version: v1.28.7
             gang-scheduler-name: "none"
             python-version: "3.8"
-          - kubernetes-version: v1.26.6
+          - kubernetes-version: v1.29.2
             gang-scheduler-name: "scheduler-plugins"
             python-version: "3.9"
-          - kubernetes-version: v1.27.3
+          - kubernetes-version: v1.27.11
             gang-scheduler-name: "scheduler-plugins"
             python-version: "3.10"
-          - kubernetes-version: v1.25.11
+          - kubernetes-version: v1.28.7
             gang-scheduler-name: "scheduler-plugins"
             python-version: "3.10"
-          - kubernetes-version: v1.26.6
+          - kubernetes-version: v1.29.2
             gang-scheduler-name: "volcano"
             python-version: "3.9"
-          - kubernetes-version: v1.27.3
+          - kubernetes-version: v1.27.11
             gang-scheduler-name: "volcano"
             python-version: "3.10"
-          - kubernetes-version: v1.25.11
+          - kubernetes-version: v1.28.7
             gang-scheduler-name: "volcano"
             python-version: "3.10"
 
     steps:
-      # This step is a Workaround to avoid the "No space left on device" error.
-      # ref: https://github.com/actions/runner-images/issues/2840
-      - name: Remove unnecessary files
-        shell: bash
-        run: |
-          sudo rm -rf /usr/share/dotnet
-          sudo rm -rf /opt/ghc
-          sudo rm -rf "/usr/local/share/boost"
-          sudo rm -rf "$AGENT_TOOLSDIRECTORY"
-          sudo rm -rf /usr/local/lib/android
-          sudo rm -rf /usr/local/share/powershell
-          sudo rm -rf /usr/share/swift
-
-          echo "Disk usage after cleanup:"
-          df -h
-
       - name: Checkout
         uses: actions/checkout@v3
 
+      - name: Free-Up Disk Space
+        uses: ./.github/workflows/free-up-disk-space
+
       - name: Setup Python
         uses: actions/setup-python@v4
         with:

diff --git a/.github/workflows/publish-example-images.yaml b/.github/workflows/publish-example-images.yaml
@@ -55,8 +55,9 @@ jobs:
           - component-name: mxnet-auto-tuning
             dockerfile: examples/mxnet/tune/Dockerfile
             context: examples/mxnet/tune
-# TODO (tenzen-y): Fix the below broken Dockerfiles
-#          - component-name: pytorch-dist-mnist-mpi
-#            dockerfile: examples/pytorch/mnist/Dockerfile-mpi
-#          - component-name: pytorch-dist-mnist
-#            dockerfile: examples/pytorch/mnist/Dockerfile
+          - component-name: pytorch-dist-mnist
+            dockerfile: examples/pytorch/mnist/Dockerfile
+            context: examples/pytorch/mnist
+          - component-name: pytorch-dist-mnist-mpi
+            dockerfile: examples/pytorch/mnist/Dockerfile-mpi
+            context: examples/pytorch/mnist
diff --git a/.github/workflows/template-publish-image/action.yaml b/.github/workflows/template-publish-image/action.yaml
@@ -23,50 +23,6 @@ inputs:
 runs:
   using: composite
   steps:
-    # This step is a Workaround to avoid the "No space left on device" error.
-    # ref: https://github.com/actions/runner-images/issues/2840
-    - name: Remove unnecessary files
-      shell: bash
-      run: |
-        echo "Disk usage before cleanup:"
-        df -hT
-
-        sudo rm -rf /usr/share/dotnet
-        sudo rm -rf /opt/ghc
-        sudo rm -rf /usr/local/share/boost
-        sudo rm -rf "$AGENT_TOOLSDIRECTORY"
-        sudo rm -rf /usr/local/lib/android
-        sudo rm -rf /usr/local/share/powershell
-        sudo rm -rf /usr/share/swift
-
-        echo "Disk usage after cleanup:"
-        df -hT
-
-    - name: Prune docker images
-      shell: bash
-      run: |
-        docker image prune -a -f
-        docker system df
-        df -hT
-
-    - name: Move docker data directory
-      shell: bash
-      run: |
-        echo "Stopping docker service ..."
-        sudo systemctl stop docker
-        DOCKER_DEFAULT_ROOT_DIR=/var/lib/docker
-        DOCKER_ROOT_DIR=/mnt/docker
-        echo "Moving ${DOCKER_DEFAULT_ROOT_DIR} -> ${DOCKER_ROOT_DIR}"
-        sudo mv ${DOCKER_DEFAULT_ROOT_DIR} ${DOCKER_ROOT_DIR}
-        echo "Creating symlink ${DOCKER_DEFAULT_ROOT_DIR} -> ${DOCKER_ROOT_DIR}"
-        sudo ln -s ${DOCKER_ROOT_DIR} ${DOCKER_DEFAULT_ROOT_DIR}
-        echo "$(sudo ls -l ${DOCKER_DEFAULT_ROOT_DIR})"
-        echo "Starting docker service ..."
-        sudo systemctl daemon-reload
-        sudo systemctl start docker
-        echo "Docker service status:"
-        sudo systemctl --no-pager -l -o short status docker
-
     - name: Setup QEMU
       uses: docker/setup-qemu-action@v2
       with:
@@ -93,4 +49,4 @@ runs:
         push: ${{ inputs.push }}
         tags: ${{ steps.meta.outputs.tags }}
         cache-from: type=gha
-        cache-to: type=gha,mode=max
+        cache-to: type=gha
diff --git a/.github/workflows/test-python.yaml b/.github/workflows/test-python.yaml
@@ -18,7 +18,7 @@ jobs:
       - name: Check Python code with Black
         uses: psf/black@stable
         with:
-          version: 23.9.1
+          version: 24.2.0
           options: --check --exclude '/*kubeflow_org_v1*|__init__.py|api_client.py|configuration.py|exceptions.py|rest.py'
           src: sdk/
 

diff --git a/.github/workflows/unittests.yaml b/.github/workflows/unittests.yaml
@@ -17,7 +17,8 @@ jobs:
     strategy:
       fail-fast: false
       matrix:
-        kubernetes-version: ["1.25.0", "1.26.1", "1.27.1"]
+        # Detail: `setup-envtest list`
+        kubernetes-version: ["1.27.1", "1.28.3", "1.29.1"]
 
     steps:
       - name: Check out code

diff --git a/Makefile b/Makefile
@@ -37,7 +37,10 @@ help: ## Display this help.
 ##@ Development
 
 manifests: controller-gen ## Generate WebhookConfiguration, ClusterRole and CustomResourceDefinition objects.
-	$(CONTROLLER_GEN) $(CRD_OPTIONS) rbac:roleName=training-operator webhook paths="./pkg/..." output:crd:artifacts:config=manifests/base/crds output:rbac:artifacts:config=manifests/base/rbac
+	$(CONTROLLER_GEN) $(CRD_OPTIONS) rbac:roleName=training-operator webhook paths="./pkg/..." \
+		output:crd:artifacts:config=manifests/base/crds \
+		output:rbac:artifacts:config=manifests/base/rbac \
+		output:webhook:artifacts:config=manifests/base/webhook
 
 generate: controller-gen ## Generate apidoc, sdk and code containing DeepCopy, DeepCopyInto, and DeepCopyObject method implementations.
 	$(CONTROLLER_GEN) object:headerFile="hack/boilerplate/boilerplate.go.txt" paths="./pkg/apis/..."
@@ -57,12 +60,12 @@ vet: ## Run go vet against code.
 GOLANGCI_LINT=$(shell which golangci-lint)
 golangci-lint:
 ifeq ($(GOLANGCI_LINT),)
-	curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.53.3
+	curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(shell go env GOPATH)/bin v1.57.2
 	$(info golangci-lint has been installed)
 endif
-	golangci-lint run --timeout 5m --go 1.20 ./...
+	golangci-lint run --timeout 5m --go 1.22 ./...
 
-ENVTEST_K8S_VERSION ?= 1.27
+ENVTEST_K8S_VERSION ?= 1.29
 HAS_SETUP_ENVTEST := $(shell command -v setup-envtest;)
 
 testall: manifests generate fmt vet golangci-lint test ## Run tests.
@@ -72,7 +75,7 @@ test: envtest
 
 envtest:
 ifndef HAS_SETUP_ENVTEST
-	go install sigs.k8s.io/controller-runtime/tools/setup-envtest@116a1b831fffe7ccc3c8145306c3e1a3b1b14ffa # v0.15.0
+	go install sigs.k8s.io/controller-runtime/tools/setup-envtest@bf15e44028f908c790721fc8fe67c7bf2d06a611 # v0.17.2
 	@echo "setup-envtest has been installed"
 endif
 	@echo "setup-envtest has already installed"
@@ -108,7 +111,7 @@ PROJECT_DIR := $(shell dirname $(abspath $(lastword $(MAKEFILE_LIST))))
 
 CONTROLLER_GEN = $(shell pwd)/bin/controller-gen
 controller-gen: ## Download controller-gen locally if necessary.
-	GOBIN=$(PROJECT_DIR)/bin go install sigs.k8s.io/controller-tools/cmd/controller-gen@v0.13.0
+	GOBIN=$(PROJECT_DIR)/bin go install sigs.k8s.io/controller-tools/cmd/controller-gen@v0.14.0
 
 KUSTOMIZE = $(shell pwd)/bin/kustomize
 kustomize: ## Download kustomize locally if necessary.

diff --git a/build/images/kubectl-delivery/Dockerfile b/build/images/kubectl-delivery/Dockerfile
@@ -1,7 +1,7 @@
 FROM alpine:3.17 AS build
 
 # Install kubectl.
-ENV K8S_VERSION v1.27.5
+ENV K8S_VERSION v1.29.3
 
 RUN apk add --no-cache wget
 RUN wget -q https://storage.googleapis.com/kubernetes-release/release/${K8S_VERSION}/bin/linux/amd64/kubectl

diff --git a/build/images/training-operator/Dockerfile b/build/images/training-operator/Dockerfile
@@ -1,5 +1,5 @@
 # Build the manager binary
-FROM golang:1.20 as builder
+FROM golang:1.22 as builder
 
 WORKDIR /workspace
 # Copy the Go Modules manifests