Imporved the release process of training operator

.github/workflows/check-release.yaml

@@ -0,0 +1,46 @@
+name: Check Release
+
+on:
+  pull_request:
+    branches:
+      - release-*
+    paths:
+      - VERSION
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  SEMVER_PATTERN: '^v([0-9]+)\.([0-9]+)\.([0-9]+)(-rc\.([0-9]+))?$'
+
+jobs:
+  check-release:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Chekcout source code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check whether version matches semver pattern
+        run: |
+          VERSION=$(cat VERSION)
+          if [[ ${VERSION} =~ ${{ env.SEMVER_PATTERN }} ]]; then
+            echo "Version '${VERSION}' matches semver pattern."
+          else
+            echo "Version '${VERSION}' does not match semver pattern."
+            exit 1
+          fi
+          echo "VERSION=${VERSION}" >> $GITHUB_ENV
+
+      - name: Check if tag exists
+        run: |
+          git fetch --tags
+          if git tag -l | grep -q "^${VERSION}$"; then
+            echo "Tag '${VERSION}' already exists."
+            exit 1
+          else
+            echo "Tag '${VERSION}' does not exist."
+          fi

.github/workflows/release.yaml

@@ -0,0 +1,227 @@
+name: Release
+
+on:
+  push:
+    branches:
+      - release-*
+    paths:
+      - VERSION
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+env:
+  SEMVER_PATTERN: '^v([0-9]+)\.([0-9]+)\.([0-9]+)(-rc\.([0-9]+))?$'
+  IMAGE_REGISTRY: docker.io
+  IMAGE_REPOSITORY: kubeflow/training-operator
+
+jobs:
+  check-release:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Chekcout source code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Check whether version matches semver pattern
+        run: |
+          VERSION=$(cat VERSION)
+          if [[ ${VERSION} =~ ${{ env.SEMVER_PATTERN }} ]]; then
+            echo "Version '${VERSION}' matches semver pattern."
+          else
+            echo "Version '${VERSION}' does not match semver pattern."
+            exit 1
+          fi
+          echo "VERSION=${VERSION}" >> $GITHUB_ENV
+
+      - name: Check if tag exists
+        run: |
+          git fetch --tags
+          if git tag -l | grep -q "^${VERSION}$"; then
+            echo "Tag '${VERSION}' already exists."
+            exit 1
+          else
+            echo "Tag '${VERSION}' does not exist."
+          fi
+
+  build-images:
+    needs: check-release
+
+    runs-on: ubuntu-latest
+
+    strategy:
+      fail-fast: false # Need to confirm with maintainers
+      matrix:
+        platform:
+          - linux/amd64
+          - linux/arm64
+
+    steps:
+      - name: Prepare
+        run: |
+          platform=${{ matrix.platform }}
+          echo "PLATFORM_PAIR=${platform//\//-}" >> $GITHUB_ENV
+
+      - name: Checkout source code
+        uses: actions/checkout@v4
+
+      - name: Read version from VERSION file
+        run: |
+          VERSION=$(cat VERSION)
+          echo "VERSION=${VERSION}" >> $GITHUB_ENV
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.IMAGE_REGISTRY }}/${{ env.IMAGE_REPOSITORY }}
+          tags: |
+            type=semver,pattern={{version}},value=${{ env.VERSION }}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.IMAGE_REGISTRY }}
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Build and push by digest
+        id: build
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: build/images/training-operator/Dockerfile
+          platforms: ${{ matrix.platform }}
+          labels: ${{ steps.meta.outputs.labels }}
+          outputs: type=image,name=${{ env.IMAGE_REGISTRY }}/${{ env.IMAGE_REPOSITORY }},push-by-digest=true,name-canonical=true,push=true
+
+      - name: Export digest
+        run: |
+          mkdir -p /tmp/digests
+          digest="${{ steps.build.outputs.digest }}"
+          touch "/tmp/digests/${digest#sha256:}"
+
+      - name: Upload digest
+        uses: actions/upload-artifact@v4
+        with:
+          name: digests-${{ env.PLATFORM_PAIR }}
+          path: /tmp/digests/*
+          if-no-files-found: error
+          retention-days: 1
+
+  release-images:
+    needs: build-images
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout source code
+        uses: actions/checkout@v4
+
+      - name: Read version from VERSION file
+        run: |
+          VERSION=$(cat VERSION)
+          echo "VERSION=${VERSION}" >> $GITHUB_ENV
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.IMAGE_REGISTRY }}/${{ env.IMAGE_REPOSITORY }}
+          tags: |
+            type=semver,pattern={{version}},value=${{ env.VERSION }}
+
+      - name: Download digests
+        uses: actions/download-artifact@v4
+        with:
+          path: /tmp/digests
+          pattern: digests-*
+          merge-multiple: true
+
+      - name: Set up Docker buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Login to container registry
+        uses: docker/login-action@v3
+        with:
+          registry: ${{ env.IMAGE_REGISTRY }}
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Create manifest list and push
+        working-directory: /tmp/digests
+        run: |
+          docker buildx imagetools create $(jq -cr '.tags | map("-t " + .) | join(" ")' <<< "$DOCKER_METADATA_OUTPUT_JSON") \
+            $(printf '${{ env.IMAGE_REGISTRY }}/${{ env.IMAGE_REPOSITORY }}@sha256:%s ' *)
+
+      - name: Inspect image
+        run: |
+          docker buildx imagetools inspect ${{ env.IMAGE_REGISTRY }}/${{ env.IMAGE_REPOSITORY }}:${{ steps.meta.outputs.version }}
+
+  push-tags:
+    needs: release-images
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout source code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Configure Git
+        run: |
+          git config user.name "$GITHUB_ACTOR"
+          git config user.email "[email protected]"
+
+      - name: Read version from VERSION file
+        run: |
+          VERSION=$(cat VERSION)
+          echo "VERSION=${VERSION}" >> $GITHUB_ENV
+
+      - name: Create and push tag
+        run: |
+          git tag -a "${VERSION}" -m "Training Operator Official Release ${VERSION}"
+          git push origin "${VERSION}"
+
+  draft-release:
+    needs: push-tags
+
+    permissions:
+      contents: write
+
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Configure Git
+        run: |
+          git config user.name "$GITHUB_ACTOR"
+          git config user.email "[email protected]"
+
+      - name: Read version from VERSION file
+        run: |
+          VERSION=$(cat VERSION)
+          echo "VERSION=${VERSION}" >> $GITHUB_ENV
+
+      - name: Create release
+        id: release
+        uses: softprops/action-gh-release@v2
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}
+          name: "${{ env.VERSION }}"
+          tag_name: ${{ env.VERSION }}
+          prerelease: ${{ contains(env.VERSION, 'rc') }}
+          target_commitish: ${{ github.sha }}
+          draft: true

VERSION

@@ -0,0 +1 @@
+v1.8.1

docs/release.md

@@ -0,0 +1,100 @@
+# Releasing the Training operator
+
+## Prerequisites
+
+- [Write](https://docs.github.com/organizations/managing-access-to-your-organizations-repositories/repository-permission-levels-for-an-organization#permission-levels-for-repositories-owned-by-an-organization) permission for the Spark operator repository.
+
+- Create a [GitHub Token](https://docs.github.com/github/authenticating-to-github/keeping-your-account-and-data-secure/creating-a-personal-access-token).
+
+- Install `PyGithub` to generate the [Changelog](../CHANGELOG.md):
+
+  ```bash
+  pip install PyGithub==2.3.0
+  ```
+
+## Versioning policy
+
+Training Operator version format follows [Semantic Versioning](https://semver.org/). Training Operator versions are in the format of `vX.Y.Z`, where `X` is the major version, `Y` is the minor version, and `Z` is the patch version. The patch version contains only bug fixes.
+
+Additionally, Training Operator does pre-releases in this format: `vX.Y.Z-rc.N` where `N` is a number of the `Nth` release candidate (RC) before an upcoming public release named `vX.Y.Z`.
+
+## Release branches and tags
+
+Training Operator releases are tagged with tags like `vX.Y.Z`, for example `v1.7.2`.
+
+Release branches are in the format of `release-X.Y`, where `X.Y` stands for the minor release.
+
+`vX.Y.Z` releases are released from the `release-X.Y` branch. For example, `v1.7.2` release should be on `release-1.7` branch.
+
+If you want to push changes to the `release-X.Y` release branch, you have to cherry pick your changes from the `master` branch and submit a PR.
+
+## Create a new release
+
+### Create release branch
+
+1. Depends on what version you want to release,
+
+   - Major or Minor version - Use the GitHub UI to create a release branch from `master` and name the release branch `release-X.Y`.
+   - Patch version - You don't need to create a new release branch.
+
+2. Fetch the upstream changes into your local directory:
+
+   ```bash
+   git fetch upstream
+   ```
+
+3. Checkout into the release branch:
+
+   ```bash
+   git checkout release-X.Y
+   git rebase upstream/release-X.Y
+   ```
+
+### Create GitHub tag
+
+1. Modify `VERSION` file in the root directory of the project:
+
+    - For the RC tag as follows:
+
+    ```bash
+    vX.Y.Z-rc.N
+    ```
+
+    - For the official release tag as follows:
+
+    ```bash
+    vX.Y.Z
+    ```
+2. Commit the changes:
+
+    ```bash
+    git add VERSION
+    git commit -s -m "Training Operator Official Release v${VERSION}"
+    git push origin release-X.Y
+    ```
+3. Submit a PR to the release branch.
+
+### Release Training Operator Image
+
+After `VERSION` file is modified and pushed to the release branch, a release workflow will be triggered to build and push Training operator docker images to Docker Hub.
+
+
+## Update Changelog
+
+Update the `CHANGELOG.md` file by running:
+
+```bash
+python hack/generate-changelog.py \
+    --token=<github-token> \
+    --range=<previous-release>..<current-release>
+```
+
+If you are creating the **first minor pre-release** or the **minor** release (`X.Y`), your `previous-release` is equal to the latest release on the `release-X.Y` branch.
+For example: `--range=v1.7.1..v1.8.0`.
+
+Otherwise, your `previous-release` is equal to the latest release on the `release-X.Y` branch.
+For example: `--range=v1.7.0..v1.8.0-rc.0`
+
+Group PRs in the Changelog into Features, Bug fixes, Documentation, etc.
+
+Finally, submit a PR with the updated Changelog.