[pull] dev from ray-project:master

.buildkite/setup-env.sh

@@ -32,7 +32,7 @@ apt-get update
 apt-get install -y python3.11 python3-pip
 
 # Install requirements
-pip install --break-system-packages ray[default]==2.41.0
+pip install --break-system-packages ray[default]==2.46.0
 
 # Bypass Git's ownership check due to unconventional user IDs in Docker containers
 git config --global --add safe.directory /workdir

.buildkite/test-e2e.yml

@@ -10,11 +10,13 @@
     - bash ../.buildkite/build-start-operator.sh
     - kubectl wait --timeout=90s --for=condition=Available=true deployment kuberay-operator
     # Run e2e tests and print KubeRay operator logs if tests fail
-    - echo "--- START:Running e2e rayservice (nightly operator) tests"
+    - echo "--- START:Running e2e (nightly operator) tests"
     - if [ -n "${KUBERAY_TEST_RAY_IMAGE}"]; then echo "Using Ray Image ${KUBERAY_TEST_RAY_IMAGE}"; fi
     - set -o pipefail
-    - KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m go test -timeout 30m -v ./test/e2e 2>&1 | awk -f ../.buildkite/format.awk || (kubectl logs --tail -1 -l app.kubernetes.io/name=kuberay && exit 1)
-    - echo "--- END:e2e rayservice (nightly operator) tests finished"
+    - mkdir -p "$(pwd)/tmp" && export KUBERAY_TEST_OUTPUT_DIR=$(pwd)/tmp
+    - echo "KUBERAY_TEST_OUTPUT_DIR=$$KUBERAY_TEST_OUTPUT_DIR"
+    - KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m go test -timeout 30m -v ./test/e2e 2>&1 | awk -f ../.buildkite/format.awk | tee $$KUBERAY_TEST_OUTPUT_DIR/gotest.log || (kubectl logs --tail -1 -l app.kubernetes.io/name=kuberay | tee $$KUBERAY_TEST_OUTPUT_DIR/kuberay-operator.log && cd $$KUBERAY_TEST_OUTPUT_DIR && find . -name "*.log" | tar -cf /artifact-mount/e2e-log.tar -T - && exit 1)
+    - echo "--- END:e2e (nightly operator) tests finished"
 
 - label: 'Test E2E rayservice (nightly operator)'
   instance_size: large
@@ -31,10 +33,12 @@
     - echo "--- START:Running e2e rayservice (nightly operator) tests"
     - if [ -n "${KUBERAY_TEST_RAY_IMAGE}"]; then echo "Using Ray Image ${KUBERAY_TEST_RAY_IMAGE}"; fi
     - set -o pipefail
-    - KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m go test -timeout 30m -v ./test/e2erayservice 2>&1 | awk -f ../.buildkite/format.awk || (kubectl logs --tail -1 -l app.kubernetes.io/name=kuberay && exit 1)
+    - mkdir -p "$(pwd)/tmp" && export KUBERAY_TEST_OUTPUT_DIR=$(pwd)/tmp
+    - echo "KUBERAY_TEST_OUTPUT_DIR=$$KUBERAY_TEST_OUTPUT_DIR"
+    - KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m go test -timeout 30m -v ./test/e2erayservice 2>&1 | awk -f ../.buildkite/format.awk | tee $$KUBERAY_TEST_OUTPUT_DIR/gotest.log || (kubectl logs --tail -1 -l app.kubernetes.io/name=kuberay | tee $$KUBERAY_TEST_OUTPUT_DIR/kuberay-operator.log && cd $$KUBERAY_TEST_OUTPUT_DIR && find . -name "*.log" | tar -cf /artifact-mount/e2e-rayservice-log.tar -T - && exit 1)
     - echo "--- END:e2e rayservice (nightly operator) tests finished"
 
-- label: 'Test Autoscaler E2E (nightly operator)'
+- label: 'Test Autoscaler E2E Part 1 (nightly operator)'
   instance_size: large
   image: golang:1.24
   commands:
@@ -46,11 +50,33 @@
     - bash ../.buildkite/build-start-operator.sh
     - kubectl wait --timeout=90s --for=condition=Available=true deployment kuberay-operator
     # Run e2e tests and print KubeRay operator logs if tests fail
-    - echo "--- START:Running Autoscaler e2e (nightly operator) tests"
+    - echo "--- START:Running Autoscaler E2E Part 1 (nightly operator) tests"
     - if [ -n "${KUBERAY_TEST_RAY_IMAGE}"]; then echo "Using Ray Image ${KUBERAY_TEST_RAY_IMAGE}"; fi
     - set -o pipefail
-    - KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m go test -timeout 30m -v ./test/e2eautoscaler 2>&1 | awk -f ../.buildkite/format.awk || (kubectl logs --tail -1 -l app.kubernetes.io/name=kuberay && exit 1)
-    - echo "--- END:Autoscaler e2e (nightly operator) tests finished"
+    - mkdir -p "$(pwd)/tmp" && export KUBERAY_TEST_OUTPUT_DIR=$(pwd)/tmp
+    - echo "KUBERAY_TEST_OUTPUT_DIR=$$KUBERAY_TEST_OUTPUT_DIR"
+    - KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m go test -timeout 60m -v ./test/e2eautoscaler/raycluster_autoscaler_test.go ./test/e2eautoscaler/support.go 2>&1 | awk -f ../.buildkite/format.awk | tee $$KUBERAY_TEST_OUTPUT_DIR/gotest.log || (kubectl logs --tail -1 -l app.kubernetes.io/name=kuberay | tee $$KUBERAY_TEST_OUTPUT_DIR/kuberay-operator.log && cd $$KUBERAY_TEST_OUTPUT_DIR && find . -name "*.log" | tar -cf /artifact-mount/e2e-autoscaler-log.tar -T - && exit 1)
+    - echo "--- END:Autoscaler E2E Part 1 (nightly operator) tests finished"
+
+- label: 'Test Autoscaler E2E Part 2 (nightly operator)'
+  instance_size: large
+  image: golang:1.24
+  commands:
+    - source .buildkite/setup-env.sh
+    - kind create cluster --wait 900s --config ./ci/kind-config-buildkite.yml
+    - kubectl config set clusters.kind-kind.server https://docker:6443
+    # Build nightly KubeRay operator image
+    - pushd ray-operator
+    - bash ../.buildkite/build-start-operator.sh
+    - kubectl wait --timeout=90s --for=condition=Available=true deployment kuberay-operator
+    # Run e2e tests and print KubeRay operator logs if tests fail
+    - echo "--- START:Running Autoscaler E2E Part 2 (nightly operator) tests"
+    - if [ -n "${KUBERAY_TEST_RAY_IMAGE}"]; then echo "Using Ray Image ${KUBERAY_TEST_RAY_IMAGE}"; fi
+    - set -o pipefail
+    - mkdir -p "$(pwd)/tmp" && export KUBERAY_TEST_OUTPUT_DIR=$(pwd)/tmp
+    - echo "KUBERAY_TEST_OUTPUT_DIR=$$KUBERAY_TEST_OUTPUT_DIR"
+    - KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m go test -timeout 60m -v ./test/e2eautoscaler/raycluster_autoscaler_part2_test.go ./test/e2eautoscaler/support.go 2>&1 | awk -f ../.buildkite/format.awk | tee $$KUBERAY_TEST_OUTPUT_DIR/gotest.log || (kubectl logs --tail -1 -l app.kubernetes.io/name=kuberay | tee $$KUBERAY_TEST_OUTPUT_DIR/kuberay-operator.log && cd $$KUBERAY_TEST_OUTPUT_DIR && find . -name "*.log" | tar -cf /artifact-mount/e2e-autoscaler-log.tar -T - && exit 1)
+    - echo "--- END:Autoscaler E2E Part 2 (nightly operator) tests finished"
 
 - label: 'Test E2E Operator Version Upgrade (v1.3.0)'
   instance_size: large
@@ -66,15 +92,17 @@
     - kubectl wait --timeout=90s --for=condition=Available=true deployment kuberay-operator
     # Run e2e tests and print KubeRay operator logs if tests fail
     - echo "--- START:Running e2e Operator upgrade (v1.2.2 to v1.3.0 operator) tests"
-    - KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m KUBERAY_TEST_UPGRADE_IMAGE=v1.3.0 go test -timeout 30m -v ./test/e2eupgrade | awk -f ../.buildkite/format.awk || (kubectl logs --tail -1 -l app.kubernetes.io/name=kuberay && exit 1)
+    - mkdir -p "$(pwd)/tmp" && export KUBERAY_TEST_OUTPUT_DIR=$(pwd)/tmp
+    - echo "KUBERAY_TEST_OUTPUT_DIR=$$KUBERAY_TEST_OUTPUT_DIR"
+    - KUBERAY_TEST_TIMEOUT_SHORT=1m KUBERAY_TEST_TIMEOUT_MEDIUM=5m KUBERAY_TEST_TIMEOUT_LONG=10m KUBERAY_TEST_UPGRADE_IMAGE=v1.3.0 go test -timeout 30m -v ./test/e2eupgrade 2>&1 | awk -f ../.buildkite/format.awk | tee $$KUBERAY_TEST_OUTPUT_DIR/gotest.log || (kubectl logs --tail -1 -l app.kubernetes.io/name=kuberay | tee $$KUBERAY_TEST_OUTPUT_DIR/kuberay-operator.log && cd $$KUBERAY_TEST_OUTPUT_DIR && find . -name "*.log" | tar -cf /artifact-mount/e2e-upgrade-log.tar -T - && exit 1)
     - echo "--- END:e2e Operator upgrade (v1.2.2 to v1.3.0 operator) tests finished"
 
 - label: 'Test Apiserver E2E (nightly operator)'
   instance_size: large
   image: golang:1.24
   commands:
     - source .buildkite/setup-env.sh
-    - kind create cluster --wait 900s --config ./ci/kind-config-buildkite-e2e-apiserver.yml
+    - kind create cluster --wait 900s --config ./ci/kind-config-buildkite.yml
     - kubectl config set clusters.kind-kind.server https://docker:6443
     # Build nightly KubeRay operator image
     - pushd ray-operator
@@ -87,5 +115,7 @@
     # Run e2e tests and print KubeRay api server logs if tests fail
     - echo "--- START:Running e2e apiserver (nightly operator) tests"
     - set -o pipefail
-    - E2E_API_SERVER_URL="http://docker:31888" go test -parallel 4 -timeout 60m -v ./test/e2e/... 2>&1 | awk -f ../.buildkite/format.awk || (kubectl logs -l app.kubernetes.io/component=kuberay-apiserver --namespace ray-system > /artifact-mount/kuberay-apiserver-logs.txt && exit 1)
+    - mkdir -p "$(pwd)/tmp" && export KUBERAY_TEST_OUTPUT_DIR=$(pwd)/tmp
+    - echo "KUBERAY_TEST_OUTPUT_DIR=$$KUBERAY_TEST_OUTPUT_DIR"
+    - E2E_API_SERVER_URL="http://docker:31888" go test -parallel 4 -timeout 60m -v ./test/e2e/... 2>&1 | awk -f ../.buildkite/format.awk | tee $$KUBERAY_TEST_OUTPUT_DIR/gotest.log || (kubectl logs -l app.kubernetes.io/component=kuberay-apiserver --namespace ray-system | tee $$KUBERAY_TEST_OUTPUT_DIR/kuberay-apiserver.log && cd $$KUBERAY_TEST_OUTPUT_DIR && find . -name "*.log" | tar -cf /artifact-mount/e2e-apiserver-log.tar -T - && exit 1)
     - echo "--- END:Apiserver e2e (nightly operator) tests finished"

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -31,6 +31,8 @@ body:
       options:
         - "ray-operator"
         - "apiserver"
+        - "kubectl-plugin"
+        - "dashboard"
         - "ci"
         - "Others"
     validations:

.github/dependabot.yml

@@ -15,6 +15,13 @@ updates:
       kubernetes:
         patterns:
           - "k8s.io/*"
+          - "sigs.k8s.io/*"
       google-golang:
         patterns:
           - "google.golang.org/*"
+      github-dependencies:
+        patterns:
+          - "github.com/*"
+      all-dependencies: # for all other dependencies not listed above
+        patterns:
+          - "*"

.github/workflows/consistency-check.yaml

@@ -24,7 +24,7 @@ jobs:
         uses: actions/setup-go@v3
         with:
           # Use the same go version with build job
-          go-version: v1.22
+          go-version: v1.24
 
       - name: Check golang version
         working-directory: ./ray-operator
@@ -51,7 +51,7 @@ jobs:
         uses: actions/setup-go@v3
         with:
           # Use the same go version with build job
-          go-version: v1.22
+          go-version: v1.24
 
       - name: Check golang version
         working-directory: ./ray-operator
@@ -75,7 +75,7 @@ jobs:
         uses: actions/setup-go@v3
         with:
           # Use the same go version with build job
-          go-version: v1.22
+          go-version: v1.24
 
       - name: Update CRD/RBAC YAML files
         working-directory: ./ray-operator

.github/workflows/helm.yaml

@@ -0,0 +1,136 @@
+name: Helm
+
+on:
+  push:
+    branches:
+      - master
+      - release-*
+  pull_request:
+    branches:
+      - master
+      - release-*
+
+env:
+  CHART_DIR: helm-chart
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.actor }}
+  cancel-in-progress: true
+
+jobs:
+  lint-test:
+    name: Lint and Test
+
+    runs-on: ubuntu-24.04
+
+    strategy:
+      matrix:
+        chart:
+          - kuberay-operator
+          - kuberay-apiserver
+          - ray-cluster
+
+    steps:
+      - name: Determine branch name
+        id: get_branch
+        run: |
+          BRANCH=""
+          if [ "${{ github.event_name }}" == "push" ]; then
+            BRANCH=${{ github.ref_name }}
+          elif [ "${{ github.event_name }}" == "pull_request" ]; then
+            BRANCH=${{ github.base_ref }}
+          fi
+          echo "BRANCH=$BRANCH" >> "$GITHUB_OUTPUT"
+
+      - name: Checkout Code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Helm
+        uses: azure/[email protected]
+        with:
+          version: v3.17.3
+
+      - uses: actions/[email protected]
+        with:
+          python-version: 3.13
+
+      - name: Install Helm unittest plugin
+        run: helm plugin install https://github.com/helm-unittest/helm-unittest.git --version 0.8.1
+
+      - name: Run Helm unittest
+        run: helm unittest ${{ env.CHART_DIR }}/${{ matrix.chart }} --file "tests/**/*_test.yaml" --strict --debug
+
+      - name: Set up chart-testing
+        uses: helm/[email protected]
+
+      - name: Run chart-testing (list-changed)
+        id: list-changed
+        env:
+          BRANCH: ${{ steps.get_branch.outputs.BRANCH }}
+        run: |
+          changed=$(ct list-changed --target-branch $BRANCH --chart-dirs ${{ env.CHART_DIR }} | grep ${{ matrix.chart }} || true)
+          if [[ -n "$changed" ]]; then
+            echo "changed=true" >> "$GITHUB_OUTPUT"
+          fi
+
+      - name: Run chart-testing (lint)
+        if: steps.list-changed.outputs.changed == 'true'
+        env:
+          BRANCH: ${{ steps.get_branch.outputs.BRANCH }}
+        run: |
+          # Run 'helm lint', version checking, YAML schema validation on 'Chart.yaml',
+          # YAML linting on 'Chart.yaml' and 'values.yaml', and maintainer.
+          # [Doc]: https://github.com/helm/chart-testing/blob/main/doc/ct_lint.md
+          ct lint --charts ${{ env.CHART_DIR }}/${{ matrix.chart }} --validate-maintainers=false
+
+      - name: Create kind cluster
+        if: steps.list-changed.outputs.changed == 'true'
+        uses: helm/[email protected]
+        with:
+          cluster_name: kind
+
+      - name: Build Docker image (kuberay-operator)
+        if: steps.list-changed.outputs.changed == 'true' && matrix.chart == 'kuberay-operator'
+        run: |
+          cd ray-operator && make docker-image -e IMG=kuberay/operator:local
+
+      - name: Build Docker image (kuberay-apiserver)
+        if: steps.list-changed.outputs.changed == 'true' && matrix.chart == 'kuberay-apiserver'
+        run: |
+          cd apiserver && make docker-image -e IMG=kuberay/apiserver:local
+
+      - name: Build Docker image (security-proxy)
+        if: steps.list-changed.outputs.changed == 'true' && matrix.chart == 'kuberay-apiserver'
+        run: |
+          cd experimental && make docker-image -e IMG=kuberay/security-proxy:local
+
+      - name: Load image to kind cluster (kuberay-operator)
+        if: steps.list-changed.outputs.changed == 'true' && matrix.chart == 'kuberay-operator'
+        run: |
+          kind load docker-image kuberay/operator:local
+
+      - name: Load image to kind cluster (kuberay-apiserver)
+        if: steps.list-changed.outputs.changed == 'true' && matrix.chart == 'kuberay-apiserver'
+        run: |
+          kind load docker-image kuberay/apiserver:local
+
+      - name: Load image to kind cluster (security-proxy)
+        if: steps.list-changed.outputs.changed == 'true' && matrix.chart == 'kuberay-apiserver'
+        run: |
+          kind load docker-image kuberay/security-proxy:local
+
+      - name: Install Custom Resource Definitions to kind cluster
+        if: steps.list-changed.outputs.changed == 'true' && matrix.chart == 'ray-cluster'
+        working-directory: helm-chart/kuberay-operator
+        run: kubectl create -f crds
+
+      - name: Run chart-testing
+        if: steps.list-changed.outputs.changed == 'true'
+        env:
+          BRANCH: ${{ steps.get_branch.outputs.BRANCH }}
+        run: |
+          # Run 'helm install', 'helm test', and optionally 'helm upgrade' on specified charts.
+          # [Doc]: https://github.com/helm/chart-testing/blob/main/doc/ct_install.md
+          ct install --charts ${{ env.CHART_DIR}}/${{ matrix.chart }}