Merge pull request #4389 from JesseStutler/fix_4299

Delete secrets permission for volcano agent

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,24 +1,4 @@
 #### What type of PR is this?
-<!--
-Add one of the following kinds:
-/kind bug
-/kind cleanup
-/kind documentation
-/kind feature
-/kind failing-test
-/kind flake
-
-Optionally add one of the following areas, help us further classify and filter PRs:
-/area scheduling
-/area controllers
-/area cli
-/area dependency
-/area webhooks
-/area deploy
-/area documentation
-/area performance
-/area test
--->
 
 #### What this PR does / why we need it:
 

.github/dependabot.yml

@@ -0,0 +1,45 @@
+version: 2
+updates:
+  - package-ecosystem: gomod
+    directory: /
+    schedule:
+      interval: weekly
+    groups:
+      k8s-libs:
+        patterns:
+          - "k8s.io/api"
+          - "k8s.io/apiextensions-apiserver"
+          - "k8s.io/apimachinery"
+          - "k8s.io/apiserver"
+          - "k8s.io/cli-runtime"
+          - "k8s.io/client-go"
+          - "k8s.io/cloud-provider"
+          - "k8s.io/cluster-bootstrap"
+          - "k8s.io/code-generator"
+          - "k8s.io/component-base"
+          - "k8s.io/component-helpers"
+          - "k8s.io/controller-manager"
+          - "k8s.io/cri-api"
+          - "k8s.io/cri-client"
+          - "k8s.io/csi-translation-lib"
+          - "k8s.io/dynamic-resource-allocation"
+          - "k8s.io/endpointslice"
+          - "k8s.io/kube-aggregator"
+          - "k8s.io/kube-controller-manager"
+          - "k8s.io/kube-proxy"
+          - "k8s.io/kube-scheduler"
+          - "k8s.io/kubectl"
+          - "k8s.io/kubelet"
+          - "k8s.io/legacy-cloud-providers"
+          - "k8s.io/metrics"
+          - "k8s.io/mount-utils"
+          - "k8s.io/node-api"
+          - "k8s.io/pod-security-admission"
+          - "k8s.io/sample-apiserver"
+          - "k8s.io/sample-cli-plugin"
+          - "k8s.io/sample-controller"
+
+  - package-ecosystem: github-actions
+    directory: /
+    schedule:
+      interval: weekly

.github/stale.yml

@@ -1,50 +0,0 @@
-# Configuration for probot-stale - https://github.com/probot/stale
-
-# Only issues or pull requests with all of these labels are check if stale. Defaults to `[]` (disabled)
-onlyLabels: []
-
-# Issues or Pull Requests with these labels will never be considered stale. Set to `[]` to disable.
-# We want stale bot to notify us that something is stale so we can revisit it.
-# If one issue is marked as 'reminder' by the reminder bot, we don't mark it as 'stale' again.
-exemptLabels:
-  # This label is hardcoded on remind bot (https://probot.github.io/apps/reminders/) and is used by remind bot when
-  # issue is being reminded.
-  - reminder
-
-# Set to true to ignore issues in a project (defaults to false)
-exemptProjects: false
-# Set to true to ignore issues in a milestone (defaults to false)
-exemptMilestones: false
-# Set to true to ignore issues with an assignee (defaults to false)
-exemptAssignees: false
-# Label to use when marking as stale
-staleLabel: lifecycle/stale
-
-pull:
-  daysUntilClose: 60
-  daysUntilStale: 90
-  markComment: >
-    Hello 👋 Looks like there was no activity on this amazing PR for last 90 days.
-
-    **Do you mind updating us on the status?** Is there anything we can help with? If you plan to still work on it, just comment on this PR or push a commit. Thanks! 🤗
-
-    If there will be no activity for 60 days, this issue will be closed (we can always reopen a PR if you get back to this!).
-  #unmarkComment: No need for unmark comment.
-  closeComment: >
-    Closing for now as there was no activity for last 60 days after marked as stale, let us know if you need this to be reopened! 🤗
-
-issues:
-  daysUntilClose: 60
-  daysUntilStale: 90
-  markComment: >
-    Hello 👋 Looks like there was no activity on this issue for last 90 days.
-
-    **Do you mind updating us on the status?** Is this still reproducible or needed? If yes, just comment on this PR or push a commit. Thanks! 🤗
-
-    If there will be no activity for 60 days, this issue will be closed (we can always reopen an issue if we need!).
-  #unmarkComment: No need for unmark comment.
-  closeComment: >
-    Closing for now as there was no activity for last 60 days after marked as stale, let us know if you need this to be reopened! 🤗
-
-# Limit the number of actions per hour, from 1-30. Default is 30
-limitPerRun: 30

.github/workflows/code_verify.yaml

@@ -16,9 +16,9 @@ jobs:
       GOPATH: /home/runner/work/${{ github.repository }}
     steps:
       - name: Install Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
-          go-version: 1.22.x
+          go-version: 1.23.x
 
       - name: Checkout code
         uses: actions/checkout@v3
@@ -35,7 +35,7 @@ jobs:
         run: |
           make lint
           make verify
-          make TAG=v1.11.0-network-topology-preview.2 generate-yaml
+          make TAG=latest generate-yaml
           make verify-generated-yaml
           sudo make unit-test
         working-directory: ./src/github.com/${{ github.repository }}

.github/workflows/codeql-analysis.yml

@@ -39,7 +39,7 @@ jobs:
 
     # Initializes the CodeQL tools for scanning.
     - name: Initialize CodeQL
-      uses: github/codeql-action/init@v1
+      uses: github/codeql-action/init@v3
       with:
         languages: ${{ matrix.language }}
         # If you wish to specify custom queries, you can do so here or in a config file.
@@ -50,7 +50,7 @@ jobs:
     # Autobuild attempts to build any compiled languages  (C/C++, C#, or Java).
     # If this step fails, then you should remove it and run the build manually (see below)
     - name: Autobuild
-      uses: github/codeql-action/autobuild@v1
+      uses: github/codeql-action/autobuild@v3
 
     # ℹ️ Command-line programs to run using the OS shell.
     # 📚 https://git.io/JvXDl
@@ -64,4 +64,4 @@ jobs:
     #   make release
 
     - name: Perform CodeQL Analysis
-      uses: github/codeql-action/analyze@v1
+      uses: github/codeql-action/analyze@v3

.github/workflows/e2e_dra.yml

@@ -0,0 +1,49 @@
+name: E2E DRA
+
+on:
+  push:
+    branches:
+      - master
+    tags:
+  pull_request:
+
+jobs:
+  e2e_dra:
+    runs-on: ubuntu-24.04
+    name: E2E about DRA
+    timeout-minutes: 40
+    steps:
+      - name: Install Go
+        uses: actions/setup-go@v5
+        with:
+          go-version: 1.23.x
+
+      - name: Install musl
+        run: |
+          wget http://musl.libc.org/releases/musl-1.2.1.tar.gz
+          tar -xf musl-1.2.1.tar.gz && cd musl-1.2.1
+          ./configure
+          make && sudo make install
+      - uses: actions/cache@v4
+        with:
+          path: ~/go/pkg/mod
+          key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
+
+      - name: Install dependences
+        run: |
+          GO111MODULE="on" go install sigs.k8s.io/kind@v0.26.0
+          curl -LO https://dl.k8s.io/release/v1.32.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Run E2E Tests
+        run: |
+          export ARTIFACTS_PATH=${{ github.workspace }}/e2e-dra-logs
+          make e2e-test-dra CC=/usr/local/musl/bin/musl-gcc
+
+      - name: Upload e2e dra logs
+        if: failure()
+        uses: actions/upload-artifact@v4
+        with:
+          name: volcano_e2e_dra_logs
+          path: ${{ github.workspace }}/e2e-dra-logs

.github/workflows/e2e_parallel_jobs.yaml

@@ -7,6 +7,10 @@ on:
     tags:
   pull_request:
 
+permissions:
+  contents: read
+  actions: write
+
 jobs:
   e2e_parallel_jobs:
     runs-on: ubuntu-24.04
@@ -14,9 +18,9 @@ jobs:
     timeout-minutes: 40
     steps:
       - name: Install Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
-          go-version: 1.22.x
+          go-version: 1.23.x
 
       - name: Install musl
         run: |
@@ -31,8 +35,8 @@ jobs:
 
       - name: Install dependences
         run: |
-          GO111MODULE="on" go install sigs.k8s.io/kind@v0.24.0
-          curl -LO https://storage.googleapis.com/kubernetes-release/release/v1.31.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
+          GO111MODULE="on" go install sigs.k8s.io/kind@v0.26.0
+          curl -LO https://dl.k8s.io/release/v1.32.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
       - name: Checkout code
         uses: actions/checkout@v3
 

.github/workflows/e2e_scheduling_actions.yaml

@@ -11,12 +11,12 @@ jobs:
   e2e_scheduling_actions:
     runs-on: ubuntu-24.04
     name: E2E about Scheduling Actions
-    timeout-minutes: 40
+    timeout-minutes: 50
     steps:
       - name: Install Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
-          go-version: 1.22.x
+          go-version: 1.23.x
 
       - name: Install musl
         run: |
@@ -31,8 +31,8 @@ jobs:
 
       - name: Install dependences
         run: |
-          GO111MODULE="on" go install sigs.k8s.io/kind@v0.24.0
-          curl -LO https://storage.googleapis.com/kubernetes-release/release/v1.31.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
+          GO111MODULE="on" go install sigs.k8s.io/kind@v0.26.0
+          curl -LO https://dl.k8s.io/release/v1.32.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
       - name: Checkout code
         uses: actions/checkout@v3
 

.github/workflows/e2e_scheduling_basic.yaml

@@ -11,12 +11,12 @@ jobs:
   e2e_scheduling_basic:
     runs-on: ubuntu-24.04
     name: E2E about Basic Scheduling
-    timeout-minutes: 40
+    timeout-minutes: 50
     steps:
       - name: Install Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
-          go-version: 1.22.x
+          go-version: 1.23.x
 
       - name: Install musl
         run: |
@@ -31,8 +31,8 @@ jobs:
 
       - name: Install dependences
         run: |
-          GO111MODULE="on" go install sigs.k8s.io/kind@v0.24.0
-          curl -LO https://storage.googleapis.com/kubernetes-release/release/v1.31.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
+          GO111MODULE="on" go install sigs.k8s.io/kind@v0.26.0
+          curl -LO https://dl.k8s.io/release/v1.32.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
       - name: Checkout code
         uses: actions/checkout@v3
 

.github/workflows/e2e_sequence.yaml

@@ -11,12 +11,12 @@ jobs:
   e2e_sequence:
     runs-on: ubuntu-24.04
     name: E2E about Sequence
-    timeout-minutes: 40
+    timeout-minutes: 50
     steps:
       - name: Install Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
-          go-version: 1.22.x
+          go-version: 1.23.x
 
       - name: Install musl
         run: |
@@ -31,8 +31,8 @@ jobs:
 
       - name: Install dependences
         run: |
-          GO111MODULE="on" go install sigs.k8s.io/kind@v0.24.0
-          curl -LO https://storage.googleapis.com/kubernetes-release/release/v1.31.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
+          GO111MODULE="on" go install sigs.k8s.io/kind@v0.26.0
+          curl -LO https://dl.k8s.io/release/v1.32.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
       - name: Checkout code
         uses: actions/checkout@v3
 

.github/workflows/e2e_spark.yaml

@@ -10,7 +10,7 @@ on:
 jobs:
   k8s-integration-tests:
     name: "E2E about Spark Integration test"
-    runs-on: ubuntu-20.04
+    runs-on: ubuntu-24.04
     steps:
     - name: Free Disk Space (Ubuntu)
       uses: jlumbroso/free-disk-space@main
@@ -58,17 +58,17 @@ jobs:
         restore-keys: |
           k8s-integration-coursier-
     - name: Install Java 8
-      uses: actions/setup-java@v3
+      uses: actions/setup-java@v4
       with:
         distribution: temurin
         java-version: 8
     - name: Install Go
-      uses: actions/setup-go@v4
+      uses: actions/setup-go@v5
       with:
-        go-version: 1.22.x
+        go-version: 1.23.x
     - name: Set up Docker Buildx
       id: buildx
-      uses: docker/setup-buildx-action@v2
+      uses: docker/setup-buildx-action@v3
     - name: start minikube
       run: |
         # Use pre-install minikube
@@ -76,11 +76,12 @@ jobs:
     - name: Build lastest volcano images
       run: |
         eval $(minikube docker-env)
-        make TAG=v1.11.0-network-topology-preview.2 update-development-yaml
-        make TAG=v1.11.0-network-topology-preview.2 images
+        make TAG=latest update-development-yaml
+        sed -i 's/imagePullPolicy: Always/imagePullPolicy: IfNotPresent/g' installer/volcano-development.yaml
+        make TAG=latest images
         docker images | grep volcano
         cat ./installer/volcano-development.yaml  | grep image:
-        sed 's/imagePullPolicy: Always/imagePullPolicy: IfNotPresent/' ./installer/volcano-development.yaml | minikube kubectl -- replace --force -f -
+        minikube kubectl -- replace --force -f ./installer/volcano-development.yaml
     - name: Show all K8S pods and nodes
       run: |
         # Use minikube kubectl

.github/workflows/e2e_vcctl.yaml

@@ -11,12 +11,12 @@ jobs:
   e2e_vcctl:
     runs-on: ubuntu-24.04
     name: E2E about Volcano CLI
-    timeout-minutes: 20
+    timeout-minutes: 50
     steps:
       - name: Install Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
-          go-version: 1.22.x
+          go-version: 1.23.x
 
       - name: Install musl
         run: |
@@ -31,8 +31,8 @@ jobs:
 
       - name: Install dependences
         run: |
-          GO111MODULE="on" go install sigs.k8s.io/kind@v0.24.0
-          curl -LO https://storage.googleapis.com/kubernetes-release/release/v1.31.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
+          GO111MODULE="on" go install sigs.k8s.io/kind@v0.26.0
+          curl -LO https://dl.k8s.io/release/v1.32.0/bin/linux/amd64/kubectl && sudo install kubectl /usr/local/bin/kubectl
       - name: Checkout code
         uses: actions/checkout@v3
 

.github/workflows/fossa.yml

@@ -10,9 +10,9 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v3
-      - uses: actions/setup-go@v4
+      - uses: actions/setup-go@v5
         with:
-          go-version: 1.22.x
+          go-version: 1.23.x
       - run: go version
       # Runs a set of commands to initialize and analyze with FOSSA
       - name: run FOSSA analysis

.github/workflows/licenses_lint.yaml

@@ -11,12 +11,12 @@ jobs:
   licenses-lint:
     name: Licenses Lint
     timeout-minutes: 40
-    runs-on: ubuntu-22.04
+    runs-on: ubuntu-24.04
     steps:
       - name: Install Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
-          go-version: 1.21.x
+          go-version: 1.23.x
       - name: Checkout code
         uses: actions/checkout@v3
       - name: generate license mirror

.github/workflows/release.yaml

@@ -16,9 +16,9 @@ jobs:
       GOPATH: /home/runner/work/${{ github.repository }}
     steps:
       - name: Install Go
-        uses: actions/setup-go@v4
+        uses: actions/setup-go@v5
         with:
-          go-version: 1.22.x
+          go-version: 1.23.x
 
       - name: Install musl
         run: |
@@ -53,12 +53,12 @@ jobs:
         run: |
           make verify
           make TAG=${{ env.TAG }} generate-yaml
-          make verify-generated-yaml
+          make RELEASE_TAG=${{ env.TAG }} verify-generated-yaml
           sudo make unit-test
         working-directory: ./src/github.com/${{ github.repository }}
 
       - name: Login to DockerHub
-        uses: docker/login-action@v1 
+        uses: docker/login-action@v3 
         with:
           username: ${{ secrets.DOCKERHUB_USERNAME }}
           password: ${{ secrets.DOCKERHUB_TOKEN }}

.github/workflows/scorecards.yml

@@ -33,7 +33,7 @@ jobs:
           persist-credentials: false
 
       - name: "Run analysis"
-        uses: ossf/scorecard-action@0864cf19026789058feabb7e87baa5f140aac736 # v2.3.1
+        uses: ossf/scorecard-action@f49aabe0b5af0936a0987cfb85d86b75731b0186 # v2.4.1
         with:
           results_file: results.sarif
           results_format: sarif
@@ -55,9 +55,9 @@ jobs:
       # Upload the results as artifacts (optional). Commenting out will disable uploads of run results in SARIF
       # format to the repository Actions tab.
       - name: "Upload artifact"
-        uses: actions/upload-artifact@97a0fba1372883ab732affbe8f94b823f91727db # v3.pre.node20
+        uses: actions/upload-artifact@v4.6.2
         with:
-          name: SARIF file
+          name: sarif_file
           path: results.sarif
           retention-days: 5
 

.github/workflows/stale.yaml

@@ -0,0 +1,47 @@
+name: Mark and Close Stale Issues and PRs
+
+on:
+  schedule:
+    - cron: '0 0 * * *' # runs every day at midnight UTC
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    permissions:
+      issues: write
+      pull-requests: write
+    steps:
+      - name: Mark and close stale issues and PRs
+        uses: actions/stale@5bef64f19d7facfb25b37b414482c7164d639639 #v9.1.0
+        with:
+          remove-stale-when-updated: true
+          stale-issue-label: 'lifecycle/stale'
+          exempt-issue-labels: 'kind/feature, kind/bug, help wanted, good first issue'
+          exempt-pr-labels: ''
+          days-before-stale: 180
+          days-before-close: 90
+
+          stale-issue-message: >
+            Hello 👋 Looks like there was no activity on this issue for last 180 days.
+
+            **Do you mind updating us on the status?** Is this still reproducible or needed? If yes, just comment on this PR or push a commit. Thanks! 🤗
+
+            If there will be no activity for 90 days, this issue will be closed (we can always reopen an issue if we need!).
+
+          close-issue-message: >
+            Closing for now as there was no activity for last 90 days after marked as stale, let us know if you need this to be reopened! 🤗
+
+          stale-pr-message: >
+            Hello 👋 Looks like there was no activity on this amazing PR for last 180 days.
+
+            **Do you mind updating us on the status?** Is there anything we can help with? If you plan to still work on it, just comment on this PR or push a commit. Thanks! 🤗
+
+            If there will be no activity for 90 days, this issue will be closed (we can always reopen a PR if you get back to this!).
+
+          close-pr-message: >
+            Closing for now as there was no activity for last 90 days after marked as stale, let us know if you need this to be reopened! 🤗
+
+          exempt-all-milestones: false
+          exempt-all-assignees: false
+
+          operations-per-run: 30

.golangci.yml

@@ -69,7 +69,7 @@ linters-settings:
   depguard:
     rules:
       main:
-        list-mode: strict
+        list-mode: original
         deny:
           - pkg: "k8s.io/klog$"
             desc: "k8s.io/klog is deprecated, use k8s.io/klog/v2 instead"

CITATION.cff

@@ -0,0 +1,24 @@
+cff-version: 1.2.0
+message: "If you use Volcano in your work, please cite it using the information below. This helps us demonstrate the project's impact."
+title: "Volcano: A Cloud Native Batch System"
+authors:
+  - given-names: "Klaus"
+    family-names: "Ma"
+  - given-names: "Kevin"
+    family-names: "Wang"
+  - name: "The Volcano Community & Contributors"
+    type: entity
+
+repository-code: "https://github.com/volcano-sh/volcano"
+url: "https://volcano.sh/"
+keywords:
+  - "batch system"
+  - "kubernetes"
+  - "scheduling"
+  - "cncf"
+  - "high-performance computing"
+  - "big data"
+  - "artificial intelligence"
+  - "machine learning"
+license: "Apache-2.0"
+notes: "For a specific version, please find the release tag or use the general project information. A comprehensive list of releases can be found at: https://github.com/volcano-sh/volcano/releases"

Makefile

@@ -19,6 +19,7 @@ IMAGE_PREFIX=volcanosh
 CRD_OPTIONS ?= "crd:crdVersions=v1,generateEmbeddedObjectMeta=true"
 CRD_OPTIONS_EXCLUDE_DESCRIPTION=${CRD_OPTIONS}",maxDescLen=0"
 CC ?= "gcc"
+MUSL_CC ?= "/usr/local/musl/bin/musl-gcc"
 SUPPORT_PLUGINS ?= "no"
 CRD_VERSION ?= v1
 BUILDX_OUTPUT_TYPE ?= "docker"
@@ -73,7 +74,7 @@ init:
 
 vc-scheduler: init
 	if [ ${SUPPORT_PLUGINS} = "yes" ];then\
-		CC=${CC} CGO_ENABLED=1 go build -ldflags ${LD_FLAGS} -o ${BIN_DIR}/vc-scheduler ./cmd/scheduler;\
+		CC=${MUSL_CC} CGO_ENABLED=1 go build -ldflags ${LD_FLAGS_CGO} -o ${BIN_DIR}/vc-scheduler ./cmd/scheduler;\
 	else\
 		CC=${CC} CGO_ENABLED=0 go build -ldflags ${LD_FLAGS} -o ${BIN_DIR}/vc-scheduler ./cmd/scheduler;\
 	fi;
@@ -142,6 +143,9 @@ e2e-test-vcctl: vcctl images
 e2e-test-stress: images
 	E2E_TYPE=STRESS ./hack/run-e2e-kind.sh
 
+e2e-test-dra: images
+	E2E_TYPE=DRA FEATURE_GATES="DynamicResourceAllocation=true" ./hack/run-e2e-kind.sh
+
 generate-yaml: init manifests
 	./hack/generate-yaml.sh TAG=${RELEASE_VER} CRD_VERSION=${CRD_VERSION}
 
@@ -190,7 +194,7 @@ ifeq (, $(shell which controller-gen))
 	CONTROLLER_GEN_TMP_DIR=$$(mktemp -d) ;\
 	cd $$CONTROLLER_GEN_TMP_DIR ;\
 	go mod init tmp ;\
-	GOOS=${OS} go install sigs.k8s.io/controller-tools/cmd/controller-gen@v0.16.4 ;\
+	GOOS=${OS} go install sigs.k8s.io/controller-tools/cmd/controller-gen@v0.17.0 ;\
 	rm -rf $$CONTROLLER_GEN_TMP_DIR ;\
 	}
 CONTROLLER_GEN=$(GOBIN)/controller-gen
@@ -199,9 +203,9 @@ CONTROLLER_GEN=$(shell which controller-gen)
 endif
 
 update-development-yaml:
-	make generate-yaml TAG=v1.11.0-network-topology-preview.2 RELEASE_DIR=installer
-	mv installer/volcano-v1.11.0-network-topology-preview.2.yaml installer/volcano-development.yaml
-	mv installer/volcano-agent-v1.11.0-network-topology-preview.2.yaml installer/volcano-agent-development.yaml
+	make generate-yaml TAG=latest RELEASE_DIR=installer
+	mv installer/volcano-latest.yaml installer/volcano-development.yaml
+	mv installer/volcano-agent-latest.yaml installer/volcano-agent-development.yaml
 
 mod-download-go:
 	@-GOFLAGS="-mod=readonly" find -name go.mod -execdir go mod download \;
@@ -212,7 +216,7 @@ mod-download-go:
 
 .PHONY: mirror-licenses
 mirror-licenses: mod-download-go; \
-	GOOS=${OS} go install istio.io/tools/cmd/license-lint@1.19.7; \
+	GOOS=${OS} go install istio.io/tools/cmd/license-lint@1.25.0; \
 	cd licenses; \
 	rm -rf `ls ./ | grep -v LICENSE`; \
 	cd -; \

Makefile.def

@@ -1,11 +1,16 @@
 
 # If tag not explicitly set in users default to the git sha.
-TAG ?= v1.11.0-network-topology-preview.2
+TAG ?= $(shell git rev-parse --verify HEAD)
 GitSHA=`git rev-parse HEAD`
 Date=`date "+%Y-%m-%d %H:%M:%S"`
-RELEASE_VER=v1.11.0-network-topology-preview.2
+RELEASE_VER=latest
 OPEN_EULER_IMAGE_TAG ?= 22.03-lts-sp2
-LD_FLAGS=" \
+LD_FLAGS="\
+    -X '${REPO_PATH}/pkg/version.GitSHA=${GitSHA}' \
+    -X '${REPO_PATH}/pkg/version.Built=${Date}'   \
+    -X '${REPO_PATH}/pkg/version.Version=${RELEASE_VER}'"
+LD_FLAGS_CGO="\
+    -linkmode=external \
     -X '${REPO_PATH}/pkg/version.GitSHA=${GitSHA}' \
     -X '${REPO_PATH}/pkg/version.Built=${Date}'   \
     -X '${REPO_PATH}/pkg/version.Version=${RELEASE_VER}'"

OWNERS

@@ -19,6 +19,7 @@ reviewers:
   - Monokaix
   - lowang-bh
   - archlitchi
+  - JesseStutler
 approvers:
   - k82cn
   - kevin-wangzefeng
@@ -31,3 +32,4 @@ approvers:
   - Monokaix
   - lowang-bh
   - hwdef
+  - wangyang0616

README.md

@@ -14,20 +14,15 @@
 [![Gurubase](https://img.shields.io/badge/Gurubase-Ask%20Volcano%20Guru-006BFF)](https://gurubase.io/g/volcano)
 
 
-[Volcano](https://volcano.sh/) is a batch system built on Kubernetes. It provides a suite of mechanisms that are commonly required by
-many classes of batch & elastic workload including: machine learning/deep learning, bioinformatics/genomics and
-other "big data" applications. These types of applications typically run on generalized domain frameworks like
-TensorFlow, Spark, Ray, PyTorch, MPI, etc, which Volcano integrates with.
 
-Volcano builds upon a decade and a half of experience running a wide
-variety of high performance workloads at scale using several systems
-and platforms, combined with best-of-breed ideas and practices from
-the open source community.
+[Volcano](https://volcano.sh/) is a Kubernetes-native batch scheduling system, extending and enhancing the capabilities of the standard kube-scheduler. It provides a comprehensive set of features specifically designed to manage and optimize various batch and elastic workloads, including Artificial Intelligence (AI) / machine learning (ML) / deep learning (DL), bioinformatics / genomics, and other "Big Data" applications.
+
+These workloads commonly leverage AI, Big Data, and HPC frameworks such as Spark, Flink, Ray, TensorFlow, PyTorch, Argo, MindSpore, PaddlePaddle, Kubeflow, MPI, Horovod, MXNet, KubeGene, and others, with which Volcano offers robust integration.
+
+Volcano incorporates over fifteen years of collective experience in operating diverse high-performance workloads at scale across multiple systems and platforms. It combines proven best practices and innovative concepts from the open-source community to deliver a powerful and flexible scheduling solution.
+
+As of 2025, Volcano has seen widespread adoption across numerous industries globally, including Internet/Cloud, Finance, Manufacturing, and Medical sectors. Many organizations and institutions are not only end-users but also active contributors to the project. Hundreds of contributors actively participate in code commits, pull request reviews, issue discussions, documentation updates, and design proposals. We encourage your participation in the ongoing development and growth of the Volcano project.
 
-Until June 2021, Volcano has been widely used around the world at a variety of industries such as Internet/Cloud/Finance/
-Manufacturing/Medical. More than 20 companies or institutions are not only end users but also active contributors. Hundreds
-of contributors are taking active part in the code commit/PR review/issue discussion/docs update and design provision. We
-are looking forward to your participation.
 
 **NOTE**: the scheduler is built based on [kube-batch](https://github.com/kubernetes-sigs/kube-batch);
 refer to [#241](https://github.com/volcano-sh/volcano/issues/241) and [#288](https://github.com/volcano-sh/volcano/pull/288) for more detail.
@@ -49,7 +44,7 @@ Volcano is an incubating project of the [Cloud Native Computing Foundation](http
 - [Batch Capability of Kubernetes Intro @ KubeCon 2019 NA](https://sched.co/Uajv)
 - [Optimizing Knowledge Distillation Training With Volcano @ KubeCon 2021 EU](https://www.youtube.com/watch?v=cDPGmhVcj7Y&t=143s)
 - [Exploration About Mixing Technology of Online Services and Offline Jobs Based On Volcano @ KubeCon 2021 China](https://www.youtube.com/watch?v=daqkUlT5ReY)
-- [Volcano - Cloud Native Batch System for AI, BigData and HPC @ KubeCon 2022 EU](https://www.youtube.com/watch?v=wjy35HfIP_k)
+- [Volcano - Cloud Native Batch System for AI, Big Data and HPC @ KubeCon 2022 EU](https://www.youtube.com/watch?v=wjy35HfIP_k)
 - [How to Leverage Volcano to Improve the Resource Utilization of AI Pharmaceuticals, Autonomous Driving, and Smart Buildings @ KubeCon 2023 EU](https://www.youtube.com/watch?v=ujHDV5xteqU)
 - [Run Your AI Workloads and Microservices on Kubernetes More Easily and Efficiently @ KubeCon 2023 China](https://www.youtube.com/watch?v=OO7zpyf7fgs)
 - [Optimize LLM Workflows with Smart Infrastructure Enhanced by Volcano @ KubeCon 2024 China](https://www.youtube.com/watch?v=77Qn1-I-muQ)
@@ -59,13 +54,37 @@ Volcano is an incubating project of the [Cloud Native Computing Foundation](http
 
 ## Ecosystem
 
-- [spark-operator](https://www.kubeflow.org/docs/components/spark-operator/user-guide/volcano-integration/)
+- [Spark Operator](https://www.kubeflow.org/docs/components/spark-operator/user-guide/volcano-integration/)
+- [Native Spark](https://spark.apache.org/docs/3.5.0/running-on-kubernetes.html#using-volcano-as-customized-scheduler-for-spark-on-kubernetes)
+- [Flink](https://github.com/GoogleCloudPlatform/flink-on-k8s-operator/blob/master/docs/volcano_integration.md)
+- [KubeRay](https://docs.ray.io/en/master/cluster/kubernetes/k8s-ecosystem/volcano.html)
+- [PyTorch](https://github.com/volcano-sh/volcano/blob/master/docs/user-guide/how_to_use_pytorch_plugin.md)
+- [TensorFlow](https://github.com/volcano-sh/volcano/tree/master/example/integrations/tensorflow)
 - [kubeflow/training-operator](https://www.kubeflow.org/docs/components/training/user-guides/job-scheduling/)
 - [kubeflow/arena](https://github.com/kubeflow/arena/blob/master/docs/training/volcanojob/volcanojob.md)
-- [Horovod/MPI](https://github.com/volcano-sh/volcano/tree/master/example/integrations/mpi)
-- [paddlepaddle](https://github.com/volcano-sh/volcano/tree/master/example/integrations/paddlepaddle)
-- [cromwell](https://github.com/broadinstitute/cromwell/blob/develop/docs/backends/Volcano.md)
-- [KubeRay](https://docs.ray.io/en/master/cluster/kubernetes/k8s-ecosystem/volcano.html)
+- [MPI](https://github.com/volcano-sh/volcano/tree/master/example/integrations/mpi)
+- [Horovod](https://github.com/volcano-sh/volcano/blob/master/example/kubecon-2019-china/horovod-sample/lm-horovod-tf-mnist-v0.5.yaml)
+- [PaddlePaddle](https://github.com/volcano-sh/volcano/tree/master/example/integrations/paddlepaddle)
+- [Cromwell](https://github.com/broadinstitute/cromwell/blob/develop/docs/backends/Volcano.md)
+- [MindSpore](https://github.com/volcano-sh/volcano/tree/master/example/MindSpore-example)
+- [MXNet](https://github.com/volcano-sh/volcano/tree/master/example/integrations/mxnet/train)
+- [Argo](https://github.com/volcano-sh/volcano/tree/master/example/integrations/argo)
+- [KubeGene](https://github.com/volcano-sh/kubegene)
+
+## Use Cases
+- [Why Spark chooses Volcano as built-in batch scheduler on Kubernetes?](https://www.cncf.io/blog/2022/06/30/why-spark-chooses-volcano-as-built-in-batch-scheduler-on-kubernetes/)
+- [ING Bank: How Volcano empowers its big data analytics platform](https://www.cncf.io/blog/2023/02/21/ing-bank-how-volcano-empowers-its-big-data-analytics-platform/)
+- [Using Volcano as a custom scheduler for Apache Spark on Amazon EMR on EKS](https://docs.aws.amazon.com/emr/latest/EMR-on-EKS-DevelopmentGuide/tutorial-volcano.html)
+- [Deploy Azure Machine Learning extension on AKS or Arc Kubernetes cluster](https://learn.microsoft.com/en-us/azure/machine-learning/how-to-deploy-kubernetes-extension?view=azureml-api-2&tabs=deploy-extension-with-cli)
+- [Practical Tips for Preventing GPU Fragmentation for Volcano Scheduler](https://developer.nvidia.com/blog/practical-tips-for-preventing-gpu-fragmentation-for-volcano-scheduler/)
+- [Using Volcano in Large-Scale, Distributed Offline Computing](https://volcano.sh/en/blog/ruitian2-en/)
+- [OpenI-Octopus: How to Avoid Resource Preemption in Kubernetes Clusters](https://volcano.sh/en/blog/pengcheng-en/)
+- [How Does Volcano Empower a Content Recommendation Engine in Xiaohongshu](https://volcano.sh/en/blog/xiaohongshu-en/)
+- [How Ruitian Used Volcano to Run Large-Scale Offline HPC Jobs](https://volcano.sh/en/blog/ruitian-en/)
+- [Integrating Volcano into the Leinao Cloud OS](https://volcano.sh/en/blog/leinao-en/)
+- [HPC on Volcano: How Containers Support HPC Applications in the Meteorological Industry](https://volcano.sh/en/blog/hpc-en/)
+- [iQIYI:Volcano-based Cloud Native Migration Practices](https://volcano.sh/en/blog/aiqiyi-en/)
+- [PaddlePaddle Distributed Training on Volcano](https://volcano.sh/en/blog/paddlepaddle-en/)
 
 ## Quick Start Guide
 
@@ -85,7 +104,7 @@ Note:
 Install Volcano on an existing Kubernetes cluster. This way is both available for x86_64 and arm64 architecture.
 
 ```
-kubectl apply -f https://raw.githubusercontent.com/volcano-sh/volcano/network-topology/installer/volcano-development.yaml
+kubectl apply -f https://raw.githubusercontent.com/volcano-sh/volcano/master/installer/volcano-development.yaml
 ```
 
 Enjoy! Volcano will create the following resources in `volcano-system` namespace.
@@ -94,7 +113,6 @@ Enjoy! Volcano will create the following resources in `volcano-system` namespace
 ```
 NAME                                       READY   STATUS      RESTARTS   AGE
 pod/volcano-admission-5bd5756f79-dnr4l     1/1     Running     0          96s
-pod/volcano-admission-init-4hjpx           0/1     Completed   0          96s
 pod/volcano-controllers-687948d9c8-nw4b4   1/1     Running     0          96s
 pod/volcano-scheduler-94998fc64-4z8kh      1/1     Running     0          96s
 
@@ -118,7 +136,7 @@ job.batch/volcano-admission-init   1/1           48s        96s
 
 ### Install via helm
 
-To install official release, please visit to [helm-charts](https://github.com/volcano-sh/helm-charts) for details.
+To install official release, please visit [helm-charts](https://github.com/volcano-sh/helm-charts) for details.
 
 ```bash
 helm repo add volcano-sh https://volcano-sh.github.io/helm-charts
@@ -144,13 +162,17 @@ If you don't have a kubernetes cluster, try one-click install from code base:
 
 This way is only available for x86_64 temporarily.
 
+### Install volcano agent
+
+Please follow the guide [Volcano Agent](https://volcano.sh/en/docs/colocation) to install volcano agent.
+
 ### Install monitoring system
 
 If you want to get prometheus and grafana volcano dashboard after volcano installed, try following commands:
 
 ```bash
-make TAG=v1.11.0-network-topology-preview.2 generate-yaml
-kubectl create -f _output/release/volcano-monitoring-v1.11.0-network-topology-preview.2.yaml
+make TAG=latest generate-yaml
+kubectl create -f _output/release/volcano-monitoring-latest.yaml
 ```
 
 ### Install dashboard
@@ -159,14 +181,16 @@ Please follow the guide [Volcano Dashboard](https://github.com/volcano-sh/dashbo
 
 ## Kubernetes compatibility
 
-|                       | Kubernetes 1.17 | Kubernetes 1.18 | Kubernetes 1.19 | Kubernetes 1.20 | Kubernetes 1.21 | Kubernetes 1.22 | Kubernetes 1.23 | Kubernetes 1.24 | Kubernetes 1.25 | Kubernetes 1.26 | Kubernetes 1.27 | Kubernetes 1.28 | Kubernetes 1.29 |Kubernetes 1.30 |Kubernetes 1.31 |
-|-----------------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|---------------|---------------|
-| Volcano v1.6          | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | -               | -               | -               | -               | -               | -               |-              |-              |
-| Volcano v1.7          | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | -               |_              |_              |
-| Volcano v1.8          | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | -               |-              |_              |
-| Volcano v1.9          | -               | -               | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               |-              |_              |
-| Volcano v1.10         | -               | -               | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               |✓              |_              |
-| Volcano HEAD (master) | -               | -               | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               |✓              |✓              |
+|                       | Kubernetes 1.17 | Kubernetes 1.18 | Kubernetes 1.19 | Kubernetes 1.20 | Kubernetes 1.21 | Kubernetes 1.22 | Kubernetes 1.23 | Kubernetes 1.24 | Kubernetes 1.25 | Kubernetes 1.26 | Kubernetes 1.27 | Kubernetes 1.28 | Kubernetes 1.29 |Kubernetes 1.30 |Kubernetes 1.31 |Kubernetes 1.32 |
+|-----------------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|-----------------|---------------|--------------|---------------|
+| Volcano v1.6          | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | -               | -               | -               | -               | -               | -               |-              |-             |-              |
+| Volcano v1.7          | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | -               |_              |_             |-              |
+| Volcano v1.8          | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | -               |-              |_             |-              |
+| Volcano v1.9          | -               | -               | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               |-              |_             |-              |
+| Volcano v1.10         | -               | -               | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               |✓              |_             |-              |
+| Volcano v1.11         | -               | -               | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               |✓              |✓             |-              |
+| Volcano v1.12         | -               | -               | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               |✓              |✓             |✓              |
+| Volcano HEAD (master) | -               | -               | -               | -               | -               | -               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               | ✓               |✓              |✓             |✓              |
 
 Key:
 * `✓` Volcano and the Kubernetes version are exactly compatible.
@@ -174,6 +198,19 @@ Key:
 * `-` The Kubernetes version has features or API objects that Volcano can't use.
 
 
+## Citing Volcano
+
+If Volcano helps your research, we appreciate your citations. Here is the BibTeX entry:
+
+```bibtex
+@misc{volcano2025,
+  title={Volcano: A Cloud Native Batch System},
+  author={Klaus Ma and Kevin Wang and others},
+  year={2025},
+  howpublished={\url{https://github.com/volcano-sh/volcano}},
+}
+```
+
 ## Meeting
 
 Community weekly meeting for Asia: 15:00 - 16:00 (UTC+8) Friday. ([Convert to your timezone.](https://www.thetimezoneconverter.com/?t=10%3A00&tz=GMT%2B8&))
@@ -196,4 +233,4 @@ If you have any question, feel free to reach out to us in the following ways:
 
 [Mailing List](https://groups.google.com/forum/#!forum/volcano-sh)
 
-Wechat: Add WeChat account `k8s2222` (华为云小助手2号) to let her pull you into the group.
+WeChat: Please add WeChat account `k8s2222` and request an invitation to the group chat.

benchmark/sh/uninstall-volcano.sh

@@ -14,4 +14,5 @@
 # limitations under the License.
 set -e
 
-helm uninstall volcano --namespace volcano-system
+helm uninstall volcano --namespace volcano-system
+kubectl delete namespace volcano-system

cmd/agent/app/app.go

@@ -32,6 +32,7 @@ import (
 	"k8s.io/controller-manager/pkg/clientbuilder"
 	"k8s.io/klog/v2"
 
+	"volcano.sh/apis/pkg/apis/helpers"
 	"volcano.sh/volcano/cmd/agent/app/options"
 	"volcano.sh/volcano/pkg/agent/healthcheck"
 	"volcano.sh/volcano/pkg/agent/utils"
@@ -81,8 +82,11 @@ func RunServer(checker healthcheck.HealthChecker, address string, port int) {
 		mux.HandleFunc("/healthz", checker.HealthCheck)
 		mux.Handle("/metrics", promhttp.Handler())
 		s := &http.Server{
-			Addr:    net.JoinHostPort(address, strconv.Itoa(port)),
-			Handler: mux,
+			Addr:              net.JoinHostPort(address, strconv.Itoa(port)),
+			Handler:           mux,
+			ReadHeaderTimeout: helpers.DefaultReadHeaderTimeout,
+			ReadTimeout:       helpers.DefaultReadTimeout,
+			WriteTimeout:      helpers.DefaultWriteTimeout,
 		}
 		if err := s.ListenAndServe(); err != nil {
 			klog.Fatalf("failed to start health check server: %v", err)

cmd/controller-manager/app/options/options.go

@@ -204,7 +204,7 @@ func (s *ServerOption) ParseCAFiles(decryptFunc DecryptFunc) error {
 		return err
 	}
 
-	// users can add one function to decrypt tha data by their own way if CA data is encrypted
+	// users can add one function to decrypt the data by their own way if CA data is encrypted
 	if decryptFunc != nil {
 		return decryptFunc(s)
 	}

cmd/controller-manager/app/options/options_test.go

@@ -148,6 +148,13 @@ func TestCheckControllers(t *testing.T) {
 			},
 			expectErr: fmt.Errorf("controllers option %s cannot have both '-' and '+' prefixes", "-job-controller"),
 		},
+		{
+			name: "fail case: use duplicate job-controller",
+			serverOption: &ServerOption{
+				Controllers: []string{"+job-controller", "job-controller"},
+			},
+			expectErr: fmt.Errorf("controllers option %s cannot have both '-' and '+' prefixes", "job-controller"),
+		},
 		{
 			name: "fail case: use * but combined with other input",
 			serverOption: &ServerOption{

cmd/controller-manager/app/server.go

@@ -58,8 +58,17 @@ func Run(opt *options.ServerOption) error {
 
 	if opt.EnableMetrics {
 		go func() {
-			http.Handle("/metrics", commonutil.PromHandler())
-			klog.Fatalf("Prometheus Http Server failed %s", http.ListenAndServe(opt.ListenAddress, nil))
+			mux := http.NewServeMux()
+			mux.Handle("/metrics", commonutil.PromHandler())
+
+			server := &http.Server{
+				Addr:              opt.ListenAddress,
+				Handler:           mux,
+				ReadHeaderTimeout: helpers.DefaultReadHeaderTimeout,
+				ReadTimeout:       helpers.DefaultReadTimeout,
+				WriteTimeout:      helpers.DefaultWriteTimeout,
+			}
+			klog.Fatalf("Prometheus Http Server failed: %s", server.ListenAndServe())
 		}()
 	}
 

cmd/controller-manager/main.go

@@ -34,6 +34,7 @@ import (
 	"volcano.sh/volcano/cmd/controller-manager/app/options"
 	"volcano.sh/volcano/pkg/controllers/framework"
 	_ "volcano.sh/volcano/pkg/controllers/garbagecollector"
+	_ "volcano.sh/volcano/pkg/controllers/hypernode"
 	_ "volcano.sh/volcano/pkg/controllers/job"
 	_ "volcano.sh/volcano/pkg/controllers/jobflow"
 	_ "volcano.sh/volcano/pkg/controllers/jobtemplate"

cmd/network-qos/tools/options/options.go

@@ -39,5 +39,5 @@ func (o *Options) AddFlags(c *cobra.Command) {
 		"bandwidth usage of online jobs exceeds the defined threshold(online-bandwidth-watermark)")
 	c.Flags().StringVar(&o.OfflineHighBandwidth, utils.OfflineHighBandwidthKey, o.OfflineHighBandwidth, "offline-high-bandwidth is the maximum amount of network bandwidth that can be used by offline jobs when the"+
 		"bandwidth usage of online jobs not reach to the defined threshold(online-bandwidth-watermark)")
-	c.Flags().BoolVar(&o.EnableNetworkQoS, utils.EnableNetworkQoS, o.EnableNetworkQoS, "enbale networkqos")
+	c.Flags().BoolVar(&o.EnableNetworkQoS, utils.EnableNetworkQoS, o.EnableNetworkQoS, "enable networkqos")
 }

cmd/scheduler/app/options/options.go

@@ -32,6 +32,7 @@ import (
 const (
 	defaultSchedulerName   = "volcano"
 	defaultSchedulerPeriod = time.Second
+	defaultResyncPeriod    = 0
 	defaultQueue           = "default"
 	defaultListenAddress   = ":8080"
 	defaultHealthzAddress  = ":11251"
@@ -60,6 +61,7 @@ type ServerOption struct {
 	SchedulerNames    []string
 	SchedulerConf     string
 	SchedulePeriod    time.Duration
+	ResyncPeriod      time.Duration
 	// leaderElection defines the configuration of leader election.
 	LeaderElection config.LeaderElectionConfiguration
 	// Deprecated: use ResourceNamespace instead.
@@ -67,6 +69,7 @@ type ServerOption struct {
 	DefaultQueue        string
 	PrintVersion        bool
 	EnableMetrics       bool
+	EnablePprof         bool
 	ListenAddress       string
 	EnablePriorityClass bool
 	EnableCSIStorage    bool
@@ -112,12 +115,13 @@ func (s *ServerOption) AddFlags(fs *pflag.FlagSet) {
 		"File containing the default x509 Certificate for HTTPS. (CA cert, if any, concatenated "+
 		"after server cert).")
 	fs.StringVar(&s.KeyFile, "tls-private-key-file", s.KeyFile, "File containing the default x509 private key matching --tls-cert-file.")
-	fs.StringVar(&s.LockObjectNamespace, "lock-object-namespace", defaultLockObjectNamespace, "Define the namespace of the lock object; it is volcano-system by default.")
+	fs.StringVar(&s.LockObjectNamespace, "lock-object-namespace", "", "Define the namespace of the lock object; it is volcano-system by default.")
 	fs.MarkDeprecated("lock-object-namespace", "This flag is deprecated and will be removed in a future release. Please use --leader-elect-resource-namespace instead.")
 	// volcano scheduler will ignore pods with scheduler names other than specified with the option
 	fs.StringArrayVar(&s.SchedulerNames, "scheduler-name", []string{defaultSchedulerName}, "vc-scheduler will handle pods whose .spec.SchedulerName is same as scheduler-name")
 	fs.StringVar(&s.SchedulerConf, "scheduler-conf", "", "The absolute path of scheduler configuration file")
 	fs.DurationVar(&s.SchedulePeriod, "schedule-period", defaultSchedulerPeriod, "The period between each scheduling cycle")
+	fs.DurationVar(&s.ResyncPeriod, "resync-period", defaultResyncPeriod, "The default resync period for k8s native informer factory")
 	fs.StringVar(&s.DefaultQueue, "default-queue", defaultQueue, "The default queue name of the job")
 	fs.BoolVar(&s.PrintVersion, "version", false, "Show version and quit")
 	fs.StringVar(&s.ListenAddress, "listen-address", defaultListenAddress, "The address to listen on for HTTP requests.")
@@ -133,14 +137,15 @@ func (s *ServerOption) AddFlags(fs *pflag.FlagSet) {
 	// Minimum percentage of nodes to find and score
 	fs.Int32Var(&s.MinPercentageOfNodesToFind, "minimum-percentage-nodes-to-find", defaultMinPercentageOfNodesToFind, "The minimum percentage of nodes to find and score")
 
-	// The percentage of nodes that would be scored in each scheduling cycle; if <= 0, an adpative percentage will be calcuated
-	fs.Int32Var(&s.PercentageOfNodesToFind, "percentage-nodes-to-find", defaultPercentageOfNodesToFind, "The percentage of nodes to find and score, if <=0 will be calcuated based on the cluster size")
+	// The percentage of nodes that would be scored in each scheduling cycle; if <= 0, an adaptive percentage will be calculated
+	fs.Int32Var(&s.PercentageOfNodesToFind, "percentage-nodes-to-find", defaultPercentageOfNodesToFind, "The percentage of nodes to find and score, if <=0 will be calculated based on the cluster size")
 
 	fs.StringVar(&s.PluginsDir, "plugins-dir", defaultPluginsDir, "vc-scheduler will load custom plugins which are in this directory")
 	fs.BoolVar(&s.EnableCSIStorage, "csi-storage", false,
 		"Enable tracking of available storage capacity that CSI drivers provide; it is false by default")
 	fs.BoolVar(&s.EnableHealthz, "enable-healthz", false, "Enable the health check; it is false by default")
 	fs.BoolVar(&s.EnableMetrics, "enable-metrics", false, "Enable the metrics function; it is false by default")
+	fs.BoolVar(&s.EnablePprof, "enable-pprof", false, "Enable the pprof endpoint; it is false by default")
 	fs.StringSliceVar(&s.NodeSelector, "node-selector", nil, "volcano only work with the labeled node, like: --node-selector=volcano.sh/role:train --node-selector=volcano.sh/role:serving")
 	fs.BoolVar(&s.EnableCacheDumper, "cache-dumper", true, "Enable the cache dumper, it's true by default")
 	fs.StringVar(&s.CacheDumpFileDir, "cache-dump-dir", "/tmp", "The target dir where the json file put at when dump cache info to json file")

cmd/scheduler/app/options/options_test.go

@@ -45,6 +45,7 @@ func TestAddFlags(t *testing.T) {
 
 	args := []string{
 		"--schedule-period=5m",
+		"--resync-period=0",
 		"--priority-class=false",
 		"--cache-dumper=false",
 		"--leader-elect-lease-duration=60s",
@@ -58,6 +59,7 @@ func TestAddFlags(t *testing.T) {
 	expected := &ServerOption{
 		SchedulerNames: []string{defaultSchedulerName},
 		SchedulePeriod: 5 * time.Minute,
+		ResyncPeriod:   0,
 		LeaderElection: config.LeaderElectionConfiguration{
 			LeaderElect:       true,
 			LeaseDuration:     metav1.Duration{Duration: 60 * time.Second},
@@ -66,9 +68,8 @@ func TestAddFlags(t *testing.T) {
 			ResourceLock:      resourcelock.LeasesResourceLock,
 			ResourceNamespace: defaultLockObjectNamespace,
 		},
-		LockObjectNamespace: defaultLockObjectNamespace,
-		DefaultQueue:        defaultQueue,
-		ListenAddress:       defaultListenAddress,
+		DefaultQueue:  defaultQueue,
+		ListenAddress: defaultListenAddress,
 		KubeClientOptions: kube.ClientOptions{
 			Master:     "",
 			KubeConfig: "",

cmd/scheduler/app/server.go

@@ -20,10 +20,10 @@ import (
 	"context"
 	"fmt"
 	"net/http"
+	"net/http/pprof"
 	"os"
 
 	"volcano.sh/apis/pkg/apis/helpers"
-
 	"volcano.sh/volcano/cmd/scheduler/app/options"
 	"volcano.sh/volcano/pkg/kube"
 	"volcano.sh/volcano/pkg/scheduler"
@@ -69,11 +69,8 @@ func Run(opt *options.ServerOption) error {
 		panic(err)
 	}
 
-	if opt.EnableMetrics {
-		go func() {
-			http.Handle("/metrics", commonutil.PromHandler())
-			klog.Fatalf("Prometheus Http Server failed %s", http.ListenAndServe(opt.ListenAddress, nil))
-		}()
+	if opt.EnableMetrics || opt.EnablePprof {
+		go startMetricsServer(opt)
 	}
 
 	if opt.EnableHealthz {
@@ -142,3 +139,31 @@ func Run(opt *options.ServerOption) error {
 	})
 	return fmt.Errorf("lost lease")
 }
+
+func startMetricsServer(opt *options.ServerOption) {
+	mux := http.NewServeMux()
+
+	if opt.EnableMetrics {
+		mux.Handle("/metrics", commonutil.PromHandler())
+	}
+
+	if opt.EnablePprof {
+		mux.HandleFunc("/debug/pprof/", pprof.Index)
+		mux.HandleFunc("/debug/pprof/cmdline", pprof.Cmdline)
+		mux.HandleFunc("/debug/pprof/profile", pprof.Profile)
+		mux.HandleFunc("/debug/pprof/symbol", pprof.Symbol)
+		mux.HandleFunc("/debug/pprof/trace", pprof.Trace)
+	}
+
+	server := &http.Server{
+		Addr:              opt.ListenAddress,
+		Handler:           mux,
+		ReadHeaderTimeout: helpers.DefaultReadHeaderTimeout,
+		ReadTimeout:       helpers.DefaultReadTimeout,
+		WriteTimeout:      helpers.DefaultWriteTimeout,
+	}
+
+	if err := server.ListenAndServe(); err != nil {
+		klog.Errorf("start metrics/pprof http server failed: %v", err)
+	}
+}

cmd/scheduler/main.go

@@ -29,9 +29,6 @@ import (
 	componentbaseoptions "k8s.io/component-base/config/options"
 	"k8s.io/klog/v2"
 
-	// init pprof server
-	_ "net/http/pprof"
-
 	"volcano.sh/volcano/cmd/scheduler/app"
 	"volcano.sh/volcano/cmd/scheduler/app/options"
 	commonutil "volcano.sh/volcano/pkg/util"

cmd/webhook-manager/app/options/options.go

@@ -19,6 +19,7 @@ package options
 import (
 	"fmt"
 	"os"
+	"time"
 
 	"github.com/spf13/pflag"
 
@@ -26,31 +27,33 @@ import (
 )
 
 const (
-	defaultSchedulerName    = "volcano"
-	defaultQPS              = 50.0
-	defaultBurst            = 100
-	defaultEnabledAdmission = "/jobs/mutate,/jobs/validate,/podgroups/mutate,/pods/validate,/pods/mutate,/queues/mutate,/queues/validate"
-	defaultHealthzAddress   = ":11251"
+	defaultSchedulerName        = "volcano"
+	defaultQPS                  = 50.0
+	defaultBurst                = 100
+	defaultEnabledAdmission     = "/jobs/mutate,/jobs/validate,/podgroups/mutate,/pods/validate,/pods/mutate,/queues/mutate,/queues/validate"
+	defaultHealthzAddress       = ":11251"
+	defaultGracefulShutdownTime = time.Second * 30
 )
 
 // Config admission-controller server config.
 type Config struct {
-	KubeClientOptions kube.ClientOptions
-	CertFile          string
-	KeyFile           string
-	CaCertFile        string
-	CertData          []byte
-	KeyData           []byte
-	CaCertData        []byte
-	ListenAddress     string
-	Port              int
-	PrintVersion      bool
-	WebhookName       string
-	WebhookNamespace  string
-	SchedulerNames    []string
-	WebhookURL        string
-	ConfigPath        string
-	EnabledAdmission  string
+	KubeClientOptions    kube.ClientOptions
+	CertFile             string
+	KeyFile              string
+	CaCertFile           string
+	CertData             []byte
+	KeyData              []byte
+	CaCertData           []byte
+	ListenAddress        string
+	Port                 int
+	PrintVersion         bool
+	WebhookName          string
+	WebhookNamespace     string
+	SchedulerNames       []string
+	WebhookURL           string
+	ConfigPath           string
+	EnabledAdmission     string
+	GracefulShutdownTime time.Duration
 
 	EnableHealthz bool
 	// HealthzBindAddress is the IP address and port for the health check server to serve on
@@ -88,6 +91,7 @@ func (c *Config) AddFlags(fs *pflag.FlagSet) {
 	fs.StringVar(&c.ConfigPath, "admission-conf", "", "The configmap file of this webhook")
 	fs.BoolVar(&c.EnableHealthz, "enable-healthz", false, "Enable the health check; it is false by default")
 	fs.StringVar(&c.HealthzBindAddress, "healthz-address", defaultHealthzAddress, "The address to listen on for the health check server.")
+	fs.DurationVar(&c.GracefulShutdownTime, "graceful-shutdown-time", defaultGracefulShutdownTime, "The duration to wait during graceful shutdown before forcing termination.")
 }
 
 // CheckPortOrDie check valid port range.
@@ -125,7 +129,7 @@ func (c *Config) ParseCAFiles(decryptFunc DecryptFunc) error {
 		return err
 	}
 
-	// users can add one function to decrypt tha data by their own way if CA data is encrypted
+	// users can add one function to decrypt the data by their own way if CA data is encrypted
 	if decryptFunc != nil {
 		return decryptFunc(c)
 	}

cmd/webhook-manager/app/options/options_test.go

@@ -0,0 +1,66 @@
+/*
+Copyright 2025 The Volcano Authors.
+
+Licensed under the Apache License, Version 2.0 (the "License");
+you may not use this file except in compliance with the License.
+You may obtain a copy of the License at
+
+    http://www.apache.org/licenses/LICENSE-2.0
+
+Unless required by applicable law or agreed to in writing, software
+distributed under the License is distributed on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+See the License for the specific language governing permissions and
+limitations under the License.
+*/
+
+package options
+
+import (
+	"testing"
+
+	"github.com/spf13/pflag"
+	"k8s.io/apimachinery/pkg/api/equality"
+	utilfeature "k8s.io/apiserver/pkg/util/feature"
+
+	"volcano.sh/volcano/pkg/kube"
+)
+
+func TestAddFlags(t *testing.T) {
+	fs := pflag.NewFlagSet("addflagstest", pflag.ExitOnError)
+	s := NewConfig()
+	s.AddFlags(fs)
+	utilfeature.DefaultMutableFeatureGate.AddFlag(fs)
+
+	args := []string{
+		"--master=127.0.0.1",
+		"--kube-api-burst=200",
+	}
+	fs.Parse(args)
+
+	// This is a snapshot of expected options parsed by args.
+	expected := &Config{
+		KubeClientOptions: kube.ClientOptions{
+			Master:     "127.0.0.1",
+			KubeConfig: "",
+			QPS:        defaultQPS,
+			Burst:      200,
+		},
+		ListenAddress:        "",
+		Port:                 8443,
+		PrintVersion:         false,
+		WebhookName:          "",
+		WebhookNamespace:     "",
+		SchedulerNames:       []string{defaultSchedulerName},
+		WebhookURL:           "",
+		ConfigPath:           "",
+		EnabledAdmission:     defaultEnabledAdmission,
+		GracefulShutdownTime: defaultGracefulShutdownTime,
+		EnableHealthz:        false,
+		HealthzBindAddress:   defaultHealthzAddress,
+	}
+
+	if !equality.Semantic.DeepEqual(expected, s) {
+		t.Errorf("Got different run options than expected.\nGot: %+v\nExpected: %+v\n", s, expected)
+	}
+}

cmd/webhook-manager/app/server.go

@@ -17,12 +17,11 @@ limitations under the License.
 package app
 
 import (
+	"context"
+	"errors"
 	"fmt"
 	"net/http"
-	"os"
-	"os/signal"
 	"strconv"
-	"syscall"
 
 	v1 "k8s.io/api/core/v1"
 	corev1 "k8s.io/client-go/kubernetes/typed/core/v1"
@@ -34,6 +33,7 @@ import (
 	informers "volcano.sh/apis/pkg/client/informers/externalversions"
 	"volcano.sh/volcano/cmd/webhook-manager/app/options"
 	"volcano.sh/volcano/pkg/kube"
+	"volcano.sh/volcano/pkg/signals"
 	commonutil "volcano.sh/volcano/pkg/util"
 	wkconfig "volcano.sh/volcano/pkg/webhooks/config"
 	"volcano.sh/volcano/pkg/webhooks/router"
@@ -97,8 +97,7 @@ func Run(config *options.Config) error {
 	klog.V(3).Infof("Successfully added caCert for all webhooks")
 
 	webhookServeError := make(chan struct{})
-	stopChannel := make(chan os.Signal, 1)
-	signal.Notify(stopChannel, syscall.SIGTERM, syscall.SIGINT)
+	ctx := signals.SetupSignalContext()
 
 	factory.Start(webhookServeError)
 	for informerType, ok := range factory.WaitForCacheSync(webhookServeError) {
@@ -108,26 +107,31 @@ func Run(config *options.Config) error {
 	}
 
 	server := &http.Server{
-		Addr:      config.ListenAddress + ":" + strconv.Itoa(config.Port),
-		TLSConfig: configTLS(config, restConfig),
+		Addr:              config.ListenAddress + ":" + strconv.Itoa(config.Port),
+		TLSConfig:         configTLS(config, restConfig),
+		ReadHeaderTimeout: helpers.DefaultReadHeaderTimeout,
+		ReadTimeout:       helpers.DefaultReadTimeout,
+		WriteTimeout:      helpers.DefaultWriteTimeout,
 	}
 	go func() {
 		err = server.ListenAndServeTLS("", "")
-		if err != nil && err != http.ErrServerClosed {
+		if err != nil && !errors.Is(err, http.ErrServerClosed) {
 			klog.Fatalf("ListenAndServeTLS for admission webhook failed: %v", err)
 			close(webhookServeError)
 		}
 
-		klog.Info("Volcano Webhook manager started.")
+		klog.Info("Volcano Webhook manager stopped.")
 	}()
 
 	if config.ConfigPath != "" {
-		go wkconfig.WatchAdmissionConf(config.ConfigPath, stopChannel)
+		go wkconfig.WatchAdmissionConf(config.ConfigPath, ctx.Done())
 	}
 
 	select {
-	case <-stopChannel:
-		if err := server.Close(); err != nil {
+	case <-ctx.Done():
+		timeoutCtx, cancel := context.WithTimeout(context.Background(), config.GracefulShutdownTime)
+		defer cancel()
+		if err := server.Shutdown(timeoutCtx); err != nil {
 			return fmt.Errorf("close admission server failed: %v", err)
 		}
 		return nil

cmd/webhook-manager/main.go

@@ -32,9 +32,11 @@ import (
 	"volcano.sh/volcano/cmd/webhook-manager/app/options"
 	"volcano.sh/volcano/pkg/version"
 	_ "volcano.sh/volcano/pkg/webhooks/admission/hypernodes/validate"
+	_ "volcano.sh/volcano/pkg/webhooks/admission/jobflows/validate"
 	_ "volcano.sh/volcano/pkg/webhooks/admission/jobs/mutate"
 	_ "volcano.sh/volcano/pkg/webhooks/admission/jobs/validate"
 	_ "volcano.sh/volcano/pkg/webhooks/admission/podgroups/mutate"
+	_ "volcano.sh/volcano/pkg/webhooks/admission/podgroups/validate"
 	_ "volcano.sh/volcano/pkg/webhooks/admission/pods/mutate"
 	_ "volcano.sh/volcano/pkg/webhooks/admission/pods/validate"
 	_ "volcano.sh/volcano/pkg/webhooks/admission/queues/mutate"

config/crd/jobflow/bases/flow.volcano.sh_jobflows.yaml

@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: jobflows.flow.volcano.sh
 spec:
   group: flow.volcano.sh

config/crd/jobflow/bases/flow.volcano.sh_jobtemplates.yaml

@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: jobtemplates.flow.volcano.sh
 spec:
   group: flow.volcano.sh
@@ -2811,6 +2811,39 @@ spec:
                               x-kubernetes-list-map-keys:
                               - name
                               x-kubernetes-list-type: map
+                            resources:
+                              properties:
+                                claims:
+                                  items:
+                                    properties:
+                                      name:
+                                        type: string
+                                      request:
+                                        type: string
+                                    required:
+                                    - name
+                                    type: object
+                                  type: array
+                                  x-kubernetes-list-map-keys:
+                                  - name
+                                  x-kubernetes-list-type: map
+                                limits:
+                                  additionalProperties:
+                                    anyOf:
+                                    - type: integer
+                                    - type: string
+                                    pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
+                                    x-kubernetes-int-or-string: true
+                                  type: object
+                                requests:
+                                  additionalProperties:
+                                    anyOf:
+                                    - type: integer
+                                    - type: string
+                                    pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
+                                    x-kubernetes-int-or-string: true
+                                  type: object
+                              type: object
                             restartPolicy:
                               type: string
                             runtimeClassName:
@@ -2853,6 +2886,8 @@ spec:
                                 runAsUser:
                                   format: int64
                                   type: integer
+                                seLinuxChangePolicy:
+                                  type: string
                                 seLinuxOptions:
                                   properties:
                                     level:

config/crd/volcano/bases/batch.volcano.sh_jobs.yaml

@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: jobs.batch.volcano.sh
 spec:
   group: batch.volcano.sh
@@ -2829,6 +2829,39 @@ spec:
                               x-kubernetes-list-map-keys:
                               - name
                               x-kubernetes-list-type: map
+                            resources:
+                              properties:
+                                claims:
+                                  items:
+                                    properties:
+                                      name:
+                                        type: string
+                                      request:
+                                        type: string
+                                    required:
+                                    - name
+                                    type: object
+                                  type: array
+                                  x-kubernetes-list-map-keys:
+                                  - name
+                                  x-kubernetes-list-type: map
+                                limits:
+                                  additionalProperties:
+                                    anyOf:
+                                    - type: integer
+                                    - type: string
+                                    pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
+                                    x-kubernetes-int-or-string: true
+                                  type: object
+                                requests:
+                                  additionalProperties:
+                                    anyOf:
+                                    - type: integer
+                                    - type: string
+                                    pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
+                                    x-kubernetes-int-or-string: true
+                                  type: object
+                              type: object
                             restartPolicy:
                               type: string
                             runtimeClassName:
@@ -2871,6 +2904,8 @@ spec:
                                 runAsUser:
                                   format: int64
                                   type: integer
+                                seLinuxChangePolicy:
+                                  type: string
                                 seLinuxOptions:
                                   properties:
                                     level:

config/crd/volcano/bases/bus.volcano.sh_commands.yaml

@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: commands.bus.volcano.sh
 spec:
   group: bus.volcano.sh

config/crd/volcano/bases/nodeinfo.volcano.sh_numatopologies.yaml

@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: numatopologies.nodeinfo.volcano.sh
 spec:
   group: nodeinfo.volcano.sh

config/crd/volcano/bases/scheduling.volcano.sh_podgroups.yaml

@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: podgroups.scheduling.volcano.sh
 spec:
   group: scheduling.volcano.sh
@@ -117,6 +117,7 @@ spec:
                   default.
                 type: string
               queue:
+                default: default
                 description: |-
                   Queue defines the queue to allocate resource for PodGroup; if queue does not exist,
                   the PodGroup will not be scheduled. Defaults to `default` Queue with the lowest weight.

config/crd/volcano/bases/scheduling.volcano.sh_queues.yaml

@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: queues.scheduling.volcano.sh
 spec:
   group: scheduling.volcano.sh
@@ -17,7 +17,11 @@ spec:
     singular: queue
   scope: Cluster
   versions:
-  - name: v1beta1
+  - additionalPrinterColumns:
+    - jsonPath: .spec.parent
+      name: PARENT
+      type: string
+    name: v1beta1
     schema:
       openAPIV3Schema:
         description: Queue is a queue of PodGroup.
@@ -149,7 +153,10 @@ spec:
                 description: Type define the type of queue
                 type: string
               weight:
+                default: 1
                 format: int32
+                maximum: 65535
+                minimum: 1
                 type: integer
             type: object
           status:

config/crd/volcano/bases/topology.volcano.sh_hypernodes.yaml

@@ -3,7 +3,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: hypernodes.topology.volcano.sh
 spec:
   group: topology.volcano.sh

config/license-lint.yaml

@@ -66,6 +66,10 @@ allowlisted_modules:
 - github.com/google/cadvisor
 # Apache-2.0: k8s.io/kubernetes@v1.27.2/logo/LICENSE
 - k8s.io/kubernetes
+# Apache-2.0: github.com/spf13/cobra@v1.8.1/LICENSE
+- github.com/spf13/cobra
+# BSD: gopkg.in/inf.v0@v0.9.1/LICENSE
+- gopkg.in/inf.v0
 # BSD: github.com/gogo/protobuf@v1.3.2/LICENSE
 - github.com/gogo/protobuf
 # MIT: sigs.k8s.io/yaml@v1.3.0/LICENSE

docs/design/Network Topology Aware Scheduling.md

@@ -237,7 +237,7 @@ spec:
 #### network topology generation and update
 
 * **Network topology discovery/detection tool**: a tool to generate network topology CR by analyzing labels, system file or API of HW vendor. The community will offer a tool to generate CR by label.  
-![nework topology generation](images/network-topology-aware/nework-topology-generation.png)    
+![network topology generation](images/network-topology-aware/nework-topology-generation.png)    
 
 ### Job management
 
@@ -565,13 +565,19 @@ Allocate resources for queue-\> Job \-\> Task.
 Phase2:
 Allocate resources for queue-\> hyperJob \-\> Job \-\> Task.
 
-**plugin:** NetworkTopology
+**plugin:** network-topology-aware
 
 - AddJobGroupReadyFn: check whether hyperJob minAvailable is met.(phase 2)  
 
 - AddHyperNodeOrderFn: score for hyperNodes.(take effect in hard limit, closest tiers have higher score)
+1. If a Job is being scheduled for the very first time, candidate hypernodes that need to be scored will get a score of 0 and then return right away. The name of the HyperNode where the Job eventually gets scheduled successfully will be recorded in the Job's annotations under the key JobAllocatedHyperNode.
+2. If it is not the first scheduling of a job, calculate the LCAHyperNode (Lowest Common Ancestor HyperNode) between candidate hypernodes(In the Allocate process, the system will calculate whether the LCAHyperNode tier of the hyperNode meets the Hard limit. If it doesn't, the hyperNode will be filtered out.) that need to be scored and the `JobAllocatedHyperNode` of the job. The lower the tier of the calculated LCAHyperNode, the higher the score. If there is only one highest score, return the scoring result.
+3. If there is more than one HyperNode with the highest score in the scoring result of step 2, calculate the distribution of the tasks that have been successfully scheduled for the job among these HyperNodes. The greater the distribution quantity, the higher the score.
+4. The HyperNode that is successfully scheduled in the end in steps 2 and 3 will also be recorded as the `JobAllocatedHyperNode` attribute of the job.
 
-- AddNodeOrderFn: score for nodes.(take effect in soft limit,take effect in )
+- AddNodeOrderFn: score for nodes.(take effect in soft limit, closest tiers have higher score)
+1. To score all nodes, we need to first obtain the HyperNode to which the node belongs and the `JobAllocatedHyperNode` of the job to which the task belongs.
+2. The subsequent scoring logic is the same as that in the Hard mode. The score of the HyperNode to which it belongs is calculated as the score of the node. 
 
 ### Webhook
 

docs/design/capacity-scheduling.md

@@ -37,11 +37,11 @@ Administrator can create two queues with deserved capacity configured and the de
 
 ### Story 3
 
-Administrator can create two queues with guarantee and deserved resources configured and the deserved resource can be reclaim back. And different resource type can hold diffferent guarantee and deserved quantity. For example, we consume there are 2 orgs Org1 and Org2, and use Queue1 and Queue2 respectively, Queue1's guarantee resources are A100 GPU card number=10, V100 GPU card number=10, and deserved resources are A100 GPU card number=20, V00 GPU card number=50, for Queue2, its guarantee resources are A100 GPU card number=10,V100 GPU card number=10, and deserved resources are A100 GPU card number=80, V100 GPU card number=50. 
+Administrator can create two queues with guarantee and deserved resources configured and the deserved resource can be reclaim back. And different resource type can hold different guarantee and deserved quantity. For example, we consume there are 2 orgs Org1 and Org2, and use Queue1 and Queue2 respectively, Queue1's guarantee resources are A100 GPU card number=10, V100 GPU card number=10, and deserved resources are A100 GPU card number=20, V100 GPU card number=50, for Queue2, its guarantee resources are A100 GPU card number=10,V100 GPU card number=10, and deserved resources are A100 GPU card number=80, V100 GPU card number=50. 
 
 <div align="center"><img width="582" height="393" src="images/capacity-scheduling/queue-deserved.png" /></div>
 
-Queue1 can use cluster's total resoures when Queue2 is idle.
+Queue1 can use cluster's total resources when Queue2 is idle.
 
 <div align="center"><img width="612" height="303" src="images/capacity-scheduling/queue1-use-all.png" /></div>
 

docs/design/colocation/Overview.md

@@ -34,7 +34,7 @@ You can set different qos levels to identify workloads of different priorities,
 Follow the [installation guide](https://github.com/volcano-sh/volcano?tab=readme-ov-file#quick-start-guide) to install volcano first, and then install volcano agent via kubectl, this way is both available for x86_64 and arm64 architecture. 
 
 ```shell
-kubectl apply -f https://raw.githubusercontent.com/volcano-sh/volcano/network-topology/installer/volcano-agent-development.yaml
+kubectl apply -f https://raw.githubusercontent.com/volcano-sh/volcano/master/installer/volcano-agent-development.yaml
 ```
 
 Check volcano components including agent runs successfully.
@@ -49,7 +49,7 @@ volcano-controllers-7655bb499f-gpg9l   1/1     Running     0          3d
 volcano-scheduler-6bf4759c45-c666z     1/1     Running     0          3d
 ```
 
-Enable node level colocation by setting lable volcano.sh/oversubscription=true and volcano.sh/colocation=true.
+Enable node level colocation by setting label volcano.sh/oversubscription=true and volcano.sh/colocation=true.
 
 ```
 $ kubectl label node $node volcano.sh/oversubscription=true # replace $node with real node name in your kubernetes cluster.
@@ -150,11 +150,11 @@ CPU burst relies on capabilities provided by the linux kernel, this feature only
 
 ### Dynamic resource oversubscription tutorial
 
-This example will demonstrate the resource overoversubscription capability on node, and shows the suppression and eviction mechanism when node is suffering from pressure. The node flavor is 8 core cpu and 16GB memory.
+This example will demonstrate the resource oversubscription capability on node, and shows the suppression and eviction mechanism when node is suffering from pressure. The node flavor is 8 core cpu and 16GB memory.
 
-#### Check node oversubscription resoures
+#### Check node oversubscription resources
 
-Node oversubscription resources are calculated by node allocatable resources sub actual resource usage, oversubscription resources include cpu and memory and is represented by `kubernetes.io/batch-cpu` and `kubernetes.io/batch-memory` respectively, and reported as extended resources to node.Allocatable filed. Online workloads use noraml resources and offline workloads use oversubscription resources so we can improve pod deployment density and resource utilization. 
+Node oversubscription resources are calculated by node allocatable resources sub actual resource usage, oversubscription resources include cpu and memory and is represented by `kubernetes.io/batch-cpu` and `kubernetes.io/batch-memory` respectively, and reported as extended resources to node.Allocatable filed. Online workloads use normal resources and offline workloads use oversubscription resources so we can improve pod deployment density and resource utilization. 
 
 ```shell
 $ kubectl describe node $node # replace $node with real node name in your kubernetes cluster.

docs/design/deploy-multi-volcano-schedulers-without-using-selector.md

@@ -5,7 +5,7 @@
 Currently the single scheduler can not satisfy the high throughput requirement in some scenarios. Besides the performance optimization against the single scheduler, another choice is to deploy multiple volcano schedulers to improve the overall scheduling throughput.
 
 ## Introduction
-Previously we use label to divide the cluster nodes to multiple sections and each volcano scheduler is responsible for one section and then specify the schedulerName in the Pod Spec and submit it. It is inconvenient in some conditions especially for large clusters. This doc privides a another option for user to deploy multiple scheduler which needs less modification for workload and nodes.
+Previously we use label to divide the cluster nodes to multiple sections and each volcano scheduler is responsible for one section and then specify the schedulerName in the Pod Spec and submit it. It is inconvenient in some conditions especially for large clusters. This doc provides a another option for user to deploy multiple scheduler which needs less modification for workload and nodes.
 A statefulset is used to deploy the volcano scheduler. The Job and Node are assigned to scheduler automatically based on the hash algorithm. 
 
 ！[multi-scheduler-deployment](images/multi-volcano-schedulers-without-using-selector.png) 

docs/design/device-sharing.md

@@ -74,20 +74,29 @@ Details of methods mapping is shown in the table below:
 
 ## How to add a new device-share policy
 
-### 1. Define your device in /pkg/scheduler/api/shared_device_pool.go
+### 1. Create a new package in /pkg/scheduler/api/devices/"your device name"/"your policy name"
 
-Name your policy and put it in shared_device_pool.go as follows:
+For example, if you try to implement a NPU share policy, then you are recommended to create a package in /pkg/scheduler/api/device/ascend/npushare
+
+Define the device name in /pkg/scheduler/api/devices/"your device name"/"your policy name"/type.go:
 
 ```
 const (
-	GPUSharingDevice = "GpuShare"
-	Your_new_sharing_policy = "xxxxx"
+    DeviceName = "xxx"
 )
 ```
 
-### 2. Create a new package in /pkg/scheduler/api/devices/"your device name"/"your policy name"
+### 2. Register your device in /pkg/scheduler/api/shared_device_pool.go
 
-For example, if you try to implement a NPU share policy, then you are recommended to create a package in /pkg/scheduler/api/device/ascend/npushare
+Register your device name in shared_device_pool.go as follows:
+
+```
+var RegisteredDevices = []string{
+	gpushare.DeviceName,
+	vgpu.DeviceName,
+	"your new package name".DeviceName,  // add your device name here
+}
+```
 
 ### 3. Implement methods of interface shared_device_pool, and put them in your new package
 
@@ -112,15 +121,16 @@ This is the *only* place you hack into scheduler.api ,which you have to register
 
 // setNodeOthersResource initialize sharable devices
 func (ni *NodeInfo) setNodeOthersResource(node *v1.Node) {
-	ni.Others[GPUSharingDevice] = gpushare.NewGPUDevices(ni.Name, node)
-	//ni.Others["your device sharing policy name"] = your device sharing package initialization method
+    ni.Others[gpushare.DeviceName] = gpushare.NewGPUDevices(ni.Name, node)
+    ni.Others[vgpu.DeviceName] = vgpu.NewGPUDevices(ni.Name, node)
+    ni.Others["your new package name".DeviceName] = your device sharing package initialization method // add your device sharing package initialization method here
 }
 
 ```
 
 ### 5. Check if your policy is enabled in /pkg/scheduler/plugins/predicate/predicates.go
 
-This is the *only* plae you hack into predicates.go, when the scheduler checks if your policy is enabled in scheduler configuration.
+This is the *only* place you hack into predicates.go, when the scheduler checks if your policy is enabled in scheduler configuration.
 
 predicates.go:
 
@@ -129,11 +139,7 @@ predicates.go:
 // Checks whether predicate.GPUSharingEnable is provided or not, if given, modifies the value in predicateEnable struct.
 args.GetBool(&gpushare.GpuSharingEnable, GPUSharingPredicate)
 args.GetBool(&gpushare.GpuNumberEnable, GPUNumberPredicate)
-args.GetBool(&gpushare.NodeLockEnable, NodeLockEnable)
+args.GetBool(&vgpu.VGPUEnable, VGPUEnable)
 args.GetBool("your policy enable variable","your policy enable parameter")
 ...
 ```
-
-
-
-

docs/design/dynamic-mig.md

@@ -0,0 +1,173 @@
+# NVIDIA GPU MPS and MIG dynamic slice plugin
+
+## Special Thanks
+
+This feature will not be implemented without the help of @sailorvii.
+
+## Introduction
+
+The NVIDIA GPU build-in sharing method includes: time-slice, MPS and MIG. The context switch for time slice sharing would waste some time, so we chose the MPS and MIG. The GPU MIG profile is variable, the user could acquire the MIG device in the profile definition, but current implementation only defines the dedicated profile before the user requirement. That limits the usage of MIG. We want to develop an automatic slice plugin and create the slice when the user require it.
+For the scheduling method, node-level binpack and spread will be supported. Referring to the binpack plugin, we consider the CPU, Mem, GPU memory and other user-defined resource.
+Volcano already have a [vgpu feature](https://github.com/Project-HAMi/volcano-vgpu-device-plugin) for NVIDIA devices after v1.9, it is done by using [hami-core](https://github.com/Project-HAMi/HAMi-core), which is a cuda-hacking library. It can dynamically share GPUs and ensure both quality of service and resource isolation. But considering MIG is also widely used across the world. Supporting MIG mode along with 'hami-core' in volcano-vgpu can be helpful. A unified API for dynamic-MIG and hami-core for volcano-vgpu is needed.
+
+## Targets
+
+- CPU, Mem, and GPU combined scheduling
+- GPU dynamic slice: Hami-core and MIG
+- Support node-level binpack and spread by GPU memory, CPU and Mem
+- A unified vGPU Pool different virtualization technics
+- Tasks can choose to use MIG, use HAMi-core, or use both.
+
+### Config maps
+- volcano-device-configMap
+This configmap defines the plugin configurations including resourceName, and MIG geometries, and node-level configurations.
+
+```yaml
+apiVersion: v1
+data:
+  volcano-device-share.conf: |
+    nvidia:
+      resourceCountName: volcano.sh/vgpu-number
+      resourceMemoryName: volcano.sh/vgpu-memory
+      resourceCoreName: volcano.sh/vgpu-cores
+      knownMigGeometries:
+      - models: [ "A30" ]
+        allowedGeometries:
+          - group: group1 
+            geometries: 
+            - name: 1g.6gb
+              memory: 6144
+              count: 4
+          - group: group2
+            geometries:
+            - name: 2g.12gb
+              memory: 12288
+              count: 2
+          - group: group3
+            geometries:
+            - name: 4g.24gb
+              memory: 24576
+              count: 1
+      - models: [ "A100-SXM4-40GB", "A100-40GB-PCIe", "A100-PCIE-40GB", "A100-SXM4-40GB" ]
+        allowedGeometries:
+          - group: group1
+            geometries:
+            - name: 1g.5gb
+              memory: 5120
+              count: 7
+          - group: group2
+            geometries:
+            - name: 2g.10gb
+              memory: 10240
+              count: 3
+            - name: 1g.5gb
+              memory: 5120
+              count: 1
+          - group: group3
+            geometries:
+            - name: 3g.20gb
+              memory: 20480
+              count: 2
+          - group: group4
+            geometries:
+            - name: 7g.40gb
+              memory: 40960
+              count: 1
+      - models: [ "A100-SXM4-80GB", "A100-80GB-PCIe", "A100-PCIE-80GB"]
+        allowedGeometries:
+          - group: group1
+            geometries:
+            - name: 1g.10gb
+              memory: 10240
+              count: 7
+          - group: group2
+            geometries:
+            - name: 2g.20gb
+              memory: 20480
+              count: 3
+            - name: 1g.10gb
+              memory: 10240
+              count: 1
+          - group: group3
+            geometries:
+            - name: 3g.40gb
+              memory: 40960
+              count: 2
+          - group: group4
+            geometries:
+            - name: 7g.79gb
+              memory: 80896
+              count: 1
+```
+
+## Structure
+
+<img src="./images/volcano-dynamic-mig-structure.png" width = "400" /> 
+
+## Examples
+
+Dynamic mig is compatable with volcano-vgpu tasks, as the example below: 
+Just Setting `volcano.sh/vgpu-number` and `volcano.sh/vgpu-memory`.
+
+```yaml
+apiVersion: v1
+kind: Pod
+metadata:
+  name: gpu-pod1
+spec:
+  containers:
+    - name: ubuntu-container1
+      image: ubuntu:20.04
+      command: ["bash", "-c", "sleep 86400"]
+      resources:
+        limits:
+          volcano.sh/vgpu-number: 2 # requesting 2 vGPUs
+          volcano.sh/vgpu-memory: 8000 # Each vGPU contains 8000m device memory （Optional,Integer
+```
+
+A task can decide only to use `mig` or `hami-core` by setting `annotations.volcano.sh/vgpu-mode` to corresponding value, as the example below shows:
+
+```yaml
+apiVersion: v1
+kind: Pod
+metadata:
+  name: gpu-pod1
+  annotations:
+    volcano.sh/vgpu-mode: "mig"
+spec:
+  containers:
+    - name: ubuntu-container1
+      image: ubuntu:20.04
+      command: ["bash", "-c", "sleep 86400"]
+      resources:
+        limits:
+          volcano.sh/vgpu-number: 2 # requesting 2 vGPUs
+          volcano.sh/vgpu-memory: 8000 # Each vGPU contains 8000m device memory （Optional,Integer）
+```
+
+## Procedures
+
+The Procedure of a vGPU task which uses dynamic-mig is shown below:
+
+<img src="./images/volcano-dynamic-mig-procedure.png" width = "800" /> 
+
+Note that after submited a task, deviceshare plugin will iterate over templates defined in configMap `volcano-device-share`, and find the first available template to fit. You can always change the content of that configMap, and restart vc-scheduler to customize.
+
+If you submit the example above(a pod requests 2 * 8G GPUs) to a cluster, which has an empty A100-PCIE-40GB node, then it will follow the procedure below:
+
+<img src="./images/dynamic-mig-example.png" width = "400" />
+
+The walkthrough will be shown in bold line
+
+As the figure shows, after the procedure, it will adopt geometry 'group2' to that GPU with the definiation below:
+
+```yaml
+group2:
+  2g.10gb : 3
+  1g.5gb : 1
+```
+
+There are four mig instances in total, vc-scheduler will return 2 '2g.10gb' instances to the task, and add the remaining instances (1 '2g.10gb' + 1 '1g.5gb' ) to the available empty mig instances, for future usage.
+
+In the end, start the container with 2g.10gb instances * 2
+

docs/design/hyperNode-auto-discovery.md

@@ -0,0 +1,220 @@
+# HyperNode Auto Discovery Design Document
+
+## Introduction
+
+This design document describes the design and implementation of the HyperNode network topology discovery feature in Volcano. This feature automatically discovers the network topology structure within the cluster and creates and maintains HyperNode custom resources (CRs) based on the discovered topology information. Consequently, the Volcano Scheduler will leverage these HyperNode CRs for scheduling decisions, eliminating the need for users to manually maintain HyperNode information.
+
+## Design Goals
+
+*   **Automated Discovery**: Automatically discover network topology information from different data sources (such as UFM, RoCE, etc.).
+*   **Scalability**: Support multiple network topology discovery sources and easily extend new discovery methods.
+*   **Real-time**: Be able to reflect changes in network topology in a timely manner.
+*   **Fault Tolerance**: When a discovery source fails, it does not affect the normal operation of the system.
+*   **Security**: Securely manage authentication credentials using Kubernetes Secrets.
+
+## Overall Design
+
+### Component Architecture
+
+The entire network topology discovery function consists of the following core components:
+
+*   **Config Loader**: Responsible for loading network topology discovery configuration information from ConfigMap.
+*   **Discovery Manager**: Responsible for managing and coordinating various network topology discoverers.
+*   **Discoverer**: A specific network topology discoverer, responsible for obtaining network topology information from a specific data source and converting it into `HyperNode` resources.
+*   **HyperNode Controller**: Responsible for listening to changes in `HyperNode` resources and creating, updating, or deleting `HyperNode` resources based on the discovered topology information.
+
+### Process Flow
+
+```
+ConfigMap -> Config Loader -> Discovery Manager -> Discoverer -> HyperNode Controller -> HyperNode
+```
+
+1.  **Configuration Loading**: `Config Loader` loads network topology discovery configuration information from ConfigMap, including enabled discovery sources, discovery intervals, data source addresses, etc.
+2.  **Discovery Management**: `Discovery Manager` creates and starts the corresponding `Discoverer` based on the configuration information.
+3.  **Topology Discovery**: `Discoverer` obtains network topology information from the specified data source and converts the topology information into `HyperNode` resources.
+4.  **Resource Synchronization**: `HyperNode Controller` receives the `HyperNode` resources discovered by `Discoverer`, compares them with the existing `HyperNode` resources, and then creates, updates, or deletes `HyperNode` resources to keep the `HyperNode` resources in the cluster consistent with the actual network topology.
+
+## Detailed Design
+
+### Config Loader
+
+`Config Loader` is responsible for loading network topology discovery configuration information from ConfigMap.
+
+*   **Function**:
+    *   Read configuration information from the specified ConfigMap.
+    *   Parse configuration information and convert it into a `NetworkTopologyConfig` object.
+*   **Configuration Format**:
+
+```yaml
+# volcano-controller.conf file in ConfigMap
+networkTopologyDiscovery:
+  - source: ufm
+    enabled: true
+    interval: 10m
+    credentials:
+      secretRef:
+        name: ufm-credentials
+        namespace: volcano-system
+    config:
+      [...]
+  - source: roce
+    enabled: false
+    interval: 15m
+    config:
+      [...]
+  - source: label
+    enabled: false
+    config:
+      # Configuration of the label discovery source
+```
+
+*   **Code Example**:
+
+```go
+// NetworkTopologyConfig represents the configuration of the network topology
+type NetworkTopologyConfig struct {
+    // NetworkTopologyDiscovery specifies the network topology to discover,
+    // Each discovery source has its own specific configuration
+	NetworkTopologyDiscovery []DiscoveryConfig `json:"networkTopologyDiscovery" yaml:"networkTopologyDiscovery"`
+}
+
+// SecretRef refers to a secret containing sensitive information
+type SecretRef struct {
+    Name      string `json:"name" yaml:"name"`
+    Namespace string `json:"namespace" yaml:"namespace"`
+}
+
+// Credentials specifies how to retrieve credentials
+type Credentials struct {
+    SecretRef *SecretRef `json:"secretRef" yaml:"secretRef"`
+}
+
+// DiscoveryConfig contains configuration for a specific discovery source
+type DiscoveryConfig struct {
+    // Source specifies the discover source (e.g., "ufm", "roce", etc.)
+    Source string `json:"source" yaml:"source"`
+
+    // Enabled determines if discovery for this source is active
+    Enabled bool `json:"enabled" yaml:"enabled"`
+
+    // Interval is the period between topology discovery operations
+    // If not specified, DefaultDiscoveryInterval will be used
+    Interval time.Duration `json:"interval" yaml:"interval"`
+	
+    // Credentials specifies the username/password to access the discovery source
+    Credentials *Credentials `json:"credentials" yaml:"credentials"`
+
+    // Config contains specific configuration parameters for each discovery source
+    Config map[string]interface{} `json:"config" yaml:"config"`
+}
+```
+
+### Discovery Manager
+
+`Discovery Manager` is responsible for managing and coordinating various network topology discoverers.
+
+*   **Function**:
+    *   Create and start the corresponding `Discoverer` based on the configuration information.
+    *   Periodically obtain network topology information from `Discoverer`.
+    *   Send network topology information to `HyperNode Controller`.
+*   **Key Code**:
+
+```go
+// RegisterDiscoverer registers the discoverer constructor for the specified source
+func RegisterDiscoverer(source string, constructor DiscovererConstructor, kubeClient clientset.Interface) {
+    discovererRegistry[source] = constructor
+}
+```
+
+### Discoverer
+
+`Discoverer` is a specific network topology discoverer, responsible for obtaining network topology information from a specific data source and converting it into `HyperNode` resources.
+
+*   **Function**:
+    *   Retrieve authentication credentials from Kubernetes Secrets.
+    *   Obtain network topology information from the specified data source.
+    *   Convert network topology information into `HyperNode` resources.
+*   **Interface Definition**:
+
+```go
+// Discoverer is the interface for network topology discovery
+type Discoverer interface {
+    // Start begins the discovery process, sending discovered nodes through the provided channel
+    Start(outputCh chan<- []*topologyv1alpha1.HyperNode) error
+
+    // Stop halts the discovery process
+    Stop() error
+
+    // Name returns the discoverer identifier, this is used for labeling discovered hyperNodes for distinction.
+    Name() string
+}
+```
+
+*   **Implementation**:
+    *   **UFM Discoverer**: Obtain network topology information from UFM (Unified Fabric Manager).
+    *   **RoCE Discoverer**: Obtain network topology information from RoCE (RDMA over Converged Ethernet) devices.
+    *   **Label Discoverer**: Discover network topology information based on the Label on the Node.
+
+*   **Credential Management**:
+    *  Credentials are retrieved from Kubernetes Secrets specified in the configuration.
+    *  The Secret reference includes both name and namespace parameters.
+
+### HyperNode Controller
+
+`HyperNode Controller` is responsible for listening to changes in `HyperNode` resources and creating, updating, or deleting `HyperNode` resources based on the discovered topology information.
+
+*   **Function**:
+    *   Listen to change events of `HyperNode` resources.
+    *   Create, update, or delete `HyperNode` resources based on the network topology information provided by `Discoverer`.
+*   **Key Code**:
+
+```go
+func (hn *hyperNodeController) reconcileTopology(source string, discoveredNodes []*topologyv1alpha1.HyperNode) {
+ klog.InfoS("Starting topology reconciliation", "source", source, "discoveredNodeCount", len(discoveredNodes))
+
+ existingNodes, err := hn.hyperNodeLister.List(labels.SelectorFromSet(labels.Set{
+  api.NetworkTopologySourceLabelKey: source,
+ }))
+ if err != nil {
+  klog.ErrorS(err, "Failed to list existing HyperNode resources")
+  return
+ }
+
+ existingNodeMap := make(map[string]*topologyv1alpha1.HyperNode)
+ for _, node := range existingNodes {
+  existingNodeMap[node.Name] = node
+ }
+
+ discoveredNodeMap := make(map[string]*topologyv1alpha1.HyperNode)
+ for _, node := range discoveredNodes {
+  if node.Labels == nil {
+   node.Labels = make(map[string]string)
+  }
+  node.Labels[api.NetworkTopologySourceLabelKey] = source
+  discoveredNodeMap[node.Name] = node
+ }
+
+ for name, node := range discoveredNodeMap {
+  if _, exists := existingNodeMap[name]; !exists {
+   [...]
+  } else {
+   [...]
+  }
+
+  delete(existingNodeMap, name)
+ }
+
+ for name := range existingNodeMap {
+  klog.InfoS("Deleting HyperNode", "name", name, "source", source)
+  if err := utils.DeleteHyperNode(hn.vcClient, name); err != nil {
+   klog.ErrorS(err, "Failed to delete HyperNode", "name", name)
+  }
+ }
+
+ klog.InfoS("Topology reconciliation completed",
+  "source", source,
+  "discovered", len(discoveredNodes),
+  "created/updated", len(discoveredNodeMap),
+  "deleted", len(existingNodeMap))
+}
+```

docs/design/metrics.md

@@ -27,32 +27,41 @@ This metrics track execution of plugins and actions of volcano loop.
 ### volcano operations
 This metrics describe internal state of volcano.
 
-| **Metric Name**                 | **Metric Type** | **Labels**                                                  | **Description**                               |
-|---------------------------------|-----------------|-------------------------------------------------------------|-----------------------------------------------|
-| `schedule_attempts_total`       | Counter         | `result`=<result>                                     | The number of attempts to schedule pods       |
-| `pod_preemption_victims`        | Gauge           | None                                                        | The number of selected preemption victims     |
-| `total_preemption_attempts`     | Counter         | None                                                        | Total preemption attempts in the cluster      |
-| `unschedule_task_count`         | Gauge           | `job_id`=<job_id>                                     | The number of tasks failed to schedule        |
-| `unschedule_job_counts`         | Gauge           | None                                                        | The number of jobs could not be scheduled     |
-| `queue_allocated_milli_cpu`     | Gauge           | `queue_name`=<queue_name>                             | Allocated CPU count for one queue             |
-| `queue_allocated_memory_bytes`  | Gauge           | `queue_name`=<queue_name>                             | Allocated memory for one queue                |
-| `queue_request_milli_cpu`       | Gauge           | `queue_name`=<queue_name>                             | Requested CPU count for one queue             |
-| `queue_request_memory_bytes`    | Gauge           | `queue_name`=<queue_name>                             | Requested memory for one queue                |
-| `queue_deserved_milli_cpu`      | Gauge           | `queue_name`=<queue_name>                             | Deserved CPU count for one queue              |
-| `queue_deserved_memory_bytes`   | Gauge           | `queue_name`=<queue_name>                             | Deserved memory for one queue                 |
-| `queue_share`                   | Gauge           | `queue_name`=<queue_name>                             | Share for one queue                           |
-| `queue_weight`                  | Gauge           | `queue_name`=<queue_name>                             | Weight for one queue                          |
-| `queue_overused`                | Gauge           | `queue_name`=<queue_name>                             | Whether one queue is overused                 |
-| `queue_pod_group_inqueue_count` | Gauge           | `queue_name`=<queue_name>                             | The number of Inqueue PodGroups in this queue |
-| `queue_pod_group_pending_count` | Gauge           | `queue_name`=<queue_name>                             | The number of Pending PodGroups in this queue |
-| `queue_pod_group_running_count` | Gauge           | `queue_name`=<queue_name>                             | The number of Running PodGroups in this queue |
-| `queue_pod_group_unknown_count` | Gauge           | `queue_name`=<queue_name>                             | The number of Unknown PodGroups in this queue |
-| `namespace_share`               | Gauge           | `namespace_name`=<namespace_name>                     | Deserved CPU count for one namespace          |
-| `namespace_weight`              | Gauge           | `namespace_name`=<namespace_name>                     | Weight for one namespace                      |
-| `job_share`                     | Gauge           | `job_id`=<job_id>, `job_ns`=<job_ns>            | Share for one job                             |
-| `job_retry_counts`              | Counter         | `job_id`=<job_id>                                     | The number of retry counts for one job        |
-| `job_completed_phase_count`     | Counter         | `job_name`=<job_name> `queue_name`=<queue_name> | The number of job completed phase             |
-| `job_failed_phase_count`        | Counter         | `job_name`=<job_name> `queue_name`=<queue_name> | The number of job failed phase                |
+| **Metric Name**                        | **Metric Type** | **Labels**                                                        | **Description**                               |
+|----------------------------------------|-----------------|-------------------------------------------------------------------|-----------------------------------------------|
+| `schedule_attempts_total`              | Counter         | `result`=<result>                                           | The number of attempts to schedule pods       |
+| `pod_preemption_victims`               | Gauge           | None                                                              | The number of selected preemption victims     |
+| `total_preemption_attempts`            | Counter         | None                                                              | Total preemption attempts in the cluster      |
+| `unschedule_task_count`                | Gauge           | `job_id`=<job_id>                                           | The number of tasks failed to schedule        |
+| `unschedule_job_counts`                | Gauge           | None                                                              | The number of jobs could not be scheduled     |
+| `queue_allocated_milli_cpu`            | Gauge           | `queue_name`=<queue_name>                                   | Allocated CPU count for one queue             |
+| `queue_allocated_memory_bytes`         | Gauge           | `queue_name`=<queue_name>                                   | Allocated memory for one queue                |
+| `queue_allocated_scalar_resources`     | Gauge           | `queue_name`=<queue_name>, `resource`=<resource_name> | Allocated scalar resource for one queue       |
+| `queue_request_milli_cpu`              | Gauge           | `queue_name`=<queue_name>                                   | Requested CPU count for one queue             |
+| `queue_request_memory_bytes`           | Gauge           | `queue_name`=<queue_name>                                   | Requested memory for one queue                |
+| `queue_request_scalar_resources`       | Gauge           | `queue_name`=<queue_name>, `resource`=<resource_name> | Requested scalar resource for one queue       |
+| `queue_deserved_milli_cpu`             | Gauge           | `queue_name`=<queue_name>                                   | Deserved CPU count for one queue              |
+| `queue_deserved_memory_bytes`          | Gauge           | `queue_name`=<queue_name>                                   | Deserved memory for one queue                 |
+| `queue_deserved_scalar_resources`      | Gauge           | `queue_name`=<queue_name>,                                  | Deserved scalar resource for one queue        |
+| `queue_capacity_mill_cpu`              | Gauge           | `queue_name`=<queue_name>,                                  | CPU count capacity for one queue              |
+| `queue_capacity_memory_bytes`          | Gauge           | `queue_name`=<queue_name>,                                  | memory capacity for one queue                 |
+| `queue_capacity_scalar_resources`      | Gauge           | `queue_name`=<queue_name>, `resource`=<resource_name> | Scalar resource capacity for one queue        |
+| `queue_real_capacity_mill_cpu`         | Gauge           | `queue_name`=<queue_name>,                                  | CPU count real capacity for one queue         |
+| `queue_real_capacity_memory_bytes`     | Gauge           | `queue_name`=<queue_name>,                                  | Memory real capacity for one queue            |
+| `queue_real_capacity_scalar_resources` | Gauge           | `queue_name`=<queue_name>, `resource`=<resource_name> | Scalar resource real capacity for one queue   |
+| `queue_share`                          | Gauge           | `queue_name`=<queue_name>                                   | Share for one queue                           |
+| `queue_weight`                         | Gauge           | `queue_name`=<queue_name>                                   | Weight for one queue                          |
+| `queue_overused`                       | Gauge           | `queue_name`=<queue_name>                                   | Whether one queue is overused                 |
+| `queue_pod_group_inqueue_count`        | Gauge           | `queue_name`=<queue_name>                                   | The number of Inqueue PodGroups in this queue |
+| `queue_pod_group_pending_count`        | Gauge           | `queue_name`=<queue_name>                                   | The number of Pending PodGroups in this queue |
+| `queue_pod_group_running_count`        | Gauge           | `queue_name`=<queue_name>                                   | The number of Running PodGroups in this queue |
+| `queue_pod_group_unknown_count`        | Gauge           | `queue_name`=<queue_name>                                   | The number of Unknown PodGroups in this queue |
+| `namespace_share`                      | Gauge           | `namespace_name`=<namespace_name>                           | Deserved CPU count for one namespace          |
+| `namespace_weight`                     | Gauge           | `namespace_name`=<namespace_name>                           | Weight for one namespace                      |
+| `job_share`                            | Gauge           | `job_id`=<job_id>, `job_ns`=<job_ns>                  | Share for one job                             |
+| `job_retry_counts`                     | Counter         | `job_id`=<job_id>                                           | The number of retry counts for one job        |
+| `job_completed_phase_count`            | Counter         | `job_name`=<job_name> `queue_name`=<queue_name>       | The number of job completed phase             |
+| `job_failed_phase_count`               | Counter         | `job_name`=<job_name> `queue_name`=<queue_name>       | The number of job failed phase                |
 
 ### volcano Liveness
 Healthcheck last time of volcano activity and timeout

docs/design/node-lock.md

@@ -6,7 +6,7 @@
 
 ## Backguards
 
-We intended to provide volcano the ability to share third-party resources link GPU,NPU,etc in the near future. These resources are usually registered and allocated in a daemonset called `device plugin`. When a pod requests any third-party resource, the api-server send an `AllocateRequest` to device plugin, containing the target device uuid it requests. However, it does not contain any information about the pod or container requesting the device, so it is impossible for deviceplugin to access the annotation of pod, because is does not know which pod sends this request.
+We intended to provide volcano the ability to share third-party resources link GPU,NPU,etc in the near future. These resources are usually registered and allocated in a daemonset called `device plugin`. When a pod requests any third-party resource, the kubelet send an `AllocateRequest` to device plugin, containing the target device uuid it requests. However, it does not contain any information about the pod or container requesting the device, so it is impossible for deviceplugin to access the annotation of pod, because is does not know which pod sends this request.
 Using `Node Lock` will resolve this problem because only one pod is requesting this resource on this node. So, device-plugin can access additional information in pod.annotations written by scheduler and will be able to do more fine-grained work As the figure shown below:
 
 ![img](./images/node-lock.jpg)

docs/design/prebind.md

@@ -0,0 +1,84 @@
+# PreBind
+
+## Backgrounds
+Inspired by [#3618](https://github.com/volcano-sh/volcano/issues/3618). Volcano has introduced a lot of plugins from kube-scheduler,
+such as `NodeAffinity`, `TaintToleration`, `PodTopologySpread`, `ImageLocality`, etc. These plugins implement the `PreFilter`, `Filter`, 
+`PreScore`, `Score` in the predicates and nodeorder plugins. However, plugins such as `VolumeBinding` and `DynamicResourceAllocation` 
+require the `PreBind` extension point. This extension point is executed before binding the Pod to a node and is used to bind additional resources, 
+such as `PVC` and `ResourceClaim`. If the `PreBind` operation fails, the pod cannot be bound to a node. Currently, volcano lacks the `PreBind` extension point.
+
+## Motivation
+Add `PreBind` extension point to volcano, enables the introduction of plugins such as `VolumeBinding` and `DynamicResourceAllocation`, to bind additional resources
+
+## Design Details
+A scheduling session is responsible for filtering nodes, scoring nodes, and pre-selecting a node for a pod. 
+While the cache is responsible for binding the Pod to a node. The session and cache execute in two different goroutines. 
+Since `Bind` is executed in the cache, `PreBind` also needs to be executed in the cache. 
+However, the current extension points are all registered in the session, such as `PrePredicateFn`, `PredicateFn`, `NodeOrderFn`, etc.
+Adding an extension point like called `PreBindFn` in the session is meaningless because `PreBind` needs to be executed in the cache,
+If we try to add `PreBindFn` to the session like adding other extension points, when the session dispatches the pod bind task to the cache, 
+it still needs to copy the plugins' `PreBind` execution func to the cache. If some plugins' `PreBind` logic contains references to the session, 
+this might also lead to the session not being released even after `CloseSession` has been called.
+Therefore, it is best for the plugin to register `PreBind` directly to the cache. 
+
+### PreBinder interface
+A new interface needs to be added to the cache, called the `PreBinder` interface:
+```go
+type PreBinder interface {
+	PreBind(ctx context.Context, bindCtx *BindContext) error
+
+	// PreBindRollBack is called when the pre-bind or bind fails.
+	PreBindRollBack(ctx context.Context, bindCtx *BindContext)
+}
+```
+It contains two methods, one is `PreBind`, which is the method for the plugin to execute the main `PreBind` logic, and the other is `PreBindRollBack`. 
+When `PreBind` fails or `Bind` fails, the executed `PreBind` needs to be rolled back to unbind the additional bound resources. If the plugin wants to execute `PreBind`, 
+it needs to implement the `PreBinder` interface and call the newly added `RegisterPreBinder` method in session to register the plugin into the cache:
+```go
+// RegisterPreBinder registers the passed bind handler to the cache
+func (ssn *Session) RegisterPreBinder(name string, preBinder interface{}) {
+	ssn.cache.RegisterPreBinder(name, preBinder)
+}
+```
+### BindContext
+For the parameters of `PreBind` and `PreBindRollBack`, `BindContext` is a newly defined structure:
+```go
+type BindContextExtension interface{}
+
+type BindContext struct {
+	TaskInfo *schedulingapi.TaskInfo
+	// Extensions stores extra bind context information of each plugin
+	Extensions map[string]BindContextExtension
+}
+```
+This structure contains the `TaskInfo` that needs to be bound, and a new field called `Extensions`. It's a map contains the bind context information of each plugin.
+The `BindContextExtension` carries the information that the plugin needs to pass into the `PreBind` extension point, the `Bind` extension point, 
+and even the `PostBind` extension point that may need to be added in the future. The `BindContextExtension` is just a empty `interface{}` type.
+```go
+type BindContextHandler interface {
+	// SetupBindContextExtension allows the plugin to set up extension information in the bind context
+	SetupBindContextExtension(ssn *Session, bindCtx *cache.BindContext)
+}
+```
+`BindContextHandler` is a new interface added to session. Plugin can choose whether to implement `BindContextHandler` interface. For example, 
+`VolumeBinding` needs to carry cycleState to `PreBind`, it can wrap cycleState and then set the additional information to be passed through `SetUpBindContextExtension` method.
+```go
+// bind context extension information
+type bindContextExtension struct {
+	State *k8sframework.CycleState
+}
+
+func (pp *predicatesPlugin) SetupBindContextExtension(ssn *framework.Session, bindCtx *cache.BindContext) {
+	// ...
+	// set up bind context extension
+	bindCtx.Extensions[pp.Name()] = &bindContextExtension{State: ssn.GetCycleState(bindCtx.TaskInfo.UID)}
+}
+```
+So to summarize, if a new plugin needs to call `PreBind`, the process involves:
+1. Implement the `PreBinder` interface
+2. Call `RegisterPreBinder` to register the plugin when in `OpenSession`
+
+(Optional) If the plugin needs to pass additional information to `PreBind`, the process involves:
+1. Implement the `SetupBindContextExtension` method of the `BindContextHandler` interface
+2. In the `SetupBindContextExtension` implementation, set the additional information that the plugin needs to carry in the `Extensions` map of the `BindContext` parameter
+

docs/design/preempt-action-support-topology.md

@@ -0,0 +1,98 @@
+# Preempt Action Support Topology
+
+## Motivation
+
+In cloud-native task scheduling scenarios, preemption is a key feature to ensure timely scheduling of high-priority tasks. Compared to the K8s scheduler, Volcano's current preemption implementation is relatively simple, especially in handling affinity judgments. To improve the accuracy and efficiency of the preemption mechanism, the existing implementation needs to be optimized, particularly in supporting topology awareness.
+
+## In Scope
+
+- Optimize Volcano's preemption mechanism to support affinity judgments
+- Improve single Pod preemption process
+- Implement simulation scheduling interface to ensure simulated addition and removal of pods won't cause topology changes
+
+## Out of Scope
+
+- Gang scheduling preemption scenario optimization
+
+## User Stories
+
+### Story 1
+
+As a cluster administrator, I want the system to accurately judge Pod affinity constraints during preemption scheduling to avoid scheduling failures caused by topology changes.
+
+### Story 2
+
+As a user, I expect high-priority Pod preemption to minimize impact on existing Pods while maintaining consistency of affinity rules.
+
+### Story 3
+
+When topology-sensitive resources like GPUs exist, the preemption process needs to consider resource topology relationships to ensure resource allocation after preemption still satisfies original topology constraints.
+
+For example, if a node has 2 GPUs (8GB each), Pod A and Pod B each use 4GB, and Pod C needs 8GB. When Pod C needs to be scheduled, it triggers the preemption mechanism. During the simulation scheduling process, the system will try to preempt Pod A and reschedule it. There are two possible scenarios:
+
+1. If topology changes during simulation scheduling:
+
+   - System chooses to preempt Pod A
+   - The predicate function check successfully for Pod C
+   - When simulating the re-addition of Pod A, the binpack strategy causes Pod A to be scheduled to a different GPU
+   - After re-adding Pod A, the predicate function check still passes for Pod C
+   - This means Pod C can be scheduled without actually removing Pod A
+   - Therefore, the preemption is considered unnecessary and fails
+2. If topology remains consistent during simulation scheduling:
+
+   - System chooses to preempt Pod A
+   - The predicate function check successfully for Pod C
+   - When simulating the re-addition of Pod A, the original topology relationship is maintained
+   - After re-adding Pod A, the predicate function check fails for Pod C
+   - This confirms that Pod A must be removed for Pod C to be scheduled
+   - Therefore, the preemption is considered necessary and succeeds
+
+Therefore, when implementing the preemption mechanism, it's crucial to verify the necessity of preemption by checking if the topology changes during pod re-addition would affect the scheduling of the preempting pod.
+
+![preempt-action-support-topology-1](images/preempt-action-support-topology/preempt-action-support-topology-1.png)
+
+## Design Detail
+
+### Preemption Process
+
+![preempt-action-support-topology-2](images/preempt-action-support-topology/preempt-action-support-topology-2.png)
+
+1. Execute Predicate on all nodes that are not UnschedulableAndUnresolvable to obtain candidate node list, and perform parallel simulation scheduling on all candidate nodes.
+2. The simulation scheduling process for each node is as follows:
+
+   1. First consider Pods with lower priority as potential victims on the node
+   2. Sort the victim list (lower priority and non-PDB-violating victims come first)
+   3. Remove victims in order, add each removed one to eviction candidates, and observe if the verification function passes
+   4. Verification function: Try to add pods (pipelined) with higher priority targeting the current node, observe if they can pass predicate; then remove them and observe if they can pass predicate
+   5. If passed, try to add back the previous eviction candidates in PDB and priority order (to minimize impact), calling verification function after each addition; if verification fails, add to final eviction list
+   6. If final eviction list is not empty, return it
+3. Sort filtered nodes using PreemptNodeOrderFn
+4. Schedule Pod to the top-ranked node, evict victims list, and cancel nominatedNodeName of lower priority pods that had nominated this node, moving them from pipeline to pending schedule
+
+### Key Function Modifications
+
+- `SimulateRemoveTaskFn`: Simulate the removal of a task from a node, plugins implement this function to ensure the removal action does not cause topology changes
+
+  ```go
+  type SimulateRemoveTaskFn func(ctx context.Context, state *k8sframework.CycleState, taskToSchedule *TaskInfo, taskInfoToRemove *TaskInfo, nodeInfo *NodeInfo) error
+  ```
+- `SimulateAddTaskFn`: Simulate the addition of a task to a node, plugins implement this function to ensure the addition action does not cause topology changes
+
+  ```go
+  type SimulateAddTaskFn func(ctx context.Context, state *k8sframework.CycleState, taskToSchedule *TaskInfo, taskInfoToAdd *TaskInfo, nodeInfo *NodeInfo) error
+  ```
+- `SimulatePredicateFn`: Simulate the predicate check for a task on a node, plugins implement this function to verify if the task can be scheduled to the node while maintaining topology constraints
+
+  ```go
+  type SimulatePredicateFn func(ctx context.Context, state *k8sframework.CycleState, task *TaskInfo, nodeInfo *NodeInfo) error
+  ```
+- `SimulateAllocatableFn`: Simulate the allocatable check for a node, plugins implement this function to verify if the queue has enough resources to schedule the task while maintaining topology constraints
+
+  ```go
+  type SimulateAllocatableFn func(ctx context.Context, state *k8sframework.CycleState, queue *QueueInfo, task *TaskInfo) bool
+  ```
+
+### Limitations
+
+- Current design focuses on single pod preemption scenarios. Does not handle complex topology changes in gang scheduling
+- For complex combinations of affinity rules, multiple attempts may be needed to find the optimal solution. Performance impact of simulation scheduling needs to be evaluated in large-scale clusters

docs/design/scheduling-reason.md

@@ -2,6 +2,7 @@
 
 [@eggiter](https://github.com/eggiter); Aug 13, 2021
 [@tgaddair](https://github.com/tgaddair); Dec 12, 2022
+[@ouyangshengjia](https://github.com/ouyangshengjia); Mar 20, 2025
 
 ## Table of Contents
 
@@ -20,31 +21,28 @@
 - Introducing an extra scheduling reasons in PodScheduled PodCondition:
   + `Schedulable`: means that the scheduler can schedule the pod right now, but not bind yet.
 
-An additional reason was originally considered that conflicts with cluster autoscaler. Instead, this reason only appears in the detailed `Message` field, and shows up with `Reason: Unschedulable` in the pod:
-  + `Undetermined`: means that the scheduler skips scheduling the pod which left the pod `Undetermined`, for example due to unschedulable pod already occurred.
-
 - Case:
   + 3 nodes: node1, node2, node3;
   + 6 tasks in the PodGroup(`minAvailable = 6`);
-    + only 1 task(Task6) is unschedulable and other 5 tasks(Task1 ~ 5) can be scheduled, thus the whole job is unscheduable.
+    + 3 tasks(Task1 ~ 3) can be scheduled and other 3 tasks(Task4 ~ 6) is unschedulable, thus the whole job is unscheduable.
   
 - Current information:
-  +  |Tasks|Reason|Message|
-     |-|-|-|
-     |PodGroup |NotEnoughResources|6/6 tasks in gang unschedulable: pod group is not ready, 6 Pending, 6 minAvailable |
-     |Task1 ~ 5|Unschedulable|6/6 tasks in gang unschedulable: pod group is not ready, 6 Pending, 6 minAvailable|
-     |Task6|Unschedulable| all nodes are unavailable: 1 plugin InterPodAffinity predicates failed node(s) didn't match pod affinity/anti-affinity, node(s) didn't match pod affinity rules, 2 node(s) resource fit failed.|
+  +  | Tasks     | Reason             | Message                                                                                                                                                                                         |
+     |-----------|--------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+     | PodGroup  | NotEnoughResources | 6/6 tasks in gang unschedulable: pod group is not ready, 6 Pending, 6 minAvailable                                                                                                              |
+     | Task1 ~ 3 | Unschedulable      | 6/6 tasks in gang unschedulable: pod group is not ready, 6 Pending, 6 minAvailable                                                                                                              |
+     | Task4 ~ 6 | Unschedulable      | all nodes are unavailable: 1 plugin InterPodAffinity predicates failed node(s) didn't match pod affinity/anti-affinity, node(s) didn't match pod affinity rules, 2 node(s) resource fit failed. |
 
 - Improved information:
-  + |Tasks|Reason|Message|
-    |-|-|-|
-    |PodGroup |(same)| **3/6** tasks in gang unschedulable: pod group is not ready, 6 Pending, 6 minAvailable; **Pending: 1 Unschedulable, 2 Undetermined, 3 Schedulable** |
-    |Task1 ~ 2|**Unschedulable**| **3/6** tasks in gang unschedulable: pod group is not ready, 6 Pending, 6 minAvailable; **Pending: 1 Unschedulable, 2 Undetermined, 3 Schedulable**  |
-    |Task3|**Schedulable**| **Pod ns1/task-1 can possibly be assgined to node1** |
-    |Task4|**Schedulable**| **Pod ns1/task-2 can possibly be assgined to node2** |
-    |Task5|**Schedulable**| **Pod ns1/task-3 can possibly be assgined to node3** |
-    |Task6|Unschedulable| all nodes are unavailable: 1 plugin InterPodAffinity predicates failed node(s) didn't match pod affinity/anti-affinity, node(s) didn't match pod affinity rules, 2 node(s) resource fit failed.|
+  + | Tasks     | Reason             | Message                                                                                                                                                                                         |
+    |-----------|--------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
+    | PodGroup  | NotEnoughResources | **3/6** tasks in gang unschedulable: pod group is not ready, 6 Pending, 6 minAvailable; **Pending: 3 Unschedulable, 3 Schedulable**                                                             |
+    | Task1     | **Schedulable**    | **Pod ns1/task-1 can possibly be assgined to node1, once minAvailable is satisfied**                                                                                                            |
+    | Task2     | **Schedulable**    | **Pod ns1/task-2 can possibly be assgined to node2, once minAvailable is satisfied**                                                                                                            |
+    | Task3     | **Schedulable**    | **Pod ns1/task-3 can possibly be assgined to node3, once minAvailable is satisfied**                                                                                                            |
+    | Task4     | Unschedulable      | all nodes are unavailable: 1 plugin InterPodAffinity predicates failed node(s) didn't match pod affinity/anti-affinity, node(s) didn't match pod affinity rules, 2 node(s) resource fit failed. |
+    | Task5 ~ 6 | Unschedulable      | **3/6** tasks in gang unschedulable: pod group is not ready, 6 Pending, 6 minAvailable; **Pending: 3 Unschedulable, 3 Schedulable**                                                             |
 
-    - Note: Task1 & 2 are `Unschedulable` maybe because that this two locate after task6 by `TaskOrderFn`;
+    - Note: Task5 ~ 6 are `Unschedulable` maybe because that this two locate after task4 by `TaskOrderFn`;
 
 - In improved information, we can easily find the one that breaks the whole scheduling cycle and why dose that happen. Additionally,  we can find the histogram of reason why there are some tasks whose status is pending.

docs/design/tdm-plugin.md

@@ -14,7 +14,7 @@ TDM plugin enhance the volcano time-sharing multiplexing resource ability. It wi
 
 ![tdmsolution](./images/tdmsolution.png)
 
-1. Add `volcano.sh/preemptable` annotaion for Pod/PodGroup. For volcano job when add this annotaion in job level, Pod/PodGroup will inherit this annotation. The pod with `volcano.sh/preemptable: "true"` annotation can be dispatched to `revocable node`.
+1. Add `volcano.sh/preemptable` annotation for Pod/PodGroup. For volcano job when add this annotation in job level, Pod/PodGroup will inherit this annotation. The pod with `volcano.sh/preemptable: "true"` annotation can be dispatched to `revocable node`.
 Otherwise, the pod can not be dispatched to `revocable node`.
 2. Add `tdm` plugin and config for volcano scheduler. `tdm.revocable-zone` is a const prefix(), `rz1` is the revocable zone name and the value is a time frame. 
 

docs/design/volume-binding.md

@@ -0,0 +1,39 @@
+# Volume Binding
+
+## Backgrounds
+Currently, Volcano does not support the `WaitForFirstConsumer` mode for volume binding. 
+The current operations for binding volumes are intrusively modified into the scheduler cache, becoming part of the cache's interface.
+The `VolumeBinding` plugin, as a plugin also introduced from kube-scheduler, should be introduced into the `predicates` or `nodeorder` plugins like other plugins, 
+volume binding functionality should not be intrusively modified into the cache.
+
+## Design Details
+`BindVolumes`, `AllocateVolumes`, and other intrusive changes to the scheduler cache as interfaces need to be removed, 
+which are originally part of the binder in the `VolumeBinding` plugin and should not be exposed to the cache. 
+The extension points involved in the `VolumeBinding` plugin are `PreFilter`, `Filter`, `PreScore`, `Score`, `Reserve`, `Unreserve`, and `PreBind`, 
+so it is most appropriate to introduce `VolumeBinding` into the `predicates` plugin, and `predicates` is the core plugin. 
+`VolumeBinding` should be integrated into `predicates` plugin as a default enabled feature. However, 
+predicates did not implement extension points such as `Score`, `Reserve`, `PreBind`, etc., so the predicates plugin can implement these interfaces as follows:
+1. `Score`: For scoring, `predicates` can refer to and reuse the `AddBatchNodeOrderFn` logic of the 
+[nodeorder](https://github.com/volcano-sh/volcano/blob/7103c18de19821cd278f949fa24c13da350a8c5d/pkg/scheduler/plugins/nodeorder/nodeorder.go#L301-L335) plugin
+2. `Reserve` and `Unreserve`: For `Reserve` and `Unreserve`, `predicates` plugin can implement them in event handler's `AllocateFunc` and `DeallocateFunc`, for example,
+add following codes for `Reserve`:
+```go
+func (pp *predicatesPlugin) runReservePlugins(ssn *framework.Session, event *framework.Event) {
+	// Volume Binding Reserve
+	if pp.volumeBindingPlugin != nil {
+		status := pp.volumeBindingPlugin.Reserve(context.TODO(), state, event.Task.Pod, event.Task.Pod.Spec.NodeName)
+		if !status.IsSuccess() {
+			event.Err = status.AsError()
+			return
+		}
+	}
+	
+	// other plugins' Reserve
+}
+```
+3. `PreBind`: For `PreBind`, a new interface called `PreBinder` should be added and the predicates plugin should implement it, contains
+two methods `PreBind` and `PreBindRollback`, and `PreBind` method directly calls the `PreBind` extension points of each plugin. 
+Because the plugin lifecycle is generally in the session, that is, to pre-allocate nodes to pods, while `PreBind` and `Bind` are in the cache, 
+which are two different goroutines, so if the plugin needs to pass additional information to the `PreBind` method, 
+it can be set through the `BindContext` parameter of the `PreBind` method, which is a new struct containing a map that can carry the information that the plugin needs to pass to `PreBind`. 
+The specific implementation details of `PreBind` can be referred to this doc: [PreBind](prebind.md).

docs/development/development.md

@@ -1,6 +1,4 @@
-This document helps you get started using the Volcano code base.
-If you follow this guide and find some problem, please take
-a few minutes to update this file.
+This document helps you get started using the Volcano code base. If you follow this guide and find a problem, please take a few minutes to update this file.
 
 - [Building the code](#building-the-code)
 - [Building docker images](#building-docker-images)
@@ -13,39 +11,37 @@ a few minutes to update this file.
 - [Adding dependencies](#adding-dependencies)
 - [About testing](#about-testing)
 
+## Cloning the Code
 
-## Cloning the code
+You will need to clone the main `volcano` repo to `$GOPATH/src/volcano.sh/volcano` for the below commands to work correctly.
 
-You will need to clone the main `volcano` repo to `$GOPATH/src/volcano.sh/volcano` for
-the below commands to work correctly.
+## Building the Code
 
-## Building the code
-
-To build volcano all components for your host architecture, go to
-the source root and run:
+To build all Volcano components for your host architecture, go to the source root and run:
 
 ```bash
 make image_bins
 ```
-the binaries will be generated at .../src/volcano.sh/volcano/_output/bin/linux/amd64/
-but if we just make as below
+
+The binaries will be generated at `.../src/volcano.sh/volcano/_output/bin/linux/amd64/`.
+
+If we just run `make` as below:
 
 ```bash
 make
 ```
-then the binaries would be generated at .../src/volcano.sh/volcano/_output/bin/
 
-To build a specific component for your host architecture, go to
-the source root and run `make <component name>`:
+Then the binaries would be generated at `.../src/volcano.sh/volcano/_output/bin/`.
+
+To build a specific component for your host architecture, go to the source root and run `make <component name>`:
 
 ```bash
 make vc-scheduler
 ```
 
+## Building Docker Images
 
-## Building docker images
-
-Build the containers in your local docker cache:
+Build the containers in your local Docker cache:
 
 ```bash
 make images
@@ -57,44 +53,44 @@ To build cross-platform images:
 make images DOCKER_PLATFORMS="linux/amd64,linux/arm64" BUILDX_OUTPUT_TYPE=registry IMAGE_PREFIX=[yourregistry]
 ```
 
+## Building a Specific Component
 
-## Building a specific component
+If you want to make a local change and test some component, say `vc-controller-manager`, you could do:
 
-If you want to make a local change and test some component, say `vc-controller-manager`, you
-could do:
-
-Under volcano.sh/volcano repo
+Under `volcano.sh/volcano` repo:
 
 ```bash
 pwd
 ```
-The path should be
+
+The path should be:
 
 ```bash
 .../src/volcano.sh/volcano
 ```
 
-Set up environment variables HUB and TAG by
+Set up environment variables HUB and TAG:
+
 ```bash
 export HUB=docker.io/yourrepo
 export TAG=citadel
 ```
 
-Make some local change of the code, then build `vc-controller-manager`
+Make some local change to the code, then build `vc-controller-manager`:
 
 ```bash
 make vc-controller-manager
 ```
 
-## Building the Volcano manifests
+## Building the Volcano Manifests
 
-Use the following command to build the deploy yaml files:
+Use the following command to build the deploy YAML files:
 
 ```bash
 make generate-yaml
 ```
 
-## Cleaning outputs
+## Cleaning Outputs
 
 You can delete any build artifacts with:
 
@@ -102,9 +98,9 @@ You can delete any build artifacts with:
 make clean
 ```
 
-## Running tests
+## Running Tests
 
-### Running unit tests
+### Running Unit Tests
 
 You can run all the available unit tests with:
 
@@ -112,7 +108,7 @@ You can run all the available unit tests with:
 make unit-test
 ```
 
-### Running e2e tests
+### Running E2E Tests
 
 You can run all the available e2e tests with:
 
@@ -122,23 +118,22 @@ make images
 make e2e
 ```
 
-If you want to run e2e test in a existing cluster with volcano deployed, run the following:
+If you want to run e2e tests in an existing cluster with Volcano deployed, run the following:
 
 ```bash
-export VC_BIN= need to set vcctl binary path (eg:.../src/volcano.sh/volcano/_output/bin/)
+export VC_BIN=<path-to-vcctl-binary> (e.g., .../src/volcano.sh/volcano/_output/bin/)
 KUBECONFIG=${KUBECONFIG} go test ./test/e2e
 ```
 
-## Auto-formatting source code
+## Auto-Formatting Source Code
 
-You can automatically format the source code to follow our conventions by going to the
-top of the repo and entering:
+You can automatically format the source code to follow our conventions by going to the top of the repo and entering:
 
 ```bash
 ./hack/update-gofmt.sh
 ```
 
-## Running the verification
+## Running the Verification
 
 You can run all the verification we require on your local repo by going to the top of the repo and entering:
 
@@ -146,10 +141,9 @@ You can run all the verification we require on your local repo by going to the t
 make verify
 ```
 
-## Adding dependencies
+## Adding Dependencies
 
-Volcano uses [Go Modules](https://blog.golang.org/migrating-to-go-modules) to manage its dependencies.
-If you want to add or update a dependency, running:
+Volcano uses [Go Modules](https://blog.golang.org/migrating-to-go-modules) to manage its dependencies. If you want to add or update a dependency, run:
 
 ```bash
 go get dependency-name@version
@@ -157,19 +151,17 @@ go mod tidy
 go mod vendor
 ```
 
-Note: Go's module system, introduced in Go 1.11, provides an official dependency management solution built into the go command.
-      Make sure `GO111MODULE` env is not `off` before using it.
+Note: Go's module system, introduced in Go 1.11, provides an official dependency management solution built into the `go` command. Make sure `GO111MODULE` env is not `off` before using it.
 
-## About testing
+## About Testing
 
-Before sending pull requests you should at least make sure your changes have
-passed both unit and the verification. We only merge pull requests when
-**all** tests are passing.
+Before sending pull requests, you should at least make sure your changes have passed both unit tests and verification. We only merge pull requests when **all** tests are passing.
 
 - Unit tests should be fully hermetic
   - Only access resources in the test binary.
 - All packages and any significant files require unit tests.
 - Unit tests are written using the standard Go testing package.
-- The preferred method of testing multiple scenarios or input is
-  [table driven testing](https://github.com/golang/go/wiki/TableDrivenTests)
+- The preferred method of testing multiple scenarios or input is [table-driven testing](https://github.com/golang/go/wiki/TableDrivenTests).
 - Concurrent unit test runs must pass.
+
+

docs/user-guide/how_to_enable_dra.md

@@ -0,0 +1,76 @@
+# How to Enable Dynamic Resource Allocation (DRA) in Volcano Scheduler
+
+This document describes the steps required to enable Dynamic Resource Allocation (DRA) support in the Volcano scheduler.
+
+## Prerequisites
+Before proceeding with the configuration steps, ensure your cluster meets the following prerequisites:
+
+### Configure Cluster Nodes (Containerd)
+For nodes running containerd as the container runtime, you must enable the Container Device Interface (CDI) feature. 
+This is crucial for containerd to properly interact with DRA drivers and inject dynamic resources into Pods.
+
+Modify the containerd configuration file on each node (typically /etc/containerd/config.toml) to ensure the following setting is present:
+```toml
+# Enable CDI as described in
+# https://tags.cncf.io/container-device-interface#containerd-configuration
+[plugins."io.containerd.grpc.v1.cri"]
+  enable_cdi = true
+  cdi_spec_dirs = ["/etc/cdi", "/var/run/cdi"]
+```
+After modifying the configuration, restart the containerd service on each node for the changes to take effect. For example: `sudo systemctl restart containerd`
+
+> If you are using other container runtimes, please refer to: [how-to-configure-cdi](https://github.com/cncf-tags/container-device-interface?tab=readme-ov-file#how-to-configure-cdi)
+
+## 1. Configure Kube-apiserver
+DRA-related APIs are k8s built-in resources instead of CRD resources, and these resources are not registered by default in v1.32, 
+so you need to set the startup parameters of kube-apiserver to manually register DRA-related APIs, add or ensure the following flag is present in your kube-apiserver manifest or configuration:
+```yaml
+--runtime-config=resource.k8s.io/v1beta1=true
+```
+
+## 2. Install Volcano With DRA feature gates enabled
+When installing Volcano, you need to enable the DRA related feature gates, e.g., `DynamicResourceAllocation` must be enabled when you need to use DRA, 
+you can also choose to enable the `DRAAdminAccess` feature gate to manage devices as your need.
+
+When you are using helm to install Volcano, you can use following command to install Volcano with DRA feature gates enabled:
+```bash
+helm install volcano volcano/volcano --namespace volcano-system --create-namespace \
+  --set custom.scheduler_feature_gates="DynamicResourceAllocation=true" \
+  # Add other necessary Helm values for your installation
+```
+
+When you directly use `kubectl apply -f` to install Volcano, you need to add or ensure the following flag is present in your volcano-scheduler manifest:
+```yaml
+--feature-gates=DynamicResourceAllocation=true
+```
+
+## 3. Configure Volcano Scheduler Plugins
+After installing Volcano, you need to configure the Volcano scheduler's plugin configuration to enable the DRA plugin within the predicates plugin arguments.
+
+Locate your Volcano scheduler configuration (A ConfigMap contains the configuration). Find the predicates plugin configuration and add or modify its arguments to enable DRA plugin.
+
+An example snippet of the scheduler configuration (within the volcano-scheduler.conf key of the ConfigMap) might look like this:
+```yaml
+actions: "enqueue, allocate, backfill"
+tiers:
+- plugins:
+  - name: priority
+  - name: gang
+- plugins:
+  - name: drf
+  - name: predicates
+    arguments:
+      predicate.DynamicResourceAllocationEnable: true
+  - name: proportion
+  - name: nodeorder
+  - name: binpack
+```
+
+## 4. Deploy a DRA Driver
+To utilize Dynamic Resource Allocation, you need to deploy a DRA driver in your cluster. The driver is responsible for managing the lifecycle of dynamic resources.
+For example, you can refer to the [kubernetes-sigs/dra-example-driver](https://github.com/kubernetes-sigs/dra-example-driver) to deploy a example DRA driver for testing.
+
+For some DRA Drivers which have already been used in actual production, you can refer to:
+- [NVIDIA/k8s-dra-driver-gpu](https://github.com/NVIDIA/k8s-dra-driver-gpu)
+- [intel/intel-resource-drivers-for-kubernetes](https://github.com/intel/intel-resource-drivers-for-kubernetes)
+

docs/user-guide/how_to_use_hypernode_auto_discovery.md

@@ -0,0 +1,113 @@
+# Usage Document
+
+## Introduction
+
+This document describes how to use the HyperNode network topology auto-discovery feature in Volcano. This feature automatically discovers the network topology within the cluster and creates and maintains HyperNode custom resources (CRs) based on the discovered information. The Volcano scheduler leverages these HyperNode CRs for scheduling decisions, eliminating the need for users to manually maintain HyperNode information.
+
+## Prerequisites
+
+Please [Install Volcano](https://github.com/volcano-sh/volcano/tree/master?tab=readme-ov-file#quick-start-guide) with version >= v1.12.0 first.
+
+## Configuration
+
+The HyperNode network topology discovery feature is configured via a ConfigMap. The ConfigMap contains the configuration for the discovery sources, such as UFM, RoCE, and label, you can modify the configuration according to your own cluster environments.
+Please note that you should replace with your Volcano namespace if Volcano is not installed in the default namespace.
+
+### Secret Configuration (Required First Step)
+
+Before configuring the UFM discovery, you must first create a Kubernetes Secret to store your UFM credentials:
+
+```bash
+kubectl create secret generic ufm-credentials \
+  --from-literal=username='your-ufm-username' \
+  --from-literal=password='your-ufm-password' \
+  -n volcano-system
+```
+ > Note: Replace your-ufm-username and your-ufm-password with your actual UFM credentials, and adjust the namespace if needed.
+
+### Example ConfigMap
+
+```yaml
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: volcano-controller-configmap
+  namespace: volcano-system # Replace with your Volcano namespace if Volcano is not installed in the default namespace.
+data:
+  volcano-controller.conf: |
+    networkTopologyDiscovery:
+      - source: ufm
+        enabled: true
+        interval: 10m
+        credentials:
+          secretRef:
+            name: ufm-credentials # Replace with the secret name that stores the UFM credentials.
+            namespace: volcano-system #Replace with the secret namespace that stores the UFM credentials.
+        config:
+          endpoint: https://ufm-server:8080
+          insecureSkipVerify: true
+      - source: roce
+        enabled: false
+        interval: 15m
+        config:
+          endpoint: https://roce-server:9090
+      - source: label
+        enabled: false
+        config: {}
+```
+
+### Configuration Options
+
+*   `source`: The discovery source. Supported values are `ufm`, `roce`, and `label`.
+*   `enabled`: Whether the discovery source is enabled.
+*   `interval`: The interval between discovery operations. If not specified, the default value is 1 hour.
+*   `config`: The configuration for the discovery source. The configuration options vary depending on the discovery source.
+*   `credentials`: The credentials configuration for accessing the discovery source.
+      * `secretRef`: Reference to a Kubernetes Secret containing credentials.
+        * `name`: The name of the Secret.
+        * `namespace`: The namespace of the Secret.
+
+#### UFM Configuration Options
+
+*   `endpoint`: The UFM API endpoint.
+*   `insecureSkipVerify`: Whether to skip TLS certificate verification. This should only be used in development environments.
+
+#### RoCE Configuration Options(Currently not supported)
+
+*   `endpoint`: The RoCE API endpoint.
+*   `token`: The RoCE API token.
+
+#### Label Configuration Options(Currently not supported)
+
+*   No configuration options are currently supported for the label discovery source.
+
+## Verification
+
+1.  Check the Volcano controller logs to ensure that the discovery sources are started successfully.
+
+```bash
+kubectl logs -n volcano-system -l app=volcano-controllers -c volcano-controllers | grep "Successfully started all network topology discoverers"
+```
+
+2.  Check the created HyperNode resources.
+
+```bash
+kubectl get hypernodes -l volcano.sh/network-topology-source=<source>
+```
+
+Replace `<source>` with the discovery source you configured, such as `ufm`.
+
+## Troubleshooting
+
+*   If the discovery sources are not started successfully, check the Volcano controller logs for errors.
+*   If the HyperNode resources are not created, check the discovery source configuration and ensure that the discovery source is able to connect to the network topology data source.
+
+## Best Practices
+
+* Volcano uses Kubernetes-standard Secrets to store sensitive credential information (username/password or token). For more stringent key encryption requirements, users should consider additional mechanisms like [Encrypting Secret Data at Rest](https://kubernetes.io/docs/tasks/administer-cluster/encrypt-data/).
+* The credential Secrets can be placed in a specified namespace for better isolation.
+* For UFM discoverer, the controller only needs read access to the specific Secret containing credentials.
+* When deploying in production environments, proper RBAC policies should be configured to limit access to Secrets.
+* TLS certificate verification should be enabled in production environments to prevent MITM attacks.
+* Monitor the Volcano controller logs for errors.
+* Set a reasonable discovery interval to avoid overloading the network topology data source.

docs/user-guide/how_to_use_job_policy.md

@@ -11,7 +11,7 @@ event(events) happens, the target action will be triggered. If timeout is config
 under `task.spec` only, it will only work for the task. If the policy is configured in both job and task level, it will obey
 the task policy.
 * Users can set multiple policy for a job or a task.
-* Currently, Volcano provides **6 build-in events** for users. The details are as follows.
+* Currently, Volcano provides **6 built-in events** for users. The details are as follows.
 
 | ID  | Event           | Description                                                                                                       |
 |-----|----------------|-------------------------------------------------------------------------------------------------------------------|
@@ -22,7 +22,7 @@ the task policy.
 | 4   | `Unknown`      | Check whether the status of a volcano job is `Unknown`. The most possible factor is task unschedulable. It is triggered when part pods can't be scheduled while some are already running in gang-scheduling case. |
 | 5   | `*`           | It means all the events, which is not so common used.                                                             |
 
-* Currently, Volcano provides **5 build-in actions** for users. The details are as follows.
+* Currently, Volcano provides **5 built-in actions** for users. The details are as follows.
 
 | ID  | Action            | Description                                                                                                      |
 |-----|-------------------|------------------------------------------------------------------------------------------------------------------|

docs/user-guide/how_to_use_volcano_vgpu.md

@@ -0,0 +1,190 @@
+# Volcano vGPU User Guide
+
+## Background Knowledge of GPU Sharing Modes in Volcano
+
+Volcano supports **two GPU sharing modes** for virtual GPU (vGPU) scheduling:
+
+### 1. HAMI-core (Software-based vGPU)
+
+**Description**:
+Leverages **VCUDA**, a CUDA API hijacking technique to enforce GPU core and memory usage limits, enabling **software-level virtual GPU slicing**.
+
+**Use case**:
+Ideal for environments requiring **fine-grained GPU sharing**. Compatible with all GPU types.
+
+---
+
+### 2. Dynamic MIG (Hardware-level GPU Slicing)
+
+**Description**:
+Utilizes **NVIDIA's MIG (Multi-Instance GPU)** technology to partition a physical GPU into isolated instances with **hardware-level performance guarantees**.
+
+**Use case**:
+Best for **performance-sensitive** workloads. Requires **MIG-capable GPUs** (e.g., A100, H100).
+
+---
+
+GPU Sharing mode is a node configuration. Volcano supports heterogeneous cluster(i.e a part of node uses HAMi-core while another part uses dynamic MIG), See [volcano-vgpu-device-plugin](https://github.com/Project-HAMi/volcano-vgpu-device-plugin) for configuration and details.
+
+## Installation
+
+To enable vGPU scheduling, the following components must be set up based on the selected mode:
+
+### Common Requirements
+
+* **Prerequisites**:
+
+  * NVIDIA driver > 440
+  * nvidia-docker > 2.0
+  * Docker configured with `nvidia` as the default runtime
+  * Kubernetes >= 1.16
+  * Volcano >= 1.9
+
+* **Install Volcano**:
+
+  * Follow instructions in [Volcano Installer Guide](https://github.com/volcano-sh/volcano?tab=readme-ov-file#quick-start-guide)
+
+* **Install Device Plugin**:
+
+  * Deploy [`volcano-vgpu-device-plugin`](https://github.com/Project-HAMi/volcano-vgpu-device-plugin)
+
+  **Note:** the [vgpu device plugin yaml](https://github.com/Project-HAMi/volcano-vgpu-device-plugin/blob/main/volcano-vgpu-device-plugin.yml) also includes the ***Node GPU mode*** and the ***MIG geometry*** configuration. Please refer to the [vgpu device plugin config](https://github.com/Project-HAMi/volcano-vgpu-device-plugin/blob/main/doc/config.md).
+
+* **Validate Setup**:
+  Ensure node allocatable resources include:
+
+```yaml
+volcano.sh/vgpu-memory: "89424"
+volcano.sh/vgpu-number: "8"
+```
+* **Scheduler Config Update**:
+
+```yaml
+kind: ConfigMap
+apiVersion: v1
+metadata:
+  name: volcano-scheduler-configmap
+  namespace: volcano-system
+data:
+  volcano-scheduler.conf: |
+    actions: "enqueue, allocate, backfill"
+    tiers:
+    - plugins:
+      - name: predicates
+      - name: deviceshare
+        arguments:
+          deviceshare.VGPUEnable: true   # enable vgpu plugin
+          deviceshare.SchedulePolicy: binpack  # scheduling policy. binpack / spread
+```
+
+Check with:
+
+```bash
+kubectl get node {node-name} -o yaml
+```
+
+---
+
+### HAMI-core Usage
+
+* **Pod Spec**:
+
+```yaml
+metadata:
+  name: hami-pod
+  annotations:
+    volcano.sh/vgpu-mode: "hami-core"
+spec:
+  schedulerName: volcano
+  containers:
+  - name: cuda-container
+    image: nvidia/cuda:9.0-devel
+    resources:
+      limits:
+        volcano.sh/vgpu-number: 1    # requesting 1 gpu cards
+        volcano.sh/vgpu-cores: 50    # (optional)each vGPU uses 50%
+        volcano.sh/vgpu-memory: 3000 # (optional)each vGPU uses 3G GPU memory
+```
+
+---
+
+### Dynamic MIG Usage
+
+* **Enable MIG Mode**:
+
+If you need to use MIG (Multi-Instance GPU), you must run the following command on the GPU node.
+
+```bash
+sudo nvidia-smi -mig 1
+```
+
+* **Geometry Config (Optional)**:
+  The volcano-vgpu-device-plugin automatically generates an initial MIG configuration, which is stored in the `volcano-vgpu-device-config` ConfigMap under the `kube-system` namespace. You can customize this configuration as needed. For more details, refer to the [vgpu device plugin yaml](https://github.com/Project-HAMi/volcano-vgpu-device-plugin/blob/main/volcano-vgpu-device-plugin.yml).
+
+* **Pod Spec with MIG Annotation**:
+
+```yaml
+metadata:
+  name: mig-pod
+  annotations:
+    volcano.sh/vgpu-mode: "mig"
+spec:
+  schedulerName: volcano
+  containers:
+  - name: cuda-container
+    image: nvidia/cuda:9.0-devel
+    resources:
+      limits:
+        volcano.sh/vgpu-number: 1
+        volcano.sh/vgpu-memory: 3000
+```
+
+Note: Actual memory allocated depends on best-fit MIG slice (e.g., request 3GB → 5GB slice used).
+
+---
+
+## Scheduler Mode Selection
+
+* **Explicit Mode**:
+
+  * Use annotation `volcano.sh/vgpu-mode` to force hami-core or MIG mode.
+  * If annotation is absent, scheduler selects mode based on resource fit and policy.
+
+* **Scheduling Policy**:
+
+  * Modes like `binpack` or `spread` influence node selection.
+
+---
+
+## Summary Table
+
+| Mode        | Isolation        | MIG GPU Required | Annotation | Core/Memory Control | Recommended For            |
+| ----------- | ---------------- | ---------------- | ---------- | ------------------- | -------------------------- |
+| HAMI-core   | Software (VCUDA) | No               | No         | Yes                 | General workloads          |
+| Dynamic MIG | Hardware         | Yes              | Yes        | MIG-controlled      | Performance-sensitive jobs |
+
+---
+
+## Monitoring
+
+* **Scheduler Metrics**:
+
+```bash
+curl http://<volcano-scheduler-ip>:8080/metrics
+```
+
+* **Device Plugin Metrics**:
+
+```bash
+curl http://<plugin-pod-ip>:9394/metrics
+```
+
+Metrics include GPU utilization, pod memory usage, and limits.
+
+---
+
+## Issues and Contributions
+
+* File bugs: [Volcano Issues](https://github.com/volcano-sh/volcano/issues)
+* Contribute: [Pull Requests Guide](https://help.github.com/articles/using-pull-requests/)
+

example/custom-plugin/Dockerfile

@@ -1,2 +1,33 @@
-FROM volcanosh/vc-scheduler:latest
-COPY plugins plugins
+FROM golang:1.23.7 AS builder
+
+WORKDIR /go/src/volcano.sh/
+
+# Install musl
+RUN apt-get update && \
+    apt-get install -y sudo
+
+RUN wget http://musl.libc.org/releases/musl-latest.tar.gz && \
+    mkdir musl-latest && \
+    tar -xf musl-latest.tar.gz -C musl-latest --strip-components=1 && \
+    cd musl-latest && \
+    ./configure && make && sudo make install
+
+COPY go.mod go.sum ./
+
+RUN go mod download
+
+ADD . volcano
+
+# Build plugin
+RUN cd volcano && CC=/usr/local/musl/bin/musl-gcc CGO_ENABLED=1 \
+    go build -buildmode=plugin -ldflags '-linkmode=external' \
+    -o example/custom-plugin/magic.so example/custom-plugin/magic.go
+
+# Build vc scheduler base image with plugin enabled
+RUN cd volcano && SUPPORT_PLUGINS=yes make vc-scheduler
+
+# Build vc scheduler image with plugin
+FROM alpine:latest
+COPY --from=builder /go/src/volcano.sh/volcano/_output/bin/vc-scheduler /vc-scheduler
+COPY --from=builder /go/src/volcano.sh/volcano/example/custom-plugin/magic.so /plugins/magic.so
+ENTRYPOINT ["/vc-scheduler"]

example/custom-plugin/README.md

@@ -1,29 +1,45 @@
-# Build plugin
+# Build image and plugin
 
-## Use `musl-libc` build plugin
+## Use `musl-libc` build image and plugin
 
 Because the default `vc-scheduler` base image is `alpine`, which only has `musl-libc`, so we should use `musl-gcc` to
 build the plugin.
 
-### Build the plugin in `Docker`:
+### Build the image and plugin in `Docker`(Recommended):
 
+Please run this command at the root path of the project.
 ```bash
-# You may need run this command at the root path of the project, cause this need the go.mod file.
-docker run -v `pwd`:/volcano golang:1.20-alpine sh -c "cd /volcano && apk add musl-dev gcc && go build -buildmode=plugin -o example/custom-plugin/magic.so example/custom-plugin/magic.go"
+docker build -t volcanosh/vc-scheduler:custom-plugins -f example/custom-plugin/Dockerfile .
 ```
+And then replace the image and set `--plugins-dir=plugins` parameter in `vc-scheduler` deployment yaml file.
 
-### Build the plugin in local:
+### Build the image and plugin locally:
 
+Please run this command at the root path of the project.
 ```bash
 # install musl
-wget http://musl.libc.org/releases/musl-1.2.1.tar.gz
-tar -xf musl-1.2.1.tar.gz && cd musl-1.2.1
+wget http://musl.libc.org/releases/musl-latest.tar.gz
+mkdir musl-latest && tar -xf musl-latest.tar.gz -C musl-latest --strip-components=1 && cd musl-latest
 ./configure
 make && sudo make install
 
-# build plugin
-CC=/usr/local/musl/bin/musl-gcc CGO_ENABLED=1 go build -buildmode=plugin magic.go
+# build plugin .so file
+CC=/usr/local/musl/bin/musl-gcc CGO_ENABLED=1 go build -buildmode=plugin -ldflags '-linkmode=external' \
+    -o example/custom-plugin/magic.so example/custom-plugin/magic.go
+
+# build vc scheduler binary
+SUPPORT_PLUGINS=yes make vc-scheduler
+cat << EOF > Dockerfile
+FROM alpine:latest
+COPY _output/bin/vc-scheduler /vc-scheduler
+COPY example/custom-plugin/magic.so /plugins/magic.so
+ENTRYPOINT ["/vc-scheduler"]
+EOF
+
+# build vc scheduler image
+docker build -t volcanosh/vc-scheduler:custom-plugins .
 ```
+And then replace the image and set `--plugins-dir=plugins` parameter in `vc-scheduler` deployment yaml file.
 
 ## Use `gnu-libc` build plugin
 

example/integrations/argo/README.md

@@ -67,7 +67,7 @@ spec:
       # of the resource (not just labels). Multiple AND conditions can be represented by comma
       # delimited expressions.
       # For more details: https://kubernetes.io/docs/concepts/overview/working-with-objects/labels/
-      # argoexec will get the resource information by "kubectl get -o json -w resouce/name" and check if the conditions are match
+      # argoexec will get the resource information by "kubectl get -o json -w resource/name" and check if the conditions are match
       # Completed is the phase that all tasks of Job are completed
       # Failed is the phase that the job is restarted failed reached the maximum number of retries.
       # change the successCondition or failureCondition according to the actual situation

example/jobflow/JobTemplate.yaml

@@ -5,15 +5,6 @@ metadata:
 spec:
   minAvailable: 1
   schedulerName: volcano
-  priorityClassName: high-priority
-  policies:
-    - event: PodEvicted
-      action: RestartJob
-  plugins:
-    ssh: []
-    env: []
-    svc: []
-  maxRetry: 5
   queue: default
   tasks:
     - replicas: 1
@@ -42,15 +33,6 @@ metadata:
 spec:
   minAvailable: 1
   schedulerName: volcano
-  priorityClassName: high-priority
-  policies:
-    - event: PodEvicted
-      action: RestartJob
-  plugins:
-    ssh: []
-    env: []
-    svc: []
-  maxRetry: 5
   queue: default
   tasks:
     - replicas: 1
@@ -79,15 +61,6 @@ metadata:
 spec:
   minAvailable: 1
   schedulerName: volcano
-  priorityClassName: high-priority
-  policies:
-    - event: PodEvicted
-      action: RestartJob
-  plugins:
-    ssh: []
-    env: []
-    svc: []
-  maxRetry: 5
   queue: default
   tasks:
     - replicas: 1
@@ -116,15 +89,6 @@ metadata:
 spec:
   minAvailable: 1
   schedulerName: volcano
-  priorityClassName: high-priority
-  policies:
-    - event: PodEvicted
-      action: RestartJob
-  plugins:
-    ssh: []
-    env: []
-    svc: []
-  maxRetry: 5
   queue: default
   tasks:
     - replicas: 1
@@ -153,15 +117,6 @@ metadata:
 spec:
   minAvailable: 1
   schedulerName: volcano
-  priorityClassName: high-priority
-  policies:
-    - event: PodEvicted
-      action: RestartJob
-  plugins:
-    ssh: []
-    env: []
-    svc: []
-  maxRetry: 5
   queue: default
   tasks:
     - replicas: 1

example/jobflow/README.md

@@ -8,53 +8,16 @@ read design at [here](../../docs/design/jobflow).
 
 ### Prerequisites
 
-- docker: `18.06`
 - Kubernetes: >`1.17`
 
 ## startup steps
 
-build image from local
-```bash
-# get volcano and jobflow source code from github
-git clone http://github.com/volcano-sh/volcano.git
-git clone https://github.com/BoCloud/JobFlow.git
-
-# build image beyondcent/jobflow:v0.0.1 from local
-cd JobFlow
-make
-make docker-build
-```
-
-##### deploy JobFlow from [here](https://github.com/BoCloud/JobFlow#deploy)
-```bash
-kubectl apply -f https://raw.githubusercontent.com/BoCloud/JobFlow/main/deploy/jobflow.yaml
-```
-
-##### deploy Volcano from [here](https://volcano.sh/en/docs/installation/#install-with-yaml-files)
-```bash
-kubectl apply -f https://raw.githubusercontent.com/volcano-sh/volcano/master/installer/volcano-development.yaml
-```
-
-if cert of `jobflow-webhook-service.kube-system.svc` has expired, generate one to replace it.
-```bash
-# delete expired cert in secrets
-kubectl delete secret jobflow-webhook-server-cert -nkube-system
-
-# use gen-admission-secret.sh register new secret
-cd volcano
-./installer/dockerfile/webhook-manager/gen-admission-secret.sh --service jobflow-webhook-service --namespace kube-system --secret jobflow-webhook-server-cert
-
-# restart jobflow-controller-manager
-kubectl delete pod/jobflow-controller-manager-67847d59dd-j8dmc -nkube-system
-```
-
-##### run jobflow example
+### run jobflow example
 ```bash
 # deploy jobTemplate first
-cd volcano
-kubectl apply -f example/jobflow/JobTemplate.yaml
+kubectl apply -f JobTemplate.yaml
 # deploy jobFlow second
-kubectl apply -f example/jobflow/JobFlow.yaml
+kubectl apply -f JobFlow.yaml
 
 # check them
 kubectl get jt

example/kubecon-2019-china/horovod-sample/lm-horovod-tf-mnist-v0.5.yaml

@@ -10,7 +10,7 @@ spec:
   plugins:
     ssh: []
     svc: []
-  # 如果有pod被 杀死，重启整个作业
+  # Restart the entire job if any pod is killed.
   policies:
     - event: PodEvicted
       action: RestartJob

go.mod

@@ -1,10 +1,11 @@
 module volcano.sh/volcano
 
-go 1.22.0
+go 1.23.0
 
 require (
+	github.com/AdaLogics/go-fuzz-headers v0.0.0-20240806141605-e8a1dd7889d6
 	github.com/agiledragon/gomonkey/v2 v2.11.0
-	github.com/cilium/ebpf v0.9.3
+	github.com/cilium/ebpf v0.16.0
 	github.com/containernetworking/cni v1.1.2
 	github.com/containernetworking/plugins v1.1.1
 	github.com/elastic/go-elasticsearch/v7 v7.17.7
@@ -15,9 +16,9 @@ require (
 	github.com/hashicorp/go-multierror v1.1.1
 	github.com/imdario/mergo v0.3.16
 	github.com/mitchellh/mapstructure v1.5.0
-	github.com/onsi/ginkgo/v2 v2.19.0
-	github.com/onsi/gomega v1.33.1
-	github.com/opencontainers/runc v1.1.13
+	github.com/onsi/ginkgo/v2 v2.21.0
+	github.com/onsi/gomega v1.35.1
+	github.com/opencontainers/runc v1.2.1
 	github.com/pkg/errors v0.9.1
 	github.com/prometheus/client_golang v1.19.1
 	github.com/prometheus/common v0.55.0
@@ -25,44 +26,64 @@ require (
 	github.com/spf13/cobra v1.8.1
 	github.com/spf13/pflag v1.0.5
 	github.com/stretchr/testify v1.9.0
-	github.com/vishvananda/netlink v1.1.1-0.20210330154013-f5de75959ad5
+	github.com/vishvananda/netlink v1.3.1-0.20240905180732-b1ce50cfa9be
 	go.uber.org/automaxprocs v1.5.1
-	golang.org/x/crypto v0.24.0
-	golang.org/x/sys v0.21.0
-	golang.org/x/time v0.3.0
+	golang.org/x/crypto v0.37.0
+	golang.org/x/sys v0.32.0
+	golang.org/x/time v0.7.0
 	gopkg.in/yaml.v2 v2.4.0
-	k8s.io/api v0.31.3
-	k8s.io/apimachinery v0.31.3
-	k8s.io/apiserver v0.31.3
-	k8s.io/client-go v0.31.3
-	k8s.io/code-generator v0.31.3
-	k8s.io/component-base v0.31.3
-	k8s.io/component-helpers v0.31.3
-	k8s.io/csi-translation-lib v0.31.3
+	k8s.io/api v0.32.2
+	k8s.io/apimachinery v0.32.2
+	k8s.io/apiserver v0.32.2
+	k8s.io/client-go v0.32.2
+	k8s.io/code-generator v0.32.2
+	k8s.io/component-base v0.32.2
+	k8s.io/component-helpers v0.32.2
+	k8s.io/csi-translation-lib v0.32.2
 	k8s.io/klog/v2 v2.130.1
-	k8s.io/kubernetes v1.31.3
-	k8s.io/metrics v0.0.0
-	k8s.io/utils v0.0.0-20240711033017-18e509b52bc8
+	k8s.io/kubectl v0.0.0
+	k8s.io/kubernetes v1.32.2
+	k8s.io/metrics v0.32.2
+	k8s.io/pod-security-admission v0.0.0
+	k8s.io/utils v0.0.0-20241104100929-3ea5e8cea738
 	sigs.k8s.io/controller-runtime v0.13.0
 	sigs.k8s.io/yaml v1.4.0
 	stathat.com/c/consistent v1.0.0
-	volcano.sh/apis v1.11.0-network-topology-preview.2
+	volcano.sh/apis v1.12.1
 )
 
 require (
-	github.com/Microsoft/go-winio v0.6.0 // indirect
+	cel.dev/expr v0.18.0 // indirect
+	github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161 // indirect
+	github.com/JeffAshton/win_pdh v0.0.0-20161109143554-76bb4ee9f0ab // indirect
+	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/antlr4-go/antlr/v4 v4.13.0 // indirect
-	github.com/bits-and-blooms/bitset v1.2.0 // indirect
-	github.com/cyphar/filepath-securejoin v0.2.4 // indirect
+	github.com/container-storage-interface/spec v1.9.0 // indirect
+	github.com/containerd/containerd/api v1.7.19 // indirect
+	github.com/containerd/errdefs v0.1.0 // indirect
+	github.com/containerd/log v0.1.0 // indirect
+	github.com/containerd/ttrpc v1.2.5 // indirect
+	github.com/cyphar/filepath-securejoin v0.3.4 // indirect
+	github.com/docker/go-units v0.5.0 // indirect
+	github.com/euank/go-kmsg-parser v2.0.0+incompatible // indirect
 	github.com/go-task/slim-sprig/v3 v3.0.0 // indirect
 	github.com/godbus/dbus/v5 v5.1.0 // indirect
-	github.com/opencontainers/runtime-spec v1.0.3-0.20220909204839-494a5a6aca78 // indirect
+	github.com/google/btree v1.0.1 // indirect
+	github.com/gorilla/websocket v1.5.0 // indirect
+	github.com/karrick/godirwalk v1.17.0 // indirect
+	github.com/mistifyio/go-zfs v2.1.2-0.20190413222219-f784269be439+incompatible // indirect
+	github.com/moby/spdystream v0.5.0 // indirect
+	github.com/moby/sys/userns v0.1.0 // indirect
+	github.com/moby/term v0.5.0 // indirect
+	github.com/mxk/go-flowrate v0.0.0-20140419014527-cca7078d478f // indirect
+	github.com/opencontainers/runtime-spec v1.2.0 // indirect
 	github.com/sirupsen/logrus v1.9.3 // indirect
 	github.com/vishvananda/netns v0.0.4 // indirect
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.53.0 // indirect
-	k8s.io/cri-api v0.31.3 // indirect
+	k8s.io/cri-api v0.32.2 // indirect
 	k8s.io/cri-client v0.0.0 // indirect
-	k8s.io/gengo/v2 v2.0.0-20240228010128-51d4e06bde70 // indirect
+	k8s.io/dynamic-resource-allocation v0.0.0 // indirect
+	k8s.io/gengo/v2 v2.0.0-20240911193312-2b36238f13e9 // indirect
 )
 
 require (
@@ -75,24 +96,23 @@ require (
 	github.com/coreos/go-semver v0.3.1 // indirect
 	github.com/coreos/go-systemd/v22 v22.5.0 // indirect
 	github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc // indirect
-	github.com/distribution/reference v0.5.0 // indirect
+	github.com/distribution/reference v0.6.0 // indirect
 	github.com/emicklei/go-restful/v3 v3.11.0 // indirect
 	github.com/evanphx/json-patch/v5 v5.6.0 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
 	github.com/fxamacker/cbor/v2 v2.7.0 // indirect
 	github.com/go-logr/logr v1.4.2 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
-	github.com/go-openapi/jsonpointer v0.19.6 // indirect
+	github.com/go-openapi/jsonpointer v0.21.0 // indirect
 	github.com/go-openapi/jsonreference v0.20.2 // indirect
-	github.com/go-openapi/swag v0.22.4 // indirect
+	github.com/go-openapi/swag v0.23.0 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
-	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
 	github.com/golang/protobuf v1.5.4 // indirect
-	github.com/google/cadvisor v0.49.0 // indirect
-	github.com/google/cel-go v0.20.1 // indirect
+	github.com/google/cadvisor v0.51.0 // indirect
+	github.com/google/cel-go v0.22.0 // indirect
 	github.com/google/gnostic-models v0.6.8 // indirect
 	github.com/google/gofuzz v1.2.0 // indirect
-	github.com/google/pprof v0.0.0-20240525223248-4bfdf5a9a2af // indirect
+	github.com/google/pprof v0.0.0-20241029153458-d1b30febd7db // indirect
 	github.com/google/uuid v1.6.0 // indirect
 	github.com/grpc-ecosystem/go-grpc-prometheus v1.2.0 // indirect
 	github.com/grpc-ecosystem/grpc-gateway/v2 v2.20.0 // indirect
@@ -101,20 +121,20 @@ require (
 	github.com/josharian/intern v1.0.0 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/mailru/easyjson v0.7.7 // indirect
-	github.com/moby/sys/mountinfo v0.7.1 // indirect
+	github.com/moby/sys/mountinfo v0.7.2 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 // indirect
 	github.com/opencontainers/go-digest v1.0.0 // indirect
-	github.com/opencontainers/selinux v1.11.0 // indirect
+	github.com/opencontainers/selinux v1.11.1 // indirect
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/prometheus/client_model v0.6.1 // indirect
 	github.com/prometheus/procfs v0.15.1 // indirect
-	github.com/stoewer/go-strcase v1.2.0 // indirect
+	github.com/stoewer/go-strcase v1.3.0 // indirect
 	github.com/x448/float16 v0.8.4 // indirect
-	go.etcd.io/etcd/api/v3 v3.5.14 // indirect
-	go.etcd.io/etcd/client/pkg/v3 v3.5.14 // indirect
-	go.etcd.io/etcd/client/v3 v3.5.14 // indirect
+	go.etcd.io/etcd/api/v3 v3.5.16 // indirect
+	go.etcd.io/etcd/client/pkg/v3 v3.5.16 // indirect
+	go.etcd.io/etcd/client/v3 v3.5.16 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.53.0 // indirect
 	go.opentelemetry.io/otel v1.28.0 // indirect
 	go.opentelemetry.io/otel/exporters/otlp/otlptrace v1.28.0 // indirect
@@ -124,70 +144,70 @@ require (
 	go.opentelemetry.io/otel/trace v1.28.0 // indirect
 	go.opentelemetry.io/proto/otlp v1.3.1 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
-	go.uber.org/zap v1.26.0 // indirect
-	golang.org/x/exp v0.0.0-20230515195305-f3d0a9c9a5cc // indirect
-	golang.org/x/mod v0.17.0 // indirect
-	golang.org/x/net v0.26.0 // indirect
-	golang.org/x/oauth2 v0.21.0 // indirect
-	golang.org/x/sync v0.7.0 // indirect
-	golang.org/x/term v0.21.0 // indirect
-	golang.org/x/text v0.16.0 // indirect
-	golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d // indirect
-	google.golang.org/genproto/googleapis/api v0.0.0-20240528184218-531527333157 // indirect
-	google.golang.org/genproto/googleapis/rpc v0.0.0-20240701130421-f6361c86f094 // indirect
+	go.uber.org/zap v1.27.0 // indirect
+	golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 // indirect
+	golang.org/x/mod v0.21.0 // indirect
+	golang.org/x/net v0.38.0 // indirect
+	golang.org/x/oauth2 v0.23.0 // indirect
+	golang.org/x/sync v0.13.0 // indirect
+	golang.org/x/term v0.31.0 // indirect
+	golang.org/x/text v0.24.0 // indirect
+	golang.org/x/tools v0.26.0 // indirect
+	google.golang.org/genproto/googleapis/api v0.0.0-20240826202546-f6391c0de4c7 // indirect
+	google.golang.org/genproto/googleapis/rpc v0.0.0-20240826202546-f6391c0de4c7 // indirect
 	google.golang.org/grpc v1.65.0 // indirect
-	google.golang.org/protobuf v1.34.2 // indirect
+	google.golang.org/protobuf v1.35.1 // indirect
 	gopkg.in/evanphx/json-patch.v4 v4.12.0 // indirect
 	gopkg.in/inf.v0 v0.9.1 // indirect
 	gopkg.in/natefinch/lumberjack.v2 v2.2.1 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
 	k8s.io/apiextensions-apiserver v0.25.0 // indirect
 	k8s.io/cloud-provider v0.0.0 // indirect
-	k8s.io/controller-manager v0.31.3
-	k8s.io/kms v0.31.3 // indirect
-	k8s.io/kube-openapi v0.0.0-20240228011516-70dd3763d340 // indirect
+	k8s.io/controller-manager v0.32.2
+	k8s.io/kms v0.32.2 // indirect
+	k8s.io/kube-openapi v0.0.0-20241105132330-32ad38e42d3f // indirect
 	k8s.io/kube-scheduler v0.0.0 // indirect
-	k8s.io/kubelet v0.0.0 // indirect
+	k8s.io/kubelet v0.32.2 // indirect
 	k8s.io/mount-utils v0.0.0 // indirect
-	sigs.k8s.io/apiserver-network-proxy/konnectivity-client v0.30.3 // indirect
-	sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd // indirect
-	sigs.k8s.io/structured-merge-diff/v4 v4.4.1 // indirect
+	sigs.k8s.io/apiserver-network-proxy/konnectivity-client v0.31.0 // indirect
+	sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3 // indirect
+	sigs.k8s.io/structured-merge-diff/v4 v4.4.2 // indirect
 )
 
 replace (
 	cloud.google.com/go => cloud.google.com/go v0.100.2
-	github.com/opencontainers/runc => github.com/opencontainers/runc v1.0.3
 	go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc => go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracegrpc v1.19.0
 	google.golang.org/grpc => google.golang.org/grpc v1.57.0
-	k8s.io/api => k8s.io/api v0.31.1
-	k8s.io/apiextensions-apiserver => k8s.io/apiextensions-apiserver v0.31.3
-	k8s.io/apimachinery => k8s.io/apimachinery v0.31.3
-	k8s.io/apiserver => k8s.io/apiserver v0.31.3
-	k8s.io/cli-runtime => k8s.io/cli-runtime v0.31.3
-	k8s.io/client-go => k8s.io/client-go v0.31.3
-	k8s.io/cloud-provider => k8s.io/cloud-provider v0.31.3
-	k8s.io/cluster-bootstrap => k8s.io/cluster-bootstrap v0.31.3
-	k8s.io/code-generator => k8s.io/code-generator v0.31.3
-	k8s.io/component-base => k8s.io/component-base v0.31.3
-	k8s.io/component-helpers => k8s.io/component-helpers v0.31.3
-	k8s.io/controller-manager => k8s.io/controller-manager v0.31.3
-	k8s.io/cri-api => k8s.io/cri-api v0.31.3
-	k8s.io/cri-client => k8s.io/cri-client v0.31.3
-	k8s.io/csi-translation-lib => k8s.io/csi-translation-lib v0.31.3
-	k8s.io/dynamic-resource-allocation => k8s.io/dynamic-resource-allocation v0.31.3
-	k8s.io/endpointslice => k8s.io/endpointslice v0.31.3
-	k8s.io/kube-aggregator => k8s.io/kube-aggregator v0.31.3
-	k8s.io/kube-controller-manager => k8s.io/kube-controller-manager v0.31.3
-	k8s.io/kube-proxy => k8s.io/kube-proxy v0.31.3
-	k8s.io/kube-scheduler => k8s.io/kube-scheduler v0.31.3
-	k8s.io/kubectl => k8s.io/kubectl v0.31.3
-	k8s.io/kubelet => k8s.io/kubelet v0.31.3
-	k8s.io/legacy-cloud-providers => k8s.io/legacy-cloud-providers v0.31.3
-	k8s.io/metrics => k8s.io/metrics v0.31.3
-	k8s.io/mount-utils => k8s.io/mount-utils v0.31.3
-	k8s.io/node-api => k8s.io/node-api v0.31.3
-	k8s.io/pod-security-admission => k8s.io/pod-security-admission v0.31.3
-	k8s.io/sample-apiserver => k8s.io/sample-apiserver v0.31.3
-	k8s.io/sample-cli-plugin => k8s.io/sample-cli-plugin v0.31.3
-	k8s.io/sample-controller => k8s.io/sample-controller v0.31.3
+	k8s.io/api => k8s.io/api v0.32.2
+	k8s.io/apiextensions-apiserver => k8s.io/apiextensions-apiserver v0.32.2
+	k8s.io/apimachinery => k8s.io/apimachinery v0.32.2
+	k8s.io/apiserver => k8s.io/apiserver v0.32.2
+	k8s.io/cli-runtime => k8s.io/cli-runtime v0.32.2
+	k8s.io/client-go => k8s.io/client-go v0.32.2
+	k8s.io/cloud-provider => k8s.io/cloud-provider v0.32.2
+	k8s.io/cluster-bootstrap => k8s.io/cluster-bootstrap v0.32.2
+	k8s.io/code-generator => k8s.io/code-generator v0.32.2
+	k8s.io/component-base => k8s.io/component-base v0.32.2
+	k8s.io/component-helpers => k8s.io/component-helpers v0.32.2
+	k8s.io/controller-manager => k8s.io/controller-manager v0.32.2
+	k8s.io/cri-api => k8s.io/cri-api v0.32.2
+	k8s.io/cri-client => k8s.io/cri-client v0.32.2
+	k8s.io/csi-translation-lib => k8s.io/csi-translation-lib v0.32.2
+	k8s.io/dynamic-resource-allocation => k8s.io/dynamic-resource-allocation v0.32.2
+	k8s.io/endpointslice => k8s.io/endpointslice v0.32.2
+	k8s.io/externaljwt => k8s.io/externaljwt v0.32.2
+	k8s.io/kube-aggregator => k8s.io/kube-aggregator v0.32.2
+	k8s.io/kube-controller-manager => k8s.io/kube-controller-manager v0.32.2
+	k8s.io/kube-proxy => k8s.io/kube-proxy v0.32.2
+	k8s.io/kube-scheduler => k8s.io/kube-scheduler v0.32.2
+	k8s.io/kubectl => k8s.io/kubectl v0.32.2
+	k8s.io/kubelet => k8s.io/kubelet v0.32.2
+	k8s.io/legacy-cloud-providers => k8s.io/legacy-cloud-providers v0.32.2
+	k8s.io/metrics => k8s.io/metrics v0.32.2
+	k8s.io/mount-utils => k8s.io/mount-utils v0.32.2
+	k8s.io/node-api => k8s.io/node-api v0.32.2
+	k8s.io/pod-security-admission => k8s.io/pod-security-admission v0.32.2
+	k8s.io/sample-apiserver => k8s.io/sample-apiserver v0.32.2
+	k8s.io/sample-cli-plugin => k8s.io/sample-cli-plugin v0.32.2
+	k8s.io/sample-controller => k8s.io/sample-controller v0.32.2
 )

go.sum

@@ -1,67 +1,86 @@
-github.com/BurntSushi/toml v0.3.1/go.mod h1:xHWCNGjB5oqiDr8zfno3MHue2Ht5sIBksp03qcyfWMU=
-github.com/Microsoft/go-winio v0.6.0 h1:slsWYD/zyx7lCXoZVlvQrj0hPTM1HI4+v1sIda2yDvg=
-github.com/Microsoft/go-winio v0.6.0/go.mod h1:cTAf44im0RAYeL23bpB+fzCyDH2MJiz2BO69KH/soAE=
+cel.dev/expr v0.18.0 h1:CJ6drgk+Hf96lkLikr4rFf19WrU0BOWEihyZnI2TAzo=
+cel.dev/expr v0.18.0/go.mod h1:MrpN08Q+lEBs+bGYdLxxHkZoUSsCp0nSKTs0nTymJgw=
+github.com/AdaLogics/go-fuzz-headers v0.0.0-20240806141605-e8a1dd7889d6 h1:He8afgbRMd7mFxO99hRNu+6tazq8nFF9lIwo9JFroBk=
+github.com/AdaLogics/go-fuzz-headers v0.0.0-20240806141605-e8a1dd7889d6/go.mod h1:8o94RPi1/7XTJvwPpRSzSUedZrtlirdB3r9Z20bi2f8=
+github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161 h1:L/gRVlceqvL25UVaW/CKtUDjefjrs0SPonmDGUVOYP0=
+github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161/go.mod h1:xomTg63KZ2rFqZQzSB4Vz2SUXa1BpHTVz9L5PTmPC4E=
+github.com/JeffAshton/win_pdh v0.0.0-20161109143554-76bb4ee9f0ab h1:UKkYhof1njT1/xq4SEg5z+VpTgjmNeHwPGRQl7takDI=
+github.com/JeffAshton/win_pdh v0.0.0-20161109143554-76bb4ee9f0ab/go.mod h1:3VYc5hodBMJ5+l/7J4xAyMeuM2PNuepvHlGs8yilUCA=
+github.com/Microsoft/go-winio v0.6.2 h1:F2VQgta7ecxGYO8k3ZZz3RS8fVIXVxONVUPlNERoyfY=
+github.com/Microsoft/go-winio v0.6.2/go.mod h1:yd8OoFMLzJbo9gZq8j5qaps8bJ9aShtEA8Ipt1oGCvU=
 github.com/NYTimes/gziphandler v1.1.1 h1:ZUDjpQae29j0ryrS0u/B8HZfJBtBQHjqw2rQ2cqUQ3I=
 github.com/NYTimes/gziphandler v1.1.1/go.mod h1:n/CVRwUEOgIxrgPvAQhUUr9oeUtvrhMomdKFjzJNB0c=
 github.com/agiledragon/gomonkey/v2 v2.11.0 h1:5oxSgA+tC1xuGsrIorR+sYiziYltmJyEZ9qA25b6l5U=
 github.com/agiledragon/gomonkey/v2 v2.11.0/go.mod h1:ap1AmDzcVOAz1YpeJ3TCzIgstoaWLA6jbbgxfB4w2iY=
 github.com/antlr4-go/antlr/v4 v4.13.0 h1:lxCg3LAv+EUK6t1i0y1V6/SLeUi0eKEKdhQAlS8TVTI=
 github.com/antlr4-go/antlr/v4 v4.13.0/go.mod h1:pfChB/xh/Unjila75QW7+VU4TSnWnnk9UTnmpPaOR2g=
+github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5 h1:0CwZNZbxp69SHPdPJAN/hZIm0C4OItdklCFmMRWYpio=
+github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5/go.mod h1:wHh0iHkYZB8zMSxRWpUBQtwG5a7fFgvEO+odwuTv2gs=
 github.com/asaskevich/govalidator v0.0.0-20230301143203-a9d515a09cc2 h1:DklsrG3dyBCFEj5IhUbnKptjxatkF07cF2ak3yi77so=
 github.com/asaskevich/govalidator v0.0.0-20230301143203-a9d515a09cc2/go.mod h1:WaHUgvxTVq04UNunO+XhnAqY/wQc+bxr74GqbsZ/Jqw=
 github.com/beorn7/perks v1.0.1 h1:VlbKKnNfV8bJzeqoa4cOKqO6bYr3WgKZxO8Z16+hsOM=
 github.com/beorn7/perks v1.0.1/go.mod h1:G2ZrVWU2WbWT9wwq4/hrbKbnv/1ERSJQ0ibhJ6rlkpw=
-github.com/bits-and-blooms/bitset v1.2.0 h1:Kn4yilvwNtMACtf1eYDlG8H77R07mZSPbMjLyS07ChA=
-github.com/bits-and-blooms/bitset v1.2.0/go.mod h1:gIdJ4wp64HaoK2YrL1Q5/N7Y16edYb8uY+O0FJTyyDA=
 github.com/blang/semver/v4 v4.0.0 h1:1PFHFE6yCCTv8C1TeyNNarDzntLi7wMI5i/pzqYIsAM=
 github.com/blang/semver/v4 v4.0.0/go.mod h1:IbckMUScFkM3pff0VJDNKRiT6TG/YpiHIM2yvyW5YoQ=
 github.com/cenkalti/backoff/v4 v4.3.0 h1:MyRJ/UdXutAwSAT+s3wNd7MfTIcy71VQueUuFK343L8=
 github.com/cenkalti/backoff/v4 v4.3.0/go.mod h1:Y3VNntkOUPxTVeUxJ/G5vcM//AlwfmyYozVcomhLiZE=
 github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
 github.com/cespare/xxhash/v2 v2.3.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
-github.com/checkpoint-restore/go-criu/v5 v5.0.0/go.mod h1:cfwC0EG7HMUenopBsUf9d89JlCLQIfgVcNsNN0t6T2M=
 github.com/chzyer/logex v1.1.10/go.mod h1:+Ywpsq7O8HXn0nuIou7OrIPyXbp3wmkHB+jjWRnGsAI=
 github.com/chzyer/readline v0.0.0-20180603132655-2972be24d48e/go.mod h1:nSuG5e5PlCu98SY8svDHJxuZscDgtXS6KTTbou5AhLI=
 github.com/chzyer/test v0.0.0-20180213035817-a1ea475d72b1/go.mod h1:Q3SI9o4m/ZMnBNeIyt5eFwwo7qiLfzFZmjNmxjkiQlU=
-github.com/cilium/ebpf v0.6.2/go.mod h1:4tRaxcgiL706VnOzHOdBlY8IEAIdxINsQBcU4xJJXRs=
-github.com/cilium/ebpf v0.9.3 h1:5KtxXZU+scyERvkJMEm16TbScVvuuMrlhPly78ZMbSc=
-github.com/cilium/ebpf v0.9.3/go.mod h1:w27N4UjpaQ9X/DGrSugxUG+H+NhgntDuPb5lCzxCn8A=
-github.com/containerd/console v1.0.2/go.mod h1:ytZPjGgY2oeTkAONYafi2kSj0aYggsf8acV1PGKCbzQ=
+github.com/cilium/ebpf v0.16.0 h1:+BiEnHL6Z7lXnlGUsXQPPAE7+kenAd4ES8MQ5min0Ok=
+github.com/cilium/ebpf v0.16.0/go.mod h1:L7u2Blt2jMM/vLAVgjxluxtBKlz3/GWjB0dMOEngfwE=
+github.com/container-storage-interface/spec v1.9.0 h1:zKtX4STsq31Knz3gciCYCi1SXtO2HJDecIjDVboYavY=
+github.com/container-storage-interface/spec v1.9.0/go.mod h1:ZfDu+3ZRyeVqxZM0Ds19MVLkN2d1XJ5MAfi1L3VjlT0=
+github.com/containerd/containerd/api v1.7.19 h1:VWbJL+8Ap4Ju2mx9c9qS1uFSB1OVYr5JJrW2yT5vFoA=
+github.com/containerd/containerd/api v1.7.19/go.mod h1:fwGavl3LNwAV5ilJ0sbrABL44AQxmNjDRcwheXDb6Ig=
+github.com/containerd/errdefs v0.1.0 h1:m0wCRBiu1WJT/Fr+iOoQHMQS/eP5myQ8lCv4Dz5ZURM=
+github.com/containerd/errdefs v0.1.0/go.mod h1:YgWiiHtLmSeBrvpw+UfPijzbLaB77mEG1WwJTDETIV0=
+github.com/containerd/log v0.1.0 h1:TCJt7ioM2cr/tfR8GPbGf9/VRAX8D2B4PjzCpfX540I=
+github.com/containerd/log v0.1.0/go.mod h1:VRRf09a7mHDIRezVKTRCrOq78v577GXq3bSa3EhrzVo=
+github.com/containerd/ttrpc v1.2.5 h1:IFckT1EFQoFBMG4c3sMdT8EP3/aKfumK1msY+Ze4oLU=
+github.com/containerd/ttrpc v1.2.5/go.mod h1:YCXHsb32f+Sq5/72xHubdiJRQY9inL4a4ZQrAbN1q9o=
+github.com/containerd/typeurl/v2 v2.2.0 h1:6NBDbQzr7I5LHgp34xAXYF5DOTQDn05X58lsPEmzLso=
+github.com/containerd/typeurl/v2 v2.2.0/go.mod h1:8XOOxnyatxSWuG8OfsZXVnAF4iZfedjS/8UHSPJnX4g=
 github.com/containernetworking/cni v1.1.2 h1:wtRGZVv7olUHMOqouPpn3cXJWpJgM6+EUl31EQbXALQ=
 github.com/containernetworking/cni v1.1.2/go.mod h1:sDpYKmGVENF3s6uvMvGgldDWeG8dMxakj/u+i9ht9vw=
 github.com/containernetworking/plugins v1.1.1 h1:+AGfFigZ5TiQH00vhR8qPeSatj53eNGz0C1d3wVYlHE=
 github.com/containernetworking/plugins v1.1.1/go.mod h1:Sr5TH/eBsGLXK/h71HeLfX19sZPp3ry5uHSkI4LPxV8=
 github.com/coreos/go-semver v0.3.1 h1:yi21YpKnrx1gt5R+la8n5WgS0kCrsPp33dmEyHReZr4=
 github.com/coreos/go-semver v0.3.1/go.mod h1:irMmmIw/7yzSRPWryHsK7EYSg09caPQL03VsM8rvUec=
-github.com/coreos/go-systemd/v22 v22.3.2/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
 github.com/coreos/go-systemd/v22 v22.5.0 h1:RrqgGjYQKalulkV8NGVIfkXQf6YYmOyiJKk8iXXhfZs=
 github.com/coreos/go-systemd/v22 v22.5.0/go.mod h1:Y58oyj3AT4RCenI/lSvhwexgC+NSVTIJ3seZv2GcEnc=
-github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
 github.com/cpuguy83/go-md2man/v2 v2.0.4/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
-github.com/cyphar/filepath-securejoin v0.2.2/go.mod h1:FpkQEhXnPnOthhzymB7CGsFk2G9VLXONKD9G7QGMM+4=
-github.com/cyphar/filepath-securejoin v0.2.4 h1:Ugdm7cg7i6ZK6x3xDF1oEu1nfkyfH53EtKeQYTC3kyg=
-github.com/cyphar/filepath-securejoin v0.2.4/go.mod h1:aPGpWjXOXUn2NCNjFvBE6aRxGGx79pTxQpKOJNYHHl4=
+github.com/creack/pty v1.1.18 h1:n56/Zwd5o6whRC5PMGretI4IdRLlmBXYNjScPaBgsbY=
+github.com/creack/pty v1.1.18/go.mod h1:MOBLtS5ELjhRRrroQr9kyvTxUAFNvYEK993ew/Vr4O4=
+github.com/cyphar/filepath-securejoin v0.3.4 h1:VBWugsJh2ZxJmLFSM06/0qzQyiQX2Qs0ViKrUAcqdZ8=
+github.com/cyphar/filepath-securejoin v0.3.4/go.mod h1:8s/MCNJREmFK0H02MF6Ihv1nakJe4L/w3WZLHNkvlYM=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc h1:U9qPSI2PIWSS1VwoXQT9A3Wy9MM3WgvqSxFWenqJduM=
 github.com/davecgh/go-spew v1.1.2-0.20180830191138-d8f796af33cc/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
-github.com/distribution/reference v0.5.0 h1:/FUIFXtfc/x2gpa5/VGfiGLuOIdYa1t65IKK2OFGvA0=
-github.com/distribution/reference v0.5.0/go.mod h1:BbU0aIcezP1/5jX/8MP0YiH4SdvB5Y4f/wlDRiLyi3E=
-github.com/docker/go-units v0.4.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
+github.com/distribution/reference v0.6.0 h1:0IXCQ5g4/QMHHkarYzh5l+u8T3t73zM5QvfrDyIgxBk=
+github.com/distribution/reference v0.6.0/go.mod h1:BbU0aIcezP1/5jX/8MP0YiH4SdvB5Y4f/wlDRiLyi3E=
+github.com/docker/docker v26.1.4+incompatible h1:vuTpXDuoga+Z38m1OZHzl7NKisKWaWlhjQk7IDPSLsU=
+github.com/docker/docker v26.1.4+incompatible/go.mod h1:eEKB0N0r5NX/I1kEveEz05bcu8tLC/8azJZsviup8Sk=
+github.com/docker/go-connections v0.5.0 h1:USnMq7hx7gwdVZq1L49hLXaFtUdTADjXGp+uj1Br63c=
+github.com/docker/go-connections v0.5.0/go.mod h1:ov60Kzw0kKElRwhNs9UlUHAE/F9Fe6GLaXnqyDdmEXc=
+github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4=
+github.com/docker/go-units v0.5.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
 github.com/dustin/go-humanize v1.0.1 h1:GzkhY7T5VNhEkwH0PVJgjz+fX1rhBrR7pRT3mDkpeCY=
 github.com/dustin/go-humanize v1.0.1/go.mod h1:Mu1zIs6XwVuF/gI1OepvI0qD18qycQx+mFykh5fBlto=
 github.com/elastic/go-elasticsearch/v7 v7.17.7 h1:pcYNfITNPusl+cLwLN6OLmVT+F73Els0nbaWOmYachs=
 github.com/elastic/go-elasticsearch/v7 v7.17.7/go.mod h1:OJ4wdbtDNk5g503kvlHLyErCgQwwzmDtaFC4XyOxXA4=
 github.com/emicklei/go-restful/v3 v3.11.0 h1:rAQeMHw1c7zTmncogyy8VvRZwtkmkZ4FxERmMY4rD+g=
 github.com/emicklei/go-restful/v3 v3.11.0/go.mod h1:6n3XBCmQQb25CM2LCACGz8ukIrRry+4bhvbpWn3mrbc=
+github.com/euank/go-kmsg-parser v2.0.0+incompatible h1:cHD53+PLQuuQyLZeriD1V/esuG4MuU0Pjs5y6iknohY=
+github.com/euank/go-kmsg-parser v2.0.0+incompatible/go.mod h1:MhmAMZ8V4CYH4ybgdRwPr2TU5ThnS43puaKEMpja1uw=
 github.com/evanphx/json-patch/v5 v5.6.0 h1:b91NhWfaz02IuVxO9faSllyAtNXHMPkC5J8sJCLunww=
 github.com/evanphx/json-patch/v5 v5.6.0/go.mod h1:G79N1coSVB93tBe7j6PhzjmR3/2VvlbKOFpnXhI9Bw4=
 github.com/felixge/httpsnoop v1.0.4 h1:NFTV2Zj1bL4mc9sqWACXbQFVBBg2W3GPvqp8/ESS2Wg=
 github.com/felixge/httpsnoop v1.0.4/go.mod h1:m8KPJKqk1gH5J9DgRY2ASl2lWCfGKXixSwevea8zH2U=
-github.com/frankban/quicktest v1.11.3/go.mod h1:wRf/ReqHper53s+kmmSZizM8NamnL3IM0I9ntUbOk+k=
-github.com/frankban/quicktest v1.14.0 h1:+cqqvzZV87b4adx/5ayVOaYZ2CrvM4ejQvUdBzPPUss=
-github.com/frankban/quicktest v1.14.0/go.mod h1:NeW+ay9A/U67EYXNFA1nPE8e/tnQv/09mUdL/ijj8og=
 github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
 github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/fsnotify/fsnotify v1.7.0 h1:8JEhPFa5W2WU7YfeZzPNqzMP6Lwt7L2715Ggo0nosvA=
@@ -75,13 +94,16 @@ github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
 github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
 github.com/go-logr/zapr v1.3.0 h1:XGdV8XW8zdwFiwOA2Dryh1gj2KRQyOOoNmBy4EplIcQ=
 github.com/go-logr/zapr v1.3.0/go.mod h1:YKepepNBd1u/oyhd/yQmtjVXmm9uML4IXUgMOwR8/Gg=
-github.com/go-openapi/jsonpointer v0.19.6 h1:eCs3fxoIi3Wh6vtgmLTOjdhSpiqphQ+DaPn38N2ZdrE=
 github.com/go-openapi/jsonpointer v0.19.6/go.mod h1:osyAmYz/mB/C3I+WsTTSgw1ONzaLJoLCyoi6/zppojs=
+github.com/go-openapi/jsonpointer v0.21.0 h1:YgdVicSA9vH5RiHs9TZW5oyafXZFc6+2Vc1rr/O9oNQ=
+github.com/go-openapi/jsonpointer v0.21.0/go.mod h1:IUyH9l/+uyhIYQ/PXVA41Rexl+kOkAPDdXEYns6fzUY=
 github.com/go-openapi/jsonreference v0.20.2 h1:3sVjiK66+uXK/6oQ8xgcRKcFgQ5KXa2KvnJRumpMGbE=
 github.com/go-openapi/jsonreference v0.20.2/go.mod h1:Bl1zwGIM8/wsvqjsOQLJ/SH+En5Ap4rVB5KVcIDZG2k=
 github.com/go-openapi/swag v0.22.3/go.mod h1:UzaqsxGiab7freDnrUUra0MwWfN/q7tE4j+VcZ0yl14=
-github.com/go-openapi/swag v0.22.4 h1:QLMzNJnMGPRNDCbySlcj1x01tzU8/9LTTL9hZZZogBU=
-github.com/go-openapi/swag v0.22.4/go.mod h1:UzaqsxGiab7freDnrUUra0MwWfN/q7tE4j+VcZ0yl14=
+github.com/go-openapi/swag v0.23.0 h1:vsEVJDUo2hPJ2tu0/Xc+4noaxyEffXNIs3cOULZ+GrE=
+github.com/go-openapi/swag v0.23.0/go.mod h1:esZ8ITTYEsH1V2trKHjAN8Ai7xHb8RV+YSZ577vPjgQ=
+github.com/go-quicktest/qt v1.101.0 h1:O1K29Txy5P2OK0dGo59b7b0LR6wKfIhttaAhHUyn7eI=
+github.com/go-quicktest/qt v1.101.0/go.mod h1:14Bz/f7NwaXPtdYEgzsx46kqSxVwTbzVZsDC26tQJow=
 github.com/go-task/slim-sprig v0.0.0-20210107165309-348f09dbbbc0/go.mod h1:fyg7847qk6SyHyPtNmDHnmrv/HOrqktSC+C9fM+CJOE=
 github.com/go-task/slim-sprig/v3 v3.0.0 h1:sUs3vkvUymDpBKi3qH1YSqBQk9+9D/8M2mN1vB6EwHI=
 github.com/go-task/slim-sprig/v3 v3.0.0/go.mod h1:W848ghGpv3Qj3dhTPRyJypKRiqCdHZiAzKg9hl15HA8=
@@ -92,8 +114,6 @@ github.com/gogo/protobuf v1.3.2 h1:Ov1cvc58UF3b5XjBnZv7+opcTcQFZebYjWzi34vdm4Q=
 github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69NZV8Q=
 github.com/golang-jwt/jwt/v4 v4.5.0 h1:7cYmW1XlMY7h7ii7UhUyChSgS5wUJEnm9uZVTGqOWzg=
 github.com/golang-jwt/jwt/v4 v4.5.0/go.mod h1:m21LjoU+eqJr34lmDMbreY2eSTRJ1cv77w39/MY0Ch0=
-github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da h1:oI5xCqsCo564l8iNU+DwB5epxmsaqB+rhGL0m5jtYqE=
-github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da/go.mod h1:cIg4eruTrX1D+g88fzRXU5OdNfaM+9IcxsU14FzY7Hc=
 github.com/golang/mock v1.6.0 h1:ErTB+efbowRARo13NNdxyJji2egdxLGQhRaY+DUumQc=
 github.com/golang/mock v1.6.0/go.mod h1:p6yTPP+5HYm5mzsMV8JkE6ZKdX+/wYM6Hr+LicevLPs=
 github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
@@ -103,23 +123,21 @@ github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrU
 github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
 github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
 github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
-github.com/golang/protobuf v1.4.3/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
 github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
 github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
 github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
 github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
 github.com/google/btree v1.0.1 h1:gK4Kx5IaGY9CD5sPJ36FHiBJ6ZXl0kilRiiCj+jdYp4=
 github.com/google/btree v1.0.1/go.mod h1:xXMiIv4Fb/0kKde4SpL7qlzvu5cMJDRkFDxJfI9uaxA=
-github.com/google/cadvisor v0.49.0 h1:1PYeiORXmcFYi609M4Qvq5IzcvcVaWgYxDt78uH8jYA=
-github.com/google/cadvisor v0.49.0/go.mod h1:s6Fqwb2KiWG6leCegVhw4KW40tf9f7m+SF1aXiE8Wsk=
-github.com/google/cel-go v0.20.1 h1:nDx9r8S3L4pE61eDdt8igGj8rf5kjYR3ILxWIpWNi84=
-github.com/google/cel-go v0.20.1/go.mod h1:kWcIzTsPX0zmQ+H3TirHstLLf9ep5QTsZBN9u4dOYLg=
+github.com/google/cadvisor v0.51.0 h1:BspqSPdZoLKrnvuZNOvM/KiJ/A+RdixwagN20n+2H8k=
+github.com/google/cadvisor v0.51.0/go.mod h1:czGE/c/P/i0QFpVNKTFrIEzord9Y10YfpwuaSWXELc0=
+github.com/google/cel-go v0.22.0 h1:b3FJZxpiv1vTMo2/5RDUqAHPxkT8mmMfJIrq1llbf7g=
+github.com/google/cel-go v0.22.0/go.mod h1:BuznPXXfQDpXKWQ9sPW3TzlAJN5zzFe+i9tIs0yC4s8=
 github.com/google/gnostic-models v0.6.8 h1:yo/ABAfM5IMRsS1VnXjTBvUb61tFIHozhlYvRgGre9I=
 github.com/google/gnostic-models v0.6.8/go.mod h1:5n7qKqH0f5wFt+aWF8CW6pZLLNOfYuF5OpfBSENuI8U=
 github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
 github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
 github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.4/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
@@ -128,8 +146,8 @@ github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/
 github.com/google/gofuzz v1.2.0 h1:xRy4A+RhZaiKjJ1bPfwQ8sedCA+YS2YcCHW6ec7JMi0=
 github.com/google/gofuzz v1.2.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/pprof v0.0.0-20210407192527-94a9f03dee38/go.mod h1:kpwsk12EmLew5upagYY7GY0pfYCcupk39gWOCRROcvE=
-github.com/google/pprof v0.0.0-20240525223248-4bfdf5a9a2af h1:kmjWCqn2qkEml422C2Rrd27c3VGxi6a/6HNq8QmHRKM=
-github.com/google/pprof v0.0.0-20240525223248-4bfdf5a9a2af/go.mod h1:K1liHPHnj73Fdn/EKuT8nrFqBihUSKXoLYU0BuatOYo=
+github.com/google/pprof v0.0.0-20241029153458-d1b30febd7db h1:097atOisP2aRj7vFgYQBbFN4U4JNXUNYpxael3UzMyo=
+github.com/google/pprof v0.0.0-20241029153458-d1b30febd7db/go.mod h1:vavhavw2zAxS5dIdcRluK6cSGGPlZynqzFM8NdvU144=
 github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 h1:El6M4kTTCOh6aBiKaUGG7oYTSPP8MxqL4YI3kZKwcP4=
 github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510/go.mod h1:pupxD2MaaD3pAXIBCelhxNneeOaAeabZDe5s4K6zSpQ=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
@@ -157,8 +175,8 @@ github.com/imdario/mergo v0.3.16/go.mod h1:WBLT9ZmE3lPoWsEzCh9LPo3TiwVN+ZKEjmz+h
 github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
 github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
 github.com/jessevdk/go-flags v1.4.0/go.mod h1:4FA24M0QyGHXBuZZK/XkWh8h0e1EYbRYJSGM75WSRxI=
-github.com/jonboulle/clockwork v0.2.2 h1:UOGuzwb1PwsrDAObMuhUnj0p5ULPj8V/xJ7Kx9qUBdQ=
-github.com/jonboulle/clockwork v0.2.2/go.mod h1:Pkfl5aHPm1nk2H9h0bjmnJD/BcgbGXUBGnn1kMkgxc8=
+github.com/jonboulle/clockwork v0.4.0 h1:p4Cf1aMWXnXAUh8lVfewRBx1zaTSYKrKMF2g3ST4RZ4=
+github.com/jonboulle/clockwork v0.4.0/go.mod h1:xgRqUGwRcjKCO1vbZUEtSLrqKoPSsUpK7fnezOII0kc=
 github.com/josharian/intern v1.0.0 h1:vlS4z54oSdjm0bgjRigI+G1HpF+tI+9rE5LLzOg8HmY=
 github.com/josharian/intern v1.0.0/go.mod h1:5DoeVV0s6jJacbCEi61lwdGj/aVlrQvzHFFd8Hwg//Y=
 github.com/jpillora/backoff v1.0.0 h1:uvFg412JmmHBHw7iwprIxkPMI+sGQ4kzOWsMeHnm2EA=
@@ -166,6 +184,8 @@ github.com/jpillora/backoff v1.0.0/go.mod h1:J/6gKK9jxlEcS3zixgDgUAsiuZ7yrSoa/FX
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
 github.com/json-iterator/go v1.1.12/go.mod h1:e30LSqwooZae/UwlEbR2852Gd8hjQvJoHmT4TnhNGBo=
 github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
+github.com/karrick/godirwalk v1.17.0 h1:b4kY7nqDdioR/6qnbHQyDvmA17u5G1cZ6J+CZXwSWoI=
+github.com/karrick/godirwalk v1.17.0/go.mod h1:j4mkqPuvaLI8mp1DroR3P6ad7cyYd4c1qeJ3RV7ULlk=
 github.com/kisielk/errcheck v1.5.0/go.mod h1:pFxgyoBC7bSaBwPgfKdkLd5X25qrDl4LWUI2bnpBCr8=
 github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
@@ -177,21 +197,31 @@ github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
 github.com/mailru/easyjson v0.7.7 h1:UGYAvKxe3sBsEDzO8ZeWOSlIQfWFlxbzLZe7hwFURr0=
 github.com/mailru/easyjson v0.7.7/go.mod h1:xzfreul335JAWq5oZzymOObrkdz5UnU4kGfJJLY9Nlc=
+github.com/mistifyio/go-zfs v2.1.2-0.20190413222219-f784269be439+incompatible h1:aKW/4cBs+yK6gpqU3K/oIwk9Q/XICqd3zOX/UFuvqmk=
+github.com/mistifyio/go-zfs v2.1.2-0.20190413222219-f784269be439+incompatible/go.mod h1:8AuVvqP/mXw1px98n46wfvcGfQ4ci2FwoAjKYxuo3Z4=
 github.com/mitchellh/mapstructure v1.5.0 h1:jeMsZIYE/09sWLaz43PL7Gy6RuMjD2eJVyuac5Z2hdY=
 github.com/mitchellh/mapstructure v1.5.0/go.mod h1:bFUtVrKA4DC2yAKiSyO/QUcy7e+RRV2QTWOzhPopBRo=
-github.com/moby/sys/mountinfo v0.4.1/go.mod h1:rEr8tzG/lsIZHBtN/JjGG+LMYx9eXgW2JI+6q0qou+A=
-github.com/moby/sys/mountinfo v0.7.1 h1:/tTvQaSJRr2FshkhXiIpux6fQ2Zvc4j7tAhMTStAG2g=
-github.com/moby/sys/mountinfo v0.7.1/go.mod h1:IJb6JQeOklcdMU9F5xQ8ZALD+CUr5VlGpwtX+VE0rpI=
+github.com/moby/docker-image-spec v1.3.1 h1:jMKff3w6PgbfSa69GfNg+zN/XLhfXJGnEx3Nl2EsFP0=
+github.com/moby/docker-image-spec v1.3.1/go.mod h1:eKmb5VW8vQEh/BAr2yvVNvuiJuY6UIocYsFu/DxxRpo=
+github.com/moby/spdystream v0.5.0 h1:7r0J1Si3QO/kjRitvSLVVFUjxMEb/YLj6S9FF62JBCU=
+github.com/moby/spdystream v0.5.0/go.mod h1:xBAYlnt/ay+11ShkdFKNAG7LsyK/tmNBVvVOwrfMgdI=
+github.com/moby/sys/mountinfo v0.7.2 h1:1shs6aH5s4o5H2zQLn796ADW1wMrIwHsyJ2v9KouLrg=
+github.com/moby/sys/mountinfo v0.7.2/go.mod h1:1YOa8w8Ih7uW0wALDUgT1dTTSBrZ+HiBLGws92L2RU4=
+github.com/moby/sys/userns v0.1.0 h1:tVLXkFOxVu9A64/yh59slHVv9ahO9UIev4JZusOLG/g=
+github.com/moby/sys/userns v0.1.0/go.mod h1:IHUYgu/kao6N8YZlp9Cf444ySSvCmDlmzUcYfDHOl28=
+github.com/moby/term v0.5.0 h1:xt8Q1nalod/v7BqbG21f8mQPqH+xAaC9C3N3wfWbVP0=
+github.com/moby/term v0.5.0/go.mod h1:8FzsFHVUBGZdbDsJw/ot+X+d5HLUbvklYLJ9uGfcI3Y=
 github.com/modern-go/concurrent v0.0.0-20180228061459-e0a39a4cb421/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd h1:TRLaZ9cD/w8PVh93nsPXa1VrQ6jlwL5oN8l14QlcNfg=
 github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd/go.mod h1:6dJC0mAP4ikYIbvyc7fijjWJddQyLn8Ig3JB5CqoB9Q=
 github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9Gz0M=
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
-github.com/mrunalp/fileutils v0.5.0/go.mod h1:M1WthSahJixYnrXQl/DFQuteStB1weuxD2QJNHXfbSQ=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822 h1:C3w9PqII01/Oq1c1nUAm88MOHcQC9l5mIlSMApZMrHA=
 github.com/munnerz/goautoneg v0.0.0-20191010083416-a7dc8b61c822/go.mod h1:+n7T8mK8HuQTcFwEeznm/DIxMOiR9yIdICNftLE1DvQ=
 github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f h1:KUppIJq7/+SVif2QVs3tOP0zanoHgBEVAwHxUSIzRqU=
 github.com/mwitkow/go-conntrack v0.0.0-20190716064945-2f068394615f/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
+github.com/mxk/go-flowrate v0.0.0-20140419014527-cca7078d478f h1:y5//uYreIhSUg3J1GEMiLbxo1LJaP8RfCpH6pymGZus=
+github.com/mxk/go-flowrate v0.0.0-20140419014527-cca7078d478f/go.mod h1:ZdcZmHo+o7JKHSa8/e818NopupXU1YMK5fe1lsApnBw=
 github.com/nxadm/tail v1.4.4/go.mod h1:kenIhsEOeOJmVchQTgglprH7qJGnHDVpk1VPCcaMI8A=
 github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
 github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
@@ -201,23 +231,23 @@ github.com/onsi/ginkgo v1.16.4/go.mod h1:dX+/inL/fNMqNlz0e9LfyB9TswhZpCVdJM/Z6Vv
 github.com/onsi/ginkgo v1.16.5 h1:8xi0RTUf59SOSfEtZMvwTvXYMzG4gV23XVHOZiXNtnE=
 github.com/onsi/ginkgo v1.16.5/go.mod h1:+E8gABHa3K6zRBolWtd+ROzc/U5bkGt0FwiG042wbpU=
 github.com/onsi/ginkgo/v2 v2.1.3/go.mod h1:vw5CSIxN1JObi/U8gcbwft7ZxR2dgaR70JSE3/PpL4c=
-github.com/onsi/ginkgo/v2 v2.19.0 h1:9Cnnf7UHo57Hy3k6/m5k3dRfGTMXGvxhHFvkDTCTpvA=
-github.com/onsi/ginkgo/v2 v2.19.0/go.mod h1:rlwLi9PilAFJ8jCg9UE1QP6VBpd6/xj3SRC0d6TU0To=
+github.com/onsi/ginkgo/v2 v2.21.0 h1:7rg/4f3rB88pb5obDgNZrNHrQ4e6WpjonchcpuBRnZM=
+github.com/onsi/ginkgo/v2 v2.21.0/go.mod h1:7Du3c42kxCUegi0IImZ1wUQzMBVecgIHjR1C+NkhLQo=
 github.com/onsi/gomega v1.7.1/go.mod h1:XdKZgCCFLUoM/7CFJVPcG8C1xQ1AJ0vpAezJrB7JYyY=
 github.com/onsi/gomega v1.10.1/go.mod h1:iN09h71vgCQne3DLsj+A5owkum+a2tYe+TOCB1ybHNo=
 github.com/onsi/gomega v1.17.0/go.mod h1:HnhC7FXeEQY45zxNK3PPoIUhzk/80Xly9PcubAlGdZY=
-github.com/onsi/gomega v1.33.1 h1:dsYjIxxSR755MDmKVsaFQTE22ChNBcuuTWgkUDSubOk=
-github.com/onsi/gomega v1.33.1/go.mod h1:U4R44UsT+9eLIaYRB2a5qajjtQYn0hauxvRm16AVYg0=
+github.com/onsi/gomega v1.35.1 h1:Cwbd75ZBPxFSuZ6T+rN/WCb/gOc6YgFBXLlZLhC7Ds4=
+github.com/onsi/gomega v1.35.1/go.mod h1:PvZbdDc8J6XJEpDK4HCuRBm8a6Fzp9/DmhC9C7yFlog=
 github.com/opencontainers/go-digest v1.0.0 h1:apOUWs51W5PlhuyGyz9FCeeBIOUDA/6nW8Oi/yOhh5U=
 github.com/opencontainers/go-digest v1.0.0/go.mod h1:0JzlMkj0TRzQZfJkVvzbP0HBR3IKzErnv2BNG4W4MAM=
-github.com/opencontainers/runc v1.0.3 h1:1hbqejyQWCJBvtKAfdO0b1FmaEf2z/bxnjqbARass5k=
-github.com/opencontainers/runc v1.0.3/go.mod h1:aTaHFFwQXuA71CiyxOdFFIorAoemI04suvGRQFzWTD0=
-github.com/opencontainers/runtime-spec v1.0.3-0.20210326190908-1c3f411f0417/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
-github.com/opencontainers/runtime-spec v1.0.3-0.20220909204839-494a5a6aca78 h1:R5M2qXZiK/mWPMT4VldCOiSL9HIAMuxQZWdG0CSM5+4=
-github.com/opencontainers/runtime-spec v1.0.3-0.20220909204839-494a5a6aca78/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
-github.com/opencontainers/selinux v1.8.2/go.mod h1:MUIHuUEvKB1wtJjQdOyYRgOnLD2xAPP8dBsCoU0KuF8=
-github.com/opencontainers/selinux v1.11.0 h1:+5Zbo97w3Lbmb3PeqQtpmTkMwsW5nRI3YaLpt7tQ7oU=
-github.com/opencontainers/selinux v1.11.0/go.mod h1:E5dMC3VPuVvVHDYmi78qvhJp8+M586T4DlDRYpFkyec=
+github.com/opencontainers/image-spec v1.1.0 h1:8SG7/vwALn54lVB/0yZ/MMwhFrPYtpEHQb2IpWsCzug=
+github.com/opencontainers/image-spec v1.1.0/go.mod h1:W4s4sFTMaBeK1BQLXbG4AdM2szdn85PY75RI83NrTrM=
+github.com/opencontainers/runc v1.2.1 h1:mQkmeFSUxqFaVmvIn1VQPeQIKpHFya5R07aJw0DKQa8=
+github.com/opencontainers/runc v1.2.1/go.mod h1:/PXzF0h531HTMsYQnmxXkBD7YaGShm/2zcRB79dksUc=
+github.com/opencontainers/runtime-spec v1.2.0 h1:z97+pHb3uELt/yiAWD691HNHQIF07bE7dzrbT927iTk=
+github.com/opencontainers/runtime-spec v1.2.0/go.mod h1:jwyrGlmzljRJv/Fgzds9SsS/C5hL+LL3ko9hs6T5lQ0=
+github.com/opencontainers/selinux v1.11.1 h1:nHFvthhM0qY8/m+vfhJylliSshm8G1jJ2jDMcgULaH8=
+github.com/opencontainers/selinux v1.11.1/go.mod h1:E5dMC3VPuVvVHDYmi78qvhJp8+M586T4DlDRYpFkyec=
 github.com/pkg/errors v0.8.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
@@ -238,13 +268,7 @@ github.com/prometheus/prometheus v0.39.1 h1:abZM6A+sKAv2eKTbRIaHq4amM/nT07MuxRm0
 github.com/prometheus/prometheus v0.39.1/go.mod h1:GjQjgLhHMc0oo4Ko7qt/yBSJMY4hUoiAZwsYQgjaePA=
 github.com/rogpeppe/go-internal v1.12.0 h1:exVL4IDcn6na9z1rAb56Vxr+CgyK3nn3O+epU5NdKM8=
 github.com/rogpeppe/go-internal v1.12.0/go.mod h1:E+RYuTGaKKdloAfM02xzb0FW3Paa99yedzYV+kq4uf4=
-github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
-github.com/seccomp/libseccomp-golang v0.9.1/go.mod h1:GbW5+tmTXfcxTToHLXlScSlAvWlF4P2Ca7zGrPiEpWo=
-github.com/seccomp/libseccomp-golang v0.10.0 h1:aA4bp+/Zzi0BnWZ2F1wgNBs5gTpm+na2rWM6M9YjLpY=
-github.com/seccomp/libseccomp-golang v0.10.0/go.mod h1:JA8cRccbGaA1s33RQf7Y1+q9gHmZX1yB/z9WDN1C6fg=
-github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
-github.com/sirupsen/logrus v1.8.1/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
 github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ=
 github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
 github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d/go.mod h1:OnSkiWE9lh6wB0YB77sQom3nweQdgAjqCqsofrRNTgc=
@@ -255,12 +279,13 @@ github.com/spf13/cobra v1.8.1 h1:e5/vxKd/rZsfSJMUX1agtjeTDf+qv1/JdBF8gg5k9ZM=
 github.com/spf13/cobra v1.8.1/go.mod h1:wHxEcudfqmLYa8iTfL+OuZPbBZkmvliBWKIezN3kD9Y=
 github.com/spf13/pflag v1.0.5 h1:iy+VFUOCP1a+8yFto/drg2CJ5u0yRoB7fZw3DKv/JXA=
 github.com/spf13/pflag v1.0.5/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
-github.com/stoewer/go-strcase v1.2.0 h1:Z2iHWqGXH00XYgqDmNgQbIBxf3wrNq0F3feEy0ainaU=
-github.com/stoewer/go-strcase v1.2.0/go.mod h1:IBiWB2sKIp3wVVQ3Y035++gc+knqhUQag1KpM8ahLw8=
+github.com/stoewer/go-strcase v1.3.0 h1:g0eASXYtp+yvN9fK8sH94oCIk0fau9uV1/ZdJ0AVEzs=
+github.com/stoewer/go-strcase v1.3.0/go.mod h1:fAH5hQ5pehh+j3nZfvwdk2RgEgQjAoM8wodgtPmh1xo=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
 github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpEOglKo=
-github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
+github.com/stretchr/objx v0.5.2 h1:xuMeJ0Sdp5ZMRXx/aWO6RZxdr3beISkG5/G/aIRr3pY=
+github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
 github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
@@ -269,40 +294,35 @@ github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO
 github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.9.0 h1:HtqpIVDClZ4nwg75+f6Lvsy/wHu+3BoSGCbBAcpTsTg=
 github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
-github.com/syndtr/gocapability v0.0.0-20200815063812-42c35b437635/go.mod h1:hkRG7XYTFWNJGYcbNJQlaLq0fg1yr4J4t/NcTQtrfww=
 github.com/tmc/grpc-websocket-proxy v0.0.0-20220101234140-673ab2c3ae75 h1:6fotK7otjonDflCTK0BCfls4SPy3NcCVb5dqqmbRknE=
 github.com/tmc/grpc-websocket-proxy v0.0.0-20220101234140-673ab2c3ae75/go.mod h1:KO6IkyS8Y3j8OdNO85qEYBsRPuteD+YciPomcXdrMnk=
-github.com/urfave/cli v1.22.1/go.mod h1:Gos4lmkARVdJ6EkW0WaNv/tZAAMe9V7XWyB60NtXRu0=
-github.com/vishvananda/netlink v1.1.0/go.mod h1:cTgwzPIzzgDAYoQrMm0EdrjRUBkTqKYppBueQtXaqoE=
-github.com/vishvananda/netlink v1.1.1-0.20210330154013-f5de75959ad5 h1:+UB2BJA852UkGH42H+Oee69djmxS3ANzl2b/JtT1YiA=
-github.com/vishvananda/netlink v1.1.1-0.20210330154013-f5de75959ad5/go.mod h1:twkDnbuQxJYemMlGd4JFIcuhgX83tXhKS2B/PRMpOho=
-github.com/vishvananda/netns v0.0.0-20191106174202-0a2b9b5464df/go.mod h1:JP3t17pCcGlemwknint6hfoeCVQrEMVwxRLRjXpq+BU=
-github.com/vishvananda/netns v0.0.0-20200728191858-db3c7e526aae/go.mod h1:DD4vA1DwXk04H54A1oHXtwZmA0grkVMdPxx/VGLCah0=
+github.com/vishvananda/netlink v1.3.1-0.20240905180732-b1ce50cfa9be h1:xdCMvyhnKzaepIUgVpUmTJo/+H1AQ7HuFYn1hv7/Neo=
+github.com/vishvananda/netlink v1.3.1-0.20240905180732-b1ce50cfa9be/go.mod h1:i6NetklAujEcC6fK0JPjT8qSwWyO0HLn4UKG+hGqeJs=
 github.com/vishvananda/netns v0.0.4 h1:Oeaw1EM2JMxD51g9uhtC0D7erkIjgmj8+JZc26m1YX8=
 github.com/vishvananda/netns v0.0.4/go.mod h1:SpkAiCQRtJ6TvvxPnOSyH3BMl6unz3xZlaprSwhNNJM=
 github.com/x448/float16 v0.8.4 h1:qLwI1I70+NjRFUR3zs1JPUCgaCXSh3SW62uAKT1mSBM=
 github.com/x448/float16 v0.8.4/go.mod h1:14CWIYCyZA/cWjXOioeEpHeN/83MdbZDRQHoFcYsOfg=
-github.com/xiang90/probing v0.0.0-20190116061207-43a291ad63a2 h1:eY9dn8+vbi4tKz5Qo6v2eYzo7kUS51QINcR5jNpbZS8=
-github.com/xiang90/probing v0.0.0-20190116061207-43a291ad63a2/go.mod h1:UETIi67q53MR2AWcXfiuqkDkRtnGDLqkBTpCHuJHxtU=
+github.com/xiang90/probing v0.0.0-20221125231312-a49e3df8f510 h1:S2dVYn90KE98chqDkyE9Z4N61UnQd+KOfgp5Iu53llk=
+github.com/xiang90/probing v0.0.0-20221125231312-a49e3df8f510/go.mod h1:UETIi67q53MR2AWcXfiuqkDkRtnGDLqkBTpCHuJHxtU=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.3.5/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
-go.etcd.io/bbolt v1.3.9 h1:8x7aARPEXiXbHmtUwAIv7eV2fQFHrLLavdiJ3uzJXoI=
-go.etcd.io/bbolt v1.3.9/go.mod h1:zaO32+Ti0PK1ivdPtgMESzuzL2VPoIG1PCQNvOdo/dE=
-go.etcd.io/etcd/api/v3 v3.5.14 h1:vHObSCxyB9zlF60w7qzAdTcGaglbJOpSj1Xj9+WGxq0=
-go.etcd.io/etcd/api/v3 v3.5.14/go.mod h1:BmtWcRlQvwa1h3G2jvKYwIQy4PkHlDej5t7uLMUdJUU=
-go.etcd.io/etcd/client/pkg/v3 v3.5.14 h1:SaNH6Y+rVEdxfpA2Jr5wkEvN6Zykme5+YnbCkxvuWxQ=
-go.etcd.io/etcd/client/pkg/v3 v3.5.14/go.mod h1:8uMgAokyG1czCtIdsq+AGyYQMvpIKnSvPjFMunkgeZI=
-go.etcd.io/etcd/client/v2 v2.305.13 h1:RWfV1SX5jTU0lbCvpVQe3iPQeAHETWdOTb6pxhd77C8=
-go.etcd.io/etcd/client/v2 v2.305.13/go.mod h1:iQnL7fepbiomdXMb3om1rHq96htNNGv2sJkEcZGDRRg=
-go.etcd.io/etcd/client/v3 v3.5.14 h1:CWfRs4FDaDoSz81giL7zPpZH2Z35tbOrAJkkjMqOupg=
-go.etcd.io/etcd/client/v3 v3.5.14/go.mod h1:k3XfdV/VIHy/97rqWjoUzrj9tk7GgJGH9J8L4dNXmAk=
-go.etcd.io/etcd/pkg/v3 v3.5.13 h1:st9bDWNsKkBNpP4PR1MvM/9NqUPfvYZx/YXegsYEH8M=
-go.etcd.io/etcd/pkg/v3 v3.5.13/go.mod h1:N+4PLrp7agI/Viy+dUYpX7iRtSPvKq+w8Y14d1vX+m0=
-go.etcd.io/etcd/raft/v3 v3.5.13 h1:7r/NKAOups1YnKcfro2RvGGo2PTuizF/xh26Z2CTAzA=
-go.etcd.io/etcd/raft/v3 v3.5.13/go.mod h1:uUFibGLn2Ksm2URMxN1fICGhk8Wu96EfDQyuLhAcAmw=
-go.etcd.io/etcd/server/v3 v3.5.13 h1:V6KG+yMfMSqWt+lGnhFpP5z5dRUj1BDRJ5k1fQ9DFok=
-go.etcd.io/etcd/server/v3 v3.5.13/go.mod h1:K/8nbsGupHqmr5MkgaZpLlH1QdX1pcNQLAkODy44XcQ=
+go.etcd.io/bbolt v1.3.11 h1:yGEzV1wPz2yVCLsD8ZAiGHhHVlczyC9d1rP43/VCRJ0=
+go.etcd.io/bbolt v1.3.11/go.mod h1:dksAq7YMXoljX0xu6VF5DMZGbhYYoLUalEiSySYAS4I=
+go.etcd.io/etcd/api/v3 v3.5.16 h1:WvmyJVbjWqK4R1E+B12RRHz3bRGy9XVfh++MgbN+6n0=
+go.etcd.io/etcd/api/v3 v3.5.16/go.mod h1:1P4SlIP/VwkDmGo3OlOD7faPeP8KDIFhqvciH5EfN28=
+go.etcd.io/etcd/client/pkg/v3 v3.5.16 h1:ZgY48uH6UvB+/7R9Yf4x574uCO3jIx0TRDyetSfId3Q=
+go.etcd.io/etcd/client/pkg/v3 v3.5.16/go.mod h1:V8acl8pcEK0Y2g19YlOV9m9ssUe6MgiDSobSoaBAM0E=
+go.etcd.io/etcd/client/v2 v2.305.16 h1:kQrn9o5czVNaukf2A2At43cE9ZtWauOtf9vRZuiKXow=
+go.etcd.io/etcd/client/v2 v2.305.16/go.mod h1:h9YxWCzcdvZENbfzBTFCnoNumr2ax3F19sKMqHFmXHE=
+go.etcd.io/etcd/client/v3 v3.5.16 h1:sSmVYOAHeC9doqi0gv7v86oY/BTld0SEFGaxsU9eRhE=
+go.etcd.io/etcd/client/v3 v3.5.16/go.mod h1:X+rExSGkyqxvu276cr2OwPLBaeqFu1cIl4vmRjAD/50=
+go.etcd.io/etcd/pkg/v3 v3.5.16 h1:cnavs5WSPWeK4TYwPYfmcr3Joz9BH+TZ6qoUtz6/+mc=
+go.etcd.io/etcd/pkg/v3 v3.5.16/go.mod h1:+lutCZHG5MBBFI/U4eYT5yL7sJfnexsoM20Y0t2uNuY=
+go.etcd.io/etcd/raft/v3 v3.5.16 h1:zBXA3ZUpYs1AwiLGPafYAKKl/CORn/uaxYDwlNwndAk=
+go.etcd.io/etcd/raft/v3 v3.5.16/go.mod h1:P4UP14AxofMJ/54boWilabqqWoW9eLodl6I5GdGzazI=
+go.etcd.io/etcd/server/v3 v3.5.16 h1:d0/SAdJ3vVsZvF8IFVb1k8zqMZ+heGcNfft71ul9GWE=
+go.etcd.io/etcd/server/v3 v3.5.16/go.mod h1:ynhyZZpdDp1Gq49jkUg5mfkDWZwXnn3eIqCqtJnrD/s=
 go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.53.0 h1:9G6E0TXzGFVfTnawRzrPl83iHOAV7L8NJiR8RSGYV1g=
 go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.53.0/go.mod h1:azvtTADFQJA8mX80jIH/akaE7h+dbm/sVuaHqN13w74=
 go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.53.0 h1:4K4tsIXefpVJtvA/8srF4V4y0akAoPHkIslgAkjixJA=
@@ -327,20 +347,20 @@ go.uber.org/goleak v1.3.0 h1:2K3zAYmnTNqV73imy9J1T3WC+gmCePx2hEGkimedGto=
 go.uber.org/goleak v1.3.0/go.mod h1:CoHD4mav9JJNrW/WLlf7HGZPjdw8EucARQHekz1X6bE=
 go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
 go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
-go.uber.org/zap v1.26.0 h1:sI7k6L95XOKS281NhVKOFCUNIvv9e0w4BF8N3u+tCRo=
-go.uber.org/zap v1.26.0/go.mod h1:dtElttAiwGvoJ/vj4IwHBS/gXsEu/pZ50mUIRWuG0so=
+go.uber.org/zap v1.27.0 h1:aJMhYGrd5QSmlpLMr2MftRKl7t8J8PTZPA732ud/XR8=
+go.uber.org/zap v1.27.0/go.mod h1:GB2qFLM7cTU87MWRP2mPIjqfIDnGu+VIO4V/SdhGo2E=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
-golang.org/x/crypto v0.24.0 h1:mnl8DM0o513X8fdIkmyFE/5hTYxbwYOjDS/+rK6qpRI=
-golang.org/x/crypto v0.24.0/go.mod h1:Z1PMYSOR5nyMcyAVAIQSKCDwalqy85Aqn1x3Ws4L5DM=
-golang.org/x/exp v0.0.0-20230515195305-f3d0a9c9a5cc h1:mCRnTeVUjcrhlRmO0VK8a6k6Rrf6TF9htwo2pJVSjIU=
-golang.org/x/exp v0.0.0-20230515195305-f3d0a9c9a5cc/go.mod h1:V1LtkGg67GoY2N1AnLN78QLrzxkLyJw7RJb1gzOOz9w=
+golang.org/x/crypto v0.37.0 h1:kJNSjF/Xp7kU0iB2Z+9viTPMW4EqqsrywMXLJOOsXSE=
+golang.org/x/crypto v0.37.0/go.mod h1:vg+k43peMZ0pUMhYmVAWysMK35e6ioLh3wB8ZCAfbVc=
+golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56 h1:2dVuKD2vS7b0QIHQbpyTISPd0LeHDbnYEryqj5Q1ug8=
+golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56/go.mod h1:M4RDyNAINzryxdtnbRXRL/OHtkFuWGRjvuhBJpk2IlY=
 golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.4.2/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
-golang.org/x/mod v0.17.0 h1:zY54UmvipHiNd+pm+m0x9KhZ9hl1/7QNMyxXbc6ICqA=
-golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
+golang.org/x/mod v0.21.0 h1:vvrHzRwRfVKSiLrG+d4FMl/Qi4ukBCE6kZlTUkDYRT0=
+golang.org/x/mod v0.21.0/go.mod h1:6SkKJ3Xj0I0BrPOZoBy3bdMptDDU9oJrpohJ3eWZ1fY=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20190311183353-d8887717615a/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
@@ -348,56 +368,49 @@ golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLL
 golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200520004742-59133d7f0dd7/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
-golang.org/x/net v0.0.0-20201224014010-6772e930b67b/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
 golang.org/x/net v0.0.0-20210405180319-a5a99cb37ef4/go.mod h1:p54w0d4576C0XHj96bSt6lcn1PtDYWL6XObtHCRCNQM=
 golang.org/x/net v0.0.0-20210428140749-89ef3d95e781/go.mod h1:OJAsFXCWl8Ukc7SiCT/9KSuxbyM7479/AVlXFRxuMCk=
-golang.org/x/net v0.26.0 h1:soB7SVo0PWrY4vPW/+ay0jKDNScG2X9wFeYlXIvJsOQ=
-golang.org/x/net v0.26.0/go.mod h1:5YKkiSynbBIh3p6iOc/vibscux0x38BZDkn8sCUPxHE=
-golang.org/x/oauth2 v0.21.0 h1:tsimM75w1tF/uws5rbeHzIWxEqElMehnc+iW793zsZs=
-golang.org/x/oauth2 v0.21.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI=
+golang.org/x/net v0.38.0 h1:vRMAPTMaeGqVhG5QyLJHqNDwecKTomGeqbnfZyKlBI8=
+golang.org/x/net v0.38.0/go.mod h1:ivrbrMbzFq5J41QOQh0siUuly180yBYtLp+CKbEaFx8=
+golang.org/x/oauth2 v0.23.0 h1:PbgcYx2W7i4LvjJWEbf0ngHV6qJYr86PkAV3bXdLEbs=
+golang.org/x/oauth2 v0.23.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20210220032951-036812b2e83c/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
-golang.org/x/sync v0.7.0 h1:YsImfSBoP9QPYL0xyKJPq0gcaJdG3rInoqxTWbfQu9M=
-golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
+golang.org/x/sync v0.13.0 h1:AauUjRAJ9OSnvULf/ARrrVywoJDy0YS2AwQ98I37610=
+golang.org/x/sync v0.13.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20190606203320-7fc4e5ec1444/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190904154756-749cb33beabd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191005200804-aed5e4c7ecf9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20191115151921-52ab43148777/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191120155948-bd437916bb0e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191204072324-ce4227a45e2e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200217220822-9197077df867/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200728102440-3e129f6d46b1/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20200909081042-eff7692f9009/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210112080510-489259a85091/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210330210617-4fbd30eecc44/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
-golang.org/x/sys v0.0.0-20210426230700-d19ff857e887/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210510120138-977fb7262007/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20210616094352-59db8d763f22/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
-golang.org/x/sys v0.21.0 h1:rF+pYz3DAGSQAxAu1CbC7catZg4ebC4UIeIhKxBZvws=
-golang.org/x/sys v0.21.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
+golang.org/x/sys v0.2.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.10.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.32.0 h1:s77OFDvIQeibCmezSnk/q6iAfkdiQaJi4VzroCFrN20=
+golang.org/x/sys v0.32.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
-golang.org/x/term v0.21.0 h1:WVXCp+/EBEHOj53Rvu+7KiT/iElMrO8ACK16SMZ3jaA=
-golang.org/x/term v0.21.0/go.mod h1:ooXLefLobQVslOqselCNF4SxFAaoS6KujMbsGzSDmX0=
+golang.org/x/term v0.31.0 h1:erwDkOK1Msy6offm1mOgvspSkslFnIGsFnxOKoufg3o=
+golang.org/x/term v0.31.0/go.mod h1:R4BeIy7D95HzImkxGkTW1UQTtP54tio2RyHz7PwK0aw=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
 golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
-golang.org/x/text v0.16.0 h1:a94ExnEXNtEwYLGJSIUxnWoxoRz/ZcCsV63ROupILh4=
-golang.org/x/text v0.16.0/go.mod h1:GhwF1Be+LQoKShO3cGOHzqOgRrGaYc9AvblQOmPVHnI=
-golang.org/x/time v0.3.0 h1:rg5rLMjNzMS1RkNLzCG38eapWhnYLFYXDXj2gOlr8j4=
-golang.org/x/time v0.3.0/go.mod h1:tRJNPiyCQ0inRvYxbN9jk5I+vvW/OXSQhTDSoE431IQ=
+golang.org/x/text v0.24.0 h1:dd5Bzh4yt5KYA8f9CJHCP4FB4D51c2c6JvN37xJJkJ0=
+golang.org/x/text v0.24.0/go.mod h1:L8rBsPeo2pSS+xqN0d5u2ikmjtmoJbDBT1b7nHvFCdU=
+golang.org/x/time v0.7.0 h1:ntUhktv3OPE6TgYxXWv9vKvUSJyIFJlyohwbkEwPrKQ=
+golang.org/x/time v0.7.0/go.mod h1:3BpzKBy/shNhVucY/MWOyx10tF3SFh9QdLuxbVysPQM=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20190328211700-ab21143f2384/go.mod h1:LCzVGOaR6xXOjkQ3onu1FJEFr0SW1gC7cKk1uF8kGRs=
 golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
@@ -405,20 +418,20 @@ golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roY
 golang.org/x/tools v0.0.0-20201224043029-2b0845dc783e/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.1.1/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
-golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d h1:vU5i/LfpvrRCpgM/VPfJLg5KjxD3E+hfT1SH+d9zLwg=
-golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
+golang.org/x/tools v0.26.0 h1:v/60pFQmzmT9ExmjDv2gGIfi3OqfKoEP6I5+umXlbnQ=
+golang.org/x/tools v0.26.0/go.mod h1:TPVVj70c7JJ3WCazhD8OdXcZg/og+b9+tH/KxylGwH0=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 gomodules.xyz/jsonpatch/v2 v2.2.0 h1:4pT439QV83L+G9FkcCriY6EkpcK6r6bK+A5FBUMI7qY=
 gomodules.xyz/jsonpatch/v2 v2.2.0/go.mod h1:WXp+iVDkoLQqPudfQ9GBlwB2eZ5DKOnjQZCYdOS8GPY=
-google.golang.org/genproto v0.0.0-20230822172742-b8732ec3820d h1:VBu5YqKPv6XiJ199exd8Br+Aetz+o08F+PLMnwJQHAY=
-google.golang.org/genproto v0.0.0-20230822172742-b8732ec3820d/go.mod h1:yZTlhN0tQnXo3h00fuXNCxJdLdIdnVFVBaRJ5LWBbw4=
-google.golang.org/genproto/googleapis/api v0.0.0-20240528184218-531527333157 h1:7whR9kGa5LUwFtpLm2ArCEejtnxlGeLbAyjFY8sGNFw=
-google.golang.org/genproto/googleapis/api v0.0.0-20240528184218-531527333157/go.mod h1:99sLkeliLXfdj2J75X3Ho+rrVCaJze0uwN7zDDkjPVU=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20240701130421-f6361c86f094 h1:BwIjyKYGsK9dMCBOorzRri8MQwmi7mT9rGHsCEinZkA=
-google.golang.org/genproto/googleapis/rpc v0.0.0-20240701130421-f6361c86f094/go.mod h1:Ue6ibwXGpU+dqIcODieyLOcgj7z8+IcskoNIgZxtrFY=
+google.golang.org/genproto v0.0.0-20240123012728-ef4313101c80 h1:KAeGQVN3M9nD0/bQXnr/ClcEMJ968gUXJQ9pwfSynuQ=
+google.golang.org/genproto v0.0.0-20240123012728-ef4313101c80/go.mod h1:cc8bqMqtv9gMOr0zHg2Vzff5ULhhL2IXP4sbcn32Dro=
+google.golang.org/genproto/googleapis/api v0.0.0-20240826202546-f6391c0de4c7 h1:YcyjlL1PRr2Q17/I0dPk2JmYS5CDXfcdb2Z3YRioEbw=
+google.golang.org/genproto/googleapis/api v0.0.0-20240826202546-f6391c0de4c7/go.mod h1:OCdP9MfskevB/rbYvHTsXTtKC+3bHWajPdoKgjcYkfo=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240826202546-f6391c0de4c7 h1:2035KHhUv+EpyB+hWgJnaWKJOdX1E95w2S8Rr4uWKTs=
+google.golang.org/genproto/googleapis/rpc v0.0.0-20240826202546-f6391c0de4c7/go.mod h1:UqMtugtsSgubUsoxbuAoiCXvqvErP7Gf0so0mK9tHxU=
 google.golang.org/grpc v1.57.0 h1:kfzNeI/klCGD2YPMUlaGNT3pxvYfga7smW3Vth8Zsiw=
 google.golang.org/grpc v1.57.0/go.mod h1:Sd+9RMTACXwmub0zcNY2c4arhtrbBYD1AUHI/dt16Mo=
 google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
@@ -429,8 +442,8 @@ google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzi
 google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
 google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
 google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
-google.golang.org/protobuf v1.34.2 h1:6xV6lTsCfpGD21XK49h7MhtcApnLqkfYgPcdHftf6hg=
-google.golang.org/protobuf v1.34.2/go.mod h1:qYOHts0dSfpeUzUFpOMr/WGzszTmLH+DiWniOlNbLDw=
+google.golang.org/protobuf v1.35.1 h1:m3LfL6/Ca+fqnjnlqQXNpFPABW1UD7mjh8KO2mKFytA=
+google.golang.org/protobuf v1.35.1/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
@@ -445,70 +458,75 @@ gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkep
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
 gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
-gopkg.in/yaml.v2 v2.2.8/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
 gopkg.in/yaml.v2 v2.4.0 h1:D8xgwECY7CYvx+Y2n4sBz93Jn9JRvxdiyyo8CTfuKaY=
 gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
-k8s.io/api v0.31.1 h1:Xe1hX/fPW3PXYYv8BlozYqw63ytA92snr96zMW9gWTU=
-k8s.io/api v0.31.1/go.mod h1:sbN1g6eY6XVLeqNsZGLnI5FwVseTrZX7Fv3O26rhAaI=
-k8s.io/apiextensions-apiserver v0.31.3 h1:+GFGj2qFiU7rGCsA5o+p/rul1OQIq6oYpQw4+u+nciE=
-k8s.io/apiextensions-apiserver v0.31.3/go.mod h1:2DSpFhUZZJmn/cr/RweH1cEVVbzFw9YBu4T+U3mf1e4=
-k8s.io/apimachinery v0.31.3 h1:6l0WhcYgasZ/wk9ktLq5vLaoXJJr5ts6lkaQzgeYPq4=
-k8s.io/apimachinery v0.31.3/go.mod h1:rsPdaZJfTfLsNJSQzNHQvYoTmxhoOEofxtOsF3rtsMo=
-k8s.io/apiserver v0.31.3 h1:+1oHTtCB+OheqFEz375D0IlzHZ5VeQKX1KGXnx+TTuY=
-k8s.io/apiserver v0.31.3/go.mod h1:PrxVbebxrxQPFhJk4powDISIROkNMKHibTg9lTRQ0Qg=
-k8s.io/client-go v0.31.3 h1:CAlZuM+PH2cm+86LOBemaJI/lQ5linJ6UFxKX/SoG+4=
-k8s.io/client-go v0.31.3/go.mod h1:2CgjPUTpv3fE5dNygAr2NcM8nhHzXvxB8KL5gYc3kJs=
-k8s.io/cloud-provider v0.31.3 h1:7C3CHQUUwnv/HWWVIaibZH06iPg663RYQ6C6Zy4FnO8=
-k8s.io/cloud-provider v0.31.3/go.mod h1:c7csKppoVb9Ej6upJ28AvHy4B3BtlRMzXfgezsDdPKw=
-k8s.io/code-generator v0.31.3 h1:Pj0fYOBms+ZrsulLi4DMsCEx1jG8fWKRLy44onHsLBI=
-k8s.io/code-generator v0.31.3/go.mod h1:/umCIlT84g1+Yu5ZXtP1KGSRTnGiIzzX5AzUAxsNlts=
-k8s.io/component-base v0.31.3 h1:DMCXXVx546Rfvhj+3cOm2EUxhS+EyztH423j+8sOwhQ=
-k8s.io/component-base v0.31.3/go.mod h1:xME6BHfUOafRgT0rGVBGl7TuSg8Z9/deT7qq6w7qjIU=
-k8s.io/component-helpers v0.31.3 h1:0zGPD2PrekhFWgmz85XxlMEl7dfhlKC1tERZDe3onQc=
-k8s.io/component-helpers v0.31.3/go.mod h1:HZ1HZx2TKXM7xSUV2cR9L5yDoyZPhhHQNaE3BPBLPUQ=
-k8s.io/controller-manager v0.31.3 h1:TyUav69iNYwLGwA96JDhusoZoGRdh1sdrLjXmWTcPgs=
-k8s.io/controller-manager v0.31.3/go.mod h1:yuhec+dbXmBz+4c32kxJxmcauB+1pjO2ttfYODWuv18=
-k8s.io/cri-api v0.31.3 h1:dsZXzrGrCEwHjsTDlAV7rutEplpMLY8bfNRMIqrtXjo=
-k8s.io/cri-api v0.31.3/go.mod h1:Po3TMAYH/+KrZabi7QiwQI4a692oZcUOUThd/rqwxrI=
-k8s.io/cri-client v0.31.3 h1:9ZwddaNJomqkTBYQqSmB+Ccns3beY4HyYDwmRtWTCJM=
-k8s.io/cri-client v0.31.3/go.mod h1:klbWiYkOatOQOkXOYZMZMGSTM8q9eC/efsYGuXcgPes=
-k8s.io/csi-translation-lib v0.31.3 h1:hxcPRNdtEsk766jCXSKjgH1V8jUNx5tVqdooQ1Ars/M=
-k8s.io/csi-translation-lib v0.31.3/go.mod h1:0B1gQwd868XUIDwJYy5gB2jDXWEwlcWvSsfcQEgzbRk=
-k8s.io/gengo/v2 v2.0.0-20240228010128-51d4e06bde70 h1:NGrVE502P0s0/1hudf8zjgwki1X/TByhmAoILTarmzo=
-k8s.io/gengo/v2 v2.0.0-20240228010128-51d4e06bde70/go.mod h1:VH3AT8AaQOqiGjMF9p0/IM1Dj+82ZwjfxUP1IxaHE+8=
+k8s.io/api v0.32.2 h1:bZrMLEkgizC24G9eViHGOPbW+aRo9duEISRIJKfdJuw=
+k8s.io/api v0.32.2/go.mod h1:hKlhk4x1sJyYnHENsrdCWw31FEmCijNGPJO5WzHiJ6Y=
+k8s.io/apiextensions-apiserver v0.32.2 h1:2YMk285jWMk2188V2AERy5yDwBYrjgWYggscghPCvV4=
+k8s.io/apiextensions-apiserver v0.32.2/go.mod h1:GPwf8sph7YlJT3H6aKUWtd0E+oyShk/YHWQHf/OOgCA=
+k8s.io/apimachinery v0.32.2 h1:yoQBR9ZGkA6Rgmhbp/yuT9/g+4lxtsGYwW6dR6BDPLQ=
+k8s.io/apimachinery v0.32.2/go.mod h1:GpHVgxoKlTxClKcteaeuF1Ul/lDVb74KpZcxcmLDElE=
+k8s.io/apiserver v0.32.2 h1:WzyxAu4mvLkQxwD9hGa4ZfExo3yZZaYzoYvvVDlM6vw=
+k8s.io/apiserver v0.32.2/go.mod h1:PEwREHiHNU2oFdte7BjzA1ZyjWjuckORLIK/wLV5goM=
+k8s.io/client-go v0.32.2 h1:4dYCD4Nz+9RApM2b/3BtVvBHw54QjMFUl1OLcJG5yOA=
+k8s.io/client-go v0.32.2/go.mod h1:fpZ4oJXclZ3r2nDOv+Ux3XcJutfrwjKTCHz2H3sww94=
+k8s.io/cloud-provider v0.32.2 h1:8EC+fCYo0r0REczSjOZcVuQPCMxXxCKlgxDbYMrzC30=
+k8s.io/cloud-provider v0.32.2/go.mod h1:2s8TeAXhVezp5VISaTxM6vW3yDonOZXoN4Aryz1p1PQ=
+k8s.io/code-generator v0.32.2 h1:CIvyPrLWP7cMgrqval2qYT839YAwCDeSvGfXgWSNpHQ=
+k8s.io/code-generator v0.32.2/go.mod h1:plh7bWk7JztAUkHM4zpbdy0KOMdrhsePcZL2HLWFH7Y=
+k8s.io/component-base v0.32.2 h1:1aUL5Vdmu7qNo4ZsE+569PV5zFatM9hl+lb3dEea2zU=
+k8s.io/component-base v0.32.2/go.mod h1:PXJ61Vx9Lg+P5mS8TLd7bCIr+eMJRQTyXe8KvkrvJq0=
+k8s.io/component-helpers v0.32.2 h1:2usSAm3zNE5yu5DdAdrKBWLfSYNpU4OPjZywJY5ovP8=
+k8s.io/component-helpers v0.32.2/go.mod h1:fvQAoiiOP7jUEUBc9qR0PXiBPuB0I56WTxTkkpcI8g8=
+k8s.io/controller-manager v0.32.2 h1:/9XuHWEqofO2Aqa4l7KJGckJUcLVRWfx+qnVkdXoStI=
+k8s.io/controller-manager v0.32.2/go.mod h1:o5uo2tLCQhuoMt0RfKcQd0eqaNmSKOKiT+0YELCqXOk=
+k8s.io/cri-api v0.32.2 h1:7DuaOHpOcXweZeBUbRdK0iCroxctGp73VwgrA0u7kho=
+k8s.io/cri-api v0.32.2/go.mod h1:DCzMuTh2padoinefWME0G678Mc3QFbLMF2vEweGzBAI=
+k8s.io/cri-client v0.32.2 h1:vjowJUyu14IbmifqCKJHE9rK/BPSfkXvltqN42W1Zuo=
+k8s.io/cri-client v0.32.2/go.mod h1:fRZhmmZW16Qviln8hfy+e8dd2wP/n9B6TiGxLE3zBe0=
+k8s.io/csi-translation-lib v0.32.2 h1:aLzAyaoJUc5rgtLi8Xd4No1tet6UpvUsGIgRoGnPSSE=
+k8s.io/csi-translation-lib v0.32.2/go.mod h1:PlOKan6Vc0G6a+giQbm36plJ+E1LH+GPRLAVMQMSMcY=
+k8s.io/dynamic-resource-allocation v0.32.2 h1:6wP8/GGvhhvTJLrzwPSoMJDnspmosFj1CKmfrAH6m5U=
+k8s.io/dynamic-resource-allocation v0.32.2/go.mod h1:+3qnQfvikLHVZrdZ0/gYkRiV96weUR9j7+Ph3Ui/hYU=
+k8s.io/gengo/v2 v2.0.0-20240911193312-2b36238f13e9 h1:si3PfKm8dDYxgfbeA6orqrtLkvvIeH8UqffFJDl0bz4=
+k8s.io/gengo/v2 v2.0.0-20240911193312-2b36238f13e9/go.mod h1:EJykeLsmFC60UQbYJezXkEsG2FLrt0GPNkU5iK5GWxU=
 k8s.io/klog/v2 v2.130.1 h1:n9Xl7H1Xvksem4KFG4PYbdQCQxqc/tTUyrgXaOhHSzk=
 k8s.io/klog/v2 v2.130.1/go.mod h1:3Jpz1GvMt720eyJH1ckRHK1EDfpxISzJ7I9OYgaDtPE=
-k8s.io/kms v0.31.3 h1:XCFmiJn5CCKs8xoOLpCmu42Ubm/KW85wNHybGFcSAYc=
-k8s.io/kms v0.31.3/go.mod h1:OZKwl1fan3n3N5FFxnW5C4V3ygrah/3YXeJWS3O6+94=
-k8s.io/kube-openapi v0.0.0-20240228011516-70dd3763d340 h1:BZqlfIlq5YbRMFko6/PM7FjZpUb45WallggurYhKGag=
-k8s.io/kube-openapi v0.0.0-20240228011516-70dd3763d340/go.mod h1:yD4MZYeKMBwQKVht279WycxKyM84kkAx2DPrTXaeb98=
-k8s.io/kube-scheduler v0.31.3 h1:indE2jtvbwyyEYDrQMjPR2EmnoM1pd4L6cK8r2/KY0I=
-k8s.io/kube-scheduler v0.31.3/go.mod h1:vhDtABcWycLi8139K5ScOg54WKlbEZJRgtQmLhW0Wjo=
-k8s.io/kubelet v0.31.3 h1:DIXRAmvVGp42mV2vpA1GCLU6oO8who0/vp3Oq6kSpbI=
-k8s.io/kubelet v0.31.3/go.mod h1:KSdbEfNy5VzqUlAHlytA/fH12s+sE1u8fb/8JY9sL/8=
-k8s.io/kubernetes v1.31.3 h1:oqb7HdfnTelrGlZ6ziNugvQ/L/aJWR704114EAhUn9Q=
-k8s.io/kubernetes v1.31.3/go.mod h1:9xmT2buyTYj8TRKwRae7FcuY8k5+xlxv7VivvO0KKfs=
-k8s.io/metrics v0.31.3 h1:DkT9I3gFlb2/z+/4BMY7WrQ/PnbukuV4Yli82v/KBCM=
-k8s.io/metrics v0.31.3/go.mod h1:2w9gpd8z+13oJmaPR6p3kDyrDqnxSyoKpnOw2qLIdhI=
-k8s.io/mount-utils v0.31.3 h1:CANy3prUYvvDCc2X7ZKgpjpDhAidx4gjGh/WwDrCPq8=
-k8s.io/mount-utils v0.31.3/go.mod h1:HV/VYBUGqYUj4vt82YltzpWvgv8FPg0G9ItyInT3NPU=
-k8s.io/utils v0.0.0-20240711033017-18e509b52bc8 h1:pUdcCO1Lk/tbT5ztQWOBi5HBgbBP1J8+AsQnQCKsi8A=
-k8s.io/utils v0.0.0-20240711033017-18e509b52bc8/go.mod h1:OLgZIPagt7ERELqWJFomSt595RzquPNLL48iOWgYOg0=
-sigs.k8s.io/apiserver-network-proxy/konnectivity-client v0.30.3 h1:2770sDpzrjjsAtVhSeUFseziht227YAWYHLGNM8QPwY=
-sigs.k8s.io/apiserver-network-proxy/konnectivity-client v0.30.3/go.mod h1:Ve9uj1L+deCXFrPOk1LpFXqTg7LCFzFso6PA48q/XZw=
+k8s.io/kms v0.32.2 h1:7Ff23ht7W40gTcDwUC8G5WjX5W/nxD8WxbNhIYYNZCI=
+k8s.io/kms v0.32.2/go.mod h1:Bk2evz/Yvk0oVrvm4MvZbgq8BD34Ksxs2SRHn4/UiOM=
+k8s.io/kube-openapi v0.0.0-20241105132330-32ad38e42d3f h1:GA7//TjRY9yWGy1poLzYYJJ4JRdzg3+O6e8I+e+8T5Y=
+k8s.io/kube-openapi v0.0.0-20241105132330-32ad38e42d3f/go.mod h1:R/HEjbvWI0qdfb8viZUeVZm0X6IZnxAydC7YU42CMw4=
+k8s.io/kube-scheduler v0.32.2 h1:vBm6iIjWaD10OPmtkt/503LTKvrN8dWVceeBcpKj/ns=
+k8s.io/kube-scheduler v0.32.2/go.mod h1:dD5yuYpnsCfgZmzvncUNPdvXGJXA1hw3gXq7DH3+aCQ=
+k8s.io/kubectl v0.32.2 h1:TAkag6+XfSBgkqK9I7ZvwtF0WVtUAvK8ZqTt+5zi1Us=
+k8s.io/kubectl v0.32.2/go.mod h1:+h/NQFSPxiDZYX/WZaWw9fwYezGLISP0ud8nQKg+3g8=
+k8s.io/kubelet v0.32.2 h1:WFTSYdt3BB1aTApDuKNI16x/4MYqqX8WBBBBh3KupDg=
+k8s.io/kubelet v0.32.2/go.mod h1:cC1ms5RS+lu0ckVr6AviCQXHLSPKEBC3D5oaCBdTGkI=
+k8s.io/kubernetes v1.32.2 h1:mShetlA102UpjRVSGzB+5vjJwy8oPy8FMWrkTH5f37o=
+k8s.io/kubernetes v1.32.2/go.mod h1:tiIKO63GcdPRBHW2WiUFm3C0eoLczl3f7qi56Dm1W8I=
+k8s.io/metrics v0.32.2 h1:7t/rZzTHFrGa9f94XcgLlm3ToAuJtdlHANcJEHlYl9g=
+k8s.io/metrics v0.32.2/go.mod h1:VL3nJpzcgB6L5nSljkkzoE0nilZhVgcjCfNRgoylaIQ=
+k8s.io/mount-utils v0.32.2 h1:aDwp+ucWiVnDr/LpRg88/dsXf/vm6gI1VZkYH3+3+Vw=
+k8s.io/mount-utils v0.32.2/go.mod h1:Kun5c2svjAPx0nnvJKYQWhfeNW+O0EpzHgRhDcYoSY0=
+k8s.io/pod-security-admission v0.32.2 h1:zDfAb/t0LbNU3z0ZMHtCb1zp8x05gWCGhmBYpUptm9A=
+k8s.io/pod-security-admission v0.32.2/go.mod h1:yxMPB3i1pGMLfxbe4BiWMuowMD7cdHR32y4nCj4wH+s=
+k8s.io/utils v0.0.0-20241104100929-3ea5e8cea738 h1:M3sRQVHv7vB20Xc2ybTt7ODCeFj6JSWYFzOFnYeS6Ro=
+k8s.io/utils v0.0.0-20241104100929-3ea5e8cea738/go.mod h1:OLgZIPagt7ERELqWJFomSt595RzquPNLL48iOWgYOg0=
+sigs.k8s.io/apiserver-network-proxy/konnectivity-client v0.31.0 h1:CPT0ExVicCzcpeN4baWEV2ko2Z/AsiZgEdwgcfwLgMo=
+sigs.k8s.io/apiserver-network-proxy/konnectivity-client v0.31.0/go.mod h1:Ve9uj1L+deCXFrPOk1LpFXqTg7LCFzFso6PA48q/XZw=
 sigs.k8s.io/controller-runtime v0.13.0 h1:iqa5RNciy7ADWnIc8QxCbOX5FEKVR3uxVxKHRMc2WIQ=
 sigs.k8s.io/controller-runtime v0.13.0/go.mod h1:Zbz+el8Yg31jubvAEyglRZGdLAjplZl+PgtYNI6WNTI=
-sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd h1:EDPBXCAspyGV4jQlpZSudPeMmr1bNJefnuqLsRAsHZo=
-sigs.k8s.io/json v0.0.0-20221116044647-bc3834ca7abd/go.mod h1:B8JuhiUyNFVKdsE8h686QcCxMaH6HrOAZj4vswFpcB0=
-sigs.k8s.io/structured-merge-diff/v4 v4.4.1 h1:150L+0vs/8DA78h1u02ooW1/fFq/Lwr+sGiqlzvrtq4=
-sigs.k8s.io/structured-merge-diff/v4 v4.4.1/go.mod h1:N8hJocpFajUSSeSJ9bOZ77VzejKZaXsTtZo4/u7Io08=
+sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3 h1:/Rv+M11QRah1itp8VhT6HoVx1Ray9eB4DBr+K+/sCJ8=
+sigs.k8s.io/json v0.0.0-20241010143419-9aa6b5e7a4b3/go.mod h1:18nIHnGi6636UCz6m8i4DhaJ65T6EruyzmoQqI2BVDo=
+sigs.k8s.io/structured-merge-diff/v4 v4.4.2 h1:MdmvkGuXi/8io6ixD5wud3vOLwc1rj0aNqRlpuvjmwA=
+sigs.k8s.io/structured-merge-diff/v4 v4.4.2/go.mod h1:N8f93tFZh9U6vpxwRArLiikrE5/2tiu1w1AGfACIGE4=
 sigs.k8s.io/yaml v1.4.0 h1:Mk1wCc2gy/F0THH0TAp1QYyJNzRm2KCLy3o5ASXVI5E=
 sigs.k8s.io/yaml v1.4.0/go.mod h1:Ejl7/uTz7PSA4eKMyQCUTnhZYNmLIl+5c2lQPGR2BPY=
 stathat.com/c/consistent v1.0.0 h1:ezyc51EGcRPJUxfHGSgJjWzJdj3NiMU9pNfLNGiXV0c=
 stathat.com/c/consistent v1.0.0/go.mod h1:QkzMWzcbB+yQBL2AttO6sgsQS/JSTapcDISJalmCDS0=
-volcano.sh/apis v1.11.0-network-topology-preview.2 h1:6zNehsV9RkBsK1O1U28Zx3dC1uHKqThANWyK+bHPoAM=
-volcano.sh/apis v1.11.0-network-topology-preview.2/go.mod h1:FOdmG++9+8lgENJ9XXDh+O3Jcb9YVRnlMSpgIh3NSVI=
+volcano.sh/apis v1.12.1 h1:yq5dVj/g21vnWObCIKsJKPhMoThpzDrHDD/GMouYVxk=
+volcano.sh/apis v1.12.1/go.mod h1:0XNNnIOevJSYNiXRmwhXUrYCcCcWcBeTY0nxrlkk03A=

hack/check-generated-yaml.sh

@@ -20,24 +20,25 @@ set -o pipefail
 
 VK_ROOT=$( cd "$( dirname "${BASH_SOURCE[0]}" )" && pwd )/..
 export RELEASE_FOLDER=${VK_ROOT}/${RELEASE_DIR}
+export RELEASE_TAG=${RELEASE_TAG:-"latest"}
 
-if ! diff ${VK_ROOT}/installer/volcano-development.yaml ${RELEASE_FOLDER}/volcano-v1.11.0-network-topology-preview.2.yaml ; then
+if ! diff ${VK_ROOT}/installer/volcano-development.yaml ${RELEASE_FOLDER}/volcano-${RELEASE_TAG}.yaml ; then
 	{
 		echo
 		echo "The Generated yaml is different from the one in installer/volcano-development.yaml"
-		echo "please run 'make generate-yaml TAG=v1.11.0-network-topology-preview.2 RELEASE_DIR=installer \
-		&& mv ${VK_ROOT}/installer/volcano-v1.11.0-network-topology-preview.2.yaml ${VK_ROOT}/installer/volcano-development.yaml' to update"
+		echo "please run 'make generate-yaml RELEASE_TAG=${RELEASE_TAG} RELEASE_DIR=installer \
+		&& mv ${VK_ROOT}/installer/volcano-${RELEASE_TAG}.yaml ${VK_ROOT}/installer/volcano-development.yaml' to update"
 		echo
 	} >&2
 	false
 fi
 
-if ! diff ${VK_ROOT}/installer/volcano-agent-development.yaml ${RELEASE_FOLDER}/volcano-agent-v1.11.0-network-topology-preview.2.yaml ; then
+if ! diff ${VK_ROOT}/installer/volcano-agent-development.yaml ${RELEASE_FOLDER}/volcano-agent-${RELEASE_TAG}.yaml ; then
 	{
 		echo
 		echo "The Generated yaml is different from the one in installer/volcano-agent-development.yaml"
-		echo "please run 'make generate-yaml TAG=v1.11.0-network-topology-preview.2 RELEASE_DIR=installer \
-		&& mv ${VK_ROOT}/installer/volcano-agent-v1.11.0-network-topology-preview.2.yaml ${VK_ROOT}/installer/volcano-agent-development.yaml' to update"
+		echo "please run 'make generate-yaml RELEASE_TAG=${RELEASE_TAG} RELEASE_DIR=installer \
+		&& mv ${VK_ROOT}/installer/volcano-agent-${RELEASE_TAG}.yaml ${VK_ROOT}/installer/volcano-agent-development.yaml' to update"
 		echo
 	} >&2
 	false

hack/e2e-kind-config.yaml

@@ -1,15 +1,29 @@
 # this config file contains all config fields with comments
 kind: Cluster
 apiVersion: kind.x-k8s.io/v1alpha4
+featureGates:
+  DynamicResourceAllocation: true
+  DRAResourceClaimDeviceStatus: true
+containerdConfigPatches:
+  # Enable CDI as described in
+  # https://tags.cncf.io/container-device-interface#containerd-configuration
+  - |-
+    [plugins."io.containerd.grpc.v1.cri"]
+      enable_cdi = true
 # 1 control plane node and 4 workers
 nodes:
   # the control plane node config
   - role: control-plane
     kubeadmConfigPatches:
-    - |
-      apiVersion: kubelet.config.k8s.io/v1beta1
-      kind: KubeletConfiguration
-      containerLogMaxSize: "50Mi"
+      - |
+        apiVersion: kubelet.config.k8s.io/v1beta1
+        kind: KubeletConfiguration
+        containerLogMaxSize: "50Mi"
+      - |
+        kind: ClusterConfiguration
+        apiServer:
+          extraArgs:
+            runtime-config: "resource.k8s.io/v1beta1=true"
   # the four workers
   - role: worker
   - role: worker

hack/generate-charts.sh

@@ -27,6 +27,10 @@ export RELEASE_FOLDER=${VK_ROOT}/${RELEASE_DIR}
 export HELM_VER=${HELM_VER:-v3.6.3}
 export VOLCANO_CHART_VERSION=${TAG:-"latest"}
 export VOLCANO_IMAGE_TAG=${VOLCANO_CHART_VERSION}
+# Add a v prefix to VOLCANO_IMAGE_TAG if it doesn't have one because v is removed in .github/workflows/release.yaml.
+if [[ ! ${VOLCANO_IMAGE_TAG} =~ ^v ]]; then
+    VOLCANO_IMAGE_TAG="v${VOLCANO_IMAGE_TAG}"
+fi
 
 LOCAL_OS=${OSTYPE}
 case $LOCAL_OS in

hack/generate-yaml.sh

@@ -41,7 +41,7 @@ case $CRD_VERSION in
   v1beta1)
     ;;
   *)
-    echo Invaild CRD_VERSION $CRD_VERSION !!!
+    echo Invalid CRD_VERSION $CRD_VERSION !!!
     echo CRD_VERSION only support \"bases\", \"v1\" and \"v1beta1\"
     exit 1
     ;;

hack/lib/install.sh

@@ -69,7 +69,7 @@ function check-kind {
   which kind >/dev/null 2>&1
   if [[ $? -ne 0 ]]; then
     echo "Installing kind ..."
-    GOOS=${OS} go install sigs.k8s.io/kind@v0.24.0
+    GOOS=${OS} go install sigs.k8s.io/kind@v0.26.0
   else
     echo -n "Found kind, version: " && kind version
   fi

hack/oss-fuzz-build.sh

@@ -0,0 +1,6 @@
+#!/bin/bash -eu
+
+printf "package job\nimport _ \"github.com/AdamKorcz/go-118-fuzz-build/testing\"\n" >"$SRC"/volcano/pkg/controllers/job/register.go
+go mod tidy
+compile_native_go_fuzzer volcano.sh/volcano/pkg/controllers/job FuzzApplyPolicies FuzzApplyPolicies 
+compile_native_go_fuzzer volcano.sh/volcano/pkg/controllers/job FuzzCreateJobPod FuzzCreateJobPod 

hack/run-e2e-kind.sh

@@ -62,20 +62,31 @@ basic:
   crd_version: ${crd_version}
 
 custom:
+  scheduler_log_level: 5
   admission_tolerations:
     - key: "node-role.kubernetes.io/control-plane"
       operator: "Exists"
       effect: "NoSchedule"
+    - key: "node-role.kubernetes.io/master"
+      operator: "Exists"
+      effect: "NoSchedule"
   controller_tolerations:
     - key: "node-role.kubernetes.io/control-plane"
       operator: "Exists"
       effect: "NoSchedule"
+    - key: "node-role.kubernetes.io/master"
+      operator: "Exists"
+      effect: "NoSchedule"
   scheduler_tolerations:
     - key: "node-role.kubernetes.io/control-plane"
       operator: "Exists"
       effect: "NoSchedule"
+    - key: "node-role.kubernetes.io/master"
+      operator: "Exists"
+      effect: "NoSchedule"
   default_ns:
     node-role.kubernetes.io/control-plane: ""
+  scheduler_feature_gates: ${FEATURE_GATES}
 EOF
 }
 
@@ -141,30 +152,35 @@ case ${E2E_TYPE} in
     KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --slow-spec-threshold='30s' --progress ./test/e2e/schedulingbase/
     KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --slow-spec-threshold='30s' --progress ./test/e2e/schedulingaction/
     KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --slow-spec-threshold='30s' --progress ./test/e2e/vcctl/
+    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --slow-spec-threshold='30s' --progress --focus="DRA E2E Test" ./test/e2e/dra/
     ;;
 "JOBP")
     echo "Running parallel job e2e suite..."
-    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --nodes=4 --compilers=4 --randomize-all --randomize-suites --fail-on-pending --cover --trace --race --slow-spec-threshold='30s' --progress ./test/e2e/jobp/
+    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -v -r --nodes=4 --compilers=4 --randomize-all --randomize-suites --fail-on-pending --cover --trace --race --slow-spec-threshold='30s' --progress ./test/e2e/jobp/
     ;;
 "JOBSEQ")
     echo "Running sequence job e2e suite..."
-    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --slow-spec-threshold='30s' --progress ./test/e2e/jobseq/
+    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -v -r --slow-spec-threshold='30s' --progress ./test/e2e/jobseq/
     ;;
 "SCHEDULINGBASE")
     echo "Running scheduling base e2e suite..."
-    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --slow-spec-threshold='30s' --progress ./test/e2e/schedulingbase/
+    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -v -r --slow-spec-threshold='30s' --progress ./test/e2e/schedulingbase/
     ;;
 "SCHEDULINGACTION")
     echo "Running scheduling action e2e suite..."
-    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --slow-spec-threshold='30s' --progress ./test/e2e/schedulingaction/
+    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -v -r --slow-spec-threshold='30s' --progress ./test/e2e/schedulingaction/
     ;;
 "VCCTL")
     echo "Running vcctl e2e suite..."
-    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --slow-spec-threshold='30s' --progress ./test/e2e/vcctl/
+    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -v -r --slow-spec-threshold='30s' --progress ./test/e2e/vcctl/
     ;;
 "STRESS")
     echo "Running stress e2e suite..."
-    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -r --slow-spec-threshold='30s' --progress ./test/e2e/stress/
+    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -v -r --slow-spec-threshold='30s' --progress ./test/e2e/stress/
+    ;;
+"DRA")
+    echo "Running dra e2e suite..."
+    KUBECONFIG=${KUBECONFIG} GOOS=${OS} ginkgo -v -r --slow-spec-threshold='30s' --progress --focus="DRA E2E Test" ./test/e2e/dra/
     ;;
 esac
 

hack/sync-scheduler-code.sh

@@ -25,7 +25,7 @@ CHECK_GIT_REMOTE=${CHECK_GIT_REMOTE:-true}
 # Useful Defaults
 ## Target github organization name
 TARGET_ORG=${TARGET_ORG:-"volcano-sh"}
-## main repo uptream configs
+## main repo upstream configs
 UPSTREAM=${UPSTREAM:-"upstream"}
 UPSTREAM_HEAD=${UPSTREAM_HEAD:-"master"}
 UPSTREAM_REPO_NAME=${UPSTREAM_REPO_NAME:-"volcano"}

hack/update-vendor-licenses.sh

@@ -163,7 +163,7 @@ cd "${LICENSE_ROOT}"
 
 kube::util::ensure-temp-dir
 
-# Save the genreated LICENSE file for each package temporarily
+# Save the generated LICENSE file for each package temporarily
 TMP_LICENSE_FILE="${KUBE_TEMP}/LICENSES.$$"
 
 # The directory to save all the LICENSE files

hack/verify-golangci-lint.sh

@@ -27,7 +27,7 @@ function check_golangci-lint() {
   command -v golangci-lint >/dev/null 2>&1
   if [[ $? -ne 0 ]]; then
     echo "installing golangci-lint ."
-    curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin v1.54.2
+    curl -sSfL https://raw.githubusercontent.com/golangci/golangci-lint/master/install.sh | sh -s -- -b $(go env GOPATH)/bin v1.60.3
     if [[ $? -ne 0 ]]; then
       echo "golangci-lint installed failed, exiting."
       exit 1

installer/README.md

@@ -100,6 +100,7 @@ The following are the list configurable parameters of Volcano Chart and their de
 |`custom.leader_elect_enable`|Whether to Enable leader elect|`false`|
 |`custom.admission_config_override`|Override admission configmap|`~`|
 |`custom.scheduler_config_override`|Override scheduler configmap|`~`|
+| `custom.controller_config_override`| Override controller configmap|`~`|
 |`custom.default_affinity`|Default affinity for Admission/Controller/Scheduler pods|`~`|
 |`custom.admission_affinity`|Affinity for Admission pods|`~`|
 |`custom.controller_affinity`|Affinity for Controller pods|`~`|
@@ -130,6 +131,7 @@ The following are the list configurable parameters of Volcano Chart and their de
 |`custom.controller_log_level`|Settings log print level for Controller|`4`|
 |`custom.scheduler_resources`|Resources for Scheduler pods|`~`|
 |`custom.scheduler_log_level`|Settings log print level for Scheduler|`3`|
+|`custom.scheduler_plugins_dir`| Settings dir for the Scheduler to load custom plugins|``|
 |`custom.webhooks_namespace_selector_expressions`|Additional namespace selector expressions for Volcano admission webhooks|`~`|
 |`service.ipFamilyPolicy`|Settings service the family policy|``|
 |`service.ipFamilies`|Settings service the address families|`[]`|

installer/build/volcano-agent/install.sh

@@ -14,6 +14,8 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
+set -e
+
 VOLCANO_AGENT_LOG_DIR="/var/log/volcano/agent"
 VOLCANO_AGENT_LOG_PATH="${VOLCANO_AGENT_LOG_DIR}/volcano-agent.log"
 NETWORK_QOS_LOG_PATH="${VOLCANO_AGENT_LOG_DIR}/network-qos.log"
@@ -53,5 +55,9 @@ touch ${VOLCANO_AGENT_LOG_PATH}
 touch ${NETWORK_QOS_LOG_PATH}
 touch ${NETWORK_QOS_TOOLS_LOG_PATH}
 
+chmod 750 ${VOLCANO_AGENT_LOG_DIR}
+chown -R 1000:1000 ${VOLCANO_AGENT_LOG_DIR}
+chmod 640 ${VOLCANO_AGENT_LOG_DIR}/*.log
+
 set_memory_qos_enabled
 set_sched_prio_load_balance_enabled

installer/dockerfile/agent/Dockerfile

@@ -15,7 +15,7 @@
 ARG OPEN_EULER_IMAGE_TAG
 ARG BWM_RPM_NAME
 
-FROM golang:1.22.2 AS builder
+FROM golang:1.23.7 AS builder
 WORKDIR /go/src/volcano.sh/
 COPY go.mod go.sum ./
 RUN go mod download
@@ -29,10 +29,14 @@ RUN yum install -y cpio && \
     rpm2cpio $(ls | grep oncn-bwm) | cpio -div
 
 FROM alpine:latest
-RUN apk add sudo
+RUN apk add sudo libcap
 COPY --from=builder /go/src/volcano.sh/volcano/_output/bin/vc-agent /vc-agent
 COPY --from=builder /go/src/volcano.sh/volcano/_output/bin/network-qos \
                     /go/src/volcano.sh/volcano/installer/build/volcano-agent/install.sh /usr/local/bin/
 COPY --from=repo /usr/share/bwmcli/bwm_tc.o /usr/local/bin/
-RUN chmod +x /usr/local/bin/install.sh
+RUN adduser -u 1000 -D appuser
+RUN chmod +x /usr/local/bin/install.sh \
+    && setcap "cap_dac_override=eip" /vc-agent \
+    && setcap "cap_dac_override=eip" /usr/local/bin/network-qos \
+    && echo -e '%appuser ALL=(root) NOPASSWD: /bin/cp -f /usr/local/bin/network-qos /opt/cni/bin\n%appuser ALL=(root) NOPASSWD: /bin/cp -f /usr/local/bin/bwm_tc.o /usr/share/bwmcli' >> /etc/sudoers
 

installer/dockerfile/controller-manager/Dockerfile

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-FROM golang:1.22.2 AS builder
+FROM golang:1.23.7 AS builder
 WORKDIR /go/src/volcano.sh/
 COPY go.mod go.sum ./
 RUN go mod download

installer/dockerfile/scheduler/Dockerfile

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-FROM golang:1.22.2 AS builder
+FROM golang:1.23.7 AS builder
 WORKDIR /go/src/volcano.sh/
 COPY go.mod go.sum ./
 RUN go mod download

installer/dockerfile/webhook-manager/Dockerfile

@@ -12,7 +12,7 @@
 # See the License for the specific language governing permissions and
 # limitations under the License.
 
-FROM golang:1.22.2 AS builder
+FROM golang:1.23.7 AS builder
 WORKDIR /go/src/volcano.sh/
 COPY go.mod go.sum ./
 RUN go mod download
@@ -20,14 +20,14 @@ ADD . volcano
 RUN cd volcano && make vc-webhook-manager
 
 FROM alpine:latest
-ARG KUBE_VERSION="1.31.0"
+ARG KUBE_VERSION="1.32.0"
 ARG TARGETARCH
 ARG APK_MIRROR
 RUN if [[ -n "$APK_MIRROR" ]]; then sed -i "s@https://dl-cdn.alpinelinux.org@${APK_MIRROR}@g" /etc/apk/repositories ; fi && \
     apk add --update ca-certificates && \
     apk add --update openssl && \
     apk add --update -t deps curl && \
-    curl -L https://storage.googleapis.com/kubernetes-release/release/v$KUBE_VERSION/bin/linux/$TARGETARCH/kubectl -o /usr/local/bin/kubectl && \
+    curl -L https://dl.k8s.io/release/v$KUBE_VERSION/bin/linux/$TARGETARCH/kubectl -o /usr/local/bin/kubectl && \
     chmod +x /usr/local/bin/kubectl && \
     apk del --purge deps && \
     rm /var/cache/apk/*

installer/helm/chart/volcano/Chart.yaml

@@ -1,7 +1,7 @@
 apiVersion: v1
 description: A Helm chart for Volcano
 name: volcano
-version: "1.11.0-network-topology-preview.2"
+version: "1.5"
 appVersion: "0.1"
 icon: https://raw.githubusercontent.com/volcano-sh/charts/master/docs/images/volcano-logo.png
 home: https://volcano.sh

installer/helm/chart/volcano/charts/jobflow/crd/bases/flow.volcano.sh_jobflows.yaml

@@ -2,7 +2,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: jobflows.flow.volcano.sh
 spec:
   group: flow.volcano.sh

installer/helm/chart/volcano/charts/jobflow/crd/bases/flow.volcano.sh_jobtemplates.yaml

@@ -2,7 +2,7 @@ apiVersion: apiextensions.k8s.io/v1
 kind: CustomResourceDefinition
 metadata:
   annotations:
-    controller-gen.kubebuilder.io/version: v0.16.4
+    controller-gen.kubebuilder.io/version: v0.17.0
   name: jobtemplates.flow.volcano.sh
 spec:
   group: flow.volcano.sh
@@ -2810,6 +2810,39 @@ spec:
                               x-kubernetes-list-map-keys:
                               - name
                               x-kubernetes-list-type: map
+                            resources:
+                              properties:
+                                claims:
+                                  items:
+                                    properties:
+                                      name:
+                                        type: string
+                                      request:
+                                        type: string
+                                    required:
+                                    - name
+                                    type: object
+                                  type: array
+                                  x-kubernetes-list-map-keys:
+                                  - name
+                                  x-kubernetes-list-type: map
+                                limits:
+                                  additionalProperties:
+                                    anyOf:
+                                    - type: integer
+                                    - type: string
+                                    pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
+                                    x-kubernetes-int-or-string: true
+                                  type: object
+                                requests:
+                                  additionalProperties:
+                                    anyOf:
+                                    - type: integer
+                                    - type: string
+                                    pattern: ^(\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))(([KMGTPE]i)|[numkMGTPE]|([eE](\+|-)?(([0-9]+(\.[0-9]*)?)|(\.[0-9]+))))?$
+                                    x-kubernetes-int-or-string: true
+                                  type: object
+                              type: object
                             restartPolicy:
                               type: string
                             runtimeClassName:
@@ -2852,6 +2885,8 @@ spec:
                                 runAsUser:
                                   format: int64
                                   type: integer
+                                seLinuxChangePolicy:
+                                  type: string
                                 seLinuxOptions:
                                   properties:
                                     level:

installer/helm/chart/volcano/config/volcano-scheduler-ci.conf

@@ -11,6 +11,8 @@ tiers:
   - name: drf
     enablePreemptable: false
   - name: predicates
+    arguments:
+      predicate.DynamicResourceAllocationEnable: true
   - name: proportion
   - name: nodeorder
   - name: binpack