Check CentOS-Base.repo exists for CentOS 7 (#11546)

Signed-off-by: tu1h <lihai.tu@daocloud.io>
Co-authored-by: tu1h <lihai.tu@daocloud.io>

.ansible-lint

@@ -36,8 +36,3 @@ exclude_paths:
   # Generated files
   - tests/files/custom_cni/cilium.yaml
   - venv
-  - .github
-  - .ansible
-  - .cache
-mock_modules:
-  - gluster.gluster.gluster_volume

.gitattributes

@@ -1 +0,0 @@
-docs/_sidebar.md linguist-generated=true

.github/ISSUE_TEMPLATE/bug-report.yaml

@@ -36,35 +36,11 @@ body:
     attributes:
       value: '### Environment'
 
-  - type: dropdown
+  - type: textarea
     id: os
     attributes:
       label: OS
-      options:
+      placeholder: 'printf "$(uname -srm)\n$(cat /etc/os-release)\n"'
-        - 'RHEL 9'
-        - 'RHEL 8'
-        - 'Fedora 40'
-        - 'Ubuntu 24'
-        - 'Ubuntu 22'
-        - 'Ubuntu 20'
-        - 'Debian 12'
-        - 'Debian 11'
-        - 'Flatcar Container Linux'
-        - 'openSUSE Leap'
-        - 'openSUSE Tumbleweed'
-        - 'Oracle Linux 9'
-        - 'Oracle Linux 8'
-        - 'AlmaLinux 9'
-        - 'AlmaLinux 8'
-        - 'Rocky Linux 9'
-        - 'Rocky Linux 8'
-        - 'Amazon Linux 2'
-        - 'Kylin Linux Advanced Server V10'
-        - 'UOS Linux 20'
-        - 'openEuler 24'
-        - 'openEuler 22'
-        - 'openEuler 20'
-        - 'Other|Unsupported'
     validations:
       required: true
 
@@ -117,24 +93,17 @@ body:
     attributes:
       label: Full inventory with variables
       placeholder: 'ansible -i inventory/sample/inventory.ini all -m debug -a "var=hostvars[inventory_hostname]"'
-      description: We recommend using snippets services like https://gist.github.com/ etc.
-    validations:
-      required: true
 
   - type: input
     id: ansible_command
     attributes:
       label: Command used to invoke ansible
-    validations:
-      required: true
 
   - type: textarea
     id: ansible_output
     attributes:
       label: Output of ansible run
       description: We recommend using snippets services like https://gist.github.com/ etc.
-    validations:
-      required: true
 
   - type: textarea
     id: anything_else

.github/ISSUE_TEMPLATE/config.yml

@@ -1,5 +1,4 @@
 ---
-blank_issues_enabled: false
 contact_links:
   - name: Support Request
     url: https://kubernetes.slack.com/channels/kubespray

.github/dependabot.yml

@@ -1,20 +0,0 @@
-version: 2
-updates:
-  - package-ecosystem: "pip"
-    directory: "/"
-    schedule:
-      interval: "weekly"
-    labels:
-      - dependencies
-      - release-note-none
-    groups:
-      molecule:
-        patterns:
-          - molecule
-          - molecule-plugins*
-  - package-ecosystem: "github-actions"
-    directory: "/"
-    labels:
-      - release-note-none
-    schedule:
-      interval: "weekly"

.github/workflows/auto-label-os.yml

@@ -1,32 +0,0 @@
-name: Issue labeler
-on:
-  issues:
-    types: [opened]
-
-permissions:
-  contents: read
-
-jobs:
-  label-component:
-    runs-on: ubuntu-latest
-    permissions:
-      issues: write
-
-    steps:
-      - uses: actions/checkout@v3
-
-      - name: Parse issue form
-        uses: stefanbuck/github-issue-parser@v3
-        id: issue-parser
-        with:
-          template-path: .github/ISSUE_TEMPLATE/bug-report.yaml
-
-      - name: Set labels based on OS field
-        uses: redhat-plumbers-in-action/advanced-issue-labeler@v2
-        with:
-          issue-form: ${{ steps.issue-parser.outputs.jsonString }}
-          section: os
-          block-list: |
-            None
-            Other
-          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/upgrade-patch-versions-schedule.yml

@@ -1,54 +0,0 @@
-name: Upgrade Kubespray components with new patches versions - all branches
-
-on:
-  schedule:
-  - cron: '22 2 * * *' # every day, 02:22 UTC
-  workflow_dispatch:
-
-permissions: {}
-jobs:
-  get-releases-branches:
-    runs-on: ubuntu-latest
-    outputs:
-      branches: ${{ steps.get-branches.outputs.data }}
-    steps:
-    - uses: octokit/graphql-action@v2.3.2
-      id: get-branches
-      with:
-        query: |
-          query get_release_branches($owner:String!, $name:String!) {
-            repository(owner:$owner, name:$name) {
-              refs(refPrefix: "refs/heads/",
-                   first: 0, # TODO increment once we have release branch with the new checksums format
-                   query: "release-",
-                   orderBy: {
-                     field: ALPHABETICAL,
-                     direction: DESC
-                   }) {
-                     nodes {
-                       name
-                     }
-              }
-            }
-          }
-        variables: |
-          owner: ${{ github.repository_owner }}
-          name: ${{ github.event.repository.name }}
-      env:
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-
-  update-versions:
-    needs: get-releases-branches
-    strategy:
-      fail-fast: false
-      matrix:
-        branch:
-          - name: ${{ github.event.repository.default_branch }}
-          -  ${{ fromJSON(needs.get-releases-branches.outputs.branches).repository.refs.nodes }}
-    uses: ./.github/workflows/upgrade-patch-versions.yml
-    permissions:
-      contents: write
-      pull-requests: write
-    name: Update patch updates on ${{ matrix.branch.name }}
-    with:
-      branch: ${{ matrix.branch.name }}

.github/workflows/upgrade-patch-versions.yml

@@ -1,44 +0,0 @@
-on:
-  workflow_call:
-    inputs:
-      branch:
-        description: Which branch to update with new patch versions
-        default: master
-        required: true
-        type: string
-
-jobs:
-  update-patch-versions:
-    runs-on: ubuntu-latest
-    steps:
-    - uses: actions/checkout@v4
-      with:
-        ref: ${{ inputs.branch }}
-    - uses: actions/setup-python@v5
-      with:
-        python-version: '3.13'
-        cache: 'pip'
-    - run: pip install scripts/component_hash_update pre-commit
-    - run: update-hashes
-      env:
-        API_KEY: ${{ secrets.GITHUB_TOKEN }}
-    - uses: actions/cache@v4
-      with:
-        key: pre-commit-hook-propagate
-        path: |
-          ~/.cache/pre-commit
-    - run: pre-commit run --all-files propagate-ansible-variables
-      continue-on-error: true
-    - uses: peter-evans/create-pull-request@v7
-      with:
-        commit-message: Patch versions updates
-        title: Patch versions updates - ${{ inputs.branch }}
-        labels: bot
-        branch: ${{ inputs.branch }}-patch-updates
-        sign-commits: true
-        body: |
-          /kind feature
-
-          ```release-note
-          NONE
-          ```

.gitignore

@@ -3,8 +3,6 @@
 **/vagrant_ansible_inventory
 *.iml
 temp
-contrib/offline/container-images
-contrib/offline/container-images.tar.gz
 contrib/offline/offline-files
 contrib/offline/offline-files.tar.gz
 .idea

.gitlab-ci.yml

@@ -1,34 +1,37 @@
 ---
 stages:
   - build
-  - test
+  - unit-tests
   - deploy-part1
-  - deploy-extended
+  - moderator
+  - deploy-part2
+  - deploy-part3
+  - deploy-special
 
 variables:
+  KUBESPRAY_VERSION: v2.23.2
   FAILFASTCI_NAMESPACE: 'kargo-ci'
   GITLAB_REPOSITORY: 'kargo-ci/kubernetes-sigs-kubespray'
-  GIT_CONFIG_COUNT: 2
-  GIT_CONFIG_KEY_0: user.email
-  GIT_CONFIG_VALUE_0: "ci@kubespray.io"
-  GIT_CONFIG_KEY_1: user.name
-  GIT_CONFIG_VALUE_1: "Kubespray CI"
   ANSIBLE_FORCE_COLOR: "true"
   MAGIC: "ci check this"
+  TEST_ID: "$CI_PIPELINE_ID-$CI_JOB_ID"
+  CI_TEST_VARS: "./tests/files/${CI_JOB_NAME}.yml"
+  CI_TEST_REGISTRY_MIRROR: "./tests/common/_docker_hub_registry_mirror.yml"
+  CI_TEST_SETTING: "./tests/common/_kubespray_test_settings.yml"
   GS_ACCESS_KEY_ID: $GS_KEY
   GS_SECRET_ACCESS_KEY: $GS_SECRET
   CONTAINER_ENGINE: docker
+  SSH_USER: root
   GCE_PREEMPTIBLE: "false"
   ANSIBLE_KEEP_REMOTE_FILES: "1"
   ANSIBLE_CONFIG: ./tests/ansible.cfg
-  ANSIBLE_REMOTE_USER: kubespray
+  ANSIBLE_INVENTORY: ./inventory/sample/${CI_JOB_NAME}-${BUILD_NUMBER}.ini
-  ANSIBLE_PRIVATE_KEY_FILE: /tmp/id_rsa
+  IDEMPOT_CHECK: "false"
-  ANSIBLE_INVENTORY: /tmp/inventory
   RESET_CHECK: "false"
   REMOVE_NODE_CHECK: "false"
   UPGRADE_TEST: "false"
   MITOGEN_ENABLE: "false"
-  ANSIBLE_VERBOSITY: 2
+  ANSIBLE_LOG_LEVEL: "-vv"
   RECOVER_CONTROL_PLANE_TEST: "false"
   RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:]:kube_control_plane[1:]"
   TERRAFORM_VERSION: 1.3.7
@@ -40,27 +43,16 @@ before_script:
 
 .job: &job
   tags:
-    - ffci
+    - packet
   image: $PIPELINE_IMAGE
   artifacts:
     when: always
     paths:
       - cluster-dump/
-  needs:
-    - pipeline-image
-  variables:
-    ANSIBLE_STDOUT_CALLBACK: "debug"
-
-.job-moderated:
-  extends: .job
-  needs:
-    - pipeline-image
-    - ci-not-authorized
-    - pre-commit            # lint
-    - vagrant-validate      # lint
 
 .testcases: &testcases
-  extends: .job-moderated
+  <<: *job
+  retry: 1
   interruptible: true
   before_script:
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
@@ -73,34 +65,19 @@ before_script:
 
 # For failfast, at least 1 job must be defined in .gitlab-ci.yml
 # Premoderated with manual actions
-ci-not-authorized:
+ci-authorized:
-  stage: build
+  extends: .job
-  before_script: []
+  stage: moderator
-  after_script: []
-  rules:
-    # LGTM or ok-to-test labels
-    - if: $PR_LABELS =~ /.*,(lgtm|approved|ok-to-test).*|^(lgtm|approved|ok-to-test).*/i
-      variables:
-        CI_OK_TO_TEST: '0'
-      when: always
-    - if: $CI_PIPELINE_SOURCE == "schedule" || $CI_PIPELINE_SOURCE == "trigger"
-      variables:
-        CI_OK_TO_TEST: '0'
-    - if: $CI_COMMIT_BRANCH == "master"
-      variables:
-        CI_OK_TO_TEST: '0'
-    - when: always
-      variables:
-        CI_OK_TO_TEST: '1'
   script:
-    - exit $CI_OK_TO_TEST
+    - /bin/sh scripts/premoderator.sh
-  tags:
+  except: ['triggers', 'master']
-    - ffci
+  # Disable ci moderator
-  needs: []
+  only: []
 
 include:
   - .gitlab-ci/build.yml
   - .gitlab-ci/lint.yml
+  - .gitlab-ci/shellcheck.yml
   - .gitlab-ci/terraform.yml
   - .gitlab-ci/packet.yml
   - .gitlab-ci/vagrant.yml

.gitlab-ci/build.yml

@@ -1,33 +1,40 @@
 ---
-.build-container:
+.build:
-  cache:
-    key: $CI_COMMIT_REF_SLUG
-    paths:
-      - image-cache
-  tags:
-    - ffci
   stage: build
   image:
-    name: gcr.io/kaniko-project/executor:debug
+    name: moby/buildkit:rootless
-    entrypoint: ['']
+    entrypoint: [""]
   variables:
-    TAG: $CI_COMMIT_SHORT_SHA
+    BUILDKITD_FLAGS: --oci-worker-no-process-sandbox
-    PROJECT_DIR: $CI_PROJECT_DIR
-    DOCKERFILE: Dockerfile
-    GODEBUG: "http2client=0"
   before_script:
-    - echo "{\"auths\":{\"$CI_REGISTRY\":{\"auth\":\"$(echo -n ${CI_REGISTRY_USER}:${CI_REGISTRY_PASSWORD} | base64)\"}}}" > /kaniko/.docker/config.json
+    - mkdir ~/.docker
-  script:
+    - echo "{\"auths\":{\"$CI_REGISTRY\":{\"username\":\"$CI_REGISTRY_USER\",\"password\":\"$CI_REGISTRY_PASSWORD\"}}}" > ~/.docker/config.json
-    - /kaniko/executor --cache=true
-                       --cache-dir=image-cache
-                       --context $PROJECT_DIR
-                       --dockerfile $PROJECT_DIR/$DOCKERFILE
-                       --label 'git-branch'=$CI_COMMIT_REF_SLUG
-                       --label 'git-tag=$CI_COMMIT_TAG'
-                       --destination $PIPELINE_IMAGE
-                       --log-timestamp=true
 
-pipeline-image:
+pipeline image:
-  extends: .build-container
+  extends: .build
-  variables:
+  script:
-    DOCKERFILE: pipeline.Dockerfile
+    - |
+      buildctl-daemonless.sh build \
+        --frontend=dockerfile.v0 \
+        --local context=. \
+        --local dockerfile=. \
+        --opt filename=./pipeline.Dockerfile \
+        --output type=image,name=$PIPELINE_IMAGE,push=true \
+        --import-cache type=registry,ref=$CI_REGISTRY_IMAGE/pipeline:cache
+  rules:
+    - if: '$CI_COMMIT_REF_NAME != $CI_DEFAULT_BRANCH'
+
+pipeline image and build cache:
+  extends: .build
+  script:
+    - |
+      buildctl-daemonless.sh build \
+        --frontend=dockerfile.v0 \
+        --local context=. \
+        --local dockerfile=. \
+        --opt filename=./pipeline.Dockerfile \
+        --output type=image,name=$PIPELINE_IMAGE,push=true \
+        --import-cache type=registry,ref=$CI_REGISTRY_IMAGE/pipeline:cache \
+        --export-cache type=registry,ref=$CI_REGISTRY_IMAGE/pipeline:cache,mode=max
+  rules:
+    - if: '$CI_COMMIT_REF_NAME == $CI_DEFAULT_BRANCH'

.gitlab-ci/lint.yml

@@ -1,26 +1,118 @@
 ---
-pre-commit:
+yamllint:
-  stage: test
+  extends: .job
-  tags:
+  stage: unit-tests
-  - ffci
+  tags: [light]
-  image: 'ghcr.io/pre-commit-ci/runner-image@sha256:fe01a6ec51b298412990b88627c3973b1146c7304f930f469bafa29ba60bcde9'
   variables:
-    PRE_COMMIT_HOME: ${CI_PROJECT_DIR}/.cache/pre-commit
+    LANG: C.UTF-8
   script:
-  - pre-commit run --all-files --show-diff-on-failure
+    - yamllint --strict .
-  cache:
+  except: ['triggers', 'master']
-    key: pre-commit-2
-    paths:
-    - ${PRE_COMMIT_HOME}
-    when: 'always'
-  needs: []
 
 vagrant-validate:
   extends: .job
-  stage: test
+  stage: unit-tests
-  tags: [ffci]
+  tags: [light]
   variables:
     VAGRANT_VERSION: 2.3.7
   script:
-  - ./tests/scripts/vagrant-validate.sh
+    - ./tests/scripts/vagrant-validate.sh
   except: ['triggers', 'master']
+
+ansible-lint:
+  extends: .job
+  stage: unit-tests
+  tags: [light]
+  script:
+    - ansible-lint -v
+  except: ['triggers', 'master']
+
+jinja-syntax-check:
+  extends: .job
+  stage: unit-tests
+  tags: [light]
+  script:
+    - "find -name '*.j2' -exec tests/scripts/check-templates.py {} +"
+  except: ['triggers', 'master']
+
+syntax-check:
+  extends: .job
+  stage: unit-tests
+  tags: [light]
+  variables:
+    ANSIBLE_INVENTORY: inventory/local-tests.cfg
+    ANSIBLE_REMOTE_USER: root
+    ANSIBLE_BECOME: "true"
+    ANSIBLE_BECOME_USER: root
+    ANSIBLE_VERBOSITY: "3"
+  script:
+    - ansible-playbook --syntax-check cluster.yml
+    - ansible-playbook --syntax-check playbooks/cluster.yml
+    - ansible-playbook --syntax-check upgrade-cluster.yml
+    - ansible-playbook --syntax-check playbooks/upgrade_cluster.yml
+    - ansible-playbook --syntax-check reset.yml
+    - ansible-playbook --syntax-check playbooks/reset.yml
+    - ansible-playbook --syntax-check extra_playbooks/upgrade-only-k8s.yml
+  except: ['triggers', 'master']
+
+collection-build-install-sanity-check:
+  extends: .job
+  stage: unit-tests
+  tags: [light]
+  variables:
+    ANSIBLE_COLLECTIONS_PATH: "./ansible_collections"
+  script:
+    - ansible-galaxy collection build
+    - ansible-galaxy collection install kubernetes_sigs-kubespray-$(grep "^version:" galaxy.yml | awk '{print $2}').tar.gz
+    - ansible-galaxy collection list $(egrep -i '(name:\s+|namespace:\s+)' galaxy.yml | awk '{print $2}' | tr '\n' '.' | sed 's|\.$||g') | grep "^kubernetes_sigs.kubespray"
+    - test -f ansible_collections/kubernetes_sigs/kubespray/playbooks/cluster.yml
+    - test -f ansible_collections/kubernetes_sigs/kubespray/playbooks/reset.yml
+  except: ['triggers', 'master']
+
+tox-inventory-builder:
+  stage: unit-tests
+  tags: [light]
+  extends: .job
+  before_script:
+    - ./tests/scripts/rebase.sh
+  script:
+    - pip3 install tox
+    - cd contrib/inventory_builder && tox
+  except: ['triggers', 'master']
+
+markdownlint:
+  stage: unit-tests
+  tags: [light]
+  image: node
+  before_script:
+    - npm install -g markdownlint-cli@0.22.0
+  script:
+    - markdownlint $(find . -name '*.md' | grep -vF './.git') --ignore docs/_sidebar.md --ignore contrib/dind/README.md
+
+check-readme-versions:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/check_readme_versions.sh
+
+check-galaxy-version:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/check_galaxy_version.sh
+
+check-typo:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/check_typo.sh
+
+ci-matrix:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/md-table/test.sh

.gitlab-ci/molecule.yml

@@ -1,15 +1,24 @@
 ---
 .molecule:
-  tags: [ffci]
+  tags: [ffci-vm-med]
   only: [/^pr-.*$/]
   except: ['triggers']
+  image: quay.io/kubespray/vm-kubespray-ci:v6
+  services: []
   stage: deploy-part1
-  image: $PIPELINE_IMAGE
+  variables:
-  needs:
+    VAGRANT_DEFAULT_PROVIDER: "libvirt"
-  - pipeline-image
-  # - ci-not-authorized
   before_script:
+  - groups
+  - python3 -m venv citest
+  - source citest/bin/activate
+  - vagrant plugin expunge --reinstall --force --no-tty
+  - vagrant plugin install vagrant-libvirt
+  - pip install --no-compile --no-cache-dir pip -U
+  - pip install --no-compile --no-cache-dir -r $CI_PROJECT_DIR/requirements.txt
+  - pip install --no-compile --no-cache-dir -r $CI_PROJECT_DIR/tests/requirements.txt
   - ./tests/scripts/rebase.sh
+  - ./tests/scripts/vagrant_clean.sh
   script:
   - ./tests/scripts/molecule_run.sh
   after_script:
@@ -19,38 +28,66 @@
     paths:
     - molecule_logs/
 
-molecule:
-  extends: .molecule
-  script:
-  - ./tests/scripts/molecule_run.sh -i $ROLE
-  parallel:
-    matrix:
-    - ROLE:
-      - container-engine/cri-dockerd
-      - container-engine/containerd
-      - container-engine/cri-o
-      - adduser
-      - bastion-ssh-config
-      - bootstrap-os
-
 # CI template for periodic CI jobs
 # Enabled when PERIODIC_CI_ENABLED var is set
-molecule_full:
+
+.molecule_periodic:
   only:
     variables:
     - $PERIODIC_CI_ENABLED
   allow_failure: true
-  extends: molecule
+  extends: .molecule
-  parallel:
+
-    matrix:
+molecule_full:
-    - ROLE:
+  extends: .molecule_periodic
-      - container-engine/cri-dockerd
+
-      - container-engine/containerd
+molecule_no_container_engines:
-      - container-engine/cri-o
+  extends: .molecule
-      - adduser
+  script:
-      - bastion-ssh-config
+  - ./tests/scripts/molecule_run.sh -e container-engine
-      - bootstrap-os
+  when: on_success
-      # FIXME : tests below are perma-failing
+
-      - container-engine/kata-containers
+molecule_docker:
-      - container-engine/gvisor
+  extends: .molecule
-      - container-engine/youki
+  script:
+  - ./tests/scripts/molecule_run.sh -i container-engine/cri-dockerd
+  when: on_success
+
+molecule_containerd:
+  extends: .molecule
+  script:
+  - ./tests/scripts/molecule_run.sh -i container-engine/containerd
+  when: on_success
+
+molecule_cri-o:
+  extends: .molecule
+  stage: deploy-part2
+  script:
+  - ./tests/scripts/molecule_run.sh -i container-engine/cri-o
+  allow_failure: true
+  when: on_success
+
+# Stage 3 container engines don't get as much attention so allow them to fail
+molecule_kata:
+  extends: .molecule
+  stage: deploy-part3
+  allow_failure: true
+  script:
+  - ./tests/scripts/molecule_run.sh -i container-engine/kata-containers
+  when: on_success
+
+molecule_gvisor:
+  extends: .molecule
+  stage: deploy-part3
+  allow_failure: true
+  script:
+  - ./tests/scripts/molecule_run.sh -i container-engine/gvisor
+  when: on_success
+
+molecule_youki:
+  extends: .molecule
+  stage: deploy-part3
+  allow_failure: true
+  script:
+  - ./tests/scripts/molecule_run.sh -i container-engine/youki
+  when: on_success

.gitlab-ci/packet.yml

@@ -6,56 +6,14 @@
     CI_PLATFORM: packet
     SSH_USER: kubespray
   tags:
-    - ffci
+    - packet
-  needs:
+  except: [triggers]
-    - pipeline-image
-    - ci-not-authorized
 
 # CI template for PRs
 .packet_pr:
-  stage: deploy-part1
+  only: [/^pr-.*$/]
-  rules:
-    - if: $PR_LABELS =~ /.*ci-short.*/
-      when: manual
-      allow_failure: true
-    - if: $CI_COMMIT_BRANCH =~ /^pr-.*$/
-      when: on_success
-    - when: manual
-      allow_failure: true
   extends: .packet
 
-  ## Uncomment this to have multiple stages
-  # needs:
-  #   - packet_ubuntu20-calico-all-in-one
-
-.packet_pr_short:
-  stage: deploy-part1
-  extends: .packet
-  rules:
-    - if: $CI_COMMIT_BRANCH =~ /^pr-.*$/
-      when: on_success
-    - when: manual
-      allow_failure: true
-
-.packet_pr_manual:
-  extends: .packet_pr
-  stage: deploy-extended
-  rules:
-    - if: $PR_LABELS =~ /.*ci-full.*/
-      when: on_success
-    # Else run as manual
-    - when: manual
-      allow_failure: true
-
-.packet_pr_extended:
-  extends: .packet_pr
-  stage: deploy-extended
-  rules:
-    - if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
-      when: on_success
-    - when: manual
-      allow_failure: true
-
 # CI template for periodic CI jobs
 # Enabled when PERIODIC_CI_ENABLED var is set
 .packet_periodic:
@@ -65,193 +23,315 @@
   allow_failure: true
   extends: .packet
 
+packet_cleanup_old:
+  stage: deploy-part1
+  extends: .packet_periodic
+  script:
+    - cd tests
+    - make cleanup-packet
+  after_script: []
+
 # The ubuntu20-calico-all-in-one jobs are meant as early stages to prevent running the full CI if something is horribly broken
 packet_ubuntu20-calico-all-in-one:
   stage: deploy-part1
-  extends: .packet_pr_short
+  extends: .packet_pr
+  when: on_success
   variables:
     RESET_CHECK: "true"
 
 # ### PR JOBS PART2
 
-packet_ubuntu20-crio:
+packet_ubuntu20-all-in-one-docker:
-  extends: .packet_pr_manual
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_ubuntu20-calico-all-in-one-hardening:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_ubuntu22-all-in-one-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
 
 packet_ubuntu22-calico-all-in-one:
+  stage: deploy-part2
   extends: .packet_pr
+  when: on_success
 
-packet_ubuntu22-calico-all-in-one-upgrade:
+packet_ubuntu22-calico-etcd-datastore:
+  stage: deploy-part2
   extends: .packet_pr
-  variables:
+  when: on_success
-    UPGRADE_TEST: graceful
 
-packet_ubuntu24-calico-etcd-datastore:
+packet_centos7-flannel-addons-ha:
   extends: .packet_pr
+  stage: deploy-part2
+  when: on_success
 
-packet_almalinux9-crio:
+packet_almalinux8-crio:
   extends: .packet_pr
+  stage: deploy-part2
+  when: on_success
+  allow_failure: true
 
-packet_almalinux9-kube-ovn:
+packet_ubuntu20-crio:
   extends: .packet_pr
+  stage: deploy-part2
+  when: manual
 
-packet_debian11-calico-collection:
+packet_fedora37-crio:
   extends: .packet_pr
+  stage: deploy-part2
+  when: manual
 
-packet_debian11-macvlan:
+packet_ubuntu20-flannel-ha:
+  stage: deploy-part2
   extends: .packet_pr
+  when: manual
+
+packet_debian10-cilium-svc-proxy:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_debian10-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian10-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian11-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian11-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian12-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian12-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
 
 packet_debian12-cilium:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_centos7-calico-ha-once-localhost:
+  stage: deploy-part2
   extends: .packet_pr
+  when: on_success
+  variables:
+    # This will instruct Docker not to start over TLS.
+    DOCKER_TLS_CERTDIR: ""
+  services:
+    - docker:19.03.9-dind
+
+packet_almalinux8-kube-ovn:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
 
 packet_almalinux8-calico:
+  stage: deploy-part2
   extends: .packet_pr
+  when: on_success
 
 packet_rockylinux8-calico:
+  stage: deploy-part2
   extends: .packet_pr
+  when: on_success
+
+packet_rockylinux9-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
 
 packet_rockylinux9-cilium:
+  stage: deploy-part2
   extends: .packet_pr
+  when: on_success
   variables:
     RESET_CHECK: "true"
 
-# Need an update of the container image to use schema v2
+packet_almalinux8-docker:
-# update: quay.io/kubespray/vm-amazon-linux-2:latest
+  stage: deploy-part2
-packet_amazon-linux-2-all-in-one:
-  extends: .packet_pr_manual
-  rules:
-    - when: manual
-      allow_failure: true
-
-packet_opensuse15-6-calico:
   extends: .packet_pr
+  when: on_success
+
+packet_fedora38-docker-weave:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+  allow_failure: true
+
+packet_opensuse-docker-cilium:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+# ### MANUAL JOBS
+
+packet_ubuntu20-docker-weave-sep:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
 
 packet_ubuntu20-cilium-sep:
+  stage: deploy-special
   extends: .packet_pr
+  when: manual
 
-packet_openeuler24-calico:
+packet_ubuntu20-flannel-ha-once:
+  stage: deploy-part2
   extends: .packet_pr
+  when: manual
 
-packet_ubuntu20-calico-all-in-one-hardening:
+# Calico HA eBPF
+packet_almalinux8-calico-ha-ebpf:
+  stage: deploy-part2
   extends: .packet_pr
+  when: manual
 
-## Extended
+packet_debian10-macvlan:
-packet_debian11-docker:
+  stage: deploy-part2
-  extends: .packet_pr_extended
+  extends: .packet_pr
+  when: manual
 
-packet_debian12-docker:
+packet_centos7-calico-ha:
-  extends: .packet_pr_extended
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
 
-packet_debian12-calico:
+packet_centos7-multus-calico:
-  extends: .packet_pr_extended
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
 
-packet_almalinux9-calico-remove-node:
+packet_fedora38-docker-calico:
-  extends: .packet_pr_extended
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    RESET_CHECK: "true"
+
+packet_fedora37-calico-selinux:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_fedora37-calico-swap-selinux:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_amazon-linux-2-all-in-one:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_almalinux8-calico-nodelocaldns-secondary:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_fedora38-kube-ovn:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_debian11-custom-cni:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_debian11-kubelet-csr-approver:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_debian12-custom-cni-helm:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+# ### PR JOBS PART3
+# Long jobs (45min+)
+
+packet_centos7-weave-upgrade-ha:
+  stage: deploy-part3
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    UPGRADE_TEST: basic
+
+packet_ubuntu20-calico-etcd-kubeadm-upgrade-ha:
+  stage: deploy-part3
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    UPGRADE_TEST: basic
+
+# Calico HA Wireguard
+packet_ubuntu20-calico-ha-wireguard:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_debian11-calico-upgrade:
+  stage: deploy-part3
+  extends: .packet_pr
+  when: on_success
+  variables:
+    UPGRADE_TEST: graceful
+
+packet_almalinux8-calico-remove-node:
+  stage: deploy-part3
+  extends: .packet_pr
+  when: on_success
   variables:
     REMOVE_NODE_CHECK: "true"
     REMOVE_NODE_NAME: "instance-3"
 
-packet_rockylinux9-calico:
-  extends: .packet_pr_extended
-
-packet_almalinux9-calico:
-  extends: .packet_pr_extended
-
-packet_almalinux9-docker:
-  extends: .packet_pr_extended
-
-packet_opensuse15-6-docker-cilium:
-  extends: .packet_pr_extended
-
-packet_ubuntu24-calico-all-in-one:
-  extends: .packet_pr_extended
-
 packet_ubuntu20-calico-etcd-kubeadm:
-  extends: .packet_pr_extended
+  stage: deploy-part3
-
+  extends: .packet_pr
-packet_ubuntu24-all-in-one-docker:
+  when: on_success
-  extends: .packet_pr_extended
-
-packet_ubuntu22-all-in-one-docker:
-  extends: .packet_pr_extended
-
-# ### MANUAL JOBS
-packet_fedora39-crio:
-  extends: .packet_pr_manual
-
-packet_ubuntu20-flannel-ha:
-  extends: .packet_pr_manual
-
-packet_ubuntu20-all-in-one-docker:
-  extends: .packet_pr_manual
-
-packet_ubuntu20-flannel-ha-once:
-  extends: .packet_pr_manual
-
-packet_fedora39-calico-swap-selinux:
-  extends: .packet_pr_manual
-
-packet_almalinux9-calico-ha-ebpf:
-  extends: .packet_pr_manual
-
-packet_almalinux9-calico-nodelocaldns-secondary:
-  extends: .packet_pr_manual
-
-packet_debian11-custom-cni:
-  extends: .packet_pr_manual
-
-packet_debian11-kubelet-csr-approver:
-  extends: .packet_pr_manual
-
-packet_debian12-custom-cni-helm:
-  extends: .packet_pr_manual
-
-packet_ubuntu20-calico-ha-wireguard:
-  extends: .packet_pr_manual
-
-# PERIODIC
-packet_fedora40-docker-calico:
-  stage: deploy-extended
-  extends: .packet_periodic
-  variables:
-    RESET_CHECK: "true"
-
-packet_fedora39-calico-selinux:
-  stage: deploy-extended
-  extends: .packet_periodic
-
-packet_ubuntu20-calico-etcd-kubeadm-upgrade-ha:
-  stage: deploy-extended
-  extends: .packet_periodic
-  variables:
-    UPGRADE_TEST: basic
-
 
 packet_debian11-calico-upgrade-once:
-  stage: deploy-extended
+  stage: deploy-part3
   extends: .packet_periodic
+  when: on_success
   variables:
     UPGRADE_TEST: graceful
 
 packet_ubuntu20-calico-ha-recover:
-  stage: deploy-extended
+  stage: deploy-part3
   extends: .packet_periodic
+  when: on_success
   variables:
     RECOVER_CONTROL_PLANE_TEST: "true"
     RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:]:kube_control_plane[1:]"
 
 packet_ubuntu20-calico-ha-recover-noquorum:
-  stage: deploy-extended
+  stage: deploy-part3
   extends: .packet_periodic
+  when: on_success
   variables:
     RECOVER_CONTROL_PLANE_TEST: "true"
     RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[1:]:kube_control_plane[1:]"
-
-packet_debian11-calico-upgrade:
-  stage: deploy-extended
-  extends: .packet_periodic
-  variables:
-    UPGRADE_TEST: graceful
-
-packet_debian12-cilium-svc-proxy:
-  stage: deploy-extended
-  extends: .packet_periodic

.gitlab-ci/shellcheck.yml

@@ -0,0 +1,16 @@
+---
+shellcheck:
+  extends: .job
+  stage: unit-tests
+  tags: [light]
+  variables:
+    SHELLCHECK_VERSION: v0.7.1
+  before_script:
+    - ./tests/scripts/rebase.sh
+    - curl --silent --location "https://github.com/koalaman/shellcheck/releases/download/"${SHELLCHECK_VERSION}"/shellcheck-"${SHELLCHECK_VERSION}".linux.x86_64.tar.xz" | tar -xJv
+    - cp shellcheck-"${SHELLCHECK_VERSION}"/shellcheck /usr/bin/
+    - shellcheck --version
+  script:
+    # Run shellcheck for all *.sh
+    - find . -name '*.sh' -not -path './.git/*' | xargs shellcheck --severity error
+  except: ['triggers', 'master']

.gitlab-ci/terraform.yml

@@ -2,10 +2,6 @@
 # Tests for contrib/terraform/
 .terraform_install:
   extends: .job
-  needs:
-    - ci-not-authorized
-    - pipeline-image
-  stage: deploy-part1
   before_script:
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
     - ./tests/scripts/rebase.sh
@@ -28,19 +24,17 @@
 
 .terraform_validate:
   extends: .terraform_install
-  tags: [ffci]
+  stage: unit-tests
+  tags: [light]
   only: ['master', /^pr-.*$/]
   script:
     - terraform -chdir="contrib/terraform/$PROVIDER" validate
     - terraform -chdir="contrib/terraform/$PROVIDER" fmt -check -diff
-  stage: test
-  needs:
-    - pipeline-image
 
 .terraform_apply:
   extends: .terraform_install
-  tags: [ffci]
+  tags: [light]
-  stage: deploy-extended
+  stage: deploy-part3
   when: manual
   only: [/^pr-.*$/]
   artifacts:
@@ -152,7 +146,8 @@ tf-validate-nifcloud:
   TF_VAR_router_id: "ab95917c-41fb-4881-b507-3a6dfe9403df"
 
 tf-elastx_cleanup:
-  tags: [ffci]
+  stage: unit-tests
+  tags: [light]
   image: python
   variables:
     <<: *elastx_variables
@@ -164,7 +159,7 @@ tf-elastx_cleanup:
 
 tf-elastx_ubuntu20-calico:
   extends: .terraform_apply
-  stage: deploy-part1
+  stage: deploy-part3
   when: on_success
   allow_failure: true
   variables:

.gitlab-ci/vagrant.yml

@@ -1,8 +1,6 @@
 ---
 .vagrant:
   extends: .testcases
-  needs:
-    - ci-not-authorized
   variables:
     CI_PLATFORM: "vagrant"
     SSH_USER: "vagrant"
@@ -10,12 +8,10 @@
     KUBESPRAY_VAGRANT_CONFIG: tests/files/${CI_JOB_NAME}.rb
     DOCKER_NAME: vagrant
     VAGRANT_ANSIBLE_TAGS: facts
-    VAGRANT_HOME: "$CI_PROJECT_DIR/.vagrant.d"
-    PIP_CACHE_DIR: "$CI_PROJECT_DIR/.cache/pip"
   tags: [ffci-vm-large]
   # only: [/^pr-.*$/]
   # except: ['triggers']
-  image: quay.io/kubespray/vm-kubespray-ci:v13
+  image: quay.io/kubespray/vm-kubespray-ci:v6
   services: []
   before_script:
     - echo $USER
@@ -29,53 +25,36 @@
     - ./tests/scripts/vagrant_clean.sh
   script:
     - ./tests/scripts/testcases_run.sh
-  cache:
-    key: $CI_JOB_NAME_SLUG
-    paths:
-      - .vagrant.d/boxes
-      - .cache/pip
-    policy: pull-push # TODO: change to "pull" when not on main
 
-vagrant_ubuntu24-calico-dual-stack:
+vagrant_ubuntu20-calico-dual-stack:
-  stage: deploy-extended
+  stage: deploy-part2
   extends: .vagrant
-  rules:
+  when: manual
-    - if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
+# FIXME: this test if broken (perma-failing)
-      when: on_success
-  allow_failure: false
 
-vagrant_ubuntu24-calico-ipv6only-stack:
+vagrant_ubuntu20-weave-medium:
-  stage: deploy-extended
+  stage: deploy-part2
   extends: .vagrant
-  rules:
+  when: manual
-    - if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
-      when: on_success
-  allow_failure: false
 
 vagrant_ubuntu20-flannel:
-  stage: deploy-part1
+  stage: deploy-part2
   extends: .vagrant
   when: on_success
   allow_failure: false
 
 vagrant_ubuntu20-flannel-collection:
-  stage: deploy-extended
+  stage: deploy-part2
   extends: .vagrant
   when: manual
 
 vagrant_ubuntu20-kube-router-sep:
-  stage: deploy-extended
+  stage: deploy-part2
   extends: .vagrant
   when: manual
 
 # Service proxy test fails connectivity testing
 vagrant_ubuntu20-kube-router-svc-proxy:
-  stage: deploy-extended
+  stage: deploy-part2
   extends: .vagrant
   when: manual
-
-vagrant_fedora39-kube-router:
-  stage: deploy-extended
-  extends: .vagrant
-  when: manual
-# FIXME: this test if broken (perma-failing)

.markdownlint.yaml

@@ -0,0 +1,3 @@
+---
+MD013: false
+MD029: false

.md_style.rb

@@ -1,4 +0,0 @@
-all
-exclude_rule 'MD013'
-exclude_rule 'MD029'
-rule 'MD007', :indent => 2

.mdlrc

@@ -1 +0,0 @@
-style "#{File.dirname(__FILE__)}/.md_style.rb"

.pre-commit-config.yaml

@@ -1,7 +1,8 @@
 ---
 repos:
+
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0
+    rev: v3.4.0
     hooks:
       - id: check-added-large-files
       - id: check-case-conflict
@@ -15,68 +16,59 @@ repos:
       - id: trailing-whitespace
 
   - repo: https://github.com/adrienverge/yamllint.git
-    rev: v1.35.1
+    rev: v1.27.1
     hooks:
       - id: yamllint
         args: [--strict]
 
-  - repo: https://github.com/shellcheck-py/shellcheck-py
+  - repo: https://github.com/markdownlint/markdownlint
-    rev: v0.10.0.1
+    rev: v0.11.0
+    hooks:
+      - id: markdownlint
+        args: [ -r, "~MD013,~MD029" ]
+        exclude: "^.git"
+
+  - repo: https://github.com/jumanjihouse/pre-commit-hooks
+    rev: 3.0.0
     hooks:
       - id: shellcheck
-        args: ["--severity=error"]
+        args: [ --severity, "error" ]
         exclude: "^.git"
         files: "\\.sh$"
 
-  - repo: https://github.com/ansible/ansible-lint
-    rev: v25.1.1
-    hooks:
-      - id: ansible-lint
-        additional_dependencies:
-          - jmespath==1.0.1
-          - netaddr==1.3.0
-          - distlib
-
-  - repo: https://github.com/golangci/misspell
-    rev: v0.6.0
-    hooks:
-      - id: misspell
-        exclude: "OWNERS_ALIASES$"
-
   - repo: local
     hooks:
-      - id: collection-build-install
+      - id: ansible-lint
-        name: Build and install kubernetes-sigs.kubespray Ansible collection
+        name: ansible-lint
+        entry: ansible-lint -v
         language: python
+        pass_filenames: false
         additional_dependencies:
-          - ansible-core>=2.16.4
+          - .[community]
-          - distlib
+
-        entry: tests/scripts/collection-build-install.sh
+      - id: ansible-syntax-check
+        name: ansible-syntax-check
+        entry: env ANSIBLE_INVENTORY=inventory/local-tests.cfg ANSIBLE_REMOTE_USER=root ANSIBLE_BECOME="true" ANSIBLE_BECOME_USER=root ANSIBLE_VERBOSITY="3" ansible-playbook --syntax-check
+        language: python
+        files: "^cluster.yml|^upgrade-cluster.yml|^reset.yml|^extra_playbooks/upgrade-only-k8s.yml"
+
+      - id: tox-inventory-builder
+        name: tox-inventory-builder
+        entry: bash -c "cd contrib/inventory_builder && tox"
+        language: python
         pass_filenames: false
 
-      - id: generate-docs-sidebar
+      - id: check-readme-versions
-        name: generate-docs-sidebar
+        name: check-readme-versions
-        entry: scripts/gen_docs_sidebar.sh
+        entry: tests/scripts/check_readme_versions.sh
         language: script
         pass_filenames: false
 
       - id: ci-matrix
         name: ci-matrix
-        entry: tests/scripts/md-table/main.py
+        entry: tests/scripts/md-table/test.sh
-        language: python
+        language: script
         pass_filenames: false
-        additional_dependencies:
-          - jinja2
-          - pathlib
-          - pyaml
-
-      - id: check-galaxy-version
-        name: Verify correct version for galaxy.yml
-        entry: scripts/galaxy_version.py
-        language: python
-        pass_filenames: false
-        additional_dependencies:
-          - ruamel.yaml
 
       - id: jinja-syntax-check
         name: jinja-syntax-check
@@ -85,26 +77,4 @@ repos:
         types:
           - jinja
         additional_dependencies:
-          - jinja2
+          - Jinja2
-
-      - id: propagate-ansible-variables
-        name: Update static files referencing default kubespray values
-        language: python
-        additional_dependencies:
-          - ansible-core>=2.16.4
-        entry: scripts/propagate_ansible_variables.yml
-        pass_filenames: false
-
-      - id: check-checksums-sorted
-        name: Check that our checksums are correctly sorted by version
-        entry: scripts/assert-sorted-checksums.yml
-        language: python
-        pass_filenames: false
-        additional_dependencies:
-          - ansible
-
-  - repo: https://github.com/markdownlint/markdownlint
-    rev: v0.12.0
-    hooks:
-      - id: markdownlint
-        exclude: "^.github|(^docs/_sidebar\\.md$)"

.yamllint

@@ -3,10 +3,9 @@ extends: default
 
 ignore: |
   .git/
-  .github/
   # Generated file
   tests/files/custom_cni/cilium.yaml
-# https://ansible.readthedocs.io/projects/lint/rules/yaml/
+
 rules:
   braces:
     min-spaces-inside: 0
@@ -14,15 +13,9 @@ rules:
   brackets:
     min-spaces-inside: 0
     max-spaces-inside: 1
-  comments:
-    min-spaces-from-content: 1
-  # https://github.com/adrienverge/yamllint/issues/384
-  comments-indentation: false
   indentation:
     spaces: 2
     indent-sequences: consistent
   line-length: disable
   new-line-at-end-of-file: disable
-  octal-values:
+  truthy: disable
-    forbid-implicit-octal: true # yamllint defaults to false
-    forbid-explicit-octal: true # yamllint defaults to false

Dockerfile

@@ -34,9 +34,11 @@ RUN --mount=type=bind,source=requirements.txt,target=requirements.txt \
 
 SHELL ["/bin/bash", "-o", "pipefail", "-c"]
 
-RUN OS_ARCHITECTURE=$(dpkg --print-architecture) \
+RUN --mount=type=bind,source=roles/kubespray-defaults/defaults/main/main.yml,target=roles/kubespray-defaults/defaults/main/main.yml \
-    && curl -L "https://dl.k8s.io/release/v1.32.3/bin/linux/${OS_ARCHITECTURE}/kubectl" -o /usr/local/bin/kubectl \
+    KUBE_VERSION=$(sed -n 's/^kube_version: //p' roles/kubespray-defaults/defaults/main/main.yml) \
-    && echo "$(curl -L "https://dl.k8s.io/release/v1.32.3/bin/linux/${OS_ARCHITECTURE}/kubectl.sha256")" /usr/local/bin/kubectl | sha256sum --check \
+    OS_ARCHITECTURE=$(dpkg --print-architecture) \
+    && curl -L "https://dl.k8s.io/release/${KUBE_VERSION}/bin/linux/${OS_ARCHITECTURE}/kubectl" -o /usr/local/bin/kubectl \
+    && echo "$(curl -L "https://dl.k8s.io/release/${KUBE_VERSION}/bin/linux/${OS_ARCHITECTURE}/kubectl.sha256")" /usr/local/bin/kubectl | sha256sum --check \
     && chmod a+x /usr/local/bin/kubectl
 
 COPY *.yml ./

Makefile

@@ -0,0 +1,7 @@
+mitogen:
+	@echo Mitogen support is deprecated.
+	@echo Please run the following command manually:
+	@echo   ansible-playbook -c local mitogen.yml -vv
+clean:
+	rm -rf dist/
+	rm *.retry

OWNERS_ALIASES

@@ -1,26 +1,32 @@
 aliases:
   kubespray-approvers:
-    - cristicalin
-    - floryut
-    - liupeng0518
-    - mzaian
-    - oomichi
-    - yankay
-    - ant31
-    - vannten
-  kubespray-reviewers:
-    - cyclinder
-    - erikjiang
-    - mrfreezeex
-    - mzaian
-    - tico88612
-    - vannten
-    - yankay
-  kubespray-emeritus_approvers:
-    - atoms
-    - chadswen
-    - luckysb
     - mattymo
+    - chadswen
+    - mirwan
     - miouge1
+    - luckysb
+    - floryut
+    - oomichi
+    - cristicalin
+    - liupeng0518
+    - yankay
+    - mzaian
+  kubespray-reviewers:
+    - holmsten
+    - bozzo
+    - eppo
+    - oomichi
+    - jayonlau
+    - cristicalin
+    - liupeng0518
+    - yankay
+    - cyclinder
+    - mzaian
+    - mrfreezeex
+    - erikjiang
+    - vannten
+  kubespray-emeritus_approvers:
     - riverzhang
+    - atoms
+    - ant31
     - woopstar

README.md

@@ -5,7 +5,7 @@
 If you have questions, check the documentation at [kubespray.io](https://kubespray.io) and join us on the [kubernetes slack](https://kubernetes.slack.com), channel **\#kubespray**.
 You can get your invite [here](http://slack.k8s.io/)
 
-- Can be deployed on **[AWS](docs/cloud_providers/aws.md), GCE, [Azure](docs/cloud_providers/azure.md), [OpenStack](docs/cloud_controllers/openstack.md), [vSphere](docs/cloud_controllers/vsphere.md), [Equinix Metal](docs/cloud_providers/equinix-metal.md) (bare metal), Oracle Cloud Infrastructure (Experimental), or Baremetal**
+- Can be deployed on **[AWS](docs/aws.md), GCE, [Azure](docs/azure.md), [OpenStack](docs/openstack.md), [vSphere](docs/vsphere.md), [Equinix Metal](docs/equinix-metal.md) (bare metal), Oracle Cloud Infrastructure (Experimental), or Baremetal**
 - **Highly available** cluster
 - **Composable** (Choice of the network plugin for instance)
 - Supports most popular **Linux distributions**
@@ -15,27 +15,78 @@ You can get your invite [here](http://slack.k8s.io/)
 
 Below are several ways to use Kubespray to deploy a Kubernetes cluster.
 
-### Docker
-
-Ensure you have installed Docker then
-
-```ShellSession
-docker run --rm -it --mount type=bind,source="$(pwd)"/inventory/sample,dst=/inventory \
-  --mount type=bind,source="${HOME}"/.ssh/id_rsa,dst=/root/.ssh/id_rsa \
-  quay.io/kubespray/kubespray:v2.27.0 bash
-# Inside the container you may now run the kubespray playbooks:
-ansible-playbook -i /inventory/inventory.ini --private-key /root/.ssh/id_rsa cluster.yml
-```
-
 ### Ansible
 
 #### Usage
 
-See [Getting started](/docs/getting_started/getting-started.md)
+Install Ansible according to [Ansible installation guide](/docs/ansible.md#installing-ansible)
+then run the following steps:
+
+```ShellSession
+# Copy ``inventory/sample`` as ``inventory/mycluster``
+cp -rfp inventory/sample inventory/mycluster
+
+# Update Ansible inventory file with inventory builder
+declare -a IPS=(10.10.1.3 10.10.1.4 10.10.1.5)
+CONFIG_FILE=inventory/mycluster/hosts.yaml python3 contrib/inventory_builder/inventory.py ${IPS[@]}
+
+# Review and change parameters under ``inventory/mycluster/group_vars``
+cat inventory/mycluster/group_vars/all/all.yml
+cat inventory/mycluster/group_vars/k8s_cluster/k8s-cluster.yml
+
+# Clean up old Kubernetes cluster with Ansible Playbook - run the playbook as root
+# The option `--become` is required, as for example cleaning up SSL keys in /etc/,
+# uninstalling old packages and interacting with various systemd daemons.
+# Without --become the playbook will fail to run!
+# And be mind it will remove the current kubernetes cluster (if it's running)!
+ansible-playbook -i inventory/mycluster/hosts.yaml  --become --become-user=root reset.yml
+
+# Deploy Kubespray with Ansible Playbook - run the playbook as root
+# The option `--become` is required, as for example writing SSL keys in /etc/,
+# installing packages and interacting with various systemd daemons.
+# Without --become the playbook will fail to run!
+ansible-playbook -i inventory/mycluster/hosts.yaml  --become --become-user=root cluster.yml
+```
+
+Note: When Ansible is already installed via system packages on the control node,
+Python packages installed via `sudo pip install -r requirements.txt` will go to
+a different directory tree (e.g. `/usr/local/lib/python2.7/dist-packages` on
+Ubuntu) from Ansible's (e.g. `/usr/lib/python2.7/dist-packages/ansible` still on
+Ubuntu). As a consequence, the `ansible-playbook` command will fail with:
+
+```raw
+ERROR! no action detected in task. This often indicates a misspelled module name, or incorrect module path.
+```
+
+This likely indicates that a task depends on a module present in ``requirements.txt``.
+
+One way of addressing this is to uninstall the system Ansible package then
+reinstall Ansible via ``pip``, but this not always possible and one must
+take care regarding package versions.
+A workaround consists of setting the `ANSIBLE_LIBRARY`
+and `ANSIBLE_MODULE_UTILS` environment variables respectively to
+the `ansible/modules` and `ansible/module_utils` subdirectories of the ``pip``
+installation location, which is the ``Location`` shown by running
+`pip show [package]` before executing `ansible-playbook`.
+
+A simple way to ensure you get all the correct version of Ansible is to use
+the [pre-built docker image from Quay](https://quay.io/repository/kubespray/kubespray?tab=tags).
+You will then need to use [bind mounts](https://docs.docker.com/storage/bind-mounts/)
+to access the inventory and SSH key in the container, like this:
+
+```ShellSession
+git checkout v2.24.2
+docker pull quay.io/kubespray/kubespray:v2.24.2
+docker run --rm -it --mount type=bind,source="$(pwd)"/inventory/sample,dst=/inventory \
+  --mount type=bind,source="${HOME}"/.ssh/id_rsa,dst=/root/.ssh/id_rsa \
+  quay.io/kubespray/kubespray:v2.23.2 bash
+# Inside the container you may now run the kubespray playbooks:
+ansible-playbook -i /inventory/inventory.ini --private-key /root/.ssh/id_rsa cluster.yml
+```
 
 #### Collection
 
-See [here](docs/ansible/ansible_collection.md) if you wish to use this repository as an Ansible collection
+See [here](docs/ansible_collection.md) if you wish to use this repository as an Ansible collection
 
 ### Vagrant
 
@@ -48,7 +99,7 @@ python -V && pip -V
 
 If this returns the version of the software, you're good to go. If not, download and install Python from here <https://www.python.org/downloads/source/>
 
-Install Ansible according to [Ansible installation guide](/docs/ansible/ansible.md#installing-ansible)
+Install Ansible according to [Ansible installation guide](/docs/ansible.md#installing-ansible)
 then run the following step:
 
 ```ShellSession
@@ -58,104 +109,102 @@ vagrant up
 ## Documents
 
 - [Requirements](#requirements)
-- [Kubespray vs ...](docs/getting_started/comparisons.md)
+- [Kubespray vs ...](docs/comparisons.md)
-- [Getting started](docs/getting_started/getting-started.md)
+- [Getting started](docs/getting-started.md)
-- [Setting up your first cluster](docs/getting_started/setting-up-your-first-cluster.md)
+- [Setting up your first cluster](docs/setting-up-your-first-cluster.md)
-- [Ansible inventory and tags](docs/ansible/ansible.md)
+- [Ansible inventory and tags](docs/ansible.md)
-- [Integration with existing ansible repo](docs/operations/integration.md)
+- [Integration with existing ansible repo](docs/integration.md)
-- [Deployment data variables](docs/ansible/vars.md)
+- [Deployment data variables](docs/vars.md)
-- [DNS stack](docs/advanced/dns-stack.md)
+- [DNS stack](docs/dns-stack.md)
-- [HA mode](docs/operations/ha-mode.md)
+- [HA mode](docs/ha-mode.md)
 - [Network plugins](#network-plugins)
-- [Vagrant install](docs/developers/vagrant.md)
+- [Vagrant install](docs/vagrant.md)
-- [Flatcar Container Linux bootstrap](docs/operating_systems/flatcar.md)
+- [Flatcar Container Linux bootstrap](docs/flatcar.md)
-- [Fedora CoreOS bootstrap](docs/operating_systems/fcos.md)
+- [Fedora CoreOS bootstrap](docs/fcos.md)
-- [openSUSE setup](docs/operating_systems/opensuse.md)
+- [Debian Jessie setup](docs/debian.md)
-- [Downloaded artifacts](docs/advanced/downloads.md)
+- [openSUSE setup](docs/opensuse.md)
-- [Equinix Metal](docs/cloud_providers/equinix-metal.md)
+- [Downloaded artifacts](docs/downloads.md)
-- [OpenStack](docs/cloud_controllers/openstack.md)
+- [Cloud providers](docs/cloud.md)
-- [vSphere](docs/cloud_controllers/vsphere.md)
+- [OpenStack](docs/openstack.md)
-- [Large deployments](docs/operations/large-deployments.md)
+- [AWS](docs/aws.md)
-- [Adding/replacing a node](docs/operations/nodes.md)
+- [Azure](docs/azure.md)
-- [Upgrades basics](docs/operations/upgrades.md)
+- [vSphere](docs/vsphere.md)
-- [Air-Gap installation](docs/operations/offline-environment.md)
+- [Equinix Metal](docs/equinix-metal.md)
-- [NTP](docs/advanced/ntp.md)
+- [Large deployments](docs/large-deployments.md)
-- [Hardening](docs/operations/hardening.md)
+- [Adding/replacing a node](docs/nodes.md)
-- [Mirror](docs/operations/mirror.md)
+- [Upgrades basics](docs/upgrades.md)
-- [Roadmap](docs/roadmap/roadmap.md)
+- [Air-Gap installation](docs/offline-environment.md)
+- [NTP](docs/ntp.md)
+- [Hardening](docs/hardening.md)
+- [Mirror](docs/mirror.md)
+- [Roadmap](docs/roadmap.md)
 
 ## Supported Linux Distributions
 
 - **Flatcar Container Linux by Kinvolk**
-- **Debian** Bookworm, Bullseye
+- **Debian** Bookworm, Bullseye, Buster
-- **Ubuntu** 20.04, 22.04, 24.04
+- **Ubuntu** 20.04, 22.04
-- **CentOS/RHEL** [8, 9](docs/operating_systems/rhel.md#rhel-8)
+- **CentOS/RHEL** 7, [8, 9](docs/centos.md#centos-8)
-- **Fedora** 39, 40
+- **Fedora** 37, 38
-- **Fedora CoreOS** (see [fcos Note](docs/operating_systems/fcos.md))
+- **Fedora CoreOS** (see [fcos Note](docs/fcos.md))
 - **openSUSE** Leap 15.x/Tumbleweed
-- **Oracle Linux** [8, 9](docs/operating_systems/rhel.md#rhel-8)
+- **Oracle Linux** 7, [8, 9](docs/centos.md#centos-8)
-- **Alma Linux** [8, 9](docs/operating_systems/rhel.md#rhel-8)
+- **Alma Linux** [8, 9](docs/centos.md#centos-8)
-- **Rocky Linux** [8, 9](docs/operating_systems/rhel.md#rhel-8)
+- **Rocky Linux** [8, 9](docs/centos.md#centos-8)
-- **Kylin Linux Advanced Server V10** (experimental: see [kylin linux notes](docs/operating_systems/kylinlinux.md))
+- **Kylin Linux Advanced Server V10** (experimental: see [kylin linux notes](docs/kylinlinux.md))
-- **Amazon Linux 2** (experimental: see [amazon linux notes](docs/operating_systems/amazonlinux.md))
+- **Amazon Linux 2** (experimental: see [amazon linux notes](docs/amazonlinux.md))
-- **UOS Linux** (experimental: see [uos linux notes](docs/operating_systems/uoslinux.md))
+- **UOS Linux** (experimental: see [uos linux notes](docs/uoslinux.md))
-- **openEuler** (experimental: see [openEuler notes](docs/operating_systems/openeuler.md))
+- **openEuler** (experimental: see [openEuler notes](docs/openeuler.md))
 
-Note:
+Note: Upstart/SysV init based OS types are not supported.
-
-- Upstart/SysV init based OS types are not supported.
-- [Kernel requirements](docs/operations/kernel-requirements.md) (please read if the OS kernel version is < 4.19).
 
 ## Supported Components
 
-<!-- BEGIN ANSIBLE MANAGED BLOCK -->
-
 - Core
-  - [kubernetes](https://github.com/kubernetes/kubernetes) 1.32.3
+  - [kubernetes](https://github.com/kubernetes/kubernetes) v1.28.14
-  - [etcd](https://github.com/etcd-io/etcd) 3.5.16
+  - [etcd](https://github.com/etcd-io/etcd) v3.5.16
-  - [docker](https://www.docker.com/) 28.0
+  - [docker](https://www.docker.com/) v20.10 (see note)
-  - [containerd](https://containerd.io/) 2.0.4
+  - [containerd](https://containerd.io/) v1.7.22
-  - [cri-o](http://cri-o.io/) 1.32.0 (experimental: see [CRI-O Note](docs/CRI/cri-o.md). Only on fedora, ubuntu and centos based OS)
+  - [cri-o](http://cri-o.io/) v1.28 (experimental: see [CRI-O Note](docs/cri-o.md). Only on fedora, ubuntu and centos based OS)
 - Network Plugin
-  - [cni-plugins](https://github.com/containernetworking/plugins) 1.4.1
+  - [cni-plugins](https://github.com/containernetworking/plugins) v1.2.0
-  - [calico](https://github.com/projectcalico/calico) 3.29.3
+  - [calico](https://github.com/projectcalico/calico) v3.26.4
-  - [cilium](https://github.com/cilium/cilium) 1.15.9
+  - [cilium](https://github.com/cilium/cilium) v1.13.4
-  - [flannel](https://github.com/flannel-io/flannel) 0.22.0
+  - [flannel](https://github.com/flannel-io/flannel) v0.22.0
-  - [kube-ovn](https://github.com/alauda/kube-ovn) 1.12.21
+  - [kube-ovn](https://github.com/alauda/kube-ovn) v1.11.5
-  - [kube-router](https://github.com/cloudnativelabs/kube-router) 2.1.1
+  - [kube-router](https://github.com/cloudnativelabs/kube-router) v2.0.0
-  - [multus](https://github.com/k8snetworkplumbingwg/multus-cni) 4.1.0
+  - [multus](https://github.com/k8snetworkplumbingwg/multus-cni) v3.8
-  - [weave](https://github.com/rajch/weave) 2.8.7
+  - [weave](https://github.com/weaveworks/weave) v2.8.1
-  - [kube-vip](https://github.com/kube-vip/kube-vip) 0.8.0
+  - [kube-vip](https://github.com/kube-vip/kube-vip) v0.5.12
 - Application
-  - [cert-manager](https://github.com/jetstack/cert-manager) 1.15.3
+  - [cert-manager](https://github.com/jetstack/cert-manager) v1.13.2
-  - [coredns](https://github.com/coredns/coredns) 1.11.3
+  - [coredns](https://github.com/coredns/coredns) v1.10.1
-  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) 1.12.1
+  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v1.9.4
-  - [argocd](https://argoproj.github.io/) 2.14.5
+  - [krew](https://github.com/kubernetes-sigs/krew) v0.4.4
-  - [helm](https://helm.sh/) 3.16.4
+  - [argocd](https://argoproj.github.io/) v2.8.4
-  - [metallb](https://metallb.universe.tf/) 0.13.9
+  - [helm](https://helm.sh/) v3.13.1
-  - [registry](https://github.com/distribution/distribution) 2.8.1
+  - [metallb](https://metallb.universe.tf/)  v0.13.9
+  - [registry](https://github.com/distribution/distribution) v2.8.1
 - Storage Plugin
-  - [cephfs-provisioner](https://github.com/kubernetes-incubator/external-storage) 2.1.0-k8s1.11
+  - [cephfs-provisioner](https://github.com/kubernetes-incubator/external-storage) v2.1.0-k8s1.11
-  - [rbd-provisioner](https://github.com/kubernetes-incubator/external-storage) 2.1.1-k8s1.11
+  - [rbd-provisioner](https://github.com/kubernetes-incubator/external-storage) v2.1.1-k8s1.11
-  - [aws-ebs-csi-plugin](https://github.com/kubernetes-sigs/aws-ebs-csi-driver) 0.5.0
+  - [aws-ebs-csi-plugin](https://github.com/kubernetes-sigs/aws-ebs-csi-driver) v0.5.0
-  - [azure-csi-plugin](https://github.com/kubernetes-sigs/azuredisk-csi-driver) 1.10.0
+  - [azure-csi-plugin](https://github.com/kubernetes-sigs/azuredisk-csi-driver) v1.10.0
-  - [cinder-csi-plugin](https://github.com/kubernetes/cloud-provider-openstack/blob/master/docs/cinder-csi-plugin/using-cinder-csi-plugin.md) 1.30.0
+  - [cinder-csi-plugin](https://github.com/kubernetes/cloud-provider-openstack/blob/master/docs/cinder-csi-plugin/using-cinder-csi-plugin.md) v1.22.0
-  - [gcp-pd-csi-plugin](https://github.com/kubernetes-sigs/gcp-compute-persistent-disk-csi-driver) 1.9.2
+  - [gcp-pd-csi-plugin](https://github.com/kubernetes-sigs/gcp-compute-persistent-disk-csi-driver) v1.9.2
-  - [local-path-provisioner](https://github.com/rancher/local-path-provisioner) 0.0.24
+  - [local-path-provisioner](https://github.com/rancher/local-path-provisioner) v0.0.24
-  - [local-volume-provisioner](https://github.com/kubernetes-sigs/sig-storage-local-static-provisioner) 2.5.0
+  - [local-volume-provisioner](https://github.com/kubernetes-sigs/sig-storage-local-static-provisioner) v2.5.0
-  - [node-feature-discovery](https://github.com/kubernetes-sigs/node-feature-discovery) 0.16.4
-
-<!-- END ANSIBLE MANAGED BLOCK -->
 
 ## Container Runtime Notes
 
+- Supported Docker versions are 18.09, 19.03, 20.10, 23.0 and 24.0. The *recommended* Docker version is 20.10 (except on Debian bookworm which without supporting for 20.10 and below any more). `Kubelet` might break on docker's non-standard version numbering (it no longer uses semantic versioning). To ensure auto-updates don't break your cluster look into e.g. the YUM  ``versionlock`` plugin or ``apt pin``).
 - The cri-o version should be aligned with the respective kubernetes version (i.e. kube_version=1.20.x, crio_version=1.20)
 
 ## Requirements
 
-- **Minimum required version of Kubernetes is v1.30**
+- **Minimum required version of Kubernetes is v1.26**
 - **Ansible v2.14+, Jinja 2.11+ and python-netaddr is installed on the machine that will run Ansible commands**
-- The target servers must have **access to the Internet** in order to pull docker images. Otherwise, additional configuration is required (See [Offline Environment](docs/operations/offline-environment.md))
+- The target servers must have **access to the Internet** in order to pull docker images. Otherwise, additional configuration is required (See [Offline Environment](docs/offline-environment.md))
 - The target servers are configured to allow **IPv4 forwarding**.
 - If using IPv6 for pods and services, the target servers are configured to allow **IPv6 forwarding**.
 - The **firewalls are not managed**, you'll need to implement your own rules the way you used to.
@@ -167,16 +216,16 @@ Note:
 Hardware:
 These limits are safeguarded by Kubespray. Actual requirements for your workload can differ. For a sizing guide go to the [Building Large Clusters](https://kubernetes.io/docs/setup/cluster-large/#size-of-master-and-master-components) guide.
 
-- Control Plane
+- Master
-  - Memory: 2 GB
+  - Memory: 1500 MB
-- Worker Node
+- Node
-  - Memory: 1 GB
+  - Memory: 1024 MB
 
 ## Network Plugins
 
 You can choose among ten network plugins. (default: `calico`, except Vagrant uses `flannel`)
 
-- [flannel](docs/CNI/flannel.md): gre/vxlan (layer 2) networking.
+- [flannel](docs/flannel.md): gre/vxlan (layer 2) networking.
 
 - [Calico](https://docs.tigera.io/calico/latest/about/) is a networking and network policy provider. Calico supports a flexible set of networking options
     designed to give you the most efficient networking across a range of situations, including non-overlay
@@ -185,32 +234,32 @@ You can choose among ten network plugins. (default: `calico`, except Vagrant use
 
 - [cilium](http://docs.cilium.io/en/latest/): layer 3/4 networking (as well as layer 7 to protect and secure application protocols), supports dynamic insertion of BPF bytecode into the Linux kernel to implement security services, networking and visibility logic.
 
-- [weave](docs/CNI/weave.md): Weave is a lightweight container overlay network that doesn't require an external K/V database cluster.
+- [weave](docs/weave.md): Weave is a lightweight container overlay network that doesn't require an external K/V database cluster.
     (Please refer to `weave` [troubleshooting documentation](https://www.weave.works/docs/net/latest/troubleshooting/)).
 
-- [kube-ovn](docs/CNI/kube-ovn.md): Kube-OVN integrates the OVN-based Network Virtualization with Kubernetes. It offers an advanced Container Network Fabric for Enterprises.
+- [kube-ovn](docs/kube-ovn.md): Kube-OVN integrates the OVN-based Network Virtualization with Kubernetes. It offers an advanced Container Network Fabric for Enterprises.
 
-- [kube-router](docs/CNI/kube-router.md): Kube-router is a L3 CNI for Kubernetes networking aiming to provide operational
+- [kube-router](docs/kube-router.md): Kube-router is a L3 CNI for Kubernetes networking aiming to provide operational
     simplicity and high performance: it uses IPVS to provide Kube Services Proxy (if setup to replace kube-proxy),
     iptables for network policies, and BGP for ods L3 networking (with optionally BGP peering with out-of-cluster BGP peers).
     It can also optionally advertise routes to Kubernetes cluster Pods CIDRs, ClusterIPs, ExternalIPs and LoadBalancerIPs.
 
-- [macvlan](docs/CNI/macvlan.md): Macvlan is a Linux network driver. Pods have their own unique Mac and Ip address, connected directly the physical (layer 2) network.
+- [macvlan](docs/macvlan.md): Macvlan is a Linux network driver. Pods have their own unique Mac and Ip address, connected directly the physical (layer 2) network.
 
-- [multus](docs/CNI/multus.md): Multus is a meta CNI plugin that provides multiple network interface support to pods. For each interface Multus delegates CNI calls to secondary CNI plugins such as Calico, macvlan, etc.
+- [multus](docs/multus.md): Multus is a meta CNI plugin that provides multiple network interface support to pods. For each interface Multus delegates CNI calls to secondary CNI plugins such as Calico, macvlan, etc.
 
 - [custom_cni](roles/network-plugin/custom_cni/) : You can specify some manifests that will be applied to the clusters to bring you own CNI and use non-supported ones by Kubespray.
   See `tests/files/custom_cni/README.md` and `tests/files/custom_cni/values.yaml`for an example with a CNI provided by a Helm Chart.
 
 The network plugin to use is defined by the variable `kube_network_plugin`. There is also an
 option to leverage built-in cloud provider networking instead.
-See also [Network checker](docs/advanced/netcheck.md).
+See also [Network checker](docs/netcheck.md).
 
 ## Ingress Plugins
 
 - [nginx](https://kubernetes.github.io/ingress-nginx): the NGINX Ingress Controller.
 
-- [metallb](docs/ingress/metallb.md): the MetalLB bare-metal service LoadBalancer provider.
+- [metallb](docs/metallb.md): the MetalLB bare-metal service LoadBalancer provider.
 
 ## Community docs and resources
 
@@ -231,4 +280,4 @@ See also [Network checker](docs/advanced/netcheck.md).
 
 CI/end-to-end tests sponsored by: [CNCF](https://cncf.io), [Equinix Metal](https://metal.equinix.com/), [OVHcloud](https://www.ovhcloud.com/), [ELASTX](https://elastx.se/).
 
-See the [test matrix](docs/developers/test_cases.md) for details.
+See the [test matrix](docs/test_cases.md) for details.

RELEASE.md

@@ -3,19 +3,17 @@
 The Kubespray Project is released on an as-needed basis. The process is as follows:
 
 1. An issue is proposing a new release with a changelog since the last release. Please see [a good sample issue](https://github.com/kubernetes-sigs/kubespray/issues/8325)
-1. At least one of the [approvers](OWNERS_ALIASES) must approve this release
+2. At least one of the [approvers](OWNERS_ALIASES) must approve this release
-1. (Only for major releases) The `kube_version_min_required` variable is set to `n-1`
+3. The `kube_version_min_required` variable is set to `n-1`
-1. (Only for major releases) Remove hashes for [EOL versions](https://github.com/kubernetes/website/blob/main/content/en/releases/patch-releases.md) of kubernetes from `*_checksums` variables.
+4. Remove hashes for [EOL versions](https://github.com/kubernetes/website/blob/main/content/en/releases/patch-releases.md) of kubernetes from `*_checksums` variables.
-1. Create the release note with [Kubernetes Release Notes Generator](https://github.com/kubernetes/release/blob/master/cmd/release-notes/README.md). See the following `Release note creation` section for the details.
+5. Create the release note with [Kubernetes Release Notes Generator](https://github.com/kubernetes/release/blob/master/cmd/release-notes/README.md). See the following `Release note creation` section for the details.
-1. An approver creates [new release in GitHub](https://github.com/kubernetes-sigs/kubespray/releases/new) using a version and tag name like `vX.Y.Z` and attaching the release notes
+6. An approver creates [new release in GitHub](https://github.com/kubernetes-sigs/kubespray/releases/new) using a version and tag name like `vX.Y.Z` and attaching the release notes
-1. (Only for major releases) An approver creates a release branch in the form `release-X.Y`
+7. An approver creates a release branch in the form `release-X.Y`
-1. (For major releases) On the `master` branch: bump the version in `galaxy.yml` to the next expected major release (X.y.0 with y = Y + 1), make a Pull Request.
+8. The corresponding version of [quay.io/kubespray/kubespray:vX.Y.Z](https://quay.io/repository/kubespray/kubespray) and [quay.io/kubespray/vagrant:vX.Y.Z](https://quay.io/repository/kubespray/vagrant) container images are built and tagged. See the following `Container image creation` section for the details.
-1. (For minor releases) On the `release-X.Y` branch: bump the version in `galaxy.yml` to the next expected minor release (X.Y.z with z = Z + 1), make a Pull Request.
+9. The `KUBESPRAY_VERSION` variable is updated in `.gitlab-ci.yml`
-1. The corresponding version of [quay.io/kubespray/kubespray:vX.Y.Z](https://quay.io/repository/kubespray/kubespray) and [quay.io/kubespray/vagrant:vX.Y.Z](https://quay.io/repository/kubespray/vagrant) container images are built and tagged. See the following `Container image creation` section for the details.
+10. The release issue is closed
-1. The release issue is closed
+11. An announcement email is sent to `dev@kubernetes.io` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
-1. An announcement email is sent to `dev@kubernetes.io` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
+12. The topic of the #kubespray channel is updated with `vX.Y.Z is released! | ...`
-1. The topic of the #kubespray channel is updated with `vX.Y.Z is released! | ...`
-1. Create/Update Issue for upgradeing kubernetes and [k8s-conformance](https://github.com/cncf/k8s-conformance)
 
 ## Major/minor releases and milestones
 
@@ -45,7 +43,7 @@ The Kubespray Project is released on an as-needed basis. The process is as follo
 
 * Minor releases can change components' versions, but not the major `kube_version`.
   Greater `kube_version` requires a new major or minor release. For example, if Kubespray v2.0.0
-  is bound to `kube_version: 1.4.x`, `calico_version: 0.22.0`, `etcd_version: 3.0.6`,
+  is bound to `kube_version: 1.4.x`, `calico_version: 0.22.0`, `etcd_version: v3.0.6`,
   then Kubespray v2.1.0 may be bound to only minor changes to `kube_version`, like v1.5.1
   and *any* changes to other components, like etcd v4, or calico 1.2.3.
   And Kubespray v3.x.x shall be bound to `kube_version: 2.x.x` respectively.

SECURITY_CONTACTS

@@ -9,7 +9,7 @@
 #
 # DO NOT REPORT SECURITY VULNERABILITIES DIRECTLY TO THESE NAMES, FOLLOW THE
 # INSTRUCTIONS AT https://kubernetes.io/security/
+mattymo
 floryut
-ant31
+oomichi
-VannTen
+cristicalin
-yankay

Vagrantfile

@@ -1,7 +1,7 @@
 # -*- mode: ruby -*-
 # # vi: set ft=ruby :
 
-# For help on using kubespray with vagrant, check out docs/developers/vagrant.md
+# For help on using kubespray with vagrant, check out docs/vagrant.md
 
 require 'fileutils'
 
@@ -21,25 +21,21 @@ SUPPORTED_OS = {
   "flatcar-edge"        => {box: "flatcar-edge",               user: "core", box_url: FLATCAR_URL_TEMPLATE % ["edge"]},
   "ubuntu2004"          => {box: "generic/ubuntu2004",         user: "vagrant"},
   "ubuntu2204"          => {box: "generic/ubuntu2204",         user: "vagrant"},
-  "ubuntu2404"          => {box: "bento/ubuntu-24.04",         user: "vagrant"},
+  "centos"              => {box: "centos/7",                   user: "vagrant"},
+  "centos-bento"        => {box: "bento/centos-7.6",           user: "vagrant"},
   "centos8"             => {box: "centos/8",                   user: "vagrant"},
   "centos8-bento"       => {box: "bento/centos-8",             user: "vagrant"},
   "almalinux8"          => {box: "almalinux/8",                user: "vagrant"},
   "almalinux8-bento"    => {box: "bento/almalinux-8",          user: "vagrant"},
-  "almalinux9"          => {box: "almalinux/9",                user: "vagrant"},
+  "rockylinux8"         => {box: "generic/rocky8",             user: "vagrant"},
-  "rockylinux8"         => {box: "rockylinux/8",               user: "vagrant"},
+  "fedora37"            => {box: "fedora/37-cloud-base",       user: "vagrant"},
-  "rockylinux9"         => {box: "rockylinux/9",               user: "vagrant"},
+  "fedora38"            => {box: "fedora/38-cloud-base",       user: "vagrant"},
-  "fedora39"            => {box: "fedora/39-cloud-base",       user: "vagrant"},
+  "opensuse"            => {box: "opensuse/Leap-15.4.x86_64",  user: "vagrant"},
-  "fedora40"            => {box: "fedora/40-cloud-base",       user: "vagrant"},
-  "fedora39-arm64"      => {box: "bento/fedora-39-arm64",      user: "vagrant"},
-  "fedora40-arm64"      => {box: "bento/fedora-40",            user: "vagrant"},
-  "opensuse"            => {box: "opensuse/Leap-15.6.x86_64",  user: "vagrant"},
   "opensuse-tumbleweed" => {box: "opensuse/Tumbleweed.x86_64", user: "vagrant"},
   "oraclelinux"         => {box: "generic/oracle7",            user: "vagrant"},
   "oraclelinux8"        => {box: "generic/oracle8",            user: "vagrant"},
+  "rhel7"               => {box: "generic/rhel7",              user: "vagrant"},
   "rhel8"               => {box: "generic/rhel8",              user: "vagrant"},
-  "debian11"            => {box: "debian/bullseye64",          user: "vagrant"},
-  "debian12"            => {box: "debian/bookworm64",          user: "vagrant"},
 }
 
 if File.exist?(CONFIG)
@@ -58,27 +54,16 @@ $subnet ||= "172.18.8"
 $subnet_ipv6 ||= "fd3c:b398:0698:0756"
 $os ||= "ubuntu2004"
 $network_plugin ||= "flannel"
-$inventories ||= []
 # Setting multi_networking to true will install Multus: https://github.com/k8snetworkplumbingwg/multus-cni
 $multi_networking ||= "False"
 $download_run_once ||= "True"
 $download_force_cache ||= "False"
-# Modify those to have separate groups (for instance, to test separate etcd:)
-# first_control_plane = 1
-# first_etcd = 4
-# control_plane_instances = 3
-# etcd_instances = 3
-$first_node ||= 1
-$first_control_plane ||= 1
-$first_etcd ||= 1
-
 # The first three nodes are etcd servers
 $etcd_instances ||= [$num_instances, 3].min
 # The first two nodes are kube masters
-$control_plane_instances ||= [$num_instances, 2].min
+$kube_master_instances ||= [$num_instances, 2].min
 # All nodes are kube nodes
-$kube_node_instances ||= $num_instances - $first_node + 1
+$kube_node_instances ||= $num_instances
-
 # The following only works when using the libvirt provider
 $kube_node_instances_with_disks ||= false
 $kube_node_instances_with_disks_size ||= "20G"
@@ -92,10 +77,7 @@ $libvirt_nested ||= false
 $ansible_verbosity ||= false
 $ansible_tags ||= ENV['VAGRANT_ANSIBLE_TAGS'] || ""
 
-$vagrant_dir ||= File.join(File.dirname(__FILE__), ".vagrant")
-
 $playbook ||= "cluster.yml"
-$extra_vars ||= {}
 
 host_vars = {}
 
@@ -107,6 +89,19 @@ if ! SUPPORTED_OS.key?($os)
 end
 
 $box = SUPPORTED_OS[$os][:box]
+# if $inventory is not set, try to use example
+$inventory = "inventory/sample" if ! $inventory
+$inventory = File.absolute_path($inventory, File.dirname(__FILE__))
+
+# if $inventory has a hosts.ini file use it, otherwise copy over
+# vars etc to where vagrant expects dynamic inventory to be
+if ! File.exist?(File.join(File.dirname($inventory), "hosts.ini"))
+  $vagrant_ansible = File.join(File.dirname(__FILE__), ".vagrant", "provisioners", "ansible")
+  FileUtils.mkdir_p($vagrant_ansible) if ! File.exist?($vagrant_ansible)
+  $vagrant_inventory = File.join($vagrant_ansible,"inventory")
+  FileUtils.rm_f($vagrant_inventory)
+  FileUtils.ln_s($inventory, $vagrant_inventory)
+end
 
 if Vagrant.has_plugin?("vagrant-proxyconf")
   $no_proxy = ENV['NO_PROXY'] || ENV['no_proxy'] || "127.0.0.1,localhost"
@@ -187,14 +182,6 @@ Vagrant.configure("2") do |config|
             lv.storage :file, :device => "hd#{driverletters[d]}", :path => "disk-#{i}-#{d}-#{DISK_UUID}.disk", :size => $kube_node_instances_with_disks_size, :bus => "scsi"
           end
         end
-        node.vm.provider :virtualbox do |vb|
-          # always make /dev/sd{a/b/c} so that CI can ensure that
-          # virtualbox and libvirt will have the same devices to use for OSDs
-          (1..$kube_node_instances_with_disks_number).each do |d|
-            vb.customize ['createhd', '--filename', "disk-#{i}-#{driverletters[d]}-#{DISK_UUID}.disk", '--size', $kube_node_instances_with_disks_size] # 10GB disk
-            vb.customize ['storageattach', :id, '--storagectl', 'SATA Controller', '--port', d, '--device', 0, '--type', 'hdd', '--medium', "disk-#{i}-#{driverletters[d]}-#{DISK_UUID}.disk", '--nonrotational', 'on', '--mtype', 'normal']
-          end
-        end
       end
 
       if $expose_docker_tcp
@@ -205,7 +192,7 @@ Vagrant.configure("2") do |config|
         node.vm.network "forwarded_port", guest: guest, host: host, auto_correct: true
       end
 
-      if ["rhel8"].include? $os
+      if ["rhel7","rhel8"].include? $os
         # Vagrant synced_folder rsync options cannot be used for RHEL boxes as Rsync package cannot
         # be installed until the host is registered with a valid Red Hat support subscription
         node.vm.synced_folder ".", "/vagrant", disabled: false
@@ -220,20 +207,14 @@ Vagrant.configure("2") do |config|
       end
 
       ip = "#{$subnet}.#{i+100}"
-      ip6 = "#{$subnet_ipv6}::#{i+100}"
       node.vm.network :private_network,
         :ip => ip,
         :libvirt__guest_ipv6 => 'yes',
-        :libvirt__ipv6_address => ip6,
+        :libvirt__ipv6_address => "#{$subnet_ipv6}::#{i+100}",
         :libvirt__ipv6_prefix => "64",
         :libvirt__forward_mode => "none",
         :libvirt__dhcp_enabled => false
 
-      # libvirt__ipv6_address does not work as intended, the address is obtained with the desired prefix, but auto-generated(like fd3c:b398:698:756:5054:ff:fe48:c61e/64)
-      # add default route for detect ansible_default_ipv6
-      # TODO: fix libvirt__ipv6 or use $subnet in shell
-      config.vm.provision "shell", inline: "ip -6 r a fd3c:b398:698:756::/64 dev eth1;ip -6 r add default via fd3c:b398:0698:0756::1 dev eth1 || true"
-
       # Disable swap for each vm
       node.vm.provision "shell", inline: "swapoff -a"
 
@@ -242,25 +223,17 @@ Vagrant.configure("2") do |config|
         node.vm.provision "shell", inline: "rm -f /etc/modprobe.d/local.conf"
         node.vm.provision "shell", inline: "sed -i '/net.ipv6.conf.all.disable_ipv6/d' /etc/sysctl.d/99-sysctl.conf /etc/sysctl.conf"
       end
-      # Hack for fedora39/40 to get the IP address of the second interface
+      # Hack for fedora37/38 to get the IP address of the second interface
-      if ["fedora39", "fedora40", "fedora39-arm64", "fedora40-arm64"].include? $os
+      if ["fedora37", "fedora38"].include? $os
         config.vm.provision "shell", inline: <<-SHELL
-          nmcli conn modify 'Wired connection 2' ipv4.addresses $(cat /etc/sysconfig/network-scripts/ifcfg-eth1 | grep IPADDR | cut -d "=" -f2)/24
+          nmcli conn modify 'Wired connection 2' ipv4.addresses $(cat /etc/sysconfig/network-scripts/ifcfg-eth1 | grep IPADDR | cut -d "=" -f2)
           nmcli conn modify 'Wired connection 2' ipv4.method manual
           service NetworkManager restart
         SHELL
       end
 
-
-      # Rockylinux boxes needs UEFI
-      if ["rockylinux8", "rockylinux9"].include? $os
-        config.vm.provider "libvirt" do |domain|
-          domain.loader = "/usr/share/OVMF/x64/OVMF_CODE.fd"
-        end
-      end
-
       # Disable firewalld on oraclelinux/redhat vms
-      if ["oraclelinux","oraclelinux8", "rhel8","rockylinux8"].include? $os
+      if ["oraclelinux","oraclelinux8","rhel7","rhel8","rockylinux8"].include? $os
         node.vm.provision "shell", inline: "systemctl stop firewalld; systemctl disable firewalld"
       end
 
@@ -294,22 +267,22 @@ Vagrant.configure("2") do |config|
           ansible.playbook = $playbook
           ansible.compatibility_mode = "2.0"
           ansible.verbose = $ansible_verbosity
+          $ansible_inventory_path = File.join( $inventory, "hosts.ini")
+          if File.exist?($ansible_inventory_path)
+            ansible.inventory_path = $ansible_inventory_path
+          end
           ansible.become = true
           ansible.limit = "all,localhost"
           ansible.host_key_checking = false
-          ansible.raw_arguments = ["--forks=#{$num_instances}",
+          ansible.raw_arguments = ["--forks=#{$num_instances}", "--flush-cache", "-e ansible_become_pass=vagrant"]
-                                   "--flush-cache",
-                                   "-e ansible_become_pass=vagrant"] +
-                                   $inventories.map {|inv| ["-i", inv]}.flatten
           ansible.host_vars = host_vars
-          ansible.extra_vars = $extra_vars
           if $ansible_tags != ""
             ansible.tags = [$ansible_tags]
           end
           ansible.groups = {
-            "etcd" => ["#{$instance_name_prefix}-[#{$first_etcd}:#{$etcd_instances + $first_etcd - 1}]"],
+            "etcd" => ["#{$instance_name_prefix}-[1:#{$etcd_instances}]"],
-            "kube_control_plane" => ["#{$instance_name_prefix}-[#{$first_control_plane}:#{$control_plane_instances + $first_control_plane - 1}]"],
+            "kube_control_plane" => ["#{$instance_name_prefix}-[1:#{$kube_master_instances}]"],
-            "kube_node" => ["#{$instance_name_prefix}-[#{$first_node}:#{$kube_node_instances + $first_node - 1}]"],
+            "kube_node" => ["#{$instance_name_prefix}-[1:#{$kube_node_instances}]"],
             "k8s_cluster:children" => ["kube_control_plane", "kube_node"],
           }
         end

ansible.cfg

@@ -1,6 +1,6 @@
 [ssh_connection]
 pipelining=True
-ssh_args = -o ControlMaster=auto -o ControlPersist=30m -o ConnectionAttempts=100 -o UserKnownHostsFile=/dev/null
+ansible_ssh_args = -o ControlMaster=auto -o ControlPersist=30m -o ConnectionAttempts=100 -o UserKnownHostsFile=/dev/null
 #control_path = ~/.ssh/ansible-%%r@%%h:%%p
 [defaults]
 # https://github.com/ansible/ansible/issues/56930 (to ignore group names with - and .)
@@ -11,7 +11,6 @@ gathering = smart
 fact_caching = jsonfile
 fact_caching_connection = /tmp
 fact_caching_timeout = 86400
-timeout = 300
 stdout_callback = default
 display_skipped_hosts = no
 library = ./library

contrib/azurerm/README.md

@@ -49,7 +49,7 @@ If you need to delete all resources from a resource group, simply call:
 
 ## Installing Ansible and the dependencies
 
-Install Ansible according to [Ansible installation guide](/docs/ansible/ansible.md#installing-ansible)
+Install Ansible according to [Ansible installation guide](/docs/ansible.md#installing-ansible)
 
 ## Generating an inventory for kubespray
 

contrib/azurerm/generate-inventory.yml

@@ -1,6 +1,6 @@
 ---
 - name: Generate Azure inventory
   hosts: localhost
-  gather_facts: false
+  gather_facts: False
   roles:
     - generate-inventory

contrib/azurerm/generate-inventory_2.yml

@@ -1,6 +1,6 @@
 ---
 - name: Generate Azure inventory
   hosts: localhost
-  gather_facts: false
+  gather_facts: False
   roles:
     - generate-inventory_2

contrib/azurerm/generate-templates.yml

@@ -1,6 +1,6 @@
 ---
 - name: Generate Azure templates
   hosts: localhost
-  gather_facts: false
+  gather_facts: False
   roles:
     - generate-templates

contrib/azurerm/roles/generate-inventory/tasks/main.yml

@@ -12,4 +12,4 @@
   template:
     src: inventory.j2
     dest: "{{ playbook_dir }}/inventory"
-    mode: "0644"
+    mode: 0644

contrib/azurerm/roles/generate-inventory_2/tasks/main.yml

@@ -22,10 +22,10 @@
   template:
     src: inventory.j2
     dest: "{{ playbook_dir }}/inventory"
-    mode: "0644"
+    mode: 0644
 
 - name: Generate Load Balancer variables
   template:
     src: loadbalancer_vars.j2
     dest: "{{ playbook_dir }}/loadbalancer_vars.yml"
-    mode: "0644"
+    mode: 0644

contrib/azurerm/roles/generate-templates/tasks/main.yml

@@ -8,13 +8,13 @@
     path: "{{ base_dir }}"
     state: directory
     recurse: true
-    mode: "0755"
+    mode: 0755
 
 - name: Store json files in base_dir
   template:
     src: "{{ item }}"
     dest: "{{ base_dir }}/{{ item }}"
-    mode: "0644"
+    mode: 0644
   with_items:
     - network.json
     - storage.json

contrib/dind/README.md

@@ -0,0 +1,177 @@
+# Kubespray DIND experimental setup
+
+This ansible playbook creates local docker containers
+to serve as Kubernetes "nodes", which in turn will run
+"normal" Kubernetes docker containers, a mode usually
+called DIND (Docker-IN-Docker).
+
+The playbook has two roles:
+
+- dind-host: creates the "nodes" as containers in localhost, with
+  appropriate settings for DIND (privileged, volume mapping for dind
+  storage, etc).
+- dind-cluster: customizes each node container to have required
+  system packages installed, and some utils (swapoff, lsattr)
+  symlinked to /bin/true to ease mimicking a real node.
+
+This playbook has been test with Ubuntu 16.04 as host and ubuntu:16.04
+as docker images (note that dind-cluster has specific customization
+for these images).
+
+The playbook also creates a `/tmp/kubespray.dind.inventory_builder.sh`
+helper (wraps up running `contrib/inventory_builder/inventory.py` with
+node containers IPs and prefix).
+
+## Deploying
+
+See below for a complete successful run:
+
+1. Create the node containers
+
+```shell
+# From the kubespray root dir
+cd contrib/dind
+pip install -r requirements.txt
+
+ansible-playbook -i hosts dind-cluster.yaml
+
+# Back to kubespray root
+cd ../..
+```
+
+NOTE: if the playbook run fails with something like below error
+message, you may need to specifically set `ansible_python_interpreter`,
+see `./hosts` file for an example expanded localhost entry.
+
+```shell
+failed: [localhost] (item=kube-node1) => {"changed": false, "item": "kube-node1", "msg": "Failed to import docker or docker-py - No module named requests.exceptions. Try `pip install docker` or `pip install docker-py` (Python 2.6)"}
+```
+
+2. Customize kubespray-dind.yaml
+
+Note that there's coupling between above created node containers
+and `kubespray-dind.yaml` settings, in particular regarding selected `node_distro`
+(as set in `group_vars/all/all.yaml`), and docker settings.
+
+```shell
+$EDITOR contrib/dind/kubespray-dind.yaml
+```
+
+3. Prepare the inventory and run the playbook
+
+```shell
+INVENTORY_DIR=inventory/local-dind
+mkdir -p ${INVENTORY_DIR}
+rm -f ${INVENTORY_DIR}/hosts.ini
+CONFIG_FILE=${INVENTORY_DIR}/hosts.ini /tmp/kubespray.dind.inventory_builder.sh
+
+ansible-playbook --become -e ansible_ssh_user=debian -i ${INVENTORY_DIR}/hosts.ini cluster.yml --extra-vars @contrib/dind/kubespray-dind.yaml
+```
+
+NOTE: You could also test other distros without editing files by
+passing `--extra-vars` as per below commandline,
+replacing `DISTRO` by either `debian`, `ubuntu`, `centos`, `fedora`:
+
+```shell
+cd contrib/dind
+ansible-playbook -i hosts dind-cluster.yaml --extra-vars node_distro=DISTRO
+
+cd ../..
+CONFIG_FILE=inventory/local-dind/hosts.ini /tmp/kubespray.dind.inventory_builder.sh
+ansible-playbook --become -e ansible_ssh_user=DISTRO -i inventory/local-dind/hosts.ini cluster.yml --extra-vars @contrib/dind/kubespray-dind.yaml --extra-vars bootstrap_os=DISTRO
+```
+
+## Resulting deployment
+
+See below to get an idea on how a completed deployment looks like,
+from the host where you ran kubespray playbooks.
+
+### node_distro: debian
+
+Running from an Ubuntu Xenial host:
+
+```shell
+$ uname -a
+Linux ip-xx-xx-xx-xx 4.4.0-1069-aws #79-Ubuntu SMP Mon Sep 24
+15:01:41 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux
+
+$ docker ps
+CONTAINER ID        IMAGE               COMMAND CREATED             STATUS              PORTS               NAMES
+1835dd183b75        debian:9.5          "sh -c 'apt-get -qy …"   43 minutes ago      Up 43 minutes                           kube-node5
+30b0af8d2924        debian:9.5          "sh -c 'apt-get -qy …"   43 minutes ago      Up 43 minutes                           kube-node4
+3e0d1510c62f        debian:9.5          "sh -c 'apt-get -qy …"   43 minutes ago      Up 43 minutes                           kube-node3
+738993566f94        debian:9.5          "sh -c 'apt-get -qy …"   44 minutes ago      Up 44 minutes                           kube-node2
+c581ef662ed2        debian:9.5          "sh -c 'apt-get -qy …"   44 minutes ago      Up 44 minutes                           kube-node1
+
+$ docker exec kube-node1 kubectl get node
+NAME         STATUS   ROLES         AGE   VERSION
+kube-node1   Ready    master,node   18m   v1.12.1
+kube-node2   Ready    master,node   17m   v1.12.1
+kube-node3   Ready    node          17m   v1.12.1
+kube-node4   Ready    node          17m   v1.12.1
+kube-node5   Ready    node          17m   v1.12.1
+
+$ docker exec kube-node1 kubectl get pod --all-namespaces
+NAMESPACE     NAME                                    READY   STATUS    RESTARTS   AGE
+default       netchecker-agent-67489                  1/1     Running   0          2m51s
+default       netchecker-agent-6qq6s                  1/1     Running   0          2m51s
+default       netchecker-agent-fsw92                  1/1     Running   0          2m51s
+default       netchecker-agent-fw6tl                  1/1     Running   0          2m51s
+default       netchecker-agent-hostnet-8f2zb          1/1     Running   0          3m
+default       netchecker-agent-hostnet-gq7ml          1/1     Running   0          3m
+default       netchecker-agent-hostnet-jfkgv          1/1     Running   0          3m
+default       netchecker-agent-hostnet-kwfwx          1/1     Running   0          3m
+default       netchecker-agent-hostnet-r46nm          1/1     Running   0          3m
+default       netchecker-agent-lxdrn                  1/1     Running   0          2m51s
+default       netchecker-server-864bd4c897-9vstl      1/1     Running   0          2m40s
+default       sh-68fcc6db45-qf55h                     1/1     Running   1          12m
+kube-system   coredns-7598f59475-6vknq                1/1     Running   0          14m
+kube-system   coredns-7598f59475-l5q5x                1/1     Running   0          14m
+kube-system   kube-apiserver-kube-node1               1/1     Running   0          17m
+kube-system   kube-apiserver-kube-node2               1/1     Running   0          18m
+kube-system   kube-controller-manager-kube-node1      1/1     Running   0          18m
+kube-system   kube-controller-manager-kube-node2      1/1     Running   0          18m
+kube-system   kube-proxy-5xx9d                        1/1     Running   0          17m
+kube-system   kube-proxy-cdqq4                        1/1     Running   0          17m
+kube-system   kube-proxy-n64ls                        1/1     Running   0          17m
+kube-system   kube-proxy-pswmj                        1/1     Running   0          18m
+kube-system   kube-proxy-x89qw                        1/1     Running   0          18m
+kube-system   kube-scheduler-kube-node1               1/1     Running   4          17m
+kube-system   kube-scheduler-kube-node2               1/1     Running   4          18m
+kube-system   kubernetes-dashboard-5db4d9f45f-548rl   1/1     Running   0          14m
+kube-system   nginx-proxy-kube-node3                  1/1     Running   4          17m
+kube-system   nginx-proxy-kube-node4                  1/1     Running   4          17m
+kube-system   nginx-proxy-kube-node5                  1/1     Running   4          17m
+kube-system   weave-net-42bfr                         2/2     Running   0          16m
+kube-system   weave-net-6gt8m                         2/2     Running   0          16m
+kube-system   weave-net-88nnc                         2/2     Running   0          16m
+kube-system   weave-net-shckr                         2/2     Running   0          16m
+kube-system   weave-net-xr46t                         2/2     Running   0          16m
+
+$ docker exec kube-node1 curl -s http://localhost:31081/api/v1/connectivity_check
+{"Message":"All 10 pods successfully reported back to the server","Absent":null,"Outdated":null}
+```
+
+## Using ./run-test-distros.sh
+
+You can use `./run-test-distros.sh` to run a set of tests via DIND,
+and excerpt from this script, to get an idea:
+
+```shell
+# The SPEC file(s) must have two arrays as e.g.
+# DISTROS=(debian centos)
+# EXTRAS=(
+#     'kube_network_plugin=calico'
+#     'kube_network_plugin=flannel'
+#     'kube_network_plugin=weave'
+# )
+# that will be tested in a "combinatory" way (e.g. from above there'll be
+# be 6 test runs), creating a sequenced <spec_filename>-nn.out with each output.
+#
+# Each $EXTRAS element will be whitespace split, and passed as --extra-vars
+# to main kubespray ansible-playbook run.
+```
+
+See e.g. `test-some_distros-most_CNIs.env` and
+`test-some_distros-kube_router_combo.env` in particular for a richer
+set of CNI specific `--extra-vars` combo.

contrib/dind/dind-cluster.yaml

@@ -0,0 +1,11 @@
+---
+- name: Create nodes as docker containers
+  hosts: localhost
+  gather_facts: False
+  roles:
+    - { role: dind-host }
+
+- name: Customize each node containers
+  hosts: containers
+  roles:
+    - { role: dind-cluster }

contrib/dind/group_vars/all/all.yaml

@@ -0,0 +1,3 @@
+---
+# See distro.yaml for supported node_distro images
+node_distro: debian

contrib/dind/group_vars/all/distro.yaml

@@ -0,0 +1,41 @@
+---
+distro_settings:
+  debian: &DEBIAN
+    image: "debian:9.5"
+    user: "debian"
+    pid1_exe: /lib/systemd/systemd
+    init: |
+      sh -c "apt-get -qy update && apt-get -qy install systemd-sysv dbus && exec /sbin/init"
+    raw_setup: apt-get -qy update && apt-get -qy install dbus python sudo iproute2
+    raw_setup_done: test -x /usr/bin/sudo
+    agetty_svc: getty@*
+    ssh_service: ssh
+    extra_packages: []
+  ubuntu:
+    <<: *DEBIAN
+    image: "ubuntu:16.04"
+    user: "ubuntu"
+    init: |
+      /sbin/init
+  centos: &CENTOS
+    image: "centos:7"
+    user: "centos"
+    pid1_exe: /usr/lib/systemd/systemd
+    init: |
+      /sbin/init
+    raw_setup: yum -qy install policycoreutils dbus python sudo iproute iptables
+    raw_setup_done: test -x /usr/bin/sudo
+    agetty_svc: getty@* serial-getty@*
+    ssh_service: sshd
+    extra_packages: []
+  fedora:
+    <<: *CENTOS
+    image: "fedora:latest"
+    user: "fedora"
+    raw_setup: yum -qy install policycoreutils dbus python sudo iproute iptables; mkdir -p /etc/modules-load.d
+    extra_packages:
+      - hostname
+      - procps
+      - findutils
+      - kmod
+      - iputils

contrib/dind/hosts

@@ -0,0 +1,15 @@
+[local]
+# If you created a virtualenv for ansible, you may need to specify running the
+# python binary from there instead:
+#localhost ansible_connection=local ansible_python_interpreter=/home/user/kubespray/.venv/bin/python
+localhost ansible_connection=local
+
+[containers]
+kube-node1
+kube-node2
+kube-node3
+kube-node4
+kube-node5
+
+[containers:vars]
+ansible_connection=docker

contrib/dind/kubespray-dind.yaml

@@ -0,0 +1,22 @@
+---
+# kubespray-dind.yaml: minimal kubespray ansible playbook usable for DIND
+# See contrib/dind/README.md
+kube_api_anonymous_auth: true
+
+kubelet_fail_swap_on: false
+
+# Docker nodes need to have been created with same "node_distro: debian"
+# at contrib/dind/group_vars/all/all.yaml
+bootstrap_os: debian
+
+docker_version: latest
+
+docker_storage_options: -s overlay2 --storage-opt overlay2.override_kernel_check=true -g /dind/docker
+
+dns_mode: coredns
+
+deploy_netchecker: True
+netcheck_agent_image_repo: quay.io/l23network/k8s-netchecker-agent
+netcheck_server_image_repo: quay.io/l23network/k8s-netchecker-server
+netcheck_agent_image_tag: v1.0
+netcheck_server_image_tag: v1.0

contrib/dind/requirements.txt

@@ -0,0 +1 @@
+docker

contrib/dind/roles/dind-cluster/tasks/main.yaml

@@ -0,0 +1,73 @@
+---
+- name: Set_fact distro_setup
+  set_fact:
+    distro_setup: "{{ distro_settings[node_distro] }}"
+
+- name: Set_fact other distro settings
+  set_fact:
+    distro_user: "{{ distro_setup['user'] }}"
+    distro_ssh_service: "{{ distro_setup['ssh_service'] }}"
+    distro_extra_packages: "{{ distro_setup['extra_packages'] }}"
+
+- name: Null-ify some linux tools to ease DIND
+  file:
+    src: "/bin/true"
+    dest: "{{ item }}"
+    state: link
+    force: yes
+  with_items:
+    # DIND box may have swap enable, don't bother
+    - /sbin/swapoff
+    # /etc/hosts handling would fail on trying to copy file attributes on edit,
+    # void it by successfully returning nil output
+    - /usr/bin/lsattr
+    # disable selinux-isms, sp needed if running on non-Selinux host
+    - /usr/sbin/semodule
+
+- name: Void installing dpkg docs and man pages on Debian based distros
+  copy:
+    content: |
+      # Delete locales
+      path-exclude=/usr/share/locale/*
+      # Delete man pages
+      path-exclude=/usr/share/man/*
+      # Delete docs
+      path-exclude=/usr/share/doc/*
+      path-include=/usr/share/doc/*/copyright
+    dest: /etc/dpkg/dpkg.cfg.d/01_nodoc
+    mode: 0644
+  when:
+    - ansible_os_family == 'Debian'
+
+- name: Install system packages to better match a full-fledge node
+  package:
+    name: "{{ item }}"
+    state: present
+  with_items: "{{ distro_extra_packages + ['rsyslog', 'openssh-server'] }}"
+
+- name: Start needed services
+  service:
+    name: "{{ item }}"
+    state: started
+  with_items:
+    - rsyslog
+    - "{{ distro_ssh_service }}"
+
+- name: Create distro user "{{ distro_user }}"
+  user:
+    name: "{{ distro_user }}"
+    uid: 1000
+    # groups: sudo
+    append: yes
+
+- name: Allow password-less sudo to "{{ distro_user }}"
+  copy:
+    content: "{{ distro_user }} ALL=(ALL) NOPASSWD:ALL"
+    dest: "/etc/sudoers.d/{{ distro_user }}"
+    mode: 0640
+
+- name: "Add my pubkey to {{ distro_user }} user authorized keys"
+  ansible.posix.authorized_key:
+    user: "{{ distro_user }}"
+    state: present
+    key: "{{ lookup('file', lookup('env', 'HOME') + '/.ssh/id_rsa.pub') }}"

contrib/dind/roles/dind-host/tasks/main.yaml

@@ -0,0 +1,87 @@
+---
+- name: Set_fact distro_setup
+  set_fact:
+    distro_setup: "{{ distro_settings[node_distro] }}"
+
+- name: Set_fact other distro settings
+  set_fact:
+    distro_image: "{{ distro_setup['image'] }}"
+    distro_init: "{{ distro_setup['init'] }}"
+    distro_pid1_exe: "{{ distro_setup['pid1_exe'] }}"
+    distro_raw_setup: "{{ distro_setup['raw_setup'] }}"
+    distro_raw_setup_done: "{{ distro_setup['raw_setup_done'] }}"
+    distro_agetty_svc: "{{ distro_setup['agetty_svc'] }}"
+
+- name: Create dind node containers from "containers" inventory section
+  community.docker.docker_container:
+    image: "{{ distro_image }}"
+    name: "{{ item }}"
+    state: started
+    hostname: "{{ item }}"
+    command: "{{ distro_init }}"
+    # recreate: yes
+    privileged: true
+    tmpfs:
+      - /sys/module/nf_conntrack/parameters
+    volumes:
+      - /boot:/boot
+      - /lib/modules:/lib/modules
+      - "{{ item }}:/dind/docker"
+  register: containers
+  with_items: "{{ groups.containers }}"
+  tags:
+    - addresses
+
+- name: Gather list of containers IPs
+  set_fact:
+    addresses: "{{ containers.results | map(attribute='ansible_facts') | map(attribute='docker_container') | map(attribute='NetworkSettings') | map(attribute='IPAddress') | list }}"
+  tags:
+    - addresses
+
+- name: Create inventory_builder helper already set with the list of node containers' IPs
+  template:
+    src: inventory_builder.sh.j2
+    dest: /tmp/kubespray.dind.inventory_builder.sh
+    mode: 0755
+  tags:
+    - addresses
+
+- name: Install needed packages into node containers via raw, need to wait for possible systemd packages to finish installing
+  raw: |
+    # agetty processes churn a lot of cpu time failing on inexistent ttys, early STOP them, to rip them in below task
+    pkill -STOP agetty || true
+    {{ distro_raw_setup_done }}  && echo SKIPPED && exit 0
+    until [ "$(readlink /proc/1/exe)" = "{{ distro_pid1_exe }}" ] ; do sleep 1; done
+    {{ distro_raw_setup }}
+  delegate_to: "{{ item._ansible_item_label | default(item.item) }}"
+  with_items: "{{ containers.results }}"
+  register: result
+  changed_when: result.stdout.find("SKIPPED") < 0
+
+- name: Remove gettys from node containers
+  raw: |
+    until test -S /var/run/dbus/system_bus_socket; do sleep 1; done
+    systemctl disable {{ distro_agetty_svc }}
+    systemctl stop {{ distro_agetty_svc }}
+  delegate_to: "{{ item._ansible_item_label | default(item.item) }}"
+  with_items: "{{ containers.results }}"
+  changed_when: false
+
+# Running systemd-machine-id-setup doesn't create a unique id for each node container on Debian,
+# handle manually
+- name: Re-create unique machine-id (as we may just get what comes in the docker image), needed by some CNIs for mac address seeding (notably weave)
+  raw: |
+    echo {{ item | hash('sha1') }} > /etc/machine-id.new
+    mv -b /etc/machine-id.new /etc/machine-id
+    cmp /etc/machine-id /etc/machine-id~ || true
+    systemctl daemon-reload
+  delegate_to: "{{ item._ansible_item_label | default(item.item) }}"
+  with_items: "{{ containers.results }}"
+
+- name: Early hack image install to adapt for DIND
+  raw: |
+    rm -fv /usr/bin/udevadm /usr/sbin/udevadm
+  delegate_to: "{{ item._ansible_item_label | default(item.item) }}"
+  with_items: "{{ containers.results }}"
+  register: result
+  changed_when: result.stdout.find("removed") >= 0

contrib/dind/roles/dind-host/templates/inventory_builder.sh.j2

@@ -0,0 +1,3 @@
+#!/bin/bash
+# NOTE: if you change HOST_PREFIX, you also need to edit ./hosts [containers] section
+HOST_PREFIX=kube-node python3 contrib/inventory_builder/inventory.py {% for ip in addresses %} {{ ip }} {% endfor %}

contrib/dind/run-test-distros.sh

@@ -0,0 +1,93 @@
+#!/bin/bash
+# Q&D test'em all: creates full DIND kubespray deploys
+# for each distro, verifying it via netchecker.
+
+info() {
+    local msg="$*"
+    local date="$(date -Isec)"
+    echo "INFO: [$date] $msg"
+}
+pass_or_fail() {
+    local rc="$?"
+    local msg="$*"
+    local date="$(date -Isec)"
+    [ $rc -eq 0 ] && echo "PASS: [$date] $msg" || echo "FAIL: [$date] $msg"
+    return $rc
+}
+test_distro() {
+    local distro=${1:?};shift
+    local extra="${*:-}"
+    local prefix="${distro[${extra}]}"
+    ansible-playbook -i hosts dind-cluster.yaml -e node_distro=$distro
+    pass_or_fail "$prefix: dind-nodes" || return 1
+    (cd ../..
+        INVENTORY_DIR=inventory/local-dind
+        mkdir -p ${INVENTORY_DIR}
+        rm -f ${INVENTORY_DIR}/hosts.ini
+        CONFIG_FILE=${INVENTORY_DIR}/hosts.ini /tmp/kubespray.dind.inventory_builder.sh
+        # expand $extra with -e in front of each word
+        extra_args=""; for extra_arg in $extra; do extra_args="$extra_args -e $extra_arg"; done
+        ansible-playbook --become -e ansible_ssh_user=$distro -i \
+            ${INVENTORY_DIR}/hosts.ini cluster.yml \
+            -e @contrib/dind/kubespray-dind.yaml -e bootstrap_os=$distro ${extra_args}
+        pass_or_fail "$prefix: kubespray"
+    ) || return 1
+    local node0=${NODES[0]}
+    docker exec ${node0} kubectl get pod --all-namespaces
+    pass_or_fail "$prefix: kube-api" || return 1
+    let retries=60
+    while ((retries--)); do
+        # Some CNI may set NodePort on "main" node interface address (thus no localhost NodePort)
+        # e.g. kube-router: https://github.com/cloudnativelabs/kube-router/pull/217
+        docker exec ${node0} curl -m2 -s http://${NETCHECKER_HOST:?}:31081/api/v1/connectivity_check | grep successfully && break
+        sleep 2
+    done
+    [ $retries -ge 0 ]
+    pass_or_fail "$prefix: netcheck" || return 1
+}
+
+NODES=($(egrep ^kube_node hosts))
+NETCHECKER_HOST=localhost
+
+: ${OUTPUT_DIR:=./out}
+mkdir -p ${OUTPUT_DIR}
+
+# The SPEC file(s) must have two arrays as e.g.
+# DISTROS=(debian centos)
+# EXTRAS=(
+#     'kube_network_plugin=calico'
+#     'kube_network_plugin=flannel'
+#     'kube_network_plugin=weave'
+# )
+# that will be tested in a "combinatory" way (e.g. from above there'll be
+# be 6 test runs), creating a sequenced <spec_filename>-nn.out with each output.
+#
+# Each $EXTRAS element will be whitespace split, and passed as --extra-vars
+# to main kubespray ansible-playbook run.
+
+SPECS=${*:?Missing SPEC files, e.g. test-most_distros-some_CNIs.env}
+for spec in ${SPECS}; do
+    unset DISTROS EXTRAS
+    echo "Loading file=${spec} ..."
+    . ${spec} || continue
+    : ${DISTROS:?} || continue
+    echo "DISTROS:" "${DISTROS[@]}"
+    echo "EXTRAS->"
+    printf "  %s\n" "${EXTRAS[@]}"
+    let n=1
+    for distro in "${DISTROS[@]}"; do
+        for extra in "${EXTRAS[@]:-NULL}"; do
+            # Magic value to let this for run once:
+            [[ ${extra} == NULL ]] && unset extra
+            docker rm -f "${NODES[@]}"
+            printf -v file_out "%s/%s-%02d.out" ${OUTPUT_DIR} ${spec} $((n++))
+            {
+                info "${distro}[${extra}] START: file_out=${file_out}"
+                time test_distro ${distro} ${extra}
+            } |& tee ${file_out}
+            # sleeping for the sake of the human to verify if they want
+            sleep 2m
+        done
+    done
+done
+egrep -H '^(....:|real)' $(ls -tr ${OUTPUT_DIR}/*.out)

contrib/dind/test-most_distros-some_CNIs.env

@@ -0,0 +1,11 @@
+# Test spec file: used from ./run-test-distros.sh, will run
+# each distro in $DISTROS overloading main kubespray ansible-playbook run
+# Get all DISTROS from distro.yaml (shame no yaml parsing, but nuff anyway)
+# DISTROS="${*:-$(egrep -o '^  \w+' group_vars/all/distro.yaml|paste -s)}"
+DISTROS=(debian ubuntu centos fedora)
+
+# Each line below will be added as --extra-vars to main playbook run
+EXTRAS=(
+    'kube_network_plugin=calico'
+    'kube_network_plugin=weave'
+)

contrib/dind/test-some_distros-kube_router_combo.env

@@ -0,0 +1,6 @@
+DISTROS=(debian centos)
+NETCHECKER_HOST=${NODES[0]}
+EXTRAS=(
+  'kube_network_plugin=kube-router {"kube_router_run_service_proxy":false}'
+  'kube_network_plugin=kube-router {"kube_router_run_service_proxy":true}'
+)

contrib/dind/test-some_distros-most_CNIs.env

@@ -0,0 +1,8 @@
+DISTROS=(debian centos)
+EXTRAS=(
+  'kube_network_plugin=calico {}'
+  'kube_network_plugin=canal {}'
+  'kube_network_plugin=cilium {}'
+  'kube_network_plugin=flannel {}'
+  'kube_network_plugin=weave {}'
+)

contrib/inventory_builder/inventory.py

@@ -0,0 +1,480 @@
+#!/usr/bin/env python3
+# 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.
+#
+# Usage: inventory.py ip1 [ip2 ...]
+# Examples: inventory.py 10.10.1.3 10.10.1.4 10.10.1.5
+#
+# Advanced usage:
+# Add another host after initial creation: inventory.py 10.10.1.5
+# Add range of hosts: inventory.py 10.10.1.3-10.10.1.5
+# Add hosts with different ip and access ip:
+# inventory.py 10.0.0.1,192.168.10.1 10.0.0.2,192.168.10.2 10.0.0.3,192.168.1.3
+# Add hosts with a specific hostname, ip, and optional access ip:
+# inventory.py first,10.0.0.1,192.168.10.1 second,10.0.0.2 last,10.0.0.3
+# Delete a host: inventory.py -10.10.1.3
+# Delete a host by id: inventory.py -node1
+#
+# Load a YAML or JSON file with inventory data: inventory.py load hosts.yaml
+# YAML file should be in the following format:
+#    group1:
+#      host1:
+#        ip: X.X.X.X
+#        var: val
+#    group2:
+#      host2:
+#        ip: X.X.X.X
+
+from collections import OrderedDict
+from ipaddress import ip_address
+from ruamel.yaml import YAML
+
+import os
+import re
+import subprocess
+import sys
+
+ROLES = ['all', 'kube_control_plane', 'kube_node', 'etcd', 'k8s_cluster',
+         'calico_rr']
+PROTECTED_NAMES = ROLES
+AVAILABLE_COMMANDS = ['help', 'print_cfg', 'print_ips', 'print_hostnames',
+                      'load', 'add']
+_boolean_states = {'1': True, 'yes': True, 'true': True, 'on': True,
+                   '0': False, 'no': False, 'false': False, 'off': False}
+yaml = YAML()
+yaml.Representer.add_representer(OrderedDict, yaml.Representer.represent_dict)
+
+
+def get_var_as_bool(name, default):
+    value = os.environ.get(name, '')
+    return _boolean_states.get(value.lower(), default)
+
+# Configurable as shell vars start
+
+
+CONFIG_FILE = os.environ.get("CONFIG_FILE", "./inventory/sample/hosts.yaml")
+# Remove the reference of KUBE_MASTERS after some deprecation cycles.
+KUBE_CONTROL_HOSTS = int(os.environ.get("KUBE_CONTROL_HOSTS",
+                         os.environ.get("KUBE_MASTERS", 2)))
+# Reconfigures cluster distribution at scale
+SCALE_THRESHOLD = int(os.environ.get("SCALE_THRESHOLD", 50))
+MASSIVE_SCALE_THRESHOLD = int(os.environ.get("MASSIVE_SCALE_THRESHOLD", 200))
+
+DEBUG = get_var_as_bool("DEBUG", True)
+HOST_PREFIX = os.environ.get("HOST_PREFIX", "node")
+USE_REAL_HOSTNAME = get_var_as_bool("USE_REAL_HOSTNAME", False)
+
+# Configurable as shell vars end
+
+
+class KubesprayInventory(object):
+
+    def __init__(self, changed_hosts=None, config_file=None):
+        self.config_file = config_file
+        self.yaml_config = {}
+        loadPreviousConfig = False
+        printHostnames = False
+        # See whether there are any commands to process
+        if changed_hosts and changed_hosts[0] in AVAILABLE_COMMANDS:
+            if changed_hosts[0] == "add":
+                loadPreviousConfig = True
+                changed_hosts = changed_hosts[1:]
+            elif changed_hosts[0] == "print_hostnames":
+                loadPreviousConfig = True
+                printHostnames = True
+            else:
+                self.parse_command(changed_hosts[0], changed_hosts[1:])
+                sys.exit(0)
+
+        # If the user wants to remove a node, we need to load the config anyway
+        if changed_hosts and changed_hosts[0][0] == "-":
+            loadPreviousConfig = True
+
+        if self.config_file and loadPreviousConfig:  # Load previous YAML file
+            try:
+                self.hosts_file = open(config_file, 'r')
+                self.yaml_config = yaml.load(self.hosts_file)
+            except OSError as e:
+                # I am assuming we are catching "cannot open file" exceptions
+                print(e)
+                sys.exit(1)
+
+        if printHostnames:
+            self.print_hostnames()
+            sys.exit(0)
+
+        self.ensure_required_groups(ROLES)
+
+        if changed_hosts:
+            changed_hosts = self.range2ips(changed_hosts)
+            self.hosts = self.build_hostnames(changed_hosts,
+                                              loadPreviousConfig)
+            self.purge_invalid_hosts(self.hosts.keys(), PROTECTED_NAMES)
+            self.set_all(self.hosts)
+            self.set_k8s_cluster()
+            etcd_hosts_count = 3 if len(self.hosts.keys()) >= 3 else 1
+            self.set_etcd(list(self.hosts.keys())[:etcd_hosts_count])
+            if len(self.hosts) >= SCALE_THRESHOLD:
+                self.set_kube_control_plane(list(self.hosts.keys())[
+                    etcd_hosts_count:(etcd_hosts_count + KUBE_CONTROL_HOSTS)])
+            else:
+                self.set_kube_control_plane(
+                  list(self.hosts.keys())[:KUBE_CONTROL_HOSTS])
+            self.set_kube_node(self.hosts.keys())
+            if len(self.hosts) >= SCALE_THRESHOLD:
+                self.set_calico_rr(list(self.hosts.keys())[:etcd_hosts_count])
+        else:  # Show help if no options
+            self.show_help()
+            sys.exit(0)
+
+        self.write_config(self.config_file)
+
+    def write_config(self, config_file):
+        if config_file:
+            with open(self.config_file, 'w') as f:
+                yaml.dump(self.yaml_config, f)
+
+        else:
+            print("WARNING: Unable to save config. Make sure you set "
+                  "CONFIG_FILE env var.")
+
+    def debug(self, msg):
+        if DEBUG:
+            print("DEBUG: {0}".format(msg))
+
+    def get_ip_from_opts(self, optstring):
+        if 'ip' in optstring:
+            return optstring['ip']
+        else:
+            raise ValueError("IP parameter not found in options")
+
+    def ensure_required_groups(self, groups):
+        for group in groups:
+            if group == 'all':
+                self.debug("Adding group {0}".format(group))
+                if group not in self.yaml_config:
+                    all_dict = OrderedDict([('hosts', OrderedDict({})),
+                                            ('children', OrderedDict({}))])
+                    self.yaml_config = {'all': all_dict}
+            else:
+                self.debug("Adding group {0}".format(group))
+                if group not in self.yaml_config['all']['children']:
+                    self.yaml_config['all']['children'][group] = {'hosts': {}}
+
+    def get_host_id(self, host):
+        '''Returns integer host ID (without padding) from a given hostname.'''
+        try:
+            short_hostname = host.split('.')[0]
+            return int(re.findall("\\d+$", short_hostname)[-1])
+        except IndexError:
+            raise ValueError("Host name must end in an integer")
+
+    # Keeps already specified hosts,
+    # and adds or removes the hosts provided as an argument
+    def build_hostnames(self, changed_hosts, loadPreviousConfig=False):
+        existing_hosts = OrderedDict()
+        highest_host_id = 0
+        # Load already existing hosts from the YAML
+        if loadPreviousConfig:
+            try:
+                for host in self.yaml_config['all']['hosts']:
+                    # Read configuration of an existing host
+                    hostConfig = self.yaml_config['all']['hosts'][host]
+                    existing_hosts[host] = hostConfig
+                    # If the existing host seems
+                    # to have been created automatically, detect its ID
+                    if host.startswith(HOST_PREFIX):
+                        host_id = self.get_host_id(host)
+                        if host_id > highest_host_id:
+                            highest_host_id = host_id
+            except Exception as e:
+                # I am assuming we are catching automatically
+                # created hosts without IDs
+                print(e)
+                sys.exit(1)
+
+        # FIXME(mattymo): Fix condition where delete then add reuses highest id
+        next_host_id = highest_host_id + 1
+        next_host = ""
+
+        all_hosts = existing_hosts.copy()
+        for host in changed_hosts:
+            # Delete the host from config the hostname/IP has a "-" prefix
+            if host[0] == "-":
+                realhost = host[1:]
+                if self.exists_hostname(all_hosts, realhost):
+                    self.debug("Marked {0} for deletion.".format(realhost))
+                    all_hosts.pop(realhost)
+                elif self.exists_ip(all_hosts, realhost):
+                    self.debug("Marked {0} for deletion.".format(realhost))
+                    self.delete_host_by_ip(all_hosts, realhost)
+            # Host/Argument starts with a digit,
+            # then we assume its an IP address
+            elif host[0].isdigit():
+                if ',' in host:
+                    ip, access_ip = host.split(',')
+                else:
+                    ip = host
+                    access_ip = host
+                if self.exists_hostname(all_hosts, host):
+                    self.debug("Skipping existing host {0}.".format(host))
+                    continue
+                elif self.exists_ip(all_hosts, ip):
+                    self.debug("Skipping existing host {0}.".format(ip))
+                    continue
+
+                if USE_REAL_HOSTNAME:
+                    cmd = ("ssh -oStrictHostKeyChecking=no "
+                           + access_ip + " 'hostname -s'")
+                    next_host = subprocess.check_output(cmd, shell=True)
+                    next_host = next_host.strip().decode('ascii')
+                else:
+                    # Generates a hostname because we have only an IP address
+                    next_host = "{0}{1}".format(HOST_PREFIX, next_host_id)
+                    next_host_id += 1
+                # Uses automatically generated node name
+                # in case we dont provide it.
+                all_hosts[next_host] = {'ansible_host': access_ip,
+                                        'ip': ip,
+                                        'access_ip': access_ip}
+            # Host/Argument starts with a letter, then we assume its a hostname
+            elif host[0].isalpha():
+                if ',' in host:
+                    try:
+                        hostname, ip, access_ip = host.split(',')
+                    except Exception:
+                        hostname, ip = host.split(',')
+                        access_ip = ip
+                if self.exists_hostname(all_hosts, host):
+                    self.debug("Skipping existing host {0}.".format(host))
+                    continue
+                elif self.exists_ip(all_hosts, ip):
+                    self.debug("Skipping existing host {0}.".format(ip))
+                    continue
+                all_hosts[hostname] = {'ansible_host': access_ip,
+                                       'ip': ip,
+                                       'access_ip': access_ip}
+        return all_hosts
+
+    # Expand IP ranges into individual addresses
+    def range2ips(self, hosts):
+        reworked_hosts = []
+
+        def ips(start_address, end_address):
+            try:
+                # Python 3.x
+                start = int(ip_address(start_address))
+                end = int(ip_address(end_address))
+            except Exception:
+                # Python 2.7
+                start = int(ip_address(str(start_address)))
+                end = int(ip_address(str(end_address)))
+            return [ip_address(ip).exploded for ip in range(start, end + 1)]
+
+        for host in hosts:
+            if '-' in host and not (host.startswith('-') or host[0].isalpha()):
+                start, end = host.strip().split('-')
+                try:
+                    reworked_hosts.extend(ips(start, end))
+                except ValueError:
+                    raise Exception("Range of ip_addresses isn't valid")
+            else:
+                reworked_hosts.append(host)
+        return reworked_hosts
+
+    def exists_hostname(self, existing_hosts, hostname):
+        return hostname in existing_hosts.keys()
+
+    def exists_ip(self, existing_hosts, ip):
+        for host_opts in existing_hosts.values():
+            if ip == self.get_ip_from_opts(host_opts):
+                return True
+        return False
+
+    def delete_host_by_ip(self, existing_hosts, ip):
+        for hostname, host_opts in existing_hosts.items():
+            if ip == self.get_ip_from_opts(host_opts):
+                del existing_hosts[hostname]
+                return
+        raise ValueError("Unable to find host by IP: {0}".format(ip))
+
+    def purge_invalid_hosts(self, hostnames, protected_names=[]):
+        for role in self.yaml_config['all']['children']:
+            if role != 'k8s_cluster' and self.yaml_config['all']['children'][role]['hosts']:  # noqa
+                all_hosts = self.yaml_config['all']['children'][role]['hosts'].copy()  # noqa
+                for host in all_hosts.keys():
+                    if host not in hostnames and host not in protected_names:
+                        self.debug(
+                            "Host {0} removed from role {1}".format(host, role))  # noqa
+                        del self.yaml_config['all']['children'][role]['hosts'][host]  # noqa
+        # purge from all
+        if self.yaml_config['all']['hosts']:
+            all_hosts = self.yaml_config['all']['hosts'].copy()
+            for host in all_hosts.keys():
+                if host not in hostnames and host not in protected_names:
+                    self.debug("Host {0} removed from role all".format(host))
+                    del self.yaml_config['all']['hosts'][host]
+
+    def add_host_to_group(self, group, host, opts=""):
+        self.debug("adding host {0} to group {1}".format(host, group))
+        if group == 'all':
+            if self.yaml_config['all']['hosts'] is None:
+                self.yaml_config['all']['hosts'] = {host: None}
+            self.yaml_config['all']['hosts'][host] = opts
+        elif group != 'k8s_cluster:children':
+            if self.yaml_config['all']['children'][group]['hosts'] is None:
+                self.yaml_config['all']['children'][group]['hosts'] = {
+                    host: None}
+            else:
+                self.yaml_config['all']['children'][group]['hosts'][host] = None  # noqa
+
+    def set_kube_control_plane(self, hosts):
+        for host in hosts:
+            self.add_host_to_group('kube_control_plane', host)
+
+    def set_all(self, hosts):
+        for host, opts in hosts.items():
+            self.add_host_to_group('all', host, opts)
+
+    def set_k8s_cluster(self):
+        k8s_cluster = {'children': {'kube_control_plane': None,
+                                    'kube_node': None}}
+        self.yaml_config['all']['children']['k8s_cluster'] = k8s_cluster
+
+    def set_calico_rr(self, hosts):
+        for host in hosts:
+            if host in self.yaml_config['all']['children']['kube_control_plane']: # noqa
+                self.debug("Not adding {0} to calico_rr group because it "
+                           "conflicts with kube_control_plane "
+                           "group".format(host))
+                continue
+            if host in self.yaml_config['all']['children']['kube_node']:
+                self.debug("Not adding {0} to calico_rr group because it "
+                           "conflicts with kube_node group".format(host))
+                continue
+            self.add_host_to_group('calico_rr', host)
+
+    def set_kube_node(self, hosts):
+        for host in hosts:
+            if len(self.yaml_config['all']['hosts']) >= SCALE_THRESHOLD:
+                if host in self.yaml_config['all']['children']['etcd']['hosts']:  # noqa
+                    self.debug("Not adding {0} to kube_node group because of "
+                               "scale deployment and host is in etcd "
+                               "group.".format(host))
+                    continue
+            if len(self.yaml_config['all']['hosts']) >= MASSIVE_SCALE_THRESHOLD:  # noqa
+                if host in self.yaml_config['all']['children']['kube_control_plane']['hosts']:  # noqa
+                    self.debug("Not adding {0} to kube_node group because of "
+                               "scale deployment and host is in "
+                               "kube_control_plane group.".format(host))
+                    continue
+            self.add_host_to_group('kube_node', host)
+
+    def set_etcd(self, hosts):
+        for host in hosts:
+            self.add_host_to_group('etcd', host)
+
+    def load_file(self, files=None):
+        '''Directly loads JSON to inventory.'''
+
+        if not files:
+            raise Exception("No input file specified.")
+
+        import json
+
+        for filename in list(files):
+            # Try JSON
+            try:
+                with open(filename, 'r') as f:
+                    data = json.load(f)
+            except ValueError:
+                raise Exception("Cannot read %s as JSON, or CSV", filename)
+
+            self.ensure_required_groups(ROLES)
+            self.set_k8s_cluster()
+            for group, hosts in data.items():
+                self.ensure_required_groups([group])
+                for host, opts in hosts.items():
+                    optstring = {'ansible_host': opts['ip'],
+                                 'ip': opts['ip'],
+                                 'access_ip': opts['ip']}
+                    self.add_host_to_group('all', host, optstring)
+                    self.add_host_to_group(group, host)
+            self.write_config(self.config_file)
+
+    def parse_command(self, command, args=None):
+        if command == 'help':
+            self.show_help()
+        elif command == 'print_cfg':
+            self.print_config()
+        elif command == 'print_ips':
+            self.print_ips()
+        elif command == 'print_hostnames':
+            self.print_hostnames()
+        elif command == 'load':
+            self.load_file(args)
+        else:
+            raise Exception("Invalid command specified.")
+
+    def show_help(self):
+        help_text = '''Usage: inventory.py ip1 [ip2 ...]
+Examples: inventory.py 10.10.1.3 10.10.1.4 10.10.1.5
+
+Available commands:
+help - Display this message
+print_cfg - Write inventory file to stdout
+print_ips - Write a space-delimited list of IPs from "all" group
+print_hostnames - Write a space-delimited list of Hostnames from "all" group
+add - Adds specified hosts into an already existing inventory
+
+Advanced usage:
+Create new or overwrite old inventory file: inventory.py 10.10.1.5
+Add another host after initial creation: inventory.py add 10.10.1.6
+Add range of hosts: inventory.py 10.10.1.3-10.10.1.5
+Add hosts with different ip and access ip: inventory.py 10.0.0.1,192.168.10.1 10.0.0.2,192.168.10.2 10.0.0.3,192.168.10.3
+Add hosts with a specific hostname, ip, and optional access ip: first,10.0.0.1,192.168.10.1 second,10.0.0.2 last,10.0.0.3
+Delete a host: inventory.py -10.10.1.3
+Delete a host by id: inventory.py -node1
+
+Configurable env vars:
+DEBUG                   Enable debug printing. Default: True
+CONFIG_FILE             File to write config to Default: ./inventory/sample/hosts.yaml
+HOST_PREFIX             Host prefix for generated hosts. Default: node
+KUBE_CONTROL_HOSTS      Set the number of kube-control-planes. Default: 2
+SCALE_THRESHOLD         Separate ETCD role if # of nodes >= 50
+MASSIVE_SCALE_THRESHOLD Separate K8s control-plane and ETCD if # of nodes >= 200
+'''  # noqa
+        print(help_text)
+
+    def print_config(self):
+        yaml.dump(self.yaml_config, sys.stdout)
+
+    def print_hostnames(self):
+        print(' '.join(self.yaml_config['all']['hosts'].keys()))
+
+    def print_ips(self):
+        ips = []
+        for host, opts in self.yaml_config['all']['hosts'].items():
+            ips.append(self.get_ip_from_opts(opts))
+        print(' '.join(ips))
+
+
+def main(argv=None):
+    if not argv:
+        argv = sys.argv[1:]
+    KubesprayInventory(argv, CONFIG_FILE)
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())

contrib/inventory_builder/requirements.txt

@@ -0,0 +1,3 @@
+configparser>=3.3.0
+ipaddress
+ruamel.yaml>=0.15.88

contrib/inventory_builder/setup.cfg

@@ -0,0 +1,3 @@
+[metadata]
+name = kubespray-inventory-builder
+version = 0.1

contrib/inventory_builder/setup.py

@@ -0,0 +1,29 @@
+# Copyright (c) 2013 Hewlett-Packard Development Company, L.P.
+#
+# 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.
+
+# THIS FILE IS MANAGED BY THE GLOBAL REQUIREMENTS REPO - DO NOT EDIT
+import setuptools
+
+# In python < 2.7.4, a lazy loading of package `pbr` will break
+# setuptools if some other modules registered functions in `atexit`.
+# solution from: http://bugs.python.org/issue15881#msg170215
+try:
+    import multiprocessing  # noqa
+except ImportError:
+    pass
+
+setuptools.setup(
+    setup_requires=[],
+    pbr=False)

contrib/inventory_builder/test-requirements.txt

@@ -0,0 +1,3 @@
+hacking>=0.10.2
+mock>=1.3.0
+pytest>=2.8.0

contrib/inventory_builder/tests/test_inventory.py

@@ -0,0 +1,595 @@
+# Copyright 2016 Mirantis, Inc.
+#
+# 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.
+
+import inventory
+from io import StringIO
+import unittest
+from unittest import mock
+
+from collections import OrderedDict
+import sys
+
+path = "./contrib/inventory_builder/"
+if path not in sys.path:
+    sys.path.append(path)
+
+import inventory  # noqa
+
+
+class TestInventoryPrintHostnames(unittest.TestCase):
+
+    @mock.patch('ruamel.yaml.YAML.load')
+    def test_print_hostnames(self, load_mock):
+        mock_io = mock.mock_open(read_data='')
+        load_mock.return_value = OrderedDict({'all': {'hosts': {
+            'node1': {'ansible_host': '10.90.0.2',
+                      'ip': '10.90.0.2',
+                      'access_ip': '10.90.0.2'},
+            'node2': {'ansible_host': '10.90.0.3',
+                      'ip': '10.90.0.3',
+                      'access_ip': '10.90.0.3'}}}})
+        with mock.patch('builtins.open', mock_io):
+            with self.assertRaises(SystemExit) as cm:
+                with mock.patch('sys.stdout', new_callable=StringIO) as stdout:
+                    inventory.KubesprayInventory(
+                        changed_hosts=["print_hostnames"],
+                        config_file="file")
+            self.assertEqual("node1 node2\n", stdout.getvalue())
+            self.assertEqual(cm.exception.code, 0)
+
+
+class TestInventory(unittest.TestCase):
+    @mock.patch('inventory.sys')
+    def setUp(self, sys_mock):
+        sys_mock.exit = mock.Mock()
+        super(TestInventory, self).setUp()
+        self.data = ['10.90.3.2', '10.90.3.3', '10.90.3.4']
+        self.inv = inventory.KubesprayInventory()
+
+    def test_get_ip_from_opts(self):
+        optstring = {'ansible_host': '10.90.3.2',
+                     'ip': '10.90.3.2',
+                     'access_ip': '10.90.3.2'}
+        expected = "10.90.3.2"
+        result = self.inv.get_ip_from_opts(optstring)
+        self.assertEqual(expected, result)
+
+    def test_get_ip_from_opts_invalid(self):
+        optstring = "notanaddr=value something random!chars:D"
+        self.assertRaisesRegex(ValueError, "IP parameter not found",
+                               self.inv.get_ip_from_opts, optstring)
+
+    def test_ensure_required_groups(self):
+        groups = ['group1', 'group2']
+        self.inv.ensure_required_groups(groups)
+        for group in groups:
+            self.assertIn(group, self.inv.yaml_config['all']['children'])
+
+    def test_get_host_id(self):
+        hostnames = ['node99', 'no99de01', '01node01', 'node1.domain',
+                     'node3.xyz123.aaa']
+        expected = [99, 1, 1, 1, 3]
+        for hostname, expected in zip(hostnames, expected):
+            result = self.inv.get_host_id(hostname)
+            self.assertEqual(expected, result)
+
+    def test_get_host_id_invalid(self):
+        bad_hostnames = ['node', 'no99de', '01node', 'node.111111']
+        for hostname in bad_hostnames:
+            self.assertRaisesRegex(ValueError, "Host name must end in an",
+                                   self.inv.get_host_id, hostname)
+
+    def test_build_hostnames_add_duplicate(self):
+        changed_hosts = ['10.90.0.2']
+        expected = OrderedDict([('node3',
+                                 {'ansible_host': '10.90.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '10.90.0.2'})])
+        self.inv.yaml_config['all']['hosts'] = expected
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_two(self):
+        changed_hosts = ['10.90.0.2', '10.90.0.3']
+        expected = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        self.inv.yaml_config['all']['hosts'] = OrderedDict()
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_three(self):
+        changed_hosts = ['10.90.0.2', '10.90.0.3', '10.90.0.4']
+        expected = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'}),
+            ('node3', {'ansible_host': '10.90.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '10.90.0.4'})])
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_one(self):
+        changed_hosts = ['10.90.0.2']
+        expected = OrderedDict([('node1',
+                                 {'ansible_host': '10.90.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '10.90.0.2'})])
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_delete_first(self):
+        changed_hosts = ['-10.90.0.2']
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        self.inv.yaml_config['all']['hosts'] = existing_hosts
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_delete_by_hostname(self):
+        changed_hosts = ['-node1']
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        self.inv.yaml_config['all']['hosts'] = existing_hosts
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_exists_hostname_positive(self):
+        hostname = 'node1'
+        expected = True
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        result = self.inv.exists_hostname(existing_hosts, hostname)
+        self.assertEqual(expected, result)
+
+    def test_exists_hostname_negative(self):
+        hostname = 'node99'
+        expected = False
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        result = self.inv.exists_hostname(existing_hosts, hostname)
+        self.assertEqual(expected, result)
+
+    def test_exists_ip_positive(self):
+        ip = '10.90.0.2'
+        expected = True
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        result = self.inv.exists_ip(existing_hosts, ip)
+        self.assertEqual(expected, result)
+
+    def test_exists_ip_negative(self):
+        ip = '10.90.0.200'
+        expected = False
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        result = self.inv.exists_ip(existing_hosts, ip)
+        self.assertEqual(expected, result)
+
+    def test_delete_host_by_ip_positive(self):
+        ip = '10.90.0.2'
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        self.inv.delete_host_by_ip(existing_hosts, ip)
+        self.assertEqual(expected, existing_hosts)
+
+    def test_delete_host_by_ip_negative(self):
+        ip = '10.90.0.200'
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        self.assertRaisesRegex(ValueError, "Unable to find host",
+                               self.inv.delete_host_by_ip, existing_hosts, ip)
+
+    def test_purge_invalid_hosts(self):
+        proper_hostnames = ['node1', 'node2']
+        bad_host = 'doesnotbelong2'
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'}),
+            ('doesnotbelong2', {'whateveropts=ilike'})])
+        self.inv.yaml_config['all']['hosts'] = existing_hosts
+        self.inv.purge_invalid_hosts(proper_hostnames)
+        self.assertNotIn(
+            bad_host, self.inv.yaml_config['all']['hosts'].keys())
+
+    def test_add_host_to_group(self):
+        group = 'etcd'
+        host = 'node1'
+        opts = {'ip': '10.90.0.2'}
+
+        self.inv.add_host_to_group(group, host, opts)
+        self.assertEqual(
+            self.inv.yaml_config['all']['children'][group]['hosts'].get(host),
+            None)
+
+    def test_set_kube_control_plane(self):
+        group = 'kube_control_plane'
+        host = 'node1'
+
+        self.inv.set_kube_control_plane([host])
+        self.assertIn(
+            host, self.inv.yaml_config['all']['children'][group]['hosts'])
+
+    def test_set_all(self):
+        hosts = OrderedDict([
+            ('node1', 'opt1'),
+            ('node2', 'opt2')])
+
+        self.inv.set_all(hosts)
+        for host, opt in hosts.items():
+            self.assertEqual(
+                self.inv.yaml_config['all']['hosts'].get(host), opt)
+
+    def test_set_k8s_cluster(self):
+        group = 'k8s_cluster'
+        expected_hosts = ['kube_node', 'kube_control_plane']
+
+        self.inv.set_k8s_cluster()
+        for host in expected_hosts:
+            self.assertIn(
+                host,
+                self.inv.yaml_config['all']['children'][group]['children'])
+
+    def test_set_kube_node(self):
+        group = 'kube_node'
+        host = 'node1'
+
+        self.inv.set_kube_node([host])
+        self.assertIn(
+            host, self.inv.yaml_config['all']['children'][group]['hosts'])
+
+    def test_set_etcd(self):
+        group = 'etcd'
+        host = 'node1'
+
+        self.inv.set_etcd([host])
+        self.assertIn(
+            host, self.inv.yaml_config['all']['children'][group]['hosts'])
+
+    def test_scale_scenario_one(self):
+        num_nodes = 50
+        hosts = OrderedDict()
+
+        for hostid in range(1, num_nodes+1):
+            hosts["node" + str(hostid)] = ""
+
+        self.inv.set_all(hosts)
+        self.inv.set_etcd(list(hosts.keys())[0:3])
+        self.inv.set_kube_control_plane(list(hosts.keys())[0:2])
+        self.inv.set_kube_node(hosts.keys())
+        for h in range(3):
+            self.assertFalse(
+                list(hosts.keys())[h] in
+                self.inv.yaml_config['all']['children']['kube_node']['hosts'])
+
+    def test_scale_scenario_two(self):
+        num_nodes = 500
+        hosts = OrderedDict()
+
+        for hostid in range(1, num_nodes+1):
+            hosts["node" + str(hostid)] = ""
+
+        self.inv.set_all(hosts)
+        self.inv.set_etcd(list(hosts.keys())[0:3])
+        self.inv.set_kube_control_plane(list(hosts.keys())[3:5])
+        self.inv.set_kube_node(hosts.keys())
+        for h in range(5):
+            self.assertFalse(
+                list(hosts.keys())[h] in
+                self.inv.yaml_config['all']['children']['kube_node']['hosts'])
+
+    def test_range2ips_range(self):
+        changed_hosts = ['10.90.0.2', '10.90.0.4-10.90.0.6', '10.90.0.8']
+        expected = ['10.90.0.2',
+                    '10.90.0.4',
+                    '10.90.0.5',
+                    '10.90.0.6',
+                    '10.90.0.8']
+        result = self.inv.range2ips(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_range2ips_incorrect_range(self):
+        host_range = ['10.90.0.4-a.9b.c.e']
+        self.assertRaisesRegex(Exception, "Range of ip_addresses isn't valid",
+                               self.inv.range2ips, host_range)
+
+    def test_build_hostnames_create_with_one_different_ips(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2']
+        expected = OrderedDict([('node1',
+                                 {'ansible_host': '192.168.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '192.168.0.2'})])
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_create_with_two_different_ips(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2', '10.90.0.3,192.168.0.3']
+        expected = OrderedDict([
+            ('node1', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node2', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'})])
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_create_with_three_different_ips(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2',
+                         '10.90.0.3,192.168.0.3',
+                         '10.90.0.4,192.168.0.4']
+        expected = OrderedDict([
+            ('node1', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node2', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node3', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_overwrite_one_with_different_ips(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2']
+        expected = OrderedDict([('node1',
+                                 {'ansible_host': '192.168.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '192.168.0.2'})])
+        existing = OrderedDict([('node5',
+                                 {'ansible_host': '192.168.0.5',
+                                  'ip': '10.90.0.5',
+                                  'access_ip': '192.168.0.5'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_overwrite_three_with_different_ips(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2']
+        expected = OrderedDict([('node1',
+                                 {'ansible_host': '192.168.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '192.168.0.2'})])
+        existing = OrderedDict([
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'}),
+            ('node5', {'ansible_host': '192.168.0.5',
+                       'ip': '10.90.0.5',
+                       'access_ip': '192.168.0.5'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_different_ips_add_duplicate(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2']
+        expected = OrderedDict([('node3',
+                                 {'ansible_host': '192.168.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '192.168.0.2'})])
+        existing = expected
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_two_different_ips_into_one_existing(self):
+        changed_hosts = ['10.90.0.3,192.168.0.3', '10.90.0.4,192.168.0.4']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_two_different_ips_into_two_existing(self):
+        changed_hosts = ['10.90.0.4,192.168.0.4', '10.90.0.5,192.168.0.5']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'}),
+            ('node5', {'ansible_host': '192.168.0.5',
+                       'ip': '10.90.0.5',
+                       'access_ip': '192.168.0.5'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_two_different_ips_into_three_existing(self):
+        changed_hosts = ['10.90.0.5,192.168.0.5', '10.90.0.6,192.168.0.6']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'}),
+            ('node5', {'ansible_host': '192.168.0.5',
+                       'ip': '10.90.0.5',
+                       'access_ip': '192.168.0.5'}),
+            ('node6', {'ansible_host': '192.168.0.6',
+                       'ip': '10.90.0.6',
+                       'access_ip': '192.168.0.6'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    # Add two IP addresses into a config that has
+    # three already defined IP addresses. One of the IP addresses
+    # is a duplicate.
+    def test_build_hostnames_add_two_duplicate_one_overlap(self):
+        changed_hosts = ['10.90.0.4,192.168.0.4', '10.90.0.5,192.168.0.5']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'}),
+            ('node5', {'ansible_host': '192.168.0.5',
+                       'ip': '10.90.0.5',
+                       'access_ip': '192.168.0.5'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    # Add two duplicate IP addresses into a config that has
+    # three already defined IP addresses
+    def test_build_hostnames_add_two_duplicate_two_overlap(self):
+        changed_hosts = ['10.90.0.3,192.168.0.3', '10.90.0.4,192.168.0.4']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)

contrib/inventory_builder/tox.ini

@@ -0,0 +1,34 @@
+[tox]
+minversion = 1.6
+skipsdist = True
+envlist = pep8
+
+[testenv]
+allowlist_externals = py.test
+usedevelop = True
+deps =
+    -r{toxinidir}/requirements.txt
+    -r{toxinidir}/test-requirements.txt
+setenv = VIRTUAL_ENV={envdir}
+passenv =
+    http_proxy
+    HTTP_PROXY
+    https_proxy
+    HTTPS_PROXY
+    no_proxy
+    NO_PROXY
+commands = pytest -vv #{posargs:./tests}
+
+[testenv:pep8]
+usedevelop = False
+allowlist_externals = bash
+commands =
+    bash -c "find {toxinidir}/* -type f -name '*.py' -print0 | xargs -0 flake8"
+
+[testenv:venv]
+commands = {posargs}
+
+[flake8]
+show-source = true
+builtins = _
+exclude=.venv,.git,.tox,dist,doc,*lib/python*,*egg

contrib/kvm-setup/kvm-setup.yml

@@ -1,8 +1,8 @@
 ---
 - name: Prepare Hypervisor to later install kubespray VMs
   hosts: localhost
-  gather_facts: false
+  gather_facts: False
-  become: true
+  become: yes
   vars:
     bootstrap_os: none
   roles:

contrib/kvm-setup/roles/kvm-setup/tasks/main.yml

@@ -11,12 +11,12 @@
 
 - name: Install required packages
   apt:
-    upgrade: true
+    upgrade: yes
-    update_cache: true
+    update_cache: yes
     cache_valid_time: 3600
     name: "{{ item }}"
     state: present
-    install_recommends: false
+    install_recommends: no
   with_items:
     - dnsutils
     - ntp

contrib/kvm-setup/roles/kvm-setup/tasks/sysctl.yml

@@ -20,7 +20,7 @@
       br-netfilter
     owner: root
     group: root
-    mode: "0644"
+    mode: 0644
   when: br_netfilter is defined
 
 
@@ -30,7 +30,7 @@
     value: 1
     sysctl_file: "{{ sysctl_file_path }}"
     state: present
-    reload: true
+    reload: yes
 
 - name: Set bridge-nf-call-{arptables,iptables} to 0
   ansible.posix.sysctl:
@@ -38,7 +38,7 @@
     state: present
     value: 0
     sysctl_file: "{{ sysctl_file_path }}"
-    reload: true
+    reload: yes
   with_items:
     - net.bridge.bridge-nf-call-arptables
     - net.bridge.bridge-nf-call-ip6tables

contrib/kvm-setup/roles/kvm-setup/tasks/user.yml

@@ -11,7 +11,7 @@
     state: directory
     owner: "{{ k8s_deployment_user }}"
     group: "{{ k8s_deployment_user }}"
-    mode: "0700"
+    mode: 0700
 
 - name: Configure sudo for deployment user
   copy:
@@ -20,13 +20,13 @@
     dest: "/etc/sudoers.d/55-k8s-deployment"
     owner: root
     group: root
-    mode: "0644"
+    mode: 0644
 
 - name: Write private SSH key
   copy:
     src: "{{ k8s_deployment_user_pkey_path }}"
     dest: "/home/{{ k8s_deployment_user }}/.ssh/id_rsa"
-    mode: "0400"
+    mode: 0400
     owner: "{{ k8s_deployment_user }}"
     group: "{{ k8s_deployment_user }}"
   when: k8s_deployment_user_pkey_path is defined
@@ -41,7 +41,7 @@
 - name: Fix ssh-pub-key permissions
   file:
     path: "/home/{{ k8s_deployment_user }}/.ssh/authorized_keys"
-    mode: "0600"
+    mode: 0600
     owner: "{{ k8s_deployment_user }}"
     group: "{{ k8s_deployment_user }}"
   when: k8s_deployment_user_pkey_path is defined

contrib/mitogen/mitogen.yml

@@ -14,7 +14,7 @@
       file:
         path: "{{ item }}"
         state: directory
-        mode: "0755"
+        mode: 0755
       become: false
       loop:
         - "{{ playbook_dir }}/plugins/mitogen"
@@ -25,7 +25,7 @@
         url: "{{ mitogen_url }}"
         dest: "{{ playbook_dir }}/dist/mitogen_{{ mitogen_version }}.tar.gz"
         validate_certs: true
-        mode: "0644"
+        mode: 0644
 
     - name: Extract archive
       unarchive:
@@ -40,7 +40,7 @@
     - name: Add strategy to ansible.cfg
       community.general.ini_file:
         path: ansible.cfg
-        mode: "0644"
+        mode: 0644
         section: "{{ item.section | d('defaults') }}"
         option: "{{ item.option }}"
         value: "{{ item.value }}"

contrib/network-storage/glusterfs/README.md

@@ -0,0 +1,92 @@
+# Deploying a Kubespray Kubernetes Cluster with GlusterFS
+
+You can either deploy using Ansible on its own by supplying your own inventory file or by using Terraform to create the VMs and then providing a dynamic inventory to Ansible. The following two sections are self-contained, you don't need to go through one to use the other. So, if you want to provision with Terraform, you can skip the **Using an Ansible inventory** section, and if you want to provision with a pre-built ansible inventory, you can neglect the **Using Terraform and Ansible**  section.
+
+## Using an Ansible inventory
+
+In the same directory of this ReadMe file you should find a file named `inventory.example` which contains an example setup. Please note that, additionally to the Kubernetes nodes/masters, we define a set of machines for GlusterFS and we add them to the group `[gfs-cluster]`, which in turn is added to the larger `[network-storage]` group as a child group.
+
+Change that file to reflect your local setup (adding more machines or removing them and setting the adequate ip numbers), and save it to `inventory/sample/k8s_gfs_inventory`. Make sure that the settings on `inventory/sample/group_vars/all.yml` make sense with your deployment. Then execute change to the kubespray root folder, and execute (supposing that the machines are all using ubuntu):
+
+```shell
+ansible-playbook -b --become-user=root -i inventory/sample/k8s_gfs_inventory --user=ubuntu ./cluster.yml
+```
+
+This will provision your Kubernetes cluster. Then, to provision and configure the GlusterFS cluster, from the same directory execute:
+
+```shell
+ansible-playbook -b --become-user=root -i inventory/sample/k8s_gfs_inventory --user=ubuntu ./contrib/network-storage/glusterfs/glusterfs.yml
+```
+
+If your machines are not using Ubuntu, you need to change the `--user=ubuntu` to the correct user. Alternatively, if your Kubernetes machines are using one OS and your GlusterFS a different one, you can instead specify the `ansible_ssh_user=<correct-user>` variable in the inventory file that you just created, for each machine/VM:
+
+```shell
+k8s-master-1 ansible_ssh_host=192.168.0.147 ip=192.168.0.147 ansible_ssh_user=core
+k8s-master-node-1 ansible_ssh_host=192.168.0.148 ip=192.168.0.148 ansible_ssh_user=core
+k8s-master-node-2 ansible_ssh_host=192.168.0.146 ip=192.168.0.146 ansible_ssh_user=core
+```
+
+## Using Terraform and Ansible
+
+First step is to fill in a `my-kubespray-gluster-cluster.tfvars` file with the specification desired for your cluster. An example with all required variables would look like:
+
+```ini
+cluster_name = "cluster1"
+number_of_k8s_masters = "1"
+number_of_k8s_masters_no_floating_ip = "2"
+number_of_k8s_nodes_no_floating_ip = "0"
+number_of_k8s_nodes = "0"
+public_key_path = "~/.ssh/my-desired-key.pub"
+image = "Ubuntu 16.04"
+ssh_user = "ubuntu"
+flavor_k8s_node = "node-flavor-id-in-your-openstack"
+flavor_k8s_master = "master-flavor-id-in-your-openstack"
+network_name = "k8s-network"
+floatingip_pool = "net_external"
+
+# GlusterFS variables
+flavor_gfs_node = "gluster-flavor-id-in-your-openstack"
+image_gfs = "Ubuntu 16.04"
+number_of_gfs_nodes_no_floating_ip = "3"
+gfs_volume_size_in_gb = "50"
+ssh_user_gfs = "ubuntu"
+```
+
+As explained in the general terraform/openstack guide, you need to source your OpenStack credentials file, add your ssh-key to the ssh-agent and setup environment variables for terraform:
+
+```shell
+$ source ~/.stackrc
+$ eval $(ssh-agent -s)
+$ ssh-add ~/.ssh/my-desired-key
+$ echo Setting up Terraform creds && \
+  export TF_VAR_username=${OS_USERNAME} && \
+  export TF_VAR_password=${OS_PASSWORD} && \
+  export TF_VAR_tenant=${OS_TENANT_NAME} && \
+  export TF_VAR_auth_url=${OS_AUTH_URL}
+```
+
+Then, standing on the kubespray directory (root base of the Git checkout), issue the following terraform command to create the VMs for the cluster:
+
+```shell
+terraform apply -state=contrib/terraform/openstack/terraform.tfstate -var-file=my-kubespray-gluster-cluster.tfvars contrib/terraform/openstack
+```
+
+This will create both your Kubernetes and Gluster VMs. Make sure that the ansible file `contrib/terraform/openstack/group_vars/all.yml` includes any ansible variable that you want to setup (like, for instance, the type of machine for bootstrapping).
+
+Then, provision your Kubernetes (kubespray) cluster with the following ansible call:
+
+```shell
+ansible-playbook -b --become-user=root -i contrib/terraform/openstack/hosts ./cluster.yml
+```
+
+Finally, provision the glusterfs nodes and add the Persistent Volume setup for GlusterFS in Kubernetes through the following ansible call:
+
+```shell
+ansible-playbook -b --become-user=root -i contrib/terraform/openstack/hosts ./contrib/network-storage/glusterfs/glusterfs.yml
+```
+
+If you need to destroy the cluster, you can run:
+
+```shell
+terraform destroy -state=contrib/terraform/openstack/terraform.tfstate -var-file=my-kubespray-gluster-cluster.tfvars contrib/terraform/openstack
+```

contrib/network-storage/glusterfs/glusterfs.yml

@@ -0,0 +1,29 @@
+---
+- name: Bootstrap hosts
+  hosts: gfs-cluster
+  gather_facts: false
+  vars:
+    ansible_ssh_pipelining: false
+  roles:
+    - { role: bootstrap-os, tags: bootstrap-os}
+
+- name: Gather facts
+  hosts: all
+  gather_facts: true
+
+- name: Install glusterfs server
+  hosts: gfs-cluster
+  vars:
+    ansible_ssh_pipelining: true
+  roles:
+    - { role: glusterfs/server }
+
+- name: Install glusterfs servers
+  hosts: k8s_cluster
+  roles:
+    - { role: glusterfs/client }
+
+- name: Configure Kubernetes to use glusterfs
+  hosts: kube_control_plane[0]
+  roles:
+    - { role: kubernetes-pv }

contrib/network-storage/glusterfs/group_vars

@@ -0,0 +1 @@
+../../../inventory/local/group_vars

contrib/network-storage/glusterfs/inventory.example

@@ -0,0 +1,43 @@
+# ## Configure 'ip' variable to bind kubernetes services on a
+# ## different ip than the default iface
+# node1 ansible_ssh_host=95.54.0.12  # ip=10.3.0.1
+# node2 ansible_ssh_host=95.54.0.13  # ip=10.3.0.2
+# node3 ansible_ssh_host=95.54.0.14  # ip=10.3.0.3
+# node4 ansible_ssh_host=95.54.0.15  # ip=10.3.0.4
+# node5 ansible_ssh_host=95.54.0.16  # ip=10.3.0.5
+# node6 ansible_ssh_host=95.54.0.17  # ip=10.3.0.6
+#
+# ## GlusterFS nodes
+# ## Set disk_volume_device_1 to desired device for gluster brick, if different to /dev/vdb (default).
+# ## As in the previous case, you can set ip to give direct communication on internal IPs
+# gfs_node1 ansible_ssh_host=95.54.0.18 # disk_volume_device_1=/dev/vdc  ip=10.3.0.7
+# gfs_node2 ansible_ssh_host=95.54.0.19 # disk_volume_device_1=/dev/vdc  ip=10.3.0.8
+# gfs_node3 ansible_ssh_host=95.54.0.20 # disk_volume_device_1=/dev/vdc  ip=10.3.0.9
+
+# [kube_control_plane]
+# node1
+# node2
+
+# [etcd]
+# node1
+# node2
+# node3
+
+# [kube_node]
+# node2
+# node3
+# node4
+# node5
+# node6
+
+# [k8s_cluster:children]
+# kube_node
+# kube_control_plane
+
+# [gfs-cluster]
+# gfs_node1
+# gfs_node2
+# gfs_node3
+
+# [network-storage:children]
+# gfs-cluster

contrib/network-storage/glusterfs/roles/bootstrap-os

@@ -0,0 +1 @@
+../../../../roles/bootstrap-os

contrib/network-storage/glusterfs/roles/glusterfs/README.md

@@ -0,0 +1,50 @@
+# Ansible Role: GlusterFS
+
+[![Build Status](https://travis-ci.org/geerlingguy/ansible-role-glusterfs.svg?branch=master)](https://travis-ci.org/geerlingguy/ansible-role-glusterfs)
+
+Installs and configures GlusterFS on Linux.
+
+## Requirements
+
+For GlusterFS to connect between servers, TCP ports `24007`, `24008`, and `24009`/`49152`+ (that port, plus an additional incremented port for each additional server in the cluster; the latter if GlusterFS is version 3.4+), and TCP/UDP port `111` must be open. You can open these using whatever firewall you wish (this can easily be configured using the `geerlingguy.firewall` role).
+
+This role performs basic installation and setup of Gluster, but it does not configure or mount bricks (volumes), since that step is easier to do in a series of plays in your own playbook. Ansible 1.9+ includes the [`gluster_volume`](https://docs.ansible.com/ansible/latest/collections/gluster/gluster/gluster_volume_module.html) module to ease the management of Gluster volumes.
+
+## Role Variables
+
+Available variables are listed below, along with default values (see `defaults/main.yml`):
+
+```yaml
+glusterfs_default_release: ""
+```
+
+You can specify a `default_release` for apt on Debian/Ubuntu by overriding this variable. This is helpful if you need a different package or version for the main GlusterFS packages (e.g. GlusterFS 3.5.x instead of 3.2.x with the `wheezy-backports` default release on Debian Wheezy).
+
+```yaml
+glusterfs_ppa_use: yes
+glusterfs_ppa_version: "3.5"
+```
+
+For Ubuntu, specify whether to use the official Gluster PPA, and which version of the PPA to use. See Gluster's [Getting Started Guide](https://docs.gluster.org/en/latest/Quick-Start-Guide/Quickstart/) for more info.
+
+## Dependencies
+
+None.
+
+## Example Playbook
+
+```yaml
+    - hosts: server
+      roles:
+        - geerlingguy.glusterfs
+```
+
+For a real-world use example, read through [Simple GlusterFS Setup with Ansible](http://www.jeffgeerling.com/blog/simple-glusterfs-setup-ansible), a blog post by this role's author, which is included in Chapter 8 of [Ansible for DevOps](https://www.ansiblefordevops.com/).
+
+## License
+
+MIT / BSD
+
+## Author Information
+
+This role was created in 2015 by [Jeff Geerling](http://www.jeffgeerling.com/), author of [Ansible for DevOps](https://www.ansiblefordevops.com/).

contrib/network-storage/glusterfs/roles/glusterfs/client/defaults/main.yml

@@ -0,0 +1,11 @@
+---
+# For Ubuntu.
+glusterfs_default_release: ""
+glusterfs_ppa_use: yes
+glusterfs_ppa_version: "4.1"
+
+# Gluster configuration.
+gluster_mount_dir: /mnt/gluster
+gluster_volume_node_mount_dir: /mnt/xfs-drive-gluster
+gluster_brick_dir: "{{ gluster_volume_node_mount_dir }}/brick"
+gluster_brick_name: gluster

contrib/network-storage/glusterfs/roles/glusterfs/client/meta/main.yml

@@ -0,0 +1,30 @@
+---
+dependencies: []
+
+galaxy_info:
+  author: geerlingguy
+  description: GlusterFS installation for Linux.
+  company: "Midwestern Mac, LLC"
+  license: "license (BSD, MIT)"
+  min_ansible_version: "2.0"
+  platforms:
+  - name: EL
+    versions:
+    - "6"
+    - "7"
+  - name: Ubuntu
+    versions:
+    - precise
+    - trusty
+    - xenial
+  - name: Debian
+    versions:
+    - wheezy
+    - jessie
+  galaxy_tags:
+  - system
+  - networking
+  - cloud
+  - clustering
+  - files
+  - sharing

contrib/network-storage/glusterfs/roles/glusterfs/client/tasks/main.yml

@@ -0,0 +1,21 @@
+---
+# This is meant for Ubuntu and RedHat installations, where apparently the glusterfs-client is not used from inside
+# hyperkube and needs to be installed as part of the system.
+
+# Setup/install tasks.
+- name: Setup RedHat distros for glusterfs
+  include_tasks: setup-RedHat.yml
+  when: ansible_os_family == 'RedHat' and groups['gfs-cluster'] is defined
+
+- name: Setup Debian distros for glusterfs
+  include_tasks: setup-Debian.yml
+  when: ansible_os_family == 'Debian' and groups['gfs-cluster'] is defined
+
+- name: Ensure Gluster mount directories exist.
+  file:
+    path: "{{ item }}"
+    state: directory
+    mode: 0775
+  with_items:
+    - "{{ gluster_mount_dir }}"
+  when: ansible_os_family in ["Debian","RedHat"] and groups['gfs-cluster'] is defined

contrib/network-storage/glusterfs/roles/glusterfs/client/tasks/setup-Debian.yml

@@ -0,0 +1,24 @@
+---
+- name: Add PPA for GlusterFS.
+  apt_repository:
+    repo: 'ppa:gluster/glusterfs-{{ glusterfs_ppa_version }}'
+    state: present
+    update_cache: yes
+  register: glusterfs_ppa_added
+  when: glusterfs_ppa_use
+
+- name: Ensure GlusterFS client will reinstall if the PPA was just added.  # noqa no-handler
+  apt:
+    name: "{{ item }}"
+    state: absent
+  with_items:
+    - glusterfs-client
+  when: glusterfs_ppa_added.changed
+
+- name: Ensure GlusterFS client is installed.
+  apt:
+    name: "{{ item }}"
+    state: present
+    default_release: "{{ glusterfs_default_release }}"
+  with_items:
+    - glusterfs-client

contrib/network-storage/glusterfs/roles/glusterfs/client/tasks/setup-RedHat.yml

@@ -0,0 +1,14 @@
+---
+- name: Install Prerequisites
+  package:
+    name: "{{ item }}"
+    state: present
+  with_items:
+    - "centos-release-gluster{{ glusterfs_default_release }}"
+
+- name: Install Packages
+  package:
+    name: "{{ item }}"
+    state: present
+  with_items:
+    - glusterfs-client

contrib/network-storage/glusterfs/roles/glusterfs/server/defaults/main.yml

@@ -0,0 +1,13 @@
+---
+# For Ubuntu.
+glusterfs_default_release: ""
+glusterfs_ppa_use: yes
+glusterfs_ppa_version: "3.12"
+
+# Gluster configuration.
+gluster_mount_dir: /mnt/gluster
+gluster_volume_node_mount_dir: /mnt/xfs-drive-gluster
+gluster_brick_dir: "{{ gluster_volume_node_mount_dir }}/brick"
+gluster_brick_name: gluster
+# Default device to mount for xfs formatting, terraform overrides this by setting the variable in the inventory.
+disk_volume_device_1: /dev/vdb

contrib/network-storage/glusterfs/roles/glusterfs/server/meta/main.yml

@@ -0,0 +1,30 @@
+---
+dependencies: []
+
+galaxy_info:
+  author: geerlingguy
+  description: GlusterFS installation for Linux.
+  company: "Midwestern Mac, LLC"
+  license: "license (BSD, MIT)"
+  min_ansible_version: "2.0"
+  platforms:
+  - name: EL
+    versions:
+    - "6"
+    - "7"
+  - name: Ubuntu
+    versions:
+    - precise
+    - trusty
+    - xenial
+  - name: Debian
+    versions:
+    - wheezy
+    - jessie
+  galaxy_tags:
+  - system
+  - networking
+  - cloud
+  - clustering
+  - files
+  - sharing

contrib/network-storage/glusterfs/roles/glusterfs/server/tasks/main.yml

@@ -0,0 +1,113 @@
+---
+# Include variables and define needed variables.
+- name: Include OS-specific variables.
+  include_vars: "{{ ansible_os_family }}.yml"
+
+# Install xfs package
+- name: Install xfs Debian
+  apt:
+    name: xfsprogs
+    state: present
+  when: ansible_os_family == "Debian"
+
+- name: Install xfs RedHat
+  package:
+    name: xfsprogs
+    state: present
+  when: ansible_os_family == "RedHat"
+
+# Format external volumes in xfs
+- name: Format volumes in xfs
+  community.general.filesystem:
+    fstype: xfs
+    dev: "{{ disk_volume_device_1 }}"
+
+# Mount external volumes
+- name: Mounting new xfs filesystem
+  ansible.posix.mount:
+    name: "{{ gluster_volume_node_mount_dir }}"
+    src: "{{ disk_volume_device_1 }}"
+    fstype: xfs
+    state: mounted
+
+# Setup/install tasks.
+- name: Setup RedHat distros for glusterfs
+  include_tasks: setup-RedHat.yml
+  when: ansible_os_family == 'RedHat'
+
+- name: Setup Debian distros for glusterfs
+  include_tasks: setup-Debian.yml
+  when: ansible_os_family == 'Debian'
+
+- name: Ensure GlusterFS is started and enabled at boot.
+  service:
+    name: "{{ glusterfs_daemon }}"
+    state: started
+    enabled: yes
+
+- name: Ensure Gluster brick and mount directories exist.
+  file:
+    path: "{{ item }}"
+    state: directory
+    mode: 0775
+  with_items:
+    - "{{ gluster_brick_dir }}"
+    - "{{ gluster_mount_dir }}"
+
+- name: Configure Gluster volume with replicas
+  gluster.gluster.gluster_volume:
+    state: present
+    name: "{{ gluster_brick_name }}"
+    brick: "{{ gluster_brick_dir }}"
+    replicas: "{{ groups['gfs-cluster'] | length }}"
+    cluster: "{% for item in groups['gfs-cluster'] -%}{{ hostvars[item]['ip'] | default(hostvars[item].ansible_default_ipv4['address']) }}{% if not loop.last %},{% endif %}{%- endfor %}"
+    host: "{{ inventory_hostname }}"
+    force: yes
+  run_once: true
+  when: groups['gfs-cluster'] | length > 1
+
+- name: Configure Gluster volume without replicas
+  gluster.gluster.gluster_volume:
+    state: present
+    name: "{{ gluster_brick_name }}"
+    brick: "{{ gluster_brick_dir }}"
+    cluster: "{% for item in groups['gfs-cluster'] -%}{{ hostvars[item]['ip'] | default(hostvars[item].ansible_default_ipv4['address']) }}{% if not loop.last %},{% endif %}{%- endfor %}"
+    host: "{{ inventory_hostname }}"
+    force: yes
+  run_once: true
+  when: groups['gfs-cluster'] | length <= 1
+
+- name: Mount glusterfs to retrieve disk size
+  ansible.posix.mount:
+    name: "{{ gluster_mount_dir }}"
+    src: "{{ ip | default(ansible_default_ipv4['address']) }}:/gluster"
+    fstype: glusterfs
+    opts: "defaults,_netdev"
+    state: mounted
+  when: groups['gfs-cluster'] is defined and inventory_hostname == groups['gfs-cluster'][0]
+
+- name: Get Gluster disk size
+  setup:
+    filter: ansible_mounts
+  register: mounts_data
+  when: groups['gfs-cluster'] is defined and inventory_hostname == groups['gfs-cluster'][0]
+
+- name: Set Gluster disk size to variable
+  set_fact:
+    gluster_disk_size_gb: "{{ (mounts_data.ansible_facts.ansible_mounts | selectattr('mount', 'equalto', gluster_mount_dir) | map(attribute='size_total') | first | int / (1024 * 1024 * 1024)) | int }}"
+  when: groups['gfs-cluster'] is defined and inventory_hostname == groups['gfs-cluster'][0]
+
+- name: Create file on GlusterFS
+  template:
+    dest: "{{ gluster_mount_dir }}/.test-file.txt"
+    src: test-file.txt
+    mode: 0644
+  when: groups['gfs-cluster'] is defined and inventory_hostname == groups['gfs-cluster'][0]
+
+- name: Unmount glusterfs
+  ansible.posix.mount:
+    name: "{{ gluster_mount_dir }}"
+    fstype: glusterfs
+    src: "{{ ip | default(ansible_default_ipv4['address']) }}:/gluster"
+    state: unmounted
+  when: groups['gfs-cluster'] is defined and inventory_hostname == groups['gfs-cluster'][0]

contrib/network-storage/glusterfs/roles/glusterfs/server/tasks/setup-Debian.yml

@@ -0,0 +1,26 @@
+---
+- name: Add PPA for GlusterFS.
+  apt_repository:
+    repo: 'ppa:gluster/glusterfs-{{ glusterfs_ppa_version }}'
+    state: present
+    update_cache: yes
+  register: glusterfs_ppa_added
+  when: glusterfs_ppa_use
+
+- name: Ensure GlusterFS will reinstall if the PPA was just added.  # noqa no-handler
+  apt:
+    name: "{{ item }}"
+    state: absent
+  with_items:
+    - glusterfs-server
+    - glusterfs-client
+  when: glusterfs_ppa_added.changed
+
+- name: Ensure GlusterFS is installed.
+  apt:
+    name: "{{ item }}"
+    state: present
+    default_release: "{{ glusterfs_default_release }}"
+  with_items:
+    - glusterfs-server
+    - glusterfs-client

contrib/network-storage/glusterfs/roles/glusterfs/server/tasks/setup-RedHat.yml

@@ -0,0 +1,15 @@
+---
+- name: Install Prerequisites
+  package:
+    name: "{{ item }}"
+    state: present
+  with_items:
+    - "centos-release-gluster{{ glusterfs_default_release }}"
+
+- name: Install Packages
+  package:
+    name: "{{ item }}"
+    state: present
+  with_items:
+    - glusterfs-server
+    - glusterfs-client

contrib/network-storage/glusterfs/roles/glusterfs/server/templates/test-file.txt

@@ -0,0 +1 @@
+test file

contrib/network-storage/glusterfs/roles/glusterfs/server/vars/Debian.yml

@@ -0,0 +1,2 @@
+---
+glusterfs_daemon: glusterd

contrib/network-storage/glusterfs/roles/glusterfs/server/vars/RedHat.yml

@@ -0,0 +1,2 @@
+---
+glusterfs_daemon: glusterd

contrib/network-storage/glusterfs/roles/kubernetes-pv/ansible/tasks/main.yaml

@@ -0,0 +1,23 @@
+---
+- name: Kubernetes Apps | Lay Down k8s GlusterFS Endpoint and PV
+  template:
+    src: "{{ item.file }}"
+    dest: "{{ kube_config_dir }}/{{ item.dest }}"
+    mode: 0644
+  with_items:
+    - { file: glusterfs-kubernetes-endpoint.json.j2, type: ep, dest: glusterfs-kubernetes-endpoint.json}
+    - { file: glusterfs-kubernetes-pv.yml.j2, type: pv, dest: glusterfs-kubernetes-pv.yml}
+    - { file: glusterfs-kubernetes-endpoint-svc.json.j2, type: svc, dest: glusterfs-kubernetes-endpoint-svc.json}
+  register: gluster_pv
+  when: inventory_hostname == groups['kube_control_plane'][0] and groups['gfs-cluster'] is defined and hostvars[groups['gfs-cluster'][0]].gluster_disk_size_gb is defined
+
+- name: Kubernetes Apps | Set GlusterFS endpoint and PV
+  kube:
+    name: glusterfs
+    namespace: default
+    kubectl: "{{ bin_dir }}/kubectl"
+    resource: "{{ item.item.type }}"
+    filename: "{{ kube_config_dir }}/{{ item.item.dest }}"
+    state: "{{ item.changed | ternary('latest', 'present') }}"
+  with_items: "{{ gluster_pv.results }}"
+  when: inventory_hostname == groups['kube_control_plane'][0] and groups['gfs-cluster'] is defined

contrib/network-storage/glusterfs/roles/kubernetes-pv/ansible/templates/glusterfs-kubernetes-endpoint-svc.json.j2

@@ -0,0 +1,12 @@
+{
+  "kind": "Service",
+  "apiVersion": "v1",
+  "metadata": {
+    "name": "glusterfs"
+  },
+  "spec": {
+    "ports": [
+      {"port": 1}
+    ]
+  }
+}

contrib/network-storage/glusterfs/roles/kubernetes-pv/ansible/templates/glusterfs-kubernetes-endpoint.json.j2

@@ -0,0 +1,23 @@
+{
+  "kind": "Endpoints",
+  "apiVersion": "v1",
+  "metadata": {
+    "name": "glusterfs"
+  },
+  "subsets": [
+    {% for host in groups['gfs-cluster'] %}
+    {
+      "addresses": [
+        {
+          "ip": "{{hostvars[host]['ip']|default(hostvars[host].ansible_default_ipv4['address'])}}"
+        }
+      ],
+      "ports": [
+        {
+          "port": 1
+        }
+      ]
+    }{%- if not loop.last %}, {% endif -%}
+    {% endfor %}
+  ]
+}

contrib/network-storage/glusterfs/roles/kubernetes-pv/ansible/templates/glusterfs-kubernetes-pv.yml.j2

@@ -0,0 +1,14 @@
+apiVersion: v1
+kind: PersistentVolume
+metadata:
+  name: glusterfs
+spec:
+  capacity:
+      storage: "{{ hostvars[groups['gfs-cluster'][0]].gluster_disk_size_gb }}Gi"
+  accessModes:
+    - ReadWriteMany
+  glusterfs:
+    endpoints: glusterfs
+    path: gluster
+    readOnly: false
+  persistentVolumeReclaimPolicy: Retain

contrib/network-storage/glusterfs/roles/kubernetes-pv/meta/main.yaml

@@ -0,0 +1,3 @@
+---
+dependencies:
+  - {role: kubernetes-pv/ansible, tags: apps}

contrib/network-storage/heketi/README.md

@@ -0,0 +1,27 @@
+# Deploy Heketi/Glusterfs into Kubespray/Kubernetes
+
+This playbook aims to automate [this](https://github.com/heketi/heketi/blob/master/docs/admin/install-kubernetes.md) tutorial. It deploys heketi/glusterfs into kubernetes and sets up a storageclass.
+
+## Important notice
+
+> Due to resource limits on the current project maintainers and general lack of contributions we are considering placing Heketi into a [near-maintenance mode](https://github.com/heketi/heketi#important-notice)
+
+## Client Setup
+
+Heketi provides a CLI that provides users with a means to administer the deployment and configuration of GlusterFS in Kubernetes. [Download and install the heketi-cli](https://github.com/heketi/heketi/releases) on your client machine.
+
+## Install
+
+Copy the inventory.yml.sample over to inventory/sample/k8s_heketi_inventory.yml and change it according to your setup.
+
+```shell
+ansible-playbook --ask-become -i inventory/sample/k8s_heketi_inventory.yml contrib/network-storage/heketi/heketi.yml
+```
+
+## Tear down
+
+```shell
+ansible-playbook --ask-become -i inventory/sample/k8s_heketi_inventory.yml contrib/network-storage/heketi/heketi-tear-down.yml
+```
+
+Add `--extra-vars "heketi_remove_lvm=true"` to the command above to remove LVM packages from the system

contrib/network-storage/heketi/heketi-tear-down.yml

@@ -0,0 +1,11 @@
+---
+- name: Tear down heketi
+  hosts: kube_control_plane[0]
+  roles:
+    - { role: tear-down }
+
+- name: Teardown disks in heketi
+  hosts: heketi-node
+  become: yes
+  roles:
+    - { role: tear-down-disks }

contrib/network-storage/heketi/heketi.yml

@@ -0,0 +1,12 @@
+---
+- name: Prepare heketi install
+  hosts: heketi-node
+  roles:
+    - { role: prepare }
+
+- name: Provision heketi
+  hosts: kube_control_plane[0]
+  tags:
+    - "provision"
+  roles:
+    - { role: provision }

contrib/network-storage/heketi/inventory.yml.sample

@@ -0,0 +1,33 @@
+all:
+    vars:
+        heketi_admin_key: "11elfeinhundertundelf"
+        heketi_user_key: "!!einseinseins"
+        glusterfs_daemonset:
+            readiness_probe:
+                timeout_seconds: 3
+                initial_delay_seconds: 3
+            liveness_probe:
+                timeout_seconds: 3
+                initial_delay_seconds: 10
+    children:
+        k8s_cluster:
+            vars:
+                kubelet_fail_swap_on: false
+            children:
+                kube_control_plane:
+                    hosts:
+                        node1:
+                etcd:
+                    hosts:
+                        node2:
+                kube_node:
+                    hosts: &kube_nodes
+                        node1:
+                        node2:
+                        node3:
+                        node4:
+                heketi-node:
+                    vars:
+                        disk_volume_device_1: "/dev/vdb"
+                    hosts:
+                        <<: *kube_nodes

contrib/network-storage/heketi/requirements.txt

@@ -0,0 +1 @@
+jmespath

contrib/network-storage/heketi/roles/prepare/tasks/main.yml

@@ -0,0 +1,24 @@
+---
+- name: "Load lvm kernel modules"
+  become: true
+  with_items:
+    - "dm_snapshot"
+    - "dm_mirror"
+    - "dm_thin_pool"
+  community.general.modprobe:
+    name: "{{ item }}"
+    state: "present"
+
+- name: "Install glusterfs mount utils (RedHat)"
+  become: true
+  package:
+    name: "glusterfs-fuse"
+    state: "present"
+  when: "ansible_os_family == 'RedHat'"
+
+- name: "Install glusterfs mount utils (Debian)"
+  become: true
+  apt:
+    name: "glusterfs-client"
+    state: "present"
+  when: "ansible_os_family == 'Debian'"

contrib/network-storage/heketi/roles/provision/defaults/main.yml

@@ -0,0 +1 @@
+---

contrib/network-storage/heketi/roles/provision/handlers/main.yml

@@ -0,0 +1,3 @@
+---
+- name: "Stop port forwarding"
+  command: "killall "

contrib/network-storage/heketi/roles/provision/tasks/bootstrap.yml

@@ -0,0 +1,64 @@
+---
+# Bootstrap heketi
+- name: "Get state of heketi service, deployment and pods."
+  register: "initial_heketi_state"
+  changed_when: false
+  command: "{{ bin_dir }}/kubectl get services,deployments,pods --selector=deploy-heketi --output=json"
+
+- name: "Bootstrap heketi."
+  when:
+    - "(initial_heketi_state.stdout | from_json | json_query(\"items[?kind=='Service']\")) | length == 0"
+    - "(initial_heketi_state.stdout | from_json | json_query(\"items[?kind=='Deployment']\")) | length == 0"
+    - "(initial_heketi_state.stdout | from_json | json_query(\"items[?kind=='Pod']\")) | length == 0"
+  include_tasks: "bootstrap/deploy.yml"
+
+# Prepare heketi topology
+- name: "Get heketi initial pod state."
+  register: "initial_heketi_pod"
+  command: "{{ bin_dir }}/kubectl get pods --selector=deploy-heketi=pod,glusterfs=heketi-pod,name=deploy-heketi --output=json"
+  changed_when: false
+
+- name: "Ensure heketi bootstrap pod is up."
+  assert:
+    that: "(initial_heketi_pod.stdout | from_json | json_query('items[*]')) | length == 1"
+
+- name: Store the initial heketi pod name
+  set_fact:
+    initial_heketi_pod_name: "{{ initial_heketi_pod.stdout | from_json | json_query(\"items[*].metadata.name | [0]\") }}"
+
+- name: "Test heketi topology."
+  changed_when: false
+  register: "heketi_topology"
+  command: "{{ bin_dir }}/kubectl exec {{ initial_heketi_pod_name }} -- heketi-cli --user admin --secret {{ heketi_admin_key }} topology info --json"
+
+- name: "Load heketi topology."
+  when: "heketi_topology.stdout | from_json | json_query(\"clusters[*].nodes[*]\") | flatten | length == 0"
+  include_tasks: "bootstrap/topology.yml"
+
+# Provision heketi database volume
+- name: "Prepare heketi volumes."
+  include_tasks: "bootstrap/volumes.yml"
+
+# Remove bootstrap heketi
+- name: "Tear down bootstrap."
+  include_tasks: "bootstrap/tear-down.yml"
+
+# Prepare heketi storage
+- name: "Test heketi storage."
+  command: "{{ bin_dir }}/kubectl get secrets,endpoints,services,jobs --output=json"
+  changed_when: false
+  register: "heketi_storage_state"
+
+# ensure endpoints actually exist before trying to move database data to it
+- name: "Create heketi storage."
+  include_tasks: "bootstrap/storage.yml"
+  vars:
+    secret_query: "items[?metadata.name=='heketi-storage-secret' && kind=='Secret']"
+    endpoints_query: "items[?metadata.name=='heketi-storage-endpoints' && kind=='Endpoints']"
+    service_query: "items[?metadata.name=='heketi-storage-endpoints' && kind=='Service']"
+    job_query: "items[?metadata.name=='heketi-storage-copy-job' && kind=='Job']"
+  when:
+    - "heketi_storage_state.stdout | from_json | json_query(secret_query) | length == 0"
+    - "heketi_storage_state.stdout | from_json | json_query(endpoints_query) | length == 0"
+    - "heketi_storage_state.stdout | from_json | json_query(service_query) | length == 0"
+    - "heketi_storage_state.stdout | from_json | json_query(job_query) | length == 0"

contrib/network-storage/heketi/roles/provision/tasks/bootstrap/deploy.yml

@@ -0,0 +1,27 @@
+---
+- name: "Kubernetes Apps | Lay Down Heketi Bootstrap"
+  become: true
+  template:
+    src: "heketi-bootstrap.json.j2"
+    dest: "{{ kube_config_dir }}/heketi-bootstrap.json"
+    mode: 0640
+  register: "rendering"
+- name: "Kubernetes Apps | Install and configure Heketi Bootstrap"
+  kube:
+    name: "GlusterFS"
+    kubectl: "{{ bin_dir }}/kubectl"
+    filename: "{{ kube_config_dir }}/heketi-bootstrap.json"
+    state: "{{ rendering.changed | ternary('latest', 'present') }}"
+- name: "Wait for heketi bootstrap to complete."
+  changed_when: false
+  register: "initial_heketi_state"
+  vars:
+    initial_heketi_state: { stdout: "{}" }
+    pods_query: "items[?kind=='Pod'].status.conditions | [0][?type=='Ready'].status | [0]"
+    deployments_query: "items[?kind=='Deployment'].status.conditions | [0][?type=='Available'].status | [0]"
+  command: "{{ bin_dir }}/kubectl get services,deployments,pods --selector=deploy-heketi --output=json"
+  until:
+    - "initial_heketi_state.stdout | from_json | json_query(pods_query) == 'True'"
+    - "initial_heketi_state.stdout | from_json | json_query(deployments_query) == 'True'"
+  retries: 60
+  delay: 5

contrib/network-storage/heketi/roles/provision/tasks/bootstrap/storage.yml

@@ -0,0 +1,33 @@
+---
+- name: "Test heketi storage."
+  command: "{{ bin_dir }}/kubectl get secrets,endpoints,services,jobs --output=json"
+  changed_when: false
+  register: "heketi_storage_state"
+- name: "Create heketi storage."
+  kube:
+    name: "GlusterFS"
+    kubectl: "{{ bin_dir }}/kubectl"
+    filename: "{{ kube_config_dir }}/heketi-storage-bootstrap.json"
+    state: "present"
+  vars:
+    secret_query: "items[?metadata.name=='heketi-storage-secret' && kind=='Secret']"
+    endpoints_query: "items[?metadata.name=='heketi-storage-endpoints' && kind=='Endpoints']"
+    service_query: "items[?metadata.name=='heketi-storage-endpoints' && kind=='Service']"
+    job_query: "items[?metadata.name=='heketi-storage-copy-job' && kind=='Job']"
+  when:
+    - "heketi_storage_state.stdout | from_json | json_query(secret_query) | length == 0"
+    - "heketi_storage_state.stdout | from_json | json_query(endpoints_query) | length == 0"
+    - "heketi_storage_state.stdout | from_json | json_query(service_query) | length == 0"
+    - "heketi_storage_state.stdout | from_json | json_query(job_query) | length == 0"
+  register: "heketi_storage_result"
+- name: "Get state of heketi database copy job."
+  command: "{{ bin_dir }}/kubectl get jobs --output=json"
+  changed_when: false
+  register: "heketi_storage_state"
+  vars:
+    heketi_storage_state: { stdout: "{}" }
+    job_query: "items[?metadata.name=='heketi-storage-copy-job' && kind=='Job' && status.succeeded==1]"
+  until:
+    - "heketi_storage_state.stdout | from_json | json_query(job_query) | length == 1"
+  retries: 60
+  delay: 5

contrib/network-storage/heketi/roles/provision/tasks/bootstrap/tear-down.yml

@@ -0,0 +1,14 @@
+---
+- name: "Get existing Heketi deploy resources."
+  command: "{{ bin_dir }}/kubectl get all --selector=\"deploy-heketi\" -o=json"
+  register: "heketi_resources"
+  changed_when: false
+- name: "Delete bootstrap Heketi."
+  command: "{{ bin_dir }}/kubectl delete all,service,jobs,deployment,secret --selector=\"deploy-heketi\""
+  when: "heketi_resources.stdout | from_json | json_query('items[*]') | length > 0"
+- name: "Ensure there is nothing left over."
+  command: "{{ bin_dir }}/kubectl get all,service,jobs,deployment,secret --selector=\"deploy-heketi\" -o=json"
+  register: "heketi_result"
+  until: "heketi_result.stdout | from_json | json_query('items[*]') | length == 0"
+  retries: 60
+  delay: 5

contrib/network-storage/heketi/roles/provision/tasks/bootstrap/topology.yml

@@ -0,0 +1,27 @@
+---
+- name: "Get heketi topology."
+  changed_when: false
+  register: "heketi_topology"
+  command: "{{ bin_dir }}/kubectl exec {{ initial_heketi_pod_name }} -- heketi-cli --user admin --secret {{ heketi_admin_key }} topology info --json"
+- name: "Render heketi topology template."
+  become: true
+  vars: { nodes: "{{ groups['heketi-node'] }}" }
+  register: "render"
+  template:
+    src: "topology.json.j2"
+    dest: "{{ kube_config_dir }}/topology.json"
+    mode: 0644
+- name: "Copy topology configuration into container."
+  changed_when: false
+  command: "{{ bin_dir }}/kubectl cp {{ kube_config_dir }}/topology.json {{ initial_heketi_pod_name }}:/tmp/topology.json"
+- name: "Load heketi topology."  # noqa no-handler
+  when: "render.changed"
+  command: "{{ bin_dir }}/kubectl exec {{ initial_heketi_pod_name }} -- heketi-cli --user admin --secret {{ heketi_admin_key }} topology load --json=/tmp/topology.json"
+  register: "load_heketi"
+- name: "Get heketi topology."
+  changed_when: false
+  register: "heketi_topology"
+  command: "{{ bin_dir }}/kubectl exec {{ initial_heketi_pod_name }} -- heketi-cli --user admin --secret {{ heketi_admin_key }} topology info --json"
+  until: "heketi_topology.stdout | from_json | json_query(\"clusters[*].nodes[*].devices[?state=='online'].id\") | flatten | length == groups['heketi-node'] | length"
+  retries: 60
+  delay: 5