Patch versions updates

.ansible-lint

@@ -12,12 +12,10 @@ skip_list:
   # (Disabled in June 2021)
   - 'role-name'
 
-  # [var-naming]
+  # [var-naming] "defaults/main.yml" File defines variable 'apiVersion' that violates variable naming standards
   # In Kubespray we use variables that use camelCase to match their k8s counterparts
   # (Disabled in June 2021)
-  - 'var-naming[pattern]'
-  # Variables names from within roles in kubespray don't need role name as a prefix
-  - 'var-naming[no-role-prefix]'
+  - 'var-naming'
 
   # [fqcn-builtins]
   # Roles in kubespray don't need fully qualified collection names
@@ -41,7 +39,5 @@ exclude_paths:
   - .github
   - .ansible
   - .cache
-  - .gitlab-ci.yml
-  - .gitlab-ci
 mock_modules:
   - gluster.gluster.gluster_volume

.github/ISSUE_TEMPLATE/bug-report.yaml

@@ -108,6 +108,7 @@ body:
         - meta
         - multus
         - ovn4nfv
+        - weave
     validations:
       required: true
 

.github/dependabot.yml

@@ -16,6 +16,5 @@ updates:
     directory: "/"
     labels:
       - release-note-none
-      - ci-short
     schedule:
       interval: "weekly"

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

@@ -13,16 +13,16 @@ jobs:
       issues: write
 
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8
+      - uses: actions/checkout@v3
 
       - name: Parse issue form
-        uses: stefanbuck/github-issue-parser@2ea9b35a8c584529ed00891a8f7e41dc46d0441e
+        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@e38e6809c5420d038eed380d49ee9a6ca7c92dbf
+        uses: redhat-plumbers-in-action/advanced-issue-labeler@v2
         with:
           issue-form: ${{ steps.issue-parser.outputs.jsonString }}
           section: os

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

@@ -8,19 +8,18 @@ on:
 permissions: {}
 jobs:
   get-releases-branches:
-    if: github.repository == 'kubernetes-sigs/kubespray'
     runs-on: ubuntu-latest
     outputs:
       branches: ${{ steps.get-branches.outputs.data }}
     steps:
-    - uses: octokit/graphql-action@8ad880e4d437783ea2ab17010324de1075228110
+    - uses: octokit/graphql-action@v2.3.2
       id: get-branches
       with:
         query: |
           query get_release_branches($owner:String!, $name:String!) {
             repository(owner:$owner, name:$name) {
               refs(refPrefix: "refs/heads/",
-                   first: 1, # TODO increment once we have release branch with the new checksums format
+                   first: 0, # TODO increment once we have release branch with the new checksums format
                    query: "release-",
                    orderBy: {
                      field: ALPHABETICAL,

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

@@ -11,10 +11,10 @@ jobs:
   update-patch-versions:
     runs-on: ubuntu-latest
     steps:
-    - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8
+    - uses: actions/checkout@v4
       with:
         ref: ${{ inputs.branch }}
-    - uses: actions/setup-python@v6
+    - uses: actions/setup-python@v5
       with:
         python-version: '3.13'
         cache: 'pip'
@@ -29,12 +29,12 @@ jobs:
           ~/.cache/pre-commit
     - run: pre-commit run --all-files propagate-ansible-variables
       continue-on-error: true
-    - uses: peter-evans/create-pull-request@271a8d0340265f705b14b6d32b9829c1cb33d45e
+    - uses: peter-evans/create-pull-request@v7
       with:
         commit-message: Patch versions updates
         title: Patch versions updates - ${{ inputs.branch }}
         labels: bot
-        branch: component_hash_update/${{ inputs.branch }}
+        branch: ${{ inputs.branch }}-patch-updates
         sign-commits: true
         body: |
           /kind feature

.gitlab-ci.yml

@@ -1,9 +1,9 @@
 ---
 stages:
-  - build # build docker image used in most other jobs
-  - test # unit tests
-  - deploy-part1 # kubespray runs - common setup
-  - deploy-extended # kubespray runs - rarer or costlier (to test) setups
+  - build
+  - test
+  - deploy-part1
+  - deploy-extended
 
 variables:
   FAILFASTCI_NAMESPACE: 'kargo-ci'
@@ -24,7 +24,6 @@ variables:
   ANSIBLE_REMOTE_USER: kubespray
   ANSIBLE_PRIVATE_KEY_FILE: /tmp/id_rsa
   ANSIBLE_INVENTORY: /tmp/inventory
-  ANSIBLE_STDOUT_CALLBACK: "default"
   RESET_CHECK: "false"
   REMOVE_NODE_CHECK: "false"
   UPGRADE_TEST: "false"
@@ -32,12 +31,12 @@ variables:
   ANSIBLE_VERBOSITY: 2
   RECOVER_CONTROL_PLANE_TEST: "false"
   RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:]:kube_control_plane[1:]"
-  OPENTOFU_VERSION: v1.9.1
+  TERRAFORM_VERSION: 1.3.7
   PIPELINE_IMAGE: "$CI_REGISTRY_IMAGE/pipeline:${CI_PIPELINE_ID}-${CI_COMMIT_SHORT_SHA}"
 
 before_script:
   - ./tests/scripts/rebase.sh
-  - mkdir -p cluster-dump $ANSIBLE_INVENTORY
+  - mkdir -p /.ssh
 
 .job: &job
   tags:
@@ -49,18 +48,60 @@ before_script:
       - 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
+  interruptible: true
+  before_script:
+    - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
+    - ./tests/scripts/rebase.sh
+    - ./tests/scripts/testcases_prepare.sh
+  script:
+    - ./tests/scripts/testcases_run.sh
+  after_script:
+    - ./tests/scripts/testcases_cleanup.sh
+
+# For failfast, at least 1 job must be defined in .gitlab-ci.yml
+# Premoderated with manual actions
+ci-not-authorized:
+  stage: build
+  before_script: []
+  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
+  tags:
+    - ffci
+  needs: []
+
 include:
   - .gitlab-ci/build.yml
   - .gitlab-ci/lint.yml
   - .gitlab-ci/terraform.yml
-  - .gitlab-ci/kubevirt.yml
+  - .gitlab-ci/packet.yml
   - .gitlab-ci/vagrant.yml
   - .gitlab-ci/molecule.yml

.gitlab-ci/build.yml

@@ -1,5 +1,5 @@
 ---
-pipeline-image:
+.build-container:
   cache:
     key: $CI_COMMIT_REF_SLUG
     paths:
@@ -7,24 +7,27 @@ pipeline-image:
   tags:
     - ffci
   stage: build
-  image: moby/buildkit:rootless
+  image:
+    name: gcr.io/kaniko-project/executor:debug
+    entrypoint: ['']
   variables:
-    BUILDKITD_FLAGS: --oci-worker-no-process-sandbox
-    CACHE_IMAGE: $CI_REGISTRY_IMAGE/pipeline:cache
-  # TODO: remove the override
-  # currently rebase.sh depends on bash (not available in the kaniko image)
-  # once we have a simpler rebase (which should be easy if the target branch ref is available as variable
-  # we'll be able to rebase here as well hopefully
+    TAG: $CI_COMMIT_SHORT_SHA
+    PROJECT_DIR: $CI_PROJECT_DIR
+    DOCKERFILE: Dockerfile
+    GODEBUG: "http2client=0"
   before_script:
-    - mkdir -p ~/.docker
-    - echo "{\"auths\":{\"$CI_REGISTRY\":{\"auth\":\"$(echo -n ${CI_REGISTRY_USER}:${CI_REGISTRY_PASSWORD} | base64)\"}}}" > ~/.docker/config.json
+    - echo "{\"auths\":{\"$CI_REGISTRY\":{\"auth\":\"$(echo -n ${CI_REGISTRY_USER}:${CI_REGISTRY_PASSWORD} | base64)\"}}}" > /kaniko/.docker/config.json
   script:
-    - |
-      buildctl-daemonless.sh build \
-        --frontend dockerfile.v0 \
-        --local context=$CI_PROJECT_DIR \
-        --local dockerfile=$CI_PROJECT_DIR \
-        --opt filename=pipeline.Dockerfile \
-        --export-cache type=registry,ref=$CACHE_IMAGE \
-        --import-cache type=registry,ref=$CACHE_IMAGE \
-        --output type=image,name=$PIPELINE_IMAGE,push=true
+    - /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:
+  extends: .build-container
+  variables:
+    DOCKERFILE: pipeline.Dockerfile

.gitlab-ci/kubevirt.yml

@@ -1,153 +0,0 @@
----
-.kubevirt:
-  extends: .job-moderated
-  interruptible: true
-  script:
-    - ansible-playbook tests/cloud_playbooks/create-kubevirt.yml
-                              -e @"tests/files/${TESTCASE}.yml"
-    - ./tests/scripts/testcases_run.sh
-  variables:
-    ANSIBLE_TIMEOUT: "120"
-  tags:
-    - ffci
-  needs:
-    - pipeline-image
-
-# TODO: generate testcases matrixes from the files in tests/files/
-# this is needed to avoid the need for PR rebasing when a job was added or removed in the target branch
-# (currently, a removed job in the target branch breaks the tests, because the
-# pipeline definition is parsed by gitlab before the rebase.sh script)
-# CI template for PRs
-pr:
-  stage: deploy-part1
-  rules:
-    - if: $PR_LABELS =~ /.*ci-short.*/
-      when: manual
-      allow_failure: true
-    - if: $CI_COMMIT_BRANCH =~ /^pr-.*$/
-      when: on_success
-    - if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
-      when: on_success
-    - when: manual
-      allow_failure: true
-  extends: .kubevirt
-  parallel:
-    matrix:
-      - TESTCASE:
-          - almalinux9-crio
-          - almalinux9-kube-ovn
-          - debian11-calico-collection
-          - debian11-macvlan
-          - debian12-cilium
-          - debian13-cilium
-          - fedora39-kube-router
-          - openeuler24-calico
-          - rockylinux9-cilium
-          - ubuntu22-calico-all-in-one
-          - ubuntu22-calico-all-in-one-upgrade
-          - ubuntu24-calico-etcd-datastore
-          - ubuntu24-calico-all-in-one-hardening
-          - ubuntu24-cilium-sep
-          - ubuntu24-flannel-collection
-          - ubuntu24-kube-router-sep
-          - ubuntu24-kube-router-svc-proxy
-          - ubuntu24-ha-separate-etcd
-          - flatcar4081-calico
-          - fedora40-flannel-crio-collection-scale
-
-# The ubuntu24-calico-all-in-one jobs are meant as early stages to prevent running the full CI if something is horribly broken
-ubuntu24-calico-all-in-one:
-  stage: deploy-part1
-  extends: .kubevirt
-  variables:
-    TESTCASE: ubuntu24-calico-all-in-one
-  rules:
-    - if: $CI_COMMIT_BRANCH =~ /^pr-.*$/
-      when: on_success
-    - if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
-      when: on_success
-    - when: manual
-      allow_failure: true
-
-pr_full:
-  extends: .kubevirt
-  stage: deploy-extended
-  rules:
-    - if: $PR_LABELS =~ /.*ci-full.*/
-      when: on_success
-    - if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
-      when: on_success
-    # Else run as manual
-    - when: manual
-      allow_failure: true
-  parallel:
-    matrix:
-      - TESTCASE:
-          - almalinux9-calico-ha-ebpf
-          - almalinux9-calico-nodelocaldns-secondary
-          - debian11-custom-cni
-          - debian11-kubelet-csr-approver
-          - debian12-custom-cni-helm
-          - fedora39-calico-swap-selinux
-          - fedora39-crio
-          - ubuntu24-calico-ha-wireguard
-          - ubuntu24-flannel-ha
-          - ubuntu24-flannel-ha-once
-
-# Need an update of the container image to use schema v2
-# update: quay.io/kubespray/vm-amazon-linux-2:latest
-manual:
-  extends: pr_full
-  parallel:
-    matrix:
-      - TESTCASE:
-          - amazon-linux-2-all-in-one
-  rules:
-    - when: manual
-      allow_failure: true
-
-pr_extended:
-  extends: .kubevirt
-  stage: deploy-extended
-  rules:
-    - if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
-      when: on_success
-    - if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
-      when: on_success
-    - when: manual
-      allow_failure: true
-  parallel:
-    matrix:
-      - TESTCASE:
-          - almalinux9-calico
-          - almalinux9-calico-remove-node
-          - almalinux9-docker
-          - debian11-docker
-          - debian12-calico
-          - debian12-docker
-          - debian13-calico
-          - rockylinux9-calico
-          - ubuntu22-all-in-one-docker
-          - ubuntu24-all-in-one-docker
-          - ubuntu24-calico-all-in-one
-          - ubuntu24-calico-etcd-kubeadm
-          - ubuntu24-flannel
-
-# TODO: migrate to pr-full, fix the broken ones
-periodic:
-  allow_failure: true
-  extends: .kubevirt
-  rules:
-    - if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
-      when: on_success
-  parallel:
-    matrix:
-      - TESTCASE:
-          - debian11-calico-upgrade
-          - debian11-calico-upgrade-once
-          - debian12-cilium-svc-proxy
-          - fedora39-calico-selinux
-          - fedora40-docker-calico
-          - ubuntu24-calico-etcd-kubeadm-upgrade-ha
-          - ubuntu24-calico-ha-recover
-          - ubuntu24-calico-ha-recover-noquorum

.gitlab-ci/lint.yml

@@ -6,7 +6,6 @@ pre-commit:
   image: 'ghcr.io/pre-commit-ci/runner-image@sha256:fe01a6ec51b298412990b88627c3973b1146c7304f930f469bafa29ba60bcde9'
   variables:
     PRE_COMMIT_HOME: ${CI_PROJECT_DIR}/.cache/pre-commit
-    ANSIBLE_STDOUT_CALLBACK: default
   script:
   - pre-commit run --all-files --show-diff-on-failure
   cache:
@@ -24,3 +23,4 @@ vagrant-validate:
     VAGRANT_VERSION: 2.3.7
   script:
   - ./tests/scripts/vagrant-validate.sh
+  except: ['triggers', 'master']

.gitlab-ci/molecule.yml

@@ -1,24 +1,19 @@
 ---
 .molecule:
   tags: [ffci]
-  rules: # run on ci-short as well
-  - if: $CI_COMMIT_BRANCH =~ /^pr-.*$/
-    when: on_success
-  - if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
-    when: on_success
-  - when: manual
-    allow_failure: true
+  only: [/^pr-.*$/]
+  except: ['triggers']
   stage: deploy-part1
   image: $PIPELINE_IMAGE
   needs:
   - pipeline-image
+  # - ci-not-authorized
+  before_script:
+  - ./tests/scripts/rebase.sh
   script:
   - ./tests/scripts/molecule_run.sh
   after_script:
-  - rm -fr molecule_logs
-  - mkdir -p molecule_logs
-  - find ~/.cache/molecule/ \( -name '*.out' -o -name '*.err' \) -type f | xargs tar -uf molecule_logs/molecule.tar
-  - gzip molecule_logs/molecule.tar
+  - ./tests/scripts/molecule_logs.sh
   artifacts:
     when: always
     paths:
@@ -34,22 +29,28 @@ molecule:
       - container-engine/cri-dockerd
       - container-engine/containerd
       - container-engine/cri-o
-      - container-engine/gvisor
-      - container-engine/youki
       - adduser
       - bastion-ssh-config
-      - bootstrap_os
+      - bootstrap-os
 
+# CI template for periodic CI jobs
+# Enabled when PERIODIC_CI_ENABLED var is set
 molecule_full:
+  only:
+    variables:
+    - $PERIODIC_CI_ENABLED
   allow_failure: true
-  rules:
-  - if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
-    when: on_success
-  - when: manual
-    allow_failure: true
   extends: molecule
   parallel:
     matrix:
     - ROLE:
+      - container-engine/cri-dockerd
+      - container-engine/containerd
+      - container-engine/cri-o
+      - adduser
+      - bastion-ssh-config
+      - bootstrap-os
       # FIXME : tests below are perma-failing
       - container-engine/kata-containers
+      - container-engine/gvisor
+      - container-engine/youki

.gitlab-ci/packet.yml

@@ -0,0 +1,257 @@
+---
+.packet:
+  extends: .testcases
+  variables:
+    ANSIBLE_TIMEOUT: "120"
+    CI_PLATFORM: packet
+    SSH_USER: kubespray
+  tags:
+    - ffci
+  needs:
+    - pipeline-image
+    - ci-not-authorized
+
+# CI template for PRs
+.packet_pr:
+  stage: deploy-part1
+  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:
+  only:
+    variables:
+      - $PERIODIC_CI_ENABLED
+  allow_failure: true
+  extends: .packet
+
+# 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
+  variables:
+    RESET_CHECK: "true"
+
+# ### PR JOBS PART2
+
+packet_ubuntu20-crio:
+  extends: .packet_pr_manual
+
+packet_ubuntu22-calico-all-in-one:
+  extends: .packet_pr
+
+packet_ubuntu22-calico-all-in-one-upgrade:
+  extends: .packet_pr
+  variables:
+    UPGRADE_TEST: graceful
+
+packet_ubuntu24-calico-etcd-datastore:
+  extends: .packet_pr
+
+packet_almalinux9-crio:
+  extends: .packet_pr
+
+packet_almalinux9-kube-ovn:
+  extends: .packet_pr
+
+packet_debian11-calico-collection:
+  extends: .packet_pr
+
+packet_debian11-macvlan:
+  extends: .packet_pr
+
+packet_debian12-cilium:
+  extends: .packet_pr
+
+packet_almalinux8-calico:
+  extends: .packet_pr
+
+packet_rockylinux8-calico:
+  extends: .packet_pr
+
+packet_rockylinux9-cilium:
+  extends: .packet_pr
+  variables:
+    RESET_CHECK: "true"
+
+# Need an update of the container image to use schema v2
+# update: quay.io/kubespray/vm-amazon-linux-2:latest
+packet_amazon-linux-2-all-in-one:
+  extends: .packet_pr_manual
+  rules:
+    - when: manual
+      allow_failure: true
+
+packet_opensuse15-6-calico:
+  extends: .packet_pr
+
+packet_ubuntu20-cilium-sep:
+  extends: .packet_pr
+
+packet_openeuler24-calico:
+  extends: .packet_pr
+
+packet_ubuntu20-calico-all-in-one-hardening:
+  extends: .packet_pr
+
+## Extended
+packet_debian11-docker:
+  extends: .packet_pr_extended
+
+packet_debian12-docker:
+  extends: .packet_pr_extended
+
+packet_debian12-calico:
+  extends: .packet_pr_extended
+
+packet_almalinux9-calico-remove-node:
+  extends: .packet_pr_extended
+  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
+
+packet_ubuntu24-all-in-one-docker:
+  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
+  extends: .packet_periodic
+  variables:
+    UPGRADE_TEST: graceful
+
+packet_ubuntu20-calico-ha-recover:
+  stage: deploy-extended
+  extends: .packet_periodic
+  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
+  extends: .packet_periodic
+  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/terraform.yml

@@ -3,41 +3,39 @@
 .terraform_install:
   extends: .job
   needs:
+    - ci-not-authorized
     - pipeline-image
-  variables:
-    TF_VAR_public_key_path: "${ANSIBLE_PRIVATE_KEY_FILE}.pub"
-    TF_VAR_ssh_private_key_path: $ANSIBLE_PRIVATE_KEY_FILE
-    CLUSTER: $CI_COMMIT_REF_NAME
-    TERRAFORM_STATE_ROOT: $CI_PROJECT_DIR
   stage: deploy-part1
   before_script:
+    - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
     - ./tests/scripts/rebase.sh
-    - mkdir -p cluster-dump $ANSIBLE_INVENTORY
-    - ./tests/scripts/opentofu_install.sh
+    - ./tests/scripts/testcases_prepare.sh
+    - ./tests/scripts/terraform_install.sh
+    # Set Ansible config
+    - cp ansible.cfg ~/.ansible.cfg
+    # Prepare inventory
     - cp contrib/terraform/$PROVIDER/sample-inventory/cluster.tfvars .
-    - ln -rs -t $ANSIBLE_INVENTORY contrib/terraform/$PROVIDER/hosts
-    - tofu -chdir="contrib/terraform/$PROVIDER" init
+    - ln -s contrib/terraform/$PROVIDER/hosts
+    - terraform -chdir="contrib/terraform/$PROVIDER" init
+    # Copy SSH keypair
+    - mkdir -p ~/.ssh
+    - echo "$PACKET_PRIVATE_KEY" | base64 -d > ~/.ssh/id_rsa
+    - chmod 400 ~/.ssh/id_rsa
+    - echo "$PACKET_PUBLIC_KEY" | base64 -d > ~/.ssh/id_rsa.pub
+    - mkdir -p contrib/terraform/$PROVIDER/group_vars
+    # Random subnet to avoid routing conflicts
+    - export TF_VAR_subnet_cidr="10.$(( $RANDOM % 256 )).$(( $RANDOM % 256 )).0/24"
 
-terraform_validate:
+.terraform_validate:
   extends: .terraform_install
   tags: [ffci]
   only: ['master', /^pr-.*$/]
   script:
-    - tofu -chdir="contrib/terraform/$PROVIDER" validate
-    - tofu -chdir="contrib/terraform/$PROVIDER" fmt -check -diff
+    - terraform -chdir="contrib/terraform/$PROVIDER" validate
+    - terraform -chdir="contrib/terraform/$PROVIDER" fmt -check -diff
   stage: test
   needs:
     - pipeline-image
-  parallel:
-    matrix:
-      - PROVIDER:
-          - openstack
-          - aws
-          - exoscale
-          - hetzner
-          - vsphere
-          - upcloud
-          - nifcloud
 
 .terraform_apply:
   extends: .terraform_install
@@ -45,24 +43,99 @@ terraform_validate:
   stage: deploy-extended
   when: manual
   only: [/^pr-.*$/]
+  artifacts:
+    when: always
+    paths:
+      - cluster-dump/
   variables:
     ANSIBLE_INVENTORY_UNPARSED_FAILED: "true"
-    ANSIBLE_REMOTE_USER: ubuntu # the openstack terraform module does not handle custom user correctly
-    ANSIBLE_SSH_RETRIES: 15
-    TF_VAR_ssh_user: $ANSIBLE_REMOTE_USER
+    ANSIBLE_INVENTORY: hosts
+    CI_PLATFORM: tf
+    TF_VAR_ssh_user: $SSH_USER
     TF_VAR_cluster_name: $CI_JOB_ID
   script:
-    # Set Ansible config
-    - cp ansible.cfg ~/.ansible.cfg
-    - ssh-keygen -N '' -f $ANSIBLE_PRIVATE_KEY_FILE -t rsa
-    - mkdir -p contrib/terraform/$PROVIDER/group_vars
-    # Random subnet to avoid routing conflicts
-    - export TF_VAR_subnet_cidr="10.$(( $RANDOM % 256 )).$(( $RANDOM % 256 )).0/24"
-    - tofu -chdir="contrib/terraform/$PROVIDER" apply -auto-approve -parallelism=1
     - tests/scripts/testcases_run.sh
   after_script:
     # Cleanup regardless of exit code
-    - tofu -chdir="contrib/terraform/$PROVIDER" destroy -auto-approve
+    - ./tests/scripts/testcases_cleanup.sh
+
+tf-validate-openstack:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: openstack
+    CLUSTER: $CI_COMMIT_REF_NAME
+
+tf-validate-equinix:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: equinix
+    CLUSTER: $CI_COMMIT_REF_NAME
+
+tf-validate-aws:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: aws
+    CLUSTER: $CI_COMMIT_REF_NAME
+
+tf-validate-exoscale:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: exoscale
+
+tf-validate-hetzner:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: hetzner
+
+tf-validate-vsphere:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: vsphere
+    CLUSTER: $CI_COMMIT_REF_NAME
+
+tf-validate-upcloud:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: upcloud
+    CLUSTER: $CI_COMMIT_REF_NAME
+
+tf-validate-nifcloud:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: nifcloud
+
+# tf-packet-ubuntu20-default:
+#   extends: .terraform_apply
+#   variables:
+#     TF_VERSION: $TERRAFORM_VERSION
+#     PROVIDER: packet
+#     CLUSTER: $CI_COMMIT_REF_NAME
+#     TF_VAR_number_of_k8s_masters: "1"
+#     TF_VAR_number_of_k8s_nodes: "1"
+#     TF_VAR_plan_k8s_masters: t1.small.x86
+#     TF_VAR_plan_k8s_nodes: t1.small.x86
+#     TF_VAR_metro: am
+#     TF_VAR_public_key_path: ""
+#     TF_VAR_operating_system: ubuntu_20_04
+
+.ovh_variables: &ovh_variables
+  OS_AUTH_URL: https://auth.cloud.ovh.net/v3
+  OS_PROJECT_ID: 8d3cd5d737d74227ace462dee0b903fe
+  OS_PROJECT_NAME: "9361447987648822"
+  OS_USER_DOMAIN_NAME: Default
+  OS_PROJECT_DOMAIN_ID: default
+  OS_USERNAME: 8XuhBMfkKVrk
+  OS_REGION_NAME: UK1
+  OS_INTERFACE: public
+  OS_IDENTITY_API_VERSION: "3"
 
 # Elastx is generously donating resources for Kubespray on Openstack CI
 # Contacts: @gix @bl0m1
@@ -96,8 +169,11 @@ tf-elastx_ubuntu20-calico:
   allow_failure: true
   variables:
     <<: *elastx_variables
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: openstack
+    CLUSTER: $CI_COMMIT_REF_NAME
     ANSIBLE_TIMEOUT: "60"
+    SSH_USER: ubuntu
     TF_VAR_number_of_k8s_masters: "1"
     TF_VAR_number_of_k8s_masters_no_floating_ip: "0"
     TF_VAR_number_of_k8s_masters_no_floating_ip_no_etcd: "0"
@@ -118,3 +194,46 @@ tf-elastx_ubuntu20-calico:
     TF_VAR_flavor_k8s_node: 3f73fc93-ec61-4808-88df-2580d94c1a9b      # v1-standard-2
     TF_VAR_image: ubuntu-20.04-server-latest
     TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'
+
+# OVH voucher expired, commenting job until things are sorted  out
+
+# tf-ovh_cleanup:
+#  stage: unit-tests
+#  tags: [light]
+#  image: python
+#  environment: ovh
+#  variables:
+#    <<: *ovh_variables
+#  before_script:
+#    - pip install -r scripts/openstack-cleanup/requirements.txt
+#  script:
+#    - ./scripts/openstack-cleanup/main.py
+
+# tf-ovh_ubuntu20-calico:
+#  extends: .terraform_apply
+#  when: on_success
+#  environment: ovh
+#  variables:
+#    <<: *ovh_variables
+#    TF_VERSION: $TERRAFORM_VERSION
+#    PROVIDER: openstack
+#    CLUSTER: $CI_COMMIT_REF_NAME
+#    ANSIBLE_TIMEOUT: "60"
+#    SSH_USER: ubuntu
+#    TF_VAR_number_of_k8s_masters: "0"
+#    TF_VAR_number_of_k8s_masters_no_floating_ip: "1"
+#    TF_VAR_number_of_k8s_masters_no_floating_ip_no_etcd: "0"
+#    TF_VAR_number_of_etcd: "0"
+#    TF_VAR_number_of_k8s_nodes: "0"
+#    TF_VAR_number_of_k8s_nodes_no_floating_ip: "1"
+#    TF_VAR_number_of_gfs_nodes_no_floating_ip: "0"
+#    TF_VAR_number_of_bastions: "0"
+#    TF_VAR_number_of_k8s_masters_no_etcd: "0"
+#    TF_VAR_use_neutron: "0"
+#    TF_VAR_floatingip_pool: "Ext-Net"
+#    TF_VAR_external_net: "6011fbc9-4cbf-46a4-8452-6890a340b60b"
+#    TF_VAR_network_name: "Ext-Net"
+#    TF_VAR_flavor_k8s_master: "defa64c3-bd46-43b4-858a-d93bbae0a229"    # s1-8
+#    TF_VAR_flavor_k8s_node: "defa64c3-bd46-43b4-858a-d93bbae0a229"      # s1-8
+#    TF_VAR_image: "Ubuntu 20.04"
+#    TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'

.gitlab-ci/vagrant.yml

@@ -1,16 +1,20 @@
 ---
-vagrant:
-  extends: .job-moderated
+.vagrant:
+  extends: .testcases
+  needs:
+    - ci-not-authorized
   variables:
     CI_PLATFORM: "vagrant"
     SSH_USER: "vagrant"
     VAGRANT_DEFAULT_PROVIDER: "libvirt"
-    KUBESPRAY_VAGRANT_CONFIG: tests/files/${TESTCASE}.rb
+    KUBESPRAY_VAGRANT_CONFIG: tests/files/${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
   services: []
   before_script:
@@ -24,26 +28,54 @@ vagrant:
     - pip install --no-compile --no-cache-dir -r $CI_PROJECT_DIR/tests/requirements.txt
     - ./tests/scripts/vagrant_clean.sh
   script:
-    - vagrant up
     - ./tests/scripts/testcases_run.sh
-  after_script:
-    - vagrant destroy -f
   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:
   stage: deploy-extended
+  extends: .vagrant
   rules:
     - if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
       when: on_success
-    - if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
+  allow_failure: false
+
+vagrant_ubuntu24-calico-ipv6only-stack:
+  stage: deploy-extended
+  extends: .vagrant
+  rules:
+    - if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
       when: on_success
-    - when: manual
-      allow_failure: true
-  parallel:
-    matrix:
-      - TESTCASE:
-          - ubuntu24-calico-dual-stack
-          - ubuntu24-calico-ipv6only-stack
+  allow_failure: false
+
+vagrant_ubuntu20-flannel:
+  stage: deploy-part1
+  extends: .vagrant
+  when: on_success
+  allow_failure: false
+
+vagrant_ubuntu20-flannel-collection:
+  stage: deploy-extended
+  extends: .vagrant
+  when: manual
+
+vagrant_ubuntu20-kube-router-sep:
+  stage: deploy-extended
+  extends: .vagrant
+  when: manual
+
+# Service proxy test fails connectivity testing
+vagrant_ubuntu20-kube-router-svc-proxy:
+  stage: deploy-extended
+  extends: .vagrant
+  when: manual
+
+vagrant_fedora39-kube-router:
+  stage: deploy-extended
+  extends: .vagrant
+  when: manual
+# FIXME: this test if broken (perma-failing)

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 ---
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v6.0.0
+    rev: v5.0.0
     hooks:
       - id: check-added-large-files
       - id: check-case-conflict
@@ -15,13 +15,13 @@ repos:
       - id: trailing-whitespace
 
   - repo: https://github.com/adrienverge/yamllint.git
-    rev: v1.37.1
+    rev: v1.35.1
     hooks:
       - id: yamllint
         args: [--strict]
 
   - repo: https://github.com/shellcheck-py/shellcheck-py
-    rev: v0.11.0.1
+    rev: v0.10.0.1
     hooks:
       - id: shellcheck
         args: ["--severity=error"]
@@ -29,7 +29,7 @@ repos:
         files: "\\.sh$"
 
   - repo: https://github.com/ansible/ansible-lint
-    rev: v25.11.0
+    rev: v25.1.1
     hooks:
       - id: ansible-lint
         additional_dependencies:
@@ -38,7 +38,7 @@ repos:
           - distlib
 
   - repo: https://github.com/golangci/misspell
-    rev: v0.7.0
+    rev: v0.6.0
     hooks:
       - id: misspell
         exclude: "OWNERS_ALIASES$"

CONTRIBUTING.md

@@ -40,7 +40,7 @@ Vagrant with VirtualBox or libvirt driver helps you to quickly spin test cluster
 2. The [repo owners](OWNERS) will respond to your issue promptly.
 3. Fork the desired repo, develop and test your code changes.
 4. Install [pre-commit](https://pre-commit.com) and install it in your development repo.
-5. Address any pre-commit validation failures.
+5. Addess any pre-commit validation failures.
 6. Sign the CNCF CLA (<https://git.k8s.io/community/CLA.md#the-contributor-license-agreement>)
 7. Submit a pull request.
 8. Work with the reviewers on their suggestions.

Dockerfile

@@ -1,6 +1,6 @@
 # syntax=docker/dockerfile:1
 
-# Use immutable image tags rather than mutable tags (like ubuntu:22.04)
+# Use imutable image tags rather than mutable tags (like ubuntu:22.04)
 FROM ubuntu:22.04@sha256:149d67e29f765f4db62aa52161009e99e389544e25a8f43c8c89d4a445a7ca37
 
 # Some tools like yamllint need this
@@ -35,8 +35,8 @@ RUN --mount=type=bind,source=requirements.txt,target=requirements.txt \
 SHELL ["/bin/bash", "-o", "pipefail", "-c"]
 
 RUN OS_ARCHITECTURE=$(dpkg --print-architecture) \
-    && curl -L "https://dl.k8s.io/release/v1.33.7/bin/linux/${OS_ARCHITECTURE}/kubectl" -o /usr/local/bin/kubectl \
-    && echo "$(curl -L "https://dl.k8s.io/release/v1.33.7/bin/linux/${OS_ARCHITECTURE}/kubectl.sha256")" /usr/local/bin/kubectl | sha256sum --check \
+    && curl -L "https://dl.k8s.io/release/v1.32.3/bin/linux/${OS_ARCHITECTURE}/kubectl" -o /usr/local/bin/kubectl \
+    && echo "$(curl -L "https://dl.k8s.io/release/v1.32.3/bin/linux/${OS_ARCHITECTURE}/kubectl.sha256")" /usr/local/bin/kubectl | sha256sum --check \
     && chmod a+x /usr/local/bin/kubectl
 
 COPY *.yml ./

OWNERS_ALIASES

@@ -1,13 +1,17 @@
 aliases:
   kubespray-approvers:
-    - ant31
+    - cristicalin
+    - floryut
+    - liupeng0518
     - mzaian
-    - tico88612
-    - vannten
+    - oomichi
     - yankay
+    - ant31
+    - vannten
   kubespray-reviewers:
     - cyclinder
     - erikjiang
+    - mrfreezeex
     - mzaian
     - tico88612
     - vannten
@@ -15,12 +19,8 @@ aliases:
   kubespray-emeritus_approvers:
     - atoms
     - chadswen
-    - cristicalin
-    - floryut
-    - liupeng0518
     - luckysb
     - mattymo
     - miouge1
-    - oomichi
     - riverzhang
     - woopstar

README.md

@@ -22,7 +22,7 @@ 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:v2.29.0 bash
+  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
 ```
@@ -87,8 +87,8 @@ vagrant up
 ## Supported Linux Distributions
 
 - **Flatcar Container Linux by Kinvolk**
-- **Debian** Bookworm, Bullseye, Trixie
-- **Ubuntu** 22.04, 24.04
+- **Debian** Bookworm, Bullseye
+- **Ubuntu** 20.04, 22.04, 24.04
 - **CentOS/RHEL** [8, 9](docs/operating_systems/rhel.md#rhel-8)
 - **Fedora** 39, 40
 - **Fedora CoreOS** (see [fcos Note](docs/operating_systems/fcos.md))
@@ -111,34 +111,37 @@ Note:
 <!-- BEGIN ANSIBLE MANAGED BLOCK -->
 
 - Core
-  - [kubernetes](https://github.com/kubernetes/kubernetes) 1.33.7
-  - [etcd](https://github.com/etcd-io/etcd) 3.5.25
-  - [docker](https://www.docker.com/) 28.3
-  - [containerd](https://containerd.io/) 2.1.5
-  - [cri-o](http://cri-o.io/) 1.33.7 (experimental: see [CRI-O Note](docs/CRI/cri-o.md). Only on fedora, ubuntu and centos based OS)
+  - [kubernetes](https://github.com/kubernetes/kubernetes) 1.32.3
+  - [etcd](https://github.com/etcd-io/etcd) 3.5.16
+  - [docker](https://www.docker.com/) 28.0
+  - [containerd](https://containerd.io/) 2.0.4
+  - [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)
 - Network Plugin
-  - [cni-plugins](https://github.com/containernetworking/plugins) 1.8.0
-  - [calico](https://github.com/projectcalico/calico) 3.30.5
-  - [cilium](https://github.com/cilium/cilium) 1.18.4
-  - [flannel](https://github.com/flannel-io/flannel) 0.27.3
+  - [cni-plugins](https://github.com/containernetworking/plugins) 1.4.1
+  - [calico](https://github.com/projectcalico/calico) 3.29.3
+  - [cilium](https://github.com/cilium/cilium) 1.15.9
+  - [flannel](https://github.com/flannel-io/flannel) 0.22.0
   - [kube-ovn](https://github.com/alauda/kube-ovn) 1.12.21
   - [kube-router](https://github.com/cloudnativelabs/kube-router) 2.1.1
-  - [multus](https://github.com/k8snetworkplumbingwg/multus-cni) 4.2.2
+  - [multus](https://github.com/k8snetworkplumbingwg/multus-cni) 4.1.0
+  - [weave](https://github.com/rajch/weave) 2.8.7
   - [kube-vip](https://github.com/kube-vip/kube-vip) 0.8.0
 - Application
   - [cert-manager](https://github.com/jetstack/cert-manager) 1.15.3
-  - [coredns](https://github.com/coredns/coredns) 1.12.0
-  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) 1.13.3
+  - [coredns](https://github.com/coredns/coredns) 1.11.3
+  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) 1.12.1
   - [argocd](https://argoproj.github.io/) 2.14.5
-  - [helm](https://helm.sh/) 3.18.4
+  - [helm](https://helm.sh/) 3.16.4
   - [metallb](https://metallb.universe.tf/) 0.13.9
   - [registry](https://github.com/distribution/distribution) 2.8.1
 - Storage Plugin
+  - [cephfs-provisioner](https://github.com/kubernetes-incubator/external-storage) 2.1.0-k8s1.11
+  - [rbd-provisioner](https://github.com/kubernetes-incubator/external-storage) 2.1.1-k8s1.11
   - [aws-ebs-csi-plugin](https://github.com/kubernetes-sigs/aws-ebs-csi-driver) 0.5.0
   - [azure-csi-plugin](https://github.com/kubernetes-sigs/azuredisk-csi-driver) 1.10.0
   - [cinder-csi-plugin](https://github.com/kubernetes/cloud-provider-openstack/blob/master/docs/cinder-csi-plugin/using-cinder-csi-plugin.md) 1.30.0
   - [gcp-pd-csi-plugin](https://github.com/kubernetes-sigs/gcp-compute-persistent-disk-csi-driver) 1.9.2
-  - [local-path-provisioner](https://github.com/rancher/local-path-provisioner) 0.0.32
+  - [local-path-provisioner](https://github.com/rancher/local-path-provisioner) 0.0.24
   - [local-volume-provisioner](https://github.com/kubernetes-sigs/sig-storage-local-static-provisioner) 2.5.0
   - [node-feature-discovery](https://github.com/kubernetes-sigs/node-feature-discovery) 0.16.4
 
@@ -182,6 +185,9 @@ 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.
+    (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-router](docs/CNI/kube-router.md): Kube-router is a L3 CNI for Kubernetes networking aiming to provide operational

Vagrantfile

@@ -4,8 +4,6 @@
 # For help on using kubespray with vagrant, check out docs/developers/vagrant.md
 
 require 'fileutils'
-require 'ipaddr'
-require 'socket'
 
 Vagrant.require_version ">= 2.0.0"
 
@@ -101,33 +99,6 @@ $extra_vars ||= {}
 
 host_vars = {}
 
-def collect_networks(subnet, subnet_ipv6)
-  Socket.getifaddrs.filter_map do |iface|
-    next unless iface&.netmask&.ip_address && iface.addr
-
-    is_ipv6 = iface.addr.ipv6?
-    ip      = IPAddr.new(iface.addr.ip_address.split('%').first)
-    ip_test = is_ipv6 ? IPAddr.new("#{subnet_ipv6}::0") : IPAddr.new("#{subnet}.0")
-
-    prefix  = IPAddr.new(iface.netmask.ip_address).to_i.to_s(2).count('1')
-    network = ip.mask(prefix)
-
-    [IPAddr.new("#{network}/#{prefix}"), ip_test]
-  end
-end
-
-def subnet_in_use?(network_ips)
-  network_ips.any? { |net, test_ip| net.include?(test_ip) && test_ip != net }
-end
-
-network_ips = collect_networks($subnet, $subnet_ipv6)
-
-if subnet_in_use?(network_ips)
-  puts "Invalid subnet provided, subnet is already in use: #{$subnet}.0"
-  puts "Subnets in use: #{network_ips.inspect}"
-  exit 1
-end
-
 # throw error if os is not supported
 if ! SUPPORTED_OS.key?($os)
   puts "Unsupported OS: #{$os}"

ansible.cfg

@@ -15,7 +15,7 @@ timeout = 300
 stdout_callback = default
 display_skipped_hosts = no
 library = ./library
-callbacks_enabled = profile_tasks
+callbacks_enabled = profile_tasks,ara_default
 roles_path = roles:$VIRTUAL_ENV/usr/local/share/kubespray/roles:$VIRTUAL_ENV/usr/local/share/ansible/roles:/usr/share/kubespray/roles
 deprecation_warnings=False
 inventory_ignore_extensions = ~, .orig, .bak, .ini, .cfg, .retry, .pyc, .pyo, .creds, .gpg

contrib/kvm-setup/README.md

@@ -0,0 +1,11 @@
+# Kubespray on KVM Virtual Machines hypervisor preparation
+
+A simple playbook to ensure your system has the right settings to enable Kubespray
+deployment on VMs.
+
+This playbook does not create Virtual Machines, nor does it run Kubespray itself.
+
+## User creation
+
+If you want to create a user for running Kubespray deployment, you should specify
+both `k8s_deployment_user` and `k8s_deployment_user_pkey_path`.

contrib/kvm-setup/group_vars/all

@@ -0,0 +1,2 @@
+#k8s_deployment_user: kubespray
+#k8s_deployment_user_pkey_path: /tmp/ssh_rsa

contrib/kvm-setup/kvm-setup.yml

@@ -0,0 +1,9 @@
+---
+- name: Prepare Hypervisor to later install kubespray VMs
+  hosts: localhost
+  gather_facts: false
+  become: true
+  vars:
+    bootstrap_os: none
+  roles:
+    - { role: kvm-setup }

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

@@ -0,0 +1,30 @@
+---
+
+- name: Install required packages
+  package:
+    name: "{{ item }}"
+    state: present
+  with_items:
+    - bind-utils
+    - ntp
+  when: ansible_os_family == "RedHat"
+
+- name: Install required packages
+  apt:
+    upgrade: true
+    update_cache: true
+    cache_valid_time: 3600
+    name: "{{ item }}"
+    state: present
+    install_recommends: false
+  with_items:
+    - dnsutils
+    - ntp
+  when: ansible_os_family == "Debian"
+
+- name: Create deployment user if required
+  include_tasks: user.yml
+  when: k8s_deployment_user is defined
+
+- name: Set proper sysctl values
+  import_tasks: sysctl.yml

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

@@ -0,0 +1,46 @@
+---
+- name: Load br_netfilter module
+  community.general.modprobe:
+    name: br_netfilter
+    state: present
+  register: br_netfilter
+
+- name: Add br_netfilter into /etc/modules
+  lineinfile:
+    dest: /etc/modules
+    state: present
+    line: 'br_netfilter'
+  when: br_netfilter is defined and ansible_os_family == 'Debian'
+
+- name: Add br_netfilter into /etc/modules-load.d/kubespray.conf
+  copy:
+    dest: /etc/modules-load.d/kubespray.conf
+    content: |-
+      ### This file is managed by Ansible
+      br-netfilter
+    owner: root
+    group: root
+    mode: "0644"
+  when: br_netfilter is defined
+
+
+- name: Enable net.ipv4.ip_forward in sysctl
+  ansible.posix.sysctl:
+    name: net.ipv4.ip_forward
+    value: 1
+    sysctl_file: "{{ sysctl_file_path }}"
+    state: present
+    reload: true
+
+- name: Set bridge-nf-call-{arptables,iptables} to 0
+  ansible.posix.sysctl:
+    name: "{{ item }}"
+    state: present
+    value: 0
+    sysctl_file: "{{ sysctl_file_path }}"
+    reload: true
+  with_items:
+    - net.bridge.bridge-nf-call-arptables
+    - net.bridge.bridge-nf-call-ip6tables
+    - net.bridge.bridge-nf-call-iptables
+  when: br_netfilter is defined

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

@@ -0,0 +1,47 @@
+---
+- name: Create user {{ k8s_deployment_user }}
+  user:
+    name: "{{ k8s_deployment_user }}"
+    groups: adm
+    shell: /bin/bash
+
+- name: Ensure that .ssh exists
+  file:
+    path: "/home/{{ k8s_deployment_user }}/.ssh"
+    state: directory
+    owner: "{{ k8s_deployment_user }}"
+    group: "{{ k8s_deployment_user }}"
+    mode: "0700"
+
+- name: Configure sudo for deployment user
+  copy:
+    content: |
+      %{{ k8s_deployment_user }} ALL=(ALL) NOPASSWD: ALL
+    dest: "/etc/sudoers.d/55-k8s-deployment"
+    owner: root
+    group: root
+    mode: "0644"
+
+- name: Write private SSH key
+  copy:
+    src: "{{ k8s_deployment_user_pkey_path }}"
+    dest: "/home/{{ k8s_deployment_user }}/.ssh/id_rsa"
+    mode: "0400"
+    owner: "{{ k8s_deployment_user }}"
+    group: "{{ k8s_deployment_user }}"
+  when: k8s_deployment_user_pkey_path is defined
+
+- name: Write public SSH key
+  shell: "ssh-keygen -y -f /home/{{ k8s_deployment_user }}/.ssh/id_rsa \
+            > /home/{{ k8s_deployment_user }}/.ssh/authorized_keys"
+  args:
+    creates: "/home/{{ k8s_deployment_user }}/.ssh/authorized_keys"
+  when: k8s_deployment_user_pkey_path is defined
+
+- name: Fix ssh-pub-key permissions
+  file:
+    path: "/home/{{ k8s_deployment_user }}/.ssh/authorized_keys"
+    mode: "0600"
+    owner: "{{ k8s_deployment_user }}"
+    group: "{{ k8s_deployment_user }}"
+  when: k8s_deployment_user_pkey_path is defined

contrib/misc/clusteradmin-rbac.yml

@@ -0,0 +1,15 @@
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: kubernetes-dashboard
+  labels:
+    k8s-app: kubernetes-dashboard
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: cluster-admin
+subjects:
+- kind: ServiceAccount
+  name: kubernetes-dashboard
+  namespace: kube-system

contrib/mitogen/mitogen.yml

@@ -0,0 +1,51 @@
+---
+- name: Check ansible version
+  import_playbook: kubernetes_sigs.kubespray.ansible_version
+
+- name: Install mitogen
+  hosts: localhost
+  strategy: linear
+  vars:
+    mitogen_version: 0.3.2
+    mitogen_url: https://github.com/mitogen-hq/mitogen/archive/refs/tags/v{{ mitogen_version }}.tar.gz
+    ansible_connection: local
+  tasks:
+    - name: Create mitogen plugin dir
+      file:
+        path: "{{ item }}"
+        state: directory
+        mode: "0755"
+      become: false
+      loop:
+        - "{{ playbook_dir }}/plugins/mitogen"
+        - "{{ playbook_dir }}/dist"
+
+    - name: Download mitogen release
+      get_url:
+        url: "{{ mitogen_url }}"
+        dest: "{{ playbook_dir }}/dist/mitogen_{{ mitogen_version }}.tar.gz"
+        validate_certs: true
+        mode: "0644"
+
+    - name: Extract archive
+      unarchive:
+        src: "{{ playbook_dir }}/dist/mitogen_{{ mitogen_version }}.tar.gz"
+        dest: "{{ playbook_dir }}/dist/"
+
+    - name: Copy plugin
+      ansible.posix.synchronize:
+        src: "{{ playbook_dir }}/dist/mitogen-{{ mitogen_version }}/"
+        dest: "{{ playbook_dir }}/plugins/mitogen"
+
+    - name: Add strategy to ansible.cfg
+      community.general.ini_file:
+        path: ansible.cfg
+        mode: "0644"
+        section: "{{ item.section | d('defaults') }}"
+        option: "{{ item.option }}"
+        value: "{{ item.value }}"
+      with_items:
+        - option: strategy
+          value: mitogen_linear
+        - option: strategy_plugins
+          value: plugins/mitogen/ansible_mitogen/plugins/strategy

contrib/offline/README.md

@@ -31,7 +31,7 @@ manage-offline-container-images.sh   register
 
 ## generate_list.sh
 
-This script generates the list of downloaded files and the list of container images by `roles/kubespray_defaults/defaults/main/download.yml` file.
+This script generates the list of downloaded files and the list of container images by `roles/kubespray-defaults/defaults/main/download.yml` file.
 
 Run this script will execute `generate_list.yml` playbook in kubespray root directory and generate four files,
 all downloaded files url in files.list, all container images in images.list, jinja2 templates in *.template.

contrib/offline/generate_list.sh

@@ -5,7 +5,7 @@ CURRENT_DIR=$(cd $(dirname $0); pwd)
 TEMP_DIR="${CURRENT_DIR}/temp"
 REPO_ROOT_DIR="${CURRENT_DIR%/contrib/offline}"
 
-: ${DOWNLOAD_YML:="roles/kubespray_defaults/defaults/main/download.yml"}
+: ${DOWNLOAD_YML:="roles/kubespray-defaults/defaults/main/download.yml"}
 
 mkdir -p ${TEMP_DIR}
 
@@ -19,7 +19,7 @@ sed -n '/^downloads:/,/download_defaults:/p' ${REPO_ROOT_DIR}/${DOWNLOAD_YML} \
     | sed 'N;s#\n# #g' | tr ' ' ':' | sed 's/\"//g' > ${TEMP_DIR}/images.list.template
 
 # add kube-* images to images list template
-# Those container images are downloaded by kubeadm, then roles/kubespray_defaults/defaults/main/download.yml
+# Those container images are downloaded by kubeadm, then roles/kubespray-defaults/defaults/main/download.yml
 # doesn't contain those images. That is reason why here needs to put those images into the
 # list separately.
 KUBE_IMAGES="kube-apiserver kube-controller-manager kube-scheduler kube-proxy"

contrib/offline/generate_list.yml

@@ -5,7 +5,7 @@
 
   roles:
     # Just load default variables from roles.
-    - role: kubespray_defaults
+    - role: kubespray-defaults
       when: false
     - role: download
       when: false

contrib/offline/manage-offline-container-images.sh

@@ -36,7 +36,7 @@ function create_container_image_tar() {
 	mkdir  ${IMAGE_DIR}
 	cd     ${IMAGE_DIR}
 
-	sudo --preserve-env=http_proxy,https_proxy,no_proxy ${runtime} pull registry:latest
+	sudo ${runtime} pull registry:latest
 	sudo ${runtime} save -o registry-latest.tar registry:latest
 
 	while read -r image
@@ -45,7 +45,7 @@ function create_container_image_tar() {
 		set +e
 		for step in $(seq 1 ${RETRY_COUNT})
 		do
-			sudo --preserve-env=http_proxy,https_proxy,no_proxy ${runtime} pull ${image}
+			sudo ${runtime} pull ${image}
 			if [ $? -eq 0 ]; then
 				break
 			fi
@@ -127,7 +127,7 @@ function register_container_images() {
 
 	tar -zxvf ${IMAGE_TAR_FILE}
 
-	if ${create_registry}; then
+	if [ "${create_registry}" ]; then
 		sudo ${runtime} load -i ${IMAGE_DIR}/registry-latest.tar
 		set +e
 
@@ -148,7 +148,7 @@ function register_container_images() {
 		if [ "${org_image}" == "ID:" ]; then
 		  org_image=$(echo "${load_image}"  | awk '{print $4}')
 		fi
-		image_id=$(sudo ${runtime} image inspect --format "{{.Id}}" "${org_image}")
+		image_id=$(sudo ${runtime} image inspect ${org_image} | grep "\"Id\":" | awk -F: '{print $3}'| sed s/'\",'//)
 		if [ -z "${file_name}" ]; then
 			echo "Failed to get file_name for line ${line}"
 			exit 1

contrib/offline/manage-offline-files.sh

@@ -41,7 +41,7 @@ fi
 
 sudo "${runtime}" container inspect nginx >/dev/null 2>&1
 if [ $? -ne 0 ]; then
-    sudo --preserve-env=http_proxy,https_proxy,no_proxy "${runtime}" run \
+    sudo "${runtime}" run \
         --restart=always -d -p ${NGINX_PORT}:80 \
         --volume "${OFFLINE_FILES_DIR}":/usr/share/nginx/html/download \
         --volume "${CURRENT_DIR}"/nginx.conf:/etc/nginx/nginx.conf \

contrib/terraform/aws/create-infrastructure.tf

@@ -1,11 +1,5 @@
 terraform {
   required_version = ">= 0.12.0"
-  required_providers {
-    aws = {
-      source  = "hashicorp/aws"
-      version = "~> 5.0"
-    }
-  }
 }
 
 provider "aws" {

contrib/terraform/equinix/README.md

@@ -0,0 +1,246 @@
+# Kubernetes on Equinix Metal with Terraform
+
+Provision a Kubernetes cluster with [Terraform](https://www.terraform.io) on
+[Equinix Metal](https://metal.equinix.com) ([formerly Packet](https://blog.equinix.com/blog/2020/10/06/equinix-metal-metal-and-more/)).
+
+## Status
+
+This will install a Kubernetes cluster on Equinix Metal. It should work in all locations and on most server types.
+
+## Approach
+
+The terraform configuration inspects variables found in
+[variables.tf](variables.tf) to create resources in your Equinix Metal project.
+There is a [python script](../terraform.py) that reads the generated`.tfstate`
+file to generate a dynamic inventory that is consumed by [cluster.yml](../../../cluster.yml)
+to actually install Kubernetes with Kubespray.
+
+### Kubernetes Nodes
+
+You can create many different kubernetes topologies by setting the number of
+different classes of hosts.
+
+- Master nodes with etcd: `number_of_k8s_masters` variable
+- Master nodes without etcd: `number_of_k8s_masters_no_etcd` variable
+- Standalone etcd hosts: `number_of_etcd` variable
+- Kubernetes worker nodes: `number_of_k8s_nodes` variable
+
+Note that the Ansible script will report an invalid configuration if you wind up
+with an *even number* of etcd instances since that is not a valid configuration. This
+restriction includes standalone etcd nodes that are deployed in a cluster along with
+master nodes with etcd replicas. As an example, if you have three master nodes with
+etcd replicas and three standalone etcd nodes, the script will fail since there are
+now six total etcd replicas.
+
+## Requirements
+
+- [Install Terraform](https://www.terraform.io/intro/getting-started/install.html)
+- [Install Ansible dependencies](/docs/ansible/ansible.md#installing-ansible)
+- Account with Equinix Metal
+- An SSH key pair
+
+## SSH Key Setup
+
+An SSH keypair is required so Ansible can access the newly provisioned nodes (Equinix Metal hosts). By default, the public SSH key defined in cluster.tfvars will be installed in authorized_key on the newly provisioned nodes (~/.ssh/id_rsa.pub). Terraform will upload this public key and then it will be distributed out to all the nodes. If you have already set this public key in Equinix Metal (i.e. via the portal), then set the public keyfile name in cluster.tfvars to blank to prevent the duplicate key from being uploaded which will cause an error.
+
+If you don't already have a keypair generated (~/.ssh/id_rsa and ~/.ssh/id_rsa.pub), then a new keypair can be generated with the command:
+
+```ShellSession
+ssh-keygen -f ~/.ssh/id_rsa
+```
+
+## Terraform
+
+Terraform will be used to provision all of the Equinix Metal resources with base software as appropriate.
+
+### Configuration
+
+#### Inventory files
+
+Create an inventory directory for your cluster by copying the existing sample and linking the `hosts` script (used to build the inventory based on Terraform state):
+
+```ShellSession
+cp -LRp contrib/terraform/equinix/sample-inventory inventory/$CLUSTER
+cd inventory/$CLUSTER
+ln -s ../../contrib/terraform/equinix/hosts
+```
+
+This will be the base for subsequent Terraform commands.
+
+#### Equinix Metal API access
+
+Your Equinix Metal API key must be available in the `METAL_AUTH_TOKEN` environment variable.
+This key is typically stored outside of the code repo since it is considered secret.
+If someone gets this key, they can startup/shutdown hosts in your project!
+
+For more information on how to generate an API key or find your project ID, please see
+[Accounts Index](https://metal.equinix.com/developers/docs/accounts/).
+
+The Equinix Metal Project ID associated with the key will be set later in `cluster.tfvars`.
+
+For more information about the API, please see [Equinix Metal API](https://metal.equinix.com/developers/api/).
+
+For more information about terraform provider authentication, please see [the equinix provider documentation](https://registry.terraform.io/providers/equinix/equinix/latest/docs).
+
+Example:
+
+```ShellSession
+export METAL_AUTH_TOKEN="Example-API-Token"
+```
+
+Note that to deploy several clusters within the same project you need to use [terraform workspace](https://www.terraform.io/docs/state/workspaces.html#using-workspaces).
+
+#### Cluster variables
+
+The construction of the cluster is driven by values found in
+[variables.tf](variables.tf).
+
+For your cluster, edit `inventory/$CLUSTER/cluster.tfvars`.
+
+The `cluster_name` is used to set a tag on each server deployed as part of this cluster.
+This helps when identifying which hosts are associated with each cluster.
+
+While the defaults in variables.tf will successfully deploy a cluster, it is recommended to set the following values:
+
+- cluster_name = the name of the inventory directory created above as $CLUSTER
+- equinix_metal_project_id = the Equinix Metal Project ID associated with the Equinix Metal API token above
+
+#### Enable localhost access
+
+Kubespray will pull down a Kubernetes configuration file to access this cluster by enabling the
+`kubeconfig_localhost: true` in the Kubespray configuration.
+
+Edit `inventory/$CLUSTER/group_vars/k8s_cluster/k8s_cluster.yml` and comment back in the following line and change from `false` to `true`:
+`\# kubeconfig_localhost: false`
+becomes:
+`kubeconfig_localhost: true`
+
+Once the Kubespray playbooks are run, a Kubernetes configuration file will be written to the local host at `inventory/$CLUSTER/artifacts/admin.conf`
+
+#### Terraform state files
+
+In the cluster's inventory folder, the following files might be created (either by Terraform
+or manually), to prevent you from pushing them accidentally they are in a
+`.gitignore` file in the `contrib/terraform/equinix` directory :
+
+- `.terraform`
+- `.tfvars`
+- `.tfstate`
+- `.tfstate.backup`
+- `.lock.hcl`
+
+You can still add them manually if you want to.
+
+### Initialization
+
+Before Terraform can operate on your cluster you need to install the required
+plugins. This is accomplished as follows:
+
+```ShellSession
+cd inventory/$CLUSTER
+terraform -chdir=../../contrib/terraform/metal init -var-file=cluster.tfvars
+```
+
+This should finish fairly quickly telling you Terraform has successfully initialized and loaded necessary modules.
+
+### Provisioning cluster
+
+You can apply the Terraform configuration to your cluster with the following command
+issued from your cluster's inventory directory (`inventory/$CLUSTER`):
+
+```ShellSession
+terraform -chdir=../../contrib/terraform/equinix apply -var-file=cluster.tfvars
+export ANSIBLE_HOST_KEY_CHECKING=False
+ansible-playbook -i hosts ../../cluster.yml
+```
+
+### Destroying cluster
+
+You can destroy your new cluster with the following command issued from the cluster's inventory directory:
+
+```ShellSession
+terraform -chdir=../../contrib/terraform/equinix destroy -var-file=cluster.tfvars
+```
+
+If you've started the Ansible run, it may also be a good idea to do some manual cleanup:
+
+- Remove SSH keys from the destroyed cluster from your `~/.ssh/known_hosts` file
+- Clean up any temporary cache files: `rm /tmp/$CLUSTER-*`
+
+### Debugging
+
+You can enable debugging output from Terraform by setting `TF_LOG` to `DEBUG` before running the Terraform command.
+
+## Ansible
+
+### Node access
+
+#### SSH
+
+Ensure your local ssh-agent is running and your ssh key has been added. This
+step is required by the terraform provisioner:
+
+```ShellSession
+eval $(ssh-agent -s)
+ssh-add ~/.ssh/id_rsa
+```
+
+If you have deployed and destroyed a previous iteration of your cluster, you will need to clear out any stale keys from your SSH "known hosts" file ( `~/.ssh/known_hosts`).
+
+#### Test access
+
+Make sure you can connect to the hosts.  Note that Flatcar Container Linux by Kinvolk will have a state `FAILED` due to Python not being present.  This is okay, because Python will be installed during bootstrapping, so long as the hosts are not `UNREACHABLE`.
+
+```ShellSession
+$ ansible -i inventory/$CLUSTER/hosts -m ping all
+example-k8s_node-1 | SUCCESS => {
+    "changed": false,
+    "ping": "pong"
+}
+example-etcd-1 | SUCCESS => {
+    "changed": false,
+    "ping": "pong"
+}
+example-k8s-master-1 | SUCCESS => {
+    "changed": false,
+    "ping": "pong"
+}
+```
+
+If it fails try to connect manually via SSH.  It could be something as simple as a stale host key.
+
+### Deploy Kubernetes
+
+```ShellSession
+ansible-playbook --become -i inventory/$CLUSTER/hosts cluster.yml
+```
+
+This will take some time as there are many tasks to run.
+
+## Kubernetes
+
+### Set up kubectl
+
+- [Install kubectl](https://kubernetes.io/docs/tasks/tools/install-kubectl/) on the localhost.
+- Verify that Kubectl runs correctly
+
+```ShellSession
+kubectl version
+```
+
+- Verify that the Kubernetes configuration file has been copied over
+
+```ShellSession
+cat inventory/alpha/$CLUSTER/admin.conf
+```
+
+- Verify that all the nodes are running correctly.
+
+```ShellSession
+kubectl version
+kubectl --kubeconfig=inventory/$CLUSTER/artifacts/admin.conf  get nodes
+```
+
+## What's next
+
+Try out your new Kubernetes cluster with the [Hello Kubernetes service](https://kubernetes.io/docs/tasks/access-application-cluster/service-access-application-cluster/).

contrib/terraform/equinix/hosts

@@ -0,0 +1 @@
+../terraform.py

contrib/terraform/equinix/kubespray.tf

@@ -0,0 +1,57 @@
+resource "equinix_metal_ssh_key" "k8s" {
+  count      = var.public_key_path != "" ? 1 : 0
+  name       = "kubernetes-${var.cluster_name}"
+  public_key = chomp(file(var.public_key_path))
+}
+
+resource "equinix_metal_device" "k8s_master" {
+  depends_on = [equinix_metal_ssh_key.k8s]
+
+  count            = var.number_of_k8s_masters
+  hostname         = "${var.cluster_name}-k8s-master-${count.index + 1}"
+  plan             = var.plan_k8s_masters
+  metro            = var.metro
+  operating_system = var.operating_system
+  billing_cycle    = var.billing_cycle
+  project_id       = var.equinix_metal_project_id
+  tags             = ["cluster-${var.cluster_name}", "k8s_cluster", "kube_control_plane", "etcd", "kube_node"]
+}
+
+resource "equinix_metal_device" "k8s_master_no_etcd" {
+  depends_on = [equinix_metal_ssh_key.k8s]
+
+  count            = var.number_of_k8s_masters_no_etcd
+  hostname         = "${var.cluster_name}-k8s-master-${count.index + 1}"
+  plan             = var.plan_k8s_masters_no_etcd
+  metro            = var.metro
+  operating_system = var.operating_system
+  billing_cycle    = var.billing_cycle
+  project_id       = var.equinix_metal_project_id
+  tags             = ["cluster-${var.cluster_name}", "k8s_cluster", "kube_control_plane"]
+}
+
+resource "equinix_metal_device" "k8s_etcd" {
+  depends_on = [equinix_metal_ssh_key.k8s]
+
+  count            = var.number_of_etcd
+  hostname         = "${var.cluster_name}-etcd-${count.index + 1}"
+  plan             = var.plan_etcd
+  metro            = var.metro
+  operating_system = var.operating_system
+  billing_cycle    = var.billing_cycle
+  project_id       = var.equinix_metal_project_id
+  tags             = ["cluster-${var.cluster_name}", "etcd"]
+}
+
+resource "equinix_metal_device" "k8s_node" {
+  depends_on = [equinix_metal_ssh_key.k8s]
+
+  count            = var.number_of_k8s_nodes
+  hostname         = "${var.cluster_name}-k8s-node-${count.index + 1}"
+  plan             = var.plan_k8s_nodes
+  metro            = var.metro
+  operating_system = var.operating_system
+  billing_cycle    = var.billing_cycle
+  project_id       = var.equinix_metal_project_id
+  tags             = ["cluster-${var.cluster_name}", "k8s_cluster", "kube_node"]
+}

contrib/terraform/equinix/output.tf

@@ -0,0 +1,15 @@
+output "k8s_masters" {
+  value = equinix_metal_device.k8s_master.*.access_public_ipv4
+}
+
+output "k8s_masters_no_etc" {
+  value = equinix_metal_device.k8s_master_no_etcd.*.access_public_ipv4
+}
+
+output "k8s_etcds" {
+  value = equinix_metal_device.k8s_etcd.*.access_public_ipv4
+}
+
+output "k8s_nodes" {
+  value = equinix_metal_device.k8s_node.*.access_public_ipv4
+}

contrib/terraform/equinix/provider.tf

@@ -0,0 +1,17 @@
+terraform {
+  required_version = ">= 1.0.0"
+
+  provider_meta "equinix" {
+    module_name = "kubespray"
+  }
+  required_providers {
+    equinix = {
+      source  = "equinix/equinix"
+      version = "1.24.0"
+    }
+  }
+}
+
+# Configure the Equinix Metal Provider
+provider "equinix" {
+}

contrib/terraform/equinix/sample-inventory/cluster.tfvars

@@ -0,0 +1,35 @@
+# your Kubernetes cluster name here
+cluster_name = "mycluster"
+
+# Your Equinix Metal project ID. See https://metal.equinix.com/developers/docs/accounts/
+equinix_metal_project_id = "Example-Project-Id"
+
+# The public SSH key to be uploaded into authorized_keys in bare metal Equinix Metal nodes provisioned
+# leave this value blank if the public key is already setup in the Equinix Metal project
+# Terraform will complain if the public key is setup in Equinix Metal
+public_key_path = "~/.ssh/id_rsa.pub"
+
+# Equinix interconnected bare metal across our global metros.
+metro = "da"
+
+# operating_system
+operating_system = "ubuntu_22_04"
+
+# standalone etcds
+number_of_etcd = 0
+
+plan_etcd = "t1.small.x86"
+
+# masters
+number_of_k8s_masters = 1
+
+number_of_k8s_masters_no_etcd = 0
+
+plan_k8s_masters = "t1.small.x86"
+
+plan_k8s_masters_no_etcd = "t1.small.x86"
+
+# nodes
+number_of_k8s_nodes = 2
+
+plan_k8s_nodes = "t1.small.x86"

contrib/terraform/equinix/sample-inventory/group_vars

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

contrib/terraform/equinix/variables.tf

@@ -0,0 +1,56 @@
+variable "cluster_name" {
+  default = "kubespray"
+}
+
+variable "equinix_metal_project_id" {
+  description = "Your Equinix Metal project ID. See https://metal.equinix.com/developers/docs/accounts/"
+}
+
+variable "operating_system" {
+  default = "ubuntu_22_04"
+}
+
+variable "public_key_path" {
+  description = "The path of the ssh pub key"
+  default     = "~/.ssh/id_rsa.pub"
+}
+
+variable "billing_cycle" {
+  default = "hourly"
+}
+
+variable "metro" {
+  default = "da"
+}
+
+variable "plan_k8s_masters" {
+  default = "c3.small.x86"
+}
+
+variable "plan_k8s_masters_no_etcd" {
+  default = "c3.small.x86"
+}
+
+variable "plan_etcd" {
+  default = "c3.small.x86"
+}
+
+variable "plan_k8s_nodes" {
+  default = "c3.medium.x86"
+}
+
+variable "number_of_k8s_masters" {
+  default = 1
+}
+
+variable "number_of_k8s_masters_no_etcd" {
+  default = 0
+}
+
+variable "number_of_etcd" {
+  default = 0
+}
+
+variable "number_of_k8s_nodes" {
+  default = 1
+}

contrib/terraform/hetzner/README.md

@@ -102,8 +102,7 @@ Please read the instructions in both repos on how to install it.
 You can teardown your infrastructure using the following Terraform command:
 
 ```bash
-cd ./kubespray
-terraform -chdir=./contrib/terraform/hetzner/ destroy --var-file=../../../inventory/$CLUSTER/default.tfvars
+terraform destroy --var-file default.tfvars ../../contrib/terraform/hetzner
 ```
 
 ## Variables

contrib/terraform/openstack/README.md

@@ -624,7 +624,7 @@ Edit `inventory/$CLUSTER/group_vars/k8s_cluster/k8s_cluster.yml`:
   - **calico** requires [configuring OpenStack Neutron ports](/docs/cloud_controllers/openstack.md) to allow service and pod subnets
 
 ```yml
-# Choose network plugin (calico or flannel)
+# Choose network plugin (calico, weave or flannel)
 # Can also be set to 'cloud', which lets the cloud provider setup appropriate routing
 kube_network_plugin: flannel
 ```

contrib/terraform/upcloud/README.md

@@ -2,6 +2,35 @@
 
 Provision a Kubernetes cluster on [UpCloud](https://upcloud.com/) using Terraform and Kubespray
 
+## Overview
+
+The setup looks like following
+
+```text
+   Kubernetes cluster
++--------------------------+
+|      +--------------+    |
+|      | +--------------+  |
+| -->  | |              |  |
+|      | | Master/etcd  |  |
+|      | | node(s)      |  |
+|      +-+              |  |
+|        +--------------+  |
+|              ^           |
+|              |           |
+|              v           |
+|      +--------------+    |
+|      | +--------------+  |
+| -->  | |              |  |
+|      | |    Worker    |  |
+|      | |    node(s)   |  |
+|      +-+              |  |
+|        +--------------+  |
++--------------------------+
+```
+
+The nodes uses a private network for node to node communication and a public interface for all external communication.
+
 ## Requirements
 
 * Terraform 0.13.0 or newer
@@ -71,8 +100,6 @@ terraform destroy --var-file cluster-settings.tfvars \
 * `template_name`: The name or UUID  of a base image
 * `username`: a user to access the nodes, defaults to "ubuntu"
 * `private_network_cidr`: CIDR to use for the private network, defaults to "172.16.0.0/24"
-* `dns_servers`: DNS servers that will be used by the nodes. Until [this is solved](https://github.com/UpCloudLtd/terraform-provider-upcloud/issues/562) this is done using user_data to reconfigure resolved. Defaults to `[]`
-* `use_public_ips`: If a NIC connencted to the Public network should be attached to all nodes by default. Can be overridden by `force_public_ip` if this is set to `false`. Defaults to `true`
 * `ssh_public_keys`: List of public SSH keys to install on all machines
 * `zone`: The zone where to run the cluster
 * `machines`: Machines to provision. Key of this object will be used as the name of the machine
@@ -81,8 +108,6 @@ terraform destroy --var-file cluster-settings.tfvars \
   * `cpu`: number of cpu cores
   * `mem`: memory size in MB
   * `disk_size`: The size of the storage in GB
-  * `force_public_ip`: If `use_public_ips` is set to `false`, this forces a public NIC onto the machine anyway when set to `true`. Useful if you're migrating from public nodes to only private. Defaults to `false`
-  * `dns_servers`: This works the same way as the global `dns_severs` but only applies to a single node. If set to `[]` while the global `dns_servers` is set to something else, then it will not add the user_data and thus will not be recreated. Useful if you're migrating from public nodes to only private. Defaults to `null`
   * `additional_disks`: Additional disks to attach to the node.
     * `size`: The size of the additional disk in GB
     * `tier`: The tier of disk to use (`maxiops` is the only one you can choose atm)
@@ -114,7 +139,6 @@ terraform destroy --var-file cluster-settings.tfvars \
   * `port`: Port to load balance.
   * `target_port`: Port to the backend servers.
   * `backend_servers`: List of servers that traffic to the port should be forwarded to.
-  * `proxy_protocol`: If the loadbalancer should set up the backend using proxy protocol.
 * `router_enable`: If a router should be connected to the private network or not
 * `gateways`: Gateways that should be connected to the router, requires router_enable is set to true
   * `features`: List of features for the gateway
@@ -147,27 +171,3 @@ terraform destroy --var-file cluster-settings.tfvars \
 * `server_groups`: Group servers together
   * `servers`: The servers that should be included in the group.
   * `anti_affinity_policy`: Defines if a server group is an anti-affinity group. Setting this to "strict" or yes" will result in all servers in the group being placed on separate compute hosts. The value can be "strict", "yes" or "no". "strict" refers to strict policy doesn't allow servers in the same server group to be on the same host. "yes" refers to best-effort policy and tries to put servers on different hosts, but this is not guaranteed.
-
-## Migration
-
-When `null_resource.inventories` and `data.template_file.inventory` was changed to `local_file.inventory` the old state file needs to be cleaned of the old state.
-The error messages you'll see if you encounter this is:
-
-```text
-Error: failed to read schema for null_resource.inventories in registry.terraform.io/hashicorp/null: failed to instantiate provider "registry.terraform.io/hashicorp/null" to obtain schema: unavailable provider "registry.terraform.io/hashicorp/null"
-Error: failed to read schema for data.template_file.inventory in registry.terraform.io/hashicorp/template: failed to instantiate provider "registry.terraform.io/hashicorp/template" to obtain schema: unavailable provider "registry.terraform.io/hashicorp/template"
-```
-
-This can be fixed with the following lines
-
-```bash
-terraform state rm -state=terraform.tfstate null_resource.inventories
-terraform state rm -state=terraform.tfstate data.template_file.inventory
-```
-
-### Public to Private only migration
-
-Since there's no way to remove the public NIC on a machine without recreating its private NIC it's not possible to inplace change a cluster to only use private IPs.
-The way to migrate is to first set `use_public_ips` to `false`, `dns_servers` to some DNS servers and then update all existing servers to have `force_public_ip` set to `true` and `dns_severs` set to `[]`.
-After that you can add new nodes without `force_public_ip` and `dns_servers` set and create them.
-Add the new nodes into the cluster and when all of them are added, remove the old nodes.

contrib/terraform/upcloud/cluster-settings.tfvars

@@ -122,11 +122,11 @@ k8s_allowed_remote_ips = [
 master_allowed_ports = []
 worker_allowed_ports = []
 
-loadbalancer_enabled = false
-loadbalancer_plan    = "development"
+loadbalancer_enabled        = false
+loadbalancer_plan           = "development"
+loadbalancer_proxy_protocol = false
 loadbalancers = {
   # "http" : {
-  #   "proxy_protocol" : false
   #   "port" : 80,
   #   "target_port" : 80,
   #   "backend_servers" : [

contrib/terraform/upcloud/main.tf

@@ -20,26 +20,24 @@ module "kubernetes" {
   username      = var.username
 
   private_network_cidr = var.private_network_cidr
-  dns_servers          = var.dns_servers
-  use_public_ips       = var.use_public_ips
 
   machines = var.machines
 
   ssh_public_keys = var.ssh_public_keys
 
-  firewall_enabled           = var.firewall_enabled
-  firewall_default_deny_in   = var.firewall_default_deny_in
-  firewall_default_deny_out  = var.firewall_default_deny_out
-  master_allowed_remote_ips  = var.master_allowed_remote_ips
-  k8s_allowed_remote_ips     = var.k8s_allowed_remote_ips
-  bastion_allowed_remote_ips = var.bastion_allowed_remote_ips
-  master_allowed_ports       = var.master_allowed_ports
-  worker_allowed_ports       = var.worker_allowed_ports
+  firewall_enabled          = var.firewall_enabled
+  firewall_default_deny_in  = var.firewall_default_deny_in
+  firewall_default_deny_out = var.firewall_default_deny_out
+  master_allowed_remote_ips = var.master_allowed_remote_ips
+  k8s_allowed_remote_ips    = var.k8s_allowed_remote_ips
+  master_allowed_ports      = var.master_allowed_ports
+  worker_allowed_ports      = var.worker_allowed_ports
 
-  loadbalancer_enabled        = var.loadbalancer_enabled
-  loadbalancer_plan           = var.loadbalancer_plan
-  loadbalancer_legacy_network = var.loadbalancer_legacy_network
-  loadbalancers               = var.loadbalancers
+  loadbalancer_enabled                 = var.loadbalancer_enabled
+  loadbalancer_plan                    = var.loadbalancer_plan
+  loadbalancer_outbound_proxy_protocol = var.loadbalancer_proxy_protocol ? "v2" : ""
+  loadbalancer_legacy_network          = var.loadbalancer_legacy_network
+  loadbalancers                        = var.loadbalancers
 
   router_enable    = var.router_enable
   gateways         = var.gateways
@@ -54,12 +52,32 @@ module "kubernetes" {
 # Generate ansible inventory
 #
 
-resource "local_file" "inventory" {
-  content = templatefile("${path.module}/templates/inventory.tpl", {
-    master_ip  = module.kubernetes.master_ip
-    worker_ip  = module.kubernetes.worker_ip
-    bastion_ip = module.kubernetes.bastion_ip
-    username   = var.username
-  })
-  filename = var.inventory_file
+data "template_file" "inventory" {
+  template = file("${path.module}/templates/inventory.tpl")
+
+  vars = {
+    connection_strings_master = join("\n", formatlist("%s ansible_user=ubuntu ansible_host=%s ip=%s etcd_member_name=etcd%d",
+      keys(module.kubernetes.master_ip),
+      values(module.kubernetes.master_ip).*.public_ip,
+      values(module.kubernetes.master_ip).*.private_ip,
+    range(1, length(module.kubernetes.master_ip) + 1)))
+    connection_strings_worker = join("\n", formatlist("%s ansible_user=ubuntu ansible_host=%s ip=%s",
+      keys(module.kubernetes.worker_ip),
+      values(module.kubernetes.worker_ip).*.public_ip,
+    values(module.kubernetes.worker_ip).*.private_ip))
+    list_master = join("\n", formatlist("%s",
+    keys(module.kubernetes.master_ip)))
+    list_worker = join("\n", formatlist("%s",
+    keys(module.kubernetes.worker_ip)))
+  }
+}
+
+resource "null_resource" "inventories" {
+  provisioner "local-exec" {
+    command = "echo '${data.template_file.inventory.rendered}' > ${var.inventory_file}"
+  }
+
+  triggers = {
+    template = data.template_file.inventory.rendered
+  }
 }

contrib/terraform/upcloud/modules/kubernetes-cluster/main.tf

@@ -53,44 +53,6 @@ locals {
   # If prefix is set, all resources will be prefixed with "${var.prefix}-"
   # Else don't prefix with anything
   resource-prefix = "%{if var.prefix != ""}${var.prefix}-%{endif}"
-
-  master_ip = {
-    for instance in upcloud_server.master :
-      instance.hostname => {
-        for nic in instance.network_interface :
-          nic.type => nic.ip_address
-        if nic.ip_address != null
-      }
-  }
-  worker_ip = {
-    for instance in upcloud_server.worker :
-      instance.hostname => {
-        for nic in instance.network_interface :
-          nic.type => nic.ip_address
-        if nic.ip_address != null
-      }
-  }
-
-  bastion_ip = {
-    for instance in upcloud_server.bastion :
-      instance.hostname => {
-        for nic in instance.network_interface :
-          nic.type => nic.ip_address
-        if nic.ip_address != null
-      }
-  }
-
-  node_user_data = {
-    for name, machine in var.machines :
-      name => <<EOF
-%{ if ( length(machine.dns_servers != null ? machine.dns_servers : [] ) > 0 ) || ( length(var.dns_servers) > 0 && machine.dns_servers == null ) ~}
-#!/bin/bash
-echo -e "[Resolve]\nDNS=${ join(" ", length(machine.dns_servers != null ? machine.dns_servers : []) > 0 ? machine.dns_servers : var.dns_servers) }" > /etc/systemd/resolved.conf
-
-systemctl restart systemd-resolved
-%{ endif ~}
-EOF
-  }
 }
 
 resource "upcloud_network" "private" {
@@ -100,9 +62,6 @@ resource "upcloud_network" "private" {
   ip_network {
     address            = var.private_network_cidr
     dhcp_default_route = var.router_enable
-    # TODO: When support for dhcp_dns for private networks are in, remove the user_data and enable it here.
-    #       See more here https://github.com/UpCloudLtd/terraform-provider-upcloud/issues/562
-    # dhcp_dns           = length(var.private_network_dns) > 0 ? var.private_network_dns : null
     dhcp               = true
     family             = "IPv4"
   }
@@ -130,8 +89,8 @@ resource "upcloud_server" "master" {
 
   hostname     = "${local.resource-prefix}${each.key}"
   plan         = each.value.plan
-  cpu          = each.value.cpu
-  mem          = each.value.mem
+  cpu          = each.value.plan == null ? null : each.value.cpu
+  mem          = each.value.plan == null ? null : each.value.mem
   zone         = var.zone
   server_group = each.value.server_group == null ? null : upcloud_server_group.server_groups[each.value.server_group].id
 
@@ -140,12 +99,9 @@ resource "upcloud_server" "master" {
     size    = each.value.disk_size
   }
 
-  dynamic "network_interface" {
-    for_each = each.value.force_public_ip || var.use_public_ips ? [1] : []
-
-    content {
-      type = "public"
-    }
+  # Public network interface
+  network_interface {
+    type = "public"
   }
 
   # Private network interface
@@ -180,9 +136,6 @@ resource "upcloud_server" "master" {
     keys            = var.ssh_public_keys
     create_password = false
   }
-
-  metadata = local.node_user_data[each.key] != "" ? true : null
-  user_data = local.node_user_data[each.key] != "" ? local.node_user_data[each.key] : null
 }
 
 resource "upcloud_server" "worker" {
@@ -194,8 +147,8 @@ resource "upcloud_server" "worker" {
 
   hostname     = "${local.resource-prefix}${each.key}"
   plan         = each.value.plan
-  cpu          = each.value.cpu
-  mem          = each.value.mem
+  cpu          = each.value.plan == null ? null : each.value.cpu
+  mem          = each.value.plan == null ? null : each.value.mem
   zone         = var.zone
   server_group = each.value.server_group == null ? null : upcloud_server_group.server_groups[each.value.server_group].id
 
@@ -205,12 +158,9 @@ resource "upcloud_server" "worker" {
     size    = each.value.disk_size
   }
 
-  dynamic "network_interface" {
-    for_each = each.value.force_public_ip || var.use_public_ips ? [1] : []
-
-    content {
-      type = "public"
-    }
+  # Public network interface
+  network_interface {
+    type = "public"
   }
 
   # Private network interface
@@ -245,63 +195,6 @@ resource "upcloud_server" "worker" {
     keys            = var.ssh_public_keys
     create_password = false
   }
-
-  metadata = local.node_user_data[each.key] != "" ? true : null
-  user_data = local.node_user_data[each.key] != "" ? local.node_user_data[each.key] : null
-}
-
-resource "upcloud_server" "bastion" {
-  for_each = {
-    for name, machine in var.machines :
-    name => machine
-    if machine.node_type == "bastion"
-  }
-
-  hostname     = "${local.resource-prefix}${each.key}"
-  plan         = each.value.plan
-  cpu          = each.value.cpu
-  mem          = each.value.mem
-  zone         = var.zone
-  server_group = each.value.server_group == null ? null : upcloud_server_group.server_groups[each.value.server_group].id
-
-
-  template {
-    storage = var.template_name
-    size    = each.value.disk_size
-  }
-
-  # Private network interface
-  network_interface {
-    type    = "private"
-    network = upcloud_network.private.id
-  }
-
-  # Private network interface
-  network_interface {
-    type    = "public"
-  }
-
-  firewall = var.firewall_enabled
-
-  dynamic "storage_devices" {
-    for_each = {
-      for disk_key_name, disk in upcloud_storage.additional_disks :
-      disk_key_name => disk
-      # Only add the disk if it matches the node name in the start of its name
-      if length(regexall("^${each.key}_.+", disk_key_name)) > 0
-    }
-
-    content {
-      storage = storage_devices.value.id
-    }
-  }
-
-  # Include at least one public SSH key
-  login {
-    user            = var.username
-    keys            = var.ssh_public_keys
-    create_password = false
-  }
 }
 
 resource "upcloud_firewall_rules" "master" {
@@ -650,53 +543,6 @@ resource "upcloud_firewall_rules" "k8s" {
   }
 }
 
-resource "upcloud_firewall_rules" "bastion" {
-  for_each  = upcloud_server.bastion
-  server_id = each.value.id
-
-  dynamic "firewall_rule" {
-    for_each = var.bastion_allowed_remote_ips
-
-    content {
-      action                 = "accept"
-      comment                = "Allow bastion SSH access from this network"
-      destination_port_end   = "22"
-      destination_port_start = "22"
-      direction              = "in"
-      family                 = "IPv4"
-      protocol               = "tcp"
-      source_address_end     = firewall_rule.value.end_address
-      source_address_start   = firewall_rule.value.start_address
-    }
-  }
-
-  dynamic "firewall_rule" {
-    for_each = length(var.bastion_allowed_remote_ips) > 0 ? [1] : []
-
-    content {
-      action                 = "drop"
-      comment                = "Drop bastion SSH access from other networks"
-      destination_port_end   = "22"
-      destination_port_start = "22"
-      direction              = "in"
-      family                 = "IPv4"
-      protocol               = "tcp"
-      source_address_end     = "255.255.255.255"
-      source_address_start   = "0.0.0.0"
-    }
-  }
-
-  firewall_rule {
-    action    = var.firewall_default_deny_in ? "drop" : "accept"
-    direction = "in"
-  }
-
-  firewall_rule {
-    action    = var.firewall_default_deny_out ? "drop" : "accept"
-    direction = "out"
-  }
-}
-
 resource "upcloud_loadbalancer" "lb" {
   count             = var.loadbalancer_enabled ? 1 : 0
   configured_status = "started"
@@ -737,7 +583,7 @@ resource "upcloud_loadbalancer_backend" "lb_backend" {
   loadbalancer = upcloud_loadbalancer.lb[0].id
   name         = "lb-backend-${each.key}"
   properties {
-    outbound_proxy_protocol = each.value.proxy_protocol ? "v2" : ""
+    outbound_proxy_protocol = var.loadbalancer_outbound_proxy_protocol
   }
 }
 
@@ -776,7 +622,7 @@ resource "upcloud_loadbalancer_static_backend_member" "lb_backend_member" {
 
   backend      = upcloud_loadbalancer_backend.lb_backend[each.value.lb_name].id
   name         = "${local.resource-prefix}${each.key}"
-  ip           = merge(local.master_ip, local.worker_ip)["${local.resource-prefix}${each.value.server_name}"].private
+  ip           = merge(upcloud_server.master, upcloud_server.worker)[each.value.server_name].network_interface[1].ip_address
   port         = each.value.port
   weight       = 100
   max_sessions = var.loadbalancer_plan == "production-small" ? 50000 : 1000
@@ -816,7 +662,7 @@ resource "upcloud_router" "router" {
 resource "upcloud_gateway" "gateway" {
   for_each = var.router_enable ? var.gateways : {}
   name = "${local.resource-prefix}${each.key}-gateway"
-  zone = var.private_cloud ? var.public_zone : var.zone
+  zone = var.zone
 
   features = each.value.features
   plan = each.value.plan

contrib/terraform/upcloud/modules/kubernetes-cluster/output.tf

@@ -1,13 +1,22 @@
+
 output "master_ip" {
-  value = local.master_ip
+  value = {
+    for instance in upcloud_server.master :
+    instance.hostname => {
+      "public_ip" : instance.network_interface[0].ip_address
+      "private_ip" : instance.network_interface[1].ip_address
+    }
+  }
 }
 
 output "worker_ip" {
-  value = local.worker_ip
-}
-
-output "bastion_ip" {
-  value = local.bastion_ip
+  value = {
+    for instance in upcloud_server.worker :
+    instance.hostname => {
+      "public_ip" : instance.network_interface[0].ip_address
+      "private_ip" : instance.network_interface[1].ip_address
+    }
+  }
 }
 
 output "loadbalancer_domain" {

contrib/terraform/upcloud/modules/kubernetes-cluster/variables.tf

@@ -20,21 +20,15 @@ variable "username" {}
 
 variable "private_network_cidr" {}
 
-variable "dns_servers" {}
-
-variable "use_public_ips" {}
-
 variable "machines" {
   description = "Cluster machines"
   type = map(object({
     node_type = string
     plan      = string
-    cpu       = optional(number)
-    mem       = optional(number)
+    cpu       = string
+    mem       = string
     disk_size = number
     server_group : string
-    force_public_ip : optional(bool, false)
-    dns_servers : optional(set(string))
     additional_disks = map(object({
       size = number
       tier = string
@@ -64,13 +58,6 @@ variable "k8s_allowed_remote_ips" {
   }))
 }
 
-variable "bastion_allowed_remote_ips" {
-  type = list(object({
-    start_address = string
-    end_address   = string
-  }))
-}
-
 variable "master_allowed_ports" {
   type = list(object({
     protocol       = string
@@ -107,6 +94,10 @@ variable "loadbalancer_plan" {
   type = string
 }
 
+variable "loadbalancer_outbound_proxy_protocol" {
+  type = string
+}
+
 variable "loadbalancer_legacy_network" {
   type = bool
   default = false
@@ -116,7 +107,6 @@ variable "loadbalancers" {
   description = "Load balancers"
 
   type = map(object({
-    proxy_protocol          = bool
     port                    = number
     target_port             = number
     allow_internal_frontend = optional(bool)

contrib/terraform/upcloud/output.tf

@@ -7,10 +7,6 @@ output "worker_ip" {
   value = module.kubernetes.worker_ip
 }
 
-output "bastion_ip" {
-  value = module.kubernetes.bastion_ip
-}
-
 output "loadbalancer_domain" {
   value = module.kubernetes.loadbalancer_domain
 }

contrib/terraform/upcloud/templates/inventory.tpl

@@ -1,33 +1,17 @@
+
 [all]
-%{ for name, ips in master_ip ~}
-${name} ansible_user=${username} ansible_host=${lookup(ips, "public", ips.private)} ip=${ips.private}
-%{ endfor ~}
-%{ for name, ips in worker_ip ~}
-${name} ansible_user=${username} ansible_host=${lookup(ips, "public", ips.private)} ip=${ips.private}
-%{ endfor ~}
+${connection_strings_master}
+${connection_strings_worker}
 
 [kube_control_plane]
-%{ for name, ips in master_ip ~}
-${name}
-%{ endfor ~}
+${list_master}
 
 [etcd]
-%{ for name, ips in master_ip ~}
-${name}
-%{ endfor ~}
+${list_master}
 
 [kube_node]
-%{ for name, ips in worker_ip ~}
-${name}
-%{ endfor ~}
+${list_worker}
 
 [k8s_cluster:children]
 kube_control_plane
 kube_node
-
-%{ if length(bastion_ip) > 0 ~}
-[bastion]
-%{ for name, ips in bastion_ip ~}
-bastion ansible_user=${username} ansible_host=${ips.public}
-%{ endfor ~}
-%{ endif ~}

contrib/terraform/upcloud/variables.tf

@@ -32,31 +32,16 @@ variable "private_network_cidr" {
   default     = "172.16.0.0/24"
 }
 
-variable "dns_servers" {
-  description = "DNS servers that will be used by the nodes. Until [this is solved](https://github.com/UpCloudLtd/terraform-provider-upcloud/issues/562) this is done using user_data to reconfigure resolved"
-
-  type    = set(string)
-  default = []
-}
-
-variable "use_public_ips" {
-  description = "If all nodes should get a public IP"
-  type        = bool
-  default     = true
-}
-
 variable "machines" {
   description = "Cluster machines"
 
   type = map(object({
     node_type = string
     plan      = string
-    cpu       = optional(number)
-    mem       = optional(number)
+    cpu       = string
+    mem       = string
     disk_size = number
     server_group : string
-    force_public_ip : optional(bool, false)
-    dns_servers : optional(set(string))
     additional_disks = map(object({
       size = number
       tier = string
@@ -104,15 +89,6 @@ variable "k8s_allowed_remote_ips" {
   default = []
 }
 
-variable "bastion_allowed_remote_ips" {
-  description = "List of IP start/end addresses allowed to SSH to bastion"
-  type = list(object({
-    start_address = string
-    end_address   = string
-  }))
-  default = []
-}
-
 variable "master_allowed_ports" {
   description = "List of ports to allow on masters"
   type = list(object({
@@ -155,6 +131,11 @@ variable "loadbalancer_plan" {
   default     = "development"
 }
 
+variable "loadbalancer_proxy_protocol" {
+  type    = bool
+  default = false
+}
+
 variable "loadbalancer_legacy_network" {
   description = "If the loadbalancer should use the deprecated network field instead of networks blocks. You probably want to have this set to false"
 
@@ -166,7 +147,6 @@ variable "loadbalancers" {
   description = "Load balancers"
 
   type = map(object({
-    proxy_protocol          = bool
     port                    = number
     target_port             = number
     allow_internal_frontend = optional(bool, false)

docs/CNI/calico.md

@@ -180,7 +180,7 @@ calico_group_id=rr1
 The inventory above will deploy the following topology assuming that calico's
 `global_as_num` is set to `65400`:
 
-![Image](../figures/kubespray-calico-rr.png?raw=true)
+![Image](figures/kubespray-calico-rr.png?raw=true)
 
 ### Optional : Define default endpoint to host action
 
@@ -377,7 +377,7 @@ To clean up any ipvs leftovers:
 
 ### Calico access to the kube-api
 
-Calico node, typha and kube-controllers need to be able to talk to the kubernetes API. Please reference the [Enabling eBPF Calico Docs](https://docs.tigera.io/calico/latest/operations/ebpf/enabling-ebpf) for guidelines on how to do this.
+Calico node, typha and kube-controllers need to be able to talk to the kubernetes API. Please reference the [Enabling eBPF Calico Docs](https://docs.projectcalico.org/maintenance/ebpf/enabling-bpf) for guidelines on how to do this.
 
 Kubespray sets up the `kubernetes-services-endpoint` configmap based on the contents of the `loadbalancer_apiserver` inventory variable documented in [HA Mode](/docs/operations/ha-mode.md).
 

docs/CNI/cilium.md

@@ -54,10 +54,6 @@ cilium_loadbalancer_ip_pools:
   - name: "blue-pool"
     cidrs:
       - "10.0.10.0/24"
-    ranges:
-      - start: "20.0.20.100"
-        stop: "20.0.20.200"
-      - start: "1.2.3.4"
 ```
 
 For further information, check [LB IPAM documentation](https://docs.cilium.io/en/stable/network/lb-ipam/)
@@ -237,7 +233,7 @@ cilium_operator_extra_volume_mounts:
 ## Choose Cilium version
 
 ```yml
-cilium_version: "1.18.4"
+cilium_version: "1.15.9"
 ```
 
 ## Add variable to config

docs/CNI/weave.md

@@ -0,0 +1,79 @@
+# Weave
+
+Weave 2.0.1 is supported by kubespray
+
+Weave uses [**consensus**](https://www.weave.works/docs/net/latest/ipam/##consensus) mode (default mode) and [**seed**](https://www.weave.works/docs/net/latest/ipam/#seed) mode.
+
+`Consensus` mode is best to use on static size cluster and `seed` mode is best to use on dynamic size cluster
+
+Weave encryption is supported for all communication
+
+* To use Weave encryption, specify a strong password (if no password, no encryption)
+
+```ShellSession
+# In file ./inventory/sample/group_vars/k8s_cluster.yml
+weave_password: EnterPasswordHere
+```
+
+This password is used to set an environment variable inside weave container.
+
+Weave is deployed by kubespray using a daemonSet
+
+* Check the status of Weave containers
+
+```ShellSession
+# From client
+kubectl -n kube-system get pods | grep weave
+# output
+weave-net-50wd2                       2/2       Running   0          2m
+weave-net-js9rb                       2/2       Running   0          2m
+```
+
+There must be as many pods as nodes (here kubernetes have 2 nodes so there are 2 weave pods).
+
+* Check status of weave (connection,encryption ...) for each node
+
+```ShellSession
+# On nodes
+curl http://127.0.0.1:6784/status
+# output on node1
+Version: 2.0.1 (up to date; next check at 2017/08/01 13:51:34)
+
+        Service: router
+       Protocol: weave 1..2
+           Name: fa:16:3e:b3:d6:b2(node1)
+     Encryption: enabled
+  PeerDiscovery: enabled
+        Targets: 2
+    Connections: 2 (1 established, 1 failed)
+          Peers: 2 (with 2 established connections)
+ TrustedSubnets: none
+
+        Service: ipam
+         Status: ready
+          Range: 10.233.64.0/18
+  DefaultSubnet: 10.233.64.0/18
+```
+
+* Check parameters of weave for each node
+
+```ShellSession
+# On nodes
+ps -aux | grep weaver
+# output on node1 (here its use seed mode)
+root      8559  0.2  3.0 365280 62700 ?        Sl   08:25   0:00 /home/weave/weaver --name=fa:16:3e:b3:d6:b2 --port=6783 --datapath=datapath --host-root=/host --http-addr=127.0.0.1:6784 --status-addr=0.0.0.0:6782 --docker-api= --no-dns --db-prefix=/weavedb/weave-net --ipalloc-range=10.233.64.0/18 --nickname=node1 --ipalloc-init seed=fa:16:3e:b3:d6:b2,fa:16:3e:f0:50:53 --conn-limit=30 --expect-npc 192.168.208.28 192.168.208.19
+```
+
+## Consensus mode (default mode)
+
+This mode is best to use on static size cluster
+
+### Seed mode
+
+This mode is best to use on dynamic size cluster
+
+The seed mode also allows multi-clouds and hybrid on-premise/cloud clusters deployment.
+
+* Switch from consensus mode to seed/Observation mode
+
+See [weave ipam documentation](https://www.weave.works/docs/net/latest/tasks/ipam/ipam/) and use `weave_extra_args` to enable.

docs/CRI/containerd.md

@@ -68,8 +68,8 @@ containerd_runc_runtime:
   engine: ""
   root: ""
   options:
-    SystemdCgroup: "false"
-    BinaryName: /usr/local/bin/my-runc
+    systemdCgroup: "false"
+    binaryName: /usr/local/bin/my-runc
   base_runtime_spec: cri-base.json
 ```
 
@@ -149,11 +149,3 @@ following configuration:
 ```yaml
 nri_enabled: true
 ```
-
-### Optional : Static Binary
-
-To ensure compatibility with older distributions (such as Debian 11), you can use a static containerd binary. By default, this is static binary if the system's glibc version is less than 2.34; otherwise, it is the default binary.
-
-```yaml
-containerd_static_binary: true
-```

docs/_sidebar.md

@@ -23,6 +23,7 @@
   * [Aws](/docs/cloud_providers/aws.md)
   * [Azure](/docs/cloud_providers/azure.md)
   * [Cloud](/docs/cloud_providers/cloud.md)
+  * [Equinix-metal](/docs/cloud_providers/equinix-metal.md)
 * CNI
   * [Calico](/docs/CNI/calico.md)
   * [Cilium](/docs/CNI/cilium.md)
@@ -32,6 +33,7 @@
   * [Kube-router](/docs/CNI/kube-router.md)
   * [Macvlan](/docs/CNI/macvlan.md)
   * [Multus](/docs/CNI/multus.md)
+  * [Weave](/docs/CNI/weave.md)
 * CRI
   * [Containerd](/docs/CRI/containerd.md)
   * [Cri-o](/docs/CRI/cri-o.md)
@@ -50,7 +52,9 @@
   * [Test Cases](/docs/developers/test_cases.md)
   * [Vagrant](/docs/developers/vagrant.md)
 * External Storage Provisioners
+  * [Cephfs Provisioner](/docs/external_storage_provisioners/cephfs_provisioner.md)
   * [Local Volume Provisioner](/docs/external_storage_provisioners/local_volume_provisioner.md)
+  * [Rbd Provisioner](/docs/external_storage_provisioners/rbd_provisioner.md)
   * [Scheduler Plugins](/docs/external_storage_provisioners/scheduler_plugins.md)
 * Getting Started
   * [Comparisons](/docs/getting_started/comparisons.md)

docs/advanced/arch.md

@@ -9,6 +9,7 @@ The following table shows the impact of the CPU architecture on compatible featu
 | kube_network_plugin | amd64 | arm64 | amd64 + arm64 |
 |---------------------|-------|-------|---------------|
 | Calico              | Y     | Y     | Y             |
+| Weave               | Y     | Y     | Y             |
 | Flannel             | Y     | N     | N             |
 | Canal               | Y     | N     | N             |
 | Cilium              | Y     | Y     | N             |

docs/advanced/proxy.md

@@ -1,6 +1,6 @@
 # Setting up Environment Proxy
 
-If you set http and https proxy, all nodes and loadbalancer will be excluded from proxy with generating no_proxy variable in `roles/kubespray_defaults/tasks/no_proxy.yml`, if you have additional resources for exclude add them to `additional_no_proxy` variable. If you want fully override your `no_proxy` setting, then fill in just `no_proxy` and no nodes or loadbalancer addresses will be added to no_proxy.
+If you set http and https proxy, all nodes and loadbalancer will be excluded from proxy with generating no_proxy variable in `roles/kubespray-defaults/tasks/no_proxy.yml`, if you have additional resources for exclude add them to `additional_no_proxy` variable. If you want fully override your `no_proxy` setting, then fill in just `no_proxy` and no nodes or loadbalancer addresses will be added to no_proxy.
 
 ## Set proxy for http and https
 

docs/ansible/ansible.md

@@ -13,7 +13,7 @@ KUBESPRAYDIR=kubespray
 python3 -m venv $VENVDIR
 source $VENVDIR/bin/activate
 cd $KUBESPRAYDIR
-pip install -r requirements.txt
+pip install -U -r requirements.txt
 ```
 
 In case you have a similar message when installing the requirements:
@@ -32,7 +32,7 @@ Based on the table below and the available python version for your ansible host
 
 | Ansible Version | Python Version |
 |-----------------|----------------|
-| >= 2.17.3       | 3.10-3.12      |
+| >= 2.16.4       | 3.10-3.12      |
 
 ## Customize Ansible vars
 
@@ -62,9 +62,10 @@ The following tags are defined in playbooks:
 | aws-ebs-csi-driver             | Configuring csi driver: aws-ebs                       |
 | azure-csi-driver               | Configuring csi driver: azure                         |
 | bastion                        | Setup ssh config for bastion                          |
-| bootstrap_os                   | Anything related to host OS configuration             |
+| bootstrap-os                   | Anything related to host OS configuration             |
 | calico                         | Network plugin Calico                                 |
 | calico_rr                      | Configuring Calico route reflector                    |
+| cephfs-provisioner             | Configuring CephFS                                    |
 | cert-manager                   | Configuring certificate manager for K8s               |
 | cilium                         | Network plugin Cilium                                 |
 | cinder-csi-driver              | Configuring csi driver: cinder                        |
@@ -118,6 +119,7 @@ The following tags are defined in playbooks:
 | local-path-provisioner         | Configure External provisioner: local-path            |
 | local-volume-provisioner       | Configure External provisioner: local-volume          |
 | macvlan                        | Network plugin macvlan                                |
+| master (DEPRECATED)            | Deprecated - see `control-plane`                      |
 | metallb                        | Installing and configuring metallb                    |
 | metrics_server                 | Configuring metrics_server                            |
 | netchecker                     | Installing netchecker K8s app                         |
@@ -145,6 +147,7 @@ The following tags are defined in playbooks:
 | registry                       | Configuring local docker registry                     |
 | reset                          | Tasks running doing the node reset                    |
 | resolvconf                     | Configuring /etc/resolv.conf for hosts/apps           |
+| rbd-provisioner                | Configure External provisioner: rdb                   |
 | services                       | Remove services (etcd, kubelet etc...) when resetting |
 | snapshot                       | Enabling csi snapshot                                 |
 | snapshot-controller            | Configuring csi snapshot controller                   |
@@ -152,16 +155,21 @@ The following tags are defined in playbooks:
 | upgrade                        | Upgrading, f.e. container images/binaries             |
 | upload                         | Distributing images/binaries across hosts             |
 | vsphere-csi-driver             | Configuring csi driver: vsphere                       |
+| weave                          | Network plugin Weave                                  |
 | win_nodes                      | Running windows specific tasks                        |
 | youki                          | Configuring youki runtime                             |
 
+Note: Use the ``bash scripts/gen_tags.sh`` command to generate a list of all
+tags found in the codebase. New tags will be listed with the empty "Used for"
+field.
+
 ## Example commands
 
 Example command to filter and apply only DNS configuration tasks and skip
 everything else related to host OS configuration and downloading images of containers:
 
 ```ShellSession
-ansible-playbook -i inventory/sample/hosts.ini cluster.yml --tags preinstall,facts --skip-tags=download,bootstrap_os
+ansible-playbook -i inventory/sample/hosts.ini cluster.yml --tags preinstall,facts --skip-tags=download,bootstrap-os
 ```
 
 And this play only removes the K8s cluster DNS resolver IP from hosts' /etc/resolv.conf files:
@@ -200,11 +208,11 @@ You will then need to use [bind mounts](https://docs.docker.com/storage/bind-mou
 to access the inventory and SSH key in the container, like this:
 
 ```ShellSession
-git checkout v2.29.0
-docker pull quay.io/kubespray/kubespray:v2.29.0
+git checkout v2.27.0
+docker pull quay.io/kubespray/kubespray:v2.27.0
 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:v2.29.0 bash
+  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
 ```

docs/ansible/ansible_collection.md

@@ -2,13 +2,14 @@
 
 Kubespray can be installed as an [Ansible collection](https://docs.ansible.com/ansible/latest/user_guide/collections_using.html).
 
+## Requirements
+
+- An inventory file with the appropriate host groups. See the [README](../README.md#usage).
+- A `group_vars` directory. These group variables **need** to match the appropriate variable names under `inventory/local/group_vars`. See the [README](../README.md#usage).
+
 ## Usage
 
-1. Set up an inventory with the appropriate host groups and required group vars.
-   See also the documentation on [kubespray inventories](./inventory.md) and the
-   general ["Getting started" documentation](../getting_started/getting-started.md#building-your-own-inventory).
-
-2. Add Kubespray to your requirements.yml file
+1. Add Kubespray to your requirements.yml file
 
    ```yaml
    collections:
@@ -17,20 +18,20 @@ Kubespray can be installed as an [Ansible collection](https://docs.ansible.com/a
      version: master # use the appropriate tag or branch for the version you need
    ```
 
-3. Install your collection
+2. Install your collection
 
    ```ShellSession
    ansible-galaxy install -r requirements.yml
    ```
 
-4. Create a playbook to install your Kubernetes cluster
+3. Create a playbook to install your Kubernetes cluster
 
    ```yaml
    - name: Install Kubernetes
      ansible.builtin.import_playbook: kubernetes_sigs.kubespray.cluster
    ```
 
-5. Update INVENTORY and PLAYBOOK so that they point to your inventory file and the playbook you created above, and then install Kubespray
+4. Update INVENTORY and PLAYBOOK so that they point to your inventory file and the playbook you created above, and then install Kubespray
 
    ```ShellSession
    ansible-playbook -i INVENTORY --become --become-user=root PLAYBOOK

docs/ansible/vars.md

@@ -103,13 +103,13 @@ following default cluster parameters:
 
 * *kube_service_addresses_ipv6* - Subnet for cluster IPv6 IPs (default is ``fd85:ee78:d8a6:8607::1000/116``). Must not overlap with ``kube_pods_subnet_ipv6``.
 
-* *kube_service_subnets* - All service subnets separated by commas (default is a mix of ``kube_service_addresses`` and ``kube_service_addresses_ipv6`` depending on ``ipv4_stack`` and ``ipv6_stack`` options),
+* *kube_service_subnets* - All service subnets separated by commas (default is a mix of ``kube_service_addresses`` and ``kube_service_addresses_ipv6`` depending on ``ipv4_stack`` and ``ipv6_stacke`` options),
   for example ``10.233.0.0/18,fd85:ee78:d8a6:8607::1000/116`` for dual stack(ipv4_stack/ipv6_stack set to `true`).
   It is not recommended to change this variable directly.
 
 * *kube_pods_subnet_ipv6* - Subnet for Pod IPv6 IPs (default is ``fd85:ee78:d8a6:8607::1:0000/112``). Must not overlap with ``kube_service_addresses_ipv6``.
 
-* *kube_pods_subnets* - All pods subnets separated by commas (default is a mix of ``kube_pods_subnet`` and ``kube_pod_subnet_ipv6`` depending on ``ipv4_stack`` and ``ipv6_stack`` options),
+* *kube_pods_subnets* - All pods subnets separated by commas (default is a mix of ``kube_pods_subnet`` and ``kube_pod_subnet_ipv6`` depending on ``ipv4_stack`` and ``ipv6_stacke`` options),
   for example ``10.233.64.0/18,fd85:ee78:d8a6:8607::1:0000/112`` for dual stack(ipv4_stack/ipv6_stack set to `true`).
   It is not recommended to change this variable directly.
 
@@ -180,7 +180,7 @@ and ``kube_pods_subnet``, for example from the ``172.18.0.0/16``.
 
 IPv4 stack enable by *ipv4_stack* is set to ``true``, by default.
 IPv6 stack enable by *ipv6_stack* is set to ``false`` by default.
-This will use the default IPv4 and IPv6 subnets specified in the defaults file in the ``kubespray_defaults`` role, unless overridden of course. The default config will give you room for up to 256 nodes with 126 pods per node, and up to 4096 services.
+This will use the default IPv4 and IPv6 subnets specified in the defaults file in the ``kubespray-defaults`` role, unless overridden of course. The default config will give you room for up to 256 nodes with 126 pods per node, and up to 4096 services.
 Set both variables to ``true`` for Dual Stack mode.
 IPv4 has higher priority in Dual Stack mode(e.g. in variables `main_ip`, `main_access_ip` and other).
 You can also make IPv6 only clusters with ``false`` in *ipv4_stack*.

docs/cloud_controllers/openstack.md

@@ -73,7 +73,6 @@ The cloud provider is configured to have Octavia by default in Kubespray.
   external_openstack_lbaas_method: ROUND_ROBIN
   external_openstack_lbaas_provider: amphora
   external_openstack_lbaas_subnet_id: "Neutron subnet ID to create LBaaS VIP"
-  external_openstack_lbaas_member_subnet_id: "Neutron subnet ID on which to create the members of the load balancer"
   external_openstack_lbaas_network_id: "Neutron network ID to create LBaaS VIP"
   external_openstack_lbaas_manage_security_groups: false
   external_openstack_lbaas_create_monitor: false

docs/cloud_providers/equinix-metal.md

@@ -0,0 +1,100 @@
+# Equinix Metal
+
+Kubespray provides support for bare metal deployments using the [Equinix Metal](http://metal.equinix.com).
+Deploying upon bare metal allows Kubernetes to run at locations where an existing public or private cloud might not exist such
+as cell tower, edge collocated installations. The deployment mechanism used by Kubespray for Equinix Metal is similar to that used for
+AWS and OpenStack clouds (notably using Terraform to deploy the infrastructure). Terraform uses the Equinix Metal provider plugin
+to provision and configure hosts which are then used by the Kubespray Ansible playbooks. The Ansible inventory is generated
+dynamically from the Terraform state file.
+
+## Local Host Configuration
+
+To perform this installation, you will need a localhost to run Terraform/Ansible (laptop, VM, etc) and an account with Equinix Metal.
+In this example, we are provisioning a m1.large CentOS7 OpenStack VM as the localhost for the Kubernetes installation.
+You'll need Ansible, Git, and PIP.
+
+```bash
+sudo yum install epel-release
+sudo yum install ansible
+sudo yum install git
+sudo yum install python-pip
+```
+
+## Playbook SSH Key
+
+An SSH key is needed by Kubespray/Ansible to run the playbooks.
+This key is installed into the bare metal hosts during the Terraform deployment.
+You can generate a key new key or use an existing one.
+
+```bash
+ssh-keygen -f ~/.ssh/id_rsa
+```
+
+## Install Terraform
+
+Terraform is required to deploy the bare metal infrastructure. The steps below are for installing on CentOS 7.
+[More terraform installation options are available.](https://learn.hashicorp.com/terraform/getting-started/install.html)
+
+Grab the latest version of Terraform and install it.
+
+```bash
+echo "https://releases.hashicorp.com/terraform/$(curl -s https://checkpoint-api.hashicorp.com/v1/check/terraform | jq -r -M '.current_version')/terraform_$(curl -s https://checkpoint-api.hashicorp.com/v1/check/terraform | jq -r -M '.current_version')_linux_amd64.zip"
+sudo yum install unzip
+sudo unzip terraform_0.14.10_linux_amd64.zip -d /usr/local/bin/
+```
+
+## Download Kubespray
+
+Pull over Kubespray and setup any required libraries.
+
+```bash
+git clone https://github.com/kubernetes-sigs/kubespray
+cd kubespray
+```
+
+## Install Ansible
+
+Install Ansible according to [Ansible installation guide](/docs/ansible/ansible.md#installing-ansible)
+
+## Cluster Definition
+
+In this example, a new cluster called "alpha" will be created.
+
+```bash
+cp -LRp contrib/terraform/packet/sample-inventory inventory/alpha
+cd inventory/alpha/
+ln -s ../../contrib/terraform/packet/hosts
+```
+
+Details about the cluster, such as the name, as well as the authentication tokens and project ID
+for Equinix Metal need to be defined. To find these values see [Equinix Metal API Accounts](https://metal.equinix.com/developers/docs/accounts/).
+
+```bash
+vi cluster.tfvars
+```
+
+* cluster_name = alpha
+* packet_project_id = ABCDEFGHIJKLMNOPQRSTUVWXYZ123456
+* public_key_path = 12345678-90AB-CDEF-GHIJ-KLMNOPQRSTUV
+
+## Deploy Bare Metal Hosts
+
+Initializing Terraform will pull down any necessary plugins/providers.
+
+```bash
+terraform init ../../contrib/terraform/packet/
+```
+
+Run Terraform to deploy the hardware.
+
+```bash
+terraform apply -var-file=cluster.tfvars ../../contrib/terraform/packet
+```
+
+## Run Kubespray Playbooks
+
+With the bare metal infrastructure deployed, Kubespray can now install Kubernetes and setup the cluster.
+
+```bash
+ansible-playbook --become -i inventory/alpha/hosts cluster.yml
+```

docs/developers/ci-setup.md

@@ -2,14 +2,19 @@
 
 ## Pipeline
 
-See [.gitlab-ci.yml](/.gitlab-ci.yml) and the included files for an overview.
+1. build: build a docker image to be used in the pipeline
+2. unit-tests: fast jobs for fast feedback (linting, etc...)
+3. deploy-part1: small number of jobs to test if the PR works with default settings
+4. deploy-extended: slow jobs testing different platforms, OS, settings, CNI, etc...
+5. deploy-extended: very slow jobs (upgrades, etc...)
 
 ## Runners
 
-Kubespray has 2 types of GitLab runners, both deployed  on the Kubespray CI cluster (hosted on Oracle Cloud Infrastucture):
+Kubespray has 3 types of GitLab runners:
 
-- pods: use the [gitlab-ci kubernetes executor](https://docs.gitlab.com/runner/executors/kubernetes/)
-- vagrant: custom executor running in pods with access to the libvirt socket on the nodes
+- packet runners: used for E2E jobs (usually long), running on Equinix Metal (ex-packet), on kubevirt managed VMs
+- light runners: used for short lived jobs, running on Equinix Metal (ex-packet), as managed pods
+- auto scaling runners (managed via docker-machine on Equinix Metal): used for on-demand resources, see [GitLab docs](https://docs.gitlab.com/runner/configuration/autoscale.html) for more info
 
 ## Vagrant
 
@@ -17,17 +22,18 @@ Vagrant jobs are using the [quay.io/kubespray/vagrant](/test-infra/vagrant-docke
 
 ## CI Variables
 
-In CI we have a [set of extra vars](/test/common_vars.yml) we use to ensure greater success of our CI jobs and avoid throttling by various APIs we depend on.
+In CI we have a set of overrides we use to ensure greater success of our CI jobs and avoid throttling by various APIs we depend on. See:
 
-## CI clusters
+- [Docker mirrors](/tests/common/_docker_hub_registry_mirror.yml)
+- [Test settings](/tests/common/_kubespray_test_settings.yml)
 
-DISCLAIMER: The following information is not fully up to date, in particular, the CI cluster is now on Oracle Cloud Infrastcture, not Equinix.
+## CI Environment
 
-The cluster is deployed with kubespray itself and maintained by the kubespray maintainers.
+The CI packet and light runners are deployed on a kubernetes cluster on Equinix Metal. The cluster is deployed with kubespray itself and maintained by the kubespray maintainers.
 
 The following files are used for that inventory:
 
-### cluster.tfvars (OBSOLETE: this section is no longer accurate)
+### cluster.tfvars
 
 ```ini
 # your Kubernetes cluster name here
@@ -160,6 +166,18 @@ kube_feature_gates:
 
 This section documents additional files used to complete a deployment of the kubespray CI, these files sit on the control-plane node and assume a working kubernetes cluster.
 
+### /root/nscleanup.sh
+
+```bash
+#!/bin/bash
+
+kubectl=/usr/local/bin/kubectl
+
+$kubectl get ns | grep -P "(\d.+-\d.+)" | awk 'match($3,/[0-9]+d/) {print $1}' | xargs -r $kubectl delete ns
+$kubectl get ns | grep -P "(\d.+-\d.+)" | awk 'match($3,/[3-9]+h/) {print $1}' | xargs -r $kubectl delete ns
+$kubectl get ns | grep Terminating | awk '{print $1}' | xargs -i $kubectl delete vmi/instance-1 vmi/instance-0 vmi/instance-2 -n {} --force --grace-period=0 &
+```
+
 ### /root/path-calico.sh
 
 ```bash

docs/developers/ci.md

@@ -6,52 +6,55 @@ To generate this Matrix run `./tests/scripts/md-table/main.py`
 
 | OS / CNI | calico | cilium | custom_cni | flannel | kube-ovn | kube-router | macvlan |
 |---| --- | --- | --- | --- | --- | --- | --- |
+almalinux8 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 almalinux9 |  :white_check_mark: | :x: | :x: | :x: | :white_check_mark: | :x: | :x: |
 amazon |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 debian11 |  :white_check_mark: | :x: | :white_check_mark: | :x: | :x: | :x: | :white_check_mark: |
 debian12 |  :white_check_mark: | :white_check_mark: | :white_check_mark: | :x: | :x: | :x: | :x: |
-debian13 |  :white_check_mark: | :white_check_mark: | :x: | :x: | :x: | :x: | :x: |
 fedora39 |  :white_check_mark: | :x: | :x: | :x: | :x: | :white_check_mark: | :x: |
 fedora40 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
-flatcar4081 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 openeuler24 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
+opensuse15 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
+rockylinux8 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 rockylinux9 |  :white_check_mark: | :white_check_mark: | :x: | :x: | :x: | :x: | :x: |
-ubuntu20 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
+ubuntu20 |  :white_check_mark: | :white_check_mark: | :x: | :white_check_mark: | :x: | :white_check_mark: | :x: |
 ubuntu22 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
-ubuntu24 |  :white_check_mark: | :white_check_mark: | :x: | :white_check_mark: | :x: | :white_check_mark: | :x: |
+ubuntu24 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 
 ## crio
 
 | OS / CNI | calico | cilium | custom_cni | flannel | kube-ovn | kube-router | macvlan |
 |---| --- | --- | --- | --- | --- | --- | --- |
+almalinux8 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 almalinux9 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 amazon |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 debian11 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 debian12 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
-debian13 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 fedora39 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
-fedora40 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
-flatcar4081 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
+fedora40 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 openeuler24 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
+opensuse15 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
+rockylinux8 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 rockylinux9 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
-ubuntu20 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
-ubuntu22 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
+ubuntu20 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
+ubuntu22 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 ubuntu24 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 
 ## docker
 
 | OS / CNI | calico | cilium | custom_cni | flannel | kube-ovn | kube-router | macvlan |
 |---| --- | --- | --- | --- | --- | --- | --- |
+almalinux8 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 almalinux9 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 amazon |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 debian11 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 debian12 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
-debian13 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 fedora39 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 fedora40 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
-flatcar4081 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 openeuler24 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
+opensuse15 |  :x: | :white_check_mark: | :x: | :x: | :x: | :x: | :x: |
+rockylinux8 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
 rockylinux9 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
-ubuntu20 |  :x: | :x: | :x: | :x: | :x: | :x: | :x: |
+ubuntu20 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 ubuntu22 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
 ubuntu24 |  :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |

docs/external_storage_provisioners/cephfs_provisioner.md

@@ -0,0 +1,73 @@
+# CephFS Volume Provisioner for Kubernetes 1.5+
+
+[![Docker Repository on Quay](https://quay.io/repository/external_storage/cephfs-provisioner/status "Docker Repository on Quay")](https://quay.io/repository/external_storage/cephfs-provisioner)
+
+Using Ceph volume client
+
+## Development
+
+Compile the provisioner
+
+``` console
+make
+```
+
+Make the container image and push to the registry
+
+``` console
+make push
+```
+
+## Test instruction
+
+- Start Kubernetes local cluster
+
+See [Kubernetes](https://kubernetes.io/)
+
+- Create a Ceph admin secret
+
+``` bash
+ceph auth get client.admin 2>&1 |grep "key = " |awk '{print  $3'} |xargs echo -n > /tmp/secret
+kubectl create ns cephfs
+kubectl create secret generic ceph-secret-admin --from-file=/tmp/secret --namespace=cephfs
+```
+
+- Start CephFS provisioner
+
+The following example uses `cephfs-provisioner-1` as the identity for the instance and assumes kubeconfig is at `/root/.kube`. The identity should remain the same if the provisioner restarts. If there are multiple provisioners, each should have a different identity.
+
+``` bash
+docker run -ti -v /root/.kube:/kube -v /var/run/kubernetes:/var/run/kubernetes --privileged --net=host cephfs-provisioner /usr/local/bin/cephfs-provisioner -master=http://127.0.0.1:8080 -kubeconfig=/kube/config -id=cephfs-provisioner-1
+```
+
+Alternatively, deploy it in kubernetes, see [deployment](deploy/README.md).
+
+- Create a CephFS Storage Class
+
+Replace Ceph monitor's IP in [example class](example/class.yaml) with your own and create storage class:
+
+``` bash
+kubectl create -f example/class.yaml
+```
+
+- Create a claim
+
+``` bash
+kubectl create -f example/claim.yaml
+```
+
+- Create a Pod using the claim
+
+``` bash
+kubectl create -f example/test-pod.yaml
+```
+
+## Known limitations
+
+- Kernel CephFS doesn't work with SELinux, setting SELinux label in Pod's securityContext will not work.
+- Kernel CephFS doesn't support quota or capacity, capacity requested by PVC is not enforced or validated.
+- Currently each Ceph user created by the provisioner has `allow r` MDS cap to permit CephFS mount.
+
+## Acknowledgement
+
+Inspired by CephFS Manila provisioner and conversation with John Spray

docs/external_storage_provisioners/rbd_provisioner.md

@@ -0,0 +1,79 @@
+# RBD Volume Provisioner for Kubernetes 1.5+
+
+`rbd-provisioner` is an out-of-tree dynamic provisioner for Kubernetes 1.5+.
+You can use it quickly & easily deploy ceph RBD storage that works almost
+anywhere.
+
+It works just like in-tree dynamic provisioner. For more information on how
+dynamic provisioning works, see [the docs](https://kubernetes.io/docs/concepts/storage/persistent-volumes/)
+or [this blog post](http://blog.kubernetes.io/2016/10/dynamic-provisioning-and-storage-in-kubernetes.html).
+
+## Development
+
+Compile the provisioner
+
+```console
+make
+```
+
+Make the container image and push to the registry
+
+```console
+make push
+```
+
+## Test instruction
+
+* Start Kubernetes local cluster
+
+See [Kubernetes](https://kubernetes.io/).
+
+* Create a Ceph admin secret
+
+```bash
+ceph auth get client.admin 2>&1 |grep "key = " |awk '{print  $3'} |xargs echo -n > /tmp/secret
+kubectl create secret generic ceph-admin-secret --from-file=/tmp/secret --namespace=kube-system
+```
+
+* Create a Ceph pool and a user secret
+
+```bash
+ceph osd pool create kube 8 8
+ceph auth add client.kube mon 'allow r' osd 'allow rwx pool=kube'
+ceph auth get-key client.kube > /tmp/secret
+kubectl create secret generic ceph-secret --from-file=/tmp/secret --namespace=kube-system
+```
+
+* Start RBD provisioner
+
+The following example uses `rbd-provisioner-1` as the identity for the instance and assumes kubeconfig is at `/root/.kube`. The identity should remain the same if the provisioner restarts. If there are multiple provisioners, each should have a different identity.
+
+```bash
+docker run -ti -v /root/.kube:/kube -v /var/run/kubernetes:/var/run/kubernetes --privileged --net=host quay.io/external_storage/rbd-provisioner /usr/local/bin/rbd-provisioner -master=http://127.0.0.1:8080 -kubeconfig=/kube/config -id=rbd-provisioner-1
+```
+
+Alternatively, deploy it in kubernetes, see [deployment](deploy/README.md).
+
+* Create a RBD Storage Class
+
+Replace Ceph monitor's IP in [examples/class.yaml](examples/class.yaml) with your own and create storage class:
+
+```bash
+kubectl create -f examples/class.yaml
+```
+
+* Create a claim
+
+```bash
+kubectl create -f examples/claim.yaml
+```
+
+* Create a Pod using the claim
+
+```bash
+kubectl create -f examples/test-pod.yaml
+```
+
+## Acknowledgements
+
+* This provisioner is extracted from [Kubernetes core](https://github.com/kubernetes/kubernetes) with some modifications for this project.

docs/external_storage_provisioners/scheduler_plugins.md

@@ -7,7 +7,7 @@ The kube-scheduler binary includes a list of plugins:
 - [CapacityScheduling](https://github.com/kubernetes-sigs/scheduler-plugins/tree/master/pkg/capacityscheduling) [Beta]
 - [CoScheduling](https://github.com/kubernetes-sigs/scheduler-plugins/tree/master/pkg/coscheduling) [Beta]
 - [NodeResources](https://github.com/kubernetes-sigs/scheduler-plugins/tree/master/pkg/noderesources) [Beta]
-- [NodeResourceTopology](https://github.com/kubernetes-sigs/scheduler-plugins/blob/master/pkg/noderesourcetopology/README.md) [Beta]
+- [NodeResouceTopology](https://github.com/kubernetes-sigs/scheduler-plugins/blob/master/pkg/noderesourcetopology/README.md) [Beta]
 - [PreemptionToleration](https://github.com/kubernetes-sigs/scheduler-plugins/blob/master/pkg/preemptiontoleration/README.md) [Alpha]
 - [Trimaran](https://github.com/kubernetes-sigs/scheduler-plugins/blob/master/pkg/trimaran/README.md) [Alpha]
 - [NetworkAware](https://github.com/kubernetes-sigs/scheduler-plugins/blob/master/pkg/networkaware/README.md) [Sample]

docs/getting_started/setting-up-your-first-cluster.md

@@ -61,12 +61,12 @@ gcloud compute networks subnets create kubernetes \
 #### Firewall Rules
 
 Create a firewall rule that allows internal communication across all protocols.
-It is important to note that the vxlan (udp) protocol has to be allowed in order for
+It is important to note that the vxlan protocol has to be allowed in order for
 the calico (see later) networking plugin to work.
 
 ```ShellSession
 gcloud compute firewall-rules create kubernetes-the-kubespray-way-allow-internal \
-  --allow tcp,udp,icmp \
+  --allow tcp,udp,icmp,vxlan \
   --network kubernetes-the-kubespray-way \
   --source-ranges 10.240.0.0/24
 ```
@@ -88,7 +88,7 @@ cluster.
 
 ### Compute Instances
 
-The compute instances in this lab will be provisioned using [Ubuntu Server](https://www.ubuntu.com/server) 24.04.
+The compute instances in this lab will be provisioned using [Ubuntu Server](https://www.ubuntu.com/server) 18.04.
 Each compute instance will be provisioned with a fixed private IP address and
  a public IP address (that can be fixed - see [guide](https://cloud.google.com/compute/docs/ip-addresses/reserve-static-external-ip-address)).
 Using fixed public IP addresses has the advantage that our cluster node
@@ -103,7 +103,7 @@ for i in 0 1 2; do
     --async \
     --boot-disk-size 200GB \
     --can-ip-forward \
-    --image-family ubuntu-2404-lts-amd64 \
+    --image-family ubuntu-1804-lts \
     --image-project ubuntu-os-cloud \
     --machine-type e2-standard-2 \
     --private-network-ip 10.240.0.1${i} \
@@ -124,7 +124,7 @@ for i in 0 1 2; do
     --async \
     --boot-disk-size 200GB \
     --can-ip-forward \
-    --image-family ubuntu-2404-lts-amd64 \
+    --image-family ubuntu-1804-lts \
     --image-project ubuntu-os-cloud \
     --machine-type e2-standard-2 \
     --private-network-ip 10.240.0.2${i} \

docs/ingress/ingress_nginx.md

@@ -35,7 +35,7 @@ kubectl create clusterrolebinding cluster-admin-binding \
 The following **Mandatory Command** is required for all deployments except for AWS. See below for the AWS version.
 
 ```console
-kubectl apply -f https://raw.githubusercontent.com/kubernetes/ingress-nginx/controller-v1.13.3/deploy/static/provider/cloud/deploy.yaml
+kubectl apply -f https://raw.githubusercontent.com/kubernetes/ingress-nginx/controller-v1.12.0/deploy/static/provider/cloud/deploy.yaml
 ```
 
 ### Provider Specific Steps

docs/operating_systems/bootstrap-os.md

@@ -1,4 +1,4 @@
-# bootstrap_os
+# bootstrap-os
 
 Bootstrap an Ansible host to be able to run Ansible modules.
 
@@ -48,8 +48,8 @@ Remember to disable fact gathering since Python might not be present on hosts.
 - hosts: all
   gather_facts: false  # not all hosts might be able to run modules yet
   roles:
-    - kubespray_defaults
-    - bootstrap_os
+    - kubespray-defaults
+    - bootstrap-os
 ```
 
 ## License

docs/operations/cgroups.md

@@ -30,6 +30,11 @@ kube_memory_reserved: 256Mi
 kube_cpu_reserved: 100m
 # kube_ephemeral_storage_reserved: 2Gi
 # kube_pid_reserved: "1000"
+# Reservation for master hosts
+kube_master_memory_reserved: 512Mi
+kube_master_cpu_reserved: 200m
+# kube_master_ephemeral_storage_reserved: 2Gi
+# kube_master_pid_reserved: "1000"
 
 # Set to true to reserve resources for system daemons
 system_reserved: true
@@ -39,6 +44,11 @@ system_memory_reserved: 512Mi
 system_cpu_reserved: 500m
 # system_ephemeral_storage_reserved: 2Gi
 # system_pid_reserved: "1000"
+# Reservation for master hosts
+system_master_memory_reserved: 256Mi
+system_master_cpu_reserved: 250m
+# system_master_ephemeral_storage_reserved: 2Gi
+# system_master_pid_reserved: "1000"
 ```
 
 After the setup, the cgroups hierarchy is as follows:

docs/operations/hardening.md

@@ -18,6 +18,8 @@ The **kubernetes** version should be at least `v1.23.6` to have all the most rec
 
 ## kube-apiserver
 authorization_modes: ['Node', 'RBAC']
+# AppArmor-based OS
+# kube_apiserver_feature_gates: ['AppArmor=true']
 kube_apiserver_request_timeout: 120s
 kube_apiserver_service_account_lookup: true
 
@@ -75,17 +77,17 @@ remove_anonymous_access: true
 ## kube-controller-manager
 kube_controller_manager_bind_address: 127.0.0.1
 kube_controller_terminated_pod_gc_threshold: 50
+# AppArmor-based OS
+# kube_controller_feature_gates: ["RotateKubeletServerCertificate=true", "AppArmor=true"]
 kube_controller_feature_gates: ["RotateKubeletServerCertificate=true"]
 
 ## kube-scheduler
 kube_scheduler_bind_address: 127.0.0.1
+# AppArmor-based OS
+# kube_scheduler_feature_gates: ["AppArmor=true"]
 
 ## etcd
-# Running etcd (on dedicated hosts) outside the Kubernetes cluster is the most secure deployment option,
-# as it isolates etcd from the cluster's CNI network and removes direct pod-level attack vectors.
-# This approach prevents RBAC misconfigurations that potentially compromise etcd,
-# creating an additional security boundary that protects the cluster's critical state store.
-etcd_deployment_type: host
+etcd_deployment_type: kubeadm
 
 ## kubelet
 kubelet_authorization_mode_webhook: true
@@ -100,8 +102,6 @@ kubelet_make_iptables_util_chains: true
 kubelet_feature_gates: ["RotateKubeletServerCertificate=true"]
 kubelet_seccomp_default: true
 kubelet_systemd_hardening: true
-# To disable kubelet's staticPodPath (for nodes that don't use static pods like worker nodes)
-kubelet_static_pod_path: ""
 # In case you have multiple interfaces in your
 # control plane nodes and you want to specify the right
 # IP addresses, kubelet_secure_addresses allows you
@@ -126,8 +126,9 @@ Let's take a deep look to the resultant **kubernetes** configuration:
 * The `encryption-provider-config` provide encryption at rest. This means that the `kube-apiserver` encrypt data that is going to be stored before they reach `etcd`. So the data is completely unreadable from `etcd` (in case an attacker is able to exploit this).
 * The `rotateCertificates` in `KubeletConfiguration` is set to `true` along with `serverTLSBootstrap`. This could be used in alternative to `tlsCertFile` and `tlsPrivateKeyFile` parameters. Additionally it automatically generates certificates by itself. By default the CSRs are approved automatically via [kubelet-csr-approver](https://github.com/postfinance/kubelet-csr-approver). You can customize approval configuration by modifying Helm values via `kubelet_csr_approver_values`.
   See <https://kubernetes.io/docs/reference/access-authn-authz/kubelet-tls-bootstrapping/> for more information on the subject.
+* If you are installing **kubernetes** in an AppArmor-based OS (eg. Debian/Ubuntu) you can enable the `AppArmor` feature gate uncommenting the lines with the comment `# AppArmor-based OS` on top.
 * The `kubelet_systemd_hardening`, both with `kubelet_secure_addresses` setup a minimal firewall on the system. To better understand how these variables work, here's an explanatory image:
-  ![kubelet hardening](../img/kubelet-hardening.png)
+  ![kubelet hardening](img/kubelet-hardening.png)
 
 Once you have the file properly filled, you can run the **Ansible** command to start the installation:
 

docs/operations/nodes.md

@@ -2,6 +2,58 @@
 
 Modified from [comments in #3471](https://github.com/kubernetes-sigs/kubespray/issues/3471#issuecomment-530036084)
 
+## Limitation: Removal of first kube_control_plane and etcd-master
+
+Currently you can't remove the first node in your kube_control_plane and etcd-master list. If you still want to remove this node you have to:
+
+### 1) Change order of current control planes
+
+Modify the order of your control plane list by pushing your first entry to any other position. E.g. if you want to remove `node-1` of the following example:
+
+```yaml
+  children:
+    kube_control_plane:
+      hosts:
+        node-1:
+        node-2:
+        node-3:
+    kube_node:
+      hosts:
+        node-1:
+        node-2:
+        node-3:
+    etcd:
+      hosts:
+        node-1:
+        node-2:
+        node-3:
+```
+
+change your inventory to:
+
+```yaml
+  children:
+    kube_control_plane:
+      hosts:
+        node-2:
+        node-3:
+        node-1:
+    kube_node:
+      hosts:
+        node-2:
+        node-3:
+        node-1:
+    etcd:
+      hosts:
+        node-2:
+        node-3:
+        node-1:
+```
+
+## 2) Upgrade the cluster
+
+run `upgrade-cluster.yml` or `cluster.yml`. Now you are good to go on with the removal.
+
 ## Adding/replacing a worker node
 
 This should be the easiest.
@@ -48,74 +100,40 @@ crictl ps | grep nginx-proxy | awk '{print $1}' | xargs crictl stop
 With the old node still in the inventory, run `remove-node.yml`. You need to pass `-e node=NODE_NAME` to the playbook to limit the execution to the node being removed.
 If the node you want to remove is not online, you should add `reset_nodes=false` and `allow_ungraceful_removal=true` to your extra-vars.
 
-## Adding/Removal of first `kube_control_plane` and etcd-master
+## Replacing a first control plane node
 
-Currently you can't remove the first node in your `kube_control_plane` and etcd-master list. If you still want to remove this node you have to:
+### 1) Change control plane nodes order in inventory
 
-### 1) Change order of current control planes
+from
 
-Modify the order of your control plane list by pushing your first entry to any other position. E.g. if you want to remove `node-1` of the following example:
-
-```yaml
-all:
-  hosts:
-  children:
-    kube_control_plane:
-      hosts:
-        node-1:
-        node-2:
-        node-3:
-    kube_node:
-      hosts:
-        node-1:
-        node-2:
-        node-3:
-    etcd:
-      hosts:
-        node-1:
-        node-2:
-        node-3:
+```ini
+[kube_control_plane]
+ node-1
+ node-2
+ node-3
 ```
 
-change your inventory to:
+to
 
-```yaml
-all:
-  hosts:
-  children:
-    kube_control_plane:
-      hosts:
-        node-2:
-        node-3:
-        node-1:
-    kube_node:
-      hosts:
-        node-2:
-        node-3:
-        node-1:
-    etcd:
-      hosts:
-        node-2:
-        node-3:
-        node-1:
+```ini
+[kube_control_plane]
+ node-2
+ node-3
+ node-1
 ```
 
-### 2) Upgrade the cluster
-
-run `upgrade-cluster.yml` or `cluster.yml`. Now you are good to go on with the removal.
-
-### 3) Remove old first control plane node from cluster
+### 2) Remove old first control plane node from cluster
 
 With the old node still in the inventory, run `remove-node.yml`. You need to pass `-e node=node-1` to the playbook to limit the execution to the node being removed.
 If the node you want to remove is not online, you should add `reset_nodes=false` and `allow_ungraceful_removal=true` to your extra-vars.
 
-### 4) Edit cluster-info configmap in kube-public namespace
+### 3) Edit cluster-info configmap in kube-public namespace
 
 `kubectl  edit cm -n kube-public cluster-info`
 
 Change ip of old kube_control_plane node with ip of live kube_control_plane node (`server` field). Also, update `certificate-authority-data` field if you changed certs.
 
-### 5) Add new control plane node
+### 4) Add new control plane node
 
 Update inventory (if needed)
 

docs/operations/offline-environment.md

@@ -22,45 +22,6 @@ Then you need to setup the following services on your offline environment:
 You can get artifact lists with [generate_list.sh](/contrib/offline/generate_list.sh) script.
 In addition, you can find some tools for offline deployment under [contrib/offline](/contrib/offline/README.md).
 
-## Access Control
-
-### Note: access controlled files_repo
-
-To specify a username and password for "{{ files_repo }}", used to download the binaries, you can use url-encoding. Be aware that the Boolean `unsafe_show_logs` will show these credentials when `roles/download/tasks/download_file.yml` runs the task "Download_file | Show url of file to download". You can disable that Boolean in a job-template when running AWX/AAP/Semaphore.
-
-```yaml
-files_repo_host: example.com
-files_repo_path: /repo
-files_repo_user: download
-files_repo_pass: !vault |
-          $ANSIBLE_VAULT;1.1;AES256
-          61663232643236353864663038616361373739613338623338656434386662363539613462626661
-          6435333438313034346164313631303534346564316361370a306661393232626364376436386439
-          64653965663965356137333436616536643132336630313235333232336661373761643766356366
-          6232353233386534380a373262313634613833623537626132633033373064336261383166323230
-          3164
-files_repo: "https://{{ files_repo_user ~ ':' ~ files_repo_pass ~ '@' ~ files_repo_host ~ files_repo_path }}"
-```
-
-### Note: access controlled registry
-
-To specify a username and password for "{{ registry_host }}", used to download the container images, you can use url-encoding too.
-
-```yaml
-registry_pass: !vault |
-          $ANSIBLE_VAULT;1.1;AES256
-          61663232643236353864663038616361373739613338623338656434386662363539613462626661
-          6435333438313034346164313631303534346564316361370a306661393232626364376436386439
-          64653965663965356137333436616536643132336630313235333232336661373761643766356366
-          6232353233386534380a373262313634613833623537626132633033373064336261383166323230
-          3164
-
-containerd_registry_auth:
-  - registry: "{{ registry_host }}"
-    username: "{{ registry_user }}"
-    password: "{{ registry_pass }}"
-```
-
 ## Configure Inventory
 
 Once all artifacts are accessible from your internal network, **adjust** the following variables
@@ -74,23 +35,21 @@ docker_image_repo: "{{ registry_host }}"
 quay_image_repo: "{{ registry_host }}"
 github_image_repo: "{{ registry_host }}"
 
-local_path_provisioner_helper_image_repo: "{{ registry_host }}/busybox"
-kubeadm_download_url: "{{ files_repo }}/kubernetes/v{{ kube_version }}/kubeadm"
-kubectl_download_url: "{{ files_repo }}/kubernetes/v{{ kube_version }}/kubectl"
-kubelet_download_url: "{{ files_repo }}/kubernetes/v{{ kube_version }}/kubelet"
+kubeadm_download_url: "{{ files_repo }}/kubernetes/{{ kube_version }}/kubeadm"
+kubectl_download_url: "{{ files_repo }}/kubernetes/{{ kube_version }}/kubectl"
+kubelet_download_url: "{{ files_repo }}/kubernetes/{{ kube_version }}/kubelet"
 # etcd is optional if you **DON'T** use etcd_deployment=host
-etcd_download_url: "{{ files_repo }}/kubernetes/etcd/etcd-v{{ etcd_version }}-linux-{{ image_arch }}.tar.gz"
-cni_download_url: "{{ files_repo }}/kubernetes/cni/cni-plugins-linux-{{ image_arch }}-v{{ cni_version }}.tgz"
-crictl_download_url: "{{ files_repo }}/kubernetes/cri-tools/crictl-v{{ crictl_version }}-{{ ansible_system | lower }}-{{ image_arch }}.tar.gz"
+etcd_download_url: "{{ files_repo }}/kubernetes/etcd/etcd-{{ etcd_version }}-linux-{{ image_arch }}.tar.gz"
+cni_download_url: "{{ files_repo }}/kubernetes/cni/cni-plugins-linux-{{ image_arch }}-{{ cni_version }}.tgz"
+crictl_download_url: "{{ files_repo }}/kubernetes/cri-tools/crictl-{{ crictl_version }}-{{ ansible_system | lower }}-{{ image_arch }}.tar.gz"
 # If using Calico
-calicoctl_download_url: "{{ files_repo }}/kubernetes/calico/v{{ calico_ctl_version }}/calicoctl-linux-{{ image_arch }}"
+calicoctl_download_url: "{{ files_repo }}/kubernetes/calico/{{ calico_ctl_version }}/calicoctl-linux-{{ image_arch }}"
 # If using Calico with kdd
-calico_crds_download_url: "{{ files_repo }}/kubernetes/calico/v{{ calico_version }}.tar.gz"
+calico_crds_download_url: "{{ files_repo }}/kubernetes/calico/{{ calico_version }}.tar.gz"
 # Containerd
 containerd_download_url: "{{ files_repo }}/containerd-{{ containerd_version }}-linux-{{ image_arch }}.tar.gz"
 runc_download_url: "{{ files_repo }}/runc.{{ image_arch }}"
 nerdctl_download_url: "{{ files_repo }}/nerdctl-{{ nerdctl_version }}-{{ ansible_system | lower }}-{{ image_arch }}.tar.gz"
-get_helm_url: "{{ files_repo }}/get.helm.sh"
 # Insecure registries for containerd
 containerd_registries_mirrors:
   - prefix: "{{ registry_addr }}"
@@ -136,7 +95,7 @@ If you use the settings like the one above, you'll need to define in your invent
 
 * `registry_host`: Container image registry. If you _don't_ use the same repository path for the container images that
   the ones defined
-  in [kubesprays-defaults's role defaults](https://github.com/kubernetes-sigs/kubespray/blob/master/roles/kubespray_defaults/defaults/main/download.yml)
+  in [kubesprays-defaults's role defaults](https://github.com/kubernetes-sigs/kubespray/blob/master/roles/kubespray-defaults/defaults/main/download.yml)
   , you need to override the `*_image_repo` for these container images. If you want to make your life easier, use the
   same repository path, you won't have to override anything else.
 * `registry_addr`: Container image registry, but only have [domain or ip]:[port].

docs/operations/upgrades.md

@@ -13,7 +13,9 @@ versions. Here are all version vars for each component:
 * etcd_version
 * calico_version
 * calico_cni_version
+* weave_version
 * flannel_version
+* kubedns_version
 
 > **Warning**
 > [Attempting to upgrade from an older release straight to the latest release is unsupported and likely to break something](https://github.com/kubernetes-sigs/kubespray/issues/3849#issuecomment-451386515)
@@ -82,7 +84,7 @@ If you don't want to upgrade all nodes in one run, you can use `--limit` [patter
 Before using `--limit` run playbook `facts.yml` without the limit to refresh facts cache for all nodes:
 
 ```ShellSession
-ansible-playbook playbooks/facts.yml -b -i inventory/sample/hosts.ini
+ansible-playbook facts.yml -b -i inventory/sample/hosts.ini
 ```
 
 After this upgrade control plane and etcd groups [#5147](https://github.com/kubernetes-sigs/kubespray/issues/5147):
@@ -355,7 +357,7 @@ follows:
 * Containerd
 * etcd
 * kubelet and kube-proxy
-* network_plugin (such as Calico)
+* network_plugin (such as Calico or Weave)
 * kube-apiserver, kube-scheduler, and kube-controller-manager
 * Add-ons (such as KubeDNS)
 

extra_playbooks/migrate_openstack_provider.yml

@@ -12,7 +12,7 @@
   hosts: kube_control_plane[0]
   tasks:
     - name: Include kubespray-default variables
-      include_vars: ../roles/kubespray_defaults/defaults/main/main.yml
+      include_vars: ../roles/kubespray-defaults/defaults/main/main.yml
     - name: Copy get_cinder_pvs.sh to first control plane node
       copy:
         src: get_cinder_pvs.sh

extra_playbooks/upgrade-only-k8s.yml

@@ -14,7 +14,7 @@
   hosts: localhost
   gather_facts: false
   roles:
-    - { role: kubespray_defaults}
+    - { role: kubespray-defaults}
     - { role: bastion-ssh-config, tags: ["localhost", "bastion"]}
 
 - name: Bootstrap hosts OS for Ansible
@@ -22,18 +22,18 @@
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
   gather_facts: false
   vars:
-    # Need to disable pipelining for bootstrap_os as some systems have requiretty in sudoers set, which makes pipelining
-    # fail. bootstrap_os fixes this on these systems, so in later plays it can be enabled.
+    # Need to disable pipelining for bootstrap-os as some systems have requiretty in sudoers set, which makes pipelining
+    # fail. bootstrap-os fixes this on these systems, so in later plays it can be enabled.
     ansible_ssh_pipelining: false
   roles:
-    - { role: kubespray_defaults}
-    - { role: bootstrap_os, tags: bootstrap_os}
+    - { role: kubespray-defaults}
+    - { role: bootstrap-os, tags: bootstrap-os}
 
 - name: Preinstall
   hosts: k8s_cluster:etcd:calico_rr
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
   roles:
-    - { role: kubespray_defaults}
+    - { role: kubespray-defaults}
     - { role: kubernetes/preinstall, tags: preinstall }
 
 - name: Handle upgrades to control plane components first to maintain backwards compat.
@@ -41,7 +41,7 @@
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
   serial: 1
   roles:
-    - { role: kubespray_defaults}
+    - { role: kubespray-defaults}
     - { role: upgrade/pre-upgrade, tags: pre-upgrade }
     - { role: kubernetes/node, tags: node }
     - { role: kubernetes/control-plane, tags: master, upgrade_cluster_setup: true }
@@ -54,8 +54,8 @@
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
   serial: "{{ serial | default('20%') }}"
   roles:
-    - { role: kubespray_defaults}
+    - { role: kubespray-defaults}
     - { role: upgrade/pre-upgrade, tags: pre-upgrade }
     - { role: kubernetes/node, tags: node }
     - { role: upgrade/post-upgrade, tags: post-upgrade }
-    - { role: kubespray_defaults}
+    - { role: kubespray-defaults}

galaxy.yml

@@ -2,7 +2,7 @@
 namespace: kubernetes_sigs
 description: Deploy a production ready Kubernetes cluster
 name: kubespray
-version: 2.29.1
+version: 2.28.0
 readme: README.md
 authors:
   - The Kubespray maintainers (https://kubernetes.slack.com/channels/kubespray)

inventory/sample/group_vars/all/all.yml

@@ -57,7 +57,7 @@ loadbalancer_apiserver_healthcheck_port: 8081
 # https_proxy: ""
 # https_proxy_cert_file: ""
 
-## Refer to roles/kubespray_defaults/defaults/main/main.yml before modifying no_proxy
+## Refer to roles/kubespray-defaults/defaults/main/main.yml before modifying no_proxy
 # no_proxy: ""
 
 ## Some problems may occur when downloading files over https proxy due to ansible bug
@@ -115,9 +115,6 @@ no_proxy_exclude_workers: false
 # sysctl_file_path to add sysctl conf to
 # sysctl_file_path: "/etc/sysctl.d/99-sysctl.conf"
 
-# ignore sysctl errors about unknown keys
-# sysctl_ignore_unknown_keys: false
-
 ## Variables for webhook token auth https://kubernetes.io/docs/reference/access-authn-authz/authentication/#webhook-token-authentication
 kube_webhook_token_auth: false
 kube_webhook_token_auth_url_skip_tls_verify: false

inventory/sample/group_vars/all/containerd.yml

@@ -50,8 +50,6 @@
 #     - host: https://registry-1.docker.io
 #       capabilities: ["pull", "resolve"]
 #       skip_verify: false
-#       header:
-#         Authorization: "Basic XXX"
 
 # containerd_max_container_log_line_size: 16384
 

inventory/sample/group_vars/all/oci.yml

@@ -43,6 +43,7 @@
 #   ocid1.subnet.oc1.phx.aaaaaaaahuxrgvs65iwdz7ekwgg3l5gyah7ww5klkwjcso74u3e4i64hvtvq: ocid1.securitylist.oc1.iad.aaaaaaaaqti5jsfvyw6ejahh7r4okb2xbtuiuguswhs746mtahn72r7adt7q
 ## If oci_use_instance_principals is true, you do not need to set the region, tenancy, user, key, passphrase, or fingerprint
 # oci_use_instance_principals: false
+# oci_cloud_controller_version: 0.6.0
 ## If you would like to control OCI query rate limits for the controller
 # oci_rate_limit:
 #   rate_limit_qps_read:

inventory/sample/group_vars/all/offline.yml

@@ -18,9 +18,9 @@
 # quay_image_repo: "{{ registry_host }}"
 
 ## Kubernetes components
-# kubeadm_download_url: "{{ files_repo }}/dl.k8s.io/release/v{{ kube_version }}/bin/linux/{{ image_arch }}/kubeadm"
-# kubectl_download_url: "{{ files_repo }}/dl.k8s.io/release/v{{ kube_version }}/bin/linux/{{ image_arch }}/kubectl"
-# kubelet_download_url: "{{ files_repo }}/dl.k8s.io/release/v{{ kube_version }}/bin/linux/{{ image_arch }}/kubelet"
+# kubeadm_download_url: "{{ files_repo }}/dl.k8s.io/release/{{ kube_version }}/bin/linux/{{ image_arch }}/kubeadm"
+# kubectl_download_url: "{{ files_repo }}/dl.k8s.io/release/{{ kube_version }}/bin/linux/{{ image_arch }}/kubectl"
+# kubelet_download_url: "{{ files_repo }}/dl.k8s.io/release/{{ kube_version }}/bin/linux/{{ image_arch }}/kubelet"
 
 
 ## Two options - Override entire repository or override only a single binary.
@@ -33,24 +33,24 @@
 
 ## [Optional] 2 - Override a specific binary
 ## CNI Plugins
-# cni_download_url: "{{ files_repo }}/github.com/containernetworking/plugins/releases/download/v{{ cni_version }}/cni-plugins-linux-{{ image_arch }}-v{{ cni_version }}.tgz"
+# cni_download_url: "{{ files_repo }}/github.com/containernetworking/plugins/releases/download/{{ cni_version }}/cni-plugins-linux-{{ image_arch }}-{{ cni_version }}.tgz"
 
 ## cri-tools
-# crictl_download_url: "{{ files_repo }}/github.com/kubernetes-sigs/cri-tools/releases/download/v{{ crictl_version }}/crictl-v{{ crictl_version }}-{{ ansible_system | lower }}-{{ image_arch }}.tar.gz"
+# crictl_download_url: "{{ files_repo }}/github.com/kubernetes-sigs/cri-tools/releases/download/{{ crictl_version }}/crictl-{{ crictl_version }}-{{ ansible_system | lower }}-{{ image_arch }}.tar.gz"
 
 ## [Optional] etcd: only if you use etcd_deployment=host
-# etcd_download_url: "{{ files_repo }}/github.com/etcd-io/etcd/releases/download/v{{ etcd_version }}/etcd-v{{ etcd_version }}-linux-{{ image_arch }}.tar.gz"
+# etcd_download_url: "{{ files_repo }}/github.com/etcd-io/etcd/releases/download/{{ etcd_version }}/etcd-{{ etcd_version }}-linux-{{ image_arch }}.tar.gz"
 
 # [Optional] Calico: If using Calico network plugin
-# calicoctl_download_url: "{{ files_repo }}/github.com/projectcalico/calico/releases/download/v{{ calico_ctl_version }}/calicoctl-linux-{{ image_arch }}"
+# calicoctl_download_url: "{{ files_repo }}/github.com/projectcalico/calico/releases/download/{{ calico_ctl_version }}/calicoctl-linux-{{ image_arch }}"
 # [Optional] Calico with kdd: If using Calico network plugin with kdd datastore
-# calico_crds_download_url: "{{ files_repo }}/github.com/projectcalico/calico/archive/v{{ calico_version }}.tar.gz"
+# calico_crds_download_url: "{{ files_repo }}/github.com/projectcalico/calico/archive/{{ calico_version }}.tar.gz"
 
 # [Optional] Cilium: If using Cilium network plugin
-# ciliumcli_download_url: "{{ files_repo }}/github.com/cilium/cilium-cli/releases/download/v{{ cilium_cli_version }}/cilium-linux-{{ image_arch }}.tar.gz"
+# ciliumcli_download_url: "{{ files_repo }}/github.com/cilium/cilium-cli/releases/download/{{ cilium_cli_version }}/cilium-linux-{{ image_arch }}.tar.gz"
 
 # [Optional] helm: only if you set helm_enabled: true
-# helm_download_url: "{{ files_repo }}/get.helm.sh/helm-v{{ helm_version }}-linux-{{ image_arch }}.tar.gz"
+# helm_download_url: "{{ files_repo }}/get.helm.sh/helm-{{ helm_version }}-linux-{{ image_arch }}.tar.gz"
 
 # [Optional] crun: only if you set crun_enabled: true
 # crun_download_url: "{{ files_repo }}/github.com/containers/crun/releases/download/{{ crun_version }}/crun-{{ crun_version }}-linux-{{ image_arch }}"
@@ -62,13 +62,13 @@
 # cri_dockerd_download_url: "{{ files_repo }}/github.com/Mirantis/cri-dockerd/releases/download/v{{ cri_dockerd_version }}/cri-dockerd-{{ cri_dockerd_version }}.{{ image_arch }}.tgz"
 
 # [Optional] runc: if you set container_manager to containerd or crio
-# runc_download_url: "{{ files_repo }}/github.com/opencontainers/runc/releases/download/v{{ runc_version }}/runc.{{ image_arch }}"
+# runc_download_url: "{{ files_repo }}/github.com/opencontainers/runc/releases/download/{{ runc_version }}/runc.{{ image_arch }}"
 
 # [Optional] cri-o: only if you set container_manager: crio
 # crio_download_base: "download.opensuse.org/repositories/devel:kubic:libcontainers:stable"
 # crio_download_crio: "http://{{ crio_download_base }}:/cri-o:/"
-# crio_download_url: "{{ files_repo }}/storage.googleapis.com/cri-o/artifacts/cri-o.{{ image_arch }}.v{{ crio_version }}.tar.gz"
-# skopeo_download_url: "{{ files_repo }}/github.com/lework/skopeo-binary/releases/download/v{{ skopeo_version }}/skopeo-linux-{{ image_arch }}"
+# crio_download_url: "{{ files_repo }}/storage.googleapis.com/cri-o/artifacts/cri-o.{{ image_arch }}.{{ crio_version }}.tar.gz"
+# skopeo_download_url: "{{ files_repo }}/github.com/lework/skopeo-binary/releases/download/{{ skopeo_version }}/skopeo-linux-{{ image_arch }}"
 
 # [Optional] containerd: only if you set container_runtime: containerd
 # containerd_download_url: "{{ files_repo }}/github.com/containerd/containerd/releases/download/v{{ containerd_version }}/containerd-{{ containerd_version }}-linux-{{ image_arch }}.tar.gz"

inventory/sample/group_vars/all/openstack.yml

@@ -1,4 +1,5 @@
 ## When OpenStack is used, Cinder version can be explicitly specified if autodetection fails (Fixed in 1.9: https://github.com/kubernetes/kubernetes/issues/50461)
+# openstack_blockstorage_version: "v1/v2/auto (default)"
 # openstack_blockstorage_ignore_volume_az: yes
 ## When OpenStack is used, if LBaaSv2 is available you can enable it with the following 2 variables.
 # openstack_lbaas_enabled: True

inventory/sample/group_vars/all/vsphere.yml

@@ -7,6 +7,26 @@
 # external_vsphere_datacenter: "DATACENTER_name"
 # external_vsphere_kubernetes_cluster_id: "kubernetes-cluster-id"
 
+## Vsphere version where located VMs
+# external_vsphere_version: "6.7u3"
+
+## Tags for the external vSphere Cloud Provider images
+## registry.k8s.io/cloud-pv-vsphere/cloud-provider-vsphere
+# external_vsphere_cloud_controller_image_tag: "v1.31.0"
+## registry.k8s.io/csi-vsphere/syncer
+# vsphere_syncer_image_tag: "v3.3.1"
+## registry.k8s.io/sig-storage/csi-attacher
+# vsphere_csi_attacher_image_tag: "v3.4.0"
+## registry.k8s.io/csi-vsphere/driver
+# vsphere_csi_controller: "v3.3.1"
+## registry.k8s.io/sig-storage/livenessprobe
+# vsphere_csi_liveness_probe_image_tag: "v2.6.0"
+## registry.k8s.io/sig-storage/csi-provisioner
+# vsphere_csi_provisioner_image_tag: "v3.1.0"
+## registry.k8s.io/sig-storage/csi-resizer
+## makes sense only for vSphere version >=7.0
+# vsphere_csi_resizer_tag: "v1.3.0"
+
 ## To use vSphere CSI plugin to provision volumes set this value to true
 # vsphere_csi_enabled: true
 # vsphere_csi_controller_replicas: 1

inventory/sample/group_vars/etcd.yml

@@ -0,0 +1,38 @@
+---
+## Etcd auto compaction retention for mvcc key value store in hour
+# etcd_compaction_retention: 0
+
+## Set level of detail for etcd exported metrics, specify 'extensive' to include histogram metrics.
+# etcd_metrics: basic
+
+## Etcd is restricted by default to 512M on systems under 4GB RAM, 512MB is not enough for much more than testing.
+## Set this if your etcd nodes have less than 4GB but you want more RAM for etcd. Set to 0 for unrestricted RAM.
+## This value is only relevant when deploying etcd with `etcd_deployment_type: docker`
+# etcd_memory_limit: "512M"
+
+## Etcd has a default of 2G for its space quota. If you put a value in etcd_memory_limit which is less than
+## etcd_quota_backend_bytes, you may encounter out of memory terminations of the etcd cluster. Please check
+## etcd documentation for more information.
+# 8G is a suggested maximum size for normal environments and etcd warns at startup if the configured value exceeds it.
+# etcd_quota_backend_bytes: "2147483648"
+
+# Maximum client request size in bytes the server will accept.
+# etcd is designed to handle small key value pairs typical for metadata.
+# Larger requests will work, but may increase the latency of other requests
+# etcd_max_request_bytes: "1572864"
+
+### ETCD: disable peer client cert authentication.
+# This affects ETCD_PEER_CLIENT_CERT_AUTH variable
+# etcd_peer_client_auth: true
+
+## Enable distributed tracing
+## To enable this experimental feature, set the etcd_experimental_enable_distributed_tracing: true, along with the
+## etcd_experimental_distributed_tracing_sample_rate to choose how many samples to collect per million spans,
+## the default sampling rate is 0 https://etcd.io/docs/v3.5/op-guide/monitoring/#distributed-tracing
+# etcd_experimental_enable_distributed_tracing: false
+# etcd_experimental_distributed_tracing_sample_rate: 100
+# etcd_experimental_distributed_tracing_address: "localhost:4317"
+# etcd_experimental_distributed_tracing_service_name: etcd
+
+## The interval for etcd watch progress notify events
+# etcd_experimental_watch_progress_notify_interval: 5s

inventory/sample/group_vars/k8s_cluster/addons.yml

@@ -29,6 +29,7 @@ local_path_provisioner_enabled: false
 # local_path_provisioner_claim_root: /opt/local-path-provisioner/
 # local_path_provisioner_debug: false
 # local_path_provisioner_image_repo: "{{ docker_image_repo }}/rancher/local-path-provisioner"
+# local_path_provisioner_image_tag: "v0.0.24"
 # local_path_provisioner_helper_image_repo: "busybox"
 # local_path_provisioner_helper_image_tag: "latest"
 
@@ -64,8 +65,40 @@ local_volume_provisioner_enabled: false
 # csi snapshot namespace
 # snapshot_controller_namespace: kube-system
 
+# CephFS provisioner deployment
+cephfs_provisioner_enabled: false
+# cephfs_provisioner_namespace: "cephfs-provisioner"
+# cephfs_provisioner_cluster: ceph
+# cephfs_provisioner_monitors: "172.24.0.1:6789,172.24.0.2:6789,172.24.0.3:6789"
+# cephfs_provisioner_admin_id: admin
+# cephfs_provisioner_secret: secret
+# cephfs_provisioner_storage_class: cephfs
+# cephfs_provisioner_reclaim_policy: Delete
+# cephfs_provisioner_claim_root: /volumes
+# cephfs_provisioner_deterministic_names: true
+
+# RBD provisioner deployment
+rbd_provisioner_enabled: false
+# rbd_provisioner_namespace: rbd-provisioner
+# rbd_provisioner_replicas: 2
+# rbd_provisioner_monitors: "172.24.0.1:6789,172.24.0.2:6789,172.24.0.3:6789"
+# rbd_provisioner_pool: kube
+# rbd_provisioner_admin_id: admin
+# rbd_provisioner_secret_name: ceph-secret-admin
+# rbd_provisioner_secret: ceph-key-admin
+# rbd_provisioner_user_id: kube
+# rbd_provisioner_user_secret_name: ceph-secret-user
+# rbd_provisioner_user_secret: ceph-key-user
+# rbd_provisioner_user_secret_namespace: rbd-provisioner
+# rbd_provisioner_fs_type: ext4
+# rbd_provisioner_image_format: "2"
+# rbd_provisioner_image_features: layering
+# rbd_provisioner_storage_class: rbd
+# rbd_provisioner_reclaim_policy: Delete
+
 # Gateway API CRDs
 gateway_api_enabled: false
+# gateway_api_experimental_channel: false
 
 # Nginx ingress controller deployment
 ingress_nginx_enabled: false
@@ -147,6 +180,7 @@ cert_manager_enabled: false
 metallb_enabled: false
 metallb_speaker_enabled: "{{ metallb_enabled }}"
 metallb_namespace: "metallb-system"
+# metallb_version: 0.13.9
 # metallb_protocol: "layer2"
 # metallb_port: "7472"
 # metallb_memberlist_port: "7946"
@@ -208,6 +242,7 @@ metallb_namespace: "metallb-system"
 #             - pool2
 
 argocd_enabled: false
+# argocd_version: 2.14.5
 # argocd_namespace: argocd
 # Default password:
 #   - https://argo-cd.readthedocs.io/en/stable/getting_started/#4-login-using-the-cli
@@ -235,7 +270,6 @@ kube_vip_enabled: false
 # kube_vip_cp_detect: false
 # kube_vip_leasename: plndr-cp-lock
 # kube_vip_enable_node_labeling: false
-# kube_vip_lb_fwdmethod: local
 
 # Node Feature Discovery
 node_feature_discovery_enabled: false

inventory/sample/group_vars/k8s_cluster/k8s-cluster.yml

@@ -16,6 +16,9 @@ kube_token_dir: "{{ kube_config_dir }}/tokens"
 
 kube_api_anonymous_auth: true
 
+## Change this to use another Kubernetes version, e.g. a current beta release
+kube_version: 1.32.2
+
 # Where the binaries will be downloaded.
 # Note: ensure that you've enough disk space (about 1G)
 local_release_dir: "/tmp/releases"
@@ -62,7 +65,7 @@ credentials_dir: "{{ inventory_dir }}/credentials"
 # kube_webhook_authorization_url: https://...
 # kube_webhook_authorization_url_skip_tls_verify: false
 
-# Choose network plugin (cilium, calico, kube-ovn or flannel. Use cni for generic cni plugin)
+# Choose network plugin (cilium, calico, kube-ovn, weave or flannel. Use cni for generic cni plugin)
 # Can also be set to 'cloud', which lets the cloud provider setup appropriate routing
 kube_network_plugin: calico
 
@@ -346,7 +349,7 @@ event_ttl_duration: "1h0m0s"
 ## Automatically renew K8S control plane certificates on first Monday of each month
 auto_renew_certificates: false
 # First Monday of each month
-# auto_renew_certificates_systemd_calendar: "Mon *-*-1,2,3,4,5,6,7 03:00:00"
+# auto_renew_certificates_systemd_calendar: "Mon *-*-1,2,3,4,5,6,7 03:{{ groups['kube_control_plane'].index(inventory_hostname) }}0:00"
 
 kubeadm_patches_dir: "{{ kube_config_dir }}/patches"
 kubeadm_patches: []

inventory/sample/group_vars/k8s_cluster/k8s-net-calico.yml

@@ -25,9 +25,15 @@ calico_pool_blocksize: 26
 # add default ippool CIDR (must be inside kube_pods_subnet, defaults to kube_pods_subnet otherwise)
 # calico_pool_cidr: 1.2.3.4/5
 
+# add default ippool CIDR to CNI config
+# calico_cni_pool: true
+
 # Add default IPV6 IPPool CIDR. Must be inside kube_pods_subnet_ipv6. Defaults to kube_pods_subnet_ipv6 if not set.
 # calico_pool_cidr_ipv6: fd85:ee78:d8a6:8607::1:0000/112
 
+# Add default IPV6 IPPool CIDR to CNI config
+# calico_cni_pool_ipv6: true
+
 # Global as_num (/calico/bgp/v1/global/as_num)
 # global_as_num: "64512"
 

inventory/sample/group_vars/k8s_cluster/k8s-net-cilium.yml

@@ -1,4 +1,6 @@
 ---
+# cilium_version: "1.15.9"
+
 # Log-level
 # cilium_debug: false
 
@@ -175,10 +177,6 @@ cilium_l2announcements: false
 ### Buffer size of the channel to receive monitor events.
 # cilium_hubble_event_queue_size: 50
 
-# Override the DNS suffix that Hubble-Relay uses to resolve its peer service.
-# It defaults to the inventory's `dns_domain`.
-# cilium_hubble_peer_service_cluster_domain: "{{ dns_domain }}"
-
 # IP address management mode for v1.9+.
 # https://docs.cilium.io/en/v1.9/concepts/networking/ipam/
 # cilium_ipam_mode: kubernetes
@@ -257,10 +255,6 @@ cilium_l2announcements: false
 #   - name: "blue-pool"
 #     cidrs:
 #       - "10.0.10.0/24"
-#     ranges:
-#       - start: "20.0.20.100"
-#         stop: "20.0.20.200"
-#       - start: "1.2.3.4"
 
 # -- Configure BGP Instances (New bgpv2 API v1.16+)
 # cilium_bgp_cluster_configs:
@@ -384,7 +378,3 @@ cilium_l2announcements: false
 #       resourceNames:
 #       - toto
 # cilium_clusterrole_rules_operator_extra_vars: []
-
-# Cilium extra values, use any values from cilium Helm Chart
-# ref: https://docs.cilium.io/en/stable/helm-reference/
-# cilium_extra_values: {}

inventory/sample/group_vars/k8s_cluster/k8s-net-custom-cni.yml

@@ -45,7 +45,7 @@
 # custom_cni_chart_repository_name: cilium
 # custom_cni_chart_repository_url: https://helm.cilium.io
 # custom_cni_chart_ref: cilium/cilium
-# custom_cni_chart_version: <chart version> (e.g.: 1.14.3)
+# custom_cni_chart_version: 1.14.3
 # custom_cni_chart_values:
 #   cluster:
 #     name: "cilium-demo"

inventory/sample/group_vars/k8s_cluster/k8s-net-kube-router.yml

@@ -1,5 +1,11 @@
 # See roles/network_plugin/kube-router/defaults/main.yml
 
+# Kube router version
+# Default to v2
+# kube_router_version: "2.0.0"
+# Uncomment to use v1 (Deprecated)
+# kube_router_version: "1.6.0"
+
 # Enables Pod Networking -- Advertises and learns the routes to Pods via iBGP
 # kube_router_run_router: true
 

inventory/sample/group_vars/k8s_cluster/k8s-net-weave.yml

@@ -0,0 +1,64 @@
+# see roles/network_plugin/weave/defaults/main.yml
+
+# Weave's network password for encryption, if null then no network encryption.
+# weave_password: ~
+
+# If set to 1, disable checking for new Weave Net versions (default is blank,
+# i.e. check is enabled)
+# weave_checkpoint_disable: false
+
+# Soft limit on the number of connections between peers. Defaults to 100.
+# weave_conn_limit: 100
+
+# Weave Net defaults to enabling hairpin on the bridge side of the veth pair
+# for containers attached. If you need to disable hairpin, e.g. your kernel is
+# one of those that can panic if hairpin is enabled, then you can disable it by
+# setting `HAIRPIN_MODE=false`.
+# weave_hairpin_mode: true
+
+# The range of IP addresses used by Weave Net and the subnet they are placed in
+# (CIDR format; default 10.32.0.0/12)
+# weave_ipalloc_range: "{{ kube_pods_subnet }}"
+
+# Set to 0 to disable Network Policy Controller (default is on)
+# weave_expect_npc: "{{ enable_network_policy }}"
+
+# List of addresses of peers in the Kubernetes cluster (default is to fetch the
+# list from the api-server)
+# weave_kube_peers: ~
+
+# Set the initialization mode of the IP Address Manager (defaults to consensus
+# amongst the KUBE_PEERS)
+# weave_ipalloc_init: ~
+
+# Set the IP address used as a gateway from the Weave network to the host
+# network - this is useful if you are configuring the addon as a static pod.
+# weave_expose_ip: ~
+
+# Address and port that the Weave Net daemon will serve Prometheus-style
+# metrics on (defaults to 0.0.0.0:6782)
+# weave_metrics_addr: ~
+
+# Address and port that the Weave Net daemon will serve status requests on
+# (defaults to disabled)
+# weave_status_addr: ~
+
+# Weave Net defaults to 1376 bytes, but you can set a smaller size if your
+# underlying network has a tighter limit, or set a larger size for better
+# performance if your network supports jumbo frames (e.g. 8916)
+# weave_mtu: 1376
+
+# Set to 1 to preserve the client source IP address when accessing Service
+# annotated with `service.spec.externalTrafficPolicy=Local`. The feature works
+# only with Weave IPAM (default).
+# weave_no_masq_local: true
+
+# set to nft to use nftables backend for iptables (default is iptables)
+# weave_iptables_backend: iptables
+
+# Extra variables that passing to launch.sh, useful for enabling seed mode, see
+# https://www.weave.works/docs/net/latest/tasks/ipam/ipam/
+# weave_extra_args: ~
+
+# Extra variables for weave_npc that passing to launch.sh, useful for change log level, ex --log-level=error
+# weave_npc_extra_args: ~

meta/runtime.yml

@@ -1,2 +1,2 @@
 ---
-requires_ansible: ">=2.17.3"
+requires_ansible: '>=2.16.4'

pipeline.Dockerfile

@@ -1,4 +1,4 @@
-# Use immutable image tags rather than mutable tags (like ubuntu:22.04)
+# Use imutable image tags rather than mutable tags (like ubuntu:22.04)
 FROM ubuntu:jammy-20230308
 # Some tools like yamllint need this
 # Pip needs this as well at the moment to install ansible
@@ -47,8 +47,8 @@ RUN update-alternatives --install /usr/bin/python python /usr/bin/python3 1 \
     && pip install --no-compile --no-cache-dir pip -U \
     && pip install --no-compile --no-cache-dir -r tests/requirements.txt \
     && pip install --no-compile --no-cache-dir -r requirements.txt \
-    && curl -L https://dl.k8s.io/release/v1.33.7/bin/linux/$(dpkg --print-architecture)/kubectl -o /usr/local/bin/kubectl \
-    && echo $(curl -L https://dl.k8s.io/release/v1.33.7/bin/linux/$(dpkg --print-architecture)/kubectl.sha256) /usr/local/bin/kubectl | sha256sum --check \
+    && curl -L https://dl.k8s.io/release/v1.32.3/bin/linux/$(dpkg --print-architecture)/kubectl -o /usr/local/bin/kubectl \
+    && echo $(curl -L https://dl.k8s.io/release/v1.32.3/bin/linux/$(dpkg --print-architecture)/kubectl.sha256) /usr/local/bin/kubectl | sha256sum --check \
     && chmod a+x /usr/local/bin/kubectl \
     # Install Vagrant
     && curl -LO https://releases.hashicorp.com/vagrant/${VAGRANT_VERSION}/vagrant_${VAGRANT_VERSION}-1_$(dpkg --print-architecture).deb \

playbooks/ansible_version.yml

@@ -5,8 +5,8 @@
   become: false
   run_once: true
   vars:
-    minimal_ansible_version: 2.17.3
-    maximal_ansible_version: 2.18.0
+    minimal_ansible_version: 2.16.4
+    maximal_ansible_version: 2.17.0
   tags: always
   tasks:
     - name: "Check {{ minimal_ansible_version }} <= Ansible version < {{ maximal_ansible_version }}"

playbooks/boilerplate.yml

@@ -6,18 +6,34 @@
 # - to ensure we keep compatibility with old style group names
 # - to reduce inventory boilerplate (defining parent groups / empty groups)
 
-- name: Inventory setup and validation
+- name: Define groups for legacy less structured inventories
   hosts: all
   gather_facts: false
   tags: always
-  roles:
-    - dynamic_groups
-    - validate_inventory
+  tasks:
+    - name: Match needed groups by their old names or definition
+      vars:
+        group_mappings:
+          kube_control_plane:
+            - kube-master
+          kube_node:
+            - kube-node
+          calico_rr:
+            - calico-rr
+          no_floating:
+            - no-floating
+          k8s_cluster:
+            - kube_node
+            - kube_control_plane
+            - calico_rr
+      group_by:
+        key: "{{ (group_names | intersect(item.value) | length > 0) | ternary(item.key, '_all') }}"
+      loop: "{{ group_mappings | dict2items }}"
 
 - name: Install bastion ssh config
   hosts: bastion[0]
   gather_facts: false
   environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray_defaults }
+    - { role: kubespray-defaults }
     - { role: bastion-ssh-config, tags: ["localhost", "bastion"] }