Refactor check_galaxy + fix version (#10729) (#10891)

* Remove checks for docs using exact tags

Instead use a more generic documentation for installing kubespray as a
collection from git.

* Check that we upgraded galaxy.yml to next version

This is only intented to check for human error. The version in galaxy
should be the next (which does not mean the same if we're on master or a
release branch).

* Set collection version to KUBESPRAY_NEXT_VERSION

.ansible-lint

@@ -24,7 +24,17 @@ skip_list:
   # (Disabled in June 2021)
   - 'role-name'
 
+  - 'experimental'
   # [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'
+  - 'var-spacing'
+
+  # [fqcn-builtins]
+  # Roles in kubespray don't need fully qualified collection names
+  # (Disabled in Feb 2023)
+  - 'fqcn-builtins'
+exclude_paths:
+  # Generated files
+  - tests/files/custom_cni/cilium.yaml

.gitignore

@@ -3,14 +3,19 @@
 **/vagrant_ansible_inventory
 *.iml
 temp
+contrib/offline/offline-files
+contrib/offline/offline-files.tar.gz
 .idea
+.vscode
 .tox
 .cache
 *.bak
 *.tfstate
 *.tfstate.backup
+*.lock.hcl
 .terraform/
 contrib/terraform/aws/credentials.tfvars
+.terraform.lock.hcl
 /ssh-bastion.conf
 **/*.sw[pon]
 *~
@@ -108,3 +113,8 @@ roles/**/molecule/**/__pycache__/
 
 # Temp location used by our scripts
 scripts/tmp/
+tmp.md
+
+# Ansible collection files
+kubernetes_sigs-kubespray*tar.gz
+ansible_collections

.gitlab-ci.yml

@@ -1,5 +1,6 @@
 ---
 stages:
+  - build
   - unit-tests
   - deploy-part1
   - moderator
@@ -8,12 +9,12 @@ stages:
   - deploy-special
 
 variables:
-  KUBESPRAY_VERSION: v2.18.1
+  KUBESPRAY_VERSION: v2.21.0
   FAILFASTCI_NAMESPACE: 'kargo-ci'
   GITLAB_REPOSITORY: 'kargo-ci/kubernetes-sigs-kubespray'
   ANSIBLE_FORCE_COLOR: "true"
   MAGIC: "ci check this"
-  TEST_ID: "$CI_PIPELINE_ID-$CI_BUILD_ID"
+  TEST_ID: "$CI_PIPELINE_ID-$CI_JOB_ID"
   CI_TEST_VARS: "./tests/files/${CI_JOB_NAME}.yml"
   CI_TEST_REGISTRY_MIRROR: "./tests/common/_docker_hub_registry_mirror.yml"
   CI_TEST_SETTING: "./tests/common/_kubespray_test_settings.yml"
@@ -33,20 +34,21 @@ variables:
   ANSIBLE_LOG_LEVEL: "-vv"
   RECOVER_CONTROL_PLANE_TEST: "false"
   RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:],kube_control_plane[1:]"
-  TERRAFORM_VERSION: 1.0.8
-  ANSIBLE_MAJOR_VERSION: "2.10"
+  TERRAFORM_VERSION: 1.3.7
+  ANSIBLE_MAJOR_VERSION: "2.11"
+  PIPELINE_IMAGE: "$CI_REGISTRY_IMAGE/pipeline:${CI_PIPELINE_ID}-${CI_COMMIT_SHORT_SHA}"
 
 before_script:
   - ./tests/scripts/rebase.sh
   - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
   - python -m pip uninstall -y ansible ansible-base ansible-core
-  - python -m pip install -r tests/requirements-${ANSIBLE_MAJOR_VERSION}.txt
+  - PIP_CONSTRAINT=tests/constraints.txt python -m pip install -r tests/requirements-${ANSIBLE_MAJOR_VERSION}.txt
   - mkdir -p /.ssh
 
 .job: &job
   tags:
     - packet
-  image: quay.io/kubespray/kubespray:$KUBESPRAY_VERSION
+  image: $PIPELINE_IMAGE
   artifacts:
     when: always
     paths:
@@ -76,6 +78,7 @@ ci-authorized:
   only: []
 
 include:
+  - .gitlab-ci/build.yml
   - .gitlab-ci/lint.yml
   - .gitlab-ci/shellcheck.yml
   - .gitlab-ci/terraform.yml

.gitlab-ci/build.yml

@@ -0,0 +1,40 @@
+---
+.build:
+  stage: build
+  image:
+    name: moby/buildkit:rootless
+    entrypoint: [""]
+  variables:
+    BUILDKITD_FLAGS: --oci-worker-no-process-sandbox
+  before_script:
+    - mkdir ~/.docker
+    - echo "{\"auths\":{\"$CI_REGISTRY\":{\"username\":\"$CI_REGISTRY_USER\",\"password\":\"$CI_REGISTRY_PASSWORD\"}}}" > ~/.docker/config.json
+
+pipeline image:
+  extends: .build
+  script:
+    - |
+      buildctl-daemonless.sh build \
+        --frontend=dockerfile.v0 \
+        --local context=. \
+        --local dockerfile=. \
+        --opt filename=./pipeline.Dockerfile \
+        --output type=image,name=$PIPELINE_IMAGE,push=true \
+        --import-cache type=registry,ref=$CI_REGISTRY_IMAGE/pipeline:cache
+  rules:
+    - if: '$CI_COMMIT_REF_NAME != $CI_DEFAULT_BRANCH'
+
+pipeline image and build cache:
+  extends: .build
+  script:
+    - |
+      buildctl-daemonless.sh build \
+        --frontend=dockerfile.v0 \
+        --local context=. \
+        --local dockerfile=. \
+        --opt filename=./pipeline.Dockerfile \
+        --output type=image,name=$PIPELINE_IMAGE,push=true \
+        --import-cache type=registry,ref=$CI_REGISTRY_IMAGE/pipeline:cache \
+        --export-cache type=registry,ref=$CI_REGISTRY_IMAGE/pipeline:cache,mode=max
+  rules:
+    - if: '$CI_COMMIT_REF_NAME == $CI_DEFAULT_BRANCH'

.gitlab-ci/lint.yml

@@ -14,7 +14,7 @@ vagrant-validate:
   stage: unit-tests
   tags: [light]
   variables:
-    VAGRANT_VERSION: 2.2.19
+    VAGRANT_VERSION: 2.3.7
   script:
     - ./tests/scripts/vagrant-validate.sh
   except: ['triggers', 'master']
@@ -39,11 +39,28 @@ syntax-check:
     ANSIBLE_VERBOSITY: "3"
   script:
     - ansible-playbook --syntax-check cluster.yml
+    - ansible-playbook --syntax-check playbooks/cluster.yml
     - ansible-playbook --syntax-check upgrade-cluster.yml
+    - ansible-playbook --syntax-check playbooks/upgrade_cluster.yml
     - ansible-playbook --syntax-check reset.yml
+    - ansible-playbook --syntax-check playbooks/reset.yml
     - ansible-playbook --syntax-check extra_playbooks/upgrade-only-k8s.yml
   except: ['triggers', 'master']
 
+collection-build-install-sanity-check:
+  extends: .job
+  stage: unit-tests
+  tags: [light]
+  variables:
+    ANSIBLE_COLLECTIONS_PATH: "./ansible_collections"
+  script:
+    - ansible-galaxy collection build
+    - ansible-galaxy collection install kubernetes_sigs-kubespray-$(grep "^version:" galaxy.yml | awk '{print $2}').tar.gz
+    - ansible-galaxy collection list $(egrep -i '(name:\s+|namespace:\s+)' galaxy.yml | awk '{print $2}' | tr '\n' '.' | sed 's|\.$||g') | grep "^kubernetes_sigs.kubespray"
+    - test -f ansible_collections/kubernetes_sigs/kubespray/playbooks/cluster.yml
+    - test -f ansible_collections/kubernetes_sigs/kubespray/playbooks/reset.yml
+  except: ['triggers', 'master']
+
 tox-inventory-builder:
   stage: unit-tests
   tags: [light]
@@ -53,7 +70,7 @@ tox-inventory-builder:
     - apt-get update && apt-get install -y python3-pip
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 10
     - python -m pip uninstall -y ansible ansible-base ansible-core
-    - python -m pip install -r tests/requirements.txt
+    - PIP_CONSTRAINT=tests/constraints.txt python -m pip install -r tests/requirements.txt
   script:
     - pip3 install tox
     - cd contrib/inventory_builder && tox
@@ -68,6 +85,27 @@ markdownlint:
   script:
     - markdownlint $(find . -name '*.md' | grep -vF './.git') --ignore docs/_sidebar.md --ignore contrib/dind/README.md
 
+check-readme-versions:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/check_readme_versions.sh
+
+check-galaxy-version:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/check_galaxy_version.sh
+
+check-typo:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/check_typo.sh
+
 ci-matrix:
   stage: unit-tests
   tags: [light]

.gitlab-ci/molecule.yml

@@ -4,7 +4,7 @@
   tags: [c3.small.x86]
   only: [/^pr-.*$/]
   except: ['triggers']
-  image: quay.io/kubespray/vagrant:$KUBESPRAY_VERSION
+  image: $PIPELINE_IMAGE
   services: []
   stage: deploy-part1
   before_script:
@@ -12,7 +12,7 @@
     - apt-get update && apt-get install -y python3-pip
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 10
     - python -m pip uninstall -y ansible ansible-base ansible-core
-    - python -m pip install -r tests/requirements.txt
+    - PIP_CONSTRAINT=tests/constraints.txt python -m pip install -r tests/requirements.txt
     - ./tests/scripts/vagrant_clean.sh
   script:
     - ./tests/scripts/molecule_run.sh
@@ -44,7 +44,7 @@ molecule_no_container_engines:
 molecule_docker:
   extends: .molecule
   script:
-    - ./tests/scripts/molecule_run.sh -i container-engine/docker
+    - ./tests/scripts/molecule_run.sh -i container-engine/cri-dockerd
   when: on_success
 
 molecule_containerd:
@@ -60,13 +60,6 @@ molecule_cri-o:
     - ./tests/scripts/molecule_run.sh -i container-engine/cri-o
   when: on_success
 
-molecule_cri-dockerd:
-  extends: .molecule
-  stage: deploy-part2
-  script:
-    - ./tests/scripts/molecule_run.sh -i container-engine/cri-dockerd
-  when: on_success
-
 # Stage 3 container engines don't get as much attention so allow them to fail
 molecule_kata:
   extends: .molecule

.gitlab-ci/packet.yml

@@ -31,23 +31,6 @@ packet_ubuntu20-calico-aio:
   variables:
     RESET_CHECK: "true"
 
-# Exericse ansible variants during the nightly jobs
-packet_ubuntu20-calico-aio-ansible-2_9:
-  stage: deploy-part1
-  extends: .packet_periodic
-  when: on_success
-  variables:
-    ANSIBLE_MAJOR_VERSION: "2.9"
-    RESET_CHECK: "true"
-
-packet_ubuntu20-calico-aio-ansible-2_10:
-  stage: deploy-part1
-  extends: .packet_periodic
-  when: on_success
-  variables:
-    ANSIBLE_MAJOR_VERSION: "2.10"
-    RESET_CHECK: "true"
-
 packet_ubuntu20-calico-aio-ansible-2_11:
   stage: deploy-part1
   extends: .packet_periodic
@@ -68,11 +51,26 @@ packet_ubuntu20-aio-docker:
   extends: .packet_pr
   when: on_success
 
+packet_ubuntu20-calico-aio-hardening:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
 packet_ubuntu18-calico-aio:
   stage: deploy-part2
   extends: .packet_pr
   when: on_success
 
+packet_ubuntu22-aio-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_ubuntu22-calico-aio:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
 packet_centos7-flannel-addons-ha:
   extends: .packet_pr
   stage: deploy-part2
@@ -88,21 +86,11 @@ packet_ubuntu18-crio:
   stage: deploy-part2
   when: manual
 
-packet_fedora35-crio:
+packet_fedora37-crio:
   extends: .packet_pr
   stage: deploy-part2
   when: manual
 
-packet_ubuntu16-canal-ha:
-  stage: deploy-part2
-  extends: .packet_periodic
-  when: on_success
-
-packet_ubuntu16-canal-sep:
-  stage: deploy-special
-  extends: .packet_pr
-  when: manual
-
 packet_ubuntu16-flannel-ha:
   stage: deploy-part2
   extends: .packet_pr
@@ -153,20 +141,33 @@ packet_almalinux8-calico:
   extends: .packet_pr
   when: on_success
 
+packet_rockylinux8-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_rockylinux9-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_rockylinux9-cilium:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+  variables:
+    RESET_CHECK: "true"
+
 packet_almalinux8-docker:
   stage: deploy-part2
   extends: .packet_pr
   when: on_success
 
-packet_fedora34-docker-weave:
+packet_fedora38-docker-weave:
   stage: deploy-part2
   extends: .packet_pr
   when: on_success
-
-packet_opensuse-canal:
-  stage: deploy-part2
-  extends: .packet_periodic
-  when: on_success
+  allow_failure: true
 
 packet_opensuse-docker-cilium:
   stage: deploy-part2
@@ -201,7 +202,7 @@ packet_almalinux8-calico-ha-ebpf:
   extends: .packet_pr
   when: manual
 
-packet_debian9-macvlan:
+packet_debian10-macvlan:
   stage: deploy-part2
   extends: .packet_pr
   when: manual
@@ -216,24 +217,19 @@ packet_centos7-multus-calico:
   extends: .packet_pr
   when: manual
 
-packet_oracle7-canal-ha:
-  stage: deploy-part2
-  extends: .packet_pr
-  when: manual
-
-packet_fedora35-docker-calico:
+packet_fedora38-docker-calico:
   stage: deploy-part2
   extends: .packet_periodic
   when: on_success
   variables:
     RESET_CHECK: "true"
 
-packet_fedora34-calico-selinux:
+packet_fedora37-calico-selinux:
   stage: deploy-part2
   extends: .packet_periodic
   when: on_success
 
-packet_fedora35-calico-swap-selinux:
+packet_fedora37-calico-swap-selinux:
   stage: deploy-part2
   extends: .packet_pr
   when: manual
@@ -248,15 +244,25 @@ packet_almalinux8-calico-nodelocaldns-secondary:
   extends: .packet_pr
   when: manual
 
-packet_fedora34-kube-ovn:
+packet_fedora38-kube-ovn:
   stage: deploy-part2
   extends: .packet_periodic
   when: on_success
 
+packet_debian11-custom-cni:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_debian11-kubelet-csr-approver:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
 # ### PR JOBS PART3
 # Long jobs (45min+)
 
-packet_centos7-docker-weave-upgrade-ha:
+packet_centos7-weave-upgrade-ha:
   stage: deploy-part3
   extends: .packet_periodic
   when: on_success
@@ -276,7 +282,7 @@ packet_ubuntu20-calico-ha-wireguard:
   extends: .packet_pr
   when: manual
 
-packet_debian10-calico-upgrade:
+packet_debian11-calico-upgrade:
   stage: deploy-part3
   extends: .packet_pr
   when: on_success
@@ -291,7 +297,12 @@ packet_almalinux8-calico-remove-node:
     REMOVE_NODE_CHECK: "true"
     REMOVE_NODE_NAME: "instance-3"
 
-packet_debian10-calico-upgrade-once:
+packet_ubuntu20-calico-etcd-kubeadm:
+  stage: deploy-part3
+  extends: .packet_pr
+  when: on_success
+
+packet_debian11-calico-upgrade-once:
   stage: deploy-part3
   extends: .packet_periodic
   when: on_success

.gitlab-ci/shellcheck.yml

@@ -11,6 +11,6 @@ shellcheck:
     - cp shellcheck-"${SHELLCHECK_VERSION}"/shellcheck /usr/bin/
     - shellcheck --version
   script:
-    # Run shellcheck for all *.sh except contrib/
-    - find . -name '*.sh' -not -path './contrib/*' -not -path './.git/*' | xargs shellcheck --severity error
+    # Run shellcheck for all *.sh
+    - find . -name '*.sh' -not -path './.git/*' | xargs shellcheck --severity error
   except: ['triggers', 'master']

.gitlab-ci/terraform.yml

@@ -60,11 +60,11 @@ tf-validate-openstack:
     PROVIDER: openstack
     CLUSTER: $CI_COMMIT_REF_NAME
 
-tf-validate-metal:
+tf-validate-equinix:
   extends: .terraform_validate
   variables:
     TF_VERSION: $TERRAFORM_VERSION
-    PROVIDER: metal
+    PROVIDER: equinix
     CLUSTER: $CI_COMMIT_REF_NAME
 
 tf-validate-aws:
@@ -80,6 +80,12 @@ tf-validate-exoscale:
     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:
@@ -104,7 +110,7 @@ tf-validate-upcloud:
 #     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_facility: ewr1
+#     TF_VAR_metro: ny
 #     TF_VAR_public_key_path: ""
 #     TF_VAR_operating_system: ubuntu_16_04
 #
@@ -118,7 +124,7 @@ tf-validate-upcloud:
 #     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_facility: ams1
+#     TF_VAR_metro: am
 #     TF_VAR_public_key_path: ""
 #     TF_VAR_operating_system: ubuntu_18_04
 

.gitlab-ci/vagrant.yml

@@ -10,13 +10,13 @@
   tags: [c3.small.x86]
   only: [/^pr-.*$/]
   except: ['triggers']
-  image: quay.io/kubespray/vagrant:$KUBESPRAY_VERSION
+  image: $PIPELINE_IMAGE
   services: []
   before_script:
     - apt-get update && apt-get install -y python3-pip
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 10
     - python -m pip uninstall -y ansible ansible-base ansible-core
-    - python -m pip install -r tests/requirements.txt
+    - PIP_CONSTRAINT=tests/constraints.txt python -m pip install -r tests/requirements.txt
     - ./tests/scripts/vagrant_clean.sh
   script:
     - ./tests/scripts/testcases_run.sh
@@ -43,6 +43,12 @@ vagrant_ubuntu20-flannel:
   stage: deploy-part2
   extends: .vagrant
   when: on_success
+  allow_failure: false
+
+vagrant_ubuntu20-flannel-collection:
+  stage: deploy-part2
+  extends: .vagrant
+  when: on_success
 
 vagrant_ubuntu16-kube-router-sep:
   stage: deploy-part2
@@ -55,7 +61,7 @@ vagrant_ubuntu16-kube-router-svc-proxy:
   extends: .vagrant
   when: manual
 
-vagrant_fedora35-kube-router:
+vagrant_fedora37-kube-router:
   stage: deploy-part2
   extends: .vagrant
   when: on_success

.markdownlint.yaml

@@ -1,2 +1,3 @@
 ---
 MD013: false
+MD029: false

.pre-commit-config.yaml

@@ -0,0 +1,71 @@
+---
+repos:
+
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.4.0
+    hooks:
+      - id: check-added-large-files
+      - id: check-case-conflict
+      - id: check-executables-have-shebangs
+      - id: check-xml
+      - id: check-merge-conflict
+      - id: detect-private-key
+      - id: end-of-file-fixer
+      - id: forbid-new-submodules
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+
+  - repo: https://github.com/adrienverge/yamllint.git
+    rev: v1.27.1
+    hooks:
+      - id: yamllint
+        args: [--strict]
+
+  - repo: https://github.com/markdownlint/markdownlint
+    rev: v0.11.0
+    hooks:
+      - id: markdownlint
+        args: [ -r, "~MD013,~MD029" ]
+        exclude: "^.git"
+
+  - repo: https://github.com/jumanjihouse/pre-commit-hooks
+    rev: 3.0.0
+    hooks:
+      - id: shellcheck
+        args: [ --severity, "error" ]
+        exclude: "^.git"
+        files: "\\.sh$"
+
+  - repo: local
+    hooks:
+      - id: ansible-lint
+        name: ansible-lint
+        entry: ansible-lint -v
+        language: python
+        pass_filenames: false
+        additional_dependencies:
+          - .[community]
+
+      - id: ansible-syntax-check
+        name: ansible-syntax-check
+        entry: env ANSIBLE_INVENTORY=inventory/local-tests.cfg ANSIBLE_REMOTE_USER=root ANSIBLE_BECOME="true" ANSIBLE_BECOME_USER=root ANSIBLE_VERBOSITY="3" ansible-playbook --syntax-check
+        language: python
+        files: "^cluster.yml|^upgrade-cluster.yml|^reset.yml|^extra_playbooks/upgrade-only-k8s.yml"
+
+      - id: tox-inventory-builder
+        name: tox-inventory-builder
+        entry: bash -c "cd contrib/inventory_builder && tox"
+        language: python
+        pass_filenames: false
+
+      - id: check-readme-versions
+        name: check-readme-versions
+        entry: tests/scripts/check_readme_versions.sh
+        language: script
+        pass_filenames: false
+
+      - id: ci-matrix
+        name: ci-matrix
+        entry: tests/scripts/md-table/test.sh
+        language: script
+        pass_filenames: false

.yamllint

@@ -3,6 +3,8 @@ extends: default
 
 ignore: |
   .git/
+  # Generated file
+  tests/files/custom_cni/cilium.yaml
 
 rules:
   braces:

CNAME

@@ -1 +1 @@
-kubespray.io
+kubespray.io

CONTRIBUTING.md

@@ -16,7 +16,12 @@ pip install -r tests/requirements.txt
 
 #### Linting
 
-Kubespray uses `yamllint` and `ansible-lint`. To run them locally use `yamllint .` and `ansible-lint`. It is a good idea to add call these tools as part of your pre-commit hook and avoid a lot of back end forth on fixing linting issues (<https://support.gitkraken.com/working-with-repositories/githooksexample/>).
+Kubespray uses [pre-commit](https://pre-commit.com) hook configuration to run several linters, please install this tool and use it to run validation tests before submitting a PR.
+
+```ShellSession
+pre-commit install
+pre-commit run -a  # To run pre-commit hook on all files in the repository, even if they were not modified
+```
 
 #### Molecule
 
@@ -33,7 +38,9 @@ Vagrant with VirtualBox or libvirt driver helps you to quickly spin test cluster
 1. Submit an issue describing your proposed change to the repo in question.
 2. The [repo owners](OWNERS) will respond to your issue promptly.
 3. Fork the desired repo, develop and test your code changes.
-4. Sign the CNCF CLA (<https://git.k8s.io/community/CLA.md#the-contributor-license-agreement>)
-5. Submit a pull request.
-6. Work with the reviewers on their suggestions.
-7. Ensure to rebase to the HEAD of your target branch and squash un-necessary commits (<https://blog.carbonfive.com/always-squash-and-rebase-your-git-commits/>) before final merger of your contribution.
+4. Install [pre-commit](https://pre-commit.com) and install it in your development repo.
+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.
+9. Ensure to rebase to the HEAD of your target branch and squash un-necessary commits (<https://blog.carbonfive.com/always-squash-and-rebase-your-git-commits/>) before final merger of your contribution.

Dockerfile

@@ -1,37 +1,44 @@
-# Use imutable image tags rather than mutable tags (like ubuntu:20.04)
-FROM ubuntu:focal-20220316
-
-ARG ARCH=amd64
-ARG TZ=Etc/UTC
-RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
-
-RUN apt update -y \
-    && apt install -y \
-    libssl-dev python3-dev sshpass apt-transport-https jq moreutils \
-    ca-certificates curl gnupg2 software-properties-common python3-pip unzip rsync git \
-    && rm -rf /var/lib/apt/lists/*
-RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add - \
-    && add-apt-repository \
-    "deb [arch=$ARCH] https://download.docker.com/linux/ubuntu \
-    $(lsb_release -cs) \
-    stable" \
-    && apt update -y && apt-get install --no-install-recommends -y docker-ce \
-    && rm -rf /var/lib/apt/lists/*
-
+# 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
-# (and potentially other packages)
+# (and potentially other packages) 
 # See: https://github.com/pypa/pip/issues/10219
-ENV LANG=C.UTF-8
-
+ENV LANG=C.UTF-8 \
+    DEBIAN_FRONTEND=noninteractive \
+    PYTHONDONTWRITEBYTECODE=1
 WORKDIR /kubespray
-COPY . .
-RUN /usr/bin/python3 -m pip install --no-cache-dir pip -U \
-    && /usr/bin/python3 -m pip install --no-cache-dir -r tests/requirements.txt \
-    && python3 -m pip install --no-cache-dir -r requirements.txt \
-    && update-alternatives --install /usr/bin/python python /usr/bin/python3 1
+COPY *.yml ./
+COPY *.cfg ./
+COPY roles ./roles
+COPY contrib ./contrib
+COPY inventory ./inventory
+COPY library ./library
+COPY extra_playbooks ./extra_playbooks
+COPY playbooks ./playbooks
+COPY plugins ./plugins
 
-RUN KUBE_VERSION=$(sed -n 's/^kube_version: //p' roles/kubespray-defaults/defaults/main.yaml) \
-    && curl -LO https://storage.googleapis.com/kubernetes-release/release/$KUBE_VERSION/bin/linux/$ARCH/kubectl \
-    && chmod a+x kubectl \
-    && mv kubectl /usr/local/bin/kubectl
+RUN apt update -q \
+    && apt install -yq --no-install-recommends \
+       curl \
+       python3 \
+       python3-pip \
+       sshpass \
+       vim \
+       rsync \
+       openssh-client \
+    && pip install --no-compile --no-cache-dir \
+       ansible==5.7.1 \
+       ansible-core==2.12.5 \
+       cryptography==3.4.8 \
+       jinja2==3.1.2 \
+       netaddr==0.8.0 \
+       jmespath==1.0.1 \
+       MarkupSafe==2.1.2 \
+       ruamel.yaml==0.17.21 \
+    && KUBE_VERSION=$(sed -n 's/^kube_version: //p' roles/kubespray-defaults/defaults/main.yaml) \
+    && curl -L https://dl.k8s.io/release/$KUBE_VERSION/bin/linux/$(dpkg --print-architecture)/kubectl -o /usr/local/bin/kubectl \
+    && echo $(curl -L https://dl.k8s.io/release/$KUBE_VERSION/bin/linux/$(dpkg --print-architecture)/kubectl.sha256) /usr/local/bin/kubectl | sha256sum --check \
+    && chmod a+x /usr/local/bin/kubectl \
+    && rm -rf /var/lib/apt/lists/* /var/log/* \
+    && find /usr -type d -name '*__pycache__' -prune -exec rm -rf {} \;

LICENSE

@@ -187,7 +187,7 @@
       identification within third-party archives.
 
    Copyright 2016 Kubespray
-   
+
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.
    You may obtain a copy of the License at

OWNERS

@@ -5,4 +5,4 @@ approvers:
 reviewers:
   - kubespray-reviewers
 emeritus_approvers:
-  - kubespray-emeritus_approvers
+  - kubespray-emeritus_approvers

OWNERS_ALIASES

@@ -8,6 +8,9 @@ aliases:
     - floryut
     - oomichi
     - cristicalin
+    - liupeng0518
+    - yankay
+    - mzaian
   kubespray-reviewers:
     - holmsten
     - bozzo
@@ -16,6 +19,10 @@ aliases:
     - jayonlau
     - cristicalin
     - liupeng0518
+    - yankay
+    - cyclinder
+    - mzaian
+    - mrfreezeex
   kubespray-emeritus_approvers:
     - riverzhang
     - atoms

README.md

@@ -13,7 +13,7 @@ You can get your invite [here](http://slack.k8s.io/)
 
 ## Quick Start
 
-To deploy the cluster you can use :
+Below are several ways to use Kubespray to deploy a Kubernetes cluster.
 
 ### Ansible
 
@@ -34,6 +34,13 @@ CONFIG_FILE=inventory/mycluster/hosts.yaml python3 contrib/inventory_builder/inv
 cat inventory/mycluster/group_vars/all/all.yml
 cat inventory/mycluster/group_vars/k8s_cluster/k8s-cluster.yml
 
+# Clean up old Kubernete cluster with Ansible Playbook - run the playbook as root
+# The option `--become` is required, as for example cleaning up SSL keys in /etc/,
+# uninstalling old packages and interacting with various systemd daemons.
+# Without --become the playbook will fail to run!
+# And be mind it will remove the current kubernetes cluster (if it's running)!
+ansible-playbook -i inventory/mycluster/hosts.yaml  --become --become-user=root reset.yml
+
 # Deploy Kubespray with Ansible Playbook - run the playbook as root
 # The option `--become` is required, as for example writing SSL keys in /etc/,
 # installing packages and interacting with various systemd daemons.
@@ -41,34 +48,50 @@ cat inventory/mycluster/group_vars/k8s_cluster/k8s-cluster.yml
 ansible-playbook -i inventory/mycluster/hosts.yaml  --become --become-user=root cluster.yml
 ```
 
-Note: When Ansible is already installed via system packages on the control machine, other python packages installed via `sudo pip install -r requirements.txt` will go to a different directory tree (e.g. `/usr/local/lib/python2.7/dist-packages` on Ubuntu) from Ansible's (e.g. `/usr/lib/python2.7/dist-packages/ansible` still on Ubuntu).
-As a consequence, `ansible-playbook` command will fail with:
+Note: When Ansible is already installed via system packages on the control node,
+Python packages installed via `sudo pip install -r requirements.txt` will go to
+a different directory tree (e.g. `/usr/local/lib/python2.7/dist-packages` on
+Ubuntu) from Ansible's (e.g. `/usr/lib/python2.7/dist-packages/ansible` still on
+Ubuntu). As a consequence, the `ansible-playbook` command will fail with:
 
 ```raw
 ERROR! no action detected in task. This often indicates a misspelled module name, or incorrect module path.
 ```
 
-probably pointing on a task depending on a module present in requirements.txt.
+This likely indicates that a task depends on a module present in ``requirements.txt``.
 
-One way of solving this would be to uninstall the Ansible package and then, to install it via pip but it is not always possible.
-A workaround consists of setting `ANSIBLE_LIBRARY` and `ANSIBLE_MODULE_UTILS` environment variables respectively to the `ansible/modules` and `ansible/module_utils` subdirectories of pip packages installation location, which can be found in the Location field of the output of `pip show [package]` before executing `ansible-playbook`.
+One way of addressing this is to uninstall the system Ansible package then
+reinstall Ansible via ``pip``, but this not always possible and one must
+take care regarding package versions.
+A workaround consists of setting the `ANSIBLE_LIBRARY`
+and `ANSIBLE_MODULE_UTILS` environment variables respectively to
+the `ansible/modules` and `ansible/module_utils` subdirectories of the ``pip``
+installation location, which is the ``Location`` shown by running
+`pip show [package]` before executing `ansible-playbook`.
 
-A simple way to ensure you get all the correct version of Ansible is to use the [pre-built docker image from Quay](https://quay.io/repository/kubespray/kubespray?tab=tags).
-You will then need to use [bind mounts](https://docs.docker.com/storage/bind-mounts/) to get the inventory and ssh key into the container, like this:
+A simple way to ensure you get all the correct version of Ansible is to use
+the [pre-built docker image from Quay](https://quay.io/repository/kubespray/kubespray?tab=tags).
+You will then need to use [bind mounts](https://docs.docker.com/storage/bind-mounts/)
+to access the inventory and SSH key in the container, like this:
 
 ```ShellSession
-docker pull quay.io/kubespray/kubespray:v2.19.0
+git checkout v2.22.2
+docker pull quay.io/kubespray/kubespray:v2.22.2
 docker run --rm -it --mount type=bind,source="$(pwd)"/inventory/sample,dst=/inventory \
   --mount type=bind,source="${HOME}"/.ssh/id_rsa,dst=/root/.ssh/id_rsa \
-  quay.io/kubespray/kubespray:v2.19.0 bash
+  quay.io/kubespray/kubespray:v2.22.0 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
 ```
 
+#### Collection
+
+See [here](docs/ansible_collection.md) if you wish to use this repository as an Ansible collection
+
 ### Vagrant
 
-For Vagrant we need to install python dependencies for provisioning tasks.
-Check if Python and pip are installed:
+For Vagrant we need to install Python dependencies for provisioning tasks.
+Check that ``Python`` and ``pip`` are installed:
 
 ```ShellSession
 python -V && pip -V
@@ -111,70 +134,87 @@ vagrant up
 - [Adding/replacing a node](docs/nodes.md)
 - [Upgrades basics](docs/upgrades.md)
 - [Air-Gap installation](docs/offline-environment.md)
+- [NTP](docs/ntp.md)
 - [Hardening](docs/hardening.md)
+- [Mirror](docs/mirror.md)
 - [Roadmap](docs/roadmap.md)
 
 ## Supported Linux Distributions
 
 - **Flatcar Container Linux by Kinvolk**
-- **Debian** Bullseye, Buster, Jessie, Stretch
-- **Ubuntu** 16.04, 18.04, 20.04
-- **CentOS/RHEL** 7, [8](docs/centos8.md)
-- **Fedora** 34, 35
+- **Debian** Bullseye, Buster
+- **Ubuntu** 16.04, 18.04, 20.04, 22.04
+- **CentOS/RHEL** 7, [8, 9](docs/centos.md#centos-8)
+- **Fedora** 37, 38
 - **Fedora CoreOS** (see [fcos Note](docs/fcos.md))
 - **openSUSE** Leap 15.x/Tumbleweed
-- **Oracle Linux** 7, [8](docs/centos8.md)
-- **Alma Linux** [8](docs/centos8.md)
-- **Rocky Linux** [8](docs/centos8.md)
+- **Oracle Linux** 7, [8, 9](docs/centos.md#centos-8)
+- **Alma Linux** [8, 9](docs/centos.md#centos-8)
+- **Rocky Linux** [8, 9](docs/centos.md#centos-8)
+- **Kylin Linux Advanced Server V10** (experimental: see [kylin linux notes](docs/kylinlinux.md))
 - **Amazon Linux 2** (experimental: see [amazon linux notes](docs/amazonlinux.md))
+- **UOS Linux** (experimental: see [uos linux notes](docs/uoslinux.md))
+- **openEuler** (experimental: see [openEuler notes](docs/openeuler.md))
 
 Note: Upstart/SysV init based OS types are not supported.
 
 ## Supported Components
 
 - Core
-  - [kubernetes](https://github.com/kubernetes/kubernetes) v1.23.7
-  - [etcd](https://github.com/etcd-io/etcd) v3.5.3
+  - [kubernetes](https://github.com/kubernetes/kubernetes) v1.26.13
+  - [etcd](https://github.com/etcd-io/etcd) v3.5.6
   - [docker](https://www.docker.com/) v20.10 (see note)
-  - [containerd](https://containerd.io/) v1.6.4
-  - [cri-o](http://cri-o.io/) v1.22 (experimental: see [CRI-O Note](docs/cri-o.md). Only on fedora, ubuntu and centos based OS)
+  - [containerd](https://containerd.io/) v1.7.13
+  - [cri-o](http://cri-o.io/) v1.24 (experimental: see [CRI-O Note](docs/cri-o.md). Only on fedora, ubuntu and centos based OS)
 - Network Plugin
-  - [cni-plugins](https://github.com/containernetworking/plugins) v1.1.1
-  - [calico](https://github.com/projectcalico/calico) v3.22.3
-  - [canal](https://github.com/projectcalico/canal) (given calico/flannel versions)
-  - [cilium](https://github.com/cilium/cilium) v1.11.3
-  - [flanneld](https://github.com/flannel-io/flannel) v0.17.0
-  - [kube-ovn](https://github.com/alauda/kube-ovn) v1.9.2
-  - [kube-router](https://github.com/cloudnativelabs/kube-router) v1.4.0
-  - [multus](https://github.com/intel/multus-cni) v3.8
+  - [cni-plugins](https://github.com/containernetworking/plugins) v1.2.0
+  - [calico](https://github.com/projectcalico/calico) v3.25.1
+  - [cilium](https://github.com/cilium/cilium) v1.13.0
+  - [flannel](https://github.com/flannel-io/flannel) v0.21.4
+  - [kube-ovn](https://github.com/alauda/kube-ovn) v1.10.7
+  - [kube-router](https://github.com/cloudnativelabs/kube-router) v1.5.1
+  - [multus](https://github.com/k8snetworkplumbingwg/multus-cni) v3.8
   - [weave](https://github.com/weaveworks/weave) v2.8.1
+  - [kube-vip](https://github.com/kube-vip/kube-vip) v0.5.12
 - Application
+  - [cert-manager](https://github.com/jetstack/cert-manager) v1.11.1
+  - [coredns](https://github.com/coredns/coredns) v1.9.3
+  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v1.7.1
+  - [krew](https://github.com/kubernetes-sigs/krew) v0.4.3
+  - [argocd](https://argoproj.github.io/) v2.7.2
+  - [helm](https://helm.sh/) v3.12.0
+  - [metallb](https://metallb.universe.tf/)  v0.13.9
+  - [registry](https://github.com/distribution/distribution) v2.8.1
+- Storage Plugin
   - [cephfs-provisioner](https://github.com/kubernetes-incubator/external-storage) v2.1.0-k8s1.11
   - [rbd-provisioner](https://github.com/kubernetes-incubator/external-storage) v2.1.1-k8s1.11
-  - [cert-manager](https://github.com/jetstack/cert-manager) v1.8.0
-  - [coredns](https://github.com/coredns/coredns) v1.8.6
-  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v1.2.1
+  - [aws-ebs-csi-plugin](https://github.com/kubernetes-sigs/aws-ebs-csi-driver) v0.5.0
+  - [azure-csi-plugin](https://github.com/kubernetes-sigs/azuredisk-csi-driver) v1.10.0
+  - [cinder-csi-plugin](https://github.com/kubernetes/cloud-provider-openstack/blob/master/docs/cinder-csi-plugin/using-cinder-csi-plugin.md) v1.22.0
+  - [gcp-pd-csi-plugin](https://github.com/kubernetes-sigs/gcp-compute-persistent-disk-csi-driver) v1.4.0
+  - [local-path-provisioner](https://github.com/rancher/local-path-provisioner) v0.0.23
+  - [local-volume-provisioner](https://github.com/kubernetes-sigs/sig-storage-local-static-provisioner) v2.5.0
 
 ## Container Runtime Notes
 
-- The list of available docker version is 18.09, 19.03 and 20.10. The recommended docker version is 20.10. The kubelet might break on docker's non-standard version numbering (it no longer uses semantic versioning). To ensure auto-updates don't break your cluster look into e.g. yum versionlock plugin or apt pin).
+- Supported Docker versions are 18.09, 19.03 and 20.10. The *recommended* Docker version is 20.10. `Kubelet` might break on docker's non-standard version numbering (it no longer uses semantic versioning). To ensure auto-updates don't break your cluster look into e.g. the YUM  ``versionlock`` plugin or ``apt pin``).
 - The cri-o version should be aligned with the respective kubernetes version (i.e. kube_version=1.20.x, crio_version=1.20)
 
 ## Requirements
 
-- **Minimum required version of Kubernetes is v1.21**
-- **Ansible v2.9.x, Jinja 2.11+ and python-netaddr is installed on the machine that will run Ansible commands**
+- **Minimum required version of Kubernetes is v1.24**
+- **Ansible v2.11+, Jinja 2.11+ and python-netaddr is installed on the machine that will run Ansible commands**
 - The target servers must have **access to the Internet** in order to pull docker images. Otherwise, additional configuration is required (See [Offline Environment](docs/offline-environment.md))
 - The target servers are configured to allow **IPv4 forwarding**.
 - If using IPv6 for pods and services, the target servers are configured to allow **IPv6 forwarding**.
 - The **firewalls are not managed**, you'll need to implement your own rules the way you used to.
     in order to avoid any issue during deployment you should disable your firewall.
-- If kubespray is ran from non-root user account, correct privilege escalation method
+- If kubespray is run from non-root user account, correct privilege escalation method
     should be configured in the target servers. Then the `ansible_become` flag
     or command parameters `--become or -b` should be specified.
 
 Hardware:
-These limits are safe guarded by Kubespray. Actual requirements for your workload can differ. For a sizing guide go to the [Building Large Clusters](https://kubernetes.io/docs/setup/cluster-large/#size-of-master-and-master-components) guide.
+These limits are safeguarded by Kubespray. Actual requirements for your workload can differ. For a sizing guide go to the [Building Large Clusters](https://kubernetes.io/docs/setup/cluster-large/#size-of-master-and-master-components) guide.
 
 - Master
   - Memory: 1500 MB
@@ -183,7 +223,7 @@ These limits are safe guarded by Kubespray. Actual requirements for your workloa
 
 ## Network Plugins
 
-You can choose between 10 network plugins. (default: `calico`, except Vagrant uses `flannel`)
+You can choose among ten network plugins. (default: `calico`, except Vagrant uses `flannel`)
 
 - [flannel](docs/flannel.md): gre/vxlan (layer 2) networking.
 
@@ -192,8 +232,6 @@ You can choose between 10 network plugins. (default: `calico`, except Vagrant us
     and overlay networks, with or without BGP. Calico uses the same engine to enforce network policy for hosts,
     pods, and (if using Istio and Envoy) applications at the service mesh layer.
 
-- [canal](https://github.com/projectcalico/canal): a composition of calico and flannel plugins.
-
 - [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/weave.md): Weave is a lightweight container overlay network that doesn't require an external K/V database cluster.
@@ -210,7 +248,10 @@ You can choose between 10 network plugins. (default: `calico`, except Vagrant us
 
 - [multus](docs/multus.md): Multus is a meta CNI plugin that provides multiple network interface support to pods. For each interface Multus delegates CNI calls to secondary CNI plugins such as Calico, macvlan, etc.
 
-The choice is defined with the variable `kube_network_plugin`. There is also an
+- [custom_cni](roles/network-plugin/custom_cni/) : You can specify some manifests that will be applied to the clusters to bring you own CNI and use non-supported ones by Kubespray.
+  See `tests/files/custom_cni/README.md` and `tests/files/custom_cni/values.yaml`for an example with a CNI provided by a Helm Chart.
+
+The network plugin to use is defined by the variable `kube_network_plugin`. There is also an
 option to leverage built-in cloud provider networking instead.
 See also [Network checker](docs/netcheck.md).
 
@@ -231,10 +272,11 @@ See also [Network checker](docs/netcheck.md).
 
 - [Digital Rebar Provision](https://github.com/digitalrebar/provision/blob/v4/doc/integrations/ansible.rst)
 - [Terraform Contrib](https://github.com/kubernetes-sigs/kubespray/tree/master/contrib/terraform)
+- [Kubean](https://github.com/kubean-io/kubean)
 
 ## CI Tests
 
-[![Build graphs](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/badges/master/pipeline.svg)](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/pipelines)
+[![Build graphs](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/badges/master/pipeline.svg)](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/-/pipelines)
 
 CI/end-to-end tests sponsored by: [CNCF](https://cncf.io), [Equinix Metal](https://metal.equinix.com/), [OVHcloud](https://www.ovhcloud.com/), [ELASTX](https://elastx.se/).
 

RELEASE.md

@@ -9,10 +9,10 @@ The Kubespray Project is released on an as-needed basis. The process is as follo
 5. Create the release note with [Kubernetes Release Notes Generator](https://github.com/kubernetes/release/blob/master/cmd/release-notes/README.md). See the following `Release note creation` section for the details.
 6. An approver creates [new release in GitHub](https://github.com/kubernetes-sigs/kubespray/releases/new) using a version and tag name like `vX.Y.Z` and attaching the release notes
 7. An approver creates a release branch in the form `release-X.Y`
-8. The corresponding version of [quay.io/kubespray/kubespray:vX.Y.Z](https://quay.io/repository/kubespray/kubespray) and [quay.io/kubespray/vagrant:vX.Y.Z](https://quay.io/repository/kubespray/vagrant) docker images are built and tagged
+8. The corresponding version of [quay.io/kubespray/kubespray:vX.Y.Z](https://quay.io/repository/kubespray/kubespray) and [quay.io/kubespray/vagrant:vX.Y.Z](https://quay.io/repository/kubespray/vagrant) container images are built and tagged. See the following `Container image creation` section for the details.
 9. The `KUBESPRAY_VERSION` variable is updated in `.gitlab-ci.yml`
 10. The release issue is closed
-11. An announcement email is sent to `kubernetes-dev@googlegroups.com` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
+11. An announcement email is sent to `dev@kubernetes.io` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
 12. The topic of the #kubespray channel is updated with `vX.Y.Z is released! | ...`
 
 ## Major/minor releases and milestones
@@ -60,4 +60,24 @@ release-notes --start-sha <The start commit-id> --end-sha <The end commit-id> --
 ```
 
 If the release note file(/tmp/kubespray-release-note) contains "### Uncategorized" pull requests, those pull requests don't have a valid kind label(`kind/feature`, etc.).
-It is necessary to put a valid label on each pull request and run the above release-notes command again to get a better release note)
+It is necessary to put a valid label on each pull request and run the above release-notes command again to get a better release note
+
+## Container image creation
+
+The container image `quay.io/kubespray/kubespray:vX.Y.Z` can be created from Dockerfile of the kubespray root directory:
+
+```shell
+cd kubespray/
+nerdctl build -t quay.io/kubespray/kubespray:vX.Y.Z .
+nerdctl push quay.io/kubespray/kubespray:vX.Y.Z
+```
+
+The container image `quay.io/kubespray/vagrant:vX.Y.Z` can be created from build.sh of test-infra/vagrant-docker/:
+
+```shell
+cd kubespray/test-infra/vagrant-docker/
+./build vX.Y.Z
+```
+
+Please note that the above operation requires the permission to push container images into quay.io/kubespray/.
+If you don't have the permission, please ask it on the #kubespray-dev channel.

SECURITY_CONTACTS

@@ -9,5 +9,7 @@
 #
 # DO NOT REPORT SECURITY VULNERABILITIES DIRECTLY TO THESE NAMES, FOLLOW THE
 # INSTRUCTIONS AT https://kubernetes.io/security/
-atoms
 mattymo
+floryut
+oomichi
+cristicalin

Vagrantfile

@@ -28,9 +28,10 @@ SUPPORTED_OS = {
   "centos8-bento"       => {box: "bento/centos-8",             user: "vagrant"},
   "almalinux8"          => {box: "almalinux/8",                user: "vagrant"},
   "almalinux8-bento"    => {box: "bento/almalinux-8",          user: "vagrant"},
-  "fedora34"            => {box: "fedora/34-cloud-base",       user: "vagrant"},
-  "fedora35"            => {box: "fedora/35-cloud-base",       user: "vagrant"},
-  "opensuse"            => {box: "opensuse/Leap-15.3.x86_64",  user: "vagrant"},
+  "rockylinux8"         => {box: "generic/rocky8",             user: "vagrant"},
+  "fedora37"            => {box: "fedora/37-cloud-base",       user: "vagrant"},
+  "fedora38"            => {box: "fedora/38-cloud-base",       user: "vagrant"},
+  "opensuse"            => {box: "opensuse/Leap-15.4.x86_64",  user: "vagrant"},
   "opensuse-tumbleweed" => {box: "opensuse/Tumbleweed.x86_64", user: "vagrant"},
   "oraclelinux"         => {box: "generic/oracle7",            user: "vagrant"},
   "oraclelinux8"        => {box: "generic/oracle8",            user: "vagrant"},
@@ -54,14 +55,14 @@ $subnet ||= "172.18.8"
 $subnet_ipv6 ||= "fd3c:b398:0698:0756"
 $os ||= "ubuntu1804"
 $network_plugin ||= "flannel"
-# Setting multi_networking to true will install Multus: https://github.com/intel/multus-cni
+# Setting multi_networking to true will install Multus: https://github.com/k8snetworkplumbingwg/multus-cni
 $multi_networking ||= "False"
 $download_run_once ||= "True"
 $download_force_cache ||= "False"
 # The first three nodes are etcd servers
-$etcd_instances ||= $num_instances
+$etcd_instances ||= [$num_instances, 3].min
 # The first two nodes are kube masters
-$kube_master_instances ||= $num_instances == 1 ? $num_instances : ($num_instances - 1)
+$kube_master_instances ||= [$num_instances, 2].min
 # All nodes are kube nodes
 $kube_node_instances ||= $num_instances
 # The following only works when using the libvirt provider
@@ -81,6 +82,13 @@ $playbook ||= "cluster.yml"
 
 host_vars = {}
 
+# throw error if os is not supported
+if ! SUPPORTED_OS.key?($os)
+  puts "Unsupported OS: #{$os}"
+  puts "Supported OS are: #{SUPPORTED_OS.keys.join(', ')}"
+  exit 1
+end
+
 $box = SUPPORTED_OS[$os][:box]
 # if $inventory is not set, try to use example
 $inventory = "inventory/sample" if ! $inventory
@@ -200,7 +208,8 @@ Vagrant.configure("2") do |config|
       end
 
       ip = "#{$subnet}.#{i+100}"
-      node.vm.network :private_network, ip: ip,
+      node.vm.network :private_network,
+        :ip => ip,
         :libvirt__guest_ipv6 => 'yes',
         :libvirt__ipv6_address => "#{$subnet_ipv6}::#{i+100}",
         :libvirt__ipv6_prefix => "64",
@@ -215,6 +224,14 @@ Vagrant.configure("2") do |config|
         node.vm.provision "shell", inline: "rm -f /etc/modprobe.d/local.conf"
         node.vm.provision "shell", inline: "sed -i '/net.ipv6.conf.all.disable_ipv6/d' /etc/sysctl.d/99-sysctl.conf /etc/sysctl.conf"
       end
+      # Hack for fedora37/38 to get the IP address of the second interface
+      if ["fedora37", "fedora38"].include? $os
+        config.vm.provision "shell", inline: <<-SHELL
+          nmcli conn modify 'Wired connection 2' ipv4.addresses $(cat /etc/sysconfig/network-scripts/ifcfg-eth1 | grep IPADDR | cut -d "=" -f2)
+          nmcli conn modify 'Wired connection 2' ipv4.method manual
+          service NetworkManager restart
+        SHELL
+      end
 
       # Disable firewalld on oraclelinux/redhat vms
       if ["oraclelinux","oraclelinux8","rhel7","rhel8"].include? $os
@@ -247,6 +264,7 @@ Vagrant.configure("2") do |config|
       if i == $num_instances
         node.vm.provision "ansible" do |ansible|
           ansible.playbook = $playbook
+          ansible.compatibility_mode = "2.0"
           ansible.verbose = $ansible_verbosity
           $ansible_inventory_path = File.join( $inventory, "hosts.ini")
           if File.exist?($ansible_inventory_path)

ansible.cfg

@@ -1,6 +1,6 @@
 [ssh_connection]
 pipelining=True
-ssh_args = -o ControlMaster=auto -o ControlPersist=30m -o ConnectionAttempts=100 -o UserKnownHostsFile=/dev/null
+ansible_ssh_args = -o ControlMaster=auto -o ControlPersist=30m -o ConnectionAttempts=100 -o UserKnownHostsFile=/dev/null
 #control_path = ~/.ssh/ansible-%%r@%%h:%%p
 [defaults]
 # https://github.com/ansible/ansible/issues/56930 (to ignore group names with - and .)
@@ -10,11 +10,11 @@ host_key_checking=False
 gathering = smart
 fact_caching = jsonfile
 fact_caching_connection = /tmp
-fact_caching_timeout = 7200
+fact_caching_timeout = 86400
 stdout_callback = default
 display_skipped_hosts = no
 library = ./library
-callback_whitelist = profile_tasks,ara_default
+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

cluster.yml

@@ -1,128 +1,3 @@
 ---
-- name: Check ansible version
-  import_playbook: ansible_version.yml
-
-- name: Ensure compatibility with old groups
-  import_playbook: legacy_groups.yml
-
-- hosts: bastion[0]
-  gather_facts: False
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: bastion-ssh-config, tags: ["localhost", "bastion"] }
-
-- hosts: k8s_cluster:etcd
-  strategy: linear
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  gather_facts: false
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: bootstrap-os, tags: bootstrap-os}
-
-- name: Gather facts
-  tags: always
-  import_playbook: facts.yml
-
-- hosts: k8s_cluster:etcd
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: kubernetes/preinstall, tags: preinstall }
-    - { role: "container-engine", tags: "container-engine", when: deploy_container_engine }
-    - { role: download, tags: download, when: "not skip_downloads" }
-
-- hosts: etcd
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - role: etcd
-      tags: etcd
-      vars:
-        etcd_cluster_setup: true
-        etcd_events_cluster_setup: "{{ etcd_events_cluster_enabled }}"
-      when: etcd_deployment_type != "kubeadm"
-
-- hosts: k8s_cluster
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - role: etcd
-      tags: etcd
-      vars:
-        etcd_cluster_setup: false
-        etcd_events_cluster_setup: false
-      when: etcd_deployment_type != "kubeadm"
-
-- hosts: k8s_cluster
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: kubernetes/node, tags: node }
-
-- hosts: kube_control_plane
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: kubernetes/control-plane, tags: master }
-    - { role: kubernetes/client, tags: client }
-    - { role: kubernetes-apps/cluster_roles, tags: cluster-roles }
-
-- hosts: k8s_cluster
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: kubernetes/kubeadm, tags: kubeadm}
-    - { role: kubernetes/node-label, tags: node-label }
-    - { role: network_plugin, tags: network }
-
-- hosts: calico_rr
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: network_plugin/calico/rr, tags: ['network', 'calico_rr'] }
-
-- hosts: kube_control_plane[0]
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: win_nodes/kubernetes_patch, tags: ["master", "win_nodes"] }
-
-- hosts: kube_control_plane
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: kubernetes-apps/external_cloud_controller, tags: external-cloud-controller }
-    - { role: kubernetes-apps/network_plugin, tags: network }
-    - { role: kubernetes-apps/policy_controller, tags: policy-controller }
-    - { role: kubernetes-apps/ingress_controller, tags: ingress-controller }
-    - { role: kubernetes-apps/external_provisioner, tags: external-provisioner }
-    - { role: kubernetes-apps, tags: apps }
-
-- name: Apply resolv.conf changes now that cluster DNS is up
-  hosts: k8s_cluster
-  gather_facts: False
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  environment: "{{ proxy_disable_env }}"
-  roles:
-    - { role: kubespray-defaults }
-    - { role: kubernetes/preinstall, when: "dns_mode != 'none' and resolvconf_mode == 'host_resolvconf'", tags: resolvconf, dns_late: true }
+- name: Install Kubernetes
+  ansible.builtin.import_playbook: playbooks/cluster.yml

contrib/aws_inventory/requirements.txt

@@ -1 +1 @@
-boto3  # Apache-2.0
+boto3  # Apache-2.0

contrib/azurerm/.gitignore

@@ -1,2 +1,2 @@
 .generated
-/inventory
+/inventory

contrib/azurerm/roles/generate-inventory_2/templates/inventory.j2

@@ -31,4 +31,3 @@
 [k8s_cluster:children]
 kube_node
 kube_control_plane
-

contrib/azurerm/roles/generate-templates/templates/availability-sets.json

@@ -27,4 +27,4 @@
       }
     }
   ]
-}
+}

contrib/azurerm/roles/generate-templates/templates/bastion.json

@@ -103,4 +103,4 @@
     }
     {% endif %}
   ]
-}
+}

contrib/azurerm/roles/generate-templates/templates/clear-rg.json

@@ -5,4 +5,4 @@
   "variables": {},
   "resources": [],
   "outputs": {}
-}
+}

contrib/azurerm/roles/generate-templates/templates/storage.json

@@ -16,4 +16,4 @@
       }
     }
   ]
-}
+}

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

@@ -43,7 +43,7 @@
   package:
     name: "{{ item }}"
     state: present
-  with_items: "{{ distro_extra_packages }} + [ 'rsyslog', 'openssh-server' ]"
+  with_items: "{{ distro_extra_packages + [ 'rsyslog', 'openssh-server' ] }}"
 
 - name: Start needed services
   service:

contrib/dind/run-test-distros.sh

@@ -17,7 +17,7 @@ pass_or_fail() {
 test_distro() {
     local distro=${1:?};shift
     local extra="${*:-}"
-    local prefix="$distro[${extra}]}"
+    local prefix="${distro[${extra}]}"
     ansible-playbook -i hosts dind-cluster.yaml -e node_distro=$distro
     pass_or_fail "$prefix: dind-nodes" || return 1
     (cd ../..
@@ -71,15 +71,15 @@ for spec in ${SPECS}; do
     echo "Loading file=${spec} ..."
     . ${spec} || continue
     : ${DISTROS:?} || continue
-    echo "DISTROS=${DISTROS[@]}"
+    echo "DISTROS:" "${DISTROS[@]}"
     echo "EXTRAS->"
     printf "  %s\n" "${EXTRAS[@]}"
     let n=1
-    for distro in ${DISTROS[@]}; do
+    for distro in "${DISTROS[@]}"; do
         for extra in "${EXTRAS[@]:-NULL}"; do
             # Magic value to let this for run once:
             [[ ${extra} == NULL ]] && unset extra
-            docker rm -f ${NODES[@]}
+            docker rm -f "${NODES[@]}"
             printf -v file_out "%s/%s-%02d.out" ${OUTPUT_DIR} ${spec} $((n++))
             {
                 info "${distro}[${extra}] START: file_out=${file_out}"

contrib/inventory_builder/requirements.txt

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

contrib/inventory_builder/test-requirements.txt

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

contrib/inventory_builder/tests/test_inventory.py

@@ -13,7 +13,7 @@
 # under the License.
 
 import inventory
-from test import support
+from io import StringIO
 import unittest
 from unittest import mock
 
@@ -41,7 +41,7 @@ class TestInventoryPrintHostnames(unittest.TestCase):
                       'access_ip': '10.90.0.3'}}}})
         with mock.patch('builtins.open', mock_io):
             with self.assertRaises(SystemExit) as cm:
-                with support.captured_stdout() as stdout:
+                with mock.patch('sys.stdout', new_callable=StringIO) as stdout:
                     inventory.KubesprayInventory(
                         changed_hosts=["print_hostnames"],
                         config_file="file")

contrib/kvm-setup/group_vars/all

@@ -1,3 +1,2 @@
 #k8s_deployment_user: kubespray
 #k8s_deployment_user_pkey_path: /tmp/ssh_rsa
-

contrib/network-storage/glusterfs/inventory.example

@@ -41,4 +41,3 @@
 
 # [network-storage:children]
 # gfs-cluster
-

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

@@ -14,12 +14,16 @@ This role performs basic installation and setup of Gluster, but it does not conf
 
 Available variables are listed below, along with default values (see `defaults/main.yml`):
 
-    glusterfs_default_release: ""
+```yaml
+glusterfs_default_release: ""
+```
 
 You can specify a `default_release` for apt on Debian/Ubuntu by overriding this variable. This is helpful if you need a different package or version for the main GlusterFS packages (e.g. GlusterFS 3.5.x instead of 3.2.x with the `wheezy-backports` default release on Debian Wheezy).
 
-    glusterfs_ppa_use: yes
-    glusterfs_ppa_version: "3.5"
+```yaml
+glusterfs_ppa_use: yes
+glusterfs_ppa_version: "3.5"
+```
 
 For Ubuntu, specify whether to use the official Gluster PPA, and which version of the PPA to use. See Gluster's [Getting Started Guide](https://docs.gluster.org/en/latest/Quick-Start-Guide/Quickstart/) for more info.
 
@@ -29,9 +33,11 @@ None.
 
 ## Example Playbook
 
+```yaml
     - hosts: server
       roles:
         - geerlingguy.glusterfs
+```
 
 For a real-world use example, read through [Simple GlusterFS Setup with Ansible](http://www.jeffgeerling.com/blog/simple-glusterfs-setup-ansible), a blog post by this role's author, which is included in Chapter 8 of [Ansible for DevOps](https://www.ansiblefordevops.com/).
 

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

@@ -21,4 +21,3 @@
     {% endfor %}
   ]
 }
-

contrib/offline/README.md

@@ -45,3 +45,21 @@ temp
 
 In some cases you may want to update some component version, you can declare version variables in ansible inventory file or group_vars,
 then run `./generate_list.sh -i [inventory_file]` to update file.list and images.list.
+
+## manage-offline-files.sh
+
+This script will download all files according to `temp/files.list` and run nginx container to provide offline file download.
+
+Step(1) generate `files.list`
+
+```shell
+./generate_list.sh
+```
+
+Step(2) download files and run nginx container
+
+```shell
+./manage-offline-files.sh
+```
+
+when nginx container is running, it can be accessed through <http://127.0.0.1:8080/>.

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

@@ -15,7 +15,7 @@ function create_container_image_tar() {
 	IMAGES=$(kubectl describe pods --all-namespaces | grep " Image:" | awk '{print $2}' | sort | uniq)
 	# NOTE: etcd and pause cannot be seen as pods.
 	# The pause image is used for --pod-infra-container-image option of kubelet.
-	EXT_IMAGES=$(kubectl cluster-info dump | egrep "quay.io/coreos/etcd:|k8s.gcr.io/pause:" | sed s@\"@@g)
+	EXT_IMAGES=$(kubectl cluster-info dump | egrep "quay.io/coreos/etcd:|registry.k8s.io/pause:" | sed s@\"@@g)
 	IMAGES="${IMAGES} ${EXT_IMAGES}"
 
 	rm -f  ${IMAGE_TAR_FILE}
@@ -46,12 +46,12 @@ function create_container_image_tar() {
 
 		# NOTE: Here removes the following repo parts from each image
 		# so that these parts will be replaced with Kubespray.
-		# - kube_image_repo: "k8s.gcr.io"
+		# - kube_image_repo: "registry.k8s.io"
 		# - gcr_image_repo: "gcr.io"
 		# - docker_image_repo: "docker.io"
 		# - quay_image_repo: "quay.io"
 		FIRST_PART=$(echo ${image} | awk -F"/" '{print $1}')
-		if [ "${FIRST_PART}" = "k8s.gcr.io" ] ||
+		if [ "${FIRST_PART}" = "registry.k8s.io" ] ||
 		   [ "${FIRST_PART}" = "gcr.io" ] ||
 		   [ "${FIRST_PART}" = "docker.io" ] ||
 		   [ "${FIRST_PART}" = "quay.io" ] ||

contrib/offline/manage-offline-files.sh

@@ -0,0 +1,44 @@
+#!/bin/bash
+
+CURRENT_DIR=$( dirname "$(readlink -f "$0")" )
+OFFLINE_FILES_DIR_NAME="offline-files"
+OFFLINE_FILES_DIR="${CURRENT_DIR}/${OFFLINE_FILES_DIR_NAME}"
+OFFLINE_FILES_ARCHIVE="${CURRENT_DIR}/offline-files.tar.gz"
+FILES_LIST=${FILES_LIST:-"${CURRENT_DIR}/temp/files.list"}
+NGINX_PORT=8080
+
+# download files
+if [ ! -f "${FILES_LIST}" ]; then
+    echo "${FILES_LIST} should exist, run ./generate_list.sh first."
+    exit 1
+fi
+
+rm -rf "${OFFLINE_FILES_DIR}"
+rm "${OFFLINE_FILES_ARCHIVE}"
+mkdir  "${OFFLINE_FILES_DIR}"
+
+wget -x -P "${OFFLINE_FILES_DIR}" -i "${FILES_LIST}"
+tar -czvf "${OFFLINE_FILES_ARCHIVE}"  "${OFFLINE_FILES_DIR_NAME}"
+
+[ -n "$NO_HTTP_SERVER" ] && echo "skip to run nginx" && exit 0
+
+# run nginx container server
+if command -v nerdctl 1>/dev/null 2>&1; then
+    runtime="nerdctl"
+elif command -v podman 1>/dev/null 2>&1; then
+    runtime="podman"
+elif command -v docker 1>/dev/null 2>&1; then
+    runtime="docker"
+else
+    echo "No supported container runtime found"
+    exit 1
+fi
+
+sudo "${runtime}" container inspect nginx >/dev/null 2>&1
+if [ $? -ne 0 ]; then
+    sudo "${runtime}" run \
+        --restart=always -d -p ${NGINX_PORT}:80 \
+        --volume "${OFFLINE_FILES_DIR}:/usr/share/nginx/html/download" \
+        --volume "$(pwd)"/nginx.conf:/etc/nginx/nginx.conf \
+        --name nginx nginx:alpine
+fi

contrib/offline/nginx.conf

@@ -0,0 +1,39 @@
+user nginx;
+worker_processes auto;
+error_log /var/log/nginx/error.log;
+pid /run/nginx.pid;
+include /usr/share/nginx/modules/*.conf;
+events {
+    worker_connections 1024;
+}
+http {
+    log_format  main  '$remote_addr - $remote_user [$time_local] "$request" '
+                      '$status $body_bytes_sent "$http_referer" '
+                      '"$http_user_agent" "$http_x_forwarded_for"';
+    access_log  /var/log/nginx/access.log  main;
+    sendfile            on;
+    tcp_nopush          on;
+    tcp_nodelay         on;
+    keepalive_timeout   65;
+    types_hash_max_size 2048;
+    default_type        application/octet-stream;
+    include /etc/nginx/conf.d/*.conf;
+    server {
+        listen       80 default_server;
+        listen       [::]:80 default_server;
+        server_name  _;
+        include /etc/nginx/default.d/*.conf;
+        location / {
+            root    /usr/share/nginx/html/download;
+        autoindex on;
+        autoindex_exact_size off;
+        autoindex_localtime on;
+        }
+        error_page 404 /404.html;
+            location = /40x.html {
+        }
+        error_page 500 502 503 504 /50x.html;
+            location = /50x.html {
+        }
+    }
+}

contrib/terraform/aws/README.md

@@ -36,8 +36,7 @@ terraform apply -var-file=credentials.tfvars
 ```
 
 - Terraform automatically creates an Ansible Inventory file called `hosts` with the created infrastructure in the directory `inventory`
-- Ansible will automatically generate an ssh config file for your bastion hosts. To connect to hosts with ssh using bastion host use generated ssh-bastion.conf.
-  Ansible automatically detects bastion and changes ssh_args  
+- Ansible will automatically generate an ssh config file for your bastion hosts. To connect to hosts with ssh using bastion host use generated `ssh-bastion.conf`. Ansible automatically detects bastion and changes `ssh_args`
 
 ```commandline
 ssh -F ./ssh-bastion.conf user@$ip

contrib/terraform/equinix/README.md

@@ -12,7 +12,7 @@ This will install a Kubernetes cluster on Equinix Metal. It should work in all l
 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)
+file to generate a dynamic inventory that is consumed by [cluster.yml](../../../cluster.yml)
 to actually install Kubernetes with Kubespray.
 
 ### Kubernetes Nodes
@@ -60,16 +60,16 @@ Terraform will be used to provision all of the Equinix Metal resources with base
 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/metal/sample-inventory inventory/$CLUSTER
+cp -LRp contrib/terraform/equinix/sample-inventory inventory/$CLUSTER
 cd inventory/$CLUSTER
-ln -s ../../contrib/terraform/metal/hosts
+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 `PACKET_AUTH_TOKEN` environment variable.
+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!
 
@@ -80,10 +80,12 @@ The Equinix Metal Project ID associated with the key will be set later in `clust
 
 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 PACKET_AUTH_TOKEN="Example-API-Token"
+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).
@@ -101,7 +103,7 @@ 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
-- metal_project_id = the Equinix Metal Project ID associated with the Equinix Metal API token above
+- equinix_metal_project_id = the Equinix Metal Project ID associated with the Equinix Metal API token above
 
 #### Enable localhost access
 
@@ -119,12 +121,13 @@ Once the Kubespray playbooks are run, a Kubernetes configuration file will be wr
 
 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 `terraform/metal` directory :
+`.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.
 
@@ -135,7 +138,7 @@ plugins. This is accomplished as follows:
 
 ```ShellSession
 cd inventory/$CLUSTER
-terraform init ../../contrib/terraform/metal
+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.
@@ -146,7 +149,7 @@ You can apply the Terraform configuration to your cluster with the following com
 issued from your cluster's inventory directory (`inventory/$CLUSTER`):
 
 ```ShellSession
-terraform apply -var-file=cluster.tfvars ../../contrib/terraform/metal
+terraform -chdir=../../contrib/terraform/equinix apply -var-file=cluster.tfvars
 export ANSIBLE_HOST_KEY_CHECKING=False
 ansible-playbook -i hosts ../../cluster.yml
 ```
@@ -156,7 +159,7 @@ ansible-playbook -i hosts ../../cluster.yml
 You can destroy your new cluster with the following command issued from the cluster's inventory directory:
 
 ```ShellSession
-terraform destroy -var-file=cluster.tfvars ../../contrib/terraform/metal
+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:

contrib/terraform/equinix/kubespray.tf

@@ -1,62 +1,57 @@
-# Configure the Equinix Metal Provider
-provider "metal" {
-}
-
-resource "metal_ssh_key" "k8s" {
+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 "metal_device" "k8s_master" {
-  depends_on = [metal_ssh_key.k8s]
+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
-  facilities       = [var.facility]
+  metro            = var.metro
   operating_system = var.operating_system
   billing_cycle    = var.billing_cycle
-  project_id       = var.metal_project_id
+  project_id       = var.equinix_metal_project_id
   tags             = ["cluster-${var.cluster_name}", "k8s_cluster", "kube_control_plane", "etcd", "kube_node"]
 }
 
-resource "metal_device" "k8s_master_no_etcd" {
-  depends_on = [metal_ssh_key.k8s]
+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
-  facilities       = [var.facility]
+  metro            = var.metro
   operating_system = var.operating_system
   billing_cycle    = var.billing_cycle
-  project_id       = var.metal_project_id
+  project_id       = var.equinix_metal_project_id
   tags             = ["cluster-${var.cluster_name}", "k8s_cluster", "kube_control_plane"]
 }
 
-resource "metal_device" "k8s_etcd" {
-  depends_on = [metal_ssh_key.k8s]
+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
-  facilities       = [var.facility]
+  metro            = var.metro
   operating_system = var.operating_system
   billing_cycle    = var.billing_cycle
-  project_id       = var.metal_project_id
+  project_id       = var.equinix_metal_project_id
   tags             = ["cluster-${var.cluster_name}", "etcd"]
 }
 
-resource "metal_device" "k8s_node" {
-  depends_on = [metal_ssh_key.k8s]
+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
-  facilities       = [var.facility]
+  metro            = var.metro
   operating_system = var.operating_system
   billing_cycle    = var.billing_cycle
-  project_id       = var.metal_project_id
+  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 = "~> 1.14"
+    }
+  }
+}
+
+# Configure the Equinix Metal Provider
+provider "equinix" {
+}

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

@@ -1,16 +1,19 @@
 # your Kubernetes cluster name here
 cluster_name = "mycluster"
 
-# Your Equinix Metal project ID. See hhttps://metal.equinix.com/developers/docs/accounts/
-metal_project_id = "Example-API-Token"
+# 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"
 
-# cluster location
-facility = "ewr1"
+# Equinix interconnected bare metal across our global metros.
+metro = "da"
+
+# operating_system
+operating_system = "ubuntu_22_04"
 
 # standalone etcds
 number_of_etcd = 0

contrib/terraform/equinix/variables.tf

@@ -2,12 +2,12 @@ variable "cluster_name" {
   default = "kubespray"
 }
 
-variable "metal_project_id" {
+variable "equinix_metal_project_id" {
   description = "Your Equinix Metal project ID. See https://metal.equinix.com/developers/docs/accounts/"
 }
 
 variable "operating_system" {
-  default = "ubuntu_20_04"
+  default = "ubuntu_22_04"
 }
 
 variable "public_key_path" {
@@ -19,8 +19,8 @@ variable "billing_cycle" {
   default = "hourly"
 }
 
-variable "facility" {
-  default = "dfw2"
+variable "metro" {
+  default = "da"
 }
 
 variable "plan_k8s_masters" {
@@ -54,4 +54,3 @@ variable "number_of_etcd" {
 variable "number_of_k8s_nodes" {
   default = 1
 }
-

contrib/terraform/exoscale/README.md

@@ -31,9 +31,7 @@ The setup looks like following
 
 ## Requirements
 
-* Terraform 0.13.0 or newer
-
-*0.12 also works if you modify the provider block to include version and remove all `versions.tf` files*
+* Terraform 0.13.0 or newer (0.12 also works if you modify the provider block to include version and remove all `versions.tf` files)
 
 ## Quickstart
 

contrib/terraform/exoscale/default.tfvars

@@ -12,7 +12,7 @@ ssh_public_keys = [
 machines = {
   "master-0" : {
     "node_type" : "master",
-    "size" : "Medium",
+    "size" : "standard.medium",
     "boot_disk" : {
       "image_name" : "Linux Ubuntu 20.04 LTS 64-bit",
       "root_partition_size" : 50,
@@ -22,7 +22,7 @@ machines = {
   },
   "worker-0" : {
     "node_type" : "worker",
-    "size" : "Large",
+    "size" : "standard.large",
     "boot_disk" : {
       "image_name" : "Linux Ubuntu 20.04 LTS 64-bit",
       "root_partition_size" : 50,
@@ -32,7 +32,7 @@ machines = {
   },
   "worker-1" : {
     "node_type" : "worker",
-    "size" : "Large",
+    "size" : "standard.large",
     "boot_disk" : {
       "image_name" : "Linux Ubuntu 20.04 LTS 64-bit",
       "root_partition_size" : 50,
@@ -42,7 +42,7 @@ machines = {
   },
   "worker-2" : {
     "node_type" : "worker",
-    "size" : "Large",
+    "size" : "standard.large",
     "boot_disk" : {
       "image_name" : "Linux Ubuntu 20.04 LTS 64-bit",
       "root_partition_size" : 50,

contrib/terraform/exoscale/main.tf

@@ -3,8 +3,8 @@ provider "exoscale" {}
 module "kubernetes" {
   source = "./modules/kubernetes-cluster"
 
-  prefix = var.prefix
-
+  prefix   = var.prefix
+  zone     = var.zone
   machines = var.machines
 
   ssh_public_keys = var.ssh_public_keys

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

@@ -1,29 +1,25 @@
-data "exoscale_compute_template" "os_image" {
+data "exoscale_template" "os_image" {
   for_each = var.machines
 
   zone = var.zone
   name = each.value.boot_disk.image_name
 }
 
-data "exoscale_compute" "master_nodes" {
-  for_each = exoscale_compute.master
+data "exoscale_compute_instance" "master_nodes" {
+  for_each = exoscale_compute_instance.master
 
-  id = each.value.id
-
-  # Since private IP address is not assigned until the nics are created we need this
-  depends_on = [exoscale_nic.master_private_network_nic]
+  id   = each.value.id
+  zone = var.zone
 }
 
-data "exoscale_compute" "worker_nodes" {
-  for_each = exoscale_compute.worker
+data "exoscale_compute_instance" "worker_nodes" {
+  for_each = exoscale_compute_instance.worker
 
-  id = each.value.id
-
-  # Since private IP address is not assigned until the nics are created we need this
-  depends_on = [exoscale_nic.worker_private_network_nic]
+  id   = each.value.id
+  zone = var.zone
 }
 
-resource "exoscale_network" "private_network" {
+resource "exoscale_private_network" "private_network" {
   zone = var.zone
   name = "${var.prefix}-network"
 
@@ -34,25 +30,29 @@ resource "exoscale_network" "private_network" {
   netmask = cidrnetmask(var.private_network_cidr)
 }
 
-resource "exoscale_compute" "master" {
+resource "exoscale_compute_instance" "master" {
   for_each = {
     for name, machine in var.machines :
     name => machine
     if machine.node_type == "master"
   }
 
-  display_name    = "${var.prefix}-${each.key}"
-  template_id     = data.exoscale_compute_template.os_image[each.key].id
-  size            = each.value.size
-  disk_size       = each.value.boot_disk.root_partition_size + each.value.boot_disk.node_local_partition_size + each.value.boot_disk.ceph_partition_size
-  state           = "Running"
-  zone            = var.zone
-  security_groups = [exoscale_security_group.master_sg.name]
+  name               = "${var.prefix}-${each.key}"
+  template_id        = data.exoscale_template.os_image[each.key].id
+  type               = each.value.size
+  disk_size          = each.value.boot_disk.root_partition_size + each.value.boot_disk.node_local_partition_size + each.value.boot_disk.ceph_partition_size
+  state              = "Running"
+  zone               = var.zone
+  security_group_ids = [exoscale_security_group.master_sg.id]
+  network_interface {
+    network_id = exoscale_private_network.private_network.id
+  }
+  elastic_ip_ids = [exoscale_elastic_ip.control_plane_lb.id]
 
   user_data = templatefile(
     "${path.module}/templates/cloud-init.tmpl",
     {
-      eip_ip_address            = exoscale_ipaddress.ingress_controller_lb.ip_address
+      eip_ip_address            = exoscale_elastic_ip.ingress_controller_lb.ip_address
       node_local_partition_size = each.value.boot_disk.node_local_partition_size
       ceph_partition_size       = each.value.boot_disk.ceph_partition_size
       root_partition_size       = each.value.boot_disk.root_partition_size
@@ -62,25 +62,29 @@ resource "exoscale_compute" "master" {
   )
 }
 
-resource "exoscale_compute" "worker" {
+resource "exoscale_compute_instance" "worker" {
   for_each = {
     for name, machine in var.machines :
     name => machine
     if machine.node_type == "worker"
   }
 
-  display_name    = "${var.prefix}-${each.key}"
-  template_id     = data.exoscale_compute_template.os_image[each.key].id
-  size            = each.value.size
-  disk_size       = each.value.boot_disk.root_partition_size + each.value.boot_disk.node_local_partition_size + each.value.boot_disk.ceph_partition_size
-  state           = "Running"
-  zone            = var.zone
-  security_groups = [exoscale_security_group.worker_sg.name]
+  name               = "${var.prefix}-${each.key}"
+  template_id        = data.exoscale_template.os_image[each.key].id
+  type               = each.value.size
+  disk_size          = each.value.boot_disk.root_partition_size + each.value.boot_disk.node_local_partition_size + each.value.boot_disk.ceph_partition_size
+  state              = "Running"
+  zone               = var.zone
+  security_group_ids = [exoscale_security_group.worker_sg.id]
+  network_interface {
+    network_id = exoscale_private_network.private_network.id
+  }
+  elastic_ip_ids = [exoscale_elastic_ip.ingress_controller_lb.id]
 
   user_data = templatefile(
     "${path.module}/templates/cloud-init.tmpl",
     {
-      eip_ip_address            = exoscale_ipaddress.ingress_controller_lb.ip_address
+      eip_ip_address            = exoscale_elastic_ip.ingress_controller_lb.ip_address
       node_local_partition_size = each.value.boot_disk.node_local_partition_size
       ceph_partition_size       = each.value.boot_disk.ceph_partition_size
       root_partition_size       = each.value.boot_disk.root_partition_size
@@ -90,41 +94,33 @@ resource "exoscale_compute" "worker" {
   )
 }
 
-resource "exoscale_nic" "master_private_network_nic" {
-  for_each = exoscale_compute.master
-
-  compute_id = each.value.id
-  network_id = exoscale_network.private_network.id
-}
-
-resource "exoscale_nic" "worker_private_network_nic" {
-  for_each = exoscale_compute.worker
-
-  compute_id = each.value.id
-  network_id = exoscale_network.private_network.id
-}
-
 resource "exoscale_security_group" "master_sg" {
   name        = "${var.prefix}-master-sg"
   description = "Security group for Kubernetes masters"
 }
 
-resource "exoscale_security_group_rules" "master_sg_rules" {
+resource "exoscale_security_group_rule" "master_sg_rule_ssh" {
   security_group_id = exoscale_security_group.master_sg.id
 
+  for_each = toset(var.ssh_whitelist)
   # SSH
-  ingress {
-    protocol  = "TCP"
-    cidr_list = var.ssh_whitelist
-    ports     = ["22"]
-  }
+  type       = "INGRESS"
+  start_port = 22
+  end_port   = 22
+  protocol   = "TCP"
+  cidr       = each.value
+}
 
+resource "exoscale_security_group_rule" "master_sg_rule_k8s_api" {
+  security_group_id = exoscale_security_group.master_sg.id
+
+  for_each = toset(var.api_server_whitelist)
   # Kubernetes API
-  ingress {
-    protocol  = "TCP"
-    cidr_list = var.api_server_whitelist
-    ports     = ["6443"]
-  }
+  type       = "INGRESS"
+  start_port = 6443
+  end_port   = 6443
+  protocol   = "TCP"
+  cidr       = each.value
 }
 
 resource "exoscale_security_group" "worker_sg" {
@@ -132,62 +128,64 @@ resource "exoscale_security_group" "worker_sg" {
   description = "security group for kubernetes worker nodes"
 }
 
-resource "exoscale_security_group_rules" "worker_sg_rules" {
+resource "exoscale_security_group_rule" "worker_sg_rule_ssh" {
   security_group_id = exoscale_security_group.worker_sg.id
 
   # SSH
-  ingress {
-    protocol  = "TCP"
-    cidr_list = var.ssh_whitelist
-    ports     = ["22"]
-  }
+  for_each   = toset(var.ssh_whitelist)
+  type       = "INGRESS"
+  start_port = 22
+  end_port   = 22
+  protocol   = "TCP"
+  cidr       = each.value
+}
+
+resource "exoscale_security_group_rule" "worker_sg_rule_http" {
+  security_group_id = exoscale_security_group.worker_sg.id
 
   # HTTP(S)
-  ingress {
-    protocol  = "TCP"
-    cidr_list = ["0.0.0.0/0"]
-    ports     = ["80", "443"]
-  }
+  for_each   = toset(["80", "443"])
+  type       = "INGRESS"
+  start_port = each.value
+  end_port   = each.value
+  protocol   = "TCP"
+  cidr       = "0.0.0.0/0"
+}
 
-  # Kubernetes Nodeport
-  ingress {
-    protocol  = "TCP"
-    cidr_list = var.nodeport_whitelist
-    ports     = ["30000-32767"]
+
+resource "exoscale_security_group_rule" "worker_sg_rule_nodeport" {
+  security_group_id = exoscale_security_group.worker_sg.id
+
+  # HTTP(S)
+  for_each   = toset(var.nodeport_whitelist)
+  type       = "INGRESS"
+  start_port = 30000
+  end_port   = 32767
+  protocol   = "TCP"
+  cidr       = each.value
+}
+
+resource "exoscale_elastic_ip" "ingress_controller_lb" {
+  zone = var.zone
+  healthcheck {
+    mode         = "http"
+    port         = 80
+    uri          = "/healthz"
+    interval     = 10
+    timeout      = 2
+    strikes_ok   = 2
+    strikes_fail = 3
   }
 }
 
-resource "exoscale_ipaddress" "ingress_controller_lb" {
-  zone                     = var.zone
-  healthcheck_mode         = "http"
-  healthcheck_port         = 80
-  healthcheck_path         = "/healthz"
-  healthcheck_interval     = 10
-  healthcheck_timeout      = 2
-  healthcheck_strikes_ok   = 2
-  healthcheck_strikes_fail = 3
-}
-
-resource "exoscale_secondary_ipaddress" "ingress_controller_lb" {
-  for_each = exoscale_compute.worker
-
-  compute_id = each.value.id
-  ip_address = exoscale_ipaddress.ingress_controller_lb.ip_address
-}
-
-resource "exoscale_ipaddress" "control_plane_lb" {
-  zone                     = var.zone
-  healthcheck_mode         = "tcp"
-  healthcheck_port         = 6443
-  healthcheck_interval     = 10
-  healthcheck_timeout      = 2
-  healthcheck_strikes_ok   = 2
-  healthcheck_strikes_fail = 3
-}
-
-resource "exoscale_secondary_ipaddress" "control_plane_lb" {
-  for_each = exoscale_compute.master
-
-  compute_id = each.value.id
-  ip_address = exoscale_ipaddress.control_plane_lb.ip_address
+resource "exoscale_elastic_ip" "control_plane_lb" {
+  zone = var.zone
+  healthcheck {
+    mode         = "tcp"
+    port         = 6443
+    interval     = 10
+    timeout      = 2
+    strikes_ok   = 2
+    strikes_fail = 3
+  }
 }

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

@@ -1,19 +1,19 @@
 output "master_ip_addresses" {
   value = {
-    for key, instance in exoscale_compute.master :
+    for key, instance in exoscale_compute_instance.master :
     instance.name => {
-      "private_ip" = contains(keys(data.exoscale_compute.master_nodes), key) ? data.exoscale_compute.master_nodes[key].private_network_ip_addresses[0] : ""
-      "public_ip"  = exoscale_compute.master[key].ip_address
+      "private_ip" = contains(keys(data.exoscale_compute_instance.master_nodes), key) ? data.exoscale_compute_instance.master_nodes[key].private_network_ip_addresses[0] : ""
+      "public_ip"  = exoscale_compute_instance.master[key].ip_address
     }
   }
 }
 
 output "worker_ip_addresses" {
   value = {
-    for key, instance in exoscale_compute.worker :
+    for key, instance in exoscale_compute_instance.worker :
     instance.name => {
-      "private_ip" = contains(keys(data.exoscale_compute.worker_nodes), key) ? data.exoscale_compute.worker_nodes[key].private_network_ip_addresses[0] : ""
-      "public_ip"  = exoscale_compute.worker[key].ip_address
+      "private_ip" = contains(keys(data.exoscale_compute_instance.worker_nodes), key) ? data.exoscale_compute_instance.worker_nodes[key].private_network_ip_addresses[0] : ""
+      "public_ip"  = exoscale_compute_instance.worker[key].ip_address
     }
   }
 }
@@ -23,9 +23,9 @@ output "cluster_private_network_cidr" {
 }
 
 output "ingress_controller_lb_ip_address" {
-  value = exoscale_ipaddress.ingress_controller_lb.ip_address
+  value = exoscale_elastic_ip.ingress_controller_lb.ip_address
 }
 
 output "control_plane_lb_ip_address" {
-  value = exoscale_ipaddress.control_plane_lb.ip_address
+  value = exoscale_elastic_ip.control_plane_lb.ip_address
 }

contrib/terraform/exoscale/modules/kubernetes-cluster/versions.tf

@@ -1,7 +1,7 @@
 terraform {
   required_providers {
     exoscale = {
-      source = "exoscale/exoscale"
+      source  = "exoscale/exoscale"
       version = ">= 0.21"
     }
   }

contrib/terraform/gcp/README.md

@@ -75,6 +75,11 @@ ansible-playbook -i contrib/terraform/gcs/inventory.ini cluster.yml -b -v
 * `api_server_whitelist`: List of IP ranges (CIDR) that will be allowed to connect to the API server
 * `nodeport_whitelist`: List of IP ranges (CIDR) that will be allowed to connect to the kubernetes nodes on port 30000-32767 (kubernetes nodeports)
 * `ingress_whitelist`: List of IP ranges (CIDR) that will be allowed to connect to ingress on ports 80 and 443
+* `extra_ingress_firewalls`: Additional ingress firewall rules. Key will be used as the name of the rule
+  * `source_ranges`: List of IP ranges (CIDR). Example: `["8.8.8.8"]`
+  * `protocol`: Protocol. Example `"tcp"`
+  * `ports`: List of ports, as string. Example `["53"]`
+  * `target_tags`: List of target tag (either the machine name or `control-plane` or `worker`). Example: `["control-plane", "worker-0"]`
 
 ### Optional
 

contrib/terraform/gcp/main.tf

@@ -34,4 +34,6 @@ module "kubernetes" {
   api_server_whitelist = var.api_server_whitelist
   nodeport_whitelist   = var.nodeport_whitelist
   ingress_whitelist    = var.ingress_whitelist
+
+  extra_ingress_firewalls = var.extra_ingress_firewalls
 }

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

@@ -219,7 +219,7 @@ resource "google_compute_instance" "master" {
   machine_type = each.value.size
   zone         = each.value.zone
 
-  tags = ["master"]
+  tags = ["control-plane", "master", each.key]
 
   boot_disk {
     initialize_params {
@@ -325,7 +325,7 @@ resource "google_compute_instance" "worker" {
   machine_type = each.value.size
   zone         = each.value.zone
 
-  tags = ["worker"]
+  tags = ["worker", each.key]
 
   boot_disk {
     initialize_params {
@@ -398,3 +398,24 @@ resource "google_compute_target_pool" "worker_lb" {
   name      = "${var.prefix}-worker-lb-pool"
   instances = local.worker_target_list
 }
+
+resource "google_compute_firewall" "extra_ingress_firewall" {
+  for_each = {
+    for name, firewall in var.extra_ingress_firewalls :
+    name => firewall
+  }
+
+  name    = "${var.prefix}-${each.key}-ingress"
+  network = google_compute_network.main.name
+
+  priority = 100
+
+  source_ranges = each.value.source_ranges
+
+  target_tags = each.value.target_tags
+
+  allow {
+    protocol = each.value.protocol
+    ports    = each.value.ports
+  }
+}

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

@@ -14,7 +14,7 @@ variable "machines" {
     }))
     boot_disk = object({
       image_name = string
-      size = number
+      size       = number
     })
   }))
 }
@@ -73,3 +73,14 @@ variable "ingress_whitelist" {
 variable "private_network_cidr" {
   default = "10.0.10.0/24"
 }
+
+variable "extra_ingress_firewalls" {
+  type = map(object({
+    source_ranges = set(string)
+    protocol      = string
+    ports         = list(string)
+    target_tags   = set(string)
+  }))
+
+  default = {}
+}

contrib/terraform/gcp/variables.tf

@@ -95,3 +95,14 @@ variable "ingress_whitelist" {
   type = list(string)
   default = ["0.0.0.0/0"]
 }
+
+variable "extra_ingress_firewalls" {
+  type = map(object({
+    source_ranges = set(string)
+    protocol      = string
+    ports         = list(string)
+    target_tags   = set(string)
+  }))
+
+  default = {}
+}

contrib/terraform/hetzner/README.md

@@ -56,11 +56,24 @@ cd inventory/$CLUSTER
 
 Edit `default.tfvars` to match your requirement.
 
+Flatcar Container Linux instead of the basic Hetzner Images.
+
+```bash
+cd ../../contrib/terraform/hetzner
+```
+
+Edit `main.tf` and reactivate the module `source = "./modules/kubernetes-cluster-flatcar"`and
+comment out the `#source = "./modules/kubernetes-cluster"`.
+
+activate `ssh_private_key_path = var.ssh_private_key_path`. The VM boots into
+Rescue-Mode with the selected image of the `var.machines` but installs Flatcar instead.
+
 Run Terraform to create the infrastructure.
 
 ```bash
-terraform init ../../contrib/terraform/hetzner
-terraform apply --var-file default.tfvars ../../contrib/terraform/hetzner/
+cd ./kubespray
+terraform -chdir=./contrib/terraform/hetzner/ init
+terraform -chdir=./contrib/terraform/hetzner/ apply --var-file=../../../inventory/$CLUSTER/default.tfvars
 ```
 
 You should now have a inventory file named `inventory.ini` that you can use with kubespray.

contrib/terraform/hetzner/default.tfvars

@@ -1,6 +1,6 @@
-prefix = "default"
-zone   = "hel1"
-network_zone = "eu-central"
+prefix         = "default"
+zone           = "hel1"
+network_zone   = "eu-central"
 inventory_file = "inventory.ini"
 
 ssh_public_keys = [
@@ -9,21 +9,23 @@ ssh_public_keys = [
   "ssh-rsa I-did-not-read-the-docs 2",
 ]
 
+ssh_private_key_path = "~/.ssh/id_rsa"
+
 machines = {
   "master-0" : {
     "node_type" : "master",
     "size" : "cx21",
-    "image" : "ubuntu-20.04",
+    "image" : "ubuntu-22.04",
   },
   "worker-0" : {
     "node_type" : "worker",
     "size" : "cx21",
-    "image" : "ubuntu-20.04",
+    "image" : "ubuntu-22.04",
   },
   "worker-1" : {
     "node_type" : "worker",
     "size" : "cx21",
-    "image" : "ubuntu-20.04",
+    "image" : "ubuntu-22.04",
   }
 }
 

contrib/terraform/hetzner/main.tf

@@ -2,6 +2,7 @@ provider "hcloud" {}
 
 module "kubernetes" {
   source = "./modules/kubernetes-cluster"
+  # source = "./modules/kubernetes-cluster-flatcar"
 
   prefix = var.prefix
 
@@ -9,8 +10,11 @@ module "kubernetes" {
 
   machines = var.machines
 
+  #only for flatcar
+  #ssh_private_key_path = var.ssh_private_key_path
+
   ssh_public_keys = var.ssh_public_keys
-  network_zone = var.network_zone
+  network_zone    = var.network_zone
 
   ssh_whitelist        = var.ssh_whitelist
   api_server_whitelist = var.api_server_whitelist
@@ -22,31 +26,32 @@ module "kubernetes" {
 # Generate ansible inventory
 #
 
-data "template_file" "inventory" {
-  template = file("${path.module}/templates/inventory.tpl")
-
-  vars = {
-    connection_strings_master = join("\n", formatlist("%s ansible_user=ubuntu ansible_host=%s ip=%s etcd_member_name=etcd%d",
-      keys(module.kubernetes.master_ip_addresses),
-      values(module.kubernetes.master_ip_addresses).*.public_ip,
-      values(module.kubernetes.master_ip_addresses).*.private_ip,
-    range(1, length(module.kubernetes.master_ip_addresses) + 1)))
-    connection_strings_worker = join("\n", formatlist("%s ansible_user=ubuntu ansible_host=%s ip=%s",
-      keys(module.kubernetes.worker_ip_addresses),
-      values(module.kubernetes.worker_ip_addresses).*.public_ip,
-    values(module.kubernetes.worker_ip_addresses).*.private_ip))
-    list_master = join("\n", keys(module.kubernetes.master_ip_addresses))
-    list_worker = join("\n", keys(module.kubernetes.worker_ip_addresses))
-    network_id = module.kubernetes.network_id
-  }
+locals {
+  inventory = templatefile(
+    "${path.module}/templates/inventory.tpl",
+    {
+      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_addresses),
+        values(module.kubernetes.master_ip_addresses).*.public_ip,
+        values(module.kubernetes.master_ip_addresses).*.private_ip,
+      range(1, length(module.kubernetes.master_ip_addresses) + 1)))
+      connection_strings_worker = join("\n", formatlist("%s ansible_user=ubuntu ansible_host=%s ip=%s",
+        keys(module.kubernetes.worker_ip_addresses),
+        values(module.kubernetes.worker_ip_addresses).*.public_ip,
+      values(module.kubernetes.worker_ip_addresses).*.private_ip))
+      list_master = join("\n", keys(module.kubernetes.master_ip_addresses))
+      list_worker = join("\n", keys(module.kubernetes.worker_ip_addresses))
+      network_id  = module.kubernetes.network_id
+    }
+  )
 }
 
 resource "null_resource" "inventories" {
   provisioner "local-exec" {
-    command = "echo '${data.template_file.inventory.rendered}' > ${var.inventory_file}"
+    command = "echo '${local.inventory}' > ${var.inventory_file}"
   }
 
   triggers = {
-    template = data.template_file.inventory.rendered
+    template = local.inventory
   }
 }

contrib/terraform/hetzner/modules/kubernetes-cluster-flatcar/main.tf

@@ -0,0 +1,144 @@
+resource "hcloud_network" "kubernetes" {
+  name     = "${var.prefix}-network"
+  ip_range = var.private_network_cidr
+}
+
+resource "hcloud_network_subnet" "kubernetes" {
+  type         = "cloud"
+  network_id   = hcloud_network.kubernetes.id
+  network_zone = var.network_zone
+  ip_range     = var.private_subnet_cidr
+}
+
+resource "hcloud_ssh_key" "first" {
+  name       = var.prefix
+  public_key = var.ssh_public_keys.0
+}
+
+resource "hcloud_server" "machine" {
+  for_each = {
+    for name, machine in var.machines :
+    name => machine
+  }
+
+  name     = "${var.prefix}-${each.key}"
+  ssh_keys = [hcloud_ssh_key.first.id]
+  # boot into rescue OS
+  rescue = "linux64"
+  # dummy value for the OS because Flatcar is not available
+  image       = each.value.image
+  server_type = each.value.size
+  location    = var.zone
+  connection {
+    host        = self.ipv4_address
+    timeout     = "5m"
+    private_key = file(var.ssh_private_key_path)
+  }
+  firewall_ids = each.value.node_type == "master" ? [hcloud_firewall.master.id] : [hcloud_firewall.worker.id]
+  provisioner "file" {
+    content     = data.ct_config.machine-ignitions[each.key].rendered
+    destination = "/root/ignition.json"
+  }
+
+  provisioner "remote-exec" {
+    inline = [
+      "set -ex",
+      "apt update",
+      "apt install -y gawk",
+      "curl -fsSLO --retry-delay 1 --retry 60 --retry-connrefused --retry-max-time 60 --connect-timeout 20 https://raw.githubusercontent.com/flatcar/init/flatcar-master/bin/flatcar-install",
+      "chmod +x flatcar-install",
+      "./flatcar-install -s -i /root/ignition.json -C stable",
+      "shutdown -r +1",
+    ]
+  }
+
+  # optional:
+  provisioner "remote-exec" {
+    connection {
+      host        = self.ipv4_address
+      private_key = file(var.ssh_private_key_path)
+      timeout     = "3m"
+      user        = var.user_flatcar
+    }
+
+    inline = [
+      "sudo hostnamectl set-hostname ${self.name}",
+    ]
+  }
+}
+
+resource "hcloud_server_network" "machine" {
+  for_each = {
+    for name, machine in var.machines :
+    name => hcloud_server.machine[name]
+  }
+  server_id = each.value.id
+  subnet_id = hcloud_network_subnet.kubernetes.id
+}
+
+data "ct_config" "machine-ignitions" {
+  for_each = {
+    for name, machine in var.machines :
+    name => machine
+  }
+
+  strict = false
+  content = templatefile(
+    "${path.module}/templates/machine.yaml.tmpl",
+    {
+      ssh_keys     = jsonencode(var.ssh_public_keys)
+      user_flatcar = var.user_flatcar
+      name         = each.key
+    }
+  )
+}
+
+resource "hcloud_firewall" "master" {
+  name = "${var.prefix}-master-firewall"
+
+  rule {
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "22"
+    source_ips = var.ssh_whitelist
+  }
+
+  rule {
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "6443"
+    source_ips = var.api_server_whitelist
+  }
+}
+
+resource "hcloud_firewall" "worker" {
+  name = "${var.prefix}-worker-firewall"
+
+  rule {
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "22"
+    source_ips = var.ssh_whitelist
+  }
+
+  rule {
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "80"
+    source_ips = var.ingress_whitelist
+  }
+
+  rule {
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "443"
+    source_ips = var.ingress_whitelist
+  }
+
+  rule {
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "30000-32767"
+    source_ips = var.nodeport_whitelist
+  }
+}

contrib/terraform/hetzner/modules/kubernetes-cluster-flatcar/outputs.tf

@@ -0,0 +1,29 @@
+output "master_ip_addresses" {
+  value = {
+    for name, machine in var.machines :
+      name => {
+        "private_ip" = hcloud_server_network.machine[name].ip
+        "public_ip"  = hcloud_server.machine[name].ipv4_address
+      }
+      if machine.node_type == "master"
+  }
+}
+
+output "worker_ip_addresses" {
+  value = {
+    for name, machine in var.machines :
+      name => {
+        "private_ip" = hcloud_server_network.machine[name].ip
+        "public_ip"  = hcloud_server.machine[name].ipv4_address
+      }
+      if machine.node_type == "worker"
+  }
+}
+
+output "cluster_private_network_cidr" {
+  value = var.private_subnet_cidr
+}
+
+output "network_id" {
+  value = hcloud_network.kubernetes.id
+}

contrib/terraform/hetzner/modules/kubernetes-cluster-flatcar/templates/machine.yaml.tmpl

@@ -0,0 +1,19 @@
+variant: flatcar
+version: 1.0.0
+
+passwd:
+  users:
+    - name: ${user_flatcar}
+      ssh_authorized_keys: ${ssh_keys}
+
+storage:
+  files:
+    - path: /home/core/works
+      filesystem: root
+      mode: 0755
+      contents:
+        inline: |
+          #!/bin/bash
+          set -euo pipefail
+          hostname="$(hostname)"
+          echo My name is ${name} and the hostname is $${hostname}

contrib/terraform/hetzner/modules/kubernetes-cluster-flatcar/variables.tf

@@ -0,0 +1,60 @@
+
+variable "zone" {
+  type    = string
+  default = "fsn1"
+}
+
+variable "prefix" {
+  default = "k8s"
+}
+
+variable "user_flatcar" {
+  type    = string
+  default = "core"
+}
+
+variable "machines" {
+  type = map(object({
+    node_type = string
+    size      = string
+    image     = string
+  }))
+}
+
+
+
+variable "ssh_public_keys" {
+  type = list(string)
+}
+
+variable "ssh_private_key_path" {
+  type    = string
+  default = "~/.ssh/id_rsa"
+}
+
+variable "ssh_whitelist" {
+  type = list(string)
+}
+
+variable "api_server_whitelist" {
+  type = list(string)
+}
+
+variable "nodeport_whitelist" {
+  type = list(string)
+}
+
+variable "ingress_whitelist" {
+  type = list(string)
+}
+
+variable "private_network_cidr" {
+  default = "10.0.0.0/16"
+}
+
+variable "private_subnet_cidr" {
+  default = "10.0.10.0/24"
+}
+variable "network_zone" {
+  default = "eu-central"
+}

contrib/terraform/hetzner/modules/kubernetes-cluster-flatcar/versions.tf

@@ -0,0 +1,14 @@
+terraform {
+  required_providers {
+    hcloud = {
+      source = "hetznercloud/hcloud"
+    }
+    ct = {
+      source  = "poseidon/ct"
+      version = "0.11.0"
+    }
+    null = {
+      source = "hashicorp/null"
+    }
+  }
+}

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

@@ -75,17 +75,17 @@ resource "hcloud_firewall" "master" {
   name = "${var.prefix}-master-firewall"
 
   rule {
-   direction = "in"
-   protocol = "tcp"
-   port = "22"
-   source_ips = var.ssh_whitelist
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "22"
+    source_ips = var.ssh_whitelist
   }
 
   rule {
-   direction = "in"
-   protocol = "tcp"
-   port = "6443"
-   source_ips = var.api_server_whitelist
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "6443"
+    source_ips = var.api_server_whitelist
   }
 }
 
@@ -93,30 +93,30 @@ resource "hcloud_firewall" "worker" {
   name = "${var.prefix}-worker-firewall"
 
   rule {
-   direction = "in"
-   protocol = "tcp"
-   port = "22"
-   source_ips = var.ssh_whitelist
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "22"
+    source_ips = var.ssh_whitelist
   }
 
   rule {
-   direction = "in"
-   protocol = "tcp"
-   port = "80"
-   source_ips = var.ingress_whitelist
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "80"
+    source_ips = var.ingress_whitelist
   }
 
   rule {
-   direction = "in"
-   protocol = "tcp"
-   port = "443"
-   source_ips = var.ingress_whitelist
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "443"
+    source_ips = var.ingress_whitelist
   }
 
   rule {
-   direction = "in"
-   protocol = "tcp"
-   port = "30000-32767"
-   source_ips = var.nodeport_whitelist
+    direction  = "in"
+    protocol   = "tcp"
+    port       = "30000-32767"
+    source_ips = var.nodeport_whitelist
   }
 }

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

@@ -24,4 +24,4 @@ output "cluster_private_network_cidr" {
 
 output "network_id" {
   value = hcloud_network.kubernetes.id
-}
+}

contrib/terraform/hetzner/modules/kubernetes-cluster/templates/cloud-init.tmpl

@@ -14,4 +14,3 @@ ssh_authorized_keys:
 %{ for ssh_public_key in ssh_public_keys ~}
   - ${ssh_public_key}
 %{ endfor ~}
-

contrib/terraform/hetzner/modules/kubernetes-cluster/versions.tf

@@ -1,8 +1,8 @@
 terraform {
   required_providers {
     hcloud = {
-      source = "hetznercloud/hcloud"
-      version = "1.31.1"
+      source  = "hetznercloud/hcloud"
+      version = "1.38.2"
     }
   }
   required_version = ">= 0.14"

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

@@ -0,0 +1,46 @@
+prefix         = "default"
+zone           = "hel1"
+network_zone   = "eu-central"
+inventory_file = "inventory.ini"
+
+ssh_public_keys = [
+  # Put your public SSH key here
+  "ssh-rsa I-did-not-read-the-docs",
+  "ssh-rsa I-did-not-read-the-docs 2",
+]
+
+ssh_private_key_path = "~/.ssh/id_rsa"
+
+machines = {
+  "master-0" : {
+    "node_type" : "master",
+    "size" : "cx21",
+    "image" : "ubuntu-22.04",
+  },
+  "worker-0" : {
+    "node_type" : "worker",
+    "size" : "cx21",
+    "image" : "ubuntu-22.04",
+  },
+  "worker-1" : {
+    "node_type" : "worker",
+    "size" : "cx21",
+    "image" : "ubuntu-22.04",
+  }
+}
+
+nodeport_whitelist = [
+  "0.0.0.0/0"
+]
+
+ingress_whitelist = [
+  "0.0.0.0/0"
+]
+
+ssh_whitelist = [
+  "0.0.0.0/0"
+]
+
+api_server_whitelist = [
+  "0.0.0.0/0"
+]

contrib/terraform/hetzner/sample-inventory/group_vars

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

contrib/terraform/hetzner/templates/inventory.tpl

@@ -2,18 +2,18 @@
 ${connection_strings_master}
 ${connection_strings_worker}
 
-[kube-master]
+[kube_control_plane]
 ${list_master}
 
 [etcd]
 ${list_master}
 
-[kube-node]
+[kube_node]
 ${list_worker}
 
-[k8s-cluster:children]
+[k8s_cluster:children]
 kube-master
 kube-node
 
-[k8s-cluster:vars]
+[k8s_cluster:vars]
 network_id=${network_id}

contrib/terraform/hetzner/variables.tf

@@ -3,7 +3,7 @@ variable "zone" {
 }
 variable "network_zone" {
   description = "The network zone where the cluster is running"
-  default = "eu-central"
+  default     = "eu-central"
 }
 
 variable "prefix" {
@@ -25,6 +25,12 @@ variable "ssh_public_keys" {
   type        = list(string)
 }
 
+variable "ssh_private_key_path" {
+  description = "Private SSH key which connect to the VMs."
+  type        = string
+  default     = "~/.ssh/id_rsa"
+}
+
 variable "ssh_whitelist" {
   description = "List of IP ranges (CIDR) to whitelist for ssh"
   type        = list(string)

contrib/terraform/hetzner/versions.tf

@@ -2,14 +2,11 @@ terraform {
   required_providers {
     hcloud = {
       source  = "hetznercloud/hcloud"
-      version = "1.31.1"
+      version = "1.38.2"
     }
     null = {
       source = "hashicorp/null"
     }
-    template = {
-      source = "hashicorp/template"
-    }
   }
   required_version = ">= 0.14"
 }

contrib/terraform/metal/output.tf

@@ -1,16 +0,0 @@
-output "k8s_masters" {
-  value = metal_device.k8s_master.*.access_public_ipv4
-}
-
-output "k8s_masters_no_etc" {
-  value = metal_device.k8s_master_no_etcd.*.access_public_ipv4
-}
-
-output "k8s_etcds" {
-  value = metal_device.k8s_etcd.*.access_public_ipv4
-}
-
-output "k8s_nodes" {
-  value = metal_device.k8s_node.*.access_public_ipv4
-}
-

contrib/terraform/metal/versions.tf

@@ -1,9 +0,0 @@
-
-terraform {
-  required_version = ">= 0.12"
-  required_providers {
-    metal = {
-      source = "equinix/metal"
-    }
-  }
-}

contrib/terraform/openstack/README.md

@@ -88,7 +88,7 @@ binaries available on hyperkube v1.4.3_coreos.0 or higher.
 
 ## Requirements
 
-- [Install Terraform](https://www.terraform.io/intro/getting-started/install.html) 0.12 or later
+- [Install Terraform](https://www.terraform.io/intro/getting-started/install.html) 0.14 or later
 - [Install Ansible](http://docs.ansible.com/ansible/latest/intro_installation.html)
 - you already have a suitable OS image in Glance
 - you already have a floating IP pool created
@@ -270,6 +270,7 @@ For your cluster, edit `inventory/$CLUSTER/cluster.tfvars`.
 |`supplementary_node_groups` | To add ansible groups to the nodes, such as `kube_ingress` for running ingress controller pods, empty by default. |
 |`bastion_allowed_remote_ips` | List of CIDR allowed to initiate a SSH connection, `["0.0.0.0/0"]` by default |
 |`master_allowed_remote_ips` | List of CIDR blocks allowed to initiate an API connection, `["0.0.0.0/0"]` by default |
+|`bastion_allowed_ports` | List of ports to open on bastion node, `[]` by default |
 |`k8s_allowed_remote_ips` | List of CIDR allowed to initiate a SSH connection, empty by default |
 |`worker_allowed_ports` | List of ports to open on worker nodes, `[{ "protocol" = "tcp", "port_range_min" = 30000, "port_range_max" = 32767, "remote_ip_prefix" = "0.0.0.0/0"}]` by default |
 |`master_allowed_ports` | List of ports to open on master nodes, expected format is `[{ "protocol" = "tcp", "port_range_min" = 443, "port_range_max" = 443, "remote_ip_prefix" = "0.0.0.0/0"}]`, empty by default |
@@ -283,6 +284,7 @@ For your cluster, edit `inventory/$CLUSTER/cluster.tfvars`.
 |`master_server_group_policy` | Enable and use openstack nova servergroups for masters with set policy, default: "" (disabled) |
 |`node_server_group_policy` | Enable and use openstack nova servergroups for nodes with set policy, default: "" (disabled) |
 |`etcd_server_group_policy` | Enable and use openstack nova servergroups for etcd with set policy, default: "" (disabled) |
+|`additional_server_groups` | Extra server groups to create. Set "policy" to the policy for the group, expected format is `{"new-server-group" = {"policy" = "anti-affinity"}}`, default: {} (to not create any extra groups) |
 |`use_access_ip` | If 1, nodes with floating IPs will transmit internal cluster traffic via floating IPs; if 0 private IPs will be used instead. Default value is 1. |
 |`port_security_enabled` | Allow to disable port security by setting this to `false`. `true` by default |
 |`force_null_port_security` | Set `null` instead of `true` or `false` for `port_security`. `false` by default |
@@ -291,10 +293,32 @@ For your cluster, edit `inventory/$CLUSTER/cluster.tfvars`.
 
 ##### k8s_nodes
 
-Allows a custom definition of worker nodes giving the operator full control over individual node flavor and
-availability zone placement. To enable the use of this mode set the `number_of_k8s_nodes` and
-`number_of_k8s_nodes_no_floating_ip` variables to 0. Then define your desired worker node configuration
-using the `k8s_nodes` variable.
+Allows a custom definition of worker nodes giving the operator full control over individual node flavor and availability zone placement.
+To enable the use of this mode set the `number_of_k8s_nodes` and `number_of_k8s_nodes_no_floating_ip` variables to 0.
+Then define your desired worker node configuration using the `k8s_nodes` variable.
+The `az`, `flavor` and `floating_ip` parameters are mandatory.
+The optional parameter `extra_groups` (a comma-delimited string) can be used to define extra inventory group memberships for specific nodes.
+
+```yaml
+k8s_nodes:
+   node-name:
+    az: string # Name of the AZ
+    flavor: string # Flavor ID to use
+    floating_ip: bool # If floating IPs should be created or not
+    extra_groups: string # (optional) Additional groups to add for kubespray, defaults to no groups
+    image_id: string # (optional) Image ID to use, defaults to var.image_id or var.image
+    root_volume_size_in_gb: number # (optional) Size of the block storage to use as root disk, defaults to var.node_root_volume_size_in_gb or to use volume from flavor otherwise
+    volume_type: string # (optional) Volume type to use, defaults to var.node_volume_type
+    network_id: string # (optional) Use this network_id for the node, defaults to either var.network_id or ID of var.network_name
+    server_group: string # (optional) Server group to add this node to. If set, this has to be one specified in additional_server_groups, defaults to use the server group specified in node_server_group_policy
+    cloudinit: # (optional) Options for cloud-init
+      extra_partitions: # List of extra partitions (other than the root partition) to setup during creation
+        volume_path: string # Path to the volume to create partition for (e.g. /dev/vda )
+        partition_path: string # Path to the partition (e.g. /dev/vda2 )
+        mount_path: string # Path to where the partition should be mounted
+        partition_start: string # Where the partition should start (e.g. 10GB ). Note, if you set the partition_start to 0 there will be no space left for the root partition
+        partition_end: string # Where the partition should end (e.g. 10GB or -1 for end of volume)
+```
 
 For example:
 
@@ -314,6 +338,7 @@ k8s_nodes = {
     "az" = "sto3"
     "flavor" = "83d8b44a-26a0-4f02-a981-079446926445"
     "floating_ip" = true
+    "extra_groups" = "calico_rr"
   }
 }
 ```
@@ -424,7 +449,7 @@ This should finish fairly quickly telling you Terraform has successfully initial
 
 You can apply cloud-init based customization for the openstack instances before provisioning your cluster.
 One common template is used for all instances. Adjust the file shown below:
-`contrib/terraform/openstack/modules/compute/templates/cloudinit.yaml`
+`contrib/terraform/openstack/modules/compute/templates/cloudinit.yaml.tmpl`
 For example, to enable openstack novnc access and ansible_user=root SSH access:
 
 ```ShellSession

contrib/terraform/openstack/kubespray.tf

@@ -84,6 +84,7 @@ module "compute" {
   supplementary_node_groups                    = var.supplementary_node_groups
   master_allowed_ports                         = var.master_allowed_ports
   worker_allowed_ports                         = var.worker_allowed_ports
+  bastion_allowed_ports                        = var.bastion_allowed_ports
   use_access_ip                                = var.use_access_ip
   master_server_group_policy                   = var.master_server_group_policy
   node_server_group_policy                     = var.node_server_group_policy
@@ -96,6 +97,12 @@ module "compute" {
   network_router_id                            = module.network.router_id
   network_id                                   = module.network.network_id
   use_existing_network                         = var.use_existing_network
+  private_subnet_id                            = module.network.subnet_id
+  additional_server_groups                     = var.additional_server_groups
+
+  depends_on = [
+    module.network.subnet_id
+  ]
 }
 
 output "private_subnet_id" {
@@ -111,7 +118,7 @@ output "router_id" {
 }
 
 output "k8s_master_fips" {
-  value = concat(module.ips.k8s_master_fips, module.ips.k8s_master_no_etcd_fips)
+  value = var.number_of_k8s_masters + var.number_of_k8s_masters_no_etcd > 0 ? concat(module.ips.k8s_master_fips, module.ips.k8s_master_no_etcd_fips) : [for key, value in module.ips.k8s_masters_fips : value.address]
 }
 
 output "k8s_node_fips" {

contrib/terraform/openstack/modules/compute/main.tf

@@ -15,8 +15,14 @@ data "openstack_images_image_v2" "image_master" {
   name = var.image_master == "" ? var.image : var.image_master
 }
 
-data "template_file" "cloudinit" {
-  template = file("${path.module}/templates/cloudinit.yaml")
+data "cloudinit_config" "cloudinit" {
+  part {
+    content_type =  "text/cloud-config"
+    content = templatefile("${path.module}/templates/cloudinit.yaml.tmpl", {
+      # template_file doesn't support lists
+      extra_partitions = ""
+    })
+  }
 }
 
 data "openstack_networking_network_v2" "k8s_network" {
@@ -82,6 +88,17 @@ resource "openstack_networking_secgroup_rule_v2" "bastion" {
   security_group_id = openstack_networking_secgroup_v2.bastion[0].id
 }
 
+resource "openstack_networking_secgroup_rule_v2" "k8s_bastion_ports" {
+  count             = length(var.bastion_allowed_ports)
+  direction         = "ingress"
+  ethertype         = "IPv4"
+  protocol          = lookup(var.bastion_allowed_ports[count.index], "protocol", "tcp")
+  port_range_min    = lookup(var.bastion_allowed_ports[count.index], "port_range_min")
+  port_range_max    = lookup(var.bastion_allowed_ports[count.index], "port_range_max")
+  remote_ip_prefix  = lookup(var.bastion_allowed_ports[count.index], "remote_ip_prefix", "0.0.0.0/0")
+  security_group_id = openstack_networking_secgroup_v2.bastion[0].id
+}
+
 resource "openstack_networking_secgroup_v2" "k8s" {
   name                 = "${var.cluster_name}-k8s"
   description          = "${var.cluster_name} - Kubernetes"
@@ -156,6 +173,12 @@ resource "openstack_compute_servergroup_v2" "k8s_etcd" {
   policies = [var.etcd_server_group_policy]
 }
 
+resource "openstack_compute_servergroup_v2" "k8s_node_additional" {
+  for_each = var.additional_server_groups
+  name     = "k8s-${each.key}-srvgrp"
+  policies = [each.value.policy]
+}
+
 locals {
 # master groups
   master_sec_groups = compact([
@@ -185,6 +208,29 @@ locals {
   image_to_use_gfs = var.image_gfs_uuid != "" ? var.image_gfs_uuid : var.image_uuid != "" ? var.image_uuid : data.openstack_images_image_v2.gfs_image[0].id
 # image_master uuidimage_gfs_uuid
   image_to_use_master = var.image_master_uuid != "" ? var.image_master_uuid : var.image_uuid != "" ? var.image_uuid : data.openstack_images_image_v2.image_master[0].id
+
+  k8s_nodes_settings = {
+    for name, node in var.k8s_nodes :
+      name => {
+        "use_local_disk" = (node.root_volume_size_in_gb != null ? node.root_volume_size_in_gb : var.node_root_volume_size_in_gb) == 0,
+        "image_id"       = node.image_id != null ? node.image_id : local.image_to_use_node,
+        "volume_size"    = node.root_volume_size_in_gb != null ? node.root_volume_size_in_gb : var.node_root_volume_size_in_gb,
+        "volume_type"    = node.volume_type != null ? node.volume_type : var.node_volume_type,
+        "network_id"     = node.network_id != null ? node.network_id : (var.use_existing_network ? data.openstack_networking_network_v2.k8s_network[0].id : var.network_id)
+        "server_group"   = node.server_group != null ? [openstack_compute_servergroup_v2.k8s_node_additional[node.server_group].id] : (var.node_server_group_policy != ""  ? [openstack_compute_servergroup_v2.k8s_node[0].id] : [])
+      }
+  }
+
+  k8s_masters_settings = {
+    for name, node in var.k8s_masters :
+      name => {
+        "use_local_disk" = (node.root_volume_size_in_gb != null ? node.root_volume_size_in_gb : var.master_root_volume_size_in_gb) == 0,
+        "image_id"       = node.image_id != null ? node.image_id : local.image_to_use_master,
+        "volume_size"    = node.root_volume_size_in_gb != null ? node.root_volume_size_in_gb : var.master_root_volume_size_in_gb,
+        "volume_type"    = node.volume_type != null ? node.volume_type : var.master_volume_type,
+        "network_id"     = node.network_id != null ? node.network_id : (var.use_existing_network ? data.openstack_networking_network_v2.k8s_network[0].id : var.network_id)
+      }
+  }
 }
 
 resource "openstack_networking_port_v2" "bastion_port" {
@@ -195,6 +241,12 @@ resource "openstack_networking_port_v2" "bastion_port" {
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.bastion_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -207,7 +259,7 @@ resource "openstack_compute_instance_v2" "bastion" {
   image_id   = var.bastion_root_volume_size_in_gb == 0 ? local.image_to_use_node : null
   flavor_id  = var.flavor_bastion
   key_pair   = openstack_compute_keypair_v2.k8s.name
-  user_data  = data.template_file.cloudinit.rendered
+  user_data  = data.cloudinit_config.cloudinit.rendered
 
   dynamic "block_device" {
     for_each = var.bastion_root_volume_size_in_gb > 0 ? [local.image_to_use_node] : []
@@ -245,6 +297,12 @@ resource "openstack_networking_port_v2" "k8s_master_port" {
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.master_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -258,7 +316,7 @@ resource "openstack_compute_instance_v2" "k8s_master" {
   image_id          = var.master_root_volume_size_in_gb == 0 ? local.image_to_use_master : null
   flavor_id         = var.flavor_k8s_master
   key_pair          = openstack_compute_keypair_v2.k8s.name
-  user_data         = data.template_file.cloudinit.rendered
+  user_data         = data.cloudinit_config.cloudinit.rendered
 
 
   dynamic "block_device" {
@@ -300,11 +358,17 @@ resource "openstack_compute_instance_v2" "k8s_master" {
 resource "openstack_networking_port_v2" "k8s_masters_port" {
   for_each              = var.number_of_k8s_masters == 0 && var.number_of_k8s_masters_no_etcd == 0 && var.number_of_k8s_masters_no_floating_ip == 0 && var.number_of_k8s_masters_no_floating_ip_no_etcd == 0 ? var.k8s_masters : {}
   name                  = "${var.cluster_name}-k8s-${each.key}"
-  network_id            = var.use_existing_network ? data.openstack_networking_network_v2.k8s_network[0].id : var.network_id
+  network_id            = local.k8s_masters_settings[each.key].network_id
   admin_state_up        = "true"
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.master_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -315,17 +379,17 @@ resource "openstack_compute_instance_v2" "k8s_masters" {
   for_each          = var.number_of_k8s_masters == 0 && var.number_of_k8s_masters_no_etcd == 0 && var.number_of_k8s_masters_no_floating_ip == 0 && var.number_of_k8s_masters_no_floating_ip_no_etcd == 0 ? var.k8s_masters : {}
   name              = "${var.cluster_name}-k8s-${each.key}"
   availability_zone = each.value.az
-  image_id          = var.master_root_volume_size_in_gb == 0 ? local.image_to_use_master : null
+  image_id          = local.k8s_masters_settings[each.key].use_local_disk ? local.k8s_masters_settings[each.key].image_id : null
   flavor_id         = each.value.flavor
   key_pair          = openstack_compute_keypair_v2.k8s.name
 
   dynamic "block_device" {
-    for_each = var.master_root_volume_size_in_gb > 0 ? [local.image_to_use_master] : []
+    for_each = !local.k8s_masters_settings[each.key].use_local_disk ? [local.k8s_masters_settings[each.key].image_id] : []
     content {
-      uuid                  = local.image_to_use_master
+      uuid                  = block_device.value
       source_type           = "image"
-      volume_size           = var.master_root_volume_size_in_gb
-      volume_type           = var.master_volume_type
+      volume_size           = local.k8s_masters_settings[each.key].volume_size
+      volume_type           = local.k8s_masters_settings[each.key].volume_type
       boot_index            = 0
       destination_type      = "volume"
       delete_on_termination = true
@@ -351,7 +415,7 @@ resource "openstack_compute_instance_v2" "k8s_masters" {
   }
 
   provisioner "local-exec" {
-    command = "%{if each.value.floating_ip}sed s/USER/${var.ssh_user}/ ${path.root}/ansible_bastion_template.txt | sed s/BASTION_ADDRESS/${element(concat(var.bastion_fips, [for key, value in var.k8s_masters_fips : value.address]), 0)}/ > ${var.group_vars_path}/no_floating.yml%{else}true%{endif}"
+    command = "%{if each.value.floating_ip}sed s/USER/${var.ssh_user}/ ${path.module}/ansible_bastion_template.txt | sed s/BASTION_ADDRESS/${element(concat(var.bastion_fips, [for key, value in var.k8s_masters_fips : value.address]), 0)}/ > ${var.group_vars_path}/no_floating.yml%{else}true%{endif}"
   }
 }
 
@@ -363,6 +427,12 @@ resource "openstack_networking_port_v2" "k8s_master_no_etcd_port" {
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.master_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -376,7 +446,7 @@ resource "openstack_compute_instance_v2" "k8s_master_no_etcd" {
   image_id          = var.master_root_volume_size_in_gb == 0 ? local.image_to_use_master : null
   flavor_id         = var.flavor_k8s_master
   key_pair          = openstack_compute_keypair_v2.k8s.name
-  user_data         = data.template_file.cloudinit.rendered
+  user_data         = data.cloudinit_config.cloudinit.rendered
 
 
   dynamic "block_device" {
@@ -423,6 +493,12 @@ resource "openstack_networking_port_v2" "etcd_port" {
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.etcd_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -436,7 +512,7 @@ resource "openstack_compute_instance_v2" "etcd" {
   image_id          = var.etcd_root_volume_size_in_gb == 0 ? local.image_to_use_master : null
   flavor_id         = var.flavor_etcd
   key_pair          = openstack_compute_keypair_v2.k8s.name
-  user_data         = data.template_file.cloudinit.rendered
+  user_data         = data.cloudinit_config.cloudinit.rendered
 
   dynamic "block_device" {
     for_each = var.etcd_root_volume_size_in_gb > 0 ? [local.image_to_use_master] : []
@@ -477,6 +553,12 @@ resource "openstack_networking_port_v2" "k8s_master_no_floating_ip_port" {
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.master_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -531,6 +613,12 @@ resource "openstack_networking_port_v2" "k8s_master_no_floating_ip_no_etcd_port"
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.master_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -544,7 +632,7 @@ resource "openstack_compute_instance_v2" "k8s_master_no_floating_ip_no_etcd" {
   image_id          = var.master_root_volume_size_in_gb == 0 ? local.image_to_use_master : null
   flavor_id         = var.flavor_k8s_master
   key_pair          = openstack_compute_keypair_v2.k8s.name
-  user_data         = data.template_file.cloudinit.rendered
+  user_data         = data.cloudinit_config.cloudinit.rendered
 
   dynamic "block_device" {
     for_each = var.master_root_volume_size_in_gb > 0 ? [local.image_to_use_master] : []
@@ -586,6 +674,12 @@ resource "openstack_networking_port_v2" "k8s_node_port" {
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.worker_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -599,7 +693,7 @@ resource "openstack_compute_instance_v2" "k8s_node" {
   image_id          = var.node_root_volume_size_in_gb == 0 ? local.image_to_use_node : null
   flavor_id         = var.flavor_k8s_node
   key_pair          = openstack_compute_keypair_v2.k8s.name
-  user_data         = data.template_file.cloudinit.rendered
+  user_data         = data.cloudinit_config.cloudinit.rendered
 
   dynamic "block_device" {
     for_each = var.node_root_volume_size_in_gb > 0 ? [local.image_to_use_node] : []
@@ -646,6 +740,12 @@ resource "openstack_networking_port_v2" "k8s_node_no_floating_ip_port" {
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.worker_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -659,7 +759,7 @@ resource "openstack_compute_instance_v2" "k8s_node_no_floating_ip" {
   image_id          = var.node_root_volume_size_in_gb == 0 ? local.image_to_use_node : null
   flavor_id         = var.flavor_k8s_node
   key_pair          = openstack_compute_keypair_v2.k8s.name
-  user_data         = data.template_file.cloudinit.rendered
+  user_data         = data.cloudinit_config.cloudinit.rendered
 
   dynamic "block_device" {
     for_each = var.node_root_volume_size_in_gb > 0 ? [local.image_to_use_node] : []
@@ -679,9 +779,9 @@ resource "openstack_compute_instance_v2" "k8s_node_no_floating_ip" {
   }
 
   dynamic "scheduler_hints" {
-    for_each = var.node_server_group_policy != "" ? [openstack_compute_servergroup_v2.k8s_node[0]] : []
+    for_each = var.node_server_group_policy != "" ? [openstack_compute_servergroup_v2.k8s_node[0].id] : []
     content {
-      group = openstack_compute_servergroup_v2.k8s_node[0].id
+      group = scheduler_hints.value
     }
   }
 
@@ -696,11 +796,17 @@ resource "openstack_compute_instance_v2" "k8s_node_no_floating_ip" {
 resource "openstack_networking_port_v2" "k8s_nodes_port" {
   for_each              = var.number_of_k8s_nodes == 0 && var.number_of_k8s_nodes_no_floating_ip == 0 ? var.k8s_nodes : {}
   name                  = "${var.cluster_name}-k8s-node-${each.key}"
-  network_id            = var.use_existing_network ? data.openstack_networking_network_v2.k8s_network[0].id : var.network_id
+  network_id            = local.k8s_nodes_settings[each.key].network_id
   admin_state_up        = "true"
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.worker_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id
@@ -711,18 +817,20 @@ resource "openstack_compute_instance_v2" "k8s_nodes" {
   for_each          = var.number_of_k8s_nodes == 0 && var.number_of_k8s_nodes_no_floating_ip == 0 ? var.k8s_nodes : {}
   name              = "${var.cluster_name}-k8s-node-${each.key}"
   availability_zone = each.value.az
-  image_id          = var.node_root_volume_size_in_gb == 0 ? local.image_to_use_node : null
+  image_id          = local.k8s_nodes_settings[each.key].use_local_disk ? local.k8s_nodes_settings[each.key].image_id : null
   flavor_id         = each.value.flavor
   key_pair          = openstack_compute_keypair_v2.k8s.name
-  user_data         = data.template_file.cloudinit.rendered
+  user_data         = each.value.cloudinit != null ? templatefile("${path.module}/templates/cloudinit.yaml.tmpl", {
+    extra_partitions = each.value.cloudinit.extra_partitions
+  }) : data.cloudinit_config.cloudinit.rendered
 
   dynamic "block_device" {
-    for_each = var.node_root_volume_size_in_gb > 0 ? [local.image_to_use_node] : []
+    for_each = !local.k8s_nodes_settings[each.key].use_local_disk ? [local.k8s_nodes_settings[each.key].image_id] : []
     content {
-      uuid                  = local.image_to_use_node
+      uuid                  = block_device.value
       source_type           = "image"
-      volume_size           = var.node_root_volume_size_in_gb
-      volume_type           = var.node_volume_type
+      volume_size           = local.k8s_nodes_settings[each.key].volume_size
+      volume_type           = local.k8s_nodes_settings[each.key].volume_type
       boot_index            = 0
       destination_type      = "volume"
       delete_on_termination = true
@@ -734,15 +842,15 @@ resource "openstack_compute_instance_v2" "k8s_nodes" {
   }
 
   dynamic "scheduler_hints" {
-    for_each = var.node_server_group_policy != "" ? [openstack_compute_servergroup_v2.k8s_node[0]] : []
+    for_each = local.k8s_nodes_settings[each.key].server_group
     content {
-      group = openstack_compute_servergroup_v2.k8s_node[0].id
+      group = scheduler_hints.value
     }
   }
 
   metadata = {
     ssh_user         = var.ssh_user
-    kubespray_groups = "kube_node,k8s_cluster,%{if each.value.floating_ip == false}no_floating,%{endif}${var.supplementary_node_groups}"
+    kubespray_groups = "kube_node,k8s_cluster,%{if each.value.floating_ip == false}no_floating,%{endif}${var.supplementary_node_groups}${each.value.extra_groups != null ? ",${each.value.extra_groups}" : ""}"
     depends_on       = var.network_router_id
     use_access_ip    = var.use_access_ip
   }
@@ -760,6 +868,12 @@ resource "openstack_networking_port_v2" "glusterfs_node_no_floating_ip_port" {
   port_security_enabled = var.force_null_port_security ? null : var.port_security_enabled
   security_group_ids    = var.port_security_enabled ? local.gfs_sec_groups : null
   no_security_groups    = var.port_security_enabled ? null : false
+  dynamic "fixed_ip" {
+    for_each = var.private_subnet_id == "" ? [] : [true]
+    content {
+      subnet_id = var.private_subnet_id
+    }
+  }
 
   depends_on = [
     var.network_router_id

contrib/terraform/openstack/modules/compute/templates/cloudinit.yaml

@@ -1,17 +0,0 @@
-# yamllint disable rule:comments
-#cloud-config
-## in some cases novnc console access is required
-## it requires ssh password to be set
-#ssh_pwauth: yes
-#chpasswd:
-#  list: |
-#    root:secret
-#  expire: False
-
-## in some cases direct root ssh access via ssh key is required
-#disable_root: false
-
-## in some cases additional CA certs are required
-#ca-certs:
-#  trusted: |
-#      -----BEGIN CERTIFICATE-----

contrib/terraform/openstack/modules/compute/templates/cloudinit.yaml.tmpl

@@ -0,0 +1,39 @@
+%{~ if length(extra_partitions) > 0 }
+#cloud-config
+bootcmd:
+%{~ for idx, partition in extra_partitions }
+- [ cloud-init-per, once, move-second-header, sgdisk, --move-second-header, ${partition.volume_path} ]
+- [ cloud-init-per, once, create-part-${idx}, parted, --script, ${partition.volume_path}, 'mkpart extended ext4 ${partition.partition_start} ${partition.partition_end}' ]
+- [ cloud-init-per, once, create-fs-part-${idx}, mkfs.ext4, ${partition.partition_path} ]
+%{~ endfor }
+
+runcmd:
+%{~ for idx, partition in extra_partitions }
+  - mkdir -p ${partition.mount_path}
+  - chown nobody:nogroup ${partition.mount_path}
+  - mount ${partition.partition_path} ${partition.mount_path}
+%{~ endfor }
+
+mounts:
+%{~ for idx, partition in extra_partitions }
+  - [ ${partition.partition_path}, ${partition.mount_path} ]
+%{~ endfor }
+%{~ else ~}
+# yamllint disable rule:comments
+#cloud-config
+## in some cases novnc console access is required
+## it requires ssh password to be set
+#ssh_pwauth: yes
+#chpasswd:
+#  list: |
+#    root:secret
+#  expire: False
+
+## in some cases direct root ssh access via ssh key is required
+#disable_root: false
+
+## in some cases additional CA certs are required
+#ca-certs:
+#  trusted: |
+#      -----BEGIN CERTIFICATE-----
+%{~ endif }

contrib/terraform/openstack/modules/compute/variables.tf

@@ -116,9 +116,48 @@ variable "k8s_allowed_egress_ips" {
   type = list
 }
 
-variable "k8s_masters" {}
+variable "k8s_masters" {
+  type = map(object({
+    az                     = string
+    flavor                 = string
+    floating_ip            = bool
+    etcd                   = bool
+    image_id               = optional(string)
+    root_volume_size_in_gb = optional(number)
+    volume_type            = optional(string)
+    network_id             = optional(string)
+  }))
+}
 
-variable "k8s_nodes" {}
+variable "k8s_nodes" {
+  type = map(object({
+    az                     = string
+    flavor                 = string
+    floating_ip            = bool
+    extra_groups           = optional(string)
+    image_id               = optional(string)
+    root_volume_size_in_gb = optional(number)
+    volume_type            = optional(string)
+    network_id             = optional(string)
+    additional_server_groups = optional(list(string))
+    server_group           = optional(string)
+    cloudinit              = optional(object({
+      extra_partitions = list(object({
+        volume_path     = string
+        partition_path  = string
+        partition_start = string
+        partition_end   = string
+        mount_path      = string
+      }))
+    }))
+  }))
+}
+
+variable "additional_server_groups" {
+  type = map(object({
+    policy = string
+  }))
+}
 
 variable "supplementary_master_groups" {
   default = ""
@@ -136,6 +175,10 @@ variable "worker_allowed_ports" {
   type = list
 }
 
+variable "bastion_allowed_ports" {
+  type = list
+}
+
 variable "use_access_ip" {}
 
 variable "master_server_group_policy" {
@@ -185,3 +228,7 @@ variable "port_security_enabled" {
 variable "force_null_port_security" {
   type = bool
 }
+
+variable "private_subnet_id" {
+  type = string
+}

contrib/terraform/openstack/modules/compute/versions.tf

@@ -4,5 +4,5 @@ terraform {
       source = "terraform-provider-openstack/openstack"
     }
   }
-  required_version = ">= 0.12.26"
+  required_version = ">= 1.3.0"
 }

contrib/terraform/openstack/modules/ips/main.tf

@@ -44,4 +44,3 @@ resource "openstack_networking_floatingip_v2" "k8s_nodes" {
   pool       = var.floatingip_pool
   depends_on = [null_resource.dummy_dependency]
 }
-

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

@@ -86,4 +86,4 @@ floatingip_pool = "<pool>"
 bastion_allowed_remote_ips = ["0.0.0.0/0"]
 
 # Force port security to be null. Some cloud providers do not allow to set port security.
-# force_null_port_security = false
+# force_null_port_security = false

contrib/terraform/openstack/variables.tf

@@ -257,6 +257,12 @@ variable "worker_allowed_ports" {
   ]
 }
 
+variable "bastion_allowed_ports" {
+  type = list(any)
+
+  default = []
+}
+
 variable "use_access_ip" {
   default = 1
 }
@@ -294,6 +300,13 @@ variable "k8s_nodes" {
   default = {}
 }
 
+variable "additional_server_groups" {
+  default = {}
+  type = map(object({
+    policy = string
+  }))
+}
+
 variable "extra_sec_groups" {
   default = false
 }

contrib/terraform/openstack/versions.tf

@@ -5,5 +5,5 @@ terraform {
       version = "~> 1.17"
     }
   }
-  required_version = ">= 0.12.26"
+  required_version = ">= 1.3.0"
 }

contrib/terraform/terraform.py

@@ -194,9 +194,19 @@ def parse_bool(string_form):
     else:
         raise ValueError('could not convert %r to a bool' % string_form)
 
+def sanitize_groups(groups):
+    _groups = []
+    chars_to_replace = ['+', '-', '=', '.', '/', ' ']
+    for i in groups:
+        _i = i
+        for char in chars_to_replace:
+            _i = _i.replace(char, '_')
+        _groups.append(_i)
+    groups.clear()
+    groups.extend(_groups)
 
-@parses('metal_device')
-def metal_device(resource, tfvars=None):
+@parses('equinix_metal_device')
+def equinix_metal_device(resource, tfvars=None):
     raw_attrs = resource['primary']['attributes']
     name = raw_attrs['hostname']
     groups = []
@@ -212,7 +222,7 @@ def metal_device(resource, tfvars=None):
         'project_id': raw_attrs['project_id'],
         'state': raw_attrs['state'],
         # ansible
-        'ansible_ssh_host': raw_attrs['network.0.address'],
+        'ansible_host': raw_attrs['network.0.address'],
         'ansible_ssh_user': 'root',  # Use root by default in metal
         # generic
         'ipv4_address': raw_attrs['network.0.address'],
@@ -220,7 +230,7 @@ def metal_device(resource, tfvars=None):
         'ipv6_address': raw_attrs['network.1.address'],
         'public_ipv6': raw_attrs['network.1.address'],
         'private_ipv4': raw_attrs['network.2.address'],
-        'provider': 'metal',
+        'provider': 'equinix',
     }
 
     if raw_attrs['operating_system'] == 'flatcar_stable':
@@ -228,13 +238,14 @@ def metal_device(resource, tfvars=None):
         attrs.update({'ansible_ssh_user': 'core'})
 
     # add groups based on attrs
-    groups.append('metal_operating_system=' + attrs['operating_system'])
-    groups.append('metal_locked=%s' % attrs['locked'])
-    groups.append('metal_state=' + attrs['state'])
-    groups.append('metal_plan=' + attrs['plan'])
+    groups.append('equinix_metal_operating_system_%s' % attrs['operating_system'])
+    groups.append('equinix_metal_locked_%s' % attrs['locked'])
+    groups.append('equinix_metal_state_%s' % attrs['state'])
+    groups.append('equinix_metal_plan_%s' % attrs['plan'])
 
     # groups specific to kubespray
     groups = groups + attrs['tags']
+    sanitize_groups(groups)
 
     return name, attrs, groups
 
@@ -273,8 +284,6 @@ def openstack_host(resource, module_name):
         'network': parse_attr_list(raw_attrs, 'network'),
         'region': raw_attrs.get('region', ''),
         'security_groups': parse_list(raw_attrs, 'security_groups'),
-        # ansible
-        'ansible_ssh_port': 22,
         # workaround for an OpenStack bug where hosts have a different domain
         # after they're restarted
         'host_domain': 'novalocal',
@@ -289,25 +298,30 @@ def openstack_host(resource, module_name):
     if 'floating_ip' in raw_attrs:
         attrs['private_ipv4'] = raw_attrs['network.0.fixed_ip_v4']
 
+    if 'metadata.use_access_ip' in raw_attrs and raw_attrs['metadata.use_access_ip'] == "0":
+        attrs.pop('access_ip')
+
     try:
         if 'metadata.prefer_ipv6' in raw_attrs and raw_attrs['metadata.prefer_ipv6'] == "1":
             attrs.update({
-                'ansible_ssh_host': re.sub("[\[\]]", "", raw_attrs['access_ip_v6']),
+                'ansible_host': re.sub("[\[\]]", "", raw_attrs['access_ip_v6']),
                 'publicly_routable': True,
             })
         else:
             attrs.update({
-                'ansible_ssh_host': raw_attrs['access_ip_v4'],
+                'ansible_host': raw_attrs['access_ip_v4'],
                 'publicly_routable': True,
             })
     except (KeyError, ValueError):
-        attrs.update({'ansible_ssh_host': '', 'publicly_routable': False})
+        attrs.update({'ansible_host': '', 'publicly_routable': False})
 
     # Handling of floating IPs has changed: https://github.com/terraform-providers/terraform-provider-openstack/blob/master/CHANGELOG.md#010-june-21-2017
 
     # attrs specific to Ansible
     if 'metadata.ssh_user' in raw_attrs:
-        attrs['ansible_ssh_user'] = raw_attrs['metadata.ssh_user']
+        attrs['ansible_user'] = raw_attrs['metadata.ssh_user']
+    if 'metadata.ssh_port' in raw_attrs:
+        attrs['ansible_port'] = raw_attrs['metadata.ssh_port']
 
     if 'volume.#' in list(raw_attrs.keys()) and int(raw_attrs['volume.#']) > 0:
         device_index = 1
@@ -334,6 +348,8 @@ def openstack_host(resource, module_name):
     for group in attrs['metadata'].get('kubespray_groups', "").split(","):
         groups.append(group)
 
+    sanitize_groups(groups)
+
     return name, attrs, groups
 
 
@@ -349,7 +365,7 @@ def iter_host_ips(hosts, ips):
                 'access_ip_v4': ip,
                 'access_ip': ip,
                 'public_ipv4': ip,
-                'ansible_ssh_host': ip,
+                'ansible_host': ip,
             })
 
         if 'use_access_ip' in host[1]['metadata'] and host[1]['metadata']['use_access_ip'] == "0":
@@ -389,7 +405,7 @@ def query_list(hosts):
 def query_hostfile(hosts):
     out = ['## begin hosts generated by terraform.py ##']
     out.extend(
-        '{}\t{}'.format(attrs['ansible_ssh_host'].ljust(16), name)
+        '{}\t{}'.format(attrs['ansible_host'].ljust(16), name)
         for name, attrs, _ in hosts
     )
 

contrib/terraform/upcloud/README.md

@@ -112,14 +112,32 @@ terraform destroy --var-file cluster-settings.tfvars \
     * `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)
 * `firewall_enabled`: Enable firewall rules
+* `firewall_default_deny_in`: Set the firewall to deny inbound traffic by default. Automatically adds UpCloud DNS server and NTP port allowlisting.
+* `firewall_default_deny_out`: Set the firewall to deny outbound traffic by default.
 * `master_allowed_remote_ips`: List of IP ranges that should be allowed to access API of masters
   * `start_address`: Start of address range to allow
   * `end_address`: End of address range to allow
 * `k8s_allowed_remote_ips`: List of IP ranges that should be allowed SSH access to all nodes
   * `start_address`: Start of address range to allow
   * `end_address`: End of address range to allow
+* `master_allowed_ports`: List of port ranges that should be allowed to access the masters
+  * `protocol`: Protocol *(tcp|udp|icmp)*
+  * `port_range_min`: Start of port range to allow
+  * `port_range_max`: End of port range to allow
+  * `start_address`: Start of address range to allow
+  * `end_address`: End of address range to allow
+* `worker_allowed_ports`: List of port ranges that should be allowed to access the workers
+  * `protocol`: Protocol *(tcp|udp|icmp)*
+  * `port_range_min`: Start of port range to allow
+  * `port_range_max`: End of port range to allow
+  * `start_address`: Start of address range to allow
+  * `end_address`: End of address range to allow
 * `loadbalancer_enabled`: Enable managed load balancer
 * `loadbalancer_plan`: Plan to use for load balancer *(development|production-small)*
 * `loadbalancers`: Ports to load balance and which machines to forward to. Key of this object will be used as the name of the load balancer frontends/backends
   * `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.
+* `server_groups`: Group servers together
+  * `servers`: The servers that should be included in the group.
+  * `anti_affinity`: If anti-affinity should be enabled, try to spread the VMs out on separate nodes.

contrib/terraform/upcloud/cluster-settings.tfvars

@@ -95,7 +95,9 @@ machines = {
   }
 }
 
-firewall_enabled = false
+firewall_enabled          = false
+firewall_default_deny_in  = false
+firewall_default_deny_out = false
 
 master_allowed_remote_ips = [
   {
@@ -111,11 +113,15 @@ k8s_allowed_remote_ips = [
   }
 ]
 
+master_allowed_ports = []
+worker_allowed_ports = []
+
 loadbalancer_enabled = false
 loadbalancer_plan    = "development"
 loadbalancers = {
   # "http" : {
   #   "port" : 80,
+  #   "target_port" : 80,
   #   "backend_servers" : [
   #     "worker-0",
   #     "worker-1",
@@ -123,3 +129,20 @@ loadbalancers = {
   #   ]
   # }
 }
+
+server_groups = {
+  # "control-plane" = {
+  #   servers = [
+  #     "master-0"
+  #   ]
+  #   anti_affinity = true
+  # },
+  # "workers" = {
+  #   servers = [
+  #     "worker-0",
+  #     "worker-1",
+  #     "worker-2"
+  #   ]
+  #   anti_affinity = true
+  # }
+}

contrib/terraform/upcloud/main.tf

@@ -24,12 +24,18 @@ module "kubernetes" {
   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
+  master_allowed_ports      = var.master_allowed_ports
+  worker_allowed_ports      = var.worker_allowed_ports
 
   loadbalancer_enabled = var.loadbalancer_enabled
   loadbalancer_plan    = var.loadbalancer_plan
   loadbalancers        = var.loadbalancers
+
+  server_groups = var.server_groups
 }
 
 #

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

@@ -13,7 +13,7 @@ locals {
   lb_backend_servers = flatten([
     for lb_name, loadbalancer in var.loadbalancers : [
       for backend_server in loadbalancer.backend_servers : {
-        port = loadbalancer.port
+        port = loadbalancer.target_port
         lb_name = lb_name
         server_name = backend_server
       }
@@ -80,7 +80,7 @@ resource "upcloud_server" "master" {
   lifecycle {
     ignore_changes = [storage_devices]
   }
-  
+
   firewall  = var.firewall_enabled
 
   dynamic "storage_devices" {
@@ -228,6 +228,126 @@ resource "upcloud_firewall_rules" "master" {
       source_address_start   = "0.0.0.0"
     }
   }
+
+  dynamic firewall_rule {
+    for_each = var.master_allowed_ports
+
+    content {
+      action                 = "accept"
+      comment                = "Allow access on this port"
+      destination_port_end   = firewall_rule.value.port_range_max
+      destination_port_start = firewall_rule.value.port_range_min
+      direction              = "in"
+      family                 = "IPv4"
+      protocol               = firewall_rule.value.protocol
+      source_address_end     = firewall_rule.value.end_address
+      source_address_start   = firewall_rule.value.start_address
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["tcp", "udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "UpCloud DNS"
+      source_port_end        = "53"
+      source_port_start      = "53"
+      direction              = "in"
+      family                 = "IPv4"
+      protocol               = firewall_rule.value
+      source_address_end     = "94.237.40.9"
+      source_address_start   = "94.237.40.9"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["tcp", "udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "UpCloud DNS"
+      source_port_end        = "53"
+      source_port_start      = "53"
+      direction              = "in"
+      family                 = "IPv4"
+      protocol               = firewall_rule.value
+      source_address_end     = "94.237.127.9"
+      source_address_start   = "94.237.127.9"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["tcp", "udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "UpCloud DNS"
+      source_port_end        = "53"
+      source_port_start      = "53"
+      direction              = "in"
+      family                 = "IPv6"
+      protocol               = firewall_rule.value
+      source_address_end     = "2a04:3540:53::1"
+      source_address_start   = "2a04:3540:53::1"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["tcp", "udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "UpCloud DNS"
+      source_port_end        = "53"
+      source_port_start      = "53"
+      direction              = "in"
+      family                 = "IPv6"
+      protocol               = firewall_rule.value
+      source_address_end     = "2a04:3544:53::1"
+      source_address_start   = "2a04:3544:53::1"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "NTP Port"
+      source_port_end        = "123"
+      source_port_start      = "123"
+      direction              = "in"
+      family                 = "IPv4"
+      protocol               = firewall_rule.value
+      source_address_end     = "255.255.255.255"
+      source_address_start   = "0.0.0.0"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "NTP Port"
+      source_port_end        = "123"
+      source_port_start      = "123"
+      direction              = "in"
+      family                 = "IPv6"
+      protocol               = firewall_rule.value
+    }
+  }
+
+  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_firewall_rules" "k8s" {
@@ -265,6 +385,126 @@ resource "upcloud_firewall_rules" "k8s" {
       source_address_start   = "0.0.0.0"
     }
   }
+
+  dynamic firewall_rule {
+    for_each = var.worker_allowed_ports
+
+    content {
+      action                 = "accept"
+      comment                = "Allow access on this port"
+      destination_port_end   = firewall_rule.value.port_range_max
+      destination_port_start = firewall_rule.value.port_range_min
+      direction              = "in"
+      family                 = "IPv4"
+      protocol               = firewall_rule.value.protocol
+      source_address_end     = firewall_rule.value.end_address
+      source_address_start   = firewall_rule.value.start_address
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["tcp", "udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "UpCloud DNS"
+      source_port_end        = "53"
+      source_port_start      = "53"
+      direction              = "in"
+      family                 = "IPv4"
+      protocol               = firewall_rule.value
+      source_address_end     = "94.237.40.9"
+      source_address_start   = "94.237.40.9"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["tcp", "udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "UpCloud DNS"
+      source_port_end        = "53"
+      source_port_start      = "53"
+      direction              = "in"
+      family                 = "IPv4"
+      protocol               = firewall_rule.value
+      source_address_end     = "94.237.127.9"
+      source_address_start   = "94.237.127.9"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["tcp", "udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "UpCloud DNS"
+      source_port_end        = "53"
+      source_port_start      = "53"
+      direction              = "in"
+      family                 = "IPv6"
+      protocol               = firewall_rule.value
+      source_address_end     = "2a04:3540:53::1"
+      source_address_start   = "2a04:3540:53::1"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["tcp", "udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "UpCloud DNS"
+      source_port_end        = "53"
+      source_port_start      = "53"
+      direction              = "in"
+      family                 = "IPv6"
+      protocol               = firewall_rule.value
+      source_address_end     = "2a04:3544:53::1"
+      source_address_start   = "2a04:3544:53::1"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "NTP Port"
+      source_port_end        = "123"
+      source_port_start      = "123"
+      direction              = "in"
+      family                 = "IPv4"
+      protocol               = firewall_rule.value
+      source_address_end     = "255.255.255.255"
+      source_address_start   = "0.0.0.0"
+    }
+  }
+
+  dynamic firewall_rule {
+    for_each = var.firewall_default_deny_in ? ["udp"] : []
+
+    content {
+      action                 = "accept"
+      comment                = "NTP Port"
+      source_port_end        = "123"
+      source_port_start      = "123"
+      direction              = "in"
+      family                 = "IPv6"
+      protocol               = firewall_rule.value
+    }
+  }
+
+  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" {
@@ -285,7 +525,7 @@ resource "upcloud_loadbalancer_backend" "lb_backend" {
 
 resource "upcloud_loadbalancer_frontend" "lb_frontend" {
   for_each = var.loadbalancer_enabled ? var.loadbalancers : {}
-  
+
   loadbalancer         = upcloud_loadbalancer.lb[0].id
   name                 = "lb-frontend-${each.key}"
   mode                 = "tcp"
@@ -295,7 +535,7 @@ resource "upcloud_loadbalancer_frontend" "lb_frontend" {
 
 resource "upcloud_loadbalancer_static_backend_member" "lb_backend_member" {
   for_each = {
-    for be_server in local.lb_backend_servers: 
+    for be_server in local.lb_backend_servers:
       "${be_server.server_name}-lb-backend-${be_server.lb_name}" => be_server
       if var.loadbalancer_enabled
   }
@@ -308,3 +548,11 @@ resource "upcloud_loadbalancer_static_backend_member" "lb_backend_member" {
   max_sessions = var.loadbalancer_plan == "production-small" ? 50000 : 1000
   enabled      = true
 }
+
+resource "upcloud_server_group" "server_groups" {
+  for_each      = var.server_groups
+  title         = each.key
+  anti_affinity = each.value.anti_affinity
+  labels        = {}
+  members       = [for server in each.value.servers : merge(upcloud_server.master, upcloud_server.worker)[server].id]
+}