Add c12s sample inventory and deploy script

Signed-off-by: yanggang <gang.yang@daocloud.io>

Signed-off-by: yanggang <gang.yang@daocloud.io>

.ansible-lint

@@ -18,3 +18,13 @@ skip_list:
   # While it can be useful to have these metadata available, they are also available in the existing documentation.
   # (Disabled in May 2019)
   - '701'
+
+  # [role-name] "meta/main.yml" Role name role-name does not match ``^+$`` pattern
+  # Meta roles in Kubespray don't need proper names
+  # (Disabled in June 2021)
+  - 'role-name'
+
+  # [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'

.gitignore

@@ -3,7 +3,10 @@
 **/vagrant_ansible_inventory
 *.iml
 temp
+contrib/offline/offline-files
+contrib/offline/offline-files.tar.gz
 .idea
+.vscode
 .tox
 .cache
 *.bak
@@ -11,16 +14,19 @@ temp
 *.tfstate.backup
 .terraform/
 contrib/terraform/aws/credentials.tfvars
+.terraform.lock.hcl
 /ssh-bastion.conf
 **/*.sw[pon]
 *~
 vagrant/
 plugins/mitogen
+deploy.sh 
 
 # Ansible inventory
 inventory/*
 !inventory/local
 !inventory/sample
+!inventory/c12s-sample
 inventory/*/artifacts/
 
 # Byte-compiled / optimized / DLL files
@@ -99,3 +105,13 @@ target/
 # virtualenv
 venv/
 ENV/
+
+# molecule
+roles/**/molecule/**/__pycache__/
+
+# macOS
+.DS_Store
+
+# Temp location used by our scripts
+scripts/tmp/
+tmp.md

.gitlab-ci.yml

@@ -8,7 +8,7 @@ stages:
   - deploy-special
 
 variables:
-  KUBESPRAY_VERSION: v2.15.1
+  KUBESPRAY_VERSION: v2.20.0
   FAILFASTCI_NAMESPACE: 'kargo-ci'
   GITLAB_REPOSITORY: 'kargo-ci/kubernetes-sigs-kubespray'
   ANSIBLE_FORCE_COLOR: "true"
@@ -16,6 +16,7 @@ variables:
   TEST_ID: "$CI_PIPELINE_ID-$CI_BUILD_ID"
   CI_TEST_VARS: "./tests/files/${CI_JOB_NAME}.yml"
   CI_TEST_REGISTRY_MIRROR: "./tests/common/_docker_hub_registry_mirror.yml"
+  CI_TEST_SETTING: "./tests/common/_kubespray_test_settings.yml"
   GS_ACCESS_KEY_ID: $GS_KEY
   GS_SECRET_ACCESS_KEY: $GS_SECRET
   CONTAINER_ENGINE: docker
@@ -26,18 +27,20 @@ variables:
   ANSIBLE_INVENTORY: ./inventory/sample/${CI_JOB_NAME}-${BUILD_NUMBER}.ini
   IDEMPOT_CHECK: "false"
   RESET_CHECK: "false"
+  REMOVE_NODE_CHECK: "false"
   UPGRADE_TEST: "false"
   MITOGEN_ENABLE: "false"
   ANSIBLE_LOG_LEVEL: "-vv"
   RECOVER_CONTROL_PLANE_TEST: "false"
   RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:],kube_control_plane[1:]"
-  TERRAFORM_14_VERSION: 0.14.10
-  TERRAFORM_13_VERSION: 0.13.6
+  TERRAFORM_VERSION: 1.0.8
+  ANSIBLE_MAJOR_VERSION: "2.11"
 
 before_script:
   - ./tests/scripts/rebase.sh
   - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
-  - python -m pip install -r tests/requirements.txt
+  - python -m pip uninstall -y ansible ansible-base ansible-core
+  - python -m pip install -r tests/requirements-${ANSIBLE_MAJOR_VERSION}.txt
   - mkdir -p /.ssh
 
 .job: &job
@@ -51,6 +54,7 @@ before_script:
 
 .testcases: &testcases
   <<: *job
+  retry: 1
   before_script:
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
     - ./tests/scripts/rebase.sh
@@ -77,3 +81,4 @@ include:
   - .gitlab-ci/terraform.yml
   - .gitlab-ci/packet.yml
   - .gitlab-ci/vagrant.yml
+  - .gitlab-ci/molecule.yml

.gitlab-ci/lint.yml

@@ -14,7 +14,7 @@ vagrant-validate:
   stage: unit-tests
   tags: [light]
   variables:
-    VAGRANT_VERSION: 2.2.15
+    VAGRANT_VERSION: 2.2.19
   script:
     - ./tests/scripts/vagrant-validate.sh
   except: ['triggers', 'master']
@@ -23,9 +23,8 @@ ansible-lint:
   extends: .job
   stage: unit-tests
   tags: [light]
-  # lint every yml/yaml file that looks like it contains Ansible plays
-  script: |-
-    grep -Rl '^- hosts: \|^  hosts: ' --include \*.yml --include \*.yaml . | xargs -P 4 -n 25 ansible-lint -v
+  script:
+    - ansible-lint -v
   except: ['triggers', 'master']
 
 syntax-check:
@@ -53,6 +52,7 @@ tox-inventory-builder:
     - ./tests/scripts/rebase.sh
     - 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
   script:
     - pip3 install tox
@@ -68,6 +68,20 @@ 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-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

@@ -0,0 +1,86 @@
+---
+
+.molecule:
+  tags: [c3.small.x86]
+  only: [/^pr-.*$/]
+  except: ['triggers']
+  image: quay.io/kubespray/vagrant:$KUBESPRAY_VERSION
+  services: []
+  stage: deploy-part1
+  before_script:
+    - tests/scripts/rebase.sh
+    - 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
+    - ./tests/scripts/vagrant_clean.sh
+  script:
+    - ./tests/scripts/molecule_run.sh
+  after_script:
+    - chronic ./tests/scripts/molecule_logs.sh
+  artifacts:
+    when: always
+    paths:
+      - molecule_logs/
+
+# CI template for periodic CI jobs
+# Enabled when PERIODIC_CI_ENABLED var is set
+.molecule_periodic:
+  only:
+    variables:
+      - $PERIODIC_CI_ENABLED
+  allow_failure: true
+  extends: .molecule
+
+molecule_full:
+  extends: .molecule_periodic
+
+molecule_no_container_engines:
+  extends: .molecule
+  script:
+    - ./tests/scripts/molecule_run.sh -e container-engine
+  when: on_success
+
+molecule_docker:
+  extends: .molecule
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/cri-dockerd
+  when: on_success
+
+molecule_containerd:
+  extends: .molecule
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/containerd
+  when: on_success
+
+molecule_cri-o:
+  extends: .molecule
+  stage: deploy-part2
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/cri-o
+  when: on_success
+
+# Stage 3 container engines don't get as much attention so allow them to fail
+molecule_kata:
+  extends: .molecule
+  stage: deploy-part3
+  allow_failure: true
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/kata-containers
+  when: on_success
+
+molecule_gvisor:
+  extends: .molecule
+  stage: deploy-part3
+  allow_failure: true
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/gvisor
+  when: on_success
+
+molecule_youki:
+  extends: .molecule
+  stage: deploy-part3
+  allow_failure: true
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/youki
+  when: on_success

.gitlab-ci/packet.yml

@@ -2,6 +2,7 @@
 .packet:
   extends: .testcases
   variables:
+    ANSIBLE_TIMEOUT: "120"
     CI_PLATFORM: packet
     SSH_USER: kubespray
   tags:
@@ -22,27 +23,60 @@
   allow_failure: true
   extends: .packet
 
-packet_ubuntu18-calico-aio:
-  stage: deploy-part1
-  extends: .packet_pr
-  when: on_success
-
-# Future AIO job
+# The ubuntu20-calico-aio jobs are meant as early stages to prevent running the full CI if something is horribly broken
 packet_ubuntu20-calico-aio:
   stage: deploy-part1
   extends: .packet_pr
   when: on_success
+  variables:
+    RESET_CHECK: "true"
+
+packet_ubuntu20-calico-aio-ansible-2_11:
+  stage: deploy-part1
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    ANSIBLE_MAJOR_VERSION: "2.11"
+    RESET_CHECK: "true"
 
 # ### PR JOBS PART2
 
-packet_centos7-flannel-containerd-addons-ha:
+packet_ubuntu18-aio-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_ubuntu20-aio-docker:
+  stage: deploy-part2
+  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
   when: on_success
-  variables:
-    MITOGEN_ENABLE: "true"
 
-packet_centos8-crio:
+packet_almalinux8-crio:
   extends: .packet_pr
   stage: deploy-part2
   when: on_success
@@ -51,10 +85,13 @@ packet_ubuntu18-crio:
   extends: .packet_pr
   stage: deploy-part2
   when: manual
-  variables:
-    MITOGEN_ENABLE: "true"
 
-packet_ubuntu16-canal-kubeadm-ha:
+packet_fedora35-crio:
+  extends: .packet_pr
+  stage: deploy-part2
+  when: manual
+
+packet_ubuntu16-canal-ha:
   stage: deploy-part2
   extends: .packet_periodic
   when: on_success
@@ -69,27 +106,30 @@ packet_ubuntu16-flannel-ha:
   extends: .packet_pr
   when: manual
 
-packet_ubuntu16-kube-router-sep:
-  stage: deploy-part2
-  extends: .packet_pr
-  when: manual
-
-packet_ubuntu16-kube-router-svc-proxy:
-  stage: deploy-part2
-  extends: .packet_pr
-  when: manual
-
 packet_debian10-cilium-svc-proxy:
   stage: deploy-part2
   extends: .packet_periodic
   when: on_success
 
-packet_debian10-containerd:
+packet_debian10-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian10-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian11-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian11-docker:
   stage: deploy-part2
   extends: .packet_pr
   when: on_success
-  variables:
-    MITOGEN_ENABLE: "true"
 
 packet_centos7-calico-ha-once-localhost:
   stage: deploy-part2
@@ -101,17 +141,32 @@ packet_centos7-calico-ha-once-localhost:
   services:
     - docker:19.03.9-dind
 
-packet_centos8-kube-ovn:
+packet_almalinux8-kube-ovn:
   stage: deploy-part2
   extends: .packet_periodic
   when: on_success
 
-packet_centos8-calico:
+packet_almalinux8-calico:
   stage: deploy-part2
   extends: .packet_pr
   when: on_success
 
-packet_fedora32-weave:
+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_almalinux8-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_fedora36-docker-weave:
   stage: deploy-part2
   extends: .packet_pr
   when: on_success
@@ -121,14 +176,14 @@ packet_opensuse-canal:
   extends: .packet_periodic
   when: on_success
 
-packet_ubuntu18-ovn4nfv:
+packet_opensuse-docker-cilium:
   stage: deploy-part2
-  extends: .packet_periodic
-  when: on_success
+  extends: .packet_pr
+  when: manual
 
 # ### MANUAL JOBS
 
-packet_ubuntu16-weave-sep:
+packet_ubuntu16-docker-weave-sep:
   stage: deploy-part2
   extends: .packet_pr
   when: manual
@@ -138,12 +193,18 @@ packet_ubuntu18-cilium-sep:
   extends: .packet_pr
   when: manual
 
-packet_ubuntu18-flannel-containerd-ha:
+packet_ubuntu18-flannel-ha:
   stage: deploy-part2
   extends: .packet_pr
   when: manual
 
-packet_ubuntu18-flannel-containerd-ha-once:
+packet_ubuntu18-flannel-ha-once:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+# Calico HA eBPF
+packet_almalinux8-calico-ha-ebpf:
   stage: deploy-part2
   extends: .packet_pr
   when: manual
@@ -158,34 +219,44 @@ packet_centos7-calico-ha:
   extends: .packet_pr
   when: manual
 
-packet_centos7-kube-router:
-  stage: deploy-part2
-  extends: .packet_pr
-  when: manual
-
 packet_centos7-multus-calico:
   stage: deploy-part2
   extends: .packet_pr
   when: manual
 
-packet_oracle7-canal-ha:
+packet_centos7-canal-ha:
   stage: deploy-part2
   extends: .packet_pr
   when: manual
 
-packet_fedora33-calico:
+packet_fedora36-docker-calico:
   stage: deploy-part2
   extends: .packet_periodic
   when: on_success
   variables:
-    MITOGEN_ENABLE: "true"
+    RESET_CHECK: "true"
+
+packet_fedora35-calico-selinux:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_fedora35-calico-swap-selinux:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
 
 packet_amazon-linux-2-aio:
   stage: deploy-part2
   extends: .packet_pr
   when: manual
 
-packet_fedora32-kube-ovn-containerd:
+packet_almalinux8-calico-nodelocaldns-secondary:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_fedora36-kube-ovn:
   stage: deploy-part2
   extends: .packet_periodic
   when: on_success
@@ -199,23 +270,46 @@ packet_centos7-weave-upgrade-ha:
   when: on_success
   variables:
     UPGRADE_TEST: basic
-    MITOGEN_ENABLE: "false"
 
-packet_debian9-calico-upgrade:
+packet_ubuntu20-calico-etcd-kubeadm-upgrade-ha:
+  stage: deploy-part3
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    UPGRADE_TEST: basic
+
+# Calico HA Wireguard
+packet_ubuntu20-calico-ha-wireguard:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_debian11-calico-upgrade:
   stage: deploy-part3
   extends: .packet_pr
   when: on_success
   variables:
     UPGRADE_TEST: graceful
-    MITOGEN_ENABLE: "false"
 
-packet_debian9-calico-upgrade-once:
+packet_almalinux8-calico-remove-node:
+  stage: deploy-part3
+  extends: .packet_pr
+  when: on_success
+  variables:
+    REMOVE_NODE_CHECK: "true"
+    REMOVE_NODE_NAME: "instance-3"
+
+packet_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
   variables:
     UPGRADE_TEST: graceful
-    MITOGEN_ENABLE: "false"
 
 packet_ubuntu18-calico-ha-recover:
   stage: deploy-part3

.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

@@ -12,13 +12,13 @@
     # Prepare inventory
     - cp contrib/terraform/$PROVIDER/sample-inventory/cluster.tfvars .
     - ln -s contrib/terraform/$PROVIDER/hosts
-    - terraform init contrib/terraform/$PROVIDER
+    - terraform -chdir="contrib/terraform/$PROVIDER" init
     # Copy SSH keypair
     - mkdir -p ~/.ssh
     - echo "$PACKET_PRIVATE_KEY" | base64 -d > ~/.ssh/id_rsa
     - chmod 400 ~/.ssh/id_rsa
     - echo "$PACKET_PUBLIC_KEY" | base64 -d > ~/.ssh/id_rsa.pub
-    - mkdir -p group_vars
+    - mkdir -p contrib/terraform/$PROVIDER/group_vars
     # Random subnet to avoid routing conflicts
     - export TF_VAR_subnet_cidr="10.$(( $RANDOM % 256 )).$(( $RANDOM % 256 )).0/24"
 
@@ -28,8 +28,8 @@
   tags: [light]
   only: ['master', /^pr-.*$/]
   script:
-    - terraform validate -var-file=cluster.tfvars contrib/terraform/$PROVIDER
-    - terraform fmt -check -diff contrib/terraform/$PROVIDER
+    - terraform -chdir="contrib/terraform/$PROVIDER" validate
+    - terraform -chdir="contrib/terraform/$PROVIDER" fmt -check -diff
 
 .terraform_apply:
   extends: .terraform_install
@@ -53,92 +53,51 @@
     # Cleanup regardless of exit code
     - chronic ./tests/scripts/testcases_cleanup.sh
 
-tf-0.13.x-validate-openstack:
+tf-validate-openstack:
   extends: .terraform_validate
   variables:
-    TF_VERSION: $TERRAFORM_13_VERSION
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: openstack
     CLUSTER: $CI_COMMIT_REF_NAME
 
-tf-0.13.x-validate-packet:
+tf-validate-metal:
   extends: .terraform_validate
   variables:
-    TF_VERSION: $TERRAFORM_13_VERSION
-    PROVIDER: packet
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: metal
     CLUSTER: $CI_COMMIT_REF_NAME
 
-tf-0.13.x-validate-aws:
+tf-validate-aws:
   extends: .terraform_validate
   variables:
-    TF_VERSION: $TERRAFORM_13_VERSION
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: aws
     CLUSTER: $CI_COMMIT_REF_NAME
 
-tf-0.13.x-validate-exoscale:
+tf-validate-exoscale:
   extends: .terraform_validate
   variables:
-    TF_VERSION: $TERRAFORM_13_VERSION
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: exoscale
 
-tf-0.13.x-validate-vsphere:
+tf-validate-vsphere:
   extends: .terraform_validate
   variables:
-    TF_VERSION: $TERRAFORM_13_VERSION
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: vsphere
     CLUSTER: $CI_COMMIT_REF_NAME
 
-tf-0.13.x-validate-upcloud:
+tf-validate-upcloud:
   extends: .terraform_validate
   variables:
-    TF_VERSION: $TERRAFORM_13_VERSION
-    PROVIDER: upcloud
-    CLUSTER: $CI_COMMIT_REF_NAME
-
-tf-0.14.x-validate-openstack:
-  extends: .terraform_validate
-  variables:
-    TF_VERSION: $TERRAFORM_14_VERSION
-    PROVIDER: openstack
-    CLUSTER: $CI_COMMIT_REF_NAME
-
-tf-0.14.x-validate-packet:
-  extends: .terraform_validate
-  variables:
-    TF_VERSION: $TERRAFORM_14_VERSION
-    PROVIDER: packet
-    CLUSTER: $CI_COMMIT_REF_NAME
-
-tf-0.14.x-validate-aws:
-  extends: .terraform_validate
-  variables:
-    TF_VERSION: $TERRAFORM_14_VERSION
-    PROVIDER: aws
-    CLUSTER: $CI_COMMIT_REF_NAME
-
-tf-0.14.x-validate-exoscale:
-  extends: .terraform_validate
-  variables:
-    TF_VERSION: $TERRAFORM_14_VERSION
-    PROVIDER: exoscale
-
-tf-0.14.x-validate-vsphere:
-  extends: .terraform_validate
-  variables:
-    TF_VERSION: $TERRAFORM_14_VERSION
-    PROVIDER: vsphere
-    CLUSTER: $CI_COMMIT_REF_NAME
-
-tf-0.14.x-validate-upcloud:
-  extends: .terraform_validate
-  variables:
-    TF_VERSION: $TERRAFORM_14_VERSION
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: upcloud
     CLUSTER: $CI_COMMIT_REF_NAME
 
 # tf-packet-ubuntu16-default:
 #   extends: .terraform_apply
 #   variables:
-#     TF_VERSION: $TERRAFORM_14_VERSION
+#     TF_VERSION: $TERRAFORM_VERSION
 #     PROVIDER: packet
 #     CLUSTER: $CI_COMMIT_REF_NAME
 #     TF_VAR_number_of_k8s_masters: "1"
@@ -152,7 +111,7 @@ tf-0.14.x-validate-upcloud:
 # tf-packet-ubuntu18-default:
 #   extends: .terraform_apply
 #   variables:
-#     TF_VERSION: $TERRAFORM_14_VERSION
+#     TF_VERSION: $TERRAFORM_VERSION
 #     PROVIDER: packet
 #     CLUSTER: $CI_COMMIT_REF_NAME
 #     TF_VAR_number_of_k8s_masters: "1"
@@ -187,10 +146,6 @@ tf-0.14.x-validate-upcloud:
   OS_INTERFACE: public
   OS_IDENTITY_API_VERSION: "3"
   TF_VAR_router_id: "ab95917c-41fb-4881-b507-3a6dfe9403df"
-  # Since ELASTX is in Stockholm, Mitogen helps with latency
-  MITOGEN_ENABLE: "false"
-  # Mitogen doesn't support interpreter discovery yet
-  ANSIBLE_PYTHON_INTERPRETER: "/usr/bin/python3"
 
 tf-elastx_cleanup:
   stage: unit-tests
@@ -207,9 +162,10 @@ tf-elastx_ubuntu18-calico:
   extends: .terraform_apply
   stage: deploy-part3
   when: on_success
+  allow_failure: true
   variables:
     <<: *elastx_variables
-    TF_VERSION: $TERRAFORM_14_VERSION
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: openstack
     CLUSTER: $CI_COMMIT_REF_NAME
     ANSIBLE_TIMEOUT: "60"
@@ -235,44 +191,45 @@ tf-elastx_ubuntu18-calico:
     TF_VAR_image: ubuntu-18.04-server-latest
     TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'
 
+# OVH voucher expired, commenting job until things are sorted  out
 
-tf-ovh_cleanup:
-  stage: unit-tests
-  tags: [light]
-  image: python
-  environment: ovh
-  variables:
-    <<: *ovh_variables
-  before_script:
-    - pip install -r scripts/openstack-cleanup/requirements.txt
-  script:
-    - ./scripts/openstack-cleanup/main.py
+# tf-ovh_cleanup:
+#  stage: unit-tests
+#  tags: [light]
+#  image: python
+#  environment: ovh
+#  variables:
+#    <<: *ovh_variables
+#  before_script:
+#    - pip install -r scripts/openstack-cleanup/requirements.txt
+#  script:
+#    - ./scripts/openstack-cleanup/main.py
 
-tf-ovh_ubuntu18-calico:
-  extends: .terraform_apply
-  when: on_success
-  environment: ovh
-  variables:
-    <<: *ovh_variables
-    TF_VERSION: $TERRAFORM_14_VERSION
-    PROVIDER: openstack
-    CLUSTER: $CI_COMMIT_REF_NAME
-    ANSIBLE_TIMEOUT: "60"
-    SSH_USER: ubuntu
-    TF_VAR_number_of_k8s_masters: "0"
-    TF_VAR_number_of_k8s_masters_no_floating_ip: "1"
-    TF_VAR_number_of_k8s_masters_no_floating_ip_no_etcd: "0"
-    TF_VAR_number_of_etcd: "0"
-    TF_VAR_number_of_k8s_nodes: "0"
-    TF_VAR_number_of_k8s_nodes_no_floating_ip: "1"
-    TF_VAR_number_of_gfs_nodes_no_floating_ip: "0"
-    TF_VAR_number_of_bastions: "0"
-    TF_VAR_number_of_k8s_masters_no_etcd: "0"
-    TF_VAR_use_neutron: "0"
-    TF_VAR_floatingip_pool: "Ext-Net"
-    TF_VAR_external_net: "6011fbc9-4cbf-46a4-8452-6890a340b60b"
-    TF_VAR_network_name: "Ext-Net"
-    TF_VAR_flavor_k8s_master: "defa64c3-bd46-43b4-858a-d93bbae0a229"    # s1-8
-    TF_VAR_flavor_k8s_node: "defa64c3-bd46-43b4-858a-d93bbae0a229"      # s1-8
-    TF_VAR_image: "Ubuntu 18.04"
-    TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'
+# tf-ovh_ubuntu18-calico:
+#  extends: .terraform_apply
+#  when: on_success
+#  environment: ovh
+#  variables:
+#    <<: *ovh_variables
+#    TF_VERSION: $TERRAFORM_VERSION
+#    PROVIDER: openstack
+#    CLUSTER: $CI_COMMIT_REF_NAME
+#    ANSIBLE_TIMEOUT: "60"
+#    SSH_USER: ubuntu
+#    TF_VAR_number_of_k8s_masters: "0"
+#    TF_VAR_number_of_k8s_masters_no_floating_ip: "1"
+#    TF_VAR_number_of_k8s_masters_no_floating_ip_no_etcd: "0"
+#    TF_VAR_number_of_etcd: "0"
+#    TF_VAR_number_of_k8s_nodes: "0"
+#    TF_VAR_number_of_k8s_nodes_no_floating_ip: "1"
+#    TF_VAR_number_of_gfs_nodes_no_floating_ip: "0"
+#    TF_VAR_number_of_bastions: "0"
+#    TF_VAR_number_of_k8s_masters_no_etcd: "0"
+#    TF_VAR_use_neutron: "0"
+#    TF_VAR_floatingip_pool: "Ext-Net"
+#    TF_VAR_external_net: "6011fbc9-4cbf-46a4-8452-6890a340b60b"
+#    TF_VAR_network_name: "Ext-Net"
+#    TF_VAR_flavor_k8s_master: "defa64c3-bd46-43b4-858a-d93bbae0a229"    # s1-8
+#    TF_VAR_flavor_k8s_node: "defa64c3-bd46-43b4-858a-d93bbae0a229"      # s1-8
+#    TF_VAR_image: "Ubuntu 18.04"
+#    TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'

.gitlab-ci/vagrant.yml

@@ -1,21 +1,5 @@
 ---
 
-molecule_tests:
-  tags: [c3.small.x86]
-  only: [/^pr-.*$/]
-  except: ['triggers']
-  image: quay.io/kubespray/vagrant:$KUBESPRAY_VERSION
-  services: []
-  stage: deploy-part1
-  before_script:
-    - tests/scripts/rebase.sh
-    - apt-get update && apt-get install -y python3-pip
-    - update-alternatives --install /usr/bin/python python /usr/bin/python3 10
-    - python -m pip install -r tests/requirements.txt
-    - ./tests/scripts/vagrant_clean.sh
-  script:
-    - ./tests/scripts/molecule_run.sh
-
 .vagrant:
   extends: .testcases
   variables:
@@ -31,12 +15,14 @@ molecule_tests:
   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
     - ./tests/scripts/vagrant_clean.sh
   script:
     - ./tests/scripts/testcases_run.sh
   after_script:
     - chronic ./tests/scripts/testcases_cleanup.sh
+  allow_failure: true
 
 vagrant_ubuntu18-calico-dual-stack:
   stage: deploy-part2
@@ -57,3 +43,25 @@ vagrant_ubuntu20-flannel:
   stage: deploy-part2
   extends: .vagrant
   when: on_success
+  allow_failure: false
+
+vagrant_ubuntu16-kube-router-sep:
+  stage: deploy-part2
+  extends: .vagrant
+  when: manual
+
+# Service proxy test fails connectivity testing
+vagrant_ubuntu16-kube-router-svc-proxy:
+  stage: deploy-part2
+  extends: .vagrant
+  when: manual
+
+vagrant_fedora35-kube-router:
+  stage: deploy-part2
+  extends: .vagrant
+  when: on_success
+
+vagrant_centos7-kube-router:
+  stage: deploy-part2
+  extends: .vagrant
+  when: manual

.markdownlint.yaml

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

.pre-commit-config.yaml

@@ -0,0 +1,48 @@
+---
+repos:
+  - 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: 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

CONTRIBUTING.md

@@ -6,11 +6,22 @@
 
 It is recommended to use filter to manage the GitHub email notification, see [examples for setting filters to Kubernetes Github notifications](https://github.com/kubernetes/community/blob/master/communication/best-practices.md#examples-for-setting-filters-to-kubernetes-github-notifications)
 
-To install development dependencies you can use `pip install -r tests/requirements.txt`
+To install development dependencies you can set up a python virtual env with the necessary dependencies:
+
+```ShellSession
+virtualenv venv
+source venv/bin/activate
+pip install -r tests/requirements.txt
+```
 
 #### Linting
 
-Kubespray uses `yamllint` and `ansible-lint`. To run them locally use `yamllint .` and `ansible-lint`
+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
 
@@ -27,5 +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.
+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

@@ -1,30 +1,37 @@
-# Use imutable image tags rather than mutable tags (like ubuntu:18.04)
-FROM ubuntu:bionic-20200807
+# Use imutable image tags rather than mutable tags (like ubuntu:20.04)
+FROM ubuntu:focal-20220531
+
+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 rsync \
+    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=amd64] https://download.docker.com/linux/ubuntu \
+    "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/*
 
+# Some tools like yamllint need this
+# Pip needs this as well at the moment to install ansible
+# (and potentially other packages)
+# See: https://github.com/pypa/pip/issues/10219
+ENV LANG=C.UTF-8
+
 WORKDIR /kubespray
 COPY . .
-RUN /usr/bin/python3 -m pip install pip -U \
-    && /usr/bin/python3 -m pip install -r tests/requirements.txt \
-    && python3 -m pip install -r requirements.txt \
+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
 
 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/amd64/kubectl \
+    && 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
-
-# Some tools like yamllint need this
-ENV LANG=C.UTF-8

Makefile

@@ -1,5 +1,7 @@
 mitogen:
-	ansible-playbook -c local mitogen.yml -vv
+	@echo Mitogen support is deprecated.
+	@echo Please run the following command manually:
+	@echo   ansible-playbook -c local mitogen.yml -vv
 clean:
 	rm -rf dist/
 	rm *.retry

OWNERS_ALIASES

@@ -4,15 +4,23 @@ aliases:
     - chadswen
     - mirwan
     - miouge1
-    - woopstar
     - luckysb
     - floryut
+    - oomichi
+    - cristicalin
+    - liupeng0518
+    - yankay
   kubespray-reviewers:
     - holmsten
     - bozzo
     - eppo
     - oomichi
+    - jayonlau
+    - cristicalin
+    - liupeng0518
+    - yankay
   kubespray-emeritus_approvers:
     - riverzhang
     - atoms
     - ant31
+    - woopstar

README.md

@@ -5,7 +5,7 @@
 If you have questions, check the documentation at [kubespray.io](https://kubespray.io) and join us on the [kubernetes slack](https://kubernetes.slack.com), channel **\#kubespray**.
 You can get your invite [here](http://slack.k8s.io/)
 
-- Can be deployed on **[AWS](docs/aws.md), GCE, [Azure](docs/azure.md), [OpenStack](docs/openstack.md), [vSphere](docs/vsphere.md), [Packet](docs/packet.md) (bare metal), Oracle Cloud Infrastructure (Experimental), or Baremetal**
+- Can be deployed on **[AWS](docs/aws.md), GCE, [Azure](docs/azure.md), [OpenStack](docs/openstack.md), [vSphere](docs/vsphere.md), [Equinix Metal](docs/equinix-metal.md) (bare metal), Oracle Cloud Infrastructure (Experimental), or Baremetal**
 - **Highly available** cluster
 - **Composable** (Choice of the network plugin for instance)
 - Supports most popular **Linux distributions**
@@ -19,10 +19,10 @@ To deploy the cluster you can use :
 
 #### Usage
 
-```ShellSession
-# Install dependencies from ``requirements.txt``
-sudo pip3 install -r requirements.txt
+Install Ansible according to [Ansible installation guide](/docs/ansible.md#installing-ansible)
+then run the following steps:
 
+```ShellSession
 # Copy ``inventory/sample`` as ``inventory/mycluster``
 cp -rfp inventory/sample inventory/mycluster
 
@@ -32,7 +32,7 @@ CONFIG_FILE=inventory/mycluster/hosts.yaml python3 contrib/inventory_builder/inv
 
 # Review and change parameters under ``inventory/mycluster/group_vars``
 cat inventory/mycluster/group_vars/all/all.yml
-cat inventory/mycluster/group_vars/k8s_cluster/k8s_cluster.yml
+cat inventory/mycluster/group_vars/k8s_cluster/k8s-cluster.yml
 
 # Deploy Kubespray with Ansible Playbook - run the playbook as root
 # The option `--become` is required, as for example writing SSL keys in /etc/,
@@ -57,10 +57,11 @@ A simple way to ensure you get all the correct version of Ansible is to use the
 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:
 
 ```ShellSession
-docker pull quay.io/kubespray/kubespray:v2.15.1
+git checkout v2.20.0
+docker pull quay.io/kubespray/kubespray:v2.20.0
 docker run --rm -it --mount type=bind,source="$(pwd)"/inventory/sample,dst=/inventory \
   --mount type=bind,source="${HOME}"/.ssh/id_rsa,dst=/root/.ssh/id_rsa \
-  quay.io/kubespray/kubespray:v2.15.1 bash
+  quay.io/kubespray/kubespray:v2.20.0 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
 ```
@@ -75,10 +76,11 @@ python -V && pip -V
 ```
 
 If this returns the version of the software, you're good to go. If not, download and install Python from here <https://www.python.org/downloads/source/>
-Install the necessary requirements
+
+Install Ansible according to [Ansible installation guide](/docs/ansible.md#installing-ansible)
+then run the following step:
 
 ```ShellSession
-sudo pip install -r requirements.txt
 vagrant up
 ```
 
@@ -105,64 +107,82 @@ vagrant up
 - [AWS](docs/aws.md)
 - [Azure](docs/azure.md)
 - [vSphere](docs/vsphere.md)
-- [Packet Host](docs/packet.md)
+- [Equinix Metal](docs/equinix-metal.md)
 - [Large deployments](docs/large-deployments.md)
 - [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** Buster, Jessie, Stretch, Wheezy
-- **Ubuntu** 16.04, 18.04, 20.04
-- **CentOS/RHEL** 7, [8](docs/centos8.md)
-- **Fedora** 32, 33
-- **Fedora CoreOS** (experimental: see [fcos Note](docs/fcos.md))
+- **Debian** Bullseye, Buster, Jessie, Stretch
+- **Ubuntu** 16.04, 18.04, 20.04, 22.04
+- **CentOS/RHEL** 7, [8, 9](docs/centos.md#centos-8)
+- **Fedora** 35, 36
+- **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)
-- **Amazon Linux 2** (experimental: see [amazon linux notes](docs/amazonlinux.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) v1.20.7
-  - [etcd](https://github.com/coreos/etcd) v3.4.13
-  - [docker](https://www.docker.com/) v19.03 (see note)
-  - [containerd](https://containerd.io/) v1.4.4
-  - [cri-o](http://cri-o.io/) v1.20 (experimental: see [CRI-O Note](docs/cri-o.md). Only on fedora, ubuntu and centos based OS)
+  - [kubernetes](https://github.com/kubernetes/kubernetes) v1.25.5
+  - [etcd](https://github.com/etcd-io/etcd) v3.5.6
+  - [docker](https://www.docker.com/) v20.10 (see note)
+  - [containerd](https://containerd.io/) v1.6.14
+  - [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) v0.9.1
-  - [calico](https://github.com/projectcalico/calico) v3.17.4
+  - [cni-plugins](https://github.com/containernetworking/plugins) v1.1.1
+  - [calico](https://github.com/projectcalico/calico) v3.24.5
   - [canal](https://github.com/projectcalico/canal) (given calico/flannel versions)
-  - [cilium](https://github.com/cilium/cilium) v1.8.9
-  - [flanneld](https://github.com/coreos/flannel) v0.13.0
-  - [kube-ovn](https://github.com/alauda/kube-ovn) v1.6.2
-  - [kube-router](https://github.com/cloudnativelabs/kube-router) v1.2.2
-  - [multus](https://github.com/intel/multus-cni) v3.7.0
-  - [ovn4nfv](https://github.com/opnfv/ovn4nfv-k8s-plugin) v1.1.0
+  - [cilium](https://github.com/cilium/cilium) v1.12.1
+  - [flannel](https://github.com/flannel-io/flannel) v0.19.2
+  - [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/intel/multus-cni) v3.8
   - [weave](https://github.com/weaveworks/weave) v2.8.1
+  - [kube-vip](https://github.com/kube-vip/kube-vip) v0.5.5
 - Application
-  - [ambassador](https://github.com/datawire/ambassador): v1.5
+  - [cert-manager](https://github.com/jetstack/cert-manager) v1.10.1
+  - [coredns](https://github.com/coredns/coredns) v1.9.3
+  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v1.5.1
+  - [krew](https://github.com/kubernetes-sigs/krew) v0.4.3
+  - [argocd](https://argoproj.github.io/) v2.4.16
+  - [helm](https://helm.sh/) v3.9.4
+  - [metallb](https://metallb.universe.tf/)  v0.12.1
+  - [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) v0.16.1
-  - [coredns](https://github.com/coredns/coredns) v1.7.0
-  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v0.43.0
+  - [aws-ebs-csi-plugin](https://github.com/kubernetes-sigs/aws-ebs-csi-driver) v0.5.0
+  - [azure-csi-plugin](https://github.com/kubernetes-sigs/azuredisk-csi-driver) 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) v0.0.22
+  - [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 19.03. 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).
+- 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).
 - 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 v1.19**
-- **Ansible v2.9.x, Jinja 2.11+ and python-netaddr is installed on the machine that will run Ansible commands, Ansible 2.10.x is experimentally supported for now**
+- **Minimum required version of Kubernetes is v1.23**
+- **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**.
@@ -195,8 +215,6 @@ You can choose between 10 network plugins. (default: `calico`, except Vagrant us
 
 - [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.
 
-- [ovn4nfv](docs/ovn4nfv.md): [ovn4nfv-k8s-plugins](https://github.com/opnfv/ovn4nfv-k8s-plugin) is the network controller, OVS agent and CNI server to offer basic SFC and OVN overlay networking.
-
 - [weave](docs/weave.md): Weave is a lightweight container overlay network that doesn't require an external K/V database cluster.
     (Please refer to `weave` [troubleshooting documentation](https://www.weave.works/docs/net/latest/troubleshooting/)).
 
@@ -217,8 +235,6 @@ See also [Network checker](docs/netcheck.md).
 
 ## Ingress Plugins
 
-- [ambassador](docs/ambassador.md): the Ambassador Ingress Controller and API gateway.
-
 - [nginx](https://kubernetes.github.io/ingress-nginx): the NGINX Ingress Controller.
 
 - [metallb](docs/metallb.md): the MetalLB bare-metal service LoadBalancer provider.
@@ -234,11 +250,12 @@ 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)
 
-CI/end-to-end tests sponsored by: [CNCF](https://cncf.io), [Packet](https://www.packet.com/), [OVHcloud](https://www.ovhcloud.com/), [ELASTX](https://elastx.se/).
+CI/end-to-end tests sponsored by: [CNCF](https://cncf.io), [Equinix Metal](https://metal.equinix.com/), [OVHcloud](https://www.ovhcloud.com/), [ELASTX](https://elastx.se/).
 
 See the [test matrix](docs/test_cases.md) for details.

RELEASE.md

@@ -2,17 +2,18 @@
 
 The Kubespray Project is released on an as-needed basis. The process is as follows:
 
-1. An issue is proposing a new release with a changelog since the last release
+1. An issue is proposing a new release with a changelog since the last release. Please see [a good sample issue](https://github.com/kubernetes-sigs/kubespray/issues/8325)
 2. At least one of the [approvers](OWNERS_ALIASES) must approve this release
 3. The `kube_version_min_required` variable is set to `n-1`
-4. Remove hashes for [EOL versions](https://github.com/kubernetes/sig-release/blob/master/releases/patch-releases.md) of kubernetes from `*_checksums` variables.
-5. An approver creates [new release in GitHub](https://github.com/kubernetes-sigs/kubespray/releases/new) using a version and tag name like `vX.Y.Z` and attaching the release notes
-6. An approver creates a release branch in the form `release-X.Y`
-7. 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 `KUBESPRAY_VERSION` variable is updated in `.gitlab-ci.yml`
-9. The release issue is closed
-10. An announcement email is sent to `kubernetes-dev@googlegroups.com` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
-11. The topic of the #kubespray channel is updated with `vX.Y.Z is released! | ...`
+4. Remove hashes for [EOL versions](https://github.com/kubernetes/website/blob/main/content/en/releases/patch-releases.md) of kubernetes from `*_checksums` variables.
+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) 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 `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
 
@@ -46,3 +47,37 @@ The Kubespray Project is released on an as-needed basis. The process is as follo
   then Kubespray v2.1.0 may be bound to only minor changes to `kube_version`, like v1.5.1
   and *any* changes to other components, like etcd v4, or calico 1.2.3.
   And Kubespray v3.x.x shall be bound to `kube_version: 2.x.x` respectively.
+
+## Release note creation
+
+You can create a release note with:
+
+```shell
+export GITHUB_TOKEN=<your-github-token>
+export ORG=kubernetes-sigs
+export REPO=kubespray
+release-notes --start-sha <The start commit-id> --end-sha <The end commit-id> --dependencies=false --output=/tmp/kubespray-release-note --required-author=""
+```
+
+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)
+
+## 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

@@ -26,9 +26,12 @@ SUPPORTED_OS = {
   "centos-bento"        => {box: "bento/centos-7.6",           user: "vagrant"},
   "centos8"             => {box: "centos/8",                   user: "vagrant"},
   "centos8-bento"       => {box: "bento/centos-8",             user: "vagrant"},
-  "fedora32"            => {box: "fedora/32-cloud-base",       user: "vagrant"},
-  "fedora33"            => {box: "fedora/33-cloud-base",       user: "vagrant"},
-  "opensuse"            => {box: "bento/opensuse-leap-15.2",   user: "vagrant"},
+  "almalinux8"          => {box: "almalinux/8",                user: "vagrant"},
+  "almalinux8-bento"    => {box: "bento/almalinux-8",          user: "vagrant"},
+  "rockylinux8"         => {box: "generic/rocky8",             user: "vagrant"},
+  "fedora35"            => {box: "fedora/35-cloud-base",       user: "vagrant"},
+  "fedora36"            => {box: "fedora/36-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"},
@@ -53,9 +56,9 @@ $subnet_ipv6 ||= "fd3c:b398:0698:0756"
 $os ||= "ubuntu1804"
 $network_plugin ||= "flannel"
 # Setting multi_networking to true will install Multus: https://github.com/intel/multus-cni
-$multi_networking ||= false
+$multi_networking ||= "False"
 $download_run_once ||= "True"
-$download_force_cache ||= "True"
+$download_force_cache ||= "False"
 # The first three nodes are etcd servers
 $etcd_instances ||= $num_instances
 # The first two nodes are kube masters
@@ -68,9 +71,12 @@ $kube_node_instances_with_disks_size ||= "20G"
 $kube_node_instances_with_disks_number ||= 2
 $override_disk_size ||= false
 $disk_size ||= "20GB"
-$local_path_provisioner_enabled ||= false
+$local_path_provisioner_enabled ||= "False"
 $local_path_provisioner_claim_root ||= "/opt/local-path-provisioner/"
 $libvirt_nested ||= false
+# boolean or string (e.g. "-vvv")
+$ansible_verbosity ||= false
+$ansible_tags ||= ENV['VAGRANT_ANSIBLE_TAGS'] || ""
 
 $playbook ||= "cluster.yml"
 
@@ -167,7 +173,7 @@ Vagrant.configure("2") do |config|
           # always make /dev/sd{a/b/c} so that CI can ensure that
           # virtualbox and libvirt will have the same devices to use for OSDs
           (1..$kube_node_instances_with_disks_number).each do |d|
-            lv.storage :file, :device => "hd#{driverletters[d]}", :path => "disk-#{i}-#{d}-#{DISK_UUID}.disk", :size => $kube_node_instances_with_disks_size, :bus => "ide"
+            lv.storage :file, :device => "hd#{driverletters[d]}", :path => "disk-#{i}-#{d}-#{DISK_UUID}.disk", :size => $kube_node_instances_with_disks_size, :bus => "scsi"
           end
         end
       end
@@ -238,9 +244,11 @@ Vagrant.configure("2") do |config|
       }
 
       # Only execute the Ansible provisioner once, when all the machines are up and ready.
+      # And limit the action to gathering facts, the full playbook is going to be ran by testcases_run.sh
       if i == $num_instances
         node.vm.provision "ansible" do |ansible|
           ansible.playbook = $playbook
+          ansible.verbose = $ansible_verbosity
           $ansible_inventory_path = File.join( $inventory, "hosts.ini")
           if File.exist?($ansible_inventory_path)
             ansible.inventory_path = $ansible_inventory_path
@@ -250,7 +258,9 @@ Vagrant.configure("2") do |config|
           ansible.host_key_checking = false
           ansible.raw_arguments = ["--forks=#{$num_instances}", "--flush-cache", "-e ansible_become_pass=vagrant"]
           ansible.host_vars = host_vars
-          #ansible.tags = ['download']
+          if $ansible_tags != ""
+            ansible.tags = [$ansible_tags]
+          end
           ansible.groups = {
             "etcd" => ["#{$instance_name_prefix}-[1:#{$etcd_instances}]"],
             "kube_control_plane" => ["#{$instance_name_prefix}-[1:#{$kube_master_instances}]"],

ansible.cfg

@@ -1,9 +1,8 @@
 [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]
-strategy_plugins = plugins/mitogen/ansible_mitogen/plugins/strategy
 # https://github.com/ansible/ansible/issues/56930 (to ignore group names with - and .)
 force_valid_group_names = ignore
 
@@ -11,11 +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
+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

ansible_version.yml

@@ -3,13 +3,14 @@
   gather_facts: false
   become: no
   vars:
-    minimal_ansible_version: 2.9.0
-    maximal_ansible_version: 2.11.0
+    minimal_ansible_version: 2.11.0
+    maximal_ansible_version: 2.14.0
     ansible_connection: local
+  tags: always
   tasks:
     - name: "Check {{ minimal_ansible_version }} <= Ansible version < {{ maximal_ansible_version }}"
       assert:
-        msg: "Ansible must be between {{ minimal_ansible_version }} and {{ maximal_ansible_version }}"
+        msg: "Ansible must be between {{ minimal_ansible_version }} and {{ maximal_ansible_version }} exclusive"
         that:
           - ansible_version.string is version(minimal_ansible_version, ">=")
           - ansible_version.string is version(maximal_ansible_version, "<")

cluster.yml

@@ -32,10 +32,10 @@
   roles:
     - { role: kubespray-defaults }
     - { role: kubernetes/preinstall, tags: preinstall }
-    - { role: "container-engine", tags: "container-engine", when: deploy_container_engine|default(true) }
+    - { role: "container-engine", tags: "container-engine", when: deploy_container_engine }
     - { role: download, tags: download, when: "not skip_downloads" }
 
-- hosts: etcd
+- hosts: etcd:kube_control_plane
   gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
   environment: "{{ proxy_disable_env }}"
@@ -46,7 +46,7 @@
       vars:
         etcd_cluster_setup: true
         etcd_events_cluster_setup: "{{ etcd_events_cluster_enabled }}"
-      when: not etcd_kubeadm_enabled| default(false)
+      when: etcd_deployment_type != "kubeadm"
 
 - hosts: k8s_cluster
   gather_facts: False
@@ -59,7 +59,10 @@
       vars:
         etcd_cluster_setup: false
         etcd_events_cluster_setup: false
-      when: not etcd_kubeadm_enabled| default(false)
+      when:
+        - etcd_deployment_type != "kubeadm"
+        - kube_network_plugin in ["calico", "flannel", "canal", "cilium"] or cilium_deploy_additionally | default(false) | bool
+        - kube_network_plugin != "calico" or calico_datastore == "etcd"
 
 - hosts: k8s_cluster
   gather_facts: False
@@ -86,8 +89,8 @@
   roles:
     - { role: kubespray-defaults }
     - { role: kubernetes/kubeadm, tags: kubeadm}
-    - { role: network_plugin, tags: network }
     - { role: kubernetes/node-label, tags: node-label }
+    - { role: network_plugin, tags: network }
 
 - hosts: calico_rr
   gather_facts: False
@@ -116,16 +119,10 @@
     - { role: kubernetes-apps/policy_controller, tags: policy-controller }
     - { role: kubernetes-apps/ingress_controller, tags: ingress-controller }
     - { role: kubernetes-apps/external_provisioner, tags: external-provisioner }
-
-- 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, tags: apps }
 
-- hosts: k8s_cluster
+- 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 }}"

contrib/aws_inventory/kubespray-aws-inventory.py

@@ -69,7 +69,7 @@ class SearchEC2Tags(object):
 
         hosts[group].append(dns_name)
         hosts['_meta']['hostvars'][dns_name] = ansible_host
-        
+
     hosts['k8s_cluster'] = {'children':['kube_control_plane', 'kube_node']}
     print(json.dumps(hosts, sort_keys=True, indent=2))
 

contrib/azurerm/README.md

@@ -47,6 +47,10 @@ If you need to delete all resources from a resource group, simply call:
 
 **WARNING** this really deletes everything from your resource group, including everything that was later created by you!
 
+## Installing Ansible and the dependencies
+
+Install Ansible according to [Ansible installation guide](/docs/ansible.md#installing-ansible)
+
 ## Generating an inventory for kubespray
 
 After you have applied the templates, you can generate an inventory with this call:
@@ -59,6 +63,5 @@ It will create the file ./inventory which can then be used with kubespray, e.g.:
 
 ```shell
 cd kubespray-root-dir
-sudo pip3 install -r requirements.txt
 ansible-playbook -i contrib/azurerm/inventory -u devops --become -e "@inventory/sample/group_vars/all/all.yml" cluster.yml
 ```

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

@@ -12,3 +12,4 @@
   template:
     src: inventory.j2
     dest: "{{ playbook_dir }}/inventory"
+    mode: 0644

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

@@ -22,8 +22,10 @@
   template:
     src: inventory.j2
     dest: "{{ playbook_dir }}/inventory"
+    mode: 0644
 
 - name: Generate Load Balancer variables
   template:
     src: loadbalancer_vars.j2
     dest: "{{ playbook_dir }}/loadbalancer_vars.yml"
+    mode: 0644

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

@@ -8,11 +8,13 @@
     path: "{{ base_dir }}"
     state: directory
     recurse: true
+    mode: 0755
 
 - name: Store json files in base_dir
   template:
     src: "{{ item }}"
     dest: "{{ base_dir }}/{{ item }}"
+    mode: 0644
   with_items:
     - network.json
     - storage.json

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

@@ -35,6 +35,7 @@
       path-exclude=/usr/share/doc/*
       path-include=/usr/share/doc/*/copyright
     dest: /etc/dpkg/dpkg.cfg.d/01_nodoc
+    mode: 0644
   when:
     - ansible_os_family == 'Debian'
 
@@ -63,6 +64,7 @@
   copy:
     content: "{{ distro_user }} ALL=(ALL) NOPASSWD:ALL"
     dest: "/etc/sudoers.d/{{ distro_user }}"
+    mode: 0640
 
 - name: Add my pubkey to "{{ distro_user }}" user authorized keys
   authorized_key:

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/inventory.py

@@ -48,7 +48,7 @@ ROLES = ['all', 'kube_control_plane', 'kube_node', 'etcd', 'k8s_cluster',
          'calico_rr']
 PROTECTED_NAMES = ROLES
 AVAILABLE_COMMANDS = ['help', 'print_cfg', 'print_ips', 'print_hostnames',
-                      'load']
+                      'load', 'add']
 _boolean_states = {'1': True, 'yes': True, 'true': True, 'on': True,
                    '0': False, 'no': False, 'false': False, 'off': False}
 yaml = YAML()
@@ -82,22 +82,43 @@ class KubesprayInventory(object):
     def __init__(self, changed_hosts=None, config_file=None):
         self.config_file = config_file
         self.yaml_config = {}
-        if self.config_file:
+        loadPreviousConfig = False
+        printHostnames = False
+        # See whether there are any commands to process
+        if changed_hosts and changed_hosts[0] in AVAILABLE_COMMANDS:
+            if changed_hosts[0] == "add":
+                loadPreviousConfig = True
+                changed_hosts = changed_hosts[1:]
+            elif changed_hosts[0] == "print_hostnames":
+                loadPreviousConfig = True
+                printHostnames = True
+            else:
+                self.parse_command(changed_hosts[0], changed_hosts[1:])
+                sys.exit(0)
+
+        # If the user wants to remove a node, we need to load the config anyway
+        if changed_hosts and changed_hosts[0][0] == "-":
+            loadPreviousConfig = True
+
+        if self.config_file and loadPreviousConfig:  # Load previous YAML file
             try:
                 self.hosts_file = open(config_file, 'r')
-                self.yaml_config = yaml.load_all(self.hosts_file)
-            except OSError:
-                pass
+                self.yaml_config = yaml.load(self.hosts_file)
+            except OSError as e:
+                # I am assuming we are catching "cannot open file" exceptions
+                print(e)
+                sys.exit(1)
 
-        if changed_hosts and changed_hosts[0] in AVAILABLE_COMMANDS:
-            self.parse_command(changed_hosts[0], changed_hosts[1:])
+        if printHostnames:
+            self.print_hostnames()
             sys.exit(0)
 
         self.ensure_required_groups(ROLES)
 
         if changed_hosts:
             changed_hosts = self.range2ips(changed_hosts)
-            self.hosts = self.build_hostnames(changed_hosts)
+            self.hosts = self.build_hostnames(changed_hosts,
+                                              loadPreviousConfig)
             self.purge_invalid_hosts(self.hosts.keys(), PROTECTED_NAMES)
             self.set_all(self.hosts)
             self.set_k8s_cluster()
@@ -158,17 +179,29 @@ class KubesprayInventory(object):
         except IndexError:
             raise ValueError("Host name must end in an integer")
 
-    def build_hostnames(self, changed_hosts):
+    # Keeps already specified hosts,
+    # and adds or removes the hosts provided as an argument
+    def build_hostnames(self, changed_hosts, loadPreviousConfig=False):
         existing_hosts = OrderedDict()
         highest_host_id = 0
-        try:
-            for host in self.yaml_config['all']['hosts']:
-                existing_hosts[host] = self.yaml_config['all']['hosts'][host]
-                host_id = self.get_host_id(host)
-                if host_id > highest_host_id:
-                    highest_host_id = host_id
-        except Exception:
-            pass
+        # Load already existing hosts from the YAML
+        if loadPreviousConfig:
+            try:
+                for host in self.yaml_config['all']['hosts']:
+                    # Read configuration of an existing host
+                    hostConfig = self.yaml_config['all']['hosts'][host]
+                    existing_hosts[host] = hostConfig
+                    # If the existing host seems
+                    # to have been created automatically, detect its ID
+                    if host.startswith(HOST_PREFIX):
+                        host_id = self.get_host_id(host)
+                        if host_id > highest_host_id:
+                            highest_host_id = host_id
+            except Exception as e:
+                # I am assuming we are catching automatically
+                # created hosts without IDs
+                print(e)
+                sys.exit(1)
 
         # FIXME(mattymo): Fix condition where delete then add reuses highest id
         next_host_id = highest_host_id + 1
@@ -176,6 +209,7 @@ class KubesprayInventory(object):
 
         all_hosts = existing_hosts.copy()
         for host in changed_hosts:
+            # Delete the host from config the hostname/IP has a "-" prefix
             if host[0] == "-":
                 realhost = host[1:]
                 if self.exists_hostname(all_hosts, realhost):
@@ -184,6 +218,8 @@ class KubesprayInventory(object):
                 elif self.exists_ip(all_hosts, realhost):
                     self.debug("Marked {0} for deletion.".format(realhost))
                     self.delete_host_by_ip(all_hosts, realhost)
+            # Host/Argument starts with a digit,
+            # then we assume its an IP address
             elif host[0].isdigit():
                 if ',' in host:
                     ip, access_ip = host.split(',')
@@ -203,11 +239,15 @@ class KubesprayInventory(object):
                     next_host = subprocess.check_output(cmd, shell=True)
                     next_host = next_host.strip().decode('ascii')
                 else:
+                    # Generates a hostname because we have only an IP address
                     next_host = "{0}{1}".format(HOST_PREFIX, next_host_id)
                     next_host_id += 1
+                # Uses automatically generated node name
+                # in case we dont provide it.
                 all_hosts[next_host] = {'ansible_host': access_ip,
                                         'ip': ip,
                                         'access_ip': access_ip}
+            # Host/Argument starts with a letter, then we assume its a hostname
             elif host[0].isalpha():
                 if ',' in host:
                     try:
@@ -226,6 +266,7 @@ class KubesprayInventory(object):
                                        'access_ip': access_ip}
         return all_hosts
 
+    # Expand IP ranges into individual addresses
     def range2ips(self, hosts):
         reworked_hosts = []
 
@@ -394,9 +435,11 @@ help - Display this message
 print_cfg - Write inventory file to stdout
 print_ips - Write a space-delimited list of IPs from "all" group
 print_hostnames - Write a space-delimited list of Hostnames from "all" group
+add - Adds specified hosts into an already existing inventory
 
 Advanced usage:
-Add another host after initial creation: inventory.py 10.10.1.5
+Create new or overwrite old inventory file: inventory.py 10.10.1.5
+Add another host after initial creation: inventory.py add 10.10.1.6
 Add range of hosts: inventory.py 10.10.1.3-10.10.1.5
 Add hosts with different ip and access ip: inventory.py 10.0.0.1,192.168.10.1 10.0.0.2,192.168.10.2 10.0.0.3,192.168.10.3
 Add hosts with a specific hostname, ip, and optional access ip: first,10.0.0.1,192.168.10.1 second,10.0.0.2 last,10.0.0.3
@@ -430,6 +473,7 @@ def main(argv=None):
     if not argv:
         argv = sys.argv[1:]
     KubesprayInventory(argv, CONFIG_FILE)
+    return 0
 
 
 if __name__ == "__main__":

contrib/inventory_builder/tests/test_inventory.py

@@ -13,6 +13,7 @@
 # under the License.
 
 import inventory
+from io import StringIO
 import unittest
 from unittest import mock
 
@@ -26,6 +27,28 @@ if path not in sys.path:
 import inventory  # noqa
 
 
+class TestInventoryPrintHostnames(unittest.TestCase):
+
+    @mock.patch('ruamel.yaml.YAML.load')
+    def test_print_hostnames(self, load_mock):
+        mock_io = mock.mock_open(read_data='')
+        load_mock.return_value = OrderedDict({'all': {'hosts': {
+            'node1': {'ansible_host': '10.90.0.2',
+                      'ip': '10.90.0.2',
+                      'access_ip': '10.90.0.2'},
+            'node2': {'ansible_host': '10.90.0.3',
+                      'ip': '10.90.0.3',
+                      'access_ip': '10.90.0.3'}}}})
+        with mock.patch('builtins.open', mock_io):
+            with self.assertRaises(SystemExit) as cm:
+                with mock.patch('sys.stdout', new_callable=StringIO) as stdout:
+                    inventory.KubesprayInventory(
+                        changed_hosts=["print_hostnames"],
+                        config_file="file")
+            self.assertEqual("node1 node2\n", stdout.getvalue())
+            self.assertEqual(cm.exception.code, 0)
+
+
 class TestInventory(unittest.TestCase):
     @mock.patch('inventory.sys')
     def setUp(self, sys_mock):
@@ -67,23 +90,14 @@ class TestInventory(unittest.TestCase):
             self.assertRaisesRegex(ValueError, "Host name must end in an",
                                    self.inv.get_host_id, hostname)
 
-    def test_build_hostnames_add_one(self):
-        changed_hosts = ['10.90.0.2']
-        expected = OrderedDict([('node1',
-                                 {'ansible_host': '10.90.0.2',
-                                  'ip': '10.90.0.2',
-                                  'access_ip': '10.90.0.2'})])
-        result = self.inv.build_hostnames(changed_hosts)
-        self.assertEqual(expected, result)
-
     def test_build_hostnames_add_duplicate(self):
         changed_hosts = ['10.90.0.2']
-        expected = OrderedDict([('node1',
+        expected = OrderedDict([('node3',
                                  {'ansible_host': '10.90.0.2',
                                   'ip': '10.90.0.2',
                                   'access_ip': '10.90.0.2'})])
         self.inv.yaml_config['all']['hosts'] = expected
-        result = self.inv.build_hostnames(changed_hosts)
+        result = self.inv.build_hostnames(changed_hosts, True)
         self.assertEqual(expected, result)
 
     def test_build_hostnames_add_two(self):
@@ -99,6 +113,30 @@ class TestInventory(unittest.TestCase):
         result = self.inv.build_hostnames(changed_hosts)
         self.assertEqual(expected, result)
 
+    def test_build_hostnames_add_three(self):
+        changed_hosts = ['10.90.0.2', '10.90.0.3', '10.90.0.4']
+        expected = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'}),
+            ('node3', {'ansible_host': '10.90.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '10.90.0.4'})])
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_one(self):
+        changed_hosts = ['10.90.0.2']
+        expected = OrderedDict([('node1',
+                                 {'ansible_host': '10.90.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '10.90.0.2'})])
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
     def test_build_hostnames_delete_first(self):
         changed_hosts = ['-10.90.0.2']
         existing_hosts = OrderedDict([
@@ -113,7 +151,24 @@ class TestInventory(unittest.TestCase):
             ('node2', {'ansible_host': '10.90.0.3',
                        'ip': '10.90.0.3',
                        'access_ip': '10.90.0.3'})])
-        result = self.inv.build_hostnames(changed_hosts)
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_delete_by_hostname(self):
+        changed_hosts = ['-node1']
+        existing_hosts = OrderedDict([
+            ('node1', {'ansible_host': '10.90.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '10.90.0.2'}),
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        self.inv.yaml_config['all']['hosts'] = existing_hosts
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '10.90.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '10.90.0.3'})])
+        result = self.inv.build_hostnames(changed_hosts, True)
         self.assertEqual(expected, result)
 
     def test_exists_hostname_positive(self):
@@ -313,7 +368,7 @@ class TestInventory(unittest.TestCase):
         self.assertRaisesRegex(Exception, "Range of ip_addresses isn't valid",
                                self.inv.range2ips, host_range)
 
-    def test_build_hostnames_different_ips_add_one(self):
+    def test_build_hostnames_create_with_one_different_ips(self):
         changed_hosts = ['10.90.0.2,192.168.0.2']
         expected = OrderedDict([('node1',
                                  {'ansible_host': '192.168.0.2',
@@ -322,17 +377,7 @@ class TestInventory(unittest.TestCase):
         result = self.inv.build_hostnames(changed_hosts)
         self.assertEqual(expected, result)
 
-    def test_build_hostnames_different_ips_add_duplicate(self):
-        changed_hosts = ['10.90.0.2,192.168.0.2']
-        expected = OrderedDict([('node1',
-                                 {'ansible_host': '192.168.0.2',
-                                  'ip': '10.90.0.2',
-                                  'access_ip': '192.168.0.2'})])
-        self.inv.yaml_config['all']['hosts'] = expected
-        result = self.inv.build_hostnames(changed_hosts)
-        self.assertEqual(expected, result)
-
-    def test_build_hostnames_different_ips_add_two(self):
+    def test_build_hostnames_create_with_two_different_ips(self):
         changed_hosts = ['10.90.0.2,192.168.0.2', '10.90.0.3,192.168.0.3']
         expected = OrderedDict([
             ('node1', {'ansible_host': '192.168.0.2',
@@ -341,6 +386,210 @@ class TestInventory(unittest.TestCase):
             ('node2', {'ansible_host': '192.168.0.3',
                        'ip': '10.90.0.3',
                        'access_ip': '192.168.0.3'})])
-        self.inv.yaml_config['all']['hosts'] = OrderedDict()
         result = self.inv.build_hostnames(changed_hosts)
         self.assertEqual(expected, result)
+
+    def test_build_hostnames_create_with_three_different_ips(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2',
+                         '10.90.0.3,192.168.0.3',
+                         '10.90.0.4,192.168.0.4']
+        expected = OrderedDict([
+            ('node1', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node2', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node3', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_overwrite_one_with_different_ips(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2']
+        expected = OrderedDict([('node1',
+                                 {'ansible_host': '192.168.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '192.168.0.2'})])
+        existing = OrderedDict([('node5',
+                                 {'ansible_host': '192.168.0.5',
+                                  'ip': '10.90.0.5',
+                                  'access_ip': '192.168.0.5'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_overwrite_three_with_different_ips(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2']
+        expected = OrderedDict([('node1',
+                                 {'ansible_host': '192.168.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '192.168.0.2'})])
+        existing = OrderedDict([
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'}),
+            ('node5', {'ansible_host': '192.168.0.5',
+                       'ip': '10.90.0.5',
+                       'access_ip': '192.168.0.5'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_different_ips_add_duplicate(self):
+        changed_hosts = ['10.90.0.2,192.168.0.2']
+        expected = OrderedDict([('node3',
+                                 {'ansible_host': '192.168.0.2',
+                                  'ip': '10.90.0.2',
+                                  'access_ip': '192.168.0.2'})])
+        existing = expected
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_two_different_ips_into_one_existing(self):
+        changed_hosts = ['10.90.0.3,192.168.0.3', '10.90.0.4,192.168.0.4']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_two_different_ips_into_two_existing(self):
+        changed_hosts = ['10.90.0.4,192.168.0.4', '10.90.0.5,192.168.0.5']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'}),
+            ('node5', {'ansible_host': '192.168.0.5',
+                       'ip': '10.90.0.5',
+                       'access_ip': '192.168.0.5'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    def test_build_hostnames_add_two_different_ips_into_three_existing(self):
+        changed_hosts = ['10.90.0.5,192.168.0.5', '10.90.0.6,192.168.0.6']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'}),
+            ('node5', {'ansible_host': '192.168.0.5',
+                       'ip': '10.90.0.5',
+                       'access_ip': '192.168.0.5'}),
+            ('node6', {'ansible_host': '192.168.0.6',
+                       'ip': '10.90.0.6',
+                       'access_ip': '192.168.0.6'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    # Add two IP addresses into a config that has
+    # three already defined IP addresses. One of the IP addresses
+    # is a duplicate.
+    def test_build_hostnames_add_two_duplicate_one_overlap(self):
+        changed_hosts = ['10.90.0.4,192.168.0.4', '10.90.0.5,192.168.0.5']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'}),
+            ('node5', {'ansible_host': '192.168.0.5',
+                       'ip': '10.90.0.5',
+                       'access_ip': '192.168.0.5'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)
+
+    # Add two duplicate IP addresses into a config that has
+    # three already defined IP addresses
+    def test_build_hostnames_add_two_duplicate_two_overlap(self):
+        changed_hosts = ['10.90.0.3,192.168.0.3', '10.90.0.4,192.168.0.4']
+        expected = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+
+        existing = OrderedDict([
+            ('node2', {'ansible_host': '192.168.0.2',
+                       'ip': '10.90.0.2',
+                       'access_ip': '192.168.0.2'}),
+            ('node3', {'ansible_host': '192.168.0.3',
+                       'ip': '10.90.0.3',
+                       'access_ip': '192.168.0.3'}),
+            ('node4', {'ansible_host': '192.168.0.4',
+                       'ip': '10.90.0.4',
+                       'access_ip': '192.168.0.4'})])
+        self.inv.yaml_config['all']['hosts'] = existing
+        result = self.inv.build_hostnames(changed_hosts, True)
+        self.assertEqual(expected, result)

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

@@ -1,7 +1,7 @@
 ---
 
 - name: Install required packages
-  yum:
+  package:
     name: "{{ item }}"
     state: present
   with_items:

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

@@ -28,7 +28,7 @@
   sysctl:
     name: net.ipv4.ip_forward
     value: 1
-    sysctl_file: /etc/sysctl.d/ipv4-ip_forward.conf
+    sysctl_file: "{{ sysctl_file_path }}"
     state: present
     reload: yes
 
@@ -37,7 +37,7 @@
     name: "{{ item }}"
     state: present
     value: 0
-    sysctl_file: /etc/sysctl.d/bridge-nf-call.conf
+    sysctl_file: "{{ sysctl_file_path }}"
     reload: yes
   with_items:
     - net.bridge.bridge-nf-call-arptables

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

@@ -11,6 +11,7 @@
     state: directory
     owner: "{{ k8s_deployment_user }}"
     group: "{{ k8s_deployment_user }}"
+    mode: 0700
 
 - name: Configure sudo for deployment user
   copy:

contrib/mitogen/mitogen.yml

@@ -5,14 +5,15 @@
 - hosts: localhost
   strategy: linear
   vars:
-    mitogen_version: 0.2.9
-    mitogen_url: https://github.com/dw/mitogen/archive/v{{ mitogen_version }}.tar.gz
+    mitogen_version: 0.3.2
+    mitogen_url: https://github.com/mitogen-hq/mitogen/archive/refs/tags/v{{ mitogen_version }}.tar.gz
     ansible_connection: local
   tasks:
     - name: Create mitogen plugin dir
       file:
         path: "{{ item }}"
         state: directory
+        mode: 0755
       become: false
       loop:
         - "{{ playbook_dir }}/plugins/mitogen"
@@ -37,6 +38,12 @@
     - name: add strategy to ansible.cfg
       ini_file:
         path: ansible.cfg
-        section: defaults
-        option: strategy
-        value: mitogen_linear
+        mode: 0644
+        section: "{{ item.section | d('defaults') }}"
+        option: "{{ item.option }}"
+        value: "{{ item.value }}"
+      with_items:
+        - option: strategy
+          value: mitogen_linear
+        - option: strategy_plugins
+          value: plugins/mitogen/ansible_mitogen/plugins/strategy

contrib/network-storage/glusterfs/inventory.example

@@ -11,8 +11,8 @@
 # ## Set disk_volume_device_1 to desired device for gluster brick, if different to /dev/vdb (default).
 # ## As in the previous case, you can set ip to give direct communication on internal IPs
 # gfs_node1 ansible_ssh_host=95.54.0.18 # disk_volume_device_1=/dev/vdc  ip=10.3.0.7
-# gfs_node2 ansible_ssh_host=95.54.0.19 # disk_volume_device_1=/dev/vdc  ip=10.3.0.8 
-# gfs_node3 ansible_ssh_host=95.54.0.20 # disk_volume_device_1=/dev/vdc  ip=10.3.0.9 
+# gfs_node2 ansible_ssh_host=95.54.0.19 # disk_volume_device_1=/dev/vdc  ip=10.3.0.8
+# gfs_node3 ansible_ssh_host=95.54.0.20 # disk_volume_device_1=/dev/vdc  ip=10.3.0.9
 
 # [kube_control_plane]
 # node1

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/glusterfs/client/tasks/setup-RedHat.yml

@@ -1,10 +1,10 @@
 ---
 - name: Install Prerequisites
-  yum: name={{ item }}  state=present
+  package: name={{ item }}  state=present
   with_items:
     - "centos-release-gluster{{ glusterfs_default_release }}"
 
 - name: Install Packages
-  yum: name={{ item }}  state=present
+  package: name={{ item }}  state=present
   with_items:
     - glusterfs-client

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

@@ -9,7 +9,7 @@
   when: ansible_os_family == "Debian"
 
 - name: install xfs RedHat
-  yum: name=xfsprogs state=present
+  package: name=xfsprogs state=present
   when: ansible_os_family == "RedHat"
 
 # Format external volumes in xfs
@@ -82,6 +82,7 @@
   template:
     dest: "{{ gluster_mount_dir }}/.test-file.txt"
     src: test-file.txt
+    mode: 0644
   when: groups['gfs-cluster'] is defined and inventory_hostname == groups['gfs-cluster'][0]
 
 - name: Unmount glusterfs

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

@@ -1,11 +1,11 @@
 ---
 - name: Install Prerequisites
-  yum: name={{ item }}  state=present
+  package: name={{ item }}  state=present
   with_items:
     - "centos-release-gluster{{ glusterfs_default_release }}"
 
 - name: Install Packages
-  yum: name={{ item }}  state=present
+  package: name={{ item }}  state=present
   with_items:
     - glusterfs-server
     - glusterfs-client

contrib/network-storage/glusterfs/roles/glusterfs/server/tests/test.yml

@@ -1,5 +0,0 @@
----
-- hosts: all
-
-  roles:
-    - role_under_test

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

@@ -3,6 +3,7 @@
   template:
     src: "{{ item.file }}"
     dest: "{{ kube_config_dir }}/{{ item.dest }}"
+    mode: 0644
   with_items:
     - { file: glusterfs-kubernetes-endpoint.json.j2, type: ep, dest: glusterfs-kubernetes-endpoint.json}
     - { file: glusterfs-kubernetes-pv.yml.j2, type: pv, dest: glusterfs-kubernetes-pv.yml}

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

@@ -2,6 +2,13 @@ all:
     vars:
         heketi_admin_key: "11elfeinhundertundelf"
         heketi_user_key: "!!einseinseins"
+        glusterfs_daemonset:
+            readiness_probe:
+                timeout_seconds: 3
+                initial_delay_seconds: 3
+            liveness_probe:
+                timeout_seconds: 3
+                initial_delay_seconds: 10
     children:
         k8s_cluster:
             vars:

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

@@ -11,7 +11,7 @@
 
 - name: "Install glusterfs mount utils (RedHat)"
   become: true
-  yum:
+  package:
     name: "glusterfs-fuse"
     state: "present"
   when: "ansible_os_family == 'RedHat'"

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

@@ -1,7 +1,10 @@
 ---
 - name: "Kubernetes Apps | Lay Down Heketi Bootstrap"
   become: true
-  template: { src: "heketi-bootstrap.json.j2", dest: "{{ kube_config_dir }}/heketi-bootstrap.json" }
+  template:
+    src: "heketi-bootstrap.json.j2"
+    dest: "{{ kube_config_dir }}/heketi-bootstrap.json"
+    mode: 0640
   register: "rendering"
 - name: "Kubernetes Apps | Install and configure Heketi Bootstrap"
   kube:

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

@@ -10,6 +10,7 @@
   template:
     src: "topology.json.j2"
     dest: "{{ kube_config_dir }}/topology.json"
+    mode: 0644
 - name: "Copy topology configuration into container."
   changed_when: false
   command: "{{ bin_dir }}/kubectl cp {{ kube_config_dir }}/topology.json {{ initial_heketi_pod_name }}:/tmp/topology.json"

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

@@ -1,6 +1,9 @@
 ---
 - name: "Kubernetes Apps | Lay Down GlusterFS Daemonset"
-  template: { src: "glusterfs-daemonset.json.j2", dest: "{{ kube_config_dir }}/glusterfs-daemonset.json" }
+  template:
+    src: "glusterfs-daemonset.json.j2"
+    dest: "{{ kube_config_dir }}/glusterfs-daemonset.json"
+    mode: 0644
   become: true
   register: "rendering"
 - name: "Kubernetes Apps | Install and configure GlusterFS daemonset"
@@ -27,7 +30,10 @@
   delay: 5
 
 - name: "Kubernetes Apps | Lay Down Heketi Service Account"
-  template: { src: "heketi-service-account.json.j2", dest: "{{ kube_config_dir }}/heketi-service-account.json" }
+  template:
+    src: "heketi-service-account.json.j2"
+    dest: "{{ kube_config_dir }}/heketi-service-account.json"
+    mode: 0644
   become: true
   register: "rendering"
 - name: "Kubernetes Apps | Install and configure Heketi Service Account"

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

@@ -4,6 +4,7 @@
   template:
     src: "heketi-deployment.json.j2"
     dest: "{{ kube_config_dir }}/heketi-deployment.json"
+    mode: 0644
   register: "rendering"
 
 - name: "Kubernetes Apps | Install and configure Heketi"

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

@@ -5,7 +5,7 @@
   changed_when: false
 
 - name: "Kubernetes Apps | Deploy cluster role binding."
-  when: "clusterrolebinding_state.stdout == \"\""
+  when: "clusterrolebinding_state.stdout | length == 0"
   command: "{{ bin_dir }}/kubectl create clusterrolebinding heketi-gluster-admin --clusterrole=edit --serviceaccount=default:heketi-service-account"
 
 - name: Get clusterrolebindings again
@@ -15,7 +15,7 @@
 
 - name: Make sure that clusterrolebindings are present now
   assert:
-    that: "clusterrolebinding_state.stdout != \"\""
+    that: "clusterrolebinding_state.stdout | length > 0"
     msg: "Cluster role binding is not present."
 
 - name: Get the heketi-config-secret secret
@@ -28,9 +28,10 @@
   template:
     src: "heketi.json.j2"
     dest: "{{ kube_config_dir }}/heketi.json"
+    mode: 0644
 
 - name: "Deploy Heketi config secret"
-  when: "secret_state.stdout == \"\""
+  when: "secret_state.stdout | length == 0"
   command: "{{ bin_dir }}/kubectl create secret generic heketi-config-secret --from-file={{ kube_config_dir }}/heketi.json"
 
 - name: Get the heketi-config-secret secret again
@@ -40,5 +41,5 @@
 
 - name: Make sure the heketi-config-secret secret exists now
   assert:
-    that: "secret_state.stdout != \"\""
+    that: "secret_state.stdout | length > 0"
     msg: "Heketi config secret is not present."

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

@@ -2,7 +2,10 @@
 - name: "Kubernetes Apps | Lay Down Heketi Storage"
   become: true
   vars: { nodes: "{{ groups['heketi-node'] }}" }
-  template: { src: "heketi-storage.json.j2", dest: "{{ kube_config_dir }}/heketi-storage.json" }
+  template:
+    src: "heketi-storage.json.j2"
+    dest: "{{ kube_config_dir }}/heketi-storage.json"
+    mode: 0644
   register: "rendering"
 - name: "Kubernetes Apps | Install and configure Heketi Storage"
   kube:

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

@@ -16,6 +16,7 @@
   template:
     src: "storageclass.yml.j2"
     dest: "{{ kube_config_dir }}/storageclass.yml"
+    mode: 0644
   register: "rendering"
 - name: "Kubernetes Apps | Install and configure Storace Class"
   kube:

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

@@ -10,6 +10,7 @@
   template:
     src: "topology.json.j2"
     dest: "{{ kube_config_dir }}/topology.json"
+    mode: 0644
 - name: "Copy topology configuration into container."  # noqa 503
   when: "rendering.changed"
   command: "{{ bin_dir }}/kubectl cp {{ kube_config_dir }}/topology.json {{ heketi_pod_name }}:/tmp/topology.json"

contrib/network-storage/heketi/roles/provision/templates/glusterfs-daemonset.json.j2

@@ -73,8 +73,8 @@
                             "privileged": true
                         },
                         "readinessProbe": {
-                            "timeoutSeconds": 3,
-                            "initialDelaySeconds": 3,
+                            "timeoutSeconds": {{ glusterfs_daemonset.readiness_probe.timeout_seconds }},
+                            "initialDelaySeconds": {{ glusterfs_daemonset.readiness_probe.initial_delay_seconds }},
                             "exec": {
                                 "command": [
                                     "/bin/bash",
@@ -84,8 +84,8 @@
                             }
                         },
                         "livenessProbe": {
-                            "timeoutSeconds": 3,
-                            "initialDelaySeconds": 10,
+                            "timeoutSeconds": {{ glusterfs_daemonset.liveness_probe.timeout_seconds }},
+                            "initialDelaySeconds": {{ glusterfs_daemonset.liveness_probe.initial_delay_seconds }},
                             "exec": {
                                 "command": [
                                     "/bin/bash",

contrib/network-storage/heketi/roles/tear-down-disks/tasks/main.yml

@@ -1,7 +1,7 @@
 ---
 - name: "Install lvm utils (RedHat)"
   become: true
-  yum:
+  package:
     name: "lvm2"
     state: "present"
   when: "ansible_os_family == 'RedHat'"
@@ -19,7 +19,7 @@
   become: true
   shell: "pvs {{ disk_volume_device_1 }} --option vg_name | tail -n+2"
   register: "volume_groups"
-  ignore_errors: true
+  ignore_errors: true   # noqa ignore-errors
   changed_when: false
 
 - name: "Remove volume groups."  # noqa 301
@@ -35,11 +35,11 @@
     PATH: "{{ ansible_env.PATH }}:/sbin"  # Make sure we can workaround RH / CentOS conservative path management
   become: true
   command: "pvremove {{ disk_volume_device_1 }} --yes"
-  ignore_errors: true
+  ignore_errors: true   # noqa ignore-errors
 
 - name: "Remove lvm utils (RedHat)"
   become: true
-  yum:
+  package:
     name: "lvm2"
     state: "absent"
   when: "ansible_os_family == 'RedHat' and heketi_remove_lvm"

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

@@ -1,51 +1,51 @@
 ---
-- name: "Remove storage class."  # noqa 301
+- name: Remove storage class.  # noqa 301
   command: "{{ bin_dir }}/kubectl delete storageclass gluster"
-  ignore_errors: true
-- name: "Tear down heketi."  # noqa 301
+  ignore_errors: true  # noqa ignore-errors
+- name: Tear down heketi.  # noqa 301
   command: "{{ bin_dir }}/kubectl delete all,service,jobs,deployment,secret --selector=\"glusterfs=heketi-pod\""
-  ignore_errors: true
-- name: "Tear down heketi."  # noqa 301
+  ignore_errors: true  # noqa ignore-errors
+- name: Tear down heketi.  # noqa 301
   command: "{{ bin_dir }}/kubectl delete all,service,jobs,deployment,secret --selector=\"glusterfs=heketi-deployment\""
-  ignore_errors: true
-- name: "Tear down bootstrap."
+  ignore_errors: true  # noqa ignore-errors
+- name: Tear down bootstrap.
   include_tasks: "../../provision/tasks/bootstrap/tear-down.yml"
-- name: "Ensure there is nothing left over."  # noqa 301
+- name: Ensure there is nothing left over.  # noqa 301
   command: "{{ bin_dir }}/kubectl get all,service,jobs,deployment,secret --selector=\"glusterfs=heketi-pod\" -o=json"
   register: "heketi_result"
   until: "heketi_result.stdout|from_json|json_query('items[*]')|length == 0"
   retries: 60
   delay: 5
-- name: "Ensure there is nothing left over."  # noqa 301
+- name: Ensure there is nothing left over.  # noqa 301
   command: "{{ bin_dir }}/kubectl get all,service,jobs,deployment,secret --selector=\"glusterfs=heketi-deployment\" -o=json"
   register: "heketi_result"
   until: "heketi_result.stdout|from_json|json_query('items[*]')|length == 0"
   retries: 60
   delay: 5
-- name: "Tear down glusterfs."  # noqa 301
+- name: Tear down glusterfs.  # noqa 301
   command: "{{ bin_dir }}/kubectl delete daemonset.extensions/glusterfs"
-  ignore_errors: true
-- name: "Remove heketi storage service."  # noqa 301
+  ignore_errors: true  # noqa ignore-errors
+- name: Remove heketi storage service.  # noqa 301
   command: "{{ bin_dir }}/kubectl delete service heketi-storage-endpoints"
-  ignore_errors: true
-- name: "Remove heketi gluster role binding"  # noqa 301
+  ignore_errors: true  # noqa ignore-errors
+- name: Remove heketi gluster role binding  # noqa 301
   command: "{{ bin_dir }}/kubectl delete clusterrolebinding heketi-gluster-admin"
-  ignore_errors: true
-- name: "Remove heketi config secret"  # noqa 301
+  ignore_errors: true  # noqa ignore-errors
+- name: Remove heketi config secret  # noqa 301
   command: "{{ bin_dir }}/kubectl delete secret heketi-config-secret"
-  ignore_errors: true
-- name: "Remove heketi db backup"  # noqa 301
+  ignore_errors: true  # noqa ignore-errors
+- name: Remove heketi db backup  # noqa 301
   command: "{{ bin_dir }}/kubectl delete secret heketi-db-backup"
-  ignore_errors: true
-- name: "Remove heketi service account"  # noqa 301
+  ignore_errors: true  # noqa ignore-errors
+- name: Remove heketi service account  # noqa 301
   command: "{{ bin_dir }}/kubectl delete serviceaccount heketi-service-account"
-  ignore_errors: true
-- name: "Get secrets"
+  ignore_errors: true  # noqa ignore-errors
+- name: Get secrets
   command: "{{ bin_dir }}/kubectl get secrets --output=\"json\""
   register: "secrets"
   changed_when: false
-- name: "Remove heketi storage secret"
+- name: Remove heketi storage secret
   vars: { storage_query: "items[?metadata.annotations.\"kubernetes.io/service-account.name\"=='heketi-service-account'].metadata.name|[0]" }
   command: "{{ bin_dir }}/kubectl delete secret {{ secrets.stdout|from_json|json_query(storage_query) }}"
   when: "storage_query is defined"
-  ignore_errors: true
+  ignore_errors: true  # noqa ignore-errors

contrib/offline/README.md

@@ -9,7 +9,8 @@ This script has two features:
 (2) Deploy local container registry and register the container images to the registry.
 
 Step(1) should be done online site as a preparation, then we bring the gotten images
-to the target offline environment.
+to the target offline environment. if images are from a private registry,
+you need to set `PRIVATE_REGISTRY` environment variable.
 Then we will run step(2) for registering the images to local registry.
 
 Step(1) can be operated with:
@@ -28,16 +29,37 @@ manage-offline-container-images.sh   register
 
 This script generates the list of downloaded files and the list of container images by `roles/download/defaults/main.yml` file.
 
-Run this script will generates three files, all downloaded files url in files.list, all container images in images.list, all component version in generate.sh.
+Run this script will execute `generate_list.yml` playbook in kubespray root directory and generate four files,
+all downloaded files url in files.list, all container images in images.list, jinja2 templates in *.template.
 
 ```shell
-bash generate_list.sh
+./generate_list.sh
 tree temp
 temp
 ├── files.list
-├── generate.sh
-└── images.list
-0 directories, 3 files
+├── files.list.template
+├── images.list
+└── images.list.template
+0 directories, 5 files
 ```
 
-In some cases you may want to update some component version, you can edit `generate.sh` file, then run `bash generate.sh | grep 'https' > files.list` to update file.list or run `bash generate.sh | grep -v 'https'> images.list` to update images.list.
+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/generate_list.sh

@@ -5,53 +5,29 @@ CURRENT_DIR=$(cd $(dirname $0); pwd)
 TEMP_DIR="${CURRENT_DIR}/temp"
 REPO_ROOT_DIR="${CURRENT_DIR%/contrib/offline}"
 
-: ${IMAGE_ARCH:="amd64"}
-: ${ANSIBLE_SYSTEM:="linux"}
-: ${ANSIBLE_ARCHITECTURE:="x86_64"}
 : ${DOWNLOAD_YML:="roles/download/defaults/main.yml"}
-: ${KUBE_VERSION_YAML:="roles/kubespray-defaults/defaults/main.yaml"}
 
 mkdir -p ${TEMP_DIR}
 
-# ARCH used in convert {%- if image_arch != 'amd64' -%}-{{ image_arch }}{%- endif -%} to {{arch}}
-if [ "${IMAGE_ARCH}" != "amd64" ]; then ARCH="${IMAGE_ARCH}"; fi
-
-cat > ${TEMP_DIR}/generate.sh << EOF
-arch=${ARCH}
-image_arch=${IMAGE_ARCH}
-ansible_system=${ANSIBLE_SYSTEM}
-ansible_architecture=${ANSIBLE_ARCHITECTURE}
-EOF
-
-# generate all component version by $DOWNLOAD_YML
-grep 'kube_version:' ${REPO_ROOT_DIR}/${KUBE_VERSION_YAML} \
-| sed 's/: /=/g' >> ${TEMP_DIR}/generate.sh
-grep '_version:' ${REPO_ROOT_DIR}/${DOWNLOAD_YML} \
-| sed 's/: /=/g;s/{{/${/g;s/}}/}/g' | tr -d ' ' >> ${TEMP_DIR}/generate.sh
-sed -i 's/kube_major_version=.*/kube_major_version=${kube_version%.*}/g' ${TEMP_DIR}/generate.sh
-sed -i 's/crictl_version=.*/crictl_version=${kube_version%.*}.0/g' ${TEMP_DIR}/generate.sh
-
-# generate all download files url
+# generate all download files url template
 grep 'download_url:' ${REPO_ROOT_DIR}/${DOWNLOAD_YML} \
-| sed 's/: /=/g;s/ //g;s/{{/${/g;s/}}/}/g;s/|lower//g;s/^.*_url=/echo /g' >> ${TEMP_DIR}/generate.sh
+    | sed 's/^.*_url: //g;s/\"//g' > ${TEMP_DIR}/files.list.template
 
-# generate all images list
-grep -E '_repo:|_tag:' ${REPO_ROOT_DIR}/${DOWNLOAD_YML} \
-| sed "s#{%- if image_arch != 'amd64' -%}-{{ image_arch }}{%- endif -%}#{{arch}}#g" \
-| sed 's/: /=/g;s/{{/${/g;s/}}/}/g' | tr -d ' ' >> ${TEMP_DIR}/generate.sh
+# generate all images list template
 sed -n '/^downloads:/,/download_defaults:/p' ${REPO_ROOT_DIR}/${DOWNLOAD_YML} \
-| sed -n "s/repo: //p;s/tag: //p" | tr -d ' ' | sed 's/{{/${/g;s/}}/}/g' \
-| sed 'N;s#\n# #g' | tr ' ' ':' | sed 's/^/echo /g' >> ${TEMP_DIR}/generate.sh
+    | sed -n "s/repo: //p;s/tag: //p" | tr -d ' ' \
+    | sed 'N;s#\n# #g' | tr ' ' ':' | sed 's/\"//g' > ${TEMP_DIR}/images.list.template
 
-# special handling for https://github.com/kubernetes-sigs/kubespray/pull/7570
-sed -i 's#^coredns_image_repo=.*#coredns_image_repo=${kube_image_repo}$(if printf "%s\\n%s\\n" v1.21 ${kube_version%.*} | sort --check=quiet --version-sort; then echo -n /coredns/coredns;else echo -n /coredns; fi)#' ${TEMP_DIR}/generate.sh
-sed -i 's#^coredns_image_tag=.*#coredns_image_tag=$(if printf "%s\\n%s\\n" v1.21 ${kube_version%.*} | sort --check=quiet --version-sort; then echo -n ${coredns_version};else echo -n ${coredns_version/v/}; fi)#' ${TEMP_DIR}/generate.sh
-
-# add kube-* images to images list
+# add kube-* images to images list template
+# Those container images are downloaded by kubeadm, then roles/download/defaults/main.yml
+# doesn't contain those images. That is reason why here needs to put those images into the
+# list separately.
 KUBE_IMAGES="kube-apiserver kube-controller-manager kube-scheduler kube-proxy"
-echo "${KUBE_IMAGES}" | tr ' ' '\n' | xargs -L1 -I {} \
-echo 'echo ${kube_image_repo}/{}:${kube_version}' >> ${TEMP_DIR}/generate.sh
+for i in $KUBE_IMAGES; do
+    echo "{{ kube_image_repo }}/$i:{{ kube_version }}" >> ${TEMP_DIR}/images.list.template
+done
 
-# print files.list and images.list
-bash ${TEMP_DIR}/generate.sh | grep 'https' | sort > ${TEMP_DIR}/files.list
-bash ${TEMP_DIR}/generate.sh | grep -v 'https' | sort > ${TEMP_DIR}/images.list
+# run ansible to expand templates
+/bin/cp ${CURRENT_DIR}/generate_list.yml ${REPO_ROOT_DIR}
+
+(cd ${REPO_ROOT_DIR} && ansible-playbook $* generate_list.yml && /bin/rm generate_list.yml) || exit 1

contrib/offline/generate_list.yml

@@ -0,0 +1,19 @@
+---
+- hosts: localhost
+  become: no
+
+  roles:
+    # Just load default variables from roles.
+    - role: kubespray-defaults
+      when: false
+    - role: download
+      when: false
+
+  tasks:
+    # Generate files.list and images.list files from templates.
+    - template:
+        src: ./contrib/offline/temp/{{ item }}.list.template
+        dest: ./contrib/offline/temp/{{ item }}.list
+      with_items:
+        - files
+        - images

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}
@@ -46,15 +46,16 @@ 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" ]; then
+		   [ "${FIRST_PART}" = "quay.io" ] ||
+		   [ "${FIRST_PART}" = "${PRIVATE_REGISTRY}" ]; then
 			image=$(echo ${image} | sed s@"${FIRST_PART}/"@@)
 		fi
 		echo "${FILE_NAME}  ${image}" >> ${IMAGE_LIST}
@@ -100,15 +101,35 @@ function register_container_images() {
 
 	tar -zxvf ${IMAGE_TAR_FILE}
 	sudo docker load -i ${IMAGE_DIR}/registry-latest.tar
-	sudo docker run --restart=always -d -p 5000:5000 --name registry registry:latest
 	set +e
-
+	sudo docker container inspect registry >/dev/null 2>&1
+	if [ $? -ne 0 ]; then
+		sudo docker run --restart=always -d -p 5000:5000 --name registry registry:latest
+	fi
 	set -e
+
 	while read -r line; do
 		file_name=$(echo ${line} | awk '{print $1}')
-		org_image=$(echo ${line} | awk '{print $2}')
-		new_image="${LOCALHOST_NAME}:5000/${org_image}"
-		image_id=$(tar -tf ${IMAGE_DIR}/${file_name} | grep "\.json" | grep -v manifest.json | sed s/"\.json"//)
+		raw_image=$(echo ${line} | awk '{print $2}')
+		new_image="${LOCALHOST_NAME}:5000/${raw_image}"
+		org_image=$(sudo docker load -i ${IMAGE_DIR}/${file_name} | head -n1 | awk '{print $3}')
+		image_id=$(sudo docker image inspect ${org_image} | grep "\"Id\":" | awk -F: '{print $3}'| sed s/'\",'//)
+		if [ -z "${file_name}" ]; then
+			echo "Failed to get file_name for line ${line}"
+			exit 1
+		fi
+		if [ -z "${raw_image}" ]; then
+			echo "Failed to get raw_image for line ${line}"
+			exit 1
+		fi
+		if [ -z "${org_image}" ]; then
+			echo "Failed to get org_image for line ${line}"
+			exit 1
+		fi
+		if [ -z "${image_id}" ]; then
+			echo "Failed to get image_id for file ${file_name}"
+			exit 1
+		fi
 		sudo docker load -i ${IMAGE_DIR}/${file_name}
 		sudo docker tag  ${image_id} ${new_image}
 		sudo docker push ${new_image}
@@ -132,7 +153,8 @@ else
 	echo "(2) Deploy local container registry and register the container images to the registry."
 	echo ""
 	echo "Step(1) should be done online site as a preparation, then we bring"
-	echo "the gotten images to the target offline environment."
+	echo "the gotten images to the target offline environment. if images are from"
+	echo "a private registry, you need to set PRIVATE_REGISTRY environment variable."
 	echo "Then we will run step(2) for registering the images to local registry."
 	echo ""
 	echo "${IMAGE_TAR_FILE} is created to contain your container images."

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/os-services/roles/prepare/tasks/main.yml

@@ -20,4 +20,4 @@
       "'ufw.service' in services"
 
   when:
-  - disable_service_firewall
+  - disable_service_firewall is defined and disable_service_firewall

contrib/packaging/rpm/kubespray.spec

@@ -9,8 +9,8 @@ Summary:        Ansible modules for installing Kubernetes
 
 Group:          System Environment/Libraries
 License:        ASL 2.0
-Url:            https://github.com/kubernetes-incubator/kubespray
-Source0:        https://github.com/kubernetes-incubator/kubespray/archive/%{upstream_version}.tar.gz#/%{name}-%{release}.tar.gz
+Url:            https://github.com/kubernetes-sigs/kubespray
+Source0:        https://github.com/kubernetes-sigs/kubespray/archive/%{upstream_version}.tar.gz#/%{name}-%{release}.tar.gz
 
 BuildArch:      noarch
 BuildRequires:  git

contrib/terraform/aws/.gitignore

@@ -1,2 +1,3 @@
 *.tfstate*
+.terraform.lock.hcl
 .terraform

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/aws/create-infrastructure.tf

@@ -20,20 +20,20 @@ module "aws-vpc" {
 
   aws_cluster_name         = var.aws_cluster_name
   aws_vpc_cidr_block       = var.aws_vpc_cidr_block
-  aws_avail_zones          = slice(data.aws_availability_zones.available.names, 0, 2)
+  aws_avail_zones          = data.aws_availability_zones.available.names
   aws_cidr_subnets_private = var.aws_cidr_subnets_private
   aws_cidr_subnets_public  = var.aws_cidr_subnets_public
   default_tags             = var.default_tags
 }
 
-module "aws-elb" {
-  source = "./modules/elb"
+module "aws-nlb" {
+  source = "./modules/nlb"
 
   aws_cluster_name      = var.aws_cluster_name
   aws_vpc_id            = module.aws-vpc.aws_vpc_id
-  aws_avail_zones       = slice(data.aws_availability_zones.available.names, 0, 2)
+  aws_avail_zones       = data.aws_availability_zones.available.names
   aws_subnet_ids_public = module.aws-vpc.aws_subnet_ids_public
-  aws_elb_api_port      = var.aws_elb_api_port
+  aws_nlb_api_port      = var.aws_nlb_api_port
   k8s_secure_api_port   = var.k8s_secure_api_port
   default_tags          = var.default_tags
 }
@@ -52,9 +52,8 @@ module "aws-iam" {
 resource "aws_instance" "bastion-server" {
   ami                         = data.aws_ami.distro.id
   instance_type               = var.aws_bastion_size
-  count                       = length(var.aws_cidr_subnets_public)
+  count                       = var.aws_bastion_num
   associate_public_ip_address = true
-  availability_zone           = element(slice(data.aws_availability_zones.available.names, 0, 2), count.index)
   subnet_id                   = element(module.aws-vpc.aws_subnet_ids_public, count.index)
 
   vpc_security_group_ids = module.aws-vpc.aws_security_group
@@ -79,11 +78,14 @@ resource "aws_instance" "k8s-master" {
 
   count = var.aws_kube_master_num
 
-  availability_zone = element(slice(data.aws_availability_zones.available.names, 0, 2), count.index)
-  subnet_id         = element(module.aws-vpc.aws_subnet_ids_private, count.index)
+  subnet_id = element(module.aws-vpc.aws_subnet_ids_private, count.index)
 
   vpc_security_group_ids = module.aws-vpc.aws_security_group
 
+  root_block_device {
+    volume_size = var.aws_kube_master_disk_size
+  }
+
   iam_instance_profile = module.aws-iam.kube_control_plane-profile
   key_name             = var.AWS_SSH_KEY_NAME
 
@@ -94,10 +96,10 @@ resource "aws_instance" "k8s-master" {
   }))
 }
 
-resource "aws_elb_attachment" "attach_master_nodes" {
-  count    = var.aws_kube_master_num
-  elb      = module.aws-elb.aws_elb_api_id
-  instance = element(aws_instance.k8s-master.*.id, count.index)
+resource "aws_lb_target_group_attachment" "tg-attach_master_nodes" {
+  count            = var.aws_kube_master_num
+  target_group_arn = module.aws-nlb.aws_nlb_api_tg_arn
+  target_id        = element(aws_instance.k8s-master.*.private_ip, count.index)
 }
 
 resource "aws_instance" "k8s-etcd" {
@@ -106,11 +108,14 @@ resource "aws_instance" "k8s-etcd" {
 
   count = var.aws_etcd_num
 
-  availability_zone = element(slice(data.aws_availability_zones.available.names, 0, 2), count.index)
-  subnet_id         = element(module.aws-vpc.aws_subnet_ids_private, count.index)
+  subnet_id = element(module.aws-vpc.aws_subnet_ids_private, count.index)
 
   vpc_security_group_ids = module.aws-vpc.aws_security_group
 
+  root_block_device {
+    volume_size = var.aws_etcd_disk_size
+  }
+
   key_name = var.AWS_SSH_KEY_NAME
 
   tags = merge(var.default_tags, tomap({
@@ -126,11 +131,14 @@ resource "aws_instance" "k8s-worker" {
 
   count = var.aws_kube_worker_num
 
-  availability_zone = element(slice(data.aws_availability_zones.available.names, 0, 2), count.index)
-  subnet_id         = element(module.aws-vpc.aws_subnet_ids_private, count.index)
+  subnet_id = element(module.aws-vpc.aws_subnet_ids_private, count.index)
 
   vpc_security_group_ids = module.aws-vpc.aws_security_group
 
+  root_block_device {
+    volume_size = var.aws_kube_worker_disk_size
+  }
+
   iam_instance_profile = module.aws-iam.kube-worker-profile
   key_name             = var.AWS_SSH_KEY_NAME
 
@@ -152,11 +160,11 @@ data "template_file" "inventory" {
     public_ip_address_bastion = join("\n", formatlist("bastion ansible_host=%s", aws_instance.bastion-server.*.public_ip))
     connection_strings_master = join("\n", formatlist("%s ansible_host=%s", aws_instance.k8s-master.*.private_dns, aws_instance.k8s-master.*.private_ip))
     connection_strings_node   = join("\n", formatlist("%s ansible_host=%s", aws_instance.k8s-worker.*.private_dns, aws_instance.k8s-worker.*.private_ip))
-    connection_strings_etcd   = join("\n", formatlist("%s ansible_host=%s", aws_instance.k8s-etcd.*.private_dns, aws_instance.k8s-etcd.*.private_ip))
     list_master               = join("\n", aws_instance.k8s-master.*.private_dns)
     list_node                 = join("\n", aws_instance.k8s-worker.*.private_dns)
-    list_etcd                 = join("\n", aws_instance.k8s-etcd.*.private_dns)
-    elb_api_fqdn              = "apiserver_loadbalancer_domain_name=\"${module.aws-elb.aws_elb_api_fqdn}\""
+    connection_strings_etcd   = join("\n", formatlist("%s ansible_host=%s", aws_instance.k8s-etcd.*.private_dns, aws_instance.k8s-etcd.*.private_ip))
+    list_etcd                 = join("\n", ((var.aws_etcd_num > 0) ? (aws_instance.k8s-etcd.*.private_dns) : (aws_instance.k8s-master.*.private_dns)))
+    nlb_api_fqdn              = "apiserver_loadbalancer_domain_name=\"${module.aws-nlb.aws_nlb_api_fqdn}\""
   }
 }
 

contrib/terraform/aws/modules/elb/main.tf

@@ -1,57 +0,0 @@
-resource "aws_security_group" "aws-elb" {
-  name   = "kubernetes-${var.aws_cluster_name}-securitygroup-elb"
-  vpc_id = var.aws_vpc_id
-
-  tags = merge(var.default_tags, tomap({
-    Name = "kubernetes-${var.aws_cluster_name}-securitygroup-elb"
-  }))
-}
-
-resource "aws_security_group_rule" "aws-allow-api-access" {
-  type              = "ingress"
-  from_port         = var.aws_elb_api_port
-  to_port           = var.k8s_secure_api_port
-  protocol          = "TCP"
-  cidr_blocks       = ["0.0.0.0/0"]
-  security_group_id = aws_security_group.aws-elb.id
-}
-
-resource "aws_security_group_rule" "aws-allow-api-egress" {
-  type              = "egress"
-  from_port         = 0
-  to_port           = 65535
-  protocol          = "TCP"
-  cidr_blocks       = ["0.0.0.0/0"]
-  security_group_id = aws_security_group.aws-elb.id
-}
-
-# Create a new AWS ELB for K8S API
-resource "aws_elb" "aws-elb-api" {
-  name            = "kubernetes-elb-${var.aws_cluster_name}"
-  subnets         = var.aws_subnet_ids_public
-  security_groups = [aws_security_group.aws-elb.id]
-
-  listener {
-    instance_port     = var.k8s_secure_api_port
-    instance_protocol = "tcp"
-    lb_port           = var.aws_elb_api_port
-    lb_protocol       = "tcp"
-  }
-
-  health_check {
-    healthy_threshold   = 2
-    unhealthy_threshold = 2
-    timeout             = 3
-    target              = "HTTPS:${var.k8s_secure_api_port}/healthz"
-    interval            = 30
-  }
-
-  cross_zone_load_balancing   = true
-  idle_timeout                = 400
-  connection_draining         = true
-  connection_draining_timeout = 400
-
-  tags = merge(var.default_tags, tomap({
-    Name = "kubernetes-${var.aws_cluster_name}-elb-api"
-  }))
-}

contrib/terraform/aws/modules/elb/outputs.tf

@@ -1,7 +0,0 @@
-output "aws_elb_api_id" {
-  value = aws_elb.aws-elb-api.id
-}
-
-output "aws_elb_api_fqdn" {
-  value = aws_elb.aws-elb-api.dns_name
-}

contrib/terraform/aws/modules/nlb/main.tf

@@ -0,0 +1,41 @@
+# Create a new AWS NLB for K8S API
+resource "aws_lb" "aws-nlb-api" {
+  name                             = "kubernetes-nlb-${var.aws_cluster_name}"
+  load_balancer_type               = "network"
+  subnets                          = length(var.aws_subnet_ids_public) <= length(var.aws_avail_zones) ? var.aws_subnet_ids_public : slice(var.aws_subnet_ids_public, 0, length(var.aws_avail_zones))
+  idle_timeout                     = 400
+  enable_cross_zone_load_balancing = true
+
+  tags = merge(var.default_tags, tomap({
+    Name = "kubernetes-${var.aws_cluster_name}-nlb-api"
+  }))
+}
+
+# Create a new AWS NLB Instance Target Group
+resource "aws_lb_target_group" "aws-nlb-api-tg" {
+  name        = "kubernetes-nlb-tg-${var.aws_cluster_name}"
+  port        = var.k8s_secure_api_port
+  protocol    = "TCP"
+  target_type = "ip"
+  vpc_id      = var.aws_vpc_id
+
+  health_check {
+    healthy_threshold   = 2
+    unhealthy_threshold = 2
+    interval            = 30
+    protocol            = "HTTPS"
+    path                = "/healthz"
+  }
+}
+
+# Create a new AWS NLB Listener listen to target group
+resource "aws_lb_listener" "aws-nlb-api-listener" {
+  load_balancer_arn = aws_lb.aws-nlb-api.arn
+  port              = var.aws_nlb_api_port
+  protocol          = "TCP"
+
+  default_action {
+    type             = "forward"
+    target_group_arn = aws_lb_target_group.aws-nlb-api-tg.arn
+  }
+}

contrib/terraform/aws/modules/nlb/outputs.tf

@@ -0,0 +1,11 @@
+output "aws_nlb_api_id" {
+  value = aws_lb.aws-nlb-api.id
+}
+
+output "aws_nlb_api_fqdn" {
+  value = aws_lb.aws-nlb-api.dns_name
+}
+
+output "aws_nlb_api_tg_arn" {
+  value = aws_lb_target_group.aws-nlb-api-tg.arn
+}

contrib/terraform/aws/modules/nlb/variables.tf

@@ -6,8 +6,8 @@ variable "aws_vpc_id" {
   description = "AWS VPC ID"
 }
 
-variable "aws_elb_api_port" {
-  description = "Port for AWS ELB"
+variable "aws_nlb_api_port" {
+  description = "Port for AWS NLB"
 }
 
 variable "k8s_secure_api_port" {

contrib/terraform/aws/modules/vpc/main.tf

@@ -25,13 +25,14 @@ resource "aws_internet_gateway" "cluster-vpc-internetgw" {
 
 resource "aws_subnet" "cluster-vpc-subnets-public" {
   vpc_id            = aws_vpc.cluster-vpc.id
-  count             = length(var.aws_avail_zones)
-  availability_zone = element(var.aws_avail_zones, count.index)
+  count             = length(var.aws_cidr_subnets_public)
+  availability_zone = element(var.aws_avail_zones, count.index % length(var.aws_avail_zones))
   cidr_block        = element(var.aws_cidr_subnets_public, count.index)
 
   tags = merge(var.default_tags, tomap({
     Name = "kubernetes-${var.aws_cluster_name}-${element(var.aws_avail_zones, count.index)}-public"
-    "kubernetes.io/cluster/${var.aws_cluster_name}" = "member"
+    "kubernetes.io/cluster/${var.aws_cluster_name}" = "shared"
+    "kubernetes.io/role/elb" = "1"
   }))
 }
 
@@ -43,12 +44,14 @@ resource "aws_nat_gateway" "cluster-nat-gateway" {
 
 resource "aws_subnet" "cluster-vpc-subnets-private" {
   vpc_id            = aws_vpc.cluster-vpc.id
-  count             = length(var.aws_avail_zones)
-  availability_zone = element(var.aws_avail_zones, count.index)
+  count             = length(var.aws_cidr_subnets_private)
+  availability_zone = element(var.aws_avail_zones, count.index % length(var.aws_avail_zones))
   cidr_block        = element(var.aws_cidr_subnets_private, count.index)
 
   tags = merge(var.default_tags, tomap({
     Name = "kubernetes-${var.aws_cluster_name}-${element(var.aws_avail_zones, count.index)}-private"
+    "kubernetes.io/cluster/${var.aws_cluster_name}" = "shared"
+    "kubernetes.io/role/internal-elb" = "1"
   }))
 }
 

contrib/terraform/aws/output.tf

@@ -11,11 +11,11 @@ output "workers" {
 }
 
 output "etcd" {
-  value = join("\n", aws_instance.k8s-etcd.*.private_ip)
+  value = join("\n", ((var.aws_etcd_num > 0) ? (aws_instance.k8s-etcd.*.private_ip) : (aws_instance.k8s-master.*.private_ip)))
 }
 
-output "aws_elb_api_fqdn" {
-  value = "${module.aws-elb.aws_elb_api_fqdn}:${var.aws_elb_api_port}"
+output "aws_nlb_api_fqdn" {
+  value = "${module.aws-nlb.aws_nlb_api_fqdn}:${var.aws_nlb_api_port}"
 }
 
 output "inventory" {

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

@@ -9,6 +9,8 @@ aws_cidr_subnets_private = ["10.250.192.0/20", "10.250.208.0/20"]
 aws_cidr_subnets_public = ["10.250.224.0/20", "10.250.240.0/20"]
 
 #Bastion Host
+aws_bastion_num = 1
+
 aws_bastion_size = "t2.medium"
 
 #Kubernetes Cluster
@@ -17,22 +19,26 @@ aws_kube_master_num = 3
 
 aws_kube_master_size = "t2.medium"
 
+aws_kube_master_disk_size = 50
+
 aws_etcd_num = 3
 
 aws_etcd_size = "t2.medium"
 
+aws_etcd_disk_size = 50
+
 aws_kube_worker_num = 4
 
 aws_kube_worker_size = "t2.medium"
 
-#Settings AWS ELB
+aws_kube_worker_disk_size = 50
 
-aws_elb_api_port = 6443
+#Settings AWS NLB
+
+aws_nlb_api_port = 6443
 
 k8s_secure_api_port = 6443
 
-kube_insecure_apiserver_address = "0.0.0.0"
-
 default_tags = {
   #  Env = "devtest"  #  Product = "kubernetes"
 }

contrib/terraform/aws/templates/inventory.tpl

@@ -10,19 +10,18 @@ ${public_ip_address_bastion}
 [kube_control_plane]
 ${list_master}
 
-
 [kube_node]
 ${list_node}
 
-
 [etcd]
 ${list_etcd}
 
+[calico_rr]
 
 [k8s_cluster:children]
 kube_node
 kube_control_plane
-
+calico_rr
 
 [k8s_cluster:vars]
-${elb_api_fqdn}
+${nlb_api_fqdn}

contrib/terraform/aws/terraform.tfvars

@@ -6,26 +6,34 @@ aws_vpc_cidr_block       = "10.250.192.0/18"
 aws_cidr_subnets_private = ["10.250.192.0/20", "10.250.208.0/20"]
 aws_cidr_subnets_public  = ["10.250.224.0/20", "10.250.240.0/20"]
 
-#Bastion Host
-aws_bastion_size = "t2.medium"
+# single AZ deployment
+#aws_cidr_subnets_private = ["10.250.192.0/20"]
+#aws_cidr_subnets_public  = ["10.250.224.0/20"]
 
+# 3+ AZ deployment
+#aws_cidr_subnets_private = ["10.250.192.0/24","10.250.193.0/24","10.250.194.0/24","10.250.195.0/24"]
+#aws_cidr_subnets_public  = ["10.250.224.0/24","10.250.225.0/24","10.250.226.0/24","10.250.227.0/24"]
+
+#Bastion Host
+aws_bastion_num  = 1
+aws_bastion_size = "t3.small"
 
 #Kubernetes Cluster
+aws_kube_master_num       = 3
+aws_kube_master_size      = "t3.medium"
+aws_kube_master_disk_size = 50
 
-aws_kube_master_num  = 3
-aws_kube_master_size = "t2.medium"
+aws_etcd_num       = 0
+aws_etcd_size      = "t3.medium"
+aws_etcd_disk_size = 50
 
-aws_etcd_num  = 3
-aws_etcd_size = "t2.medium"
-
-aws_kube_worker_num  = 4
-aws_kube_worker_size = "t2.medium"
+aws_kube_worker_num       = 4
+aws_kube_worker_size      = "t3.medium"
+aws_kube_worker_disk_size = 50
 
 #Settings AWS ELB
-
-aws_elb_api_port                = 6443
-k8s_secure_api_port             = 6443
-kube_insecure_apiserver_address = "0.0.0.0"
+aws_nlb_api_port    = 6443
+k8s_secure_api_port = 6443
 
 default_tags = {
   #  Env = "devtest"

contrib/terraform/aws/terraform.tfvars.example

@@ -8,25 +8,26 @@ aws_cidr_subnets_public = ["10.250.224.0/20","10.250.240.0/20"]
 aws_avail_zones = ["eu-central-1a","eu-central-1b"]
 
 #Bastion Host
-aws_bastion_ami = "ami-5900cc36"
-aws_bastion_size = "t2.small"
-
+aws_bastion_num = 1
+aws_bastion_size = "t3.small"
 
 #Kubernetes Cluster
-
 aws_kube_master_num = 3
-aws_kube_master_size = "t2.medium"
+aws_kube_master_size = "t3.medium"
+aws_kube_master_disk_size = 50
 
 aws_etcd_num = 3
-aws_etcd_size = "t2.medium"
+aws_etcd_size = "t3.medium"
+aws_etcd_disk_size = 50
 
 aws_kube_worker_num = 4
-aws_kube_worker_size = "t2.medium"
-
-aws_cluster_ami = "ami-903df7ff"
+aws_kube_worker_size = "t3.medium"
+aws_kube_worker_disk_size = 50
 
 #Settings AWS ELB
-
-aws_elb_api_port = 6443
+aws_nlb_api_port = 6443
 k8s_secure_api_port = 6443
-kube_insecure_apiserver_address = 0.0.0.0
+
+default_tags = { }
+
+inventory_file = "../../../inventory/hosts"

contrib/terraform/aws/variables.tf

@@ -25,7 +25,7 @@ data "aws_ami" "distro" {
 
   filter {
     name   = "name"
-    values = ["ubuntu/images/hvm-ssd/ubuntu-bionic-18.04-amd64-server-*"]
+    values = ["debian-10-amd64-*"]
   }
 
   filter {
@@ -33,7 +33,7 @@ data "aws_ami" "distro" {
     values = ["hvm"]
   }
 
-  owners = ["099720109477"] # Canonical
+  owners = ["136693071363"] # Debian-10
 }
 
 //AWS VPC Variables
@@ -63,10 +63,18 @@ variable "aws_bastion_size" {
 * The number should be divisable by the number of used
 * AWS Availability Zones without an remainder.
 */
+variable "aws_bastion_num" {
+  description = "Number of Bastion Nodes"
+}
+
 variable "aws_kube_master_num" {
   description = "Number of Kubernetes Master Nodes"
 }
 
+variable "aws_kube_master_disk_size" {
+  description = "Disk size for Kubernetes Master Nodes (in GiB)"
+}
+
 variable "aws_kube_master_size" {
   description = "Instance size of Kube Master Nodes"
 }
@@ -75,6 +83,10 @@ variable "aws_etcd_num" {
   description = "Number of etcd Nodes"
 }
 
+variable "aws_etcd_disk_size" {
+  description = "Disk size for etcd Nodes (in GiB)"
+}
+
 variable "aws_etcd_size" {
   description = "Instance size of etcd Nodes"
 }
@@ -83,16 +95,20 @@ variable "aws_kube_worker_num" {
   description = "Number of Kubernetes Worker Nodes"
 }
 
+variable "aws_kube_worker_disk_size" {
+  description = "Disk size for Kubernetes Worker Nodes (in GiB)"
+}
+
 variable "aws_kube_worker_size" {
   description = "Instance size of Kubernetes Worker Nodes"
 }
 
 /*
-* AWS ELB Settings
+* AWS NLB Settings
 *
 */
-variable "aws_elb_api_port" {
-  description = "Port for AWS ELB"
+variable "aws_nlb_api_port" {
+  description = "Port for AWS NLB"
 }
 
 variable "k8s_secure_api_port" {

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/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/gcp/README.md

@@ -74,14 +74,23 @@ ansible-playbook -i contrib/terraform/gcs/inventory.ini cluster.yml -b -v
 * `ssh_whitelist`: List of IP ranges (CIDR) that will be allowed to ssh to the nodes
 * `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
 
 ### Optional
 
 * `prefix`: Prefix to use for all resources, required to be unique for all clusters in the same project *(Defaults to `default`)*
-* `master_sa_email`: Service account email to use for the master nodes *(Defaults to `""`, auto generate one)*
-* `master_sa_scopes`: Service account email to use for the master nodes *(Defaults to `["https://www.googleapis.com/auth/cloud-platform"]`)*
+* `master_sa_email`: Service account email to use for the control plane nodes *(Defaults to `""`, auto generate one)*
+* `master_sa_scopes`: Service account email to use for the control plane nodes *(Defaults to `["https://www.googleapis.com/auth/cloud-platform"]`)*
+* `master_preemptible`: Enable [preemptible](https://cloud.google.com/compute/docs/instances/preemptible)
+  for the control plane nodes *(Defaults to `false`)*
+* `master_additional_disk_type`: [Disk type](https://cloud.google.com/compute/docs/disks/#disk-types)
+  for extra disks added on the control plane nodes *(Defaults to `"pd-ssd"`)*
 * `worker_sa_email`: Service account email to use for the worker nodes *(Defaults to `""`, auto generate one)*
 * `worker_sa_scopes`: Service account email to use for the worker nodes *(Defaults to `["https://www.googleapis.com/auth/cloud-platform"]`)*
+* `worker_preemptible`: Enable [preemptible](https://cloud.google.com/compute/docs/instances/preemptible)
+  for the worker nodes *(Defaults to `false`)*
+* `worker_additional_disk_type`: [Disk type](https://cloud.google.com/compute/docs/disks/#disk-types)
+  for extra disks added on the worker nodes *(Defaults to `"pd-ssd"`)*
 
 An example variables file can be found `tfvars.json`
 

contrib/terraform/gcp/main.tf

@@ -1,8 +1,16 @@
+terraform {
+  required_providers {
+    google = {
+      source  = "hashicorp/google"
+      version = "~> 4.0"
+    }
+  }
+}
+
 provider "google" {
   credentials = file(var.keyfile_location)
   region      = var.region
   project     = var.gcp_project_id
-  version     = "~> 3.48"
 }
 
 module "kubernetes" {
@@ -13,12 +21,17 @@ module "kubernetes" {
   machines    = var.machines
   ssh_pub_key = var.ssh_pub_key
 
-  master_sa_email  = var.master_sa_email
-  master_sa_scopes = var.master_sa_scopes
-  worker_sa_email  = var.worker_sa_email
-  worker_sa_scopes = var.worker_sa_scopes
+  master_sa_email    = var.master_sa_email
+  master_sa_scopes   = var.master_sa_scopes
+  master_preemptible = var.master_preemptible
+  master_additional_disk_type = var.master_additional_disk_type
+  worker_sa_email    = var.worker_sa_email
+  worker_sa_scopes   = var.worker_sa_scopes
+  worker_preemptible = var.worker_preemptible
+  worker_additional_disk_type = var.worker_additional_disk_type
 
   ssh_whitelist        = var.ssh_whitelist
   api_server_whitelist = var.api_server_whitelist
   nodeport_whitelist   = var.nodeport_whitelist
+  ingress_whitelist    = var.ingress_whitelist
 }

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

@@ -5,6 +5,8 @@
 
 resource "google_compute_network" "main" {
   name = "${var.prefix}-network"
+
+  auto_create_subnetworks = false
 }
 
 resource "google_compute_subnetwork" "main" {
@@ -20,6 +22,8 @@ resource "google_compute_firewall" "deny_all" {
 
   priority = 1000
 
+  source_ranges = ["0.0.0.0/0"]
+
   deny {
     protocol = "all"
   }
@@ -39,6 +43,8 @@ resource "google_compute_firewall" "allow_internal" {
 }
 
 resource "google_compute_firewall" "ssh" {
+  count = length(var.ssh_whitelist) > 0 ? 1 : 0
+
   name    = "${var.prefix}-ssh-firewall"
   network = google_compute_network.main.name
 
@@ -53,6 +59,8 @@ resource "google_compute_firewall" "ssh" {
 }
 
 resource "google_compute_firewall" "api_server" {
+  count = length(var.api_server_whitelist) > 0 ? 1 : 0
+
   name    = "${var.prefix}-api-server-firewall"
   network = google_compute_network.main.name
 
@@ -67,6 +75,8 @@ resource "google_compute_firewall" "api_server" {
 }
 
 resource "google_compute_firewall" "nodeport" {
+  count = length(var.nodeport_whitelist) > 0 ? 1 : 0
+
   name    = "${var.prefix}-nodeport-firewall"
   network = google_compute_network.main.name
 
@@ -81,11 +91,15 @@ resource "google_compute_firewall" "nodeport" {
 }
 
 resource "google_compute_firewall" "ingress_http" {
+  count = length(var.ingress_whitelist) > 0 ? 1 : 0
+
   name    = "${var.prefix}-http-ingress-firewall"
   network = google_compute_network.main.name
 
   priority = 100
 
+  source_ranges = var.ingress_whitelist
+
   allow {
     protocol = "tcp"
     ports    = ["80"]
@@ -93,11 +107,15 @@ resource "google_compute_firewall" "ingress_http" {
 }
 
 resource "google_compute_firewall" "ingress_https" {
+  count = length(var.ingress_whitelist) > 0 ? 1 : 0
+
   name    = "${var.prefix}-https-ingress-firewall"
   network = google_compute_network.main.name
 
   priority = 100
 
+  source_ranges = var.ingress_whitelist
+
   allow {
     protocol = "tcp"
     ports    = ["443"]
@@ -173,7 +191,7 @@ resource "google_compute_disk" "master" {
    }
 
   name = "${var.prefix}-${each.key}"
-  type = "pd-ssd"
+  type = var.master_additional_disk_type
   zone = each.value.machine.zone
   size = each.value.disk_size
 
@@ -229,19 +247,28 @@ resource "google_compute_instance" "master" {
 
   # Since we use google_compute_attached_disk we need to ignore this
   lifecycle {
-    ignore_changes = ["attached_disk"]
+    ignore_changes = [attached_disk]
+  }
+
+  scheduling {
+    preemptible = var.master_preemptible
+    automatic_restart = !var.master_preemptible
   }
 }
 
 resource "google_compute_forwarding_rule" "master_lb" {
+  count = length(var.api_server_whitelist) > 0 ? 1 : 0
+
   name = "${var.prefix}-master-lb-forward-rule"
 
   port_range = "6443"
 
-  target = google_compute_target_pool.master_lb.id
+  target = google_compute_target_pool.master_lb[count.index].id
 }
 
 resource "google_compute_target_pool" "master_lb" {
+  count = length(var.api_server_whitelist) > 0 ? 1 : 0
+
   name      = "${var.prefix}-master-lb-pool"
   instances = local.master_target_list
 }
@@ -258,7 +285,7 @@ resource "google_compute_disk" "worker" {
    }
 
   name = "${var.prefix}-${each.key}"
-  type = "pd-ssd"
+  type = var.worker_additional_disk_type
   zone = each.value.machine.zone
   size = each.value.disk_size
 
@@ -326,35 +353,48 @@ resource "google_compute_instance" "worker" {
 
   # Since we use google_compute_attached_disk we need to ignore this
   lifecycle {
-    ignore_changes = ["attached_disk"]
+    ignore_changes = [attached_disk]
+  }
+
+  scheduling {
+    preemptible = var.worker_preemptible
+    automatic_restart = !var.worker_preemptible
   }
 }
 
 resource "google_compute_address" "worker_lb" {
+  count = length(var.ingress_whitelist) > 0 ? 1 : 0
+
   name         = "${var.prefix}-worker-lb-address"
   address_type = "EXTERNAL"
   region       = var.region
 }
 
 resource "google_compute_forwarding_rule" "worker_http_lb" {
+  count = length(var.ingress_whitelist) > 0 ? 1 : 0
+
   name = "${var.prefix}-worker-http-lb-forward-rule"
 
-  ip_address = google_compute_address.worker_lb.address
+  ip_address = google_compute_address.worker_lb[count.index].address
   port_range = "80"
 
-  target = google_compute_target_pool.worker_lb.id
+  target = google_compute_target_pool.worker_lb[count.index].id
 }
 
 resource "google_compute_forwarding_rule" "worker_https_lb" {
+  count = length(var.ingress_whitelist) > 0 ? 1 : 0
+
   name = "${var.prefix}-worker-https-lb-forward-rule"
 
-  ip_address = google_compute_address.worker_lb.address
+  ip_address = google_compute_address.worker_lb[count.index].address
   port_range = "443"
 
-  target = google_compute_target_pool.worker_lb.id
+  target = google_compute_target_pool.worker_lb[count.index].id
 }
 
 resource "google_compute_target_pool" "worker_lb" {
+  count = length(var.ingress_whitelist) > 0 ? 1 : 0
+
   name      = "${var.prefix}-worker-lb-pool"
   instances = local.worker_target_list
 }

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

@@ -19,9 +19,9 @@ output "worker_ip_addresses" {
 }
 
 output "ingress_controller_lb_ip_address" {
-  value = google_compute_address.worker_lb.address
+  value = length(var.ingress_whitelist) > 0 ? google_compute_address.worker_lb.0.address : ""
 }
 
 output "control_plane_lb_ip_address" {
-  value = google_compute_forwarding_rule.master_lb.ip_address
+  value = length(var.api_server_whitelist) > 0 ? google_compute_forwarding_rule.master_lb.0.ip_address : ""
 }

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

@@ -27,6 +27,14 @@ variable "master_sa_scopes" {
   type = list(string)
 }
 
+variable "master_preemptible" {
+  type = bool
+}
+
+variable "master_additional_disk_type" {
+  type = string
+}
+
 variable "worker_sa_email" {
   type = string
 }
@@ -35,6 +43,14 @@ variable "worker_sa_scopes" {
   type = list(string)
 }
 
+variable "worker_preemptible" {
+  type = bool
+}
+
+variable "worker_additional_disk_type" {
+  type = string
+}
+
 variable "ssh_pub_key" {}
 
 variable "ssh_whitelist" {
@@ -49,6 +65,11 @@ variable "nodeport_whitelist" {
   type = list(string)
 }
 
+variable "ingress_whitelist" {
+  type = list(string)
+  default = ["0.0.0.0/0"]
+}
+
 variable "private_network_cidr" {
   default = "10.0.10.0/24"
 }

contrib/terraform/gcp/tfvars.json

@@ -16,6 +16,9 @@
   "nodeport_whitelist": [
     "1.2.3.4/32"
   ],
+  "ingress_whitelist": [
+    "0.0.0.0/0"
+  ],
 
   "machines": {
     "master-0": {
@@ -24,7 +27,7 @@
       "zone": "us-central1-a",
       "additional_disks": {},
       "boot_disk": {
-        "image_name": "ubuntu-os-cloud/ubuntu-1804-bionic-v20201116",
+        "image_name": "ubuntu-os-cloud/ubuntu-2004-focal-v20220118",
         "size": 50
       }
     },
@@ -38,7 +41,7 @@
         }
       },
       "boot_disk": {
-        "image_name": "ubuntu-os-cloud/ubuntu-1804-bionic-v20201116",
+        "image_name": "ubuntu-os-cloud/ubuntu-2004-focal-v20220118",
         "size": 50
       }
     },
@@ -52,7 +55,7 @@
         }
       },
       "boot_disk": {
-        "image_name": "ubuntu-os-cloud/ubuntu-1804-bionic-v20201116",
+        "image_name": "ubuntu-os-cloud/ubuntu-2004-focal-v20220118",
         "size": 50
       }
     }

contrib/terraform/gcp/variables.tf

@@ -44,6 +44,16 @@ variable "master_sa_scopes" {
   default = ["https://www.googleapis.com/auth/cloud-platform"]
 }
 
+variable "master_preemptible" {
+  type    = bool
+  default = false
+}
+
+variable "master_additional_disk_type" {
+  type = string
+  default = "pd-ssd"
+}
+
 variable "worker_sa_email" {
   type    = string
   default = ""
@@ -54,6 +64,16 @@ variable "worker_sa_scopes" {
   default = ["https://www.googleapis.com/auth/cloud-platform"]
 }
 
+variable "worker_preemptible" {
+  type    = bool
+  default = false
+}
+
+variable "worker_additional_disk_type" {
+  type = string
+  default = "pd-ssd"
+}
+
 variable ssh_pub_key {
   description = "Path to public SSH key file which is injected into the VMs."
   type        = string
@@ -70,3 +90,8 @@ variable api_server_whitelist {
 variable nodeport_whitelist {
   type = list(string)
 }
+
+variable "ingress_whitelist" {
+  type = list(string)
+  default = ["0.0.0.0/0"]
+}

contrib/terraform/hetzner/README.md

@@ -0,0 +1,108 @@
+# Kubernetes on Hetzner with Terraform
+
+Provision a Kubernetes cluster on [Hetzner](https://www.hetzner.com/cloud) using Terraform and Kubespray
+
+## Overview
+
+The setup looks like following
+
+```text
+   Kubernetes cluster
++--------------------------+
+|      +--------------+    |
+|      | +--------------+  |
+| -->  | |              |  |
+|      | | Master/etcd  |  |
+|      | | node(s)      |  |
+|      +-+              |  |
+|        +--------------+  |
+|              ^           |
+|              |           |
+|              v           |
+|      +--------------+    |
+|      | +--------------+  |
+| -->  | |              |  |
+|      | |    Worker    |  |
+|      | |    node(s)   |  |
+|      +-+              |  |
+|        +--------------+  |
++--------------------------+
+```
+
+The nodes uses a private network for node to node communication and a public interface for all external communication.
+
+## Requirements
+
+* Terraform 0.14.0 or newer
+
+## Quickstart
+
+NOTE: Assumes you are at the root of the kubespray repo.
+
+For authentication in your cluster you can use the environment variables.
+
+```bash
+export HCLOUD_TOKEN=api-token
+```
+
+Copy the cluster configuration file.
+
+```bash
+CLUSTER=my-hetzner-cluster
+cp -r inventory/sample inventory/$CLUSTER
+cp contrib/terraform/hetzner/default.tfvars inventory/$CLUSTER/
+cd inventory/$CLUSTER
+```
+
+Edit `default.tfvars` to match your requirement.
+
+Run Terraform to create the infrastructure.
+
+```bash
+terraform init ../../contrib/terraform/hetzner
+terraform apply --var-file default.tfvars ../../contrib/terraform/hetzner/
+```
+
+You should now have a inventory file named `inventory.ini` that you can use with kubespray.
+You can use the inventory file with kubespray to set up a cluster.
+
+It is a good idea to check that you have basic SSH connectivity to the nodes. You can do that by:
+
+```bash
+ansible -i inventory.ini -m ping all
+```
+
+You can setup Kubernetes with kubespray using the generated inventory:
+
+```bash
+ansible-playbook -i inventory.ini ../../cluster.yml -b -v
+```
+
+## Cloud controller
+
+For better support with the cloud you can install the [hcloud cloud controller](https://github.com/hetznercloud/hcloud-cloud-controller-manager) and [CSI driver](https://github.com/hetznercloud/csi-driver).
+
+Please read the instructions in both repos on how to install it.
+
+## Teardown
+
+You can teardown your infrastructure using the following Terraform command:
+
+```bash
+terraform destroy --var-file default.tfvars ../../contrib/terraform/hetzner
+```
+
+## Variables
+
+* `prefix`: Prefix to add to all resources, if set to "" don't set any prefix
+* `ssh_public_keys`: List of public SSH keys to install on all machines
+* `zone`: The zone where to run the cluster
+* `network_zone`: the network zone where the cluster is running
+* `machines`: Machines to provision. Key of this object will be used as the name of the machine
+  * `node_type`: The role of this node *(master|worker)*
+  * `size`: Size of the VM
+  * `image`: The image to use for the VM
+* `ssh_whitelist`: List of IP ranges (CIDR) that will be allowed to ssh to the nodes
+* `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 kubernetes workers on port 80 and 443

contrib/terraform/hetzner/default.tfvars

@@ -0,0 +1,44 @@
+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",
+]
+
+machines = {
+  "master-0" : {
+    "node_type" : "master",
+    "size" : "cx21",
+    "image" : "ubuntu-20.04",
+  },
+  "worker-0" : {
+    "node_type" : "worker",
+    "size" : "cx21",
+    "image" : "ubuntu-20.04",
+  },
+  "worker-1" : {
+    "node_type" : "worker",
+    "size" : "cx21",
+    "image" : "ubuntu-20.04",
+  }
+}
+
+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/main.tf

@@ -0,0 +1,52 @@
+provider "hcloud" {}
+
+module "kubernetes" {
+  source = "./modules/kubernetes-cluster"
+
+  prefix = var.prefix
+
+  zone = var.zone
+
+  machines = var.machines
+
+  ssh_public_keys = var.ssh_public_keys
+  network_zone = var.network_zone
+
+  ssh_whitelist        = var.ssh_whitelist
+  api_server_whitelist = var.api_server_whitelist
+  nodeport_whitelist   = var.nodeport_whitelist
+  ingress_whitelist    = var.ingress_whitelist
+}
+
+#
+# Generate ansible inventory
+#
+
+data "template_file" "inventory" {
+  template = file("${path.module}/templates/inventory.tpl")
+
+  vars = {
+    connection_strings_master = join("\n", formatlist("%s ansible_user=ubuntu ansible_host=%s ip=%s etcd_member_name=etcd%d",
+      keys(module.kubernetes.master_ip_addresses),
+      values(module.kubernetes.master_ip_addresses).*.public_ip,
+      values(module.kubernetes.master_ip_addresses).*.private_ip,
+    range(1, length(module.kubernetes.master_ip_addresses) + 1)))
+    connection_strings_worker = join("\n", formatlist("%s ansible_user=ubuntu ansible_host=%s ip=%s",
+      keys(module.kubernetes.worker_ip_addresses),
+      values(module.kubernetes.worker_ip_addresses).*.public_ip,
+    values(module.kubernetes.worker_ip_addresses).*.private_ip))
+    list_master = join("\n", keys(module.kubernetes.master_ip_addresses))
+    list_worker = join("\n", keys(module.kubernetes.worker_ip_addresses))
+    network_id = module.kubernetes.network_id
+  }
+}
+
+resource "null_resource" "inventories" {
+  provisioner "local-exec" {
+    command = "echo '${data.template_file.inventory.rendered}' > ${var.inventory_file}"
+  }
+
+  triggers = {
+    template = data.template_file.inventory.rendered
+  }
+}

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

@@ -0,0 +1,122 @@
+resource "hcloud_network" "kubernetes" {
+  name     = "${var.prefix}-network"
+  ip_range = var.private_network_cidr
+}
+
+resource "hcloud_network_subnet" "kubernetes" {
+  type         = "cloud"
+  network_id   = hcloud_network.kubernetes.id
+  network_zone = var.network_zone
+  ip_range     = var.private_subnet_cidr
+}
+
+resource "hcloud_server" "master" {
+  for_each = {
+    for name, machine in var.machines :
+    name => machine
+    if machine.node_type == "master"
+  }
+
+  name        = "${var.prefix}-${each.key}"
+  image       = each.value.image
+  server_type = each.value.size
+  location    = var.zone
+
+  user_data = templatefile(
+    "${path.module}/templates/cloud-init.tmpl",
+    {
+      ssh_public_keys = var.ssh_public_keys
+    }
+  )
+
+  firewall_ids = [hcloud_firewall.master.id]
+}
+
+resource "hcloud_server_network" "master" {
+  for_each = hcloud_server.master
+
+  server_id = each.value.id
+
+  subnet_id = hcloud_network_subnet.kubernetes.id
+}
+
+resource "hcloud_server" "worker" {
+  for_each = {
+    for name, machine in var.machines :
+    name => machine
+    if machine.node_type == "worker"
+  }
+
+  name        = "${var.prefix}-${each.key}"
+  image       = each.value.image
+  server_type = each.value.size
+  location    = var.zone
+
+  user_data = templatefile(
+    "${path.module}/templates/cloud-init.tmpl",
+    {
+      ssh_public_keys = var.ssh_public_keys
+    }
+  )
+
+  firewall_ids = [hcloud_firewall.worker.id]
+
+}
+
+resource "hcloud_server_network" "worker" {
+  for_each = hcloud_server.worker
+
+  server_id = each.value.id
+
+  subnet_id = hcloud_network_subnet.kubernetes.id
+}
+
+resource "hcloud_firewall" "master" {
+  name = "${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/output.tf

@@ -0,0 +1,27 @@
+output "master_ip_addresses" {
+  value = {
+    for key, instance in hcloud_server.master :
+    instance.name => {
+      "private_ip" = hcloud_server_network.master[key].ip
+      "public_ip"  = hcloud_server.master[key].ipv4_address
+    }
+  }
+}
+
+output "worker_ip_addresses" {
+  value = {
+    for key, instance in hcloud_server.worker :
+    instance.name => {
+      "private_ip" = hcloud_server_network.worker[key].ip
+      "public_ip"  = hcloud_server.worker[key].ipv4_address
+    }
+  }
+}
+
+output "cluster_private_network_cidr" {
+  value = var.private_subnet_cidr
+}
+
+output "network_id" {
+  value = hcloud_network.kubernetes.id
+}

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

@@ -0,0 +1,17 @@
+#cloud-config
+
+users:
+  - default
+  - name: ubuntu
+    shell: /bin/bash
+    sudo: "ALL=(ALL) NOPASSWD:ALL"
+    ssh_authorized_keys:
+    %{ for ssh_public_key in ssh_public_keys ~}
+      - ${ssh_public_key}
+    %{ endfor ~}
+
+ssh_authorized_keys:
+%{ for ssh_public_key in ssh_public_keys ~}
+  - ${ssh_public_key}
+%{ endfor ~}
+

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

@@ -0,0 +1,44 @@
+variable "zone" {
+  type = string
+}
+
+variable "prefix" {}
+
+variable "machines" {
+  type = map(object({
+    node_type = string
+    size      = string
+    image     = string
+  }))
+}
+
+variable "ssh_public_keys" {
+  type = list(string)
+}
+
+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/versions.tf

@@ -0,0 +1,9 @@
+terraform {
+  required_providers {
+    hcloud = {
+      source = "hetznercloud/hcloud"
+      version = "1.31.1"
+    }
+  }
+  required_version = ">= 0.14"
+}

contrib/terraform/hetzner/output.tf

@@ -0,0 +1,7 @@
+output "master_ips" {
+  value = module.kubernetes.master_ip_addresses
+}
+
+output "worker_ips" {
+  value = module.kubernetes.worker_ip_addresses
+}

contrib/terraform/hetzner/templates/inventory.tpl

@@ -0,0 +1,19 @@
+[all]
+${connection_strings_master}
+${connection_strings_worker}
+
+[kube_control_plane]
+${list_master}
+
+[etcd]
+${list_master}
+
+[kube_node]
+${list_worker}
+
+[k8s_cluster:children]
+kube-master
+kube-node
+
+[k8s_cluster:vars]
+network_id=${network_id}

contrib/terraform/hetzner/variables.tf

@@ -0,0 +1,50 @@
+variable "zone" {
+  description = "The zone where to run the cluster"
+}
+variable "network_zone" {
+  description = "The network zone where the cluster is running"
+  default = "eu-central"
+}
+
+variable "prefix" {
+  description = "Prefix for resource names"
+  default     = "default"
+}
+
+variable "machines" {
+  description = "Cluster machines"
+  type = map(object({
+    node_type = string
+    size      = string
+    image     = string
+  }))
+}
+
+variable "ssh_public_keys" {
+  description = "Public SSH key which are injected into the VMs."
+  type        = list(string)
+}
+
+variable "ssh_whitelist" {
+  description = "List of IP ranges (CIDR) to whitelist for ssh"
+  type        = list(string)
+}
+
+variable "api_server_whitelist" {
+  description = "List of IP ranges (CIDR) to whitelist for kubernetes api server"
+  type        = list(string)
+}
+
+variable "nodeport_whitelist" {
+  description = "List of IP ranges (CIDR) to whitelist for kubernetes nodeports"
+  type        = list(string)
+}
+
+variable "ingress_whitelist" {
+  description = "List of IP ranges (CIDR) to whitelist for HTTP"
+  type        = list(string)
+}
+
+variable "inventory_file" {
+  description = "Where to store the generated inventory file"
+}

contrib/terraform/hetzner/versions.tf

@@ -0,0 +1,15 @@
+terraform {
+  required_providers {
+    hcloud = {
+      source  = "hetznercloud/hcloud"
+      version = "1.31.1"
+    }
+    null = {
+      source = "hashicorp/null"
+    }
+    template = {
+      source = "hashicorp/template"
+    }
+  }
+  required_version = ">= 0.14"
+}

contrib/terraform/metal/README.md

@@ -1,16 +1,16 @@
-# Kubernetes on Packet with Terraform
+# Kubernetes on Equinix Metal with Terraform
 
 Provision a Kubernetes cluster with [Terraform](https://www.terraform.io) on
-[Packet](https://www.packet.com).
+[Equinix Metal](https://metal.equinix.com) ([formerly Packet](https://blog.equinix.com/blog/2020/10/06/equinix-metal-metal-and-more/)).
 
 ## Status
 
-This will install a Kubernetes cluster on Packet bare metal. It should work in all locations and on most server types.
+This will install a Kubernetes cluster on Equinix Metal. It should work in all locations and on most server types.
 
 ## Approach
 
 The terraform configuration inspects variables found in
-[variables.tf](variables.tf) to create resources in your Packet project.
+[variables.tf](variables.tf) to create resources in your Equinix Metal project.
 There is a [python script](../terraform.py) that reads the generated`.tfstate`
 file to generate a dynamic inventory that is consumed by [cluster.yml](../../..//cluster.yml)
 to actually install Kubernetes with Kubespray.
@@ -35,13 +35,13 @@ now six total etcd replicas.
 ## Requirements
 
 - [Install Terraform](https://www.terraform.io/intro/getting-started/install.html)
-- Install dependencies: `sudo pip install -r requirements.txt`
-- Account with Packet Host
+- [Install Ansible dependencies](/docs/ansible.md#installing-ansible)
+- Account with Equinix Metal
 - An SSH key pair
 
 ## SSH Key Setup
 
-An SSH keypair is required so Ansible can access the newly provisioned nodes (bare metal Packet hosts). By default, the public SSH key defined in cluster.tfvars will be installed in authorized_key on the newly provisioned nodes (~/.ssh/id_rsa.pub). Terraform will upload this public key and then it will be distributed out to all the nodes. If you have already set this public key in Packet (i.e. via the portal), then set the public keyfile name in cluster.tfvars to blank to prevent the duplicate key from being uploaded which will cause an error.
+An SSH keypair is required so Ansible can access the newly provisioned nodes (Equinix Metal hosts). By default, the public SSH key defined in cluster.tfvars will be installed in authorized_key on the newly provisioned nodes (~/.ssh/id_rsa.pub). Terraform will upload this public key and then it will be distributed out to all the nodes. If you have already set this public key in Equinix Metal (i.e. via the portal), then set the public keyfile name in cluster.tfvars to blank to prevent the duplicate key from being uploaded which will cause an error.
 
 If you don't already have a keypair generated (~/.ssh/id_rsa and ~/.ssh/id_rsa.pub), then a new keypair can be generated with the command:
 
@@ -51,7 +51,7 @@ ssh-keygen -f ~/.ssh/id_rsa
 
 ## Terraform
 
-Terraform will be used to provision all of the Packet resources with base software as appropriate.
+Terraform will be used to provision all of the Equinix Metal resources with base software as appropriate.
 
 ### Configuration
 
@@ -60,25 +60,25 @@ Terraform will be used to provision all of the Packet resources with base softwa
 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/packet/sample-inventory inventory/$CLUSTER
+cp -LRp contrib/terraform/metal/sample-inventory inventory/$CLUSTER
 cd inventory/$CLUSTER
-ln -s ../../contrib/terraform/packet/hosts
+ln -s ../../contrib/terraform/metal/hosts
 ```
 
 This will be the base for subsequent Terraform commands.
 
-#### Packet API access
+#### Equinix Metal API access
 
-Your Packet API key must be available in the `PACKET_AUTH_TOKEN` environment variable.
+Your Equinix Metal API key must be available in the `PACKET_AUTH_TOKEN` environment variable.
 This key is typically stored outside of the code repo since it is considered secret.
 If someone gets this key, they can startup/shutdown hosts in your project!
 
 For more information on how to generate an API key or find your project ID, please see
-[API Integrations](https://support.packet.com/kb/articles/api-integrations)
+[Accounts Index](https://metal.equinix.com/developers/docs/accounts/).
 
-The Packet Project ID associated with the key will be set later in cluster.tfvars.
+The Equinix Metal Project ID associated with the key will be set later in `cluster.tfvars`.
 
-For more information about the API, please see [Packet API](https://www.packet.com/developers/api/)
+For more information about the API, please see [Equinix Metal API](https://metal.equinix.com/developers/api/).
 
 Example:
 
@@ -101,7 +101,7 @@ 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
-- packet_project_id = the Packet Project ID associated with the Packet API token above
+- metal_project_id = the Equinix Metal Project ID associated with the Equinix Metal API token above
 
 #### Enable localhost access
 
@@ -119,7 +119,7 @@ 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/packet` directory :
+`.gitignore` file in the `terraform/metal` directory :
 
 - `.terraform`
 - `.tfvars`
@@ -135,7 +135,7 @@ plugins. This is accomplished as follows:
 
 ```ShellSession
 cd inventory/$CLUSTER
-terraform init ../../contrib/terraform/packet
+terraform init ../../contrib/terraform/metal
 ```
 
 This should finish fairly quickly telling you Terraform has successfully initialized and loaded necessary modules.
@@ -146,7 +146,7 @@ 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/packet
+terraform apply -var-file=cluster.tfvars ../../contrib/terraform/metal
 export ANSIBLE_HOST_KEY_CHECKING=False
 ansible-playbook -i hosts ../../cluster.yml
 ```
@@ -156,7 +156,7 @@ 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/packet
+terraform destroy -var-file=cluster.tfvars ../../contrib/terraform/metal
 ```
 
 If you've started the Ansible run, it may also be a good idea to do some manual cleanup: