Define ostree variable for runc (#9417)

The ostree variable is not defined previously raising an error when
the runtime tries to read it.

Co-authored-by: Victor Morales <chipahuac@hotmail.com>

.ansible-lint

@@ -2,15 +2,8 @@
 parseable: true
 skip_list:
   # see https://docs.ansible.com/ansible-lint/rules/default_rules.html for a list of all default rules
-  # The following rules throw errors.
-  # These either still need to be corrected in the repository and the rules re-enabled or documented why they are skipped on purpose.
-  - '301'
-  - '302'
-  - '303'
-  - '305'
-  - '306'
-  - '404'
-  - '503'
+
+  # DO NOT add any other rules to this skip_list, instead use local `# noqa` with a comment explaining WHY it is necessary
 
   # These rules are intentionally skipped:
   #
@@ -25,3 +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'

.editorconfig

@@ -0,0 +1,15 @@
+root = true
+
+[*.{yaml,yml,yml.j2,yaml.j2}]
+indent_style = space
+indent_size = 2
+trim_trailing_whitespace = true
+insert_final_newline = true
+charset = utf-8
+
+[{Dockerfile}]
+indent_style = space
+indent_size = 2
+trim_trailing_whitespace = true
+insert_final_newline = true
+charset = utf-8

.github/ISSUE_TEMPLATE/bug-report.md

@@ -18,6 +18,8 @@ explain why.
 
 - **Version of Ansible** (`ansible --version`):
 
+- **Version of Python** (`python --version`):
+
 
 **Kubespray version (commit) (`git rev-parse --short HEAD`):**
 
@@ -25,8 +27,8 @@ explain why.
 **Network plugin used**:
 
 
-**Copy of your inventory file:**
-
+**Full inventory with variables (`ansible -i inventory/sample/inventory.ini all -m debug -a "var=hostvars[inventory_hostname]"`):**
+<!-- We recommend using snippets services like https://gist.github.com/ etc. -->
 
 **Command used to invoke ansible**:
 

.github/ISSUE_TEMPLATE/support.md

@@ -1,7 +1,7 @@
 ---
 name: Support Request
 about: Support request or question relating to Kubespray
-labels: triage/support
+labels: kind/support
 
 ---
 

.github/PULL_REQUEST_TEMPLATE.md

@@ -1,9 +1,9 @@
 <!--  Thanks for sending a pull request!  Here are some tips for you:
 
-1. If this is your first time, please read our contributor guidelines: https://git.k8s.io/community/contributors/guide#your-first-contribution and developer guide https://git.k8s.io/community/contributors/devel/development.md#development-guide
+1. If this is your first time, please read our contributor guidelines: https://git.k8s.io/community/contributors/guide/first-contribution.md and developer guide https://git.k8s.io/community/contributors/devel/development.md
 2. Please label this pull request according to what type of issue you are addressing, especially if this is a release targeted pull request. For reference on required PR/issue labels, read here:
-https://git.k8s.io/community/contributors/devel/release.md#issue-kind-label
-3. Ensure you have added or ran the appropriate tests for your PR: https://git.k8s.io/community/contributors/devel/testing.md
+https://git.k8s.io/community/contributors/devel/sig-release/release.md#issuepr-kind-label
+3. Ensure you have added or ran the appropriate tests for your PR: https://git.k8s.io/community/contributors/devel/sig-testing/testing.md
 4. If you want *faster* PR reviews, read how: https://git.k8s.io/community/contributors/guide/pull-requests.md#best-practices-for-faster-reviews
 5. Follow the instructions for writing a release note: https://git.k8s.io/community/contributors/guide/release-notes.md
 6. If the PR is unfinished, see how to mark it: https://git.k8s.io/community/contributors/guide/pull-requests.md#marking-unfinished-pull-requests

.gitignore

@@ -1,6 +1,7 @@
 .vagrant
 *.retry
 **/vagrant_ansible_inventory
+*.iml
 temp
 .idea
 .tox
@@ -14,6 +15,7 @@ contrib/terraform/aws/credentials.tfvars
 **/*.sw[pon]
 *~
 vagrant/
+plugins/mitogen
 
 # Ansible inventory
 inventory/*
@@ -97,3 +99,12 @@ target/
 # virtualenv
 venv/
 ENV/
+
+# molecule
+roles/**/molecule/**/__pycache__/
+
+# macOS
+.DS_Store
+
+# Temp location used by our scripts
+scripts/tmp/

.gitlab-ci.yml

@@ -4,17 +4,19 @@ stages:
   - deploy-part1
   - moderator
   - deploy-part2
-  - deploy-gce
+  - deploy-part3
   - deploy-special
 
 variables:
+  KUBESPRAY_VERSION: v2.18.1
   FAILFASTCI_NAMESPACE: 'kargo-ci'
   GITLAB_REPOSITORY: 'kargo-ci/kubernetes-sigs-kubespray'
-  # DOCKER_HOST: tcp://localhost:2375
   ANSIBLE_FORCE_COLOR: "true"
   MAGIC: "ci check this"
   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: $GS_SECRET
   CONTAINER_ENGINE: docker
@@ -25,26 +27,34 @@ variables:
   ANSIBLE_INVENTORY: ./inventory/sample/${CI_JOB_NAME}-${BUILD_NUMBER}.ini
   IDEMPOT_CHECK: "false"
   RESET_CHECK: "false"
+  REMOVE_NODE_CHECK: "false"
   UPGRADE_TEST: "false"
-  LOG_LEVEL: "-vv"
+  MITOGEN_ENABLE: "false"
+  ANSIBLE_LOG_LEVEL: "-vv"
+  RECOVER_CONTROL_PLANE_TEST: "false"
+  RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:],kube_control_plane[1:]"
+  TERRAFORM_VERSION: 1.0.8
+  ANSIBLE_MAJOR_VERSION: "2.10"
 
 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
   tags:
     - packet
-  variables:
-    KUBESPRAY_VERSION: v2.11.0
   image: quay.io/kubespray/kubespray:$KUBESPRAY_VERSION
+  artifacts:
+    when: always
+    paths:
+      - cluster-dump/
 
 .testcases: &testcases
   <<: *job
-  services:
-    - docker:dind
+  retry: 1
   before_script:
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
     - ./tests/scripts/rebase.sh
@@ -52,7 +62,7 @@ before_script:
   script:
     - ./tests/scripts/testcases_run.sh
   after_script:
-    - ./tests/scripts/testcases_cleanup.sh
+    - chronic ./tests/scripts/testcases_cleanup.sh
 
 # For failfast, at least 1 job must be defined in .gitlab-ci.yml
 # Premoderated with manual actions
@@ -70,3 +80,5 @@ include:
   - .gitlab-ci/shellcheck.yml
   - .gitlab-ci/terraform.yml
   - .gitlab-ci/packet.yml
+  - .gitlab-ci/vagrant.yml
+  - .gitlab-ci/molecule.yml

.gitlab-ci/gce.yml

@@ -1,247 +0,0 @@
----
-.gce_variables: &gce_variables
-  GCE_USER: travis
-  SSH_USER: $GCE_USER
-  CLOUD_MACHINE_TYPE: "g1-small"
-  CI_PLATFORM: "gce"
-  PRIVATE_KEY: $GCE_PRIVATE_KEY
-
-.cache: &cache
-  cache:
-    key: "$CI_BUILD_REF_NAME"
-    paths:
-      - downloads/
-      - $HOME/.cache
-
-.gce: &gce
-  extends: .testcases
-  <<: *cache
-  variables:
-    <<: *gce_variables
-  tags:
-    - gce
-  except: ['triggers']
-  only: [/^pr-.*$/]
-
-.centos_weave_kubeadm_variables: &centos_weave_kubeadm_variables
-  # stage: deploy-part1
-  UPGRADE_TEST: "graceful"
-
-.centos7_multus_calico_variables: &centos7_multus_calico_variables
-  # stage: deploy-gce
-  UPGRADE_TEST: "graceful"
-
-# Builds for PRs only (premoderated by unit-tests step) and triggers (auto)
-### PR JOBS PART1
-
-gce_ubuntu18-flannel-aio:
-  stage: deploy-part1
-  <<: *gce
-  when: manual
-
-### PR JOBS PART2
-
-gce_coreos-calico-aio:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-
-gce_centos7-flannel-addons:
-  stage: deploy-gce
-  <<: *gce
-  when: manual
-
-### MANUAL JOBS
-
-gce_centos-weave-kubeadm-sep:
-  stage: deploy-gce
-  extends: .gce
-  variables:
-    <<: *centos_weave_kubeadm_variables
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_ubuntu-weave-sep:
-  stage: deploy-gce
-  <<: *gce
-  when: manual
-  only: ['triggers']
-  except: []
-
-gce_coreos-calico-sep-triggers:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_ubuntu-canal-ha-triggers:
-  stage: deploy-special
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_centos7-flannel-addons-triggers:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_ubuntu-weave-sep-triggers:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-# More builds for PRs/merges (manual) and triggers (auto)
-
-
-gce_ubuntu-canal-ha:
-  stage: deploy-special
-  <<: *gce
-  when: manual
-
-gce_ubuntu-canal-kubeadm:
-  stage: deploy-gce
-  <<: *gce
-  when: manual
-
-gce_ubuntu-canal-kubeadm-triggers:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_ubuntu-flannel-ha:
-  stage: deploy-gce
-  <<: *gce
-  when: manual
-
-gce_centos-weave-kubeadm-triggers:
-  stage: deploy-gce
-  extends: .gce
-  variables:
-    <<: *centos_weave_kubeadm_variables
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_ubuntu-contiv-sep:
-  stage: deploy-special
-  <<: *gce
-  when: manual
-
-gce_coreos-cilium:
-  stage: deploy-special
-  <<: *gce
-  when: manual
-
-gce_ubuntu18-cilium-sep:
-  stage: deploy-special
-  <<: *gce
-  when: manual
-
-gce_rhel7-weave:
-  stage: deploy-gce
-  <<: *gce
-  when: manual
-
-gce_rhel7-weave-triggers:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_debian9-calico-upgrade:
-  stage: deploy-gce
-  <<: *gce
-  when: manual
-
-gce_debian9-calico-triggers:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_coreos-canal:
-  stage: deploy-gce
-  <<: *gce
-  when: manual
-
-gce_coreos-canal-triggers:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_rhel7-canal-sep:
-  stage: deploy-special
-  <<: *gce
-  when: manual
-
-gce_rhel7-canal-sep-triggers:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_centos7-calico-ha:
-  stage: deploy-special
-  <<: *gce
-  when: manual
-
-gce_centos7-calico-ha-triggers:
-  stage: deploy-gce
-  <<: *gce
-  when: on_success
-  only: ['triggers']
-  except: []
-
-gce_centos7-kube-router:
-  stage: deploy-special
-  <<: *gce
-  when: manual
-
-gce_centos7-multus-calico:
-  stage: deploy-gce
-  extends: .gce
-  variables:
-    <<: *centos7_multus_calico_variables
-  when: manual
-
-gce_oracle-canal:
-  stage: deploy-gce
-  <<: *gce
-  when: manual
-  except: ['triggers']
-  only: ['master', /^pr-.*$/]
-
-gce_opensuse-canal:
-  stage: deploy-gce
-  <<: *gce
-  when: manual
-
-# no triggers yet https://github.com/kubernetes-incubator/kargo/issues/613
-gce_coreos-alpha-weave-ha:
-  stage: deploy-special
-  <<: *gce
-  when: manual
-
-gce_coreos-kube-router:
-  stage: deploy-special
-  <<: *gce
-  when: manual
-
-gce_ubuntu-kube-router-sep:
-  stage: deploy-special
-  <<: *gce
-  when: manual

.gitlab-ci/lint.yml

@@ -2,6 +2,7 @@
 yamllint:
   extends: .job
   stage: unit-tests
+  tags: [light]
   variables:
     LANG: C.UTF-8
   script:
@@ -11,23 +12,25 @@ yamllint:
 vagrant-validate:
   extends: .job
   stage: unit-tests
+  tags: [light]
+  variables:
+    VAGRANT_VERSION: 2.2.19
   script:
-    - curl -sL https://releases.hashicorp.com/vagrant/2.2.4/vagrant_2.2.4_x86_64.deb -o /tmp/vagrant_2.2.4_x86_64.deb
-    - dpkg -i /tmp/vagrant_2.2.4_x86_64.deb
-    - vagrant validate --ignore-provider
+    - ./tests/scripts/vagrant-validate.sh
   except: ['triggers', 'master']
 
 ansible-lint:
   extends: .job
   stage: unit-tests
-  # 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
+  tags: [light]
+  script:
+    - ansible-lint -v
   except: ['triggers', 'master']
 
 syntax-check:
   extends: .job
   stage: unit-tests
+  tags: [light]
   variables:
     ANSIBLE_INVENTORY: inventory/local-tests.cfg
     ANSIBLE_REMOTE_USER: root
@@ -43,11 +46,13 @@ syntax-check:
 
 tox-inventory-builder:
   stage: unit-tests
+  tags: [light]
   extends: .job
   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
   script:
     - pip3 install tox
@@ -56,8 +61,16 @@ tox-inventory-builder:
 
 markdownlint:
   stage: unit-tests
+  tags: [light]
   image: node
   before_script:
-    - npm install -g markdownlint-cli
+    - npm install -g markdownlint-cli@0.22.0
   script:
-    - markdownlint README.md docs --ignore docs/_sidebar.md
+    - markdownlint $(find . -name '*.md' | grep -vF './.git') --ignore docs/_sidebar.md --ignore contrib/dind/README.md
+
+ci-matrix:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/md-table/test.sh

.gitlab-ci/molecule.yml

@@ -0,0 +1,93 @@
+---
+
+.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/docker
+  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
+
+molecule_cri-dockerd:
+  extends: .molecule
+  stage: deploy-part2
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/cri-dockerd
+  when: on_success
+
+# Stage 3 container engines don't get as much attention so allow them to fail
+molecule_kata:
+  extends: .molecule
+  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

@@ -1,126 +1,315 @@
 ---
-.packet: &packet
+.packet:
   extends: .testcases
   variables:
-    CI_PLATFORM: "packet"
-    SSH_USER: "kubespray"
+    ANSIBLE_TIMEOUT: "120"
+    CI_PLATFORM: packet
+    SSH_USER: kubespray
   tags:
     - packet
-  only: [/^pr-.*$/]
-  except: ['triggers']
+  except: [triggers]
 
-packet_ubuntu18-calico-aio:
-  stage: deploy-part1
+# CI template for PRs
+.packet_pr:
+  only: [/^pr-.*$/]
   extends: .packet
+
+# CI template for periodic CI jobs
+# Enabled when PERIODIC_CI_ENABLED var is set
+.packet_periodic:
+  only:
+    variables:
+      - $PERIODIC_CI_ENABLED
+  allow_failure: true
+  extends: .packet
+
+# The ubuntu20-calico-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"
+
+# Exericse ansible variants during the nightly jobs
+packet_ubuntu20-calico-aio-ansible-2_9:
+  stage: deploy-part1
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    ANSIBLE_MAJOR_VERSION: "2.9"
+    RESET_CHECK: "true"
+
+packet_ubuntu20-calico-aio-ansible-2_10:
+  stage: deploy-part1
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    ANSIBLE_MAJOR_VERSION: "2.10"
+    RESET_CHECK: "true"
+
+packet_ubuntu20-calico-aio-ansible-2_11:
+  stage: deploy-part1
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    ANSIBLE_MAJOR_VERSION: "2.11"
+    RESET_CHECK: "true"
 
 # ### PR JOBS PART2
 
-packet_centos7-flannel-addons:
-  extends: .packet
+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_ubuntu18-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
 
+packet_almalinux8-crio:
+  extends: .packet_pr
+  stage: deploy-part2
+  when: on_success
+
+packet_ubuntu18-crio:
+  extends: .packet_pr
+  stage: deploy-part2
+  when: manual
+
+packet_fedora35-crio:
+  extends: .packet_pr
+  stage: deploy-part2
+  when: manual
+
+packet_ubuntu16-canal-ha:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_ubuntu16-canal-sep:
+  stage: deploy-special
+  extends: .packet_pr
+  when: manual
+
+packet_ubuntu16-flannel-ha:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_debian10-cilium-svc-proxy:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_debian10-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian10-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian11-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_debian11-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_centos7-calico-ha-once-localhost:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+  variables:
+    # This will instruct Docker not to start over TLS.
+    DOCKER_TLS_CERTDIR: ""
+  services:
+    - docker:19.03.9-dind
+
+packet_almalinux8-kube-ovn:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_almalinux8-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_almalinux8-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_fedora34-docker-weave:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_opensuse-canal:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_opensuse-docker-cilium:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
 # ### MANUAL JOBS
 
-packet_centos-weave-kubeadm-sep:
+packet_ubuntu16-docker-weave-sep:
   stage: deploy-part2
-  extends: .packet
-  when: on_success
-  variables:
-    UPGRADE_TEST: basic
-
-packet_ubuntu-weave-sep:
-  stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-# # More builds for PRs/merges (manual) and triggers (auto)
-
-packet_ubuntu-canal-ha:
-  stage: deploy-special
-  extends: .packet
-  when: manual
-
-packet_ubuntu-canal-kubeadm:
-  stage: deploy-part2
-  extends: .packet
-  when: on_success
-
-packet_ubuntu-flannel-ha:
-  stage: deploy-part2
-  extends: .packet
-  when: manual
-
-# Contiv does not work in k8s v1.16
-# packet_ubuntu-contiv-sep:
-#   stage: deploy-part2
-#   extends: .packet
-#   when: on_success
-
 packet_ubuntu18-cilium-sep:
   stage: deploy-special
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-packet_ubuntu18-flannel-containerd:
+packet_ubuntu18-flannel-ha:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-packet_debian9-macvlan-sep:
+packet_ubuntu18-flannel-ha-once:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-packet_debian9-calico-upgrade:
+# Calico HA eBPF
+packet_almalinux8-calico-ha-ebpf:
   stage: deploy-part2
-  extends: .packet
-  when: on_success
-  variables:
-    UPGRADE_TEST: graceful
+  extends: .packet_pr
+  when: manual
 
-packet_debian10-containerd:
+packet_debian9-macvlan:
   stage: deploy-part2
-  extends: .packet
-  when: on_success
+  extends: .packet_pr
+  when: manual
 
 packet_centos7-calico-ha:
   stage: deploy-part2
-  extends: .packet
-  when: manual
-
-packet_centos7-kube-ovn:
-  stage: deploy-part2
-  extends: .packet
-  when: on_success
-
-packet_centos7-kube-router:
-  stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
 packet_centos7-multus-calico:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-packet_opensuse-canal:
+packet_oracle7-canal-ha:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-packet_oracle-7-canal:
+packet_fedora35-docker-calico:
   stage: deploy-part2
-  extends: .packet
-  when: manual
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    RESET_CHECK: "true"
 
-packet_ubuntu-kube-router-sep:
+packet_fedora34-calico-selinux:
   stage: deploy-part2
-  extends: .packet
+  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
+  extends: .packet_pr
   when: manual
+
+packet_almalinux8-calico-nodelocaldns-secondary:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_fedora34-kube-ovn:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+# ### PR JOBS PART3
+# Long jobs (45min+)
+
+packet_centos7-docker-weave-upgrade-ha:
+  stage: deploy-part3
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    UPGRADE_TEST: basic
+
+packet_ubuntu20-calico-etcd-kubeadm-upgrade-ha:
+  stage: deploy-part3
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    UPGRADE_TEST: basic
+
+# Calico HA Wireguard
+packet_ubuntu20-calico-ha-wireguard:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_debian10-calico-upgrade:
+  stage: deploy-part3
+  extends: .packet_pr
+  when: on_success
+  variables:
+    UPGRADE_TEST: graceful
+
+packet_almalinux8-calico-remove-node:
+  stage: deploy-part3
+  extends: .packet_pr
+  when: on_success
+  variables:
+    REMOVE_NODE_CHECK: "true"
+    REMOVE_NODE_NAME: "instance-3"
+
+packet_debian10-calico-upgrade-once:
+  stage: deploy-part3
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    UPGRADE_TEST: graceful
+
+packet_ubuntu18-calico-ha-recover:
+  stage: deploy-part3
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    RECOVER_CONTROL_PLANE_TEST: "true"
+    RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:],kube_control_plane[1:]"
+
+packet_ubuntu18-calico-ha-recover-noquorum:
+  stage: deploy-part3
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    RECOVER_CONTROL_PLANE_TEST: "true"
+    RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[1:],kube_control_plane[1:]"

.gitlab-ci/shellcheck.yml

@@ -2,14 +2,15 @@
 shellcheck:
   extends: .job
   stage: unit-tests
+  tags: [light]
   variables:
-    SHELLCHECK_VERSION: v0.6.0
+    SHELLCHECK_VERSION: v0.7.1
   before_script:
     - ./tests/scripts/rebase.sh
-    - curl --silent "https://storage.googleapis.com/shellcheck/shellcheck-"${SHELLCHECK_VERSION}".linux.x86_64.tar.xz" | tar -xJv
+    - curl --silent --location "https://github.com/koalaman/shellcheck/releases/download/"${SHELLCHECK_VERSION}"/shellcheck-"${SHELLCHECK_VERSION}".linux.x86_64.tar.xz" | tar -xJv
     - cp shellcheck-"${SHELLCHECK_VERSION}"/shellcheck /usr/bin/
     - shellcheck --version
   script:
     # Run shellcheck for all *.sh except contrib/
-    - find . -name '*.sh' -not -path './contrib/*' | xargs shellcheck --severity error
+    - find . -name '*.sh' -not -path './contrib/*' -not -path './.git/*' | xargs shellcheck --severity error
   except: ['triggers', 'master']

.gitlab-ci/terraform.yml

@@ -12,26 +12,35 @@
     # 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 contrib/terraform/$PROVIDER/group_vars
+    # Random subnet to avoid routing conflicts
+    - export TF_VAR_subnet_cidr="10.$(( $RANDOM % 256 )).$(( $RANDOM % 256 )).0/24"
 
 .terraform_validate:
   extends: .terraform_install
   stage: unit-tests
+  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
-  stage: deploy-part2
+  tags: [light]
+  stage: deploy-part3
   when: manual
   only: [/^pr-.*$/]
+  artifacts:
+    when: always
+    paths:
+      - cluster-dump/
   variables:
     ANSIBLE_INVENTORY_UNPARSED_FAILED: "true"
     ANSIBLE_INVENTORY: hosts
@@ -42,33 +51,53 @@
     - tests/scripts/testcases_run.sh
   after_script:
     # Cleanup regardless of exit code
-    - ./tests/scripts/testcases_cleanup.sh
+    - chronic ./tests/scripts/testcases_cleanup.sh
 
 tf-validate-openstack:
   extends: .terraform_validate
   variables:
-    TF_VERSION: 0.12.12
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: openstack
     CLUSTER: $CI_COMMIT_REF_NAME
 
-tf-validate-packet:
+tf-validate-metal:
   extends: .terraform_validate
   variables:
-    TF_VERSION: 0.12.12
-    PROVIDER: packet
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: metal
     CLUSTER: $CI_COMMIT_REF_NAME
 
 tf-validate-aws:
   extends: .terraform_validate
   variables:
-    TF_VERSION: 0.12.12
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: aws
     CLUSTER: $CI_COMMIT_REF_NAME
 
+tf-validate-exoscale:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: exoscale
+
+tf-validate-vsphere:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: vsphere
+    CLUSTER: $CI_COMMIT_REF_NAME
+
+tf-validate-upcloud:
+  extends: .terraform_validate
+  variables:
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: upcloud
+    CLUSTER: $CI_COMMIT_REF_NAME
+
 # tf-packet-ubuntu16-default:
 #   extends: .terraform_apply
 #   variables:
-#     TF_VERSION: 0.12.12
+#     TF_VERSION: $TERRAFORM_VERSION
 #     PROVIDER: packet
 #     CLUSTER: $CI_COMMIT_REF_NAME
 #     TF_VAR_number_of_k8s_masters: "1"
@@ -82,7 +111,7 @@ tf-validate-aws:
 # tf-packet-ubuntu18-default:
 #   extends: .terraform_apply
 #   variables:
-#     TF_VERSION: 0.12.12
+#     TF_VERSION: $TERRAFORM_VERSION
 #     PROVIDER: packet
 #     CLUSTER: $CI_COMMIT_REF_NAME
 #     TF_VAR_number_of_k8s_masters: "1"
@@ -104,58 +133,103 @@ tf-validate-aws:
   OS_INTERFACE: public
   OS_IDENTITY_API_VERSION: "3"
 
-tf-ovh_ubuntu18-calico:
-  extends: .terraform_apply
-  when: on_success
+# Elastx is generously donating resources for Kubespray on Openstack CI
+# Contacts: @gix @bl0m1
+.elastx_variables: &elastx_variables
+  OS_AUTH_URL: https://ops.elastx.cloud:5000
+  OS_PROJECT_ID: 564c6b461c6b44b1bb19cdb9c2d928e4
+  OS_PROJECT_NAME: kubespray_ci
+  OS_USER_DOMAIN_NAME: Default
+  OS_PROJECT_DOMAIN_ID: default
+  OS_USERNAME: kubespray@root314.com
+  OS_REGION_NAME: se-sto
+  OS_INTERFACE: public
+  OS_IDENTITY_API_VERSION: "3"
+  TF_VAR_router_id: "ab95917c-41fb-4881-b507-3a6dfe9403df"
+
+tf-elastx_cleanup:
+  stage: unit-tests
+  tags: [light]
+  image: python
   variables:
-    <<: *ovh_variables
-    TF_VERSION: 0.12.12
+    <<: *elastx_variables
+  before_script:
+    - pip install -r scripts/openstack-cleanup/requirements.txt
+  script:
+    - ./scripts/openstack-cleanup/main.py
+
+tf-elastx_ubuntu18-calico:
+  extends: .terraform_apply
+  stage: deploy-part3
+  when: on_success
+  allow_failure: true
+  variables:
+    <<: *elastx_variables
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: openstack
     CLUSTER: $CI_COMMIT_REF_NAME
     ANSIBLE_TIMEOUT: "60"
     SSH_USER: ubuntu
-    TF_VAR_number_of_k8s_masters: "0"
-    TF_VAR_number_of_k8s_masters_no_floating_ip: "1"
+    TF_VAR_number_of_k8s_masters: "1"
+    TF_VAR_number_of_k8s_masters_no_floating_ip: "0"
     TF_VAR_number_of_k8s_masters_no_floating_ip_no_etcd: "0"
     TF_VAR_number_of_etcd: "0"
-    TF_VAR_number_of_k8s_nodes: "0"
-    TF_VAR_number_of_k8s_nodes_no_floating_ip: "1"
+    TF_VAR_number_of_k8s_nodes: "1"
+    TF_VAR_number_of_k8s_nodes_no_floating_ip: "0"
     TF_VAR_number_of_gfs_nodes_no_floating_ip: "0"
     TF_VAR_number_of_bastions: "0"
     TF_VAR_number_of_k8s_masters_no_etcd: "0"
-    TF_VAR_use_neutron: "0"
-    TF_VAR_floatingip_pool: "Ext-Net"
-    TF_VAR_external_net: "6011fbc9-4cbf-46a4-8452-6890a340b60b"
-    TF_VAR_network_name: "Ext-Net"
-    TF_VAR_flavor_k8s_master: "defa64c3-bd46-43b4-858a-d93bbae0a229"    # s1-8
-    TF_VAR_flavor_k8s_node: "defa64c3-bd46-43b4-858a-d93bbae0a229"      # s1-8
-    TF_VAR_image: "Ubuntu 18.04"
+    TF_VAR_floatingip_pool: "elx-public1"
+    TF_VAR_dns_nameservers: '["1.1.1.1", "8.8.8.8", "8.8.4.4"]'
+    TF_VAR_use_access_ip: "0"
+    TF_VAR_external_net: "600b8501-78cb-4155-9c9f-23dfcba88828"
+    TF_VAR_network_name: "ci-$CI_JOB_ID"
+    TF_VAR_az_list: '["sto1"]'
+    TF_VAR_az_list_node: '["sto1"]'
+    TF_VAR_flavor_k8s_master: 3f73fc93-ec61-4808-88df-2580d94c1a9b    # v1-standard-2
+    TF_VAR_flavor_k8s_node: 3f73fc93-ec61-4808-88df-2580d94c1a9b      # v1-standard-2
+    TF_VAR_image: ubuntu-18.04-server-latest
     TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'
 
-tf-ovh_coreos-calico:
-  extends: .terraform_apply
-  when: on_success
-  variables:
-    <<: *ovh_variables
-    TF_VERSION: 0.12.12
-    PROVIDER: openstack
-    CLUSTER: $CI_COMMIT_REF_NAME
-    ANSIBLE_TIMEOUT: "60"
-    SSH_USER: core
-    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: "4d4fd037-9493-4f2b-9afe-b542b5248eac"    # b2-7
-    TF_VAR_flavor_k8s_node: "4d4fd037-9493-4f2b-9afe-b542b5248eac"      # b2-7
-    TF_VAR_image: "CoreOS Stable"
-    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_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

@@ -0,0 +1,66 @@
+---
+
+.vagrant:
+  extends: .testcases
+  variables:
+    CI_PLATFORM: "vagrant"
+    SSH_USER: "vagrant"
+    VAGRANT_DEFAULT_PROVIDER: "libvirt"
+    KUBESPRAY_VAGRANT_CONFIG: tests/files/${CI_JOB_NAME}.rb
+  tags: [c3.small.x86]
+  only: [/^pr-.*$/]
+  except: ['triggers']
+  image: quay.io/kubespray/vagrant:$KUBESPRAY_VERSION
+  services: []
+  before_script:
+    - apt-get update && apt-get install -y python3-pip
+    - update-alternatives --install /usr/bin/python python /usr/bin/python3 10
+    - python -m pip uninstall -y ansible ansible-base ansible-core
+    - python -m pip install -r tests/requirements.txt
+    - ./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
+  extends: .vagrant
+  when: on_success
+
+vagrant_ubuntu18-flannel:
+  stage: deploy-part2
+  extends: .vagrant
+  when: on_success
+
+vagrant_ubuntu18-weave-medium:
+  stage: deploy-part2
+  extends: .vagrant
+  when: manual
+
+vagrant_ubuntu20-flannel:
+  stage: deploy-part2
+  extends: .vagrant
+  when: on_success
+
+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

.yamllint

@@ -1,6 +1,9 @@
 ---
 extends: default
 
+ignore: |
+  .git/
+
 rules:
   braces:
     min-spaces-inside: 0

CONTRIBUTING.md

@@ -2,10 +2,38 @@
 
 ## How to become a contributor and submit your own code
 
+### Environment setup
+
+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 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`. It is a good idea to add call these tools as part of your pre-commit hook and avoid a lot of back end forth on fixing linting issues (<https://support.gitkraken.com/working-with-repositories/githooksexample/>).
+
+#### Molecule
+
+[molecule](https://github.com/ansible-community/molecule) is designed to help the development and testing of Ansible roles. In Kubespray you can run it all for all roles with `./tests/scripts/molecule_run.sh` or for a specific role (that you are working with) with `molecule test` from the role directory (`cd roles/my-role`).
+
+When developing or debugging a role it can be useful to run `molecule create` and `molecule converge` separately. Then you can use `molecule login` to SSH into the test environment.
+
+#### Vagrant
+
+Vagrant with VirtualBox or libvirt driver helps you to quickly spin test clusters to test things end to end. See [README.md#vagrant](README.md)
+
 ### Contributing A Patch
 
 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)
+4. Sign the CNCF CLA (<https://git.k8s.io/community/CLA.md#the-contributor-license-agreement>)
 5. Submit a pull request.
+6. Work with the reviewers on their suggestions.
+7. Ensure to rebase to the HEAD of your target branch and squash un-necessary commits (<https://blog.carbonfive.com/always-squash-and-rebase-your-git-commits/>) before final merger of your contribution.

Dockerfile

@@ -1,18 +1,37 @@
-FROM ubuntu:18.04
+# Use imutable image tags rather than mutable tags (like ubuntu:20.04)
+FROM ubuntu:focal-20220316
+
+ARG ARCH=amd64
+ARG TZ=Etc/UTC
+RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
+
+RUN apt update -y \
+    && apt install -y \
+    libssl-dev python3-dev sshpass apt-transport-https jq moreutils \
+    ca-certificates curl gnupg2 software-properties-common python3-pip unzip rsync git \
+    && rm -rf /var/lib/apt/lists/*
+RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add - \
+    && add-apt-repository \
+    "deb [arch=$ARCH] https://download.docker.com/linux/ubuntu \
+    $(lsb_release -cs) \
+    stable" \
+    && apt update -y && apt-get install --no-install-recommends -y docker-ce \
+    && rm -rf /var/lib/apt/lists/*
+
+# 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
 
-RUN mkdir /kubespray
 WORKDIR /kubespray
-RUN apt update -y && \
-    apt install -y \
-    libssl-dev python3-dev sshpass apt-transport-https jq \
-    ca-certificates curl gnupg2 software-properties-common python3-pip rsync
-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 \
-     $(lsb_release -cs) \
-     stable" \
-     && apt update -y && apt-get install docker-ce -y
 COPY . .
-RUN /usr/bin/python3 -m pip install pip -U && /usr/bin/python3 -m pip install -r tests/requirements.txt && python3 -m pip install -r requirements.txt && update-alternatives --install /usr/bin/python python /usr/bin/python3 1
-RUN curl -LO https://storage.googleapis.com/kubernetes-release/release/v1.14.4/bin/linux/amd64/kubectl \
-    && chmod a+x kubectl && cp kubectl /usr/local/bin/kubectl
+RUN /usr/bin/python3 -m pip install --no-cache-dir pip -U \
+    && /usr/bin/python3 -m pip install --no-cache-dir -r tests/requirements.txt \
+    && python3 -m pip install --no-cache-dir -r requirements.txt \
+    && update-alternatives --install /usr/bin/python python /usr/bin/python3 1
+
+RUN KUBE_VERSION=$(sed -n 's/^kube_version: //p' roles/kubespray-defaults/defaults/main.yaml) \
+    && curl -LO https://storage.googleapis.com/kubernetes-release/release/$KUBE_VERSION/bin/linux/$ARCH/kubectl \
+    && chmod a+x kubectl \
+    && mv kubectl /usr/local/bin/kubectl

Makefile

@@ -1,5 +1,7 @@
 mitogen:
-	ansible-playbook -c local mitogen.yaml -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

@@ -4,3 +4,5 @@ approvers:
   - kubespray-approvers
 reviewers:
   - kubespray-reviewers
+emeritus_approvers:
+  - kubespray-emeritus_approvers

OWNERS_ALIASES

@@ -1,15 +1,23 @@
 aliases:
   kubespray-approvers:
-    - ant31
     - mattymo
-    - atoms
     - chadswen
     - mirwan
     - miouge1
-    - riverzhang
-    - verwilst
-    - woopstar
+    - luckysb
+    - floryut
+    - oomichi
+    - cristicalin
   kubespray-reviewers:
-    - jjungnickel
-    - archifleks
     - holmsten
+    - bozzo
+    - eppo
+    - oomichi
+    - jayonlau
+    - cristicalin
+    - liupeng0518
+  kubespray-emeritus_approvers:
+    - riverzhang
+    - atoms
+    - ant31
+    - woopstar

README.md

@@ -2,10 +2,10 @@
 
 ![Kubernetes Logo](https://raw.githubusercontent.com/kubernetes-sigs/kubespray/master/docs/img/kubernetes-logo.png)
 
-If you have questions, check the [documentation](https://kubespray.io) and join us on the [kubernetes slack](https://kubernetes.slack.com), channel **\#kubespray**.
+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, GCE, Azure, OpenStack, vSphere, Packet (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**
@@ -19,26 +19,26 @@ To deploy the cluster you can use :
 
 #### Usage
 
-```ShellSession
-# Install dependencies from ``requirements.txt``
-sudo pip 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
 
 # Update Ansible inventory file with inventory builder
 declare -a IPS=(10.10.1.3 10.10.1.4 10.10.1.5)
-CONFIG_FILE=inventory/mycluster/inventory.ini python3 contrib/inventory_builder/inventory.py ${IPS[@]}
+CONFIG_FILE=inventory/mycluster/hosts.yaml python3 contrib/inventory_builder/inventory.py ${IPS[@]}
 
 # Review and change parameters under ``inventory/mycluster/group_vars``
 cat inventory/mycluster/group_vars/all/all.yml
-cat inventory/mycluster/group_vars/k8s-cluster/k8s-cluster.yml
+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/,
 # installing packages and interacting with various systemd daemons.
 # Without --become the playbook will fail to run!
-ansible-playbook -i inventory/mycluster/inventory.ini --become --become-user=root cluster.yml
+ansible-playbook -i inventory/mycluster/hosts.yaml  --become --become-user=root cluster.yml
 ```
 
 Note: When Ansible is already installed via system packages on the control machine, other python packages installed via `sudo pip install -r requirements.txt` will go to a different directory tree (e.g. `/usr/local/lib/python2.7/dist-packages` on Ubuntu) from Ansible's (e.g. `/usr/lib/python2.7/dist-packages/ansible` still on Ubuntu).
@@ -48,11 +48,23 @@ As a consequence, `ansible-playbook` command will fail with:
 ERROR! no action detected in task. This often indicates a misspelled module name, or incorrect module path.
 ```
 
-probably pointing on a task depending on a module present in requirements.txt (i.e. "unseal vault").
+probably pointing on a task depending on a module present in requirements.txt.
 
 One way of solving this would be to uninstall the Ansible package and then, to install it via pip but it is not always possible.
 A workaround consists of setting `ANSIBLE_LIBRARY` and `ANSIBLE_MODULE_UTILS` environment variables respectively to the `ansible/modules` and `ansible/module_utils` subdirectories of pip packages installation location, which can be found in the Location field of the output of `pip show [package]` before executing `ansible-playbook`.
 
+A simple way to ensure you get all the correct version of Ansible is to use the [pre-built docker image from Quay](https://quay.io/repository/kubespray/kubespray?tab=tags).
+You will then need to use [bind mounts](https://docs.docker.com/storage/bind-mounts/) to get the inventory and ssh key into the container, like this:
+
+```ShellSession
+docker pull quay.io/kubespray/kubespray:v2.19.1
+docker run --rm -it --mount type=bind,source="$(pwd)"/inventory/sample,dst=/inventory \
+  --mount type=bind,source="${HOME}"/.ssh/id_rsa,dst=/root/.ssh/id_rsa \
+  quay.io/kubespray/kubespray:v2.19.1 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
+```
+
 ### Vagrant
 
 For Vagrant we need to install python dependencies for provisioning tasks.
@@ -63,10 +75,11 @@ 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
 ```
 
@@ -75,6 +88,7 @@ vagrant up
 - [Requirements](#requirements)
 - [Kubespray vs ...](docs/comparisons.md)
 - [Getting started](docs/getting-started.md)
+- [Setting up your first cluster](docs/setting-up-your-first-cluster.md)
 - [Ansible inventory and tags](docs/ansible.md)
 - [Integration with existing ansible repo](docs/integration.md)
 - [Deployment data variables](docs/vars.md)
@@ -82,7 +96,8 @@ vagrant up
 - [HA mode](docs/ha-mode.md)
 - [Network plugins](#network-plugins)
 - [Vagrant install](docs/vagrant.md)
-- [CoreOS bootstrap](docs/coreos.md)
+- [Flatcar Container Linux bootstrap](docs/flatcar.md)
+- [Fedora CoreOS bootstrap](docs/fcos.md)
 - [Debian Jessie setup](docs/debian.md)
 - [openSUSE setup](docs/opensuse.md)
 - [Downloaded artifacts](docs/downloads.md)
@@ -91,58 +106,67 @@ 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)
+- [Hardening](docs/hardening.md)
 - [Roadmap](docs/roadmap.md)
 
 ## Supported Linux Distributions
 
-- **Container Linux by CoreOS**
-- **Debian** Buster, Jessie, Stretch, Wheezy
-- **Ubuntu** 16.04, 18.04
-- **CentOS/RHEL** 7
-- **Fedora** 28
-- **Fedora/CentOS** Atomic
-- **openSUSE** Leap 42.3/Tumbleweed
-- **Oracle Linux** 7
+- **Flatcar Container Linux by Kinvolk**
+- **Debian** Bullseye, Buster, Jessie, Stretch
+- **Ubuntu** 16.04, 18.04, 20.04
+- **CentOS/RHEL** 7, [8](docs/centos8.md)
+- **Fedora** 34, 35
+- **Fedora CoreOS** (see [fcos Note](docs/fcos.md))
+- **openSUSE** Leap 15.x/Tumbleweed
+- **Oracle Linux** 7, [8](docs/centos8.md)
+- **Alma Linux** [8](docs/centos8.md)
+- **Rocky Linux** [8](docs/centos8.md)
+- **Amazon Linux 2** (experimental: see [amazon linux notes](docs/amazonlinux.md))
 
 Note: Upstart/SysV init based OS types are not supported.
 
 ## Supported Components
 
 - Core
-  - [kubernetes](https://github.com/kubernetes/kubernetes) v1.16.3
-  - [etcd](https://github.com/coreos/etcd) v3.3.10
-  - [docker](https://www.docker.com/) v18.06 (see note)
-  - [cri-o](http://cri-o.io/) v1.14.0 (experimental: see [CRI-O Note](docs/cri-o.md). Only on centos based OS)
+  - [kubernetes](https://github.com/kubernetes/kubernetes) v1.23.7
+  - [etcd](https://github.com/etcd-io/etcd) v3.5.3
+  - [docker](https://www.docker.com/) v20.10 (see note)
+  - [containerd](https://containerd.io/) v1.6.4
+  - [cri-o](http://cri-o.io/) v1.22 (experimental: see [CRI-O Note](docs/cri-o.md). Only on fedora, ubuntu and centos based OS)
 - Network Plugin
-  - [cni-plugins](https://github.com/containernetworking/plugins) v0.8.1
-  - [calico](https://github.com/projectcalico/calico) v3.7.3
+  - [cni-plugins](https://github.com/containernetworking/plugins) v1.1.1
+  - [calico](https://github.com/projectcalico/calico) v3.22.3
   - [canal](https://github.com/projectcalico/canal) (given calico/flannel versions)
-  - [cilium](https://github.com/cilium/cilium) v1.5.5
-  - [contiv](https://github.com/contiv/install) v1.2.1
-  - [flanneld](https://github.com/coreos/flannel) v0.11.0
-  - [kube-router](https://github.com/cloudnativelabs/kube-router) v0.2.5
-  - [multus](https://github.com/intel/multus-cni) v3.2.1
-  - [weave](https://github.com/weaveworks/weave) v2.5.2
+  - [cilium](https://github.com/cilium/cilium) v1.11.3
+  - [flanneld](https://github.com/flannel-io/flannel) v0.17.0
+  - [kube-ovn](https://github.com/alauda/kube-ovn) v1.9.2
+  - [kube-router](https://github.com/cloudnativelabs/kube-router) v1.4.0
+  - [multus](https://github.com/intel/multus-cni) v3.8
+  - [weave](https://github.com/weaveworks/weave) v2.8.1
 - Application
   - [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) v0.11.0
-  - [coredns](https://github.com/coredns/coredns) v1.6.0
-  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v0.26.1
+  - [cert-manager](https://github.com/jetstack/cert-manager) v1.8.0
+  - [coredns](https://github.com/coredns/coredns) v1.8.6
+  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v1.2.1
 
-Note: The list of validated [docker versions](https://github.com/kubernetes/kubernetes/blob/master/CHANGELOG-1.16.md) was updated to 1.13.1, 17.03, 17.06, 17.09, 18.06, 18.09. kubeadm now properly recognizes Docker 18.09.0 and newer, but still treats 18.06 as the default supported version. 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).
+## Container Runtime Notes
+
+- The list of available docker version is 18.09, 19.03 and 20.10. The recommended docker version is 20.10. The kubelet might break on docker's non-standard version numbering (it no longer uses semantic versioning). To ensure auto-updates don't break your cluster look into e.g. yum versionlock plugin or apt pin).
+- 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 v1.15**
-- **Ansible v2.7.8 and python-netaddr is installed on the machine that will run Ansible commands**
-- **Jinja 2.9 (or newer) is required to run the Ansible Playbooks**
-- The target servers must have **access to the Internet** in order to pull docker images. Otherwise, additional configuration is required (See [Offline Environment](https://github.com/kubernetes-sigs/kubespray/blob/master/docs/downloads.md#offline-environment))
+- **Minimum required version of Kubernetes is v1.21**
+- **Ansible v2.9.x, Jinja 2.11+ and python-netaddr is installed on the machine that will run Ansible commands**
+- 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**.
-- **Your ssh key must be copied** to all the servers part of your inventory.
+- If using IPv6 for pods and services, the target servers are configured to allow **IPv6 forwarding**.
 - The **firewalls are not managed**, you'll need to implement your own rules the way you used to.
     in order to avoid any issue during deployment you should disable your firewall.
 - If kubespray is ran from non-root user account, correct privilege escalation method
@@ -163,15 +187,15 @@ You can choose between 10 network plugins. (default: `calico`, except Vagrant us
 
 - [flannel](docs/flannel.md): gre/vxlan (layer 2) networking.
 
-- [calico](docs/calico.md): bgp (layer 3) networking.
+- [Calico](https://docs.projectcalico.org/latest/introduction/) is a networking and network policy provider. Calico supports a flexible set of networking options
+    designed to give you the most efficient networking across a range of situations, including non-overlay
+    and overlay networks, with or without BGP. Calico uses the same engine to enforce network policy for hosts,
+    pods, and (if using Istio and Envoy) applications at the service mesh layer.
 
 - [canal](https://github.com/projectcalico/canal): a composition of calico and flannel plugins.
 
 - [cilium](http://docs.cilium.io/en/latest/): layer 3/4 networking (as well as layer 7 to protect and secure application protocols), supports dynamic insertion of BPF bytecode into the Linux kernel to implement security services, networking and visibility logic.
 
-- [contiv](docs/contiv.md): supports vlan, vxlan, bgp and Cisco SDN networking. This plugin is able to
-    apply firewall policies, segregate containers in multiple network and bridging pods onto physical networks.
-
 - [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/)).
 
@@ -190,12 +214,18 @@ The choice is defined with the variable `kube_network_plugin`. There is also an
 option to leverage built-in cloud provider networking instead.
 See also [Network checker](docs/netcheck.md).
 
+## Ingress Plugins
+
+- [nginx](https://kubernetes.github.io/ingress-nginx): the NGINX Ingress Controller.
+
+- [metallb](docs/metallb.md): the MetalLB bare-metal service LoadBalancer provider.
+
 ## Community docs and resources
 
 - [kubernetes.io/docs/setup/production-environment/tools/kubespray/](https://kubernetes.io/docs/setup/production-environment/tools/kubespray/)
 - [kubespray, monitoring and logging](https://github.com/gregbkr/kubernetes-kargo-logging-monitoring) by @gregbkr
 - [Deploy Kubernetes w/ Ansible & Terraform](https://rsmitty.github.io/Terraform-Ansible-Kubernetes/) by @rsmitty
-- [Deploy a Kubernetes Cluster with Kubespray (video)](https://www.youtube.com/watch?v=N9q51JgbWu8)
+- [Deploy a Kubernetes Cluster with Kubespray (video)](https://www.youtube.com/watch?v=CJ5G4GpqDy0)
 
 ## Tools and projects on top of Kubespray
 
@@ -204,7 +234,8 @@ See also [Network checker](docs/netcheck.md).
 
 ## CI Tests
 
-[![Build graphs](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/badges/master/build.svg)](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/pipelines)
+[![Build graphs](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/badges/master/pipeline.svg)](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/pipelines)
+
+CI/end-to-end tests sponsored by: [CNCF](https://cncf.io), [Equinix Metal](https://metal.equinix.com/), [OVHcloud](https://www.ovhcloud.com/), [ELASTX](https://elastx.se/).
 
-CI/end-to-end tests sponsored by Google (GCE)
 See the [test matrix](docs/test_cases.md) for details.

RELEASE.md

@@ -2,42 +2,62 @@
 
 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. 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
-4. An approver creates a release branch in the form `release-vX.Y`
-5. The corresponding version of [quay.io/kubespray/kubespray:vX.Y.Z](https://quay.io/repository/kubespray/kubespray) docker image is built and tagged
-6. The `KUBESPRAY_VERSION` variable is updated in `.gitlab-ci.yml`
-7. The release issue is closed
-8. An announcement email is sent to `kubernetes-dev@googlegroups.com` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
+3. The `kube_version_min_required` variable is set to `n-1`
+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) docker images are built and tagged
+9. The `KUBESPRAY_VERSION` variable is updated in `.gitlab-ci.yml`
+10. The release issue is closed
+11. An announcement email is sent to `kubernetes-dev@googlegroups.com` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
+12. The topic of the #kubespray channel is updated with `vX.Y.Z is released! | ...`
 
-## Major/minor releases, merge freezes and milestones
+## Major/minor releases and milestones
 
-* Kubespray maintains one branch for major releases (vX.Y). Minor releases are available only as tags.
+* For major releases (vX.Y) Kubespray maintains one branch (`release-X.Y`). Minor releases (vX.Y.Z) are available only as tags.
 
 * Security patches and bugs might be backported.
 
-* Fixes for major releases (vX.x.0) and minor releases (vX.Y.x) are delivered
+* Fixes for major releases (vX.Y) and minor releases (vX.Y.Z) are delivered
   via maintenance releases (vX.Y.Z) and assigned to the corresponding open
-  milestone (vX.Y). That milestone remains open for the major/minor releases
-  support lifetime, which ends once the milestone closed. Then only a next major
-  or minor release can be done.
+  [GitHub milestone](https://github.com/kubernetes-sigs/kubespray/milestones).
+  That milestone remains open for the major/minor releases support lifetime,
+  which ends once the milestone is closed. Then only a next major or minor release
+  can be done.
 
-* Kubespray major and minor releases are bound to the given ``kube_version`` major/minor
+* Kubespray major and minor releases are bound to the given `kube_version` major/minor
   version numbers and other components' arbitrary versions, like etcd or network plugins.
-  Older or newer versions are not supported and not tested for the given release.
+  Older or newer component versions are not supported and not tested for the given
+  release (even if included in the checksum variables, like `kubeadm_checksums`).
 
 * There is no unstable releases and no APIs, thus Kubespray doesn't follow
-  [semver](http://semver.org/). Every version describes only a stable release.
+  [semver](https://semver.org/). Every version describes only a stable release.
   Breaking changes, if any introduced by changed defaults or non-contrib ansible roles'
   playbooks, shall be described in the release notes. Other breaking changes, if any in
   the contributed addons or bound versions of Kubernetes and other components, are
   considered out of Kubespray scope and are up to the components' teams to deal with and
   document.
 
-* Minor releases can change components' versions, but not the major ``kube_version``.
-  Greater ``kube_version`` requires a new major or minor release. For example, if Kubespray v2.0.0
-  is bound to ``kube_version: 1.4.x``, ``calico_version: 0.22.0``, ``etcd_version: v3.0.6``,
-  then Kubespray v2.1.0 may be bound to only minor changes to ``kube_version``, like v1.5.1
+* Minor releases can change components' versions, but not the major `kube_version`.
+  Greater `kube_version` requires a new major or minor release. For example, if Kubespray v2.0.0
+  is bound to `kube_version: 1.4.x`, `calico_version: 0.22.0`, `etcd_version: v3.0.6`,
+  then Kubespray v2.1.0 may be bound to only minor changes to `kube_version`, like v1.5.1
   and *any* changes to other components, like etcd v4, or calico 1.2.3.
-  And Kubespray v3.x.x shall be bound to ``kube_version: 2.x.x`` respectively.
+  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)

SECURITY_CONTACTS

@@ -1,13 +1,13 @@
 # Defined below are the security contacts for this repo.
 #
-# They are the contact point for the Product Security Team to reach out
+# They are the contact point for the Product Security Committee to reach out
 # to for triaging and handling of incoming issues.
 #
 # The below names agree to abide by the
-# [Embargo Policy](https://github.com/kubernetes/sig-release/blob/master/security-release-process-documentation/security-release-process.md#embargo-policy)
+# [Embargo Policy](https://git.k8s.io/security/private-distributors-list.md#embargo-policy)
 # and will be removed and replaced if they violate that agreement.
 #
 # DO NOT REPORT SECURITY VULNERABILITIES DIRECTLY TO THESE NAMES, FOLLOW THE
 # INSTRUCTIONS AT https://kubernetes.io/security/
 atoms
-mattymo
+mattymo

Vagrantfile

@@ -7,63 +7,80 @@ require 'fileutils'
 
 Vagrant.require_version ">= 2.0.0"
 
-CONFIG = File.join(File.dirname(__FILE__), "vagrant/config.rb")
+CONFIG = File.join(File.dirname(__FILE__), ENV['KUBESPRAY_VAGRANT_CONFIG'] || 'vagrant/config.rb')
 
-COREOS_URL_TEMPLATE = "https://storage.googleapis.com/%s.release.core-os.net/amd64-usr/current/coreos_production_vagrant.json"
+FLATCAR_URL_TEMPLATE = "https://%s.release.flatcar-linux.net/amd64-usr/current/flatcar_production_vagrant.json"
 
 # Uniq disk UUID for libvirt
 DISK_UUID = Time.now.utc.to_i
 
 SUPPORTED_OS = {
-  "coreos-stable"       => {box: "coreos-stable",      user: "core", box_url: COREOS_URL_TEMPLATE % ["stable"]},
-  "coreos-alpha"        => {box: "coreos-alpha",       user: "core", box_url: COREOS_URL_TEMPLATE % ["alpha"]},
-  "coreos-beta"         => {box: "coreos-beta",        user: "core", box_url: COREOS_URL_TEMPLATE % ["beta"]},
-  "ubuntu1604"          => {box: "generic/ubuntu1604", user: "vagrant"},
-  "ubuntu1804"          => {box: "generic/ubuntu1804", user: "vagrant"},
-  "centos"              => {box: "centos/7",           user: "vagrant"},
-  "centos-bento"        => {box: "bento/centos-7.6",   user: "vagrant"},
-  "fedora"              => {box: "fedora/28-cloud-base",                user: "vagrant"},
-  "opensuse"            => {box: "opensuse/openSUSE-15.0-x86_64",       user: "vagrant"},
-  "opensuse-tumbleweed" => {box: "opensuse/openSUSE-Tumbleweed-x86_64", user: "vagrant"},
-  "oraclelinux"         => {box: "generic/oracle7", user: "vagrant"},
+  "flatcar-stable"      => {box: "flatcar-stable",             user: "core", box_url: FLATCAR_URL_TEMPLATE % ["stable"]},
+  "flatcar-beta"        => {box: "flatcar-beta",               user: "core", box_url: FLATCAR_URL_TEMPLATE % ["beta"]},
+  "flatcar-alpha"       => {box: "flatcar-alpha",              user: "core", box_url: FLATCAR_URL_TEMPLATE % ["alpha"]},
+  "flatcar-edge"        => {box: "flatcar-edge",               user: "core", box_url: FLATCAR_URL_TEMPLATE % ["edge"]},
+  "ubuntu1604"          => {box: "generic/ubuntu1604",         user: "vagrant"},
+  "ubuntu1804"          => {box: "generic/ubuntu1804",         user: "vagrant"},
+  "ubuntu2004"          => {box: "generic/ubuntu2004",         user: "vagrant"},
+  "centos"              => {box: "centos/7",                   user: "vagrant"},
+  "centos-bento"        => {box: "bento/centos-7.6",           user: "vagrant"},
+  "centos8"             => {box: "centos/8",                   user: "vagrant"},
+  "centos8-bento"       => {box: "bento/centos-8",             user: "vagrant"},
+  "almalinux8"          => {box: "almalinux/8",                user: "vagrant"},
+  "almalinux8-bento"    => {box: "bento/almalinux-8",          user: "vagrant"},
+  "fedora34"            => {box: "fedora/34-cloud-base",       user: "vagrant"},
+  "fedora35"            => {box: "fedora/35-cloud-base",       user: "vagrant"},
+  "opensuse"            => {box: "opensuse/Leap-15.3.x86_64",  user: "vagrant"},
+  "opensuse-tumbleweed" => {box: "opensuse/Tumbleweed.x86_64", user: "vagrant"},
+  "oraclelinux"         => {box: "generic/oracle7",            user: "vagrant"},
+  "oraclelinux8"        => {box: "generic/oracle8",            user: "vagrant"},
+  "rhel7"               => {box: "generic/rhel7",              user: "vagrant"},
+  "rhel8"               => {box: "generic/rhel8",              user: "vagrant"},
 }
 
-# Defaults for config options defined in CONFIG
-$num_instances = 3
-$instance_name_prefix = "k8s"
-$vm_gui = false
-$vm_memory = 2048
-$vm_cpus = 1
-$shared_folders = {}
-$forwarded_ports = {}
-$subnet = "172.17.8"
-$os = "ubuntu1804"
-$network_plugin = "flannel"
-# Setting multi_networking to true will install Multus: https://github.com/intel/multus-cni
-$multi_networking = false
-# The first three nodes are etcd servers
-$etcd_instances = $num_instances
-# The first two nodes are kube masters
-$kube_master_instances = $num_instances == 1 ? $num_instances : ($num_instances - 1)
-# All nodes are kube nodes
-$kube_node_instances = $num_instances
-# The following only works when using the libvirt provider
-$kube_node_instances_with_disks = false
-$kube_node_instances_with_disks_size = "20G"
-$kube_node_instances_with_disks_number = 2
-$override_disk_size = false
-$disk_size = "20GB"
-$local_path_provisioner_enabled = false
-$local_path_provisioner_claim_root = "/opt/local-path-provisioner/"
-
-$playbook = "cluster.yml"
-
-host_vars = {}
-
 if File.exist?(CONFIG)
   require CONFIG
 end
 
+# Defaults for config options defined in CONFIG
+$num_instances ||= 3
+$instance_name_prefix ||= "k8s"
+$vm_gui ||= false
+$vm_memory ||= 2048
+$vm_cpus ||= 2
+$shared_folders ||= {}
+$forwarded_ports ||= {}
+$subnet ||= "172.18.8"
+$subnet_ipv6 ||= "fd3c:b398:0698:0756"
+$os ||= "ubuntu1804"
+$network_plugin ||= "flannel"
+# Setting multi_networking to true will install Multus: https://github.com/intel/multus-cni
+$multi_networking ||= "False"
+$download_run_once ||= "True"
+$download_force_cache ||= "False"
+# The first three nodes are etcd servers
+$etcd_instances ||= $num_instances
+# The first two nodes are kube masters
+$kube_master_instances ||= $num_instances == 1 ? $num_instances : ($num_instances - 1)
+# All nodes are kube nodes
+$kube_node_instances ||= $num_instances
+# The following only works when using the libvirt provider
+$kube_node_instances_with_disks ||= false
+$kube_node_instances_with_disks_size ||= "20G"
+$kube_node_instances_with_disks_number ||= 2
+$override_disk_size ||= false
+$disk_size ||= "20GB"
+$local_path_provisioner_enabled ||= "False"
+$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"
+
+host_vars = {}
+
 $box = SUPPORTED_OS[$os][:box]
 # if $inventory is not set, try to use example
 $inventory = "inventory/sample" if ! $inventory
@@ -74,16 +91,16 @@ $inventory = File.absolute_path($inventory, File.dirname(__FILE__))
 if ! File.exist?(File.join(File.dirname($inventory), "hosts.ini"))
   $vagrant_ansible = File.join(File.dirname(__FILE__), ".vagrant", "provisioners", "ansible")
   FileUtils.mkdir_p($vagrant_ansible) if ! File.exist?($vagrant_ansible)
-  if ! File.exist?(File.join($vagrant_ansible,"inventory"))
-    FileUtils.ln_s($inventory, File.join($vagrant_ansible,"inventory"))
-  end
+  $vagrant_inventory = File.join($vagrant_ansible,"inventory")
+  FileUtils.rm_f($vagrant_inventory)
+  FileUtils.ln_s($inventory, $vagrant_inventory)
 end
 
 if Vagrant.has_plugin?("vagrant-proxyconf")
-    $no_proxy = ENV['NO_PROXY'] || ENV['no_proxy'] || "127.0.0.1,localhost"
-    (1..$num_instances).each do |i|
-        $no_proxy += ",#{$subnet}.#{i+100}"
-    end
+  $no_proxy = ENV['NO_PROXY'] || ENV['no_proxy'] || "127.0.0.1,localhost"
+  (1..$num_instances).each do |i|
+      $no_proxy += ",#{$subnet}.#{i+100}"
+  end
 end
 
 Vagrant.configure("2") do |config|
@@ -133,9 +150,12 @@ Vagrant.configure("2") do |config|
         vb.gui = $vm_gui
         vb.linked_clone = true
         vb.customize ["modifyvm", :id, "--vram", "8"] # ubuntu defaults to 256 MB which is a waste of precious RAM
+        vb.customize ["modifyvm", :id, "--audio", "none"]
       end
 
       node.vm.provider :libvirt do |lv|
+        lv.nested = $libvirt_nested
+        lv.cpu_mode = "host-model"
         lv.memory = $vm_memory
         lv.cpus = $vm_cpus
         lv.default_prefix = 'kubespray'
@@ -152,7 +172,7 @@ Vagrant.configure("2") do |config|
           # always make /dev/sd{a/b/c} so that CI can ensure that
           # virtualbox and libvirt will have the same devices to use for OSDs
           (1..$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
@@ -165,30 +185,55 @@ Vagrant.configure("2") do |config|
         node.vm.network "forwarded_port", guest: guest, host: host, auto_correct: true
       end
 
-      node.vm.synced_folder ".", "/vagrant", disabled: false, type: "rsync", rsync__args: ['--verbose', '--archive', '--delete', '-z'] , rsync__exclude: ['.git','venv']
-      $shared_folders.each do |src, dst|
-        node.vm.synced_folder src, dst, type: "rsync", rsync__args: ['--verbose', '--archive', '--delete', '-z']
+      if ["rhel7","rhel8"].include? $os
+        # Vagrant synced_folder rsync options cannot be used for RHEL boxes as Rsync package cannot
+        # be installed until the host is registered with a valid Red Hat support subscription
+        node.vm.synced_folder ".", "/vagrant", disabled: false
+        $shared_folders.each do |src, dst|
+          node.vm.synced_folder src, dst
+        end
+      else
+        node.vm.synced_folder ".", "/vagrant", disabled: false, type: "rsync", rsync__args: ['--verbose', '--archive', '--delete', '-z'] , rsync__exclude: ['.git','venv']
+        $shared_folders.each do |src, dst|
+          node.vm.synced_folder src, dst, type: "rsync", rsync__args: ['--verbose', '--archive', '--delete', '-z']
+        end
       end
 
       ip = "#{$subnet}.#{i+100}"
-      node.vm.network :private_network, ip: ip
+      node.vm.network :private_network, ip: ip,
+        :libvirt__guest_ipv6 => 'yes',
+        :libvirt__ipv6_address => "#{$subnet_ipv6}::#{i+100}",
+        :libvirt__ipv6_prefix => "64",
+        :libvirt__forward_mode => "none",
+        :libvirt__dhcp_enabled => false
 
       # Disable swap for each vm
       node.vm.provision "shell", inline: "swapoff -a"
 
+      # ubuntu1804 and ubuntu2004 have IPv6 explicitly disabled. This undoes that.
+      if ["ubuntu1804", "ubuntu2004"].include? $os
+        node.vm.provision "shell", inline: "rm -f /etc/modprobe.d/local.conf"
+        node.vm.provision "shell", inline: "sed -i '/net.ipv6.conf.all.disable_ipv6/d' /etc/sysctl.d/99-sysctl.conf /etc/sysctl.conf"
+      end
+
+      # Disable firewalld on oraclelinux/redhat vms
+      if ["oraclelinux","oraclelinux8","rhel7","rhel8"].include? $os
+        node.vm.provision "shell", inline: "systemctl stop firewalld; systemctl disable firewalld"
+      end
+
       host_vars[vm_name] = {
         "ip": ip,
         "flannel_interface": "eth1",
         "kube_network_plugin": $network_plugin,
         "kube_network_plugin_multus": $multi_networking,
-        "download_run_once": "True",
+        "download_run_once": $download_run_once,
         "download_localhost": "False",
         "download_cache_dir": ENV['HOME'] + "/kubespray_cache",
         # Make kubespray cache even when download_run_once is false
-        "download_force_cache": "True",
+        "download_force_cache": $download_force_cache,
         # Keeping the cache on the nodes can improve provisioning speed while debugging kubespray
         "download_keep_remote_cache": "False",
-        "docker_keepcache": "1",
+        "docker_rpm_keepcache": "1",
         # These two settings will put kubectl and admin.config in $inventory/artifacts
         "kubeconfig_localhost": "True",
         "kubectl_localhost": "True",
@@ -198,9 +243,11 @@ 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 = $ansible_inventory_path
@@ -210,12 +257,14 @@ Vagrant.configure("2") do |config|
           ansible.host_key_checking = false
           ansible.raw_arguments = ["--forks=#{$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-master" => ["#{$instance_name_prefix}-[1:#{$kube_master_instances}]"],
-            "kube-node" => ["#{$instance_name_prefix}-[1:#{$kube_node_instances}]"],
-            "k8s-cluster:children" => ["kube-master", "kube-node"],
+            "kube_control_plane" => ["#{$instance_name_prefix}-[1:#{$kube_master_instances}]"],
+            "kube_node" => ["#{$instance_name_prefix}-[1:#{$kube_node_instances}]"],
+            "k8s_cluster:children" => ["kube_control_plane", "kube_node"],
           }
         end
       end

_config.yml

@@ -1,2 +1,2 @@
 ---
-theme: jekyll-theme-slate
+theme: jekyll-theme-slate

ansible.cfg

@@ -3,7 +3,6 @@ pipelining=True
 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
 
@@ -11,9 +10,11 @@ host_key_checking=False
 gathering = smart
 fact_caching = jsonfile
 fact_caching_connection = /tmp
-stdout_callback = skippy
+fact_caching_timeout = 7200
+stdout_callback = default
+display_skipped_hosts = no
 library = ./library
-callback_whitelist = profile_tasks
+callback_whitelist = 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

@@ -0,0 +1,45 @@
+---
+- hosts: localhost
+  gather_facts: false
+  become: no
+  vars:
+    minimal_ansible_version: 2.9.0
+    minimal_ansible_version_2_10: 2.10.11
+    maximal_ansible_version: 2.13.0
+    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 }}"
+        that:
+          - ansible_version.string is version(minimal_ansible_version, ">=")
+          - ansible_version.string is version(maximal_ansible_version, "<")
+      tags:
+        - check
+
+    - name: "Check Ansible version > {{ minimal_ansible_version_2_10 }} when using ansible 2.10"
+      assert:
+        msg: "When using Ansible 2.10, the minimum supported version is {{ minimal_ansible_version_2_10 }}"
+        that:
+          - ansible_version.string is version(minimal_ansible_version_2_10, ">=")
+          - ansible_version.string is version(maximal_ansible_version, "<")
+      when:
+        - ansible_version.string is version('2.10.0', ">=")
+      tags:
+        - check
+
+    - name: "Check that python netaddr is installed"
+      assert:
+        msg: "Python netaddr is not present"
+        that: "'127.0.0.1' | ipaddr"
+      tags:
+        - check
+
+    # CentOS 7 provides too old jinja version
+    - name: "Check that jinja is not too old (install via pip)"
+      assert:
+        msg: "Your Jinja version is too old, install via pip"
+        that: "{% set test %}It works{% endset %}{{ test == 'It works' }}"
+      tags:
+        - check

cluster.yml

@@ -1,116 +1,128 @@
 ---
-- hosts: localhost
-  gather_facts: false
-  become: no
-  tasks:
-    - name: "Check ansible version >=2.7.8"
-      assert:
-        msg: "Ansible must be v2.7.8 or higher"
-        that:
-          - ansible_version.string is version("2.7.8", ">=")
-      tags:
-        - check
-  vars:
-    ansible_connection: local
+- name: Check ansible version
+  import_playbook: ansible_version.yml
+
+- name: Ensure compatibility with old groups
+  import_playbook: legacy_groups.yml
 
 - hosts: bastion[0]
   gather_facts: False
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
-    - { role: bastion-ssh-config, tags: ["localhost", "bastion"]}
+    - { role: kubespray-defaults }
+    - { role: bastion-ssh-config, tags: ["localhost", "bastion"] }
 
-- hosts: k8s-cluster:etcd
+- hosts: k8s_cluster:etcd
+  strategy: linear
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
   gather_facts: false
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
+    - { role: kubespray-defaults }
     - { role: bootstrap-os, tags: bootstrap-os}
 
-- hosts: k8s-cluster:etcd
+- name: Gather facts
+  tags: always
+  import_playbook: facts.yml
+
+- hosts: k8s_cluster:etcd
+  gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
+    - { role: 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" }
-  environment: "{{ proxy_env }}"
 
 - hosts: etcd
+  gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
+    - { role: kubespray-defaults }
     - role: etcd
       tags: etcd
       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
+- hosts: k8s_cluster
+  gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
+    - { role: kubespray-defaults }
     - role: etcd
       tags: etcd
       vars:
         etcd_cluster_setup: false
         etcd_events_cluster_setup: false
-      when: not etcd_kubeadm_enabled| default(false)
+      when: etcd_deployment_type != "kubeadm"
 
-- hosts: k8s-cluster
+- hosts: k8s_cluster
+  gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
+    - { role: kubespray-defaults }
     - { role: kubernetes/node, tags: node }
-  environment: "{{ proxy_env }}"
 
-- hosts: kube-master
+- 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/master, tags: master }
+    - { role: kubespray-defaults }
+    - { role: kubernetes/control-plane, tags: master }
     - { role: kubernetes/client, tags: client }
     - { role: kubernetes-apps/cluster_roles, tags: cluster-roles }
 
-- hosts: k8s-cluster
+- hosts: k8s_cluster
+  gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
+    - { role: kubespray-defaults }
     - { role: kubernetes/kubeadm, tags: kubeadm}
+    - { role: kubernetes/node-label, tags: node-label }
     - { role: network_plugin, tags: network }
-    - { role: kubernetes/node-label }
 
-- hosts: calico-rr
+- hosts: calico_rr
+  gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
-    - { role: network_plugin/calico/rr, tags: ['network', 'calico_rr']}
+    - { role: kubespray-defaults }
+    - { role: network_plugin/calico/rr, tags: ['network', 'calico_rr'] }
 
-- hosts: kube-master[0]
+- hosts: kube_control_plane[0]
+  gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
-    - { role: kubernetes-apps/rotate_tokens, tags: rotate_tokens, when: "secret_changed|default(false)" }
-    - { role: win_nodes/kubernetes_patch, tags: ["master", "win_nodes"]}
+    - { role: kubespray-defaults }
+    - { role: win_nodes/kubernetes_patch, tags: ["master", "win_nodes"] }
 
-- hosts: kube-master
+- hosts: kube_control_plane
+  gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
-    - { role: kubespray-defaults}
+    - { role: kubespray-defaults }
+    - { role: kubernetes-apps/external_cloud_controller, tags: external-cloud-controller }
     - { role: kubernetes-apps/network_plugin, tags: network }
     - { role: kubernetes-apps/policy_controller, tags: policy-controller }
     - { role: kubernetes-apps/ingress_controller, tags: ingress-controller }
     - { role: kubernetes-apps/external_provisioner, tags: external-provisioner }
-
-- hosts: kube-master
-  any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
-  roles:
-    - { role: kubespray-defaults}
     - { role: kubernetes-apps, tags: apps }
-  environment: "{{ proxy_env }}"
 
-- 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 }}"
   roles:
-    - { role: kubespray-defaults}
+    - { role: kubespray-defaults }
     - { role: kubernetes/preinstall, when: "dns_mode != 'none' and resolvconf_mode == 'host_resolvconf'", tags: resolvconf, dns_late: true }

contrib/aws_inventory/kubespray-aws-inventory.py

@@ -35,7 +35,7 @@ class SearchEC2Tags(object):
     hosts['_meta'] = { 'hostvars': {} }
 
     ##Search ec2 three times to find nodes of each group type. Relies on kubespray-role key/value.
-    for group in ["kube-master", "kube-node", "etcd"]:
+    for group in ["kube_control_plane", "kube_node", "etcd"]:
       hosts[group] = []
       tag_key = "kubespray-role"
       tag_value = ["*"+group+"*"]
@@ -69,8 +69,8 @@ class SearchEC2Tags(object):
 
         hosts[group].append(dns_name)
         hosts['_meta']['hostvars'][dns_name] = ansible_host
-        
-    hosts['k8s-cluster'] = {'children':['kube-master', 'kube-node']}
+
+    hosts['k8s_cluster'] = {'children':['kube_control_plane', 'kube_node']}
     print(json.dumps(hosts, sort_keys=True, indent=2))
 
 SearchEC2Tags()

contrib/aws_inventory/requirements.txt

@@ -0,0 +1 @@
+boto3  # Apache-2.0

contrib/azurerm/README.md

@@ -15,22 +15,23 @@ Resource Group. It will not install Kubernetes itself, this has to be done in a
 
 ## Configuration through group_vars/all
 
-You have to modify at least one variable in group_vars/all, which is the **cluster_name** variable. It must be globally
-unique due to some restrictions in Azure. Most other variables should be self explanatory if you have some basic Kubernetes
+You have to modify at least two variables in group_vars/all. The one is the **cluster_name** variable, it must be globally
+unique due to some restrictions in Azure. The other one is the **ssh_public_keys** variable, it must be your ssh public
+key to access your azure virtual machines. Most other variables should be self explanatory if you have some basic Kubernetes
 experience.
 
 ## Bastion host
 
 You can enable the use of a Bastion Host by changing **use_bastion** in group_vars/all to **true**. The generated
 templates will then include an additional bastion VM which can then be used to connect to the masters and nodes. The option
-also removes all public IPs from all other VMs. 
+also removes all public IPs from all other VMs.
 
 ## Generating and applying
 
 To generate and apply the templates, call:
 
 ```shell
-$ ./apply-rg.sh <resource_group_name>
+./apply-rg.sh <resource_group_name>
 ```
 
 If you change something in the configuration (e.g. number of nodes) later, you can call this again and Azure will
@@ -41,24 +42,26 @@ take care about creating/modifying whatever is needed.
 If you need to delete all resources from a resource group, simply call:
 
 ```shell
-$ ./clear-rg.sh <resource_group_name>
+./clear-rg.sh <resource_group_name>
 ```
 
 **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:
 
 ```shell
-$ ./generate-inventory.sh <resource_group_name>
+./generate-inventory.sh <resource_group_name>
 ```
 
 It will create the file ./inventory which can then be used with kubespray, e.g.:
 
 ```shell
-$ cd kubespray-root-dir
-$ ansible-playbook -i contrib/azurerm/inventory -u devops --become -e "@inventory/sample/group_vars/all.yml" cluster.yml
+cd kubespray-root-dir
+ansible-playbook -i contrib/azurerm/inventory -u devops --become -e "@inventory/sample/group_vars/all/all.yml" cluster.yml
 ```
-

contrib/azurerm/apply-rg.sh

@@ -9,18 +9,11 @@ if [ "$AZURE_RESOURCE_GROUP" == "" ]; then
     exit 1
 fi
 
-if az &>/dev/null; then
-    echo "azure cli 2.0 found, using it instead of 1.0"
-    ./apply-rg_2.sh "$AZURE_RESOURCE_GROUP"
-elif azure &>/dev/null; then 
-    ansible-playbook generate-templates.yml
-    
-    azure group deployment create -f ./.generated/network.json -g $AZURE_RESOURCE_GROUP
-    azure group deployment create -f ./.generated/storage.json -g $AZURE_RESOURCE_GROUP
-    azure group deployment create -f ./.generated/availability-sets.json -g $AZURE_RESOURCE_GROUP
-    azure group deployment create -f ./.generated/bastion.json -g $AZURE_RESOURCE_GROUP
-    azure group deployment create -f ./.generated/masters.json -g $AZURE_RESOURCE_GROUP
-    azure group deployment create -f ./.generated/minions.json -g $AZURE_RESOURCE_GROUP
-else 
-    echo "Azure cli not found"
-fi
+ansible-playbook generate-templates.yml
+
+az deployment group create --template-file ./.generated/network.json -g $AZURE_RESOURCE_GROUP
+az deployment group create --template-file ./.generated/storage.json -g $AZURE_RESOURCE_GROUP
+az deployment group create --template-file ./.generated/availability-sets.json -g $AZURE_RESOURCE_GROUP
+az deployment group create --template-file ./.generated/bastion.json -g $AZURE_RESOURCE_GROUP
+az deployment group create --template-file ./.generated/masters.json -g $AZURE_RESOURCE_GROUP
+az deployment group create --template-file ./.generated/minions.json -g $AZURE_RESOURCE_GROUP

contrib/azurerm/apply-rg_2.sh

@@ -1,19 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-AZURE_RESOURCE_GROUP="$1"
-
-if [ "$AZURE_RESOURCE_GROUP" == "" ]; then
-    echo "AZURE_RESOURCE_GROUP is missing"
-    exit 1
-fi
-
-ansible-playbook generate-templates.yml
-
-az group deployment create --template-file ./.generated/network.json -g $AZURE_RESOURCE_GROUP
-az group deployment create --template-file ./.generated/storage.json -g $AZURE_RESOURCE_GROUP
-az group deployment create --template-file ./.generated/availability-sets.json -g $AZURE_RESOURCE_GROUP
-az group deployment create --template-file ./.generated/bastion.json -g $AZURE_RESOURCE_GROUP
-az group deployment create --template-file ./.generated/masters.json -g $AZURE_RESOURCE_GROUP
-az group deployment create --template-file ./.generated/minions.json -g $AZURE_RESOURCE_GROUP

contrib/azurerm/clear-rg.sh

@@ -9,10 +9,6 @@ if [ "$AZURE_RESOURCE_GROUP" == "" ]; then
     exit 1
 fi
 
-if az &>/dev/null; then
-    echo "azure cli 2.0 found, using it instead of 1.0"
-    ./clear-rg_2.sh "$AZURE_RESOURCE_GROUP"
-else
-    ansible-playbook generate-templates.yml
-    azure group deployment create -g "$AZURE_RESOURCE_GROUP" -f ./.generated/clear-rg.json -m Complete
-fi
+ansible-playbook generate-templates.yml
+
+az group deployment create -g "$AZURE_RESOURCE_GROUP" --template-file ./.generated/clear-rg.json --mode Complete

contrib/azurerm/clear-rg_2.sh

@@ -1,14 +0,0 @@
-#!/usr/bin/env bash
-
-set -e
-
-AZURE_RESOURCE_GROUP="$1"
-
-if [ "$AZURE_RESOURCE_GROUP" == "" ]; then
-    echo "AZURE_RESOURCE_GROUP is missing"
-    exit 1
-fi
-
-ansible-playbook generate-templates.yml
-
-az group deployment create -g "$AZURE_RESOURCE_GROUP" --template-file ./.generated/clear-rg.json --mode Complete

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

@@ -1,6 +1,6 @@
 ---
 
-- name: Query Azure VMs
+- name: Query Azure VMs  # noqa 301
   command: azure vm list-ip-address --json {{ azure_resource_group }}
   register: vm_list_cmd
 
@@ -12,3 +12,4 @@
   template:
     src: inventory.j2
     dest: "{{ playbook_dir }}/inventory"
+    mode: 0644

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

@@ -7,9 +7,9 @@
 {% endif %}
 {% endfor %}
 
-[kube-master]
+[kube_control_plane]
 {% for vm in vm_list %}
-{% if 'kube-master' in vm.tags.roles %}
+{% if 'kube_control_plane' in vm.tags.roles %}
 {{ vm.name }}
 {% endif %}
 {% endfor %}
@@ -21,13 +21,13 @@
 {% endif %}
 {% endfor %}
 
-[kube-node]
+[kube_node]
 {% for vm in vm_list %}
-{% if 'kube-node' in vm.tags.roles %}
+{% if 'kube_node' in vm.tags.roles %}
 {{ vm.name }}
 {% endif %}
 {% endfor %}
 
-[k8s-cluster:children]
-kube-node
-kube-master
+[k8s_cluster:children]
+kube_node
+kube_control_plane

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

@@ -1,14 +1,14 @@
 ---
 
-- name: Query Azure VMs IPs
+- name: Query Azure VMs IPs  # noqa 301
   command: az vm list-ip-addresses -o json --resource-group {{ azure_resource_group }}
   register: vm_ip_list_cmd
 
-- name: Query Azure VMs Roles
+- name: Query Azure VMs Roles  # noqa 301
   command: az vm list -o json --resource-group {{ azure_resource_group }}
   register: vm_list_cmd
 
-- name: Query Azure Load Balancer Public IP
+- name: Query Azure Load Balancer Public IP  # noqa 301
   command: az network public-ip show -o json -g {{ azure_resource_group }} -n kubernetes-api-pubip
   register: lb_pubip_cmd
 
@@ -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-inventory_2/templates/inventory.j2

@@ -7,9 +7,9 @@
 {% endif %}
 {% endfor %}
 
-[kube-master]
+[kube_control_plane]
 {% for vm in vm_roles_list %}
-{% if 'kube-master' in vm.tags.roles %}
+{% if 'kube_control_plane' in vm.tags.roles %}
 {{ vm.name }}
 {% endif %}
 {% endfor %}
@@ -21,14 +21,14 @@
 {% endif %}
 {% endfor %}
 
-[kube-node]
+[kube_node]
 {% for vm in vm_roles_list %}
-{% if 'kube-node' in vm.tags.roles %}
+{% if 'kube_node' in vm.tags.roles %}
 {{ vm.name }}
 {% endif %}
 {% endfor %}
 
-[k8s-cluster:children]
-kube-node
-kube-master
+[k8s_cluster:children]
+kube_node
+kube_control_plane
 

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/azurerm/roles/generate-templates/templates/masters.json

@@ -144,7 +144,7 @@
         "[concat('Microsoft.Network/networkInterfaces/', 'master-{{i}}-nic')]"
       ],
       "tags": {
-        "roles": "kube-master,etcd"
+        "roles": "kube_control_plane,etcd"
       },
       "apiVersion": "{{apiVersion}}",
       "properties": {

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

@@ -61,7 +61,7 @@
         "[concat('Microsoft.Network/networkInterfaces/', 'minion-{{i}}-nic')]"
       ],
       "tags": {
-        "roles": "kube-node"
+        "roles": "kube_node"
       },
       "apiVersion": "{{apiVersion}}",
       "properties": {
@@ -112,4 +112,4 @@
     } {% if not loop.last %},{% endif %}
     {% endfor %}
   ]
-}
+}

contrib/dind/README.md

@@ -6,6 +6,7 @@ to serve as Kubernetes "nodes", which in turn will run
 called DIND (Docker-IN-Docker).
 
 The playbook has two roles:
+
 - dind-host: creates the "nodes" as containers in localhost, with
   appropriate settings for DIND (privileged, volume mapping for dind
   storage, etc).
@@ -27,7 +28,7 @@ See below for a complete successful run:
 
 1. Create the node containers
 
-~~~~
+```shell
 # From the kubespray root dir
 cd contrib/dind
 pip install -r requirements.txt
@@ -36,15 +37,15 @@ ansible-playbook -i hosts dind-cluster.yaml
 
 # Back to kubespray root
 cd ../..
-~~~~
+```
 
 NOTE: if the playbook run fails with something like below error
 message, you may need to specifically set `ansible_python_interpreter`,
 see `./hosts` file for an example expanded localhost entry.
 
-~~~
+```shell
 failed: [localhost] (item=kube-node1) => {"changed": false, "item": "kube-node1", "msg": "Failed to import docker or docker-py - No module named requests.exceptions. Try `pip install docker` or `pip install docker-py` (Python 2.6)"}
-~~~
+```
 
 2. Customize kubespray-dind.yaml
 
@@ -52,33 +53,33 @@ Note that there's coupling between above created node containers
 and `kubespray-dind.yaml` settings, in particular regarding selected `node_distro`
 (as set in `group_vars/all/all.yaml`), and docker settings.
 
-~~~
+```shell
 $EDITOR contrib/dind/kubespray-dind.yaml
-~~~
+```
 
 3. Prepare the inventory and run the playbook
 
-~~~
+```shell
 INVENTORY_DIR=inventory/local-dind
 mkdir -p ${INVENTORY_DIR}
 rm -f ${INVENTORY_DIR}/hosts.ini
 CONFIG_FILE=${INVENTORY_DIR}/hosts.ini /tmp/kubespray.dind.inventory_builder.sh
 
 ansible-playbook --become -e ansible_ssh_user=debian -i ${INVENTORY_DIR}/hosts.ini cluster.yml --extra-vars @contrib/dind/kubespray-dind.yaml
-~~~
+```
 
 NOTE: You could also test other distros without editing files by
 passing `--extra-vars` as per below commandline,
 replacing `DISTRO` by either `debian`, `ubuntu`, `centos`, `fedora`:
 
-~~~
+```shell
 cd contrib/dind
 ansible-playbook -i hosts dind-cluster.yaml --extra-vars node_distro=DISTRO
 
 cd ../..
 CONFIG_FILE=inventory/local-dind/hosts.ini /tmp/kubespray.dind.inventory_builder.sh
 ansible-playbook --become -e ansible_ssh_user=DISTRO -i inventory/local-dind/hosts.ini cluster.yml --extra-vars @contrib/dind/kubespray-dind.yaml --extra-vars bootstrap_os=DISTRO
-~~~
+```
 
 ## Resulting deployment
 
@@ -89,7 +90,7 @@ from the host where you ran kubespray playbooks.
 
 Running from an Ubuntu Xenial host:
 
-~~~
+```shell
 $ uname -a
 Linux ip-xx-xx-xx-xx 4.4.0-1069-aws #79-Ubuntu SMP Mon Sep 24
 15:01:41 UTC 2018 x86_64 x86_64 x86_64 GNU/Linux
@@ -149,14 +150,14 @@ kube-system   weave-net-xr46t                         2/2     Running   0
 
 $ docker exec kube-node1 curl -s http://localhost:31081/api/v1/connectivity_check
 {"Message":"All 10 pods successfully reported back to the server","Absent":null,"Outdated":null}
-~~~
+```
 
 ## Using ./run-test-distros.sh
 
 You can use `./run-test-distros.sh` to run a set of tests via DIND,
 and excerpt from this script, to get an idea:
 
-~~~
+```shell
 # The SPEC file(s) must have two arrays as e.g.
 # DISTROS=(debian centos)
 # EXTRAS=(
@@ -169,7 +170,7 @@ and excerpt from this script, to get an idea:
 #
 # Each $EXTRAS element will be whitespace split, and passed as --extra-vars
 # to main kubespray ansible-playbook run.
-~~~
+```
 
 See e.g. `test-some_distros-most_CNIs.env` and
 `test-some_distros-kube_router_combo.env` in particular for a richer

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

@@ -69,7 +69,7 @@
 
 # Running systemd-machine-id-setup doesn't create a unique id for each node container on Debian,
 # handle manually
-- name: Re-create unique machine-id (as we may just get what comes in the docker image), needed by some CNIs for mac address seeding (notably weave)
+- name: Re-create unique machine-id (as we may just get what comes in the docker image), needed by some CNIs for mac address seeding (notably weave)  # noqa 301
   raw: |
     echo {{ item | hash('sha1') }} > /etc/machine-id.new
     mv -b /etc/machine-id.new /etc/machine-id

contrib/dind/run-test-distros.sh

@@ -46,7 +46,7 @@ test_distro() {
     pass_or_fail "$prefix: netcheck" || return 1
 }
 
-NODES=($(egrep ^kube-node hosts))
+NODES=($(egrep ^kube_node hosts))
 NETCHECKER_HOST=localhost
 
 : ${OUTPUT_DIR:=./out}

contrib/inventory_builder/inventory.py

@@ -41,13 +41,14 @@ from ruamel.yaml import YAML
 
 import os
 import re
+import subprocess
 import sys
 
-ROLES = ['all', 'kube-master', 'kube-node', 'etcd', 'k8s-cluster',
-         'calico-rr']
+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()
@@ -62,13 +63,16 @@ def get_var_as_bool(name, default):
 
 
 CONFIG_FILE = os.environ.get("CONFIG_FILE", "./inventory/sample/hosts.yaml")
-KUBE_MASTERS = int(os.environ.get("KUBE_MASTERS_MASTERS", 2))
+# Remove the reference of KUBE_MASTERS after some deprecation cycles.
+KUBE_CONTROL_HOSTS = int(os.environ.get("KUBE_CONTROL_HOSTS",
+                         os.environ.get("KUBE_MASTERS", 2)))
 # Reconfigures cluster distribution at scale
 SCALE_THRESHOLD = int(os.environ.get("SCALE_THRESHOLD", 50))
-MASSIVE_SCALE_THRESHOLD = int(os.environ.get("SCALE_THRESHOLD", 200))
+MASSIVE_SCALE_THRESHOLD = int(os.environ.get("MASSIVE_SCALE_THRESHOLD", 200))
 
 DEBUG = get_var_as_bool("DEBUG", True)
 HOST_PREFIX = os.environ.get("HOST_PREFIX", "node")
+USE_REAL_HOSTNAME = get_var_as_bool("USE_REAL_HOSTNAME", False)
 
 # Configurable as shell vars end
 
@@ -78,32 +82,54 @@ 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(self.hosts_file)
-            except OSError:
-                pass
+            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()
             etcd_hosts_count = 3 if len(self.hosts.keys()) >= 3 else 1
             self.set_etcd(list(self.hosts.keys())[:etcd_hosts_count])
             if len(self.hosts) >= SCALE_THRESHOLD:
-                self.set_kube_master(list(self.hosts.keys())[
-                    etcd_hosts_count:(etcd_hosts_count + KUBE_MASTERS)])
+                self.set_kube_control_plane(list(self.hosts.keys())[
+                    etcd_hosts_count:(etcd_hosts_count + KUBE_CONTROL_HOSTS)])
             else:
-                self.set_kube_master(list(self.hosts.keys())[:KUBE_MASTERS])
+                self.set_kube_control_plane(
+                  list(self.hosts.keys())[:KUBE_CONTROL_HOSTS])
             self.set_kube_node(self.hosts.keys())
             if len(self.hosts) >= SCALE_THRESHOLD:
                 self.set_calico_rr(list(self.hosts.keys())[:etcd_hosts_count])
@@ -153,23 +179,37 @@ 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
+        next_host = ""
 
         all_hosts = existing_hosts.copy()
         for host in changed_hosts:
+            # Delete the host from config the hostname/IP has a "-" prefix
             if host[0] == "-":
                 realhost = host[1:]
                 if self.exists_hostname(all_hosts, realhost):
@@ -178,6 +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(',')
@@ -191,11 +233,21 @@ class KubesprayInventory(object):
                     self.debug("Skipping existing host {0}.".format(ip))
                     continue
 
-                next_host = "{0}{1}".format(HOST_PREFIX, next_host_id)
-                next_host_id += 1
+                if USE_REAL_HOSTNAME:
+                    cmd = ("ssh -oStrictHostKeyChecking=no "
+                           + access_ip + " 'hostname -s'")
+                    next_host = subprocess.check_output(cmd, shell=True)
+                    next_host = next_host.strip().decode('ascii')
+                else:
+                    # Generates a hostname because we have only an IP address
+                    next_host = "{0}{1}".format(HOST_PREFIX, next_host_id)
+                    next_host_id += 1
+                # Uses automatically generated node name
+                # in case we dont provide it.
                 all_hosts[next_host] = {'ansible_host': access_ip,
                                         'ip': ip,
                                         'access_ip': access_ip}
+            # Host/Argument starts with a letter, then we assume its a hostname
             elif host[0].isalpha():
                 if ',' in host:
                     try:
@@ -214,6 +266,7 @@ class KubesprayInventory(object):
                                        'access_ip': access_ip}
         return all_hosts
 
+    # Expand IP ranges into individual addresses
     def range2ips(self, hosts):
         reworked_hosts = []
 
@@ -229,7 +282,7 @@ class KubesprayInventory(object):
             return [ip_address(ip).exploded for ip in range(start, end + 1)]
 
         for host in hosts:
-            if '-' in host and not host.startswith('-'):
+            if '-' in host and not (host.startswith('-') or host[0].isalpha()):
                 start, end = host.strip().split('-')
                 try:
                     reworked_hosts.extend(ips(start, end))
@@ -257,7 +310,7 @@ class KubesprayInventory(object):
 
     def purge_invalid_hosts(self, hostnames, protected_names=[]):
         for role in self.yaml_config['all']['children']:
-            if role != 'k8s-cluster' and self.yaml_config['all']['children'][role]['hosts']:  # noqa
+            if role != 'k8s_cluster' and self.yaml_config['all']['children'][role]['hosts']:  # noqa
                 all_hosts = self.yaml_config['all']['children'][role]['hosts'].copy()  # noqa
                 for host in all_hosts.keys():
                     if host not in hostnames and host not in protected_names:
@@ -278,52 +331,54 @@ class KubesprayInventory(object):
             if self.yaml_config['all']['hosts'] is None:
                 self.yaml_config['all']['hosts'] = {host: None}
             self.yaml_config['all']['hosts'][host] = opts
-        elif group != 'k8s-cluster:children':
+        elif group != 'k8s_cluster:children':
             if self.yaml_config['all']['children'][group]['hosts'] is None:
                 self.yaml_config['all']['children'][group]['hosts'] = {
                     host: None}
             else:
                 self.yaml_config['all']['children'][group]['hosts'][host] = None  # noqa
 
-    def set_kube_master(self, hosts):
+    def set_kube_control_plane(self, hosts):
         for host in hosts:
-            self.add_host_to_group('kube-master', host)
+            self.add_host_to_group('kube_control_plane', host)
 
     def set_all(self, hosts):
         for host, opts in hosts.items():
             self.add_host_to_group('all', host, opts)
 
     def set_k8s_cluster(self):
-        k8s_cluster = {'children': {'kube-master': None, 'kube-node': None}}
-        self.yaml_config['all']['children']['k8s-cluster'] = k8s_cluster
+        k8s_cluster = {'children': {'kube_control_plane': None,
+                                    'kube_node': None}}
+        self.yaml_config['all']['children']['k8s_cluster'] = k8s_cluster
 
     def set_calico_rr(self, hosts):
         for host in hosts:
-            if host in self.yaml_config['all']['children']['kube-master']:
-                self.debug("Not adding {0} to calico-rr group because it "
-                           "conflicts with kube-master group".format(host))
+            if host in self.yaml_config['all']['children']['kube_control_plane']: # noqa
+                self.debug("Not adding {0} to calico_rr group because it "
+                           "conflicts with kube_control_plane "
+                           "group".format(host))
                 continue
-            if host in self.yaml_config['all']['children']['kube-node']:
-                self.debug("Not adding {0} to calico-rr group because it "
-                           "conflicts with kube-node group".format(host))
+            if host in self.yaml_config['all']['children']['kube_node']:
+                self.debug("Not adding {0} to calico_rr group because it "
+                           "conflicts with kube_node group".format(host))
                 continue
-            self.add_host_to_group('calico-rr', host)
+            self.add_host_to_group('calico_rr', host)
 
     def set_kube_node(self, hosts):
         for host in hosts:
             if len(self.yaml_config['all']['hosts']) >= SCALE_THRESHOLD:
                 if host in self.yaml_config['all']['children']['etcd']['hosts']:  # noqa
-                    self.debug("Not adding {0} to kube-node group because of "
+                    self.debug("Not adding {0} to kube_node group because of "
                                "scale deployment and host is in etcd "
                                "group.".format(host))
                     continue
             if len(self.yaml_config['all']['hosts']) >= MASSIVE_SCALE_THRESHOLD:  # noqa
-                if host in self.yaml_config['all']['children']['kube-master']['hosts']:  # noqa
-                    self.debug("Not adding {0} to kube-node group because of "
-                               "scale deployment and host is in kube-master "
-                               "group.".format(host))
+                if host in self.yaml_config['all']['children']['kube_control_plane']['hosts']:  # noqa
+                    self.debug("Not adding {0} to kube_node group because of "
+                               "scale deployment and host is in "
+                               "kube_control_plane group.".format(host))
                     continue
-            self.add_host_to_group('kube-node', host)
+            self.add_host_to_group('kube_node', host)
 
     def set_etcd(self, hosts):
         for host in hosts:
@@ -380,9 +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
@@ -393,8 +450,9 @@ Configurable env vars:
 DEBUG                   Enable debug printing. Default: True
 CONFIG_FILE             File to write config to Default: ./inventory/sample/hosts.yaml
 HOST_PREFIX             Host prefix for generated hosts. Default: node
+KUBE_CONTROL_HOSTS      Set the number of kube-control-planes. Default: 2
 SCALE_THRESHOLD         Separate ETCD role if # of nodes >= 50
-MASSIVE_SCALE_THRESHOLD Separate K8s master and ETCD if # of nodes >= 200
+MASSIVE_SCALE_THRESHOLD Separate K8s control-plane and ETCD if # of nodes >= 200
 '''  # noqa
         print(help_text)
 
@@ -415,6 +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

@@ -13,8 +13,9 @@
 # under the License.
 
 import inventory
-import mock
+from test import support
 import unittest
+from unittest import mock
 
 from collections import OrderedDict
 import sys
@@ -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 support.captured_stdout() 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):
@@ -51,7 +74,7 @@ class TestInventory(unittest.TestCase):
         groups = ['group1', 'group2']
         self.inv.ensure_required_groups(groups)
         for group in groups:
-            self.assertTrue(group in self.inv.yaml_config['all']['children'])
+            self.assertIn(group, self.inv.yaml_config['all']['children'])
 
     def test_get_host_id(self):
         hostnames = ['node99', 'no99de01', '01node01', 'node1.domain',
@@ -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):
@@ -209,8 +264,8 @@ class TestInventory(unittest.TestCase):
             ('doesnotbelong2', {'whateveropts=ilike'})])
         self.inv.yaml_config['all']['hosts'] = existing_hosts
         self.inv.purge_invalid_hosts(proper_hostnames)
-        self.assertTrue(
-            bad_host not in self.inv.yaml_config['all']['hosts'].keys())
+        self.assertNotIn(
+            bad_host, self.inv.yaml_config['all']['hosts'].keys())
 
     def test_add_host_to_group(self):
         group = 'etcd'
@@ -222,13 +277,13 @@ class TestInventory(unittest.TestCase):
             self.inv.yaml_config['all']['children'][group]['hosts'].get(host),
             None)
 
-    def test_set_kube_master(self):
-        group = 'kube-master'
+    def test_set_kube_control_plane(self):
+        group = 'kube_control_plane'
         host = 'node1'
 
-        self.inv.set_kube_master([host])
-        self.assertTrue(
-            host in self.inv.yaml_config['all']['children'][group]['hosts'])
+        self.inv.set_kube_control_plane([host])
+        self.assertIn(
+            host, self.inv.yaml_config['all']['children'][group]['hosts'])
 
     def test_set_all(self):
         hosts = OrderedDict([
@@ -241,30 +296,30 @@ class TestInventory(unittest.TestCase):
                 self.inv.yaml_config['all']['hosts'].get(host), opt)
 
     def test_set_k8s_cluster(self):
-        group = 'k8s-cluster'
-        expected_hosts = ['kube-node', 'kube-master']
+        group = 'k8s_cluster'
+        expected_hosts = ['kube_node', 'kube_control_plane']
 
         self.inv.set_k8s_cluster()
         for host in expected_hosts:
-            self.assertTrue(
-                host in
+            self.assertIn(
+                host,
                 self.inv.yaml_config['all']['children'][group]['children'])
 
     def test_set_kube_node(self):
-        group = 'kube-node'
+        group = 'kube_node'
         host = 'node1'
 
         self.inv.set_kube_node([host])
-        self.assertTrue(
-            host in self.inv.yaml_config['all']['children'][group]['hosts'])
+        self.assertIn(
+            host, self.inv.yaml_config['all']['children'][group]['hosts'])
 
     def test_set_etcd(self):
         group = 'etcd'
         host = 'node1'
 
         self.inv.set_etcd([host])
-        self.assertTrue(
-            host in self.inv.yaml_config['all']['children'][group]['hosts'])
+        self.assertIn(
+            host, self.inv.yaml_config['all']['children'][group]['hosts'])
 
     def test_scale_scenario_one(self):
         num_nodes = 50
@@ -275,12 +330,12 @@ class TestInventory(unittest.TestCase):
 
         self.inv.set_all(hosts)
         self.inv.set_etcd(list(hosts.keys())[0:3])
-        self.inv.set_kube_master(list(hosts.keys())[0:2])
+        self.inv.set_kube_control_plane(list(hosts.keys())[0:2])
         self.inv.set_kube_node(hosts.keys())
         for h in range(3):
             self.assertFalse(
                 list(hosts.keys())[h] in
-                self.inv.yaml_config['all']['children']['kube-node']['hosts'])
+                self.inv.yaml_config['all']['children']['kube_node']['hosts'])
 
     def test_scale_scenario_two(self):
         num_nodes = 500
@@ -291,12 +346,12 @@ class TestInventory(unittest.TestCase):
 
         self.inv.set_all(hosts)
         self.inv.set_etcd(list(hosts.keys())[0:3])
-        self.inv.set_kube_master(list(hosts.keys())[3:5])
+        self.inv.set_kube_control_plane(list(hosts.keys())[3:5])
         self.inv.set_kube_node(hosts.keys())
         for h in range(5):
             self.assertFalse(
                 list(hosts.keys())[h] in
-                self.inv.yaml_config['all']['children']['kube-node']['hosts'])
+                self.inv.yaml_config['all']['children']['kube_node']['hosts'])
 
     def test_range2ips_range(self):
         changed_hosts = ['10.90.0.2', '10.90.0.4-10.90.0.6', '10.90.0.8']
@@ -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/README.md

@@ -5,7 +5,7 @@ deployment on VMs.
 
 This playbook does not create Virtual Machines, nor does it run Kubespray itself.
 
-### User creation
+## User creation
 
 If you want to create a user for running Kubespray deployment, you should specify
 both `k8s_deployment_user` and `k8s_deployment_user_pkey_path`.

contrib/kvm-setup/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/metallb/README.md

@@ -1,12 +0,0 @@
-# Deploy MetalLB into Kubespray/Kubernetes
-```
-MetalLB hooks into your Kubernetes cluster, and provides a network load-balancer implementation. In short, it allows you to create Kubernetes services of type “LoadBalancer” in clusters that don’t run on a cloud provider, and thus cannot simply hook into paid products to provide load-balancers.
-```
-This playbook aims to automate [this](https://metallb.universe.tf/concepts/layer2/). It deploys MetalLB into kubernetes and sets up a layer 2 loadbalancer.
-
-## Install
-```
-Defaults can be found in contrib/metallb/roles/provision/defaults/main.yml. You can override the defaults by copying the contents of this file to somewhere in inventory/mycluster/group_vars such as inventory/mycluster/groups_vars/k8s-cluster/addons.yml and making any adjustments as required.
-
-ansible-playbook --ask-become -i inventory/sample/hosts.ini contrib/metallb/metallb.yml
-```

contrib/metallb/library

@@ -1 +0,0 @@
-../../library

contrib/metallb/metallb.yml

@@ -1,6 +0,0 @@
----
-- hosts: kube-master[0]
-  tags:
-    - "provision"
-  roles:
-    - { role: provision }

contrib/metallb/roles/provision/defaults/main.yml

@@ -1,14 +0,0 @@
----
-metallb:
-  ip_range: "10.5.0.50-10.5.0.99"
-  protocol: "layer2"
-  # additional_address_pools:
-  #   kube_service_pool:
-  #     ip_range: "10.5.1.50-10.5.1.99"
-  #     protocol: "layer2"
-  #     auto_assign: false
-  limits:
-    cpu: "100m"
-    memory: "100Mi"
-  port: "7472"
-  version: v0.7.3

contrib/metallb/roles/provision/tasks/main.yml

@@ -1,23 +0,0 @@
----
-- name: "Kubernetes Apps | Check cluster settings for MetalLB"
-  fail:
-    msg: "MetalLB require kube_proxy_strict_arp = true, see https://github.com/danderson/metallb/issues/153#issuecomment-518651132"
-  when:
-    - "kube_proxy_mode == 'ipvs' and not kube_proxy_strict_arp"
-- name: "Kubernetes Apps | Lay Down MetalLB"
-  become: true
-  template: { src: "{{ item }}.j2", dest: "{{ kube_config_dir }}/{{ item }}" }
-  with_items: ["metallb.yml", "metallb-config.yml"]
-  register: "rendering"
-  when:
-    - "inventory_hostname == groups['kube-master'][0]"
-- name: "Kubernetes Apps | Install and configure MetalLB"
-  kube:
-    name: "MetalLB"
-    kubectl: "{{ bin_dir }}/kubectl"
-    filename: "{{ kube_config_dir }}/{{ item.item }}"
-    state: "{{ item.changed | ternary('latest','present') }}"
-  become: true
-  with_items: "{{ rendering.results }}"
-  when:
-    - "inventory_hostname == groups['kube-master'][0]"

contrib/metallb/roles/provision/templates/metallb-config.yml.j2

@@ -1,21 +0,0 @@
----
-apiVersion: v1
-kind: ConfigMap
-metadata:
-  namespace: metallb-system
-  name: config
-data:
-  config: |
-    address-pools:
-    - name: loadbalanced
-      protocol: {{ metallb.protocol }}
-      addresses:
-      - {{ metallb.ip_range }}
-{% if metallb.additional_address_pools is defined %}{% for pool in metallb.additional_address_pools %}
-    - name: {{ pool }}
-      protocol: {{ metallb.additional_address_pools[pool].protocol }}
-      addresses:
-      - {{ metallb.additional_address_pools[pool].ip_range }}
-      auto-assign: {{ metallb.additional_address_pools[pool].auto_assign }}
-{% endfor %}
-{% endif %}

contrib/metallb/roles/provision/templates/metallb.yml.j2

@@ -1,221 +0,0 @@
-apiVersion: v1
-kind: Namespace
-metadata:
-  name: metallb-system
-  labels:
-    app: metallb
----
-
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  namespace: metallb-system
-  name: controller
-  labels:
-    app: metallb
----
-apiVersion: v1
-kind: ServiceAccount
-metadata:
-  namespace: metallb-system
-  name: speaker
-  labels:
-    app: metallb
-
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: metallb-system:controller
-  labels:
-    app: metallb
-rules:
-- apiGroups: [""]
-  resources: ["services"]
-  verbs: ["get", "list", "watch", "update"]
-- apiGroups: [""]
-  resources: ["services/status"]
-  verbs: ["update"]
-- apiGroups: [""]
-  resources: ["events"]
-  verbs: ["create", "patch"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRole
-metadata:
-  name: metallb-system:speaker
-  labels:
-    app: metallb
-rules:
-- apiGroups: [""]
-  resources: ["services", "endpoints", "nodes"]
-  verbs: ["get", "list", "watch"]
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: Role
-metadata:
-  namespace: metallb-system
-  name: config-watcher
-  labels:
-    app: metallb
-rules:
-- apiGroups: [""]
-  resources: ["configmaps"]
-  verbs: ["get", "list", "watch"]
-- apiGroups: [""]
-  resources: ["events"]
-  verbs: ["create"]
----
-
-## Role bindings
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: metallb-system:controller
-  labels:
-    app: metallb
-subjects:
-- kind: ServiceAccount
-  name: controller
-  namespace: metallb-system
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: metallb-system:controller
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: ClusterRoleBinding
-metadata:
-  name: metallb-system:speaker
-  labels:
-    app: metallb
-subjects:
-- kind: ServiceAccount
-  name: speaker
-  namespace: metallb-system
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: ClusterRole
-  name: metallb-system:speaker
----
-apiVersion: rbac.authorization.k8s.io/v1
-kind: RoleBinding
-metadata:
-  namespace: metallb-system
-  name: config-watcher
-  labels:
-    app: metallb
-subjects:
-- kind: ServiceAccount
-  name: controller
-- kind: ServiceAccount
-  name: speaker
-roleRef:
-  apiGroup: rbac.authorization.k8s.io
-  kind: Role
-  name: config-watcher
----
-apiVersion: apps/v1
-kind: DaemonSet
-metadata:
-  namespace: metallb-system
-  name: speaker
-  labels:
-    app: metallb
-    component: speaker
-spec:
-  selector:
-    matchLabels:
-      app: metallb
-      component: speaker
-  template:
-    metadata:
-      labels:
-        app: metallb
-        component: speaker
-      annotations:
-        prometheus.io/scrape: "true"
-        prometheus.io/port: "{{ metallb.port }}"
-    spec:
-      serviceAccountName: speaker
-      terminationGracePeriodSeconds: 0
-      hostNetwork: true
-      containers:
-      - name: speaker
-        image: metallb/speaker:{{ metallb.version }}
-        imagePullPolicy: IfNotPresent
-        args:
-        - --port={{ metallb.port }}
-        - --config=config
-        env:
-        - name: METALLB_NODE_NAME
-          valueFrom:
-            fieldRef:
-              fieldPath: spec.nodeName
-        ports:
-        - name: monitoring
-          containerPort: {{ metallb.port }}
-        resources:
-          limits:
-            cpu: {{ metallb.limits.cpu }}
-            memory: {{ metallb.limits.memory }}
-        securityContext:
-          allowPrivilegeEscalation: false
-          readOnlyRootFilesystem: true
-          capabilities:
-            drop:
-            - all
-            add:
-            - net_raw
-
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  namespace: metallb-system
-  name: controller
-  labels:
-    app: metallb
-    component: controller
-spec:
-  revisionHistoryLimit: 3
-  selector:
-    matchLabels:
-      app: metallb
-      component: controller
-  template:
-    metadata:
-      labels:
-        app: metallb
-        component: controller
-      annotations:
-        prometheus.io/scrape: "true"
-        prometheus.io/port: "{{ metallb.port }}"
-    spec:
-      serviceAccountName: controller
-      terminationGracePeriodSeconds: 0
-      securityContext:
-        runAsNonRoot: true
-        runAsUser: 65534 # nobody
-      containers:
-      - name: controller
-        image: metallb/controller:{{ metallb.version }}
-        imagePullPolicy: IfNotPresent
-        args:
-        - --port={{ metallb.port }}
-        - --config=config
-        ports:
-        - name: monitoring
-          containerPort: {{ metallb.port }}
-        resources:
-          limits:
-            cpu: {{ metallb.limits.cpu }}
-            memory: {{ metallb.limits.memory }}
-        securityContext:
-          allowPrivilegeEscalation: false
-          capabilities:
-            drop:
-            - all
-          readOnlyRootFilesystem: true
-
----

contrib/misc/clusteradmin-rbac.yml

@@ -1,5 +1,5 @@
 ---
-apiVersion: rbac.authorization.k8s.io/v1beta1
+apiVersion: rbac.authorization.k8s.io/v1
 kind: ClusterRoleBinding
 metadata:
   name: kubernetes-dashboard

contrib/mitogen/mitogen.yml

@@ -1,14 +1,19 @@
 ---
+- name: Check ansible version
+  import_playbook: ansible_version.yml
+
 - hosts: localhost
   strategy: linear
   vars:
-    mitogen_version: master
-    mitogen_url: https://github.com/dw/mitogen/archive/{{ mitogen_version }}.zip
+    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"
@@ -17,15 +22,28 @@
     - name: download mitogen release
       get_url:
         url: "{{ mitogen_url }}"
-        dest: "{{ playbook_dir }}/dist/mitogen_{{ mitogen_version }}.zip"
+        dest: "{{ playbook_dir }}/dist/mitogen_{{ mitogen_version }}.tar.gz"
         validate_certs: true
 
-    - name: extract zip
+    - name: extract archive
       unarchive:
-        src: "{{ playbook_dir }}/dist/mitogen_{{ mitogen_version }}.zip"
+        src: "{{ playbook_dir }}/dist/mitogen_{{ mitogen_version }}.tar.gz"
         dest: "{{ playbook_dir }}/dist/"
 
     - name: copy plugin
       synchronize:
         src: "{{ playbook_dir }}/dist/mitogen-{{ mitogen_version }}/"
         dest: "{{ playbook_dir }}/plugins/mitogen"
+
+    - name: add strategy to ansible.cfg
+      ini_file:
+        path: ansible.cfg
+        mode: 0644
+        section: "{{ item.section | d('defaults') }}"
+        option: "{{ item.option }}"
+        value: "{{ item.value }}"
+      with_items:
+        - option: strategy
+          value: mitogen_linear
+        - option: strategy_plugins
+          value: plugins/mitogen/ansible_mitogen/plugins/strategy

contrib/network-storage/glusterfs/README.md

@@ -8,19 +8,19 @@ In the same directory of this ReadMe file you should find a file named `inventor
 
 Change that file to reflect your local setup (adding more machines or removing them and setting the adequate ip numbers), and save it to `inventory/sample/k8s_gfs_inventory`. Make sure that the settings on `inventory/sample/group_vars/all.yml` make sense with your deployment. Then execute change to the kubespray root folder, and execute (supposing that the machines are all using ubuntu):
 
-```
+```shell
 ansible-playbook -b --become-user=root -i inventory/sample/k8s_gfs_inventory --user=ubuntu ./cluster.yml
 ```
 
 This will provision your Kubernetes cluster. Then, to provision and configure the GlusterFS cluster, from the same directory execute:
 
-```
+```shell
 ansible-playbook -b --become-user=root -i inventory/sample/k8s_gfs_inventory --user=ubuntu ./contrib/network-storage/glusterfs/glusterfs.yml
 ```
 
 If your machines are not using Ubuntu, you need to change the `--user=ubuntu` to the correct user. Alternatively, if your Kubernetes machines are using one OS and your GlusterFS a different one, you can instead specify the `ansible_ssh_user=<correct-user>` variable in the inventory file that you just created, for each machine/VM:
 
-```
+```shell
 k8s-master-1 ansible_ssh_host=192.168.0.147 ip=192.168.0.147 ansible_ssh_user=core
 k8s-master-node-1 ansible_ssh_host=192.168.0.148 ip=192.168.0.148 ansible_ssh_user=core
 k8s-master-node-2 ansible_ssh_host=192.168.0.146 ip=192.168.0.146 ansible_ssh_user=core
@@ -30,7 +30,7 @@ k8s-master-node-2 ansible_ssh_host=192.168.0.146 ip=192.168.0.146 ansible_ssh_us
 
 First step is to fill in a `my-kubespray-gluster-cluster.tfvars` file with the specification desired for your cluster. An example with all required variables would look like:
 
-```
+```ini
 cluster_name = "cluster1"
 number_of_k8s_masters = "1"
 number_of_k8s_masters_no_floating_ip = "2"
@@ -39,7 +39,7 @@ number_of_k8s_nodes = "0"
 public_key_path = "~/.ssh/my-desired-key.pub"
 image = "Ubuntu 16.04"
 ssh_user = "ubuntu"
-flavor_k8s_node = "node-flavor-id-in-your-openstack" 
+flavor_k8s_node = "node-flavor-id-in-your-openstack"
 flavor_k8s_master = "master-flavor-id-in-your-openstack"
 network_name = "k8s-network"
 floatingip_pool = "net_external"
@@ -54,7 +54,7 @@ ssh_user_gfs = "ubuntu"
 
 As explained in the general terraform/openstack guide, you need to source your OpenStack credentials file, add your ssh-key to the ssh-agent and setup environment variables for terraform:
 
-```
+```shell
 $ source ~/.stackrc
 $ eval $(ssh-agent -s)
 $ ssh-add ~/.ssh/my-desired-key
@@ -67,7 +67,7 @@ $ echo Setting up Terraform creds && \
 
 Then, standing on the kubespray directory (root base of the Git checkout), issue the following terraform command to create the VMs for the cluster:
 
-```
+```shell
 terraform apply -state=contrib/terraform/openstack/terraform.tfstate -var-file=my-kubespray-gluster-cluster.tfvars contrib/terraform/openstack
 ```
 
@@ -75,18 +75,18 @@ This will create both your Kubernetes and Gluster VMs. Make sure that the ansibl
 
 Then, provision your Kubernetes (kubespray) cluster with the following ansible call:
 
-```
+```shell
 ansible-playbook -b --become-user=root -i contrib/terraform/openstack/hosts ./cluster.yml
 ```
 
 Finally, provision the glusterfs nodes and add the Persistent Volume setup for GlusterFS in Kubernetes through the following ansible call:
 
-```
+```shell
 ansible-playbook -b --become-user=root -i contrib/terraform/openstack/hosts ./contrib/network-storage/glusterfs/glusterfs.yml
 ```
 
 If you need to destroy the cluster, you can run:
 
-```
+```shell
 terraform destroy -state=contrib/terraform/openstack/terraform.tfstate -var-file=my-kubespray-gluster-cluster.tfvars contrib/terraform/openstack
 ```

contrib/network-storage/glusterfs/glusterfs.yml

@@ -15,10 +15,10 @@
   roles:
     - { role: glusterfs/server }
 
-- hosts: k8s-cluster
+- hosts: k8s_cluster
   roles:
     - { role: glusterfs/client }
 
-- hosts: kube-master[0]
+- hosts: kube_control_plane[0]
   roles:
     - { role: kubernetes-pv }

contrib/network-storage/glusterfs/inventory.example

@@ -11,10 +11,10 @@
 # ## 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-master]
+# [kube_control_plane]
 # node1
 # node2
 
@@ -23,16 +23,16 @@
 # node2
 # node3
 
-# [kube-node]
+# [kube_node]
 # node2
 # node3
 # node4
 # node5
 # node6
 
-# [k8s-cluster:children]
-# kube-node
-# kube-master
+# [k8s_cluster:children]
+# kube_node
+# kube_control_plane
 
 # [gfs-cluster]
 # gfs_node1

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

@@ -8,7 +8,7 @@ Installs and configures GlusterFS on Linux.
 
 For GlusterFS to connect between servers, TCP ports `24007`, `24008`, and `24009`/`49152`+ (that port, plus an additional incremented port for each additional server in the cluster; the latter if GlusterFS is version 3.4+), and TCP/UDP port `111` must be open. You can open these using whatever firewall you wish (this can easily be configured using the `geerlingguy.firewall` role).
 
-This role performs basic installation and setup of Gluster, but it does not configure or mount bricks (volumes), since that step is easier to do in a series of plays in your own playbook. Ansible 1.9+ includes the [`gluster_volume`](https://docs.ansible.com/gluster_volume_module.html) module to ease the management of Gluster volumes.
+This role performs basic installation and setup of Gluster, but it does not configure or mount bricks (volumes), since that step is easier to do in a series of plays in your own playbook. Ansible 1.9+ includes the [`gluster_volume`](https://docs.ansible.com/ansible/latest/collections/gluster/gluster/gluster_volume_module.html) module to ease the management of Gluster volumes.
 
 ## Role Variables
 

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

@@ -7,7 +7,7 @@
   register: glusterfs_ppa_added
   when: glusterfs_ppa_use
 
-- name: Ensure GlusterFS client will reinstall if the PPA was just added.
+- name: Ensure GlusterFS client will reinstall if the PPA was just added.  # noqa 503
   apt:
     name: "{{ item }}"
     state: absent
@@ -18,7 +18,7 @@
 - name: Ensure GlusterFS client is installed.
   apt:
     name: "{{ item }}"
-    state: installed
+    state: present
     default_release: "{{ glusterfs_default_release }}"
   with_items:
     - glusterfs-client

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-Debian.yml

@@ -7,7 +7,7 @@
   register: glusterfs_ppa_added
   when: glusterfs_ppa_use
 
-- name: Ensure GlusterFS will reinstall if the PPA was just added.
+- name: Ensure GlusterFS will reinstall if the PPA was just added.  # noqa 503
   apt:
     name: "{{ item }}"
     state: absent
@@ -19,7 +19,7 @@
 - name: Ensure GlusterFS is installed.
   apt:
     name: "{{ item }}"
-    state: installed
+    state: present
     default_release: "{{ glusterfs_default_release }}"
   with_items:
     - glusterfs-server

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/kubernetes-pv/ansible/tasks/main.yaml

@@ -3,12 +3,13 @@
   template:
     src: "{{ item.file }}"
     dest: "{{ kube_config_dir }}/{{ item.dest }}"
+    mode: 0644
   with_items:
     - { file: glusterfs-kubernetes-endpoint.json.j2, type: ep, dest: glusterfs-kubernetes-endpoint.json}
     - { file: glusterfs-kubernetes-pv.yml.j2, type: pv, dest: glusterfs-kubernetes-pv.yml}
     - { file: glusterfs-kubernetes-endpoint-svc.json.j2, type: svc, dest: glusterfs-kubernetes-endpoint-svc.json}
   register: gluster_pv
-  when: inventory_hostname == groups['kube-master'][0] and groups['gfs-cluster'] is defined and hostvars[groups['gfs-cluster'][0]].gluster_disk_size_gb is defined
+  when: inventory_hostname == groups['kube_control_plane'][0] and groups['gfs-cluster'] is defined and hostvars[groups['gfs-cluster'][0]].gluster_disk_size_gb is defined
 
 - name: Kubernetes Apps | Set GlusterFS endpoint and PV
   kube:
@@ -19,4 +20,4 @@
     filename: "{{ kube_config_dir }}/{{ item.item.dest }}"
     state: "{{ item.changed | ternary('latest','present') }}"
   with_items: "{{ gluster_pv.results }}"
-  when: inventory_hostname == groups['kube-master'][0] and groups['gfs-cluster'] is defined
+  when: inventory_hostname == groups['kube_control_plane'][0] and groups['gfs-cluster'] is defined

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

@@ -8,7 +8,7 @@
     {% for host in groups['gfs-cluster'] %}
     {
       "addresses": [
-        { 
+        {
           "ip": "{{hostvars[host]['ip']|default(hostvars[host].ansible_default_ipv4['address'])}}"
         }
       ],

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

@@ -1,7 +1,7 @@
 apiVersion: v1
 kind: PersistentVolume
 metadata:
-  name: glusterfs 
+  name: glusterfs
 spec:
   capacity:
       storage: "{{ hostvars[groups['gfs-cluster'][0]].gluster_disk_size_gb }}Gi"

contrib/network-storage/heketi/README.md

@@ -1,17 +1,26 @@
 # Deploy Heketi/Glusterfs into Kubespray/Kubernetes
+
 This playbook aims to automate [this](https://github.com/heketi/heketi/blob/master/docs/admin/install-kubernetes.md) tutorial. It deploys heketi/glusterfs into kubernetes and sets up a storageclass.
 
+## Important notice
+
+> Due to resource limits on the current project maintainers and general lack of contributions we are considering placing Heketi into a [near-maintenance mode](https://github.com/heketi/heketi#important-notice)
+
 ## Client Setup
+
 Heketi provides a CLI that provides users with a means to administer the deployment and configuration of GlusterFS in Kubernetes. [Download and install the heketi-cli](https://github.com/heketi/heketi/releases) on your client machine.
 
 ## Install
+
 Copy the inventory.yml.sample over to inventory/sample/k8s_heketi_inventory.yml and change it according to your setup.
-```
+
+```shell
 ansible-playbook --ask-become -i inventory/sample/k8s_heketi_inventory.yml contrib/network-storage/heketi/heketi.yml
 ```
 
 ## Tear down
-```
+
+```shell
 ansible-playbook --ask-become -i inventory/sample/k8s_heketi_inventory.yml contrib/network-storage/heketi/heketi-tear-down.yml
 ```
 

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

@@ -1,5 +1,5 @@
 ---
-- hosts: kube-master[0]
+- hosts: kube_control_plane[0]
   roles:
     - { role: tear-down }
 

contrib/network-storage/heketi/heketi.yml

@@ -3,7 +3,7 @@
   roles:
     - { role: prepare }
 
-- hosts: kube-master[0]
+- hosts: kube_control_plane[0]
   tags:
     - "provision"
   roles:

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

@@ -2,18 +2,25 @@ 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:
+        k8s_cluster:
             vars:
                 kubelet_fail_swap_on: false
             children:
-                kube-master:
+                kube_control_plane:
                     hosts:
                         node1:
                 etcd:
                     hosts:
                         node2:
-                kube-node:
+                kube_node:
                     hosts: &kube_nodes
                         node1:
                         node2:

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/tear-down.yml

@@ -6,7 +6,7 @@
 - name: "Delete bootstrap Heketi."
   command: "{{ bin_dir }}/kubectl delete all,service,jobs,deployment,secret --selector=\"deploy-heketi\""
   when: "heketi_resources.stdout|from_json|json_query('items[*]')|length > 0"
-- name: "Ensure there is nothing left over."
+- name: "Ensure there is nothing left over."  # noqa 301
   command: "{{ bin_dir }}/kubectl get all,service,jobs,deployment,secret --selector=\"deploy-heketi\" -o=json"
   register: "heketi_result"
   until: "heketi_result.stdout|from_json|json_query('items[*]')|length == 0"

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

@@ -10,10 +10,11 @@
   template:
     src: "topology.json.j2"
     dest: "{{ kube_config_dir }}/topology.json"
+    mode: 0644
 - name: "Copy topology configuration into container."
   changed_when: false
   command: "{{ bin_dir }}/kubectl cp {{ kube_config_dir }}/topology.json {{ initial_heketi_pod_name }}:/tmp/topology.json"
-- name: "Load heketi topology."
+- name: "Load heketi topology."  # noqa 503
   when: "render.changed"
   command: "{{ bin_dir }}/kubectl exec {{ initial_heketi_pod_name }} -- heketi-cli --user admin --secret {{ heketi_admin_key }} topology load --json=/tmp/topology.json"
   register: "load_heketi"

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

@@ -18,7 +18,7 @@
 - name: "Provision database volume."
   command: "{{ bin_dir }}/kubectl exec {{ initial_heketi_pod_name }} -- heketi-cli --user admin --secret {{ heketi_admin_key }} setup-openshift-heketi-storage"
   when: "heketi_database_volume_exists is undefined"
-- name: "Copy configuration from pod."
+- name: "Copy configuration from pod."  # noqa 301
   become: true
   command: "{{ bin_dir }}/kubectl cp {{ initial_heketi_pod_name }}:/heketi-storage.json {{ kube_config_dir }}/heketi-storage-bootstrap.json"
 - name: "Get heketi volume ids."

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

@@ -10,10 +10,11 @@
   template:
     src: "topology.json.j2"
     dest: "{{ kube_config_dir }}/topology.json"
-- name: "Copy topology configuration into container."
+    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"
-- name: "Load heketi topology."
+- name: "Load heketi topology."  # noqa 503
   when: "rendering.changed"
   command: "{{ bin_dir }}/kubectl exec {{ heketi_pod_name }} -- heketi-cli --user admin --secret {{ heketi_admin_key }} topology load --json=/tmp/topology.json"
 - name: "Get heketi topology."

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

@@ -12,6 +12,11 @@
         }
     },
     "spec": {
+        "selector": {
+            "matchLabels": {
+                "glusterfs-node": "daemonset"
+            }
+        },
         "template": {
             "metadata": {
                 "name": "glusterfs",
@@ -68,8 +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",
@@ -79,8 +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/provision/templates/heketi-bootstrap.json.j2

@@ -42,6 +42,11 @@
         }
       },
       "spec": {
+        "selector": {
+          "matchLabels": {
+            "name": "deploy-heketi"
+          }
+        },
         "replicas": 1,
         "template": {
           "metadata": {

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

@@ -55,6 +55,11 @@
         }
       },
       "spec": {
+        "selector": {
+          "matchLabels": {
+            "name": "heketi"
+          }
+        },
         "replicas": 1,
         "template": {
           "metadata": {

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'"
@@ -19,10 +19,10 @@
   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."
+- name: "Remove volume groups."  # noqa 301
   environment:
     PATH: "{{ ansible_env.PATH }}:/sbin"  # Make sure we can workaround RH / CentOS conservative path management
   become: true
@@ -30,16 +30,16 @@
   with_items: "{{ volume_groups.stdout_lines }}"
   loop_control: { loop_var: "volume_group" }
 
-- name: "Remove physical volume from cluster disks."
+- name: "Remove physical volume from cluster disks."  # noqa 301
   environment:
     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."
+- name: Remove storage class.  # noqa 301
   command: "{{ bin_dir }}/kubectl delete storageclass gluster"
-  ignore_errors: true
-- name: "Tear down heketi."
+  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."
+  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."
-  include_tasks: "../provision/tasks/bootstrap/tear-down.yml"
-- name: "Ensure there is nothing left over."
+  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
   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."
+- 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."
+- name: Tear down glusterfs.  # noqa 301
   command: "{{ bin_dir }}/kubectl delete daemonset.extensions/glusterfs"
-  ignore_errors: true
-- name: "Remove heketi storage service."
+  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"
+  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"
+  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"
+  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"
+  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

@@ -0,0 +1,47 @@
+# Offline deployment
+
+## manage-offline-container-images.sh
+
+Container image collecting script for offline deployment
+
+This script has two features:
+(1) Get container images from an environment which is deployed online.
+(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. 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:
+
+```shell
+manage-offline-container-images.sh   create
+```
+
+Step(2) can be operated with:
+
+```shell
+manage-offline-container-images.sh   register
+```
+
+## generate_list.sh
+
+This script generates the list of downloaded files and the list of container images by `roles/download/defaults/main.yml` file.
+
+Run this script will execute `generate_list.yml` playbook in kubespray root directory and generate four files,
+all downloaded files url in files.list, all container images in images.list, jinja2 templates in *.template.
+
+```shell
+./generate_list.sh
+tree temp
+temp
+├── files.list
+├── 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 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.

contrib/offline/docker-daemon.json

@@ -0,0 +1 @@
+{ "insecure-registries":["HOSTNAME:5000"] }

contrib/offline/generate_list.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+set -eo pipefail
+
+CURRENT_DIR=$(cd $(dirname $0); pwd)
+TEMP_DIR="${CURRENT_DIR}/temp"
+REPO_ROOT_DIR="${CURRENT_DIR%/contrib/offline}"
+
+: ${DOWNLOAD_YML:="roles/download/defaults/main.yml"}
+
+mkdir -p ${TEMP_DIR}
+
+# generate all download files url template
+grep 'download_url:' ${REPO_ROOT_DIR}/${DOWNLOAD_YML} \
+    | sed 's/^.*_url: //g;s/\"//g' > ${TEMP_DIR}/files.list.template
+
+# 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 'N;s#\n# #g' | tr ' ' ':' | sed 's/\"//g' > ${TEMP_DIR}/images.list.template
+
+# add kube-* images to images list template
+# Those container images are downloaded by kubeadm, then roles/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"
+for i in $KUBE_IMAGES; do
+    echo "{{ kube_image_repo }}/$i:{{ kube_version }}" >> ${TEMP_DIR}/images.list.template
+done
+
+# 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

@@ -0,0 +1,172 @@
+#!/bin/bash
+
+OPTION=$1
+CURRENT_DIR=$(cd $(dirname $0); pwd)
+TEMP_DIR="${CURRENT_DIR}/temp"
+
+IMAGE_TAR_FILE="${CURRENT_DIR}/container-images.tar.gz"
+IMAGE_DIR="${CURRENT_DIR}/container-images"
+IMAGE_LIST="${IMAGE_DIR}/container-images.txt"
+RETRY_COUNT=5
+
+function create_container_image_tar() {
+	set -e
+
+	IMAGES=$(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)
+	IMAGES="${IMAGES} ${EXT_IMAGES}"
+
+	rm -f  ${IMAGE_TAR_FILE}
+	rm -rf ${IMAGE_DIR}
+	mkdir  ${IMAGE_DIR}
+	cd     ${IMAGE_DIR}
+
+	sudo docker pull registry:latest
+	sudo docker save -o registry-latest.tar registry:latest
+
+	for image in ${IMAGES}
+	do
+		FILE_NAME="$(echo ${image} | sed s@"/"@"-"@g | sed s/":"/"-"/g)".tar
+		set +e
+		for step in $(seq 1 ${RETRY_COUNT})
+		do
+			sudo docker pull ${image}
+			if [ $? -eq 0 ]; then
+				break
+			fi
+			echo "Failed to pull ${image} at step ${step}"
+			if [ ${step} -eq ${RETRY_COUNT} ]; then
+				exit 1
+			fi
+		done
+		set -e
+		sudo docker save -o ${FILE_NAME}  ${image}
+
+		# NOTE: Here removes the following repo parts from each image
+		# so that these parts will be replaced with Kubespray.
+		# - kube_image_repo: "k8s.gcr.io"
+		# - gcr_image_repo: "gcr.io"
+		# - docker_image_repo: "docker.io"
+		# - quay_image_repo: "quay.io"
+		FIRST_PART=$(echo ${image} | awk -F"/" '{print $1}')
+		if [ "${FIRST_PART}" = "k8s.gcr.io" ] ||
+		   [ "${FIRST_PART}" = "gcr.io" ] ||
+		   [ "${FIRST_PART}" = "docker.io" ] ||
+		   [ "${FIRST_PART}" = "quay.io" ] ||
+		   [ "${FIRST_PART}" = "${PRIVATE_REGISTRY}" ]; then
+			image=$(echo ${image} | sed s@"${FIRST_PART}/"@@)
+		fi
+		echo "${FILE_NAME}  ${image}" >> ${IMAGE_LIST}
+	done
+
+	cd ..
+	sudo chown ${USER} ${IMAGE_DIR}/*
+	tar -zcvf ${IMAGE_TAR_FILE}  ./container-images
+	rm -rf ${IMAGE_DIR}
+
+	echo ""
+	echo "${IMAGE_TAR_FILE} is created to contain your container images."
+	echo "Please keep this file and bring it to your offline environment."
+}
+
+function register_container_images() {
+	if [ ! -f ${IMAGE_TAR_FILE} ]; then
+		echo "${IMAGE_TAR_FILE} should exist."
+		exit 1
+	fi
+	if [ ! -d ${TEMP_DIR} ]; then
+		mkdir ${TEMP_DIR}
+	fi
+
+	# To avoid "http: server gave http response to https client" error.
+	LOCALHOST_NAME=$(hostname)
+	if [ -d /etc/docker/ ]; then
+		set -e
+		# Ubuntu18.04, RHEL7/CentOS7
+		cp ${CURRENT_DIR}/docker-daemon.json      ${TEMP_DIR}/docker-daemon.json
+		sed -i s@"HOSTNAME"@"${LOCALHOST_NAME}"@  ${TEMP_DIR}/docker-daemon.json
+		sudo cp ${TEMP_DIR}/docker-daemon.json           /etc/docker/daemon.json
+	elif [ -d /etc/containers/ ]; then
+		set -e
+		# RHEL8/CentOS8
+		cp ${CURRENT_DIR}/registries.conf         ${TEMP_DIR}/registries.conf
+		sed -i s@"HOSTNAME"@"${LOCALHOST_NAME}"@  ${TEMP_DIR}/registries.conf
+		sudo cp ${TEMP_DIR}/registries.conf   /etc/containers/registries.conf
+	else
+		echo "docker package(docker-ce, etc.) should be installed"
+		exit 1
+	fi
+
+	tar -zxvf ${IMAGE_TAR_FILE}
+	sudo docker load -i ${IMAGE_DIR}/registry-latest.tar
+	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 $1}')
+		raw_image=$(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 ${new_image}
+	done <<< "$(cat ${IMAGE_LIST})"
+
+	echo "Succeeded to register container images to local registry."
+	echo "Please specify ${LOCALHOST_NAME}:5000 for the following options in your inventry:"
+	echo "- kube_image_repo"
+	echo "- gcr_image_repo"
+	echo "- docker_image_repo"
+	echo "- quay_image_repo"
+}
+
+if [ "${OPTION}" == "create" ]; then
+	create_container_image_tar
+elif [ "${OPTION}" == "register" ]; then
+	register_container_images
+else
+	echo "This script has two features:"
+	echo "(1) Get container images from an environment which is deployed online."
+	echo "(2) Deploy local container registry and register the container images to the registry."
+	echo ""
+	echo "Step(1) should be done online site as a preparation, then we bring"
+	echo "the gotten images to the target offline environment. if images are from"
+	echo "a private registry, you need to set PRIVATE_REGISTRY environment variable."
+	echo "Then we will run step(2) for registering the images to local registry."
+	echo ""
+	echo "${IMAGE_TAR_FILE} is created to contain your container images."
+	echo "Please keep this file and bring it to your offline environment."
+	echo ""
+	echo "Step(1) can be operated with:"
+	echo " $ ./manage-offline-container-images.sh   create"
+	echo ""
+	echo "Step(2) can be operated with:"
+	echo " $ ./manage-offline-container-images.sh   register"
+	echo ""
+	echo "Please specify 'create' or 'register'."
+	echo ""
+	exit 1
+fi

contrib/offline/registries.conf

@@ -0,0 +1,8 @@
+[registries.search]
+registries = ['registry.access.redhat.com', 'registry.redhat.io', 'docker.io']
+
+[registries.insecure]
+registries = ['HOSTNAME:5000']
+
+[registries.block]
+registries = []

contrib/os-services/os-services.yml

@@ -1,5 +1,4 @@
 ---
 - hosts: all
-
   roles:
-    - role_under_test
+    - { role: prepare }