Add c12s sample inventory and deploy script

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

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

.ansible-lint

@@ -18,3 +18,13 @@ skip_list:
   # While it can be useful to have these metadata available, they are also available in the existing documentation.
   # (Disabled in May 2019)
   - '701'
+
+  # [role-name] "meta/main.yml" Role name role-name does not match ``^+$`` pattern
+  # Meta roles in Kubespray don't need proper names
+  # (Disabled in June 2021)
+  - 'role-name'
+
+  # [var-naming] "defaults/main.yml" File defines variable 'apiVersion' that violates variable naming standards
+  # In Kubespray we use variables that use camelCase to match their k8s counterparts
+  # (Disabled in June 2021)
+  - 'var-naming'

.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
 
 ---
 

.gitignore

@@ -3,7 +3,10 @@
 **/vagrant_ansible_inventory
 *.iml
 temp
+contrib/offline/offline-files
+contrib/offline/offline-files.tar.gz
 .idea
+.vscode
 .tox
 .cache
 *.bak
@@ -11,15 +14,19 @@ temp
 *.tfstate.backup
 .terraform/
 contrib/terraform/aws/credentials.tfvars
+.terraform.lock.hcl
 /ssh-bastion.conf
 **/*.sw[pon]
 *~
 vagrant/
+plugins/mitogen
+deploy.sh 
 
 # Ansible inventory
 inventory/*
 !inventory/local
 !inventory/sample
+!inventory/c12s-sample
 inventory/*/artifacts/
 
 # Byte-compiled / optimized / DLL files
@@ -98,3 +105,13 @@ target/
 # virtualenv
 venv/
 ENV/
+
+# molecule
+roles/**/molecule/**/__pycache__/
+
+# macOS
+.DS_Store
+
+# Temp location used by our scripts
+scripts/tmp/
+tmp.md

.gitlab-ci.yml

@@ -8,13 +8,15 @@ stages:
   - deploy-special
 
 variables:
-  KUBESPRAY_VERSION: v2.13.3
+  KUBESPRAY_VERSION: v2.20.0
   FAILFASTCI_NAMESPACE: 'kargo-ci'
   GITLAB_REPOSITORY: 'kargo-ci/kubernetes-sigs-kubespray'
   ANSIBLE_FORCE_COLOR: "true"
   MAGIC: "ci check this"
   TEST_ID: "$CI_PIPELINE_ID-$CI_BUILD_ID"
   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: $GS_SECRET
   CONTAINER_ENGINE: docker
@@ -25,16 +27,20 @@ variables:
   ANSIBLE_INVENTORY: ./inventory/sample/${CI_JOB_NAME}-${BUILD_NUMBER}.ini
   IDEMPOT_CHECK: "false"
   RESET_CHECK: "false"
+  REMOVE_NODE_CHECK: "false"
   UPGRADE_TEST: "false"
   MITOGEN_ENABLE: "false"
   ANSIBLE_LOG_LEVEL: "-vv"
   RECOVER_CONTROL_PLANE_TEST: "false"
-  RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:],kube-master[1:]"
+  RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:],kube_control_plane[1:]"
+  TERRAFORM_VERSION: 1.0.8
+  ANSIBLE_MAJOR_VERSION: "2.11"
 
 before_script:
   - ./tests/scripts/rebase.sh
   - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
-  - python -m pip install -r tests/requirements.txt
+  - python -m pip uninstall -y ansible ansible-base ansible-core
+  - python -m pip install -r tests/requirements-${ANSIBLE_MAJOR_VERSION}.txt
   - mkdir -p /.ssh
 
 .job: &job
@@ -48,6 +54,7 @@ before_script:
 
 .testcases: &testcases
   <<: *job
+  retry: 1
   before_script:
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 1
     - ./tests/scripts/rebase.sh
@@ -74,3 +81,4 @@ include:
   - .gitlab-ci/terraform.yml
   - .gitlab-ci/packet.yml
   - .gitlab-ci/vagrant.yml
+  - .gitlab-ci/molecule.yml

.gitlab-ci/lint.yml

@@ -14,7 +14,7 @@ vagrant-validate:
   stage: unit-tests
   tags: [light]
   variables:
-    VAGRANT_VERSION: 2.2.4
+    VAGRANT_VERSION: 2.2.19
   script:
     - ./tests/scripts/vagrant-validate.sh
   except: ['triggers', 'master']
@@ -23,9 +23,8 @@ ansible-lint:
   extends: .job
   stage: unit-tests
   tags: [light]
-  # lint every yml/yaml file that looks like it contains Ansible plays
-  script: |-
-    grep -Rl '^- hosts: \|^  hosts: ' --include \*.yml --include \*.yaml . | xargs -P 4 -n 25 ansible-lint -v
+  script:
+    - ansible-lint -v
   except: ['triggers', 'master']
 
 syntax-check:
@@ -53,6 +52,7 @@ tox-inventory-builder:
     - ./tests/scripts/rebase.sh
     - apt-get update && apt-get install -y python3-pip
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 10
+    - python -m pip uninstall -y ansible ansible-base ansible-core
     - python -m pip install -r tests/requirements.txt
   script:
     - pip3 install tox
@@ -64,9 +64,23 @@ markdownlint:
   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
+
+check-readme-versions:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/check_readme_versions.sh
+
+check-typo:
+  stage: unit-tests
+  tags: [light]
+  image: python:3
+  script:
+    - tests/scripts/check_typo.sh
 
 ci-matrix:
   stage: unit-tests

.gitlab-ci/molecule.yml

@@ -0,0 +1,86 @@
+---
+
+.molecule:
+  tags: [c3.small.x86]
+  only: [/^pr-.*$/]
+  except: ['triggers']
+  image: quay.io/kubespray/vagrant:$KUBESPRAY_VERSION
+  services: []
+  stage: deploy-part1
+  before_script:
+    - tests/scripts/rebase.sh
+    - apt-get update && apt-get install -y python3-pip
+    - update-alternatives --install /usr/bin/python python /usr/bin/python3 10
+    - python -m pip uninstall -y ansible ansible-base ansible-core
+    - python -m pip install -r tests/requirements.txt
+    - ./tests/scripts/vagrant_clean.sh
+  script:
+    - ./tests/scripts/molecule_run.sh
+  after_script:
+    - chronic ./tests/scripts/molecule_logs.sh
+  artifacts:
+    when: always
+    paths:
+      - molecule_logs/
+
+# CI template for periodic CI jobs
+# Enabled when PERIODIC_CI_ENABLED var is set
+.molecule_periodic:
+  only:
+    variables:
+      - $PERIODIC_CI_ENABLED
+  allow_failure: true
+  extends: .molecule
+
+molecule_full:
+  extends: .molecule_periodic
+
+molecule_no_container_engines:
+  extends: .molecule
+  script:
+    - ./tests/scripts/molecule_run.sh -e container-engine
+  when: on_success
+
+molecule_docker:
+  extends: .molecule
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/cri-dockerd
+  when: on_success
+
+molecule_containerd:
+  extends: .molecule
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/containerd
+  when: on_success
+
+molecule_cri-o:
+  extends: .molecule
+  stage: deploy-part2
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/cri-o
+  when: on_success
+
+# Stage 3 container engines don't get as much attention so allow them to fail
+molecule_kata:
+  extends: .molecule
+  stage: deploy-part3
+  allow_failure: true
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/kata-containers
+  when: on_success
+
+molecule_gvisor:
+  extends: .molecule
+  stage: deploy-part3
+  allow_failure: true
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/gvisor
+  when: on_success
+
+molecule_youki:
+  extends: .molecule
+  stage: deploy-part3
+  allow_failure: true
+  script:
+    - ./tests/scripts/molecule_run.sh -i container-engine/youki
+  when: on_success

.gitlab-ci/packet.yml

@@ -1,88 +1,139 @@
 ---
-.packet: &packet
+.packet:
   extends: .testcases
   variables:
-    CI_PLATFORM: "packet"
-    SSH_USER: "kubespray"
+    ANSIBLE_TIMEOUT: "120"
+    CI_PLATFORM: packet
+    SSH_USER: kubespray
   tags:
     - packet
+  except: [triggers]
+
+# CI template for PRs
+.packet_pr:
   only: [/^pr-.*$/]
-  except: ['triggers']
-
-packet_ubuntu18-calico-aio:
-  stage: deploy-part1
   extends: .packet
-  when: on_success
 
-# Future AIO job
+# 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
+  extends: .packet_pr
   when: on_success
+  variables:
+    RESET_CHECK: "true"
+
+packet_ubuntu20-calico-aio-ansible-2_11:
+  stage: deploy-part1
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    ANSIBLE_MAJOR_VERSION: "2.11"
+    RESET_CHECK: "true"
 
 # ### PR JOBS PART2
 
-packet_centos7-flannel-containerd-addons-ha:
-  extends: .packet
+packet_ubuntu18-aio-docker:
   stage: deploy-part2
+  extends: .packet_pr
   when: on_success
-  variables:
-    MITOGEN_ENABLE: "true"
 
-packet_centos7-crio:
-  extends: .packet
+packet_ubuntu20-aio-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_ubuntu20-calico-aio-hardening:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_ubuntu18-calico-aio:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_ubuntu22-aio-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_ubuntu22-calico-aio:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_centos7-flannel-addons-ha:
+  extends: .packet_pr
+  stage: deploy-part2
+  when: on_success
+
+packet_almalinux8-crio:
+  extends: .packet_pr
   stage: deploy-part2
   when: on_success
-  variables:
-    MITOGEN_ENABLE: "true"
 
 packet_ubuntu18-crio:
-  extends: .packet
+  extends: .packet_pr
   stage: deploy-part2
   when: manual
-  variables:
-    MITOGEN_ENABLE: "true"
 
-packet_ubuntu16-canal-kubeadm-ha:
+packet_fedora35-crio:
+  extends: .packet_pr
   stage: deploy-part2
-  extends: .packet
+  when: manual
+
+packet_ubuntu16-canal-ha:
+  stage: deploy-part2
+  extends: .packet_periodic
   when: on_success
 
 packet_ubuntu16-canal-sep:
   stage: deploy-special
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
 packet_ubuntu16-flannel-ha:
   stage: deploy-part2
-  extends: .packet
-  when: manual
-
-packet_ubuntu16-kube-router-sep:
-  stage: deploy-part2
-  extends: .packet
-  when: manual
-
-packet_ubuntu16-kube-router-svc-proxy:
-  stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
 packet_debian10-cilium-svc-proxy:
   stage: deploy-part2
-  extends: .packet
-  when: manual
-
-packet_debian10-containerd:
-  stage: deploy-part2
-  extends: .packet
+  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
-  variables:
-    MITOGEN_ENABLE: "true"
 
 packet_centos7-calico-ha-once-localhost:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: on_success
   variables:
     # This will instruct Docker not to start over TLS.
@@ -90,99 +141,124 @@ packet_centos7-calico-ha-once-localhost:
   services:
     - docker:19.03.9-dind
 
-packet_centos8-kube-ovn:
+packet_almalinux8-kube-ovn:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_periodic
   when: on_success
 
-packet_centos8-calico:
+packet_almalinux8-calico:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: on_success
 
-packet_fedora32-weave:
+packet_rockylinux8-calico:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
+  when: on_success
+
+packet_rockylinux9-calico:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_almalinux8-docker:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: on_success
+
+packet_fedora36-docker-weave:
+  stage: deploy-part2
+  extends: .packet_pr
   when: on_success
 
 packet_opensuse-canal:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_periodic
   when: on_success
 
-packet_ubuntu18-ovn4nfv:
+packet_opensuse-docker-cilium:
   stage: deploy-part2
-  extends: .packet
-  when: on_success
-
-# Contiv does not work in k8s v1.16
-# packet_ubuntu16-contiv-sep:
-#   stage: deploy-part2
-#   extends: .packet
-#   when: on_success
+  extends: .packet_pr
+  when: manual
 
 # ### MANUAL JOBS
 
-packet_ubuntu16-weave-sep:
+packet_ubuntu16-docker-weave-sep:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
 packet_ubuntu18-cilium-sep:
   stage: deploy-special
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-packet_ubuntu18-flannel-containerd-ha:
+packet_ubuntu18-flannel-ha:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-packet_ubuntu18-flannel-containerd-ha-once:
+packet_ubuntu18-flannel-ha-once:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
+  when: manual
+
+# Calico HA eBPF
+packet_almalinux8-calico-ha-ebpf:
+  stage: deploy-part2
+  extends: .packet_pr
   when: manual
 
 packet_debian9-macvlan:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
 packet_centos7-calico-ha:
   stage: deploy-part2
-  extends: .packet
-  when: manual
-
-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_oracle7-canal-ha:
+packet_centos7-canal-ha:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-packet_fedora31-flannel:
+packet_fedora36-docker-calico:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_periodic
   when: on_success
   variables:
-    MITOGEN_ENABLE: "true"
+    RESET_CHECK: "true"
+
+packet_fedora35-calico-selinux:
+  stage: deploy-part2
+  extends: .packet_periodic
+  when: on_success
+
+packet_fedora35-calico-swap-selinux:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
 
 packet_amazon-linux-2-aio:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
   when: manual
 
-packet_fedora32-kube-ovn-containerd:
+packet_almalinux8-calico-nodelocaldns-secondary:
   stage: deploy-part2
-  extends: .packet
+  extends: .packet_pr
+  when: manual
+
+packet_fedora36-kube-ovn:
+  stage: deploy-part2
+  extends: .packet_periodic
   when: on_success
 
 # ### PR JOBS PART3
@@ -190,40 +266,63 @@ packet_fedora32-kube-ovn-containerd:
 
 packet_centos7-weave-upgrade-ha:
   stage: deploy-part3
-  extends: .packet
+  extends: .packet_periodic
   when: on_success
   variables:
     UPGRADE_TEST: basic
-    MITOGEN_ENABLE: "false"
 
-packet_debian9-calico-upgrade:
+packet_ubuntu20-calico-etcd-kubeadm-upgrade-ha:
   stage: deploy-part3
-  extends: .packet
+  extends: .packet_periodic
+  when: on_success
+  variables:
+    UPGRADE_TEST: basic
+
+# Calico HA Wireguard
+packet_ubuntu20-calico-ha-wireguard:
+  stage: deploy-part2
+  extends: .packet_pr
+  when: manual
+
+packet_debian11-calico-upgrade:
+  stage: deploy-part3
+  extends: .packet_pr
   when: on_success
   variables:
     UPGRADE_TEST: graceful
-    MITOGEN_ENABLE: "false"
 
-packet_debian9-calico-upgrade-once:
+packet_almalinux8-calico-remove-node:
   stage: deploy-part3
-  extends: .packet
+  extends: .packet_pr
+  when: on_success
+  variables:
+    REMOVE_NODE_CHECK: "true"
+    REMOVE_NODE_NAME: "instance-3"
+
+packet_ubuntu20-calico-etcd-kubeadm:
+  stage: deploy-part3
+  extends: .packet_pr
+  when: on_success
+
+packet_debian11-calico-upgrade-once:
+  stage: deploy-part3
+  extends: .packet_periodic
   when: on_success
   variables:
     UPGRADE_TEST: graceful
-    MITOGEN_ENABLE: "false"
 
 packet_ubuntu18-calico-ha-recover:
   stage: deploy-part3
-  extends: .packet
+  extends: .packet_periodic
   when: on_success
   variables:
     RECOVER_CONTROL_PLANE_TEST: "true"
-    RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:],kube-master[1:]"
+    RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:],kube_control_plane[1:]"
 
 packet_ubuntu18-calico-ha-recover-noquorum:
   stage: deploy-part3
-  extends: .packet
+  extends: .packet_periodic
   when: on_success
   variables:
     RECOVER_CONTROL_PLANE_TEST: "true"
-    RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[1:],kube-master[1:]"
+    RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[1:],kube_control_plane[1:]"

.gitlab-ci/shellcheck.yml

@@ -4,13 +4,13 @@ shellcheck:
   stage: unit-tests
   tags: [light]
   variables:
-    SHELLCHECK_VERSION: v0.6.0
+    SHELLCHECK_VERSION: v0.7.1
   before_script:
     - ./tests/scripts/rebase.sh
     - curl --silent --location "https://github.com/koalaman/shellcheck/releases/download/"${SHELLCHECK_VERSION}"/shellcheck-"${SHELLCHECK_VERSION}".linux.x86_64.tar.xz" | tar -xJv
     - cp shellcheck-"${SHELLCHECK_VERSION}"/shellcheck /usr/bin/
     - shellcheck --version
   script:
-    # Run shellcheck for all *.sh except contrib/
-    - find . -name '*.sh' -not -path './contrib/*' | xargs shellcheck --severity error
+    # Run shellcheck for all *.sh
+    - find . -name '*.sh' -not -path './.git/*' | xargs shellcheck --severity error
   except: ['triggers', 'master']

.gitlab-ci/terraform.yml

@@ -12,13 +12,13 @@
     # Prepare inventory
     - cp contrib/terraform/$PROVIDER/sample-inventory/cluster.tfvars .
     - ln -s contrib/terraform/$PROVIDER/hosts
-    - terraform init contrib/terraform/$PROVIDER
+    - terraform -chdir="contrib/terraform/$PROVIDER" init
     # Copy SSH keypair
     - mkdir -p ~/.ssh
     - echo "$PACKET_PRIVATE_KEY" | base64 -d > ~/.ssh/id_rsa
     - chmod 400 ~/.ssh/id_rsa
     - echo "$PACKET_PUBLIC_KEY" | base64 -d > ~/.ssh/id_rsa.pub
-    - mkdir -p group_vars
+    - mkdir -p contrib/terraform/$PROVIDER/group_vars
     # Random subnet to avoid routing conflicts
     - export TF_VAR_subnet_cidr="10.$(( $RANDOM % 256 )).$(( $RANDOM % 256 )).0/24"
 
@@ -28,8 +28,8 @@
   tags: [light]
   only: ['master', /^pr-.*$/]
   script:
-    - terraform validate -var-file=cluster.tfvars contrib/terraform/$PROVIDER
-    - terraform fmt -check -diff contrib/terraform/$PROVIDER
+    - terraform -chdir="contrib/terraform/$PROVIDER" validate
+    - terraform -chdir="contrib/terraform/$PROVIDER" fmt -check -diff
 
 .terraform_apply:
   extends: .terraform_install
@@ -56,28 +56,48 @@
 tf-validate-openstack:
   extends: .terraform_validate
   variables:
-    TF_VERSION: 0.12.24
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: openstack
     CLUSTER: $CI_COMMIT_REF_NAME
 
-tf-validate-packet:
+tf-validate-metal:
   extends: .terraform_validate
   variables:
-    TF_VERSION: 0.12.24
-    PROVIDER: packet
+    TF_VERSION: $TERRAFORM_VERSION
+    PROVIDER: metal
     CLUSTER: $CI_COMMIT_REF_NAME
 
 tf-validate-aws:
   extends: .terraform_validate
   variables:
-    TF_VERSION: 0.12.24
+    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: 0.12.24
+#     TF_VERSION: $TERRAFORM_VERSION
 #     PROVIDER: packet
 #     CLUSTER: $CI_COMMIT_REF_NAME
 #     TF_VAR_number_of_k8s_masters: "1"
@@ -91,7 +111,7 @@ tf-validate-aws:
 # tf-packet-ubuntu18-default:
 #   extends: .terraform_apply
 #   variables:
-#     TF_VERSION: 0.12.24
+#     TF_VERSION: $TERRAFORM_VERSION
 #     PROVIDER: packet
 #     CLUSTER: $CI_COMMIT_REF_NAME
 #     TF_VAR_number_of_k8s_masters: "1"
@@ -126,10 +146,6 @@ tf-validate-aws:
   OS_INTERFACE: public
   OS_IDENTITY_API_VERSION: "3"
   TF_VAR_router_id: "ab95917c-41fb-4881-b507-3a6dfe9403df"
-  # Since ELASTX is in Stockholm, Mitogen helps with latency
-  MITOGEN_ENABLE: "false"
-  # Mitogen doesn't support interpreter discovery yet
-  ANSIBLE_PYTHON_INTERPRETER: "/usr/bin/python3"
 
 tf-elastx_cleanup:
   stage: unit-tests
@@ -146,9 +162,10 @@ tf-elastx_ubuntu18-calico:
   extends: .terraform_apply
   stage: deploy-part3
   when: on_success
+  allow_failure: true
   variables:
     <<: *elastx_variables
-    TF_VERSION: 0.12.24
+    TF_VERSION: $TERRAFORM_VERSION
     PROVIDER: openstack
     CLUSTER: $CI_COMMIT_REF_NAME
     ANSIBLE_TIMEOUT: "60"
@@ -174,44 +191,45 @@ tf-elastx_ubuntu18-calico:
     TF_VAR_image: ubuntu-18.04-server-latest
     TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'
 
+# OVH voucher expired, commenting job until things are sorted  out
 
-tf-ovh_cleanup:
-  stage: unit-tests
-  tags: [light]
-  image: python
-  environment: ovh
-  variables:
-    <<: *ovh_variables
-  before_script:
-    - pip install -r scripts/openstack-cleanup/requirements.txt
-  script:
-    - ./scripts/openstack-cleanup/main.py
+# tf-ovh_cleanup:
+#  stage: unit-tests
+#  tags: [light]
+#  image: python
+#  environment: ovh
+#  variables:
+#    <<: *ovh_variables
+#  before_script:
+#    - pip install -r scripts/openstack-cleanup/requirements.txt
+#  script:
+#    - ./scripts/openstack-cleanup/main.py
 
-tf-ovh_ubuntu18-calico:
-  extends: .terraform_apply
-  when: on_success
-  environment: ovh
-  variables:
-    <<: *ovh_variables
-    TF_VERSION: 0.12.24
-    PROVIDER: openstack
-    CLUSTER: $CI_COMMIT_REF_NAME
-    ANSIBLE_TIMEOUT: "60"
-    SSH_USER: ubuntu
-    TF_VAR_number_of_k8s_masters: "0"
-    TF_VAR_number_of_k8s_masters_no_floating_ip: "1"
-    TF_VAR_number_of_k8s_masters_no_floating_ip_no_etcd: "0"
-    TF_VAR_number_of_etcd: "0"
-    TF_VAR_number_of_k8s_nodes: "0"
-    TF_VAR_number_of_k8s_nodes_no_floating_ip: "1"
-    TF_VAR_number_of_gfs_nodes_no_floating_ip: "0"
-    TF_VAR_number_of_bastions: "0"
-    TF_VAR_number_of_k8s_masters_no_etcd: "0"
-    TF_VAR_use_neutron: "0"
-    TF_VAR_floatingip_pool: "Ext-Net"
-    TF_VAR_external_net: "6011fbc9-4cbf-46a4-8452-6890a340b60b"
-    TF_VAR_network_name: "Ext-Net"
-    TF_VAR_flavor_k8s_master: "defa64c3-bd46-43b4-858a-d93bbae0a229"    # s1-8
-    TF_VAR_flavor_k8s_node: "defa64c3-bd46-43b4-858a-d93bbae0a229"      # s1-8
-    TF_VAR_image: "Ubuntu 18.04"
-    TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'
+# tf-ovh_ubuntu18-calico:
+#  extends: .terraform_apply
+#  when: on_success
+#  environment: ovh
+#  variables:
+#    <<: *ovh_variables
+#    TF_VERSION: $TERRAFORM_VERSION
+#    PROVIDER: openstack
+#    CLUSTER: $CI_COMMIT_REF_NAME
+#    ANSIBLE_TIMEOUT: "60"
+#    SSH_USER: ubuntu
+#    TF_VAR_number_of_k8s_masters: "0"
+#    TF_VAR_number_of_k8s_masters_no_floating_ip: "1"
+#    TF_VAR_number_of_k8s_masters_no_floating_ip_no_etcd: "0"
+#    TF_VAR_number_of_etcd: "0"
+#    TF_VAR_number_of_k8s_nodes: "0"
+#    TF_VAR_number_of_k8s_nodes_no_floating_ip: "1"
+#    TF_VAR_number_of_gfs_nodes_no_floating_ip: "0"
+#    TF_VAR_number_of_bastions: "0"
+#    TF_VAR_number_of_k8s_masters_no_etcd: "0"
+#    TF_VAR_use_neutron: "0"
+#    TF_VAR_floatingip_pool: "Ext-Net"
+#    TF_VAR_external_net: "6011fbc9-4cbf-46a4-8452-6890a340b60b"
+#    TF_VAR_network_name: "Ext-Net"
+#    TF_VAR_flavor_k8s_master: "defa64c3-bd46-43b4-858a-d93bbae0a229"    # s1-8
+#    TF_VAR_flavor_k8s_node: "defa64c3-bd46-43b4-858a-d93bbae0a229"      # s1-8
+#    TF_VAR_image: "Ubuntu 18.04"
+#    TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'

.gitlab-ci/vagrant.yml

@@ -1,21 +1,5 @@
 ---
 
-molecule_tests:
-  tags: [c3.small.x86]
-  only: [/^pr-.*$/]
-  except: ['triggers']
-  image: quay.io/kubespray/vagrant:$KUBESPRAY_VERSION
-  services: []
-  stage: deploy-part1
-  before_script:
-    - tests/scripts/rebase.sh
-    - apt-get update && apt-get install -y python3-pip
-    - update-alternatives --install /usr/bin/python python /usr/bin/python3 10
-    - python -m pip install -r tests/requirements.txt
-    - ./tests/scripts/vagrant_clean.sh
-  script:
-    - ./tests/scripts/molecule_run.sh
-
 .vagrant:
   extends: .testcases
   variables:
@@ -31,12 +15,19 @@ molecule_tests:
   before_script:
     - apt-get update && apt-get install -y python3-pip
     - update-alternatives --install /usr/bin/python python /usr/bin/python3 10
+    - python -m pip uninstall -y ansible ansible-base ansible-core
     - python -m pip install -r tests/requirements.txt
     - ./tests/scripts/vagrant_clean.sh
   script:
     - ./tests/scripts/testcases_run.sh
   after_script:
     - chronic ./tests/scripts/testcases_cleanup.sh
+  allow_failure: true
+
+vagrant_ubuntu18-calico-dual-stack:
+  stage: deploy-part2
+  extends: .vagrant
+  when: on_success
 
 vagrant_ubuntu18-flannel:
   stage: deploy-part2
@@ -52,3 +43,25 @@ vagrant_ubuntu20-flannel:
   stage: deploy-part2
   extends: .vagrant
   when: on_success
+  allow_failure: false
+
+vagrant_ubuntu16-kube-router-sep:
+  stage: deploy-part2
+  extends: .vagrant
+  when: manual
+
+# Service proxy test fails connectivity testing
+vagrant_ubuntu16-kube-router-svc-proxy:
+  stage: deploy-part2
+  extends: .vagrant
+  when: manual
+
+vagrant_fedora35-kube-router:
+  stage: deploy-part2
+  extends: .vagrant
+  when: on_success
+
+vagrant_centos7-kube-router:
+  stage: deploy-part2
+  extends: .vagrant
+  when: manual

.markdownlint.yaml

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

.pre-commit-config.yaml

@@ -0,0 +1,48 @@
+---
+repos:
+  - repo: https://github.com/adrienverge/yamllint.git
+    rev: v1.27.1
+    hooks:
+      - id: yamllint
+        args: [--strict]
+
+  - repo: https://github.com/markdownlint/markdownlint
+    rev: v0.11.0
+    hooks:
+      - id: markdownlint
+        args: [ -r, "~MD013,~MD029" ]
+        exclude: "^.git"
+
+  - repo: local
+    hooks:
+      - id: ansible-lint
+        name: ansible-lint
+        entry: ansible-lint -v
+        language: python
+        pass_filenames: false
+        additional_dependencies:
+          - .[community]
+
+      - id: ansible-syntax-check
+        name: ansible-syntax-check
+        entry: env ANSIBLE_INVENTORY=inventory/local-tests.cfg ANSIBLE_REMOTE_USER=root ANSIBLE_BECOME="true" ANSIBLE_BECOME_USER=root ANSIBLE_VERBOSITY="3" ansible-playbook --syntax-check
+        language: python
+        files: "^cluster.yml|^upgrade-cluster.yml|^reset.yml|^extra_playbooks/upgrade-only-k8s.yml"
+
+      - id: tox-inventory-builder
+        name: tox-inventory-builder
+        entry: bash -c "cd contrib/inventory_builder && tox"
+        language: python
+        pass_filenames: false
+
+      - id: check-readme-versions
+        name: check-readme-versions
+        entry: tests/scripts/check_readme_versions.sh
+        language: script
+        pass_filenames: false
+
+      - id: ci-matrix
+        name: ci-matrix
+        entry: tests/scripts/md-table/test.sh
+        language: script
+        pass_filenames: false

.yamllint

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

CONTRIBUTING.md

@@ -6,11 +6,22 @@
 
 It is recommended to use filter to manage the GitHub email notification, see [examples for setting filters to Kubernetes Github notifications](https://github.com/kubernetes/community/blob/master/communication/best-practices.md#examples-for-setting-filters-to-kubernetes-github-notifications)
 
-To install development dependencies you can use `pip install -r tests/requirements.txt`
+To install development dependencies you can set up a python virtual env with the necessary dependencies:
+
+```ShellSession
+virtualenv venv
+source venv/bin/activate
+pip install -r tests/requirements.txt
+```
 
 #### Linting
 
-Kubespray uses `yamllint` and `ansible-lint`. To run them locally use `yamllint .` and `./tests/scripts/ansible-lint.sh`
+Kubespray uses [pre-commit](https://pre-commit.com) hook configuration to run several linters, please install this tool and use it to run validation tests before submitting a PR.
+
+```ShellSession
+pre-commit install
+pre-commit run -a  # To run pre-commit hook on all files in the repository, even if they were not modified
+```
 
 #### Molecule
 
@@ -27,5 +38,9 @@ Vagrant with VirtualBox or libvirt driver helps you to quickly spin test cluster
 1. Submit an issue describing your proposed change to the repo in question.
 2. The [repo owners](OWNERS) will respond to your issue promptly.
 3. Fork the desired repo, develop and test your code changes.
-4. Sign the CNCF CLA (<https://git.k8s.io/community/CLA.md#the-contributor-license-agreement>)
-5. Submit a pull request.
+4. Install [pre-commit](https://pre-commit.com) and install it in your development repo.
+5. Addess any pre-commit validation failures.
+6. Sign the CNCF CLA (<https://git.k8s.io/community/CLA.md#the-contributor-license-agreement>)
+7. Submit a pull request.
+8. Work with the reviewers on their suggestions.
+9. Ensure to rebase to the HEAD of your target branch and squash un-necessary commits (<https://blog.carbonfive.com/always-squash-and-rebase-your-git-commits/>) before final merger of your contribution.

Dockerfile

@@ -1,21 +1,37 @@
-FROM ubuntu:18.04
+# Use imutable image tags rather than mutable tags (like ubuntu:20.04)
+FROM ubuntu:focal-20220531
 
-RUN mkdir /kubespray
-WORKDIR /kubespray
-RUN apt update -y && \
-    apt install -y \
+ARG ARCH=amd64
+ARG TZ=Etc/UTC
+RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && echo $TZ > /etc/timezone
+
+RUN apt update -y \
+    && apt install -y \
     libssl-dev python3-dev sshpass apt-transport-https jq moreutils \
-    ca-certificates curl gnupg2 software-properties-common python3-pip rsync
-RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add - && \
-    add-apt-repository \
-    "deb [arch=amd64] https://download.docker.com/linux/ubuntu \
+    ca-certificates curl gnupg2 software-properties-common python3-pip unzip rsync git \
+    && rm -rf /var/lib/apt/lists/*
+RUN curl -fsSL https://download.docker.com/linux/ubuntu/gpg | apt-key add - \
+    && add-apt-repository \
+    "deb [arch=$ARCH] https://download.docker.com/linux/ubuntu \
     $(lsb_release -cs) \
     stable" \
-    && apt update -y && apt-get install 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/v1.17.5/bin/linux/amd64/kubectl \
-    && chmod a+x kubectl && cp kubectl /usr/local/bin/kubectl
+    && apt update -y && apt-get install --no-install-recommends -y docker-ce \
+    && rm -rf /var/lib/apt/lists/*
 
 # Some tools like yamllint need this
+# Pip needs this as well at the moment to install ansible
+# (and potentially other packages)
+# See: https://github.com/pypa/pip/issues/10219
 ENV LANG=C.UTF-8
+
+WORKDIR /kubespray
+COPY . .
+RUN /usr/bin/python3 -m pip install --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.yml -vv
+	@echo Mitogen support is deprecated.
+	@echo Please run the following command manually:
+	@echo   ansible-playbook -c local mitogen.yml -vv
 clean:
 	rm -rf dist/
 	rm *.retry

OWNERS

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

OWNERS_ALIASES

@@ -1,19 +1,26 @@
 aliases:
   kubespray-approvers:
-    - ant31
     - mattymo
-    - atoms
     - chadswen
     - mirwan
     - miouge1
-    - riverzhang
-    - verwilst
-    - woopstar
     - luckysb
+    - floryut
+    - oomichi
+    - cristicalin
+    - liupeng0518
+    - yankay
   kubespray-reviewers:
-    - jjungnickel
-    - archifleks
     - holmsten
     - bozzo
-    - floryut
     - eppo
+    - oomichi
+    - jayonlau
+    - cristicalin
+    - liupeng0518
+    - yankay
+  kubespray-emeritus_approvers:
+    - riverzhang
+    - atoms
+    - ant31
+    - woopstar

README.md

@@ -5,7 +5,7 @@
 If you have questions, check the documentation at [kubespray.io](https://kubespray.io) and join us on the [kubernetes slack](https://kubernetes.slack.com), channel **\#kubespray**.
 You can get your invite [here](http://slack.k8s.io/)
 
-- Can be deployed on **[AWS](docs/aws.md), GCE, [Azure](docs/azure.md), [OpenStack](docs/openstack.md), [vSphere](docs/vsphere.md), [Packet](docs/packet.md) (bare metal), Oracle Cloud Infrastructure (Experimental), or Baremetal**
+- Can be deployed on **[AWS](docs/aws.md), GCE, [Azure](docs/azure.md), [OpenStack](docs/openstack.md), [vSphere](docs/vsphere.md), [Equinix Metal](docs/equinix-metal.md) (bare metal), Oracle Cloud Infrastructure (Experimental), or Baremetal**
 - **Highly available** cluster
 - **Composable** (Choice of the network plugin for instance)
 - Supports most popular **Linux distributions**
@@ -19,10 +19,10 @@ To deploy the cluster you can use :
 
 #### Usage
 
-```ShellSession
-# Install dependencies from ``requirements.txt``
-sudo pip3 install -r requirements.txt
+Install Ansible according to [Ansible installation guide](/docs/ansible.md#installing-ansible)
+then run the following steps:
 
+```ShellSession
 # Copy ``inventory/sample`` as ``inventory/mycluster``
 cp -rfp inventory/sample inventory/mycluster
 
@@ -32,7 +32,7 @@ CONFIG_FILE=inventory/mycluster/hosts.yaml python3 contrib/inventory_builder/inv
 
 # Review and change parameters under ``inventory/mycluster/group_vars``
 cat inventory/mycluster/group_vars/all/all.yml
-cat inventory/mycluster/group_vars/k8s-cluster/k8s-cluster.yml
+cat inventory/mycluster/group_vars/k8s_cluster/k8s-cluster.yml
 
 # Deploy Kubespray with Ansible Playbook - run the playbook as root
 # The option `--become` is required, as for example writing SSL keys in /etc/,
@@ -48,11 +48,24 @@ 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
+git checkout v2.20.0
+docker pull quay.io/kubespray/kubespray:v2.20.0
+docker run --rm -it --mount type=bind,source="$(pwd)"/inventory/sample,dst=/inventory \
+  --mount type=bind,source="${HOME}"/.ssh/id_rsa,dst=/root/.ssh/id_rsa \
+  quay.io/kubespray/kubespray:v2.20.0 bash
+# Inside the container you may now run the kubespray playbooks:
+ansible-playbook -i /inventory/inventory.ini --private-key /root/.ssh/id_rsa cluster.yml
+```
+
 ### Vagrant
 
 For Vagrant we need to install python dependencies for provisioning tasks.
@@ -63,10 +76,11 @@ python -V && pip -V
 ```
 
 If this returns the version of the software, you're good to go. If not, download and install Python from here <https://www.python.org/downloads/source/>
-Install the necessary requirements
+
+Install Ansible according to [Ansible installation guide](/docs/ansible.md#installing-ansible)
+then run the following step:
 
 ```ShellSession
-sudo pip install -r requirements.txt
 vagrant up
 ```
 
@@ -93,63 +107,85 @@ vagrant up
 - [AWS](docs/aws.md)
 - [Azure](docs/azure.md)
 - [vSphere](docs/vsphere.md)
-- [Packet Host](docs/packet.md)
+- [Equinix Metal](docs/equinix-metal.md)
 - [Large deployments](docs/large-deployments.md)
 - [Adding/replacing a node](docs/nodes.md)
 - [Upgrades basics](docs/upgrades.md)
 - [Air-Gap installation](docs/offline-environment.md)
+- [NTP](docs/ntp.md)
+- [Hardening](docs/hardening.md)
+- [Mirror](docs/mirror.md)
 - [Roadmap](docs/roadmap.md)
 
 ## Supported Linux Distributions
 
 - **Flatcar Container Linux by Kinvolk**
-- **Debian** Buster, Jessie, Stretch, Wheezy
-- **Ubuntu** 16.04, 18.04, 20.04
-- **CentOS/RHEL** 7, 8 (experimental: see [centos 8 notes](docs/centos8.md))
-- **Fedora** 31, 32
-- **Fedora CoreOS** (experimental: see [fcos Note](docs/fcos.md))
-- **openSUSE** Leap 42.3/Tumbleweed
-- **Oracle Linux** 7, 8 (experimental: [centos 8 notes](docs/centos8.md) apply)
+- **Debian** Bullseye, Buster, Jessie, Stretch
+- **Ubuntu** 16.04, 18.04, 20.04, 22.04
+- **CentOS/RHEL** 7, [8, 9](docs/centos.md#centos-8)
+- **Fedora** 35, 36
+- **Fedora CoreOS** (see [fcos Note](docs/fcos.md))
+- **openSUSE** Leap 15.x/Tumbleweed
+- **Oracle Linux** 7, [8, 9](docs/centos.md#centos-8)
+- **Alma Linux** [8, 9](docs/centos.md#centos-8)
+- **Rocky Linux** [8, 9](docs/centos.md#centos-8)
+- **Kylin Linux Advanced Server V10** (experimental: see [kylin linux notes](docs/kylinlinux.md))
+- **Amazon Linux 2** (experimental: see [amazon linux notes](docs/amazonlinux.md))
+- **UOS Linux** (experimental: see [uos linux notes](docs/uoslinux.md))
+- **openEuler** (experimental: see [openEuler notes](docs/openeuler.md))
 
 Note: Upstart/SysV init based OS types are not supported.
 
 ## Supported Components
 
 - Core
-  - [kubernetes](https://github.com/kubernetes/kubernetes) v1.18.8
-  - [etcd](https://github.com/coreos/etcd) v3.4.3
-  - [docker](https://www.docker.com/) v19.03 (see note)
-  - [containerd](https://containerd.io/) v1.2.13
-  - [cri-o](http://cri-o.io/) v1.17 (experimental: see [CRI-O Note](docs/cri-o.md). Only on fedora, ubuntu and centos based OS)
+  - [kubernetes](https://github.com/kubernetes/kubernetes) v1.25.5
+  - [etcd](https://github.com/etcd-io/etcd) v3.5.6
+  - [docker](https://www.docker.com/) v20.10 (see note)
+  - [containerd](https://containerd.io/) v1.6.14
+  - [cri-o](http://cri-o.io/) v1.24 (experimental: see [CRI-O Note](docs/cri-o.md). Only on fedora, ubuntu and centos based OS)
 - Network Plugin
-  - [cni-plugins](https://github.com/containernetworking/plugins) v0.8.6
-  - [calico](https://github.com/projectcalico/calico) v3.15.2
+  - [cni-plugins](https://github.com/containernetworking/plugins) v1.1.1
+  - [calico](https://github.com/projectcalico/calico) v3.24.5
   - [canal](https://github.com/projectcalico/canal) (given calico/flannel versions)
-  - [cilium](https://github.com/cilium/cilium) v1.8.3
-  - [contiv](https://github.com/contiv/install) v1.2.1
-  - [flanneld](https://github.com/coreos/flannel) v0.12.0
-  - [kube-ovn](https://github.com/alauda/kube-ovn) v1.3.0
-  - [kube-router](https://github.com/cloudnativelabs/kube-router) v1.0.1
-  - [multus](https://github.com/intel/multus-cni) v3.6.0
-  - [ovn4nfv](https://github.com/opnfv/ovn4nfv-k8s-plugin) v1.1.0
-  - [weave](https://github.com/weaveworks/weave) v2.7.0
+  - [cilium](https://github.com/cilium/cilium) v1.12.1
+  - [flannel](https://github.com/flannel-io/flannel) v0.19.2
+  - [kube-ovn](https://github.com/alauda/kube-ovn) v1.10.7
+  - [kube-router](https://github.com/cloudnativelabs/kube-router) v1.5.1
+  - [multus](https://github.com/intel/multus-cni) v3.8
+  - [weave](https://github.com/weaveworks/weave) v2.8.1
+  - [kube-vip](https://github.com/kube-vip/kube-vip) v0.5.5
 - Application
-  - [ambassador](https://github.com/datawire/ambassador): v1.5
+  - [cert-manager](https://github.com/jetstack/cert-manager) v1.10.1
+  - [coredns](https://github.com/coredns/coredns) v1.9.3
+  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v1.5.1
+  - [krew](https://github.com/kubernetes-sigs/krew) v0.4.3
+  - [argocd](https://argoproj.github.io/) v2.4.16
+  - [helm](https://helm.sh/) v3.9.4
+  - [metallb](https://metallb.universe.tf/)  v0.12.1
+  - [registry](https://github.com/distribution/distribution) v2.8.1
+- Storage Plugin
   - [cephfs-provisioner](https://github.com/kubernetes-incubator/external-storage) v2.1.0-k8s1.11
   - [rbd-provisioner](https://github.com/kubernetes-incubator/external-storage) v2.1.1-k8s1.11
-  - [cert-manager](https://github.com/jetstack/cert-manager) v0.16.1
-  - [coredns](https://github.com/coredns/coredns) v1.6.7
-  - [ingress-nginx](https://github.com/kubernetes/ingress-nginx) v0.35.0
+  - [aws-ebs-csi-plugin](https://github.com/kubernetes-sigs/aws-ebs-csi-driver) v0.5.0
+  - [azure-csi-plugin](https://github.com/kubernetes-sigs/azuredisk-csi-driver) v1.10.0
+  - [cinder-csi-plugin](https://github.com/kubernetes/cloud-provider-openstack/blob/master/docs/cinder-csi-plugin/using-cinder-csi-plugin.md) v1.22.0
+  - [gcp-pd-csi-plugin](https://github.com/kubernetes-sigs/gcp-compute-persistent-disk-csi-driver) v1.4.0
+  - [local-path-provisioner](https://github.com/rancher/local-path-provisioner) v0.0.22
+  - [local-volume-provisioner](https://github.com/kubernetes-sigs/sig-storage-local-static-provisioner) v2.5.0
 
-Note: The list of validated [docker versions](https://kubernetes.io/docs/setup/production-environment/container-runtimes/#docker) is 1.13.1, 17.03, 17.06, 17.09, 18.06, 18.09 and 19.03. The recommended docker version is 19.03. The kubelet might break on docker's non-standard version numbering (it no longer uses semantic versioning). To ensure auto-updates don't break your cluster look into e.g. yum versionlock plugin or apt pin).
+## 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 v1.17**
-- **Ansible v2.9+, Jinja 2.11+ and python-netaddr is installed on the machine that will run Ansible commands**
+- **Minimum required version of Kubernetes is v1.23**
+- **Ansible v2.11+, Jinja 2.11+ and python-netaddr is installed on the machine that will run Ansible commands**
 - The target servers must have **access to the Internet** in order to pull docker images. Otherwise, additional configuration is required (See [Offline Environment](docs/offline-environment.md))
 - The target servers are configured to allow **IPv4 forwarding**.
-- **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
@@ -179,11 +215,6 @@ You can choose between 10 network plugins. (default: `calico`, except Vagrant us
 
 - [cilium](http://docs.cilium.io/en/latest/): layer 3/4 networking (as well as layer 7 to protect and secure application protocols), supports dynamic insertion of BPF bytecode into the Linux kernel to implement security services, networking and visibility logic.
 
-- [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.
-
-- [ovn4nfv](docs/ovn4nfv.md): [ovn4nfv-k8s-plugins](https://github.com/opnfv/ovn4nfv-k8s-plugin) is the network controller, OVS agent and CNI server to offer basic SFC and OVN overlay networking.
-
 - [weave](docs/weave.md): Weave is a lightweight container overlay network that doesn't require an external K/V database cluster.
     (Please refer to `weave` [troubleshooting documentation](https://www.weave.works/docs/net/latest/troubleshooting/)).
 
@@ -204,10 +235,10 @@ See also [Network checker](docs/netcheck.md).
 
 ## Ingress Plugins
 
-- [ambassador](docs/ambassador.md): the Ambassador Ingress Controller and API gateway.
-
 - [nginx](https://kubernetes.github.io/ingress-nginx): the NGINX Ingress Controller.
 
+- [metallb](docs/metallb.md): the MetalLB bare-metal service LoadBalancer provider.
+
 ## Community docs and resources
 
 - [kubernetes.io/docs/setup/production-environment/tools/kubespray/](https://kubernetes.io/docs/setup/production-environment/tools/kubespray/)
@@ -219,11 +250,12 @@ See also [Network checker](docs/netcheck.md).
 
 - [Digital Rebar Provision](https://github.com/digitalrebar/provision/blob/v4/doc/integrations/ansible.rst)
 - [Terraform Contrib](https://github.com/kubernetes-sigs/kubespray/tree/master/contrib/terraform)
+- [Kubean](https://github.com/kubean-io/kubean)
 
 ## CI Tests
 
 [![Build graphs](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/badges/master/pipeline.svg)](https://gitlab.com/kargo-ci/kubernetes-sigs-kubespray/pipelines)
 
-CI/end-to-end tests sponsored by: [CNCF](https://cncf.io), [Packet](https://www.packet.com/), [OVHcloud](https://www.ovhcloud.com/), [ELASTX](https://elastx.se/).
+CI/end-to-end tests sponsored by: [CNCF](https://cncf.io), [Equinix Metal](https://metal.equinix.com/), [OVHcloud](https://www.ovhcloud.com/), [ELASTX](https://elastx.se/).
 
 See the [test matrix](docs/test_cases.md) for details.

RELEASE.md

@@ -2,17 +2,18 @@
 
 The Kubespray Project is released on an as-needed basis. The process is as follows:
 
-1. An issue is proposing a new release with a changelog since the last release
+1. An issue is proposing a new release with a changelog since the last release. Please see [a good sample issue](https://github.com/kubernetes-sigs/kubespray/issues/8325)
 2. At least one of the [approvers](OWNERS_ALIASES) must approve this release
 3. The `kube_version_min_required` variable is set to `n-1`
-4. Remove hashes for [EOL versions](https://github.com/kubernetes/sig-release/blob/master/releases/patch-releases.md) of kubernetes from `*_checksums` variables.
-5. An approver creates [new release in GitHub](https://github.com/kubernetes-sigs/kubespray/releases/new) using a version and tag name like `vX.Y.Z` and attaching the release notes
-6. An approver creates a release branch in the form `release-X.Y`
-7. The corresponding version of [quay.io/kubespray/kubespray:vX.Y.Z](https://quay.io/repository/kubespray/kubespray) and [quay.io/kubespray/vagrant:vX.Y.Z](https://quay.io/repository/kubespray/vagrant) docker images are built and tagged
-8. The `KUBESPRAY_VERSION` variable is updated in `.gitlab-ci.yml`
-9. The release issue is closed
-10. An announcement email is sent to `kubernetes-dev@googlegroups.com` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
-11. The topic of the #kubespray channel is updated with `vX.Y.Z is released! | ...`
+4. Remove hashes for [EOL versions](https://github.com/kubernetes/website/blob/main/content/en/releases/patch-releases.md) of kubernetes from `*_checksums` variables.
+5. Create the release note with [Kubernetes Release Notes Generator](https://github.com/kubernetes/release/blob/master/cmd/release-notes/README.md). See the following `Release note creation` section for the details.
+6. An approver creates [new release in GitHub](https://github.com/kubernetes-sigs/kubespray/releases/new) using a version and tag name like `vX.Y.Z` and attaching the release notes
+7. An approver creates a release branch in the form `release-X.Y`
+8. The corresponding version of [quay.io/kubespray/kubespray:vX.Y.Z](https://quay.io/repository/kubespray/kubespray) and [quay.io/kubespray/vagrant:vX.Y.Z](https://quay.io/repository/kubespray/vagrant) container images are built and tagged. See the following `Container image creation` section for the details.
+9. The `KUBESPRAY_VERSION` variable is updated in `.gitlab-ci.yml`
+10. The release issue is closed
+11. An announcement email is sent to `dev@kubernetes.io` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
+12. The topic of the #kubespray channel is updated with `vX.Y.Z is released! | ...`
 
 ## Major/minor releases and milestones
 
@@ -46,3 +47,37 @@ The Kubespray Project is released on an as-needed basis. The process is as follo
   then Kubespray v2.1.0 may be bound to only minor changes to `kube_version`, like v1.5.1
   and *any* changes to other components, like etcd v4, or calico 1.2.3.
   And Kubespray v3.x.x shall be bound to `kube_version: 2.x.x` respectively.
+
+## Release note creation
+
+You can create a release note with:
+
+```shell
+export GITHUB_TOKEN=<your-github-token>
+export ORG=kubernetes-sigs
+export REPO=kubespray
+release-notes --start-sha <The start commit-id> --end-sha <The end commit-id> --dependencies=false --output=/tmp/kubespray-release-note --required-author=""
+```
+
+If the release note file(/tmp/kubespray-release-note) contains "### Uncategorized" pull requests, those pull requests don't have a valid kind label(`kind/feature`, etc.).
+It is necessary to put a valid label on each pull request and run the above release-notes command again to get a better release note)
+
+## Container image creation
+
+The container image `quay.io/kubespray/kubespray:vX.Y.Z` can be created from Dockerfile of the kubespray root directory:
+
+```shell
+cd kubespray/
+nerdctl build -t quay.io/kubespray/kubespray:vX.Y.Z .
+nerdctl push quay.io/kubespray/kubespray:vX.Y.Z
+```
+
+The container image `quay.io/kubespray/vagrant:vX.Y.Z` can be created from build.sh of test-infra/vagrant-docker/:
+
+```shell
+cd kubespray/test-infra/vagrant-docker/
+./build vX.Y.Z
+```
+
+Please note that the above operation requires the permission to push container images into quay.io/kubespray/.
+If you don't have the permission, please ask it on the #kubespray-dev channel.

SECURITY_CONTACTS

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

Vagrantfile

@@ -26,12 +26,17 @@ SUPPORTED_OS = {
   "centos-bento"        => {box: "bento/centos-7.6",           user: "vagrant"},
   "centos8"             => {box: "centos/8",                   user: "vagrant"},
   "centos8-bento"       => {box: "bento/centos-8",             user: "vagrant"},
-  "fedora31"            => {box: "fedora/31-cloud-base",       user: "vagrant"},
-  "fedora32"            => {box: "fedora/32-cloud-base",       user: "vagrant"},
-  "opensuse"            => {box: "bento/opensuse-leap-15.1",   user: "vagrant"},
+  "almalinux8"          => {box: "almalinux/8",                user: "vagrant"},
+  "almalinux8-bento"    => {box: "bento/almalinux-8",          user: "vagrant"},
+  "rockylinux8"         => {box: "generic/rocky8",             user: "vagrant"},
+  "fedora35"            => {box: "fedora/35-cloud-base",       user: "vagrant"},
+  "fedora36"            => {box: "fedora/36-cloud-base",       user: "vagrant"},
+  "opensuse"            => {box: "opensuse/Leap-15.4.x86_64",  user: "vagrant"},
   "opensuse-tumbleweed" => {box: "opensuse/Tumbleweed.x86_64", user: "vagrant"},
   "oraclelinux"         => {box: "generic/oracle7",            user: "vagrant"},
   "oraclelinux8"        => {box: "generic/oracle8",            user: "vagrant"},
+  "rhel7"               => {box: "generic/rhel7",              user: "vagrant"},
+  "rhel8"               => {box: "generic/rhel8",              user: "vagrant"},
 }
 
 if File.exist?(CONFIG)
@@ -47,12 +52,13 @@ $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
+$multi_networking ||= "False"
 $download_run_once ||= "True"
-$download_force_cache ||= "True"
+$download_force_cache ||= "False"
 # The first three nodes are etcd servers
 $etcd_instances ||= $num_instances
 # The first two nodes are kube masters
@@ -65,9 +71,12 @@ $kube_node_instances_with_disks_size ||= "20G"
 $kube_node_instances_with_disks_number ||= 2
 $override_disk_size ||= false
 $disk_size ||= "20GB"
-$local_path_provisioner_enabled ||= false
+$local_path_provisioner_enabled ||= "False"
 $local_path_provisioner_claim_root ||= "/opt/local-path-provisioner/"
 $libvirt_nested ||= false
+# boolean or string (e.g. "-vvv")
+$ansible_verbosity ||= false
+$ansible_tags ||= ENV['VAGRANT_ANSIBLE_TAGS'] || ""
 
 $playbook ||= "cluster.yml"
 
@@ -83,9 +92,9 @@ $inventory = File.absolute_path($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")
@@ -142,6 +151,7 @@ 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|
@@ -163,7 +173,7 @@ Vagrant.configure("2") do |config|
           # always make /dev/sd{a/b/c} so that CI can ensure that
           # virtualbox and libvirt will have the same devices to use for OSDs
           (1..$kube_node_instances_with_disks_number).each do |d|
-            lv.storage :file, :device => "hd#{driverletters[d]}", :path => "disk-#{i}-#{d}-#{DISK_UUID}.disk", :size => $kube_node_instances_with_disks_size, :bus => "ide"
+            lv.storage :file, :device => "hd#{driverletters[d]}", :path => "disk-#{i}-#{d}-#{DISK_UUID}.disk", :size => $kube_node_instances_with_disks_size, :bus => "scsi"
           end
         end
       end
@@ -176,19 +186,39 @@ Vagrant.configure("2") do |config|
         node.vm.network "forwarded_port", guest: guest, host: host, auto_correct: true
       end
 
+      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"
 
-      # Disable firewalld on oraclelinux vms
-      if ["oraclelinux","oraclelinux8"].include? $os
+      # 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
 
@@ -214,9 +244,11 @@ Vagrant.configure("2") do |config|
       }
 
       # Only execute the Ansible provisioner once, when all the machines are up and ready.
+      # And limit the action to gathering facts, the full playbook is going to be ran by testcases_run.sh
       if i == $num_instances
         node.vm.provision "ansible" do |ansible|
           ansible.playbook = $playbook
+          ansible.verbose = $ansible_verbosity
           $ansible_inventory_path = File.join( $inventory, "hosts.ini")
           if File.exist?($ansible_inventory_path)
             ansible.inventory_path = $ansible_inventory_path
@@ -226,12 +258,14 @@ Vagrant.configure("2") do |config|
           ansible.host_key_checking = false
           ansible.raw_arguments = ["--forks=#{$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

ansible.cfg

@@ -1,9 +1,8 @@
 [ssh_connection]
 pipelining=True
-ssh_args = -o ControlMaster=auto -o ControlPersist=30m -o ConnectionAttempts=100 -o UserKnownHostsFile=/dev/null
+ansible_ssh_args = -o ControlMaster=auto -o ControlPersist=30m -o ConnectionAttempts=100 -o UserKnownHostsFile=/dev/null
 #control_path = ~/.ssh/ansible-%%r@%%h:%%p
 [defaults]
-strategy_plugins = plugins/mitogen/ansible_mitogen/plugins/strategy
 # https://github.com/ansible/ansible/issues/56930 (to ignore group names with - and .)
 force_valid_group_names = ignore
 
@@ -11,11 +10,11 @@ host_key_checking=False
 gathering = smart
 fact_caching = jsonfile
 fact_caching_connection = /tmp
-fact_caching_timeout = 7200
+fact_caching_timeout = 86400
 stdout_callback = default
 display_skipped_hosts = no
 library = ./library
-callback_whitelist = profile_tasks
+callbacks_enabled = profile_tasks,ara_default
 roles_path = roles:$VIRTUAL_ENV/usr/local/share/kubespray/roles:$VIRTUAL_ENV/usr/local/share/ansible/roles:/usr/share/kubespray/roles
 deprecation_warnings=False
 inventory_ignore_extensions = ~, .orig, .bak, .ini, .cfg, .retry, .pyc, .pyo, .creds, .gpg

ansible_version.yml

@@ -3,13 +3,31 @@
   gather_facts: false
   become: no
   vars:
-    minimal_ansible_version: 2.8.0
+    minimal_ansible_version: 2.11.0
+    maximal_ansible_version: 2.14.0
     ansible_connection: local
+  tags: always
   tasks:
-    - name: "Check ansible version >={{ minimal_ansible_version }}"
+    - name: "Check {{ minimal_ansible_version }} <= Ansible version < {{ maximal_ansible_version }}"
       assert:
-        msg: "Ansible must be {{ minimal_ansible_version }} or higher"
+        msg: "Ansible must be between {{ minimal_ansible_version }} and {{ maximal_ansible_version }} exclusive"
         that:
           - ansible_version.string is version(minimal_ansible_version, ">=")
+          - ansible_version.string is version(maximal_ansible_version, "<")
+      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

@@ -2,31 +2,21 @@
 - name: Check ansible version
   import_playbook: ansible_version.yml
 
-- hosts: all
-  gather_facts: false
-  tags: always
-  tasks:
-    - name: "Set up proxy environment"
-      set_fact:
-        proxy_env:
-          http_proxy: "{{ http_proxy | default ('') }}"
-          HTTP_PROXY: "{{ http_proxy | default ('') }}"
-          https_proxy: "{{ https_proxy | default ('') }}"
-          HTTPS_PROXY: "{{ https_proxy | default ('') }}"
-          no_proxy: "{{ no_proxy | default ('') }}"
-          NO_PROXY: "{{ no_proxy | default ('') }}"
-      no_log: true
+- name: Ensure compatibility with old groups
+  import_playbook: legacy_groups.yml
 
 - hosts: bastion[0]
   gather_facts: False
+  environment: "{{ proxy_disable_env }}"
   roles:
     - { role: kubespray-defaults }
     - { role: bastion-ssh-config, tags: ["localhost", "bastion"] }
 
-- hosts: k8s-cluster:etcd
+- hosts: k8s_cluster:etcd
   strategy: linear
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
   gather_facts: false
+  environment: "{{ proxy_disable_env }}"
   roles:
     - { role: kubespray-defaults }
     - { role: bootstrap-os, tags: bootstrap-os}
@@ -35,19 +25,20 @@
   tags: always
   import_playbook: facts.yml
 
-- hosts: k8s-cluster:etcd
+- hosts: k8s_cluster:etcd
   gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
     - { role: kubespray-defaults }
     - { role: kubernetes/preinstall, tags: preinstall }
-    - { role: "container-engine", tags: "container-engine", when: deploy_container_engine|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
+- hosts: etcd:kube_control_plane
   gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
     - { role: kubespray-defaults }
     - role: etcd
@@ -55,11 +46,12 @@
       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: etcd
@@ -67,52 +59,59 @@
       vars:
         etcd_cluster_setup: false
         etcd_events_cluster_setup: false
-      when: not etcd_kubeadm_enabled| default(false)
+      when:
+        - etcd_deployment_type != "kubeadm"
+        - kube_network_plugin in ["calico", "flannel", "canal", "cilium"] or cilium_deploy_additionally | default(false) | bool
+        - kube_network_plugin != "calico" or calico_datastore == "etcd"
 
-- hosts: k8s-cluster
+- hosts: k8s_cluster
   gather_facts: False
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
+  environment: "{{ proxy_disable_env }}"
   roles:
     - { role: kubespray-defaults }
     - { role: kubernetes/node, tags: node }
-  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: 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: kubernetes/kubeadm, tags: kubeadm}
-    - { role: network_plugin, tags: network }
     - { role: kubernetes/node-label, tags: node-label }
+    - { role: network_plugin, tags: network }
 
-- 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'] }
 
-- 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"] }
 
-- 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-apps/external_cloud_controller, tags: external-cloud-controller }
@@ -120,18 +119,13 @@
     - { 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
-  gather_facts: False
-  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: 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+"*"]
@@ -70,7 +70,7 @@ 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

@@ -31,7 +31,7 @@ also removes all public IPs from all other VMs.
 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
@@ -42,25 +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
-$ sudo pip3 install -r requirements.txt
-$ ansible-playbook -i contrib/azurerm/inventory -u devops --become -e "@inventory/sample/group_vars/all/all.yml" cluster.yml
+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/roles/generate-inventory/tasks/main.yml

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

contrib/azurerm/roles/generate-inventory/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

@@ -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": {

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/run-test-distros.sh

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

contrib/inventory_builder/inventory.py

@@ -44,11 +44,11 @@ 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()
@@ -63,10 +63,12 @@ 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")
@@ -80,32 +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_all(self.hosts_file)
-            except OSError:
-                pass
+                self.yaml_config = yaml.load(self.hosts_file)
+            except OSError as e:
+                # I am assuming we are catching "cannot open file" exceptions
+                print(e)
+                sys.exit(1)
 
-        if changed_hosts and changed_hosts[0] in AVAILABLE_COMMANDS:
-            self.parse_command(changed_hosts[0], changed_hosts[1:])
+        if printHostnames:
+            self.print_hostnames()
             sys.exit(0)
 
         self.ensure_required_groups(ROLES)
 
         if changed_hosts:
             changed_hosts = self.range2ips(changed_hosts)
-            self.hosts = self.build_hostnames(changed_hosts)
+            self.hosts = self.build_hostnames(changed_hosts,
+                                              loadPreviousConfig)
             self.purge_invalid_hosts(self.hosts.keys(), PROTECTED_NAMES)
             self.set_all(self.hosts)
             self.set_k8s_cluster()
             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])
@@ -155,17 +179,29 @@ class KubesprayInventory(object):
         except IndexError:
             raise ValueError("Host name must end in an integer")
 
-    def build_hostnames(self, changed_hosts):
+    # Keeps already specified hosts,
+    # and adds or removes the hosts provided as an argument
+    def build_hostnames(self, changed_hosts, loadPreviousConfig=False):
         existing_hosts = OrderedDict()
         highest_host_id = 0
+        # Load already existing hosts from the YAML
+        if loadPreviousConfig:
             try:
                 for host in self.yaml_config['all']['hosts']:
-                existing_hosts[host] = self.yaml_config['all']['hosts'][host]
+                    # 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:
-            pass
+            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
@@ -173,6 +209,7 @@ class KubesprayInventory(object):
 
         all_hosts = existing_hosts.copy()
         for host in changed_hosts:
+            # Delete the host from config the hostname/IP has a "-" prefix
             if host[0] == "-":
                 realhost = host[1:]
                 if self.exists_hostname(all_hosts, realhost):
@@ -181,6 +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(',')
@@ -200,11 +239,15 @@ class KubesprayInventory(object):
                     next_host = subprocess.check_output(cmd, shell=True)
                     next_host = next_host.strip().decode('ascii')
                 else:
+                    # Generates a hostname because we have only an IP address
                     next_host = "{0}{1}".format(HOST_PREFIX, next_host_id)
                     next_host_id += 1
+                # Uses automatically generated node name
+                # in case we dont provide it.
                 all_hosts[next_host] = {'ansible_host': access_ip,
                                         'ip': ip,
                                         'access_ip': access_ip}
+            # Host/Argument starts with a letter, then we assume its a hostname
             elif host[0].isalpha():
                 if ',' in host:
                     try:
@@ -223,6 +266,7 @@ class KubesprayInventory(object):
                                        'access_ip': access_ip}
         return all_hosts
 
+    # Expand IP ranges into individual addresses
     def range2ips(self, hosts):
         reworked_hosts = []
 
@@ -266,7 +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:
@@ -287,52 +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:
@@ -389,9 +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
@@ -402,8 +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)
 
@@ -424,6 +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 io import StringIO
 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 mock.patch('sys.stdout', new_callable=StringIO) as stdout:
+                    inventory.KubesprayInventory(
+                        changed_hosts=["print_hostnames"],
+                        config_file="file")
+            self.assertEqual("node1 node2\n", stdout.getvalue())
+            self.assertEqual(cm.exception.code, 0)
+
+
 class TestInventory(unittest.TestCase):
     @mock.patch('inventory.sys')
     def setUp(self, sys_mock):
@@ -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/mitogen/mitogen.yml

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

@@ -14,7 +14,7 @@
 # gfs_node2 ansible_ssh_host=95.54.0.19 # disk_volume_device_1=/dev/vdc  ip=10.3.0.8
 # gfs_node3 ansible_ssh_host=95.54.0.20 # disk_volume_device_1=/dev/vdc  ip=10.3.0.9
 
-# [kube-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

@@ -8,18 +8,22 @@ 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
 
 Available variables are listed below, along with default values (see `defaults/main.yml`):
 
+```yaml
 glusterfs_default_release: ""
+```
 
 You can specify a `default_release` for apt on Debian/Ubuntu by overriding this variable. This is helpful if you need a different package or version for the main GlusterFS packages (e.g. GlusterFS 3.5.x instead of 3.2.x with the `wheezy-backports` default release on Debian Wheezy).
 
+```yaml
 glusterfs_ppa_use: yes
 glusterfs_ppa_version: "3.5"
+```
 
 For Ubuntu, specify whether to use the official Gluster PPA, and which version of the PPA to use. See Gluster's [Getting Started Guide](https://docs.gluster.org/en/latest/Quick-Start-Guide/Quickstart/) for more info.
 
@@ -29,9 +33,11 @@ None.
 
 ## Example Playbook
 
+```yaml
     - hosts: server
       roles:
         - geerlingguy.glusterfs
+```
 
 For a real-world use example, read through [Simple GlusterFS Setup with Ansible](http://www.jeffgeerling.com/blog/simple-glusterfs-setup-ansible), a blog post by this role's author, which is included in Chapter 8 of [Ansible for DevOps](https://www.ansiblefordevops.com/).
 

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

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

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

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

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

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

contrib/network-storage/glusterfs/roles/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/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/topology.yml

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

contrib/offline/README.md

@@ -0,0 +1,65 @@
+# 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.
+
+## manage-offline-files.sh
+
+This script will download all files according to `temp/files.list` and run nginx container to provide offline file download.
+
+Step(1) generate `files.list`
+
+```shell
+./generate_list.sh
+```
+
+Step(2) download files and run nginx container
+
+```shell
+./manage-offline-files.sh
+```
+
+when nginx container is running, it can be accessed through <http://127.0.0.1:8080/>.

contrib/offline/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:|registry.k8s.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}  ${image}
+
+		# NOTE: Here removes the following repo parts from each image
+		# so that these parts will be replaced with Kubespray.
+		# - kube_image_repo: "registry.k8s.io"
+		# - gcr_image_repo: "gcr.io"
+		# - docker_image_repo: "docker.io"
+		# - quay_image_repo: "quay.io"
+		FIRST_PART=$(echo ${image} | awk -F"/" '{print $1}')
+		if [ "${FIRST_PART}" = "registry.k8s.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/manage-offline-files.sh

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

contrib/offline/nginx.conf

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

contrib/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 }

contrib/os-services/roles/prepare/defaults/main.yml

@@ -0,0 +1,2 @@
+---
+disable_service_firewall: false

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

@@ -0,0 +1,23 @@
+---
+- block:
+  - name: List services
+    service_facts:
+
+  - name: Disable service firewalld
+    systemd:
+      name: firewalld
+      state: stopped
+      enabled: no
+    when:
+      "'firewalld.service' in services"
+
+  - name: Disable service ufw
+    systemd:
+      name: ufw
+      state: stopped
+      enabled: no
+    when:
+      "'ufw.service' in services"
+
+  when:
+  - disable_service_firewall is defined and disable_service_firewall

contrib/packaging/rpm/kubespray.spec

@@ -9,8 +9,8 @@ Summary:        Ansible modules for installing Kubernetes
 
 Group:          System Environment/Libraries
 License:        ASL 2.0
-Url:            https://github.com/kubernetes-incubator/kubespray
-Source0:        https://github.com/kubernetes-incubator/kubespray/archive/%{upstream_version}.tar.gz#/%{name}-%{release}.tar.gz
+Url:            https://github.com/kubernetes-sigs/kubespray
+Source0:        https://github.com/kubernetes-sigs/kubespray/archive/%{upstream_version}.tar.gz#/%{name}-%{release}.tar.gz
 
 BuildArch:      noarch
 BuildRequires:  git
@@ -51,7 +51,7 @@ export SKIP_PIP_INSTALL=1
 %doc %{_docdir}/%{name}/inventory/sample/hosts.ini
 %config %{_sysconfdir}/%{name}/ansible.cfg
 %config %{_sysconfdir}/%{name}/inventory/sample/group_vars/all.yml
-%config %{_sysconfdir}/%{name}/inventory/sample/group_vars/k8s-cluster.yml
+%config %{_sysconfdir}/%{name}/inventory/sample/group_vars/k8s_cluster.yml
 %license %{_docdir}/%{name}/LICENSE
 %{python2_sitelib}/%{srcname}-%{release}-py%{python2_version}.egg-info
 %{_datarootdir}/%{name}/roles/

contrib/terraform/aws/.gitignore

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

contrib/terraform/aws/README.md

@@ -1,40 +1,43 @@
-## Kubernetes on AWS with Terraform
+# Kubernetes on AWS with Terraform
 
-**Overview:**
+## Overview
 
 This project will create:
-* VPC with Public and Private Subnets in # Availability Zones
-* Bastion Hosts and NAT Gateways in the Public Subnet
-* A dynamic number of masters, etcd, and worker nodes in the Private Subnet
- * even distributed over the # of Availability Zones
-* AWS ELB in the Public Subnet for accessing the Kubernetes API from the internet
 
-**Requirements**
+- VPC with Public and Private Subnets in # Availability Zones
+- Bastion Hosts and NAT Gateways in the Public Subnet
+- A dynamic number of masters, etcd, and worker nodes in the Private Subnet
+  - even distributed over the # of Availability Zones
+- AWS ELB in the Public Subnet for accessing the Kubernetes API from the internet
+
+## Requirements
+
 - Terraform 0.12.0 or newer
 
-**How to Use:**
+## How to Use
 
 - Export the variables for your AWS credentials or edit `credentials.tfvars`:
 
-```
+```commandline
 export TF_VAR_AWS_ACCESS_KEY_ID="www"
 export TF_VAR_AWS_SECRET_ACCESS_KEY ="xxx"
 export TF_VAR_AWS_SSH_KEY_NAME="yyy"
 export TF_VAR_AWS_DEFAULT_REGION="zzz"
 ```
+
 - Update `contrib/terraform/aws/terraform.tfvars` with your data. By default, the Terraform scripts use Ubuntu 18.04 LTS (Bionic) as base image. If you want to change this behaviour, see note "Using other distrib than Ubuntu" below.
 - Create an AWS EC2 SSH Key
 - Run with `terraform apply --var-file="credentials.tfvars"` or `terraform apply` depending if you exported your AWS credentials
 
 Example:
+
 ```commandline
 terraform apply -var-file=credentials.tfvars
 ```
 
 - Terraform automatically creates an Ansible Inventory file called `hosts` with the created infrastructure in the directory `inventory`
+- Ansible will automatically generate an ssh config file for your bastion hosts. To connect to hosts with ssh using bastion host use generated `ssh-bastion.conf`. Ansible automatically detects bastion and changes `ssh_args`
 
-- Ansible will automatically generate an ssh config file for your bastion hosts. To connect to hosts with ssh using bastion host use generated ssh-bastion.conf.
-  Ansible automatically detects bastion and changes ssh_args  
 ```commandline
 ssh -F ./ssh-bastion.conf user@$ip
 ```
@@ -42,14 +45,19 @@ ssh -F ./ssh-bastion.conf user@$ip
 - Once the infrastructure is created, you can run the kubespray playbooks and supply inventory/hosts with the `-i` flag.
 
 Example (this one assumes you are using Ubuntu)
+
 ```commandline
 ansible-playbook -i ./inventory/hosts ./cluster.yml -e ansible_user=ubuntu -b --become-user=root --flush-cache
 ```
+
 ***Using other distrib than Ubuntu***
 If you want to use another distribution than Ubuntu 18.04 (Bionic) LTS, you can modify the search filters of the 'data "aws_ami" "distro"' in variables.tf.
 
 For example, to use:
+
 - Debian Jessie, replace 'data "aws_ami" "distro"' in variables.tf with
+
+```ini
 data "aws_ami" "distro" {
   most_recent = true
 
@@ -65,8 +73,11 @@ data "aws_ami" "distro" {
 
   owners = ["379101102735"]
 }
+```
 
 - Ubuntu 16.04, replace 'data "aws_ami" "distro"' in variables.tf with
+
+```ini
 data "aws_ami" "distro" {
   most_recent = true
 
@@ -82,8 +93,11 @@ data "aws_ami" "distro" {
 
   owners = ["099720109477"]
 }
+```
 
 - Centos 7, replace 'data "aws_ami" "distro"' in variables.tf with
+
+```ini
 data "aws_ami" "distro" {
   most_recent = true
 
@@ -99,23 +113,49 @@ data "aws_ami" "distro" {
 
   owners = ["688023202711"]
 }
+```
 
-**Troubleshooting**
+## Connecting to Kubernetes
 
-***Remaining AWS IAM Instance Profile***:
+You can use the following set of commands to get the kubeconfig file from your newly created cluster. Before running the commands, make sure you are in the project's root folder.
+
+```commandline
+# Get the controller's IP address.
+CONTROLLER_HOST_NAME=$(cat ./inventory/hosts | grep "\[kube_control_plane\]" -A 1 | tail -n 1)
+CONTROLLER_IP=$(cat ./inventory/hosts | grep $CONTROLLER_HOST_NAME | grep ansible_host | cut -d'=' -f2)
+
+# Get the hostname of the load balancer.
+LB_HOST=$(cat inventory/hosts | grep apiserver_loadbalancer_domain_name | cut -d'"' -f2)
+
+# Get the controller's SSH fingerprint.
+ssh-keygen -R $CONTROLLER_IP > /dev/null 2>&1
+ssh-keyscan -H $CONTROLLER_IP >> ~/.ssh/known_hosts 2>/dev/null
+
+# Get the kubeconfig from the controller.
+mkdir -p ~/.kube
+ssh -F ssh-bastion.conf centos@$CONTROLLER_IP "sudo chmod 644 /etc/kubernetes/admin.conf"
+scp -F ssh-bastion.conf centos@$CONTROLLER_IP:/etc/kubernetes/admin.conf ~/.kube/config
+sed -i "s^server:.*^server: https://$LB_HOST:6443^" ~/.kube/config
+kubectl get nodes
+```
+
+## Troubleshooting
+
+### Remaining AWS IAM Instance Profile
 
 If the cluster was destroyed without using Terraform it is possible that
 the AWS IAM Instance Profiles still remain. To delete them you can use
 the `AWS CLI` with the following command:
-```
+
+```commandline
 aws iam delete-instance-profile --region <region_name> --instance-profile-name <profile_name>
 ```
 
-***Ansible Inventory doesn't get created:***
+### Ansible Inventory doesn't get created
 
 It could happen that Terraform doesn't create an Ansible Inventory file automatically. If this is the case copy the output after `inventory=` and create a file named `hosts`in the directory `inventory` and paste the inventory into the file.
 
-**Architecture**
+## Architecture
 
 Pictured is an AWS Infrastructure created with this Terraform project distributed over two Availability Zones.
 

contrib/terraform/aws/create-infrastructure.tf

@@ -20,20 +20,20 @@ module "aws-vpc" {
 
   aws_cluster_name         = var.aws_cluster_name
   aws_vpc_cidr_block       = var.aws_vpc_cidr_block
-  aws_avail_zones          = slice(data.aws_availability_zones.available.names, 0, 2)
+  aws_avail_zones          = data.aws_availability_zones.available.names
   aws_cidr_subnets_private = var.aws_cidr_subnets_private
   aws_cidr_subnets_public  = var.aws_cidr_subnets_public
   default_tags             = var.default_tags
 }
 
-module "aws-elb" {
-  source = "./modules/elb"
+module "aws-nlb" {
+  source = "./modules/nlb"
 
   aws_cluster_name      = var.aws_cluster_name
   aws_vpc_id            = module.aws-vpc.aws_vpc_id
-  aws_avail_zones       = slice(data.aws_availability_zones.available.names, 0, 2)
+  aws_avail_zones       = data.aws_availability_zones.available.names
   aws_subnet_ids_public = module.aws-vpc.aws_subnet_ids_public
-  aws_elb_api_port      = var.aws_elb_api_port
+  aws_nlb_api_port      = var.aws_nlb_api_port
   k8s_secure_api_port   = var.k8s_secure_api_port
   default_tags          = var.default_tags
 }
@@ -52,20 +52,19 @@ module "aws-iam" {
 resource "aws_instance" "bastion-server" {
   ami                         = data.aws_ami.distro.id
   instance_type               = var.aws_bastion_size
-  count                       = length(var.aws_cidr_subnets_public)
+  count                       = var.aws_bastion_num
   associate_public_ip_address = true
-  availability_zone           = element(slice(data.aws_availability_zones.available.names, 0, 2), count.index)
   subnet_id                   = element(module.aws-vpc.aws_subnet_ids_public, count.index)
 
   vpc_security_group_ids = module.aws-vpc.aws_security_group
 
   key_name = var.AWS_SSH_KEY_NAME
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-bastion-${count.index}",
-    "Cluster", "${var.aws_cluster_name}",
-    "Role", "bastion-${var.aws_cluster_name}-${count.index}"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name    = "kubernetes-${var.aws_cluster_name}-bastion-${count.index}"
+    Cluster = var.aws_cluster_name
+    Role    = "bastion-${var.aws_cluster_name}-${count.index}"
+  }))
 }
 
 /*
@@ -79,25 +78,28 @@ resource "aws_instance" "k8s-master" {
 
   count = var.aws_kube_master_num
 
-  availability_zone = element(slice(data.aws_availability_zones.available.names, 0, 2), count.index)
   subnet_id = element(module.aws-vpc.aws_subnet_ids_private, count.index)
 
   vpc_security_group_ids = module.aws-vpc.aws_security_group
 
-  iam_instance_profile = module.aws-iam.kube-master-profile
-  key_name             = var.AWS_SSH_KEY_NAME
-
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-master${count.index}",
-    "kubernetes.io/cluster/${var.aws_cluster_name}", "member",
-    "Role", "master"
-  ))
+  root_block_device {
+    volume_size = var.aws_kube_master_disk_size
   }
 
-resource "aws_elb_attachment" "attach_master_nodes" {
+  iam_instance_profile = module.aws-iam.kube_control_plane-profile
+  key_name             = var.AWS_SSH_KEY_NAME
+
+  tags = merge(var.default_tags, tomap({
+    Name                                            = "kubernetes-${var.aws_cluster_name}-master${count.index}"
+    "kubernetes.io/cluster/${var.aws_cluster_name}" = "member"
+    Role                                            = "master"
+  }))
+}
+
+resource "aws_lb_target_group_attachment" "tg-attach_master_nodes" {
   count            = var.aws_kube_master_num
-  elb      = module.aws-elb.aws_elb_api_id
-  instance = element(aws_instance.k8s-master.*.id, count.index)
+  target_group_arn = module.aws-nlb.aws_nlb_api_tg_arn
+  target_id        = element(aws_instance.k8s-master.*.private_ip, count.index)
 }
 
 resource "aws_instance" "k8s-etcd" {
@@ -106,18 +108,21 @@ resource "aws_instance" "k8s-etcd" {
 
   count = var.aws_etcd_num
 
-  availability_zone = element(slice(data.aws_availability_zones.available.names, 0, 2), count.index)
   subnet_id = element(module.aws-vpc.aws_subnet_ids_private, count.index)
 
   vpc_security_group_ids = module.aws-vpc.aws_security_group
 
+  root_block_device {
+    volume_size = var.aws_etcd_disk_size
+  }
+
   key_name = var.AWS_SSH_KEY_NAME
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-etcd${count.index}",
-    "kubernetes.io/cluster/${var.aws_cluster_name}", "member",
-    "Role", "etcd"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name                                            = "kubernetes-${var.aws_cluster_name}-etcd${count.index}"
+    "kubernetes.io/cluster/${var.aws_cluster_name}" = "member"
+    Role                                            = "etcd"
+  }))
 }
 
 resource "aws_instance" "k8s-worker" {
@@ -126,19 +131,22 @@ resource "aws_instance" "k8s-worker" {
 
   count = var.aws_kube_worker_num
 
-  availability_zone = element(slice(data.aws_availability_zones.available.names, 0, 2), count.index)
   subnet_id = element(module.aws-vpc.aws_subnet_ids_private, count.index)
 
   vpc_security_group_ids = module.aws-vpc.aws_security_group
 
+  root_block_device {
+    volume_size = var.aws_kube_worker_disk_size
+  }
+
   iam_instance_profile = module.aws-iam.kube-worker-profile
   key_name             = var.AWS_SSH_KEY_NAME
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-worker${count.index}",
-    "kubernetes.io/cluster/${var.aws_cluster_name}", "member",
-    "Role", "worker"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name                                            = "kubernetes-${var.aws_cluster_name}-worker${count.index}"
+    "kubernetes.io/cluster/${var.aws_cluster_name}" = "member"
+    Role                                            = "worker"
+  }))
 }
 
 /*
@@ -152,11 +160,11 @@ data "template_file" "inventory" {
     public_ip_address_bastion = join("\n", formatlist("bastion ansible_host=%s", aws_instance.bastion-server.*.public_ip))
     connection_strings_master = join("\n", formatlist("%s ansible_host=%s", aws_instance.k8s-master.*.private_dns, aws_instance.k8s-master.*.private_ip))
     connection_strings_node   = join("\n", formatlist("%s ansible_host=%s", aws_instance.k8s-worker.*.private_dns, aws_instance.k8s-worker.*.private_ip))
-    connection_strings_etcd   = join("\n", formatlist("%s ansible_host=%s", aws_instance.k8s-etcd.*.private_dns, aws_instance.k8s-etcd.*.private_ip))
     list_master               = join("\n", aws_instance.k8s-master.*.private_dns)
     list_node                 = join("\n", aws_instance.k8s-worker.*.private_dns)
-    list_etcd                 = join("\n", aws_instance.k8s-etcd.*.private_dns)
-    elb_api_fqdn              = "apiserver_loadbalancer_domain_name=\"${module.aws-elb.aws_elb_api_fqdn}\""
+    connection_strings_etcd   = join("\n", formatlist("%s ansible_host=%s", aws_instance.k8s-etcd.*.private_dns, aws_instance.k8s-etcd.*.private_ip))
+    list_etcd                 = join("\n", ((var.aws_etcd_num > 0) ? (aws_instance.k8s-etcd.*.private_dns) : (aws_instance.k8s-master.*.private_dns)))
+    nlb_api_fqdn              = "apiserver_loadbalancer_domain_name=\"${module.aws-nlb.aws_nlb_api_fqdn}\""
   }
 }
 

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

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

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

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

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

@@ -1,6 +1,6 @@
 #Add AWS Roles for Kubernetes
 
-resource "aws_iam_role" "kube-master" {
+resource "aws_iam_role" "kube_control_plane" {
   name = "kubernetes-${var.aws_cluster_name}-master"
 
   assume_role_policy = <<EOF
@@ -40,9 +40,9 @@ EOF
 
 #Add AWS Policies for Kubernetes
 
-resource "aws_iam_role_policy" "kube-master" {
+resource "aws_iam_role_policy" "kube_control_plane" {
   name = "kubernetes-${var.aws_cluster_name}-master"
-  role = aws_iam_role.kube-master.id
+  role = aws_iam_role.kube_control_plane.id
 
   policy = <<EOF
 {
@@ -130,9 +130,9 @@ EOF
 
 #Create AWS Instance Profiles
 
-resource "aws_iam_instance_profile" "kube-master" {
+resource "aws_iam_instance_profile" "kube_control_plane" {
   name = "kube_${var.aws_cluster_name}_master_profile"
-  role = aws_iam_role.kube-master.name
+  role = aws_iam_role.kube_control_plane.name
 }
 
 resource "aws_iam_instance_profile" "kube-worker" {

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

@@ -1,5 +1,5 @@
-output "kube-master-profile" {
-  value = aws_iam_instance_profile.kube-master.name
+output "kube_control_plane-profile" {
+  value = aws_iam_instance_profile.kube_control_plane.name
 }
 
 output "kube-worker-profile" {

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

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

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

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

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

@@ -6,8 +6,8 @@ variable "aws_vpc_id" {
   description = "AWS VPC ID"
 }
 
-variable "aws_elb_api_port" {
-  description = "Port for AWS ELB"
+variable "aws_nlb_api_port" {
+  description = "Port for AWS NLB"
 }
 
 variable "k8s_secure_api_port" {
@@ -16,15 +16,15 @@ variable "k8s_secure_api_port" {
 
 variable "aws_avail_zones" {
   description = "Availability Zones Used"
-  type        = "list"
+  type        = list(string)
 }
 
 variable "aws_subnet_ids_public" {
   description = "IDs of Public Subnets"
-  type        = "list"
+  type        = list(string)
 }
 
 variable "default_tags" {
   description = "Tags for all resources"
-  type        = "map"
+  type        = map(string)
 }

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

@@ -5,9 +5,9 @@ resource "aws_vpc" "cluster-vpc" {
   enable_dns_support   = true
   enable_dns_hostnames = true
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-vpc"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name = "kubernetes-${var.aws_cluster_name}-vpc"
+  }))
 }
 
 resource "aws_eip" "cluster-nat-eip" {
@@ -18,21 +18,22 @@ resource "aws_eip" "cluster-nat-eip" {
 resource "aws_internet_gateway" "cluster-vpc-internetgw" {
   vpc_id = aws_vpc.cluster-vpc.id
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-internetgw"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name = "kubernetes-${var.aws_cluster_name}-internetgw"
+  }))
 }
 
 resource "aws_subnet" "cluster-vpc-subnets-public" {
   vpc_id            = aws_vpc.cluster-vpc.id
-  count             = length(var.aws_avail_zones)
-  availability_zone = element(var.aws_avail_zones, count.index)
+  count             = length(var.aws_cidr_subnets_public)
+  availability_zone = element(var.aws_avail_zones, count.index % length(var.aws_avail_zones))
   cidr_block        = element(var.aws_cidr_subnets_public, count.index)
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-${element(var.aws_avail_zones, count.index)}-public",
-    "kubernetes.io/cluster/${var.aws_cluster_name}", "member"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name = "kubernetes-${var.aws_cluster_name}-${element(var.aws_avail_zones, count.index)}-public"
+    "kubernetes.io/cluster/${var.aws_cluster_name}" = "shared"
+    "kubernetes.io/role/elb" = "1"
+  }))
 }
 
 resource "aws_nat_gateway" "cluster-nat-gateway" {
@@ -43,13 +44,15 @@ resource "aws_nat_gateway" "cluster-nat-gateway" {
 
 resource "aws_subnet" "cluster-vpc-subnets-private" {
   vpc_id            = aws_vpc.cluster-vpc.id
-  count             = length(var.aws_avail_zones)
-  availability_zone = element(var.aws_avail_zones, count.index)
+  count             = length(var.aws_cidr_subnets_private)
+  availability_zone = element(var.aws_avail_zones, count.index % length(var.aws_avail_zones))
   cidr_block        = element(var.aws_cidr_subnets_private, count.index)
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-${element(var.aws_avail_zones, count.index)}-private"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name = "kubernetes-${var.aws_cluster_name}-${element(var.aws_avail_zones, count.index)}-private"
+    "kubernetes.io/cluster/${var.aws_cluster_name}" = "shared"
+    "kubernetes.io/role/internal-elb" = "1"
+  }))
 }
 
 #Routing in VPC
@@ -64,9 +67,9 @@ resource "aws_route_table" "kubernetes-public" {
     gateway_id = aws_internet_gateway.cluster-vpc-internetgw.id
   }
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-routetable-public"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name = "kubernetes-${var.aws_cluster_name}-routetable-public"
+  }))
 }
 
 resource "aws_route_table" "kubernetes-private" {
@@ -78,9 +81,9 @@ resource "aws_route_table" "kubernetes-private" {
     nat_gateway_id = element(aws_nat_gateway.cluster-nat-gateway.*.id, count.index)
   }
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-routetable-private-${count.index}"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name = "kubernetes-${var.aws_cluster_name}-routetable-private-${count.index}"
+  }))
 }
 
 resource "aws_route_table_association" "kubernetes-public" {
@@ -101,9 +104,9 @@ resource "aws_security_group" "kubernetes" {
   name   = "kubernetes-${var.aws_cluster_name}-securitygroup"
   vpc_id = aws_vpc.cluster-vpc.id
 
-  tags = merge(var.default_tags, map(
-    "Name", "kubernetes-${var.aws_cluster_name}-securitygroup"
-  ))
+  tags = merge(var.default_tags, tomap({
+    Name = "kubernetes-${var.aws_cluster_name}-securitygroup"
+  }))
 }
 
 resource "aws_security_group_rule" "allow-all-ingress" {

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

@@ -8,20 +8,20 @@ variable "aws_cluster_name" {
 
 variable "aws_avail_zones" {
   description = "AWS Availability Zones Used"
-  type        = "list"
+  type        = list(string)
 }
 
 variable "aws_cidr_subnets_private" {
   description = "CIDR Blocks for private subnets in Availability zones"
-  type        = "list"
+  type        = list(string)
 }
 
 variable "aws_cidr_subnets_public" {
   description = "CIDR Blocks for public subnets in Availability zones"
-  type        = "list"
+  type        = list(string)
 }
 
 variable "default_tags" {
   description = "Default tags for all resources"
-  type        = "map"
+  type        = map(string)
 }

contrib/terraform/aws/output.tf

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

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

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

contrib/terraform/aws/templates/inventory.tpl

@@ -7,22 +7,21 @@ ${public_ip_address_bastion}
 [bastion]
 ${public_ip_address_bastion}
 
-[kube-master]
+[kube_control_plane]
 ${list_master}
 
-
-[kube-node]
+[kube_node]
 ${list_node}
 
-
 [etcd]
 ${list_etcd}
 
+[calico_rr]
 
-[k8s-cluster:children]
-kube-node
-kube-master
+[k8s_cluster:children]
+kube_node
+kube_control_plane
+calico_rr
 
-
-[k8s-cluster:vars]
-${elb_api_fqdn}
+[k8s_cluster:vars]
+${nlb_api_fqdn}

contrib/terraform/aws/terraform.tfvars

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

contrib/terraform/aws/terraform.tfvars.example

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

contrib/terraform/aws/variables.tf

@@ -25,7 +25,7 @@ data "aws_ami" "distro" {
 
   filter {
     name   = "name"
-    values = ["ubuntu/images/hvm-ssd/ubuntu-bionic-18.04-amd64-server-*"]
+    values = ["debian-10-amd64-*"]
   }
 
   filter {
@@ -33,7 +33,7 @@ data "aws_ami" "distro" {
     values = ["hvm"]
   }
 
-  owners = ["099720109477"] # Canonical
+  owners = ["136693071363"] # Debian-10
 }
 
 //AWS VPC Variables
@@ -44,12 +44,12 @@ variable "aws_vpc_cidr_block" {
 
 variable "aws_cidr_subnets_private" {
   description = "CIDR Blocks for private subnets in Availability Zones"
-  type        = "list"
+  type        = list(string)
 }
 
 variable "aws_cidr_subnets_public" {
   description = "CIDR Blocks for public subnets in Availability Zones"
-  type        = "list"
+  type        = list(string)
 }
 
 //AWS EC2 Settings
@@ -63,10 +63,18 @@ variable "aws_bastion_size" {
 * The number should be divisable by the number of used
 * AWS Availability Zones without an remainder.
 */
+variable "aws_bastion_num" {
+  description = "Number of Bastion Nodes"
+}
+
 variable "aws_kube_master_num" {
   description = "Number of Kubernetes Master Nodes"
 }
 
+variable "aws_kube_master_disk_size" {
+  description = "Disk size for Kubernetes Master Nodes (in GiB)"
+}
+
 variable "aws_kube_master_size" {
   description = "Instance size of Kube Master Nodes"
 }
@@ -75,6 +83,10 @@ variable "aws_etcd_num" {
   description = "Number of etcd Nodes"
 }
 
+variable "aws_etcd_disk_size" {
+  description = "Disk size for etcd Nodes (in GiB)"
+}
+
 variable "aws_etcd_size" {
   description = "Instance size of etcd Nodes"
 }
@@ -83,16 +95,20 @@ variable "aws_kube_worker_num" {
   description = "Number of Kubernetes Worker Nodes"
 }
 
+variable "aws_kube_worker_disk_size" {
+  description = "Disk size for Kubernetes Worker Nodes (in GiB)"
+}
+
 variable "aws_kube_worker_size" {
   description = "Instance size of Kubernetes Worker Nodes"
 }
 
 /*
-* AWS ELB Settings
+* AWS NLB Settings
 *
 */
-variable "aws_elb_api_port" {
-  description = "Port for AWS ELB"
+variable "aws_nlb_api_port" {
+  description = "Port for AWS NLB"
 }
 
 variable "k8s_secure_api_port" {
@@ -101,7 +117,7 @@ variable "k8s_secure_api_port" {
 
 variable "default_tags" {
   description = "Default tags for all resources"
-  type        = "map"
+  type        = map(string)
 }
 
 variable "inventory_file" {

contrib/terraform/exoscale/README.md

@@ -0,0 +1,152 @@
+# Kubernetes on Exoscale with Terraform
+
+Provision a Kubernetes cluster on [Exoscale](https://www.exoscale.com/) using Terraform and Kubespray
+
+## Overview
+
+The setup looks like following
+
+```text
+                           Kubernetes cluster
+                        +-----------------------+
++---------------+       |   +--------------+    |
+|               |       |   | +--------------+  |
+| API server LB +---------> | |              |  |
+|               |       |   | | Master/etcd  |  |
++---------------+       |   | | node(s)      |  |
+                        |   +-+              |  |
+                        |     +--------------+  |
+                        |           ^           |
+                        |           |           |
+                        |           v           |
++---------------+       |   +--------------+    |
+|               |       |   | +--------------+  |
+|  Ingress LB   +---------> | |              |  |
+|               |       |   | |    Worker    |  |
++---------------+       |   | |    node(s)   |  |
+                        |   +-+              |  |
+                        |     +--------------+  |
+                        +-----------------------+
+```
+
+## Requirements
+
+* Terraform 0.13.0 or newer (0.12 also works if you modify the provider block to include version and remove all `versions.tf` files)
+
+## Quickstart
+
+NOTE: *Assumes you are at the root of the kubespray repo*
+
+Copy the sample inventory for your cluster and copy the default terraform variables.
+
+```bash
+CLUSTER=my-exoscale-cluster
+cp -r inventory/sample inventory/$CLUSTER
+cp contrib/terraform/exoscale/default.tfvars inventory/$CLUSTER/
+cd inventory/$CLUSTER
+```
+
+Edit `default.tfvars` to match your setup. You MUST, at the very least, change `ssh_public_keys`.
+
+```bash
+# Ensure $EDITOR points to your favorite editor, e.g., vim, emacs, VS Code, etc.
+$EDITOR default.tfvars
+```
+
+For authentication you can use the credentials file `~/.cloudstack.ini` or `./cloudstack.ini`.
+The file should look like something like this:
+
+```ini
+[cloudstack]
+key = <API key>
+secret = <API secret>
+```
+
+Follow the [Exoscale IAM Quick-start](https://community.exoscale.com/documentation/iam/quick-start/) to learn how to generate API keys.
+
+### Encrypted credentials
+
+To have the credentials encrypted at rest, you can use [sops](https://github.com/mozilla/sops) and only decrypt the credentials at runtime.
+
+```bash
+cat << EOF > cloudstack.ini
+[cloudstack]
+key =
+secret =
+EOF
+sops --encrypt --in-place --pgp <PGP key fingerprint> cloudstack.ini
+sops cloudstack.ini
+```
+
+Run terraform to create the infrastructure
+
+```bash
+terraform init ../../contrib/terraform/exoscale
+terraform apply -var-file default.tfvars ../../contrib/terraform/exoscale
+```
+
+If your cloudstack credentials file is encrypted using sops, run the following:
+
+```bash
+terraform init ../../contrib/terraform/exoscale
+sops exec-file -no-fifo cloudstack.ini 'CLOUDSTACK_CONFIG={} terraform apply -var-file default.tfvars ../../contrib/terraform/exoscale'
+```
+
+You should now have a inventory file named `inventory.ini` that you can use with kubespray.
+You can now copy your inventory file and use it with kubespray to set up a cluster.
+You can type `terraform output` to find out the IP addresses of the nodes, as well as control-plane and data-plane load-balancer.
+
+It is a good idea to check that you have basic SSH connectivity to the nodes. You can do that by:
+
+```bash
+ansible -i inventory.ini -m ping all
+```
+
+Example to use this with the default sample inventory:
+
+```bash
+ansible-playbook -i inventory.ini ../../cluster.yml -b -v
+```
+
+## Teardown
+
+The Kubernetes cluster cannot create any load-balancers or disks, hence, teardown is as simple as Terraform destroy:
+
+```bash
+terraform destroy -var-file default.tfvars ../../contrib/terraform/exoscale
+```
+
+## Variables
+
+### Required
+
+* `ssh_public_keys`: List of public SSH keys to install on all machines
+* `zone`: The zone where to run the cluster
+* `machines`: Machines to provision. Key of this object will be used as the name of the machine
+  * `node_type`: The role of this node *(master|worker)*
+  * `size`: The size to use
+  * `boot_disk`: The boot disk to use
+    * `image_name`: Name of the image
+    * `root_partition_size`: Size *(in GB)* for the root partition
+    * `ceph_partition_size`: Size *(in GB)* for the partition for rook to use as ceph storage. *(Set to 0 to disable)*
+    * `node_local_partition_size`: Size *(in GB)* for the partition for node-local-storage. *(Set to 0 to disable)*
+* `ssh_whitelist`: List of IP ranges (CIDR) that will be allowed to ssh to the nodes
+* `api_server_whitelist`: List of IP ranges (CIDR) that will be allowed to connect to the API server
+* `nodeport_whitelist`: List of IP ranges (CIDR) that will be allowed to connect to the kubernetes nodes on port 30000-32767 (kubernetes nodeports)
+
+### Optional
+
+* `prefix`: Prefix to use for all resources, required to be unique for all clusters in the same project *(Defaults to `default`)*
+
+An example variables file can be found `default.tfvars`
+
+## Known limitations
+
+### Only single disk
+
+Since Exoscale doesn't support additional disks to be mounted onto an instance, this script has the ability to create partitions for [Rook](https://rook.io/) and [node-local-storage](https://kubernetes.io/docs/concepts/storage/volumes/#local).
+
+### No Kubernetes API
+
+The current solution doesn't use the [Exoscale Kubernetes cloud controller](https://github.com/exoscale/exoscale-cloud-controller-manager).
+This means that we need to set up a HTTP(S) loadbalancer in front of all workers and set the Ingress controller to DaemonSet mode.