Compare commits

..

1 Commits

Author SHA1 Message Date
github-actions[bot]
f70f12b0a8 Patch versions updates 2025-03-28 02:47:47 +00:00
546 changed files with 42553 additions and 6688 deletions

View File

@@ -1,4 +1,5 @@
---
parseable: true
skip_list:
# see https://docs.ansible.com/ansible-lint/rules/default_rules.html for a list of all default rules
@@ -11,12 +12,10 @@ skip_list:
# (Disabled in June 2021)
- 'role-name'
# [var-naming]
# [var-naming] "defaults/main.yml" File defines variable 'apiVersion' that violates variable naming standards
# In Kubespray we use variables that use camelCase to match their k8s counterparts
# (Disabled in June 2021)
- 'var-naming[pattern]'
# Variables names from within roles in kubespray don't need role name as a prefix
- 'var-naming[no-role-prefix]'
- 'var-naming'
# [fqcn-builtins]
# Roles in kubespray don't need fully qualified collection names
@@ -33,8 +32,6 @@ skip_list:
# Disable run-once check with free strategy
# (Disabled in June 2023 after ansible upgrade; FIXME)
- 'run-once[task]'
- 'jinja[spacing]'
exclude_paths:
# Generated files
- tests/files/custom_cni/cilium.yaml
@@ -42,7 +39,5 @@ exclude_paths:
- .github
- .ansible
- .cache
- .gitlab-ci.yml
- .gitlab-ci
mock_modules:
- gluster.gluster.gluster_volume

View File

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

View File

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

View File

@@ -13,16 +13,16 @@ jobs:
issues: write
steps:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd
- uses: actions/checkout@v3
- name: Parse issue form
uses: stefanbuck/github-issue-parser@10dcc54158ba4c137713d9d69d70a2da63b6bda3
uses: stefanbuck/github-issue-parser@v3
id: issue-parser
with:
template-path: .github/ISSUE_TEMPLATE/bug-report.yaml
- name: Set labels based on OS field
uses: redhat-plumbers-in-action/advanced-issue-labeler@b80ae64e3e156e9c111b075bfa04b295d54e8e2e
uses: redhat-plumbers-in-action/advanced-issue-labeler@v2
with:
issue-form: ${{ steps.issue-parser.outputs.jsonString }}
section: os

View File

@@ -8,19 +8,18 @@ on:
permissions: {}
jobs:
get-releases-branches:
if: github.repository == 'kubernetes-sigs/kubespray'
runs-on: ubuntu-latest
outputs:
branches: ${{ steps.get-branches.outputs.data }}
steps:
- uses: octokit/graphql-action@ddde8ebb2493e79f390e6449c725c21663a67505
- uses: octokit/graphql-action@v2.3.2
id: get-branches
with:
query: |
query get_release_branches($owner:String!, $name:String!) {
repository(owner:$owner, name:$name) {
refs(refPrefix: "refs/heads/",
first: 3,
first: 0, # TODO increment once we have release branch with the new checksums format
query: "release-",
orderBy: {
field: ALPHABETICAL,

View File

@@ -11,10 +11,10 @@ jobs:
update-patch-versions:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd
- uses: actions/checkout@v4
with:
ref: ${{ inputs.branch }}
- uses: actions/setup-python@v6
- uses: actions/setup-python@v5
with:
python-version: '3.13'
cache: 'pip'
@@ -22,19 +22,19 @@ jobs:
- run: update-hashes
env:
API_KEY: ${{ secrets.GITHUB_TOKEN }}
- uses: actions/cache@v5
- uses: actions/cache@v4
with:
key: pre-commit-hook-propagate
path: |
~/.cache/pre-commit
- run: pre-commit run --all-files propagate-ansible-variables
continue-on-error: true
- uses: peter-evans/create-pull-request@c0f553fe549906ede9cf27b5156039d195d2ece0
- uses: peter-evans/create-pull-request@v7
with:
commit-message: Patch versions updates
title: Patch versions updates - ${{ inputs.branch }}
labels: bot
branch: component_hash_update/${{ inputs.branch }}
branch: ${{ inputs.branch }}-patch-updates
sign-commits: true
body: |
/kind feature

View File

@@ -1,9 +1,9 @@
---
stages:
- build # build docker image used in most other jobs
- test # unit tests
- deploy-part1 # kubespray runs - common setup
- deploy-extended # kubespray runs - rarer or costlier (to test) setups
- build
- test
- deploy-part1
- deploy-extended
variables:
FAILFASTCI_NAMESPACE: 'kargo-ci'
@@ -24,7 +24,6 @@ variables:
ANSIBLE_REMOTE_USER: kubespray
ANSIBLE_PRIVATE_KEY_FILE: /tmp/id_rsa
ANSIBLE_INVENTORY: /tmp/inventory
ANSIBLE_STDOUT_CALLBACK: "default"
RESET_CHECK: "false"
REMOVE_NODE_CHECK: "false"
UPGRADE_TEST: "false"
@@ -32,12 +31,12 @@ variables:
ANSIBLE_VERBOSITY: 2
RECOVER_CONTROL_PLANE_TEST: "false"
RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:]:kube_control_plane[1:]"
OPENTOFU_VERSION: v1.9.1
TERRAFORM_VERSION: 1.3.7
PIPELINE_IMAGE: "$CI_REGISTRY_IMAGE/pipeline:${CI_PIPELINE_ID}-${CI_COMMIT_SHORT_SHA}"
before_script:
- ./tests/scripts/rebase.sh
- mkdir -p cluster-dump $ANSIBLE_INVENTORY
- mkdir -p /.ssh
.job: &job
tags:
@@ -49,18 +48,60 @@ before_script:
- cluster-dump/
needs:
- pipeline-image
variables:
ANSIBLE_STDOUT_CALLBACK: "debug"
.job-moderated:
extends: .job
needs:
- pipeline-image
- ci-not-authorized
- pre-commit # lint
- vagrant-validate # lint
.testcases: &testcases
extends: .job-moderated
interruptible: true
before_script:
- update-alternatives --install /usr/bin/python python /usr/bin/python3 1
- ./tests/scripts/rebase.sh
- ./tests/scripts/testcases_prepare.sh
script:
- ./tests/scripts/testcases_run.sh
after_script:
- ./tests/scripts/testcases_cleanup.sh
# For failfast, at least 1 job must be defined in .gitlab-ci.yml
# Premoderated with manual actions
ci-not-authorized:
stage: build
before_script: []
after_script: []
rules:
# LGTM or ok-to-test labels
- if: $PR_LABELS =~ /.*,(lgtm|approved|ok-to-test).*|^(lgtm|approved|ok-to-test).*/i
variables:
CI_OK_TO_TEST: '0'
when: always
- if: $CI_PIPELINE_SOURCE == "schedule" || $CI_PIPELINE_SOURCE == "trigger"
variables:
CI_OK_TO_TEST: '0'
- if: $CI_COMMIT_BRANCH == "master"
variables:
CI_OK_TO_TEST: '0'
- when: always
variables:
CI_OK_TO_TEST: '1'
script:
- exit $CI_OK_TO_TEST
tags:
- ffci
needs: []
include:
- .gitlab-ci/build.yml
- .gitlab-ci/lint.yml
- .gitlab-ci/terraform.yml
- .gitlab-ci/kubevirt.yml
- .gitlab-ci/packet.yml
- .gitlab-ci/vagrant.yml
- .gitlab-ci/molecule.yml

View File

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

View File

@@ -1,155 +0,0 @@
---
.kubevirt:
extends: .job-moderated
interruptible: true
script:
- ansible-playbook tests/cloud_playbooks/create-kubevirt.yml
-e @"tests/files/${TESTCASE}.yml"
- ./tests/scripts/testcases_run.sh
variables:
ANSIBLE_TIMEOUT: "120"
tags:
- ffci
needs:
- pipeline-image
# TODO: generate testcases matrixes from the files in tests/files/
# this is needed to avoid the need for PR rebasing when a job was added or removed in the target branch
# (currently, a removed job in the target branch breaks the tests, because the
# pipeline definition is parsed by gitlab before the rebase.sh script)
# CI template for PRs
pr:
stage: deploy-part1
rules:
- if: $PR_LABELS =~ /.*ci-short.*/
when: manual
allow_failure: true
- if: $CI_COMMIT_BRANCH =~ /^pr-.*$/
when: on_success
- if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
when: on_success
- when: manual
allow_failure: true
extends: .kubevirt
parallel:
matrix:
- TESTCASE:
- almalinux9-crio
- almalinux9-kube-ovn
- debian11-calico-collection
- debian11-macvlan
- debian12-cilium
- debian13-cilium
- fedora39-kube-router
- openeuler24-calico
- rockylinux9-cilium
- rockylinux10-cilium
- ubuntu22-calico-all-in-one
- ubuntu22-calico-all-in-one-upgrade
- ubuntu24-calico-etcd-datastore
- ubuntu24-calico-all-in-one-hardening
- ubuntu24-cilium-sep
- ubuntu24-flannel-collection
- ubuntu24-kube-router-sep
- ubuntu24-kube-router-svc-proxy
- ubuntu24-ha-separate-etcd
- flatcar4081-calico
- fedora40-flannel-crio-collection-scale
# The ubuntu24-calico-all-in-one jobs are meant as early stages to prevent running the full CI if something is horribly broken
ubuntu24-calico-all-in-one:
stage: deploy-part1
extends: .kubevirt
variables:
TESTCASE: ubuntu24-calico-all-in-one
rules:
- if: $CI_COMMIT_BRANCH =~ /^pr-.*$/
when: on_success
- if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
when: on_success
- when: manual
allow_failure: true
pr_full:
extends: .kubevirt
stage: deploy-extended
rules:
- if: $PR_LABELS =~ /.*ci-full.*/
when: on_success
- if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
when: on_success
# Else run as manual
- when: manual
allow_failure: true
parallel:
matrix:
- TESTCASE:
- almalinux9-calico-ha-ebpf
- almalinux9-calico-nodelocaldns-secondary
- debian11-custom-cni
- debian11-kubelet-csr-approver
- debian12-custom-cni-helm
- fedora39-calico-swap-selinux
- fedora39-crio
- ubuntu24-calico-ha-wireguard
- ubuntu24-flannel-ha
- ubuntu24-flannel-ha-once
# Need an update of the container image to use schema v2
# update: quay.io/kubespray/vm-amazon-linux-2:latest
manual:
extends: pr_full
parallel:
matrix:
- TESTCASE:
- amazon-linux-2-all-in-one
rules:
- when: manual
allow_failure: true
pr_extended:
extends: .kubevirt
stage: deploy-extended
rules:
- if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
when: on_success
- if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
when: on_success
- when: manual
allow_failure: true
parallel:
matrix:
- TESTCASE:
- almalinux9-calico
- almalinux9-calico-remove-node
- almalinux9-docker
- debian11-docker
- debian12-calico
- debian12-docker
- debian13-calico
- rockylinux9-calico
- rockylinux10-calico
- ubuntu22-all-in-one-docker
- ubuntu24-all-in-one-docker
- ubuntu24-calico-all-in-one
- ubuntu24-calico-etcd-kubeadm
- ubuntu24-flannel
# TODO: migrate to pr-full, fix the broken ones
periodic:
allow_failure: true
extends: .kubevirt
rules:
- if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
when: on_success
parallel:
matrix:
- TESTCASE:
- debian11-calico-upgrade
- debian11-calico-upgrade-once
- debian12-cilium-svc-proxy
- fedora39-calico-selinux
- fedora40-docker-calico
- ubuntu24-calico-etcd-kubeadm-upgrade-ha
- ubuntu24-calico-ha-recover
- ubuntu24-calico-ha-recover-noquorum

View File

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

View File

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

257
.gitlab-ci/packet.yml Normal file
View File

@@ -0,0 +1,257 @@
---
.packet:
extends: .testcases
variables:
ANSIBLE_TIMEOUT: "120"
CI_PLATFORM: packet
SSH_USER: kubespray
tags:
- ffci
needs:
- pipeline-image
- ci-not-authorized
# CI template for PRs
.packet_pr:
stage: deploy-part1
rules:
- if: $PR_LABELS =~ /.*ci-short.*/
when: manual
allow_failure: true
- if: $CI_COMMIT_BRANCH =~ /^pr-.*$/
when: on_success
- when: manual
allow_failure: true
extends: .packet
## Uncomment this to have multiple stages
# needs:
# - packet_ubuntu20-calico-all-in-one
.packet_pr_short:
stage: deploy-part1
extends: .packet
rules:
- if: $CI_COMMIT_BRANCH =~ /^pr-.*$/
when: on_success
- when: manual
allow_failure: true
.packet_pr_manual:
extends: .packet_pr
stage: deploy-extended
rules:
- if: $PR_LABELS =~ /.*ci-full.*/
when: on_success
# Else run as manual
- when: manual
allow_failure: true
.packet_pr_extended:
extends: .packet_pr
stage: deploy-extended
rules:
- if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
when: on_success
- when: manual
allow_failure: true
# CI template for periodic CI jobs
# Enabled when PERIODIC_CI_ENABLED var is set
.packet_periodic:
only:
variables:
- $PERIODIC_CI_ENABLED
allow_failure: true
extends: .packet
# The ubuntu20-calico-all-in-one jobs are meant as early stages to prevent running the full CI if something is horribly broken
packet_ubuntu20-calico-all-in-one:
stage: deploy-part1
extends: .packet_pr_short
variables:
RESET_CHECK: "true"
# ### PR JOBS PART2
packet_ubuntu20-crio:
extends: .packet_pr_manual
packet_ubuntu22-calico-all-in-one:
extends: .packet_pr
packet_ubuntu22-calico-all-in-one-upgrade:
extends: .packet_pr
variables:
UPGRADE_TEST: graceful
packet_ubuntu24-calico-etcd-datastore:
extends: .packet_pr
packet_almalinux9-crio:
extends: .packet_pr
packet_almalinux9-kube-ovn:
extends: .packet_pr
packet_debian11-calico-collection:
extends: .packet_pr
packet_debian11-macvlan:
extends: .packet_pr
packet_debian12-cilium:
extends: .packet_pr
packet_almalinux8-calico:
extends: .packet_pr
packet_rockylinux8-calico:
extends: .packet_pr
packet_rockylinux9-cilium:
extends: .packet_pr
variables:
RESET_CHECK: "true"
# Need an update of the container image to use schema v2
# update: quay.io/kubespray/vm-amazon-linux-2:latest
packet_amazon-linux-2-all-in-one:
extends: .packet_pr_manual
rules:
- when: manual
allow_failure: true
packet_opensuse15-6-calico:
extends: .packet_pr
packet_ubuntu20-cilium-sep:
extends: .packet_pr
packet_openeuler24-calico:
extends: .packet_pr
packet_ubuntu20-calico-all-in-one-hardening:
extends: .packet_pr
## Extended
packet_debian11-docker:
extends: .packet_pr_extended
packet_debian12-docker:
extends: .packet_pr_extended
packet_debian12-calico:
extends: .packet_pr_extended
packet_almalinux9-calico-remove-node:
extends: .packet_pr_extended
variables:
REMOVE_NODE_CHECK: "true"
REMOVE_NODE_NAME: "instance-3"
packet_rockylinux9-calico:
extends: .packet_pr_extended
packet_almalinux9-calico:
extends: .packet_pr_extended
packet_almalinux9-docker:
extends: .packet_pr_extended
packet_opensuse15-6-docker-cilium:
extends: .packet_pr_extended
packet_ubuntu24-calico-all-in-one:
extends: .packet_pr_extended
packet_ubuntu20-calico-etcd-kubeadm:
extends: .packet_pr_extended
packet_ubuntu24-all-in-one-docker:
extends: .packet_pr_extended
packet_ubuntu22-all-in-one-docker:
extends: .packet_pr_extended
# ### MANUAL JOBS
packet_fedora39-crio:
extends: .packet_pr_manual
packet_ubuntu20-flannel-ha:
extends: .packet_pr_manual
packet_ubuntu20-all-in-one-docker:
extends: .packet_pr_manual
packet_ubuntu20-flannel-ha-once:
extends: .packet_pr_manual
packet_fedora39-calico-swap-selinux:
extends: .packet_pr_manual
packet_almalinux9-calico-ha-ebpf:
extends: .packet_pr_manual
packet_almalinux9-calico-nodelocaldns-secondary:
extends: .packet_pr_manual
packet_debian11-custom-cni:
extends: .packet_pr_manual
packet_debian11-kubelet-csr-approver:
extends: .packet_pr_manual
packet_debian12-custom-cni-helm:
extends: .packet_pr_manual
packet_ubuntu20-calico-ha-wireguard:
extends: .packet_pr_manual
# PERIODIC
packet_fedora40-docker-calico:
stage: deploy-extended
extends: .packet_periodic
variables:
RESET_CHECK: "true"
packet_fedora39-calico-selinux:
stage: deploy-extended
extends: .packet_periodic
packet_ubuntu20-calico-etcd-kubeadm-upgrade-ha:
stage: deploy-extended
extends: .packet_periodic
variables:
UPGRADE_TEST: basic
packet_debian11-calico-upgrade-once:
stage: deploy-extended
extends: .packet_periodic
variables:
UPGRADE_TEST: graceful
packet_ubuntu20-calico-ha-recover:
stage: deploy-extended
extends: .packet_periodic
variables:
RECOVER_CONTROL_PLANE_TEST: "true"
RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[2:]:kube_control_plane[1:]"
packet_ubuntu20-calico-ha-recover-noquorum:
stage: deploy-extended
extends: .packet_periodic
variables:
RECOVER_CONTROL_PLANE_TEST: "true"
RECOVER_CONTROL_PLANE_TEST_GROUPS: "etcd[1:]:kube_control_plane[1:]"
packet_debian11-calico-upgrade:
stage: deploy-extended
extends: .packet_periodic
variables:
UPGRADE_TEST: graceful
packet_debian12-cilium-svc-proxy:
stage: deploy-extended
extends: .packet_periodic

View File

@@ -3,40 +3,39 @@
.terraform_install:
extends: .job
needs:
- ci-not-authorized
- pipeline-image
variables:
TF_VAR_public_key_path: "${ANSIBLE_PRIVATE_KEY_FILE}.pub"
TF_VAR_ssh_private_key_path: $ANSIBLE_PRIVATE_KEY_FILE
CLUSTER: $CI_COMMIT_REF_NAME
TERRAFORM_STATE_ROOT: $CI_PROJECT_DIR
stage: deploy-part1
before_script:
- update-alternatives --install /usr/bin/python python /usr/bin/python3 1
- ./tests/scripts/rebase.sh
- mkdir -p cluster-dump $ANSIBLE_INVENTORY
- ./tests/scripts/opentofu_install.sh
- ./tests/scripts/testcases_prepare.sh
- ./tests/scripts/terraform_install.sh
# Set Ansible config
- cp ansible.cfg ~/.ansible.cfg
# Prepare inventory
- cp contrib/terraform/$PROVIDER/sample-inventory/cluster.tfvars .
- ln -rs -t $ANSIBLE_INVENTORY contrib/terraform/$PROVIDER/hosts
- tofu -chdir="contrib/terraform/$PROVIDER" init
- ln -s contrib/terraform/$PROVIDER/hosts
- terraform -chdir="contrib/terraform/$PROVIDER" init
# Copy SSH keypair
- mkdir -p ~/.ssh
- echo "$PACKET_PRIVATE_KEY" | base64 -d > ~/.ssh/id_rsa
- chmod 400 ~/.ssh/id_rsa
- echo "$PACKET_PUBLIC_KEY" | base64 -d > ~/.ssh/id_rsa.pub
- mkdir -p contrib/terraform/$PROVIDER/group_vars
# Random subnet to avoid routing conflicts
- export TF_VAR_subnet_cidr="10.$(( $RANDOM % 256 )).$(( $RANDOM % 256 )).0/24"
terraform_validate:
.terraform_validate:
extends: .terraform_install
tags: [ffci]
only: ['master', /^pr-.*$/]
script:
- tofu -chdir="contrib/terraform/$PROVIDER" validate
- tofu -chdir="contrib/terraform/$PROVIDER" fmt -check -diff
- terraform -chdir="contrib/terraform/$PROVIDER" validate
- terraform -chdir="contrib/terraform/$PROVIDER" fmt -check -diff
stage: test
needs:
- pipeline-image
parallel:
matrix:
- PROVIDER:
- openstack
- aws
- exoscale
- hetzner
- vsphere
- upcloud
.terraform_apply:
extends: .terraform_install
@@ -44,24 +43,99 @@ terraform_validate:
stage: deploy-extended
when: manual
only: [/^pr-.*$/]
artifacts:
when: always
paths:
- cluster-dump/
variables:
ANSIBLE_INVENTORY_UNPARSED_FAILED: "true"
ANSIBLE_REMOTE_USER: ubuntu # the openstack terraform module does not handle custom user correctly
ANSIBLE_SSH_RETRIES: 15
TF_VAR_ssh_user: $ANSIBLE_REMOTE_USER
ANSIBLE_INVENTORY: hosts
CI_PLATFORM: tf
TF_VAR_ssh_user: $SSH_USER
TF_VAR_cluster_name: $CI_JOB_ID
script:
# Set Ansible config
- cp ansible.cfg ~/.ansible.cfg
- ssh-keygen -N '' -f $ANSIBLE_PRIVATE_KEY_FILE -t rsa
- mkdir -p contrib/terraform/$PROVIDER/group_vars
# Random subnet to avoid routing conflicts
- export TF_VAR_subnet_cidr="10.$(( $RANDOM % 256 )).$(( $RANDOM % 256 )).0/24"
- tofu -chdir="contrib/terraform/$PROVIDER" apply -auto-approve -parallelism=1
- tests/scripts/testcases_run.sh
after_script:
# Cleanup regardless of exit code
- tofu -chdir="contrib/terraform/$PROVIDER" destroy -auto-approve
- ./tests/scripts/testcases_cleanup.sh
tf-validate-openstack:
extends: .terraform_validate
variables:
TF_VERSION: $TERRAFORM_VERSION
PROVIDER: openstack
CLUSTER: $CI_COMMIT_REF_NAME
tf-validate-equinix:
extends: .terraform_validate
variables:
TF_VERSION: $TERRAFORM_VERSION
PROVIDER: equinix
CLUSTER: $CI_COMMIT_REF_NAME
tf-validate-aws:
extends: .terraform_validate
variables:
TF_VERSION: $TERRAFORM_VERSION
PROVIDER: aws
CLUSTER: $CI_COMMIT_REF_NAME
tf-validate-exoscale:
extends: .terraform_validate
variables:
TF_VERSION: $TERRAFORM_VERSION
PROVIDER: exoscale
tf-validate-hetzner:
extends: .terraform_validate
variables:
TF_VERSION: $TERRAFORM_VERSION
PROVIDER: hetzner
tf-validate-vsphere:
extends: .terraform_validate
variables:
TF_VERSION: $TERRAFORM_VERSION
PROVIDER: vsphere
CLUSTER: $CI_COMMIT_REF_NAME
tf-validate-upcloud:
extends: .terraform_validate
variables:
TF_VERSION: $TERRAFORM_VERSION
PROVIDER: upcloud
CLUSTER: $CI_COMMIT_REF_NAME
tf-validate-nifcloud:
extends: .terraform_validate
variables:
TF_VERSION: $TERRAFORM_VERSION
PROVIDER: nifcloud
# tf-packet-ubuntu20-default:
# extends: .terraform_apply
# variables:
# TF_VERSION: $TERRAFORM_VERSION
# PROVIDER: packet
# CLUSTER: $CI_COMMIT_REF_NAME
# TF_VAR_number_of_k8s_masters: "1"
# TF_VAR_number_of_k8s_nodes: "1"
# TF_VAR_plan_k8s_masters: t1.small.x86
# TF_VAR_plan_k8s_nodes: t1.small.x86
# TF_VAR_metro: am
# TF_VAR_public_key_path: ""
# TF_VAR_operating_system: ubuntu_20_04
.ovh_variables: &ovh_variables
OS_AUTH_URL: https://auth.cloud.ovh.net/v3
OS_PROJECT_ID: 8d3cd5d737d74227ace462dee0b903fe
OS_PROJECT_NAME: "9361447987648822"
OS_USER_DOMAIN_NAME: Default
OS_PROJECT_DOMAIN_ID: default
OS_USERNAME: 8XuhBMfkKVrk
OS_REGION_NAME: UK1
OS_INTERFACE: public
OS_IDENTITY_API_VERSION: "3"
# Elastx is generously donating resources for Kubespray on Openstack CI
# Contacts: @gix @bl0m1
@@ -88,14 +162,18 @@ tf-elastx_cleanup:
- ./scripts/openstack-cleanup/main.py
allow_failure: true
tf-elastx_ubuntu24-calico:
tf-elastx_ubuntu20-calico:
extends: .terraform_apply
stage: deploy-part1
when: on_success
allow_failure: true
variables:
<<: *elastx_variables
TF_VERSION: $TERRAFORM_VERSION
PROVIDER: openstack
CLUSTER: $CI_COMMIT_REF_NAME
ANSIBLE_TIMEOUT: "60"
SSH_USER: ubuntu
TF_VAR_number_of_k8s_masters: "1"
TF_VAR_number_of_k8s_masters_no_floating_ip: "0"
TF_VAR_number_of_k8s_masters_no_floating_ip_no_etcd: "0"
@@ -114,5 +192,48 @@ tf-elastx_ubuntu24-calico:
TF_VAR_az_list_node: '["sto1"]'
TF_VAR_flavor_k8s_master: 3f73fc93-ec61-4808-88df-2580d94c1a9b # v1-standard-2
TF_VAR_flavor_k8s_node: 3f73fc93-ec61-4808-88df-2580d94c1a9b # v1-standard-2
TF_VAR_image: ubuntu-24.04-server-latest
TF_VAR_image: ubuntu-20.04-server-latest
TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'
# OVH voucher expired, commenting job until things are sorted out
# tf-ovh_cleanup:
# stage: unit-tests
# tags: [light]
# image: python
# environment: ovh
# variables:
# <<: *ovh_variables
# before_script:
# - pip install -r scripts/openstack-cleanup/requirements.txt
# script:
# - ./scripts/openstack-cleanup/main.py
# tf-ovh_ubuntu20-calico:
# extends: .terraform_apply
# when: on_success
# environment: ovh
# variables:
# <<: *ovh_variables
# TF_VERSION: $TERRAFORM_VERSION
# PROVIDER: openstack
# CLUSTER: $CI_COMMIT_REF_NAME
# ANSIBLE_TIMEOUT: "60"
# SSH_USER: ubuntu
# TF_VAR_number_of_k8s_masters: "0"
# TF_VAR_number_of_k8s_masters_no_floating_ip: "1"
# TF_VAR_number_of_k8s_masters_no_floating_ip_no_etcd: "0"
# TF_VAR_number_of_etcd: "0"
# TF_VAR_number_of_k8s_nodes: "0"
# TF_VAR_number_of_k8s_nodes_no_floating_ip: "1"
# TF_VAR_number_of_gfs_nodes_no_floating_ip: "0"
# TF_VAR_number_of_bastions: "0"
# TF_VAR_number_of_k8s_masters_no_etcd: "0"
# TF_VAR_use_neutron: "0"
# TF_VAR_floatingip_pool: "Ext-Net"
# TF_VAR_external_net: "6011fbc9-4cbf-46a4-8452-6890a340b60b"
# TF_VAR_network_name: "Ext-Net"
# TF_VAR_flavor_k8s_master: "defa64c3-bd46-43b4-858a-d93bbae0a229" # s1-8
# TF_VAR_flavor_k8s_node: "defa64c3-bd46-43b4-858a-d93bbae0a229" # s1-8
# TF_VAR_image: "Ubuntu 20.04"
# TF_VAR_k8s_allowed_remote_ips: '["0.0.0.0/0"]'

View File

@@ -1,16 +1,20 @@
---
vagrant:
extends: .job-moderated
.vagrant:
extends: .testcases
needs:
- ci-not-authorized
variables:
CI_PLATFORM: "vagrant"
SSH_USER: "vagrant"
VAGRANT_DEFAULT_PROVIDER: "libvirt"
KUBESPRAY_VAGRANT_CONFIG: tests/files/${TESTCASE}.rb
KUBESPRAY_VAGRANT_CONFIG: tests/files/${CI_JOB_NAME}.rb
DOCKER_NAME: vagrant
VAGRANT_ANSIBLE_TAGS: facts
VAGRANT_HOME: "$CI_PROJECT_DIR/.vagrant.d"
PIP_CACHE_DIR: "$CI_PROJECT_DIR/.cache/pip"
tags: [ffci-vm-large]
# only: [/^pr-.*$/]
# except: ['triggers']
image: quay.io/kubespray/vm-kubespray-ci:v13
services: []
before_script:
@@ -24,26 +28,54 @@ vagrant:
- pip install --no-compile --no-cache-dir -r $CI_PROJECT_DIR/tests/requirements.txt
- ./tests/scripts/vagrant_clean.sh
script:
- vagrant up
- ./tests/scripts/testcases_run.sh
after_script:
- vagrant destroy -f
cache:
key: $CI_JOB_NAME_SLUG
paths:
- .vagrant.d/boxes
- .cache/pip
policy: pull-push # TODO: change to "pull" when not on main
vagrant_ubuntu24-calico-dual-stack:
stage: deploy-extended
extends: .vagrant
rules:
- if: $PR_LABELS =~ /.*ci-full.*/
- if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
when: on_success
- if: $CI_PIPELINE_SOURCE == "schedule" && $CI_PIPELINE_SCHEDULE_DESCRIPTION == "daily-ci"
allow_failure: false
vagrant_ubuntu24-calico-ipv6only-stack:
stage: deploy-extended
extends: .vagrant
rules:
- if: $PR_LABELS =~ /.*(ci-extended|ci-full).*/
when: on_success
- when: manual
allow_failure: true
parallel:
matrix:
- TESTCASE:
- ubuntu24-calico-dual-stack
- ubuntu24-calico-ipv6only-stack
allow_failure: false
vagrant_ubuntu20-flannel:
stage: deploy-part1
extends: .vagrant
when: on_success
allow_failure: false
vagrant_ubuntu20-flannel-collection:
stage: deploy-extended
extends: .vagrant
when: manual
vagrant_ubuntu20-kube-router-sep:
stage: deploy-extended
extends: .vagrant
when: manual
# Service proxy test fails connectivity testing
vagrant_ubuntu20-kube-router-svc-proxy:
stage: deploy-extended
extends: .vagrant
when: manual
vagrant_fedora39-kube-router:
stage: deploy-extended
extends: .vagrant
when: manual
# FIXME: this test if broken (perma-failing)

View File

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

View File

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

View File

@@ -1,7 +1,7 @@
# syntax=docker/dockerfile:1
# Use immutable image tags rather than mutable tags (like ubuntu:24.04)
FROM ubuntu:noble-20260113@sha256:cd1dba651b3080c3686ecf4e3c4220f026b521fb76978881737d24f200828b2b
# Use imutable image tags rather than mutable tags (like ubuntu:22.04)
FROM ubuntu:22.04@sha256:149d67e29f765f4db62aa52161009e99e389544e25a8f43c8c89d4a445a7ca37
# Some tools like yamllint need this
# Pip needs this as well at the moment to install ansible
@@ -29,14 +29,14 @@ RUN --mount=type=cache,target=/var/cache/apt,sharing=locked \
RUN --mount=type=bind,source=requirements.txt,target=requirements.txt \
--mount=type=cache,sharing=locked,id=pipcache,mode=0777,target=/root/.cache/pip \
pip install --break-system-packages --no-compile --no-cache-dir -r requirements.txt \
pip install --no-compile --no-cache-dir -r requirements.txt \
&& find /usr -type d -name '*__pycache__' -prune -exec rm -rf {} \;
SHELL ["/bin/bash", "-o", "pipefail", "-c"]
RUN OS_ARCHITECTURE=$(dpkg --print-architecture) \
&& curl -L "https://dl.k8s.io/release/v1.34.3/bin/linux/${OS_ARCHITECTURE}/kubectl" -o /usr/local/bin/kubectl \
&& echo "$(curl -L "https://dl.k8s.io/release/v1.34.3/bin/linux/${OS_ARCHITECTURE}/kubectl.sha256")" /usr/local/bin/kubectl | sha256sum --check \
&& curl -L "https://dl.k8s.io/release/v1.32.3/bin/linux/${OS_ARCHITECTURE}/kubectl" -o /usr/local/bin/kubectl \
&& echo "$(curl -L "https://dl.k8s.io/release/v1.32.3/bin/linux/${OS_ARCHITECTURE}/kubectl.sha256")" /usr/local/bin/kubectl | sha256sum --check \
&& chmod a+x /usr/local/bin/kubectl
COPY *.yml ./

View File

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

View File

@@ -22,7 +22,7 @@ Ensure you have installed Docker then
```ShellSession
docker run --rm -it --mount type=bind,source="$(pwd)"/inventory/sample,dst=/inventory \
--mount type=bind,source="${HOME}"/.ssh/id_rsa,dst=/root/.ssh/id_rsa \
quay.io/kubespray/kubespray:v2.30.0 bash
quay.io/kubespray/kubespray:v2.27.0 bash
# Inside the container you may now run the kubespray playbooks:
ansible-playbook -i /inventory/inventory.ini --private-key /root/.ssh/id_rsa cluster.yml
```
@@ -87,15 +87,15 @@ vagrant up
## Supported Linux Distributions
- **Flatcar Container Linux by Kinvolk**
- **Debian** Bookworm, Bullseye, Trixie
- **Ubuntu** 22.04, 24.04
- **CentOS Stream / RHEL** [9, 10](docs/operating_systems/rhel.md#rhel-8)
- **Debian** Bookworm, Bullseye
- **Ubuntu** 20.04, 22.04, 24.04
- **CentOS/RHEL** [8, 9](docs/operating_systems/rhel.md#rhel-8)
- **Fedora** 39, 40
- **Fedora CoreOS** (see [fcos Note](docs/operating_systems/fcos.md))
- **openSUSE** Leap 15.x/Tumbleweed
- **Oracle Linux** [9, 10](docs/operating_systems/rhel.md#rhel-8)
- **Alma Linux** [9, 10](docs/operating_systems/rhel.md#rhel-8)
- **Rocky Linux** [9, 10](docs/operating_systems/rhel.md#rhel-8) (experimental in 10: see [Rocky Linux 10 notes](docs/operating_systems/rhel.md#rocky-linux-10))
- **Oracle Linux** [8, 9](docs/operating_systems/rhel.md#rhel-8)
- **Alma Linux** [8, 9](docs/operating_systems/rhel.md#rhel-8)
- **Rocky Linux** [8, 9](docs/operating_systems/rhel.md#rhel-8)
- **Kylin Linux Advanced Server V10** (experimental: see [kylin linux notes](docs/operating_systems/kylinlinux.md))
- **Amazon Linux 2** (experimental: see [amazon linux notes](docs/operating_systems/amazonlinux.md))
- **UOS Linux** (experimental: see [uos linux notes](docs/operating_systems/uoslinux.md))
@@ -111,34 +111,37 @@ Note:
<!-- BEGIN ANSIBLE MANAGED BLOCK -->
- Core
- [kubernetes](https://github.com/kubernetes/kubernetes) 1.34.3
- [etcd](https://github.com/etcd-io/etcd) 3.5.26
- [docker](https://www.docker.com/) 28.3
- [containerd](https://containerd.io/) 2.2.1
- [cri-o](http://cri-o.io/) 1.34.4 (experimental: see [CRI-O Note](docs/CRI/cri-o.md). Only on fedora, ubuntu and centos based OS)
- [kubernetes](https://github.com/kubernetes/kubernetes) 1.32.3
- [etcd](https://github.com/etcd-io/etcd) 3.5.16
- [docker](https://www.docker.com/) 28.0
- [containerd](https://containerd.io/) 2.0.4
- [cri-o](http://cri-o.io/) 1.32.0 (experimental: see [CRI-O Note](docs/CRI/cri-o.md). Only on fedora, ubuntu and centos based OS)
- Network Plugin
- [cni-plugins](https://github.com/containernetworking/plugins) 1.8.0
- [calico](https://github.com/projectcalico/calico) 3.30.6
- [cilium](https://github.com/cilium/cilium) 1.18.6
- [flannel](https://github.com/flannel-io/flannel) 0.27.3
- [cni-plugins](https://github.com/containernetworking/plugins) 1.4.1
- [calico](https://github.com/projectcalico/calico) 3.29.3
- [cilium](https://github.com/cilium/cilium) 1.15.9
- [flannel](https://github.com/flannel-io/flannel) 0.22.0
- [kube-ovn](https://github.com/alauda/kube-ovn) 1.12.21
- [kube-router](https://github.com/cloudnativelabs/kube-router) 2.1.1
- [multus](https://github.com/k8snetworkplumbingwg/multus-cni) 4.2.2
- [kube-vip](https://github.com/kube-vip/kube-vip) 1.0.3
- [multus](https://github.com/k8snetworkplumbingwg/multus-cni) 4.1.0
- [weave](https://github.com/rajch/weave) 2.8.7
- [kube-vip](https://github.com/kube-vip/kube-vip) 0.8.0
- Application
- [cert-manager](https://github.com/jetstack/cert-manager) 1.15.3
- [coredns](https://github.com/coredns/coredns) 1.12.1
- [ingress-nginx](https://github.com/kubernetes/ingress-nginx) 1.13.3
- [coredns](https://github.com/coredns/coredns) 1.11.3
- [ingress-nginx](https://github.com/kubernetes/ingress-nginx) 1.12.1
- [argocd](https://argoproj.github.io/) 2.14.5
- [helm](https://helm.sh/) 3.18.4
- [helm](https://helm.sh/) 3.16.4
- [metallb](https://metallb.universe.tf/) 0.13.9
- [registry](https://github.com/distribution/distribution) 2.8.1
- Storage Plugin
- [cephfs-provisioner](https://github.com/kubernetes-incubator/external-storage) 2.1.0-k8s1.11
- [rbd-provisioner](https://github.com/kubernetes-incubator/external-storage) 2.1.1-k8s1.11
- [aws-ebs-csi-plugin](https://github.com/kubernetes-sigs/aws-ebs-csi-driver) 0.5.0
- [azure-csi-plugin](https://github.com/kubernetes-sigs/azuredisk-csi-driver) 1.10.0
- [cinder-csi-plugin](https://github.com/kubernetes/cloud-provider-openstack/blob/master/docs/cinder-csi-plugin/using-cinder-csi-plugin.md) 1.30.0
- [gcp-pd-csi-plugin](https://github.com/kubernetes-sigs/gcp-compute-persistent-disk-csi-driver) 1.9.2
- [local-path-provisioner](https://github.com/rancher/local-path-provisioner) 0.0.32
- [local-path-provisioner](https://github.com/rancher/local-path-provisioner) 0.0.24
- [local-volume-provisioner](https://github.com/kubernetes-sigs/sig-storage-local-static-provisioner) 2.5.0
- [node-feature-discovery](https://github.com/kubernetes-sigs/node-feature-discovery) 0.16.4
@@ -182,6 +185,9 @@ You can choose among ten network plugins. (default: `calico`, except Vagrant use
- [cilium](http://docs.cilium.io/en/latest/): layer 3/4 networking (as well as layer 7 to protect and secure application protocols), supports dynamic insertion of BPF bytecode into the Linux kernel to implement security services, networking and visibility logic.
- [weave](docs/CNI/weave.md): Weave is a lightweight container overlay network that doesn't require an external K/V database cluster.
(Please refer to `weave` [troubleshooting documentation](https://www.weave.works/docs/net/latest/troubleshooting/)).
- [kube-ovn](docs/CNI/kube-ovn.md): Kube-OVN integrates the OVN-based Network Virtualization with Kubernetes. It offers an advanced Container Network Fabric for Enterprises.
- [kube-router](docs/CNI/kube-router.md): Kube-router is a L3 CNI for Kubernetes networking aiming to provide operational

View File

@@ -15,7 +15,7 @@ The Kubespray Project is released on an as-needed basis. The process is as follo
1. The release issue is closed
1. An announcement email is sent to `dev@kubernetes.io` with the subject `[ANNOUNCE] Kubespray $VERSION is released`
1. The topic of the #kubespray channel is updated with `vX.Y.Z is released! | ...`
1. Create/Update Issue for upgrading kubernetes and [k8s-conformance](https://github.com/cncf/k8s-conformance)
1. Create/Update Issue for upgradeing kubernetes and [k8s-conformance](https://github.com/cncf/k8s-conformance)
## Major/minor releases and milestones

29
Vagrantfile vendored
View File

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

View File

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

View File

@@ -1,9 +0,0 @@
#!/bin/bash -eux
# Install collection from source assuming dependencies are present.
# Run in SemaphoreUI this bash script can install Kubespray from the repo
NAMESPACE=kubernetes_sigs
COLLECTION=kubespray
MY_VER=$(grep '^version:' galaxy.yml|cut -d: -f2|sed 's/ //')
ansible-galaxy collection build --force --output-path .
ansible-galaxy collection install --offline --force $NAMESPACE-$COLLECTION-$MY_VER.tar.gz

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -20,6 +20,7 @@ function create_container_image_tar() {
kubectl describe cronjobs,jobs,pods --all-namespaces | grep " Image:" | awk '{print $2}' | sort | uniq > "${IMAGES}"
# NOTE: etcd and pause cannot be seen as pods.
# The pause image is used for --pod-infra-container-image option of kubelet.
kubectl cluster-info dump | grep -E "quay.io/coreos/etcd:|registry.k8s.io/pause:" | sed s@\"@@g >> "${IMAGES}"
else
echo "Getting images from file \"${IMAGES_FROM_FILE}\""
@@ -35,7 +36,7 @@ function create_container_image_tar() {
mkdir ${IMAGE_DIR}
cd ${IMAGE_DIR}
sudo --preserve-env=http_proxy,https_proxy,no_proxy ${runtime} pull registry:latest
sudo ${runtime} pull registry:latest
sudo ${runtime} save -o registry-latest.tar registry:latest
while read -r image
@@ -44,7 +45,7 @@ function create_container_image_tar() {
set +e
for step in $(seq 1 ${RETRY_COUNT})
do
sudo --preserve-env=http_proxy,https_proxy,no_proxy ${runtime} pull ${image}
sudo ${runtime} pull ${image}
if [ $? -eq 0 ]; then
break
fi
@@ -126,7 +127,7 @@ function register_container_images() {
tar -zxvf ${IMAGE_TAR_FILE}
if ${create_registry}; then
if [ "${create_registry}" ]; then
sudo ${runtime} load -i ${IMAGE_DIR}/registry-latest.tar
set +e
@@ -147,7 +148,7 @@ function register_container_images() {
if [ "${org_image}" == "ID:" ]; then
org_image=$(echo "${load_image}" | awk '{print $4}')
fi
image_id=$(sudo ${runtime} image inspect --format "{{.Id}}" "${org_image}")
image_id=$(sudo ${runtime} image inspect ${org_image} | grep "\"Id\":" | awk -F: '{print $3}'| sed s/'\",'//)
if [ -z "${file_name}" ]; then
echo "Failed to get file_name for line ${line}"
exit 1

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

View File

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

5
contrib/terraform/nifcloud/.gitignore vendored Normal file
View File

@@ -0,0 +1,5 @@
*.tfstate*
.terraform.lock.hcl
.terraform
sample-inventory/inventory.ini

View File

@@ -0,0 +1,138 @@
# Kubernetes on NIFCLOUD with Terraform
Provision a Kubernetes cluster on [NIFCLOUD](https://pfs.nifcloud.com/) using Terraform and Kubespray
## Overview
The setup looks like following
```text
Kubernetes cluster
+----------------------------+
+---------------+ | +--------------------+ |
| | | | +--------------------+ |
| API server LB +---------> | | | |
| | | | | Control Plane/etcd | |
+---------------+ | | | node(s) | |
| +-+ | |
| +--------------------+ |
| ^ |
| | |
| v |
| +--------------------+ |
| | +--------------------+ |
| | | | |
| | | Worker | |
| | | node(s) | |
| +-+ | |
| +--------------------+ |
+----------------------------+
```
## Requirements
* Terraform 1.3.7
## Quickstart
### Export Variables
* Your NIFCLOUD credentials:
```bash
export NIFCLOUD_ACCESS_KEY_ID=<YOUR ACCESS KEY>
export NIFCLOUD_SECRET_ACCESS_KEY=<YOUR SECRET ACCESS KEY>
```
* The SSH KEY used to connect to the instance:
* FYI: [Cloud Help(SSH Key)](https://pfs.nifcloud.com/help/ssh.htm)
```bash
export TF_VAR_SSHKEY_NAME=<YOUR SSHKEY NAME>
```
* The IP address to connect to bastion server:
```bash
export TF_VAR_working_instance_ip=$(curl ifconfig.me)
```
### Create The Infrastructure
* Run terraform:
```bash
terraform init
terraform apply -var-file ./sample-inventory/cluster.tfvars
```
### Setup The Kubernetes
* Generate cluster configuration file:
```bash
./generate-inventory.sh > sample-inventory/inventory.ini
```
* Export Variables:
```bash
BASTION_IP=$(terraform output -json | jq -r '.kubernetes_cluster.value.bastion_info | to_entries[].value.public_ip')
API_LB_IP=$(terraform output -json | jq -r '.kubernetes_cluster.value.control_plane_lb')
CP01_IP=$(terraform output -json | jq -r '.kubernetes_cluster.value.control_plane_info | to_entries[0].value.private_ip')
export ANSIBLE_SSH_ARGS="-o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -o ProxyCommand=\"ssh root@${BASTION_IP} -W %h:%p\""
```
* Set ssh-agent"
```bash
eval `ssh-agent`
ssh-add <THE PATH TO YOUR SSH KEY>
```
* Run cluster.yml playbook:
```bash
cd ./../../../
ansible-playbook -i contrib/terraform/nifcloud/inventory/inventory.ini cluster.yml
```
### Connecting to Kubernetes
* [Install kubectl](https://kubernetes.io/docs/tasks/tools/) on the localhost
* Fetching kubeconfig file:
```bash
mkdir -p ~/.kube
scp -o ProxyCommand="ssh root@${BASTION_IP} -W %h:%p" root@${CP01_IP}:/etc/kubernetes/admin.conf ~/.kube/config
```
* Rewrite /etc/hosts
```bash
sudo echo "${API_LB_IP} lb-apiserver.kubernetes.local" >> /etc/hosts
```
* Run kubectl
```bash
kubectl get node
```
## Variables
* `region`: Region where to run the cluster
* `az`: Availability zone where to run the cluster
* `private_ip_bn`: Private ip address of bastion server
* `private_network_cidr`: Subnet of private network
* `instances_cp`: Machine to provision as Control Plane. Key of this object will be used as part of the machine' name
* `private_ip`: private ip address of machine
* `instances_wk`: Machine to provision as Worker Node. Key of this object will be used as part of the machine' name
* `private_ip`: private ip address of machine
* `instance_key_name`: The key name of the Key Pair to use for the instance
* `instance_type_bn`: The instance type of bastion server
* `instance_type_wk`: The instance type of worker node
* `instance_type_cp`: The instance type of control plane
* `image_name`: OS image used for the instance
* `working_instance_ip`: The IP address to connect to bastion server
* `accounting_type`: Accounting type. (1: monthly, 2: pay per use)

View File

@@ -0,0 +1,64 @@
#!/bin/bash
#
# Generates a inventory file based on the terraform output.
# After provisioning a cluster, simply run this command and supply the terraform state file
# Default state file is terraform.tfstate
#
set -e
TF_OUT=$(terraform output -json)
CONTROL_PLANES=$(jq -r '.kubernetes_cluster.value.control_plane_info | to_entries[]' <(echo "${TF_OUT}"))
WORKERS=$(jq -r '.kubernetes_cluster.value.worker_info | to_entries[]' <(echo "${TF_OUT}"))
mapfile -t CONTROL_PLANE_NAMES < <(jq -r '.key' <(echo "${CONTROL_PLANES}"))
mapfile -t WORKER_NAMES < <(jq -r '.key' <(echo "${WORKERS}"))
API_LB=$(jq -r '.kubernetes_cluster.value.control_plane_lb' <(echo "${TF_OUT}"))
echo "[all]"
# Generate control plane hosts
i=1
for name in "${CONTROL_PLANE_NAMES[@]}"; do
private_ip=$(jq -r '. | select( .key=='"\"${name}\""' ) | .value.private_ip' <(echo "${CONTROL_PLANES}"))
echo "${name} ansible_user=root ansible_host=${private_ip} access_ip=${private_ip} ip=${private_ip} etcd_member_name=etcd${i}"
i=$(( i + 1 ))
done
# Generate worker hosts
for name in "${WORKER_NAMES[@]}"; do
private_ip=$(jq -r '. | select( .key=='"\"${name}\""' ) | .value.private_ip' <(echo "${WORKERS}"))
echo "${name} ansible_user=root ansible_host=${private_ip} access_ip=${private_ip} ip=${private_ip}"
done
API_LB=$(jq -r '.kubernetes_cluster.value.control_plane_lb' <(echo "${TF_OUT}"))
echo ""
echo "[all:vars]"
echo "upstream_dns_servers=['8.8.8.8','8.8.4.4']"
echo "loadbalancer_apiserver={'address':'${API_LB}','port':'6443'}"
echo ""
echo "[kube_control_plane]"
for name in "${CONTROL_PLANE_NAMES[@]}"; do
echo "${name}"
done
echo ""
echo "[etcd]"
for name in "${CONTROL_PLANE_NAMES[@]}"; do
echo "${name}"
done
echo ""
echo "[kube_node]"
for name in "${WORKER_NAMES[@]}"; do
echo "${name}"
done
echo ""
echo "[k8s_cluster:children]"
echo "kube_control_plane"
echo "kube_node"

View File

@@ -0,0 +1,36 @@
provider "nifcloud" {
region = var.region
}
module "kubernetes_cluster" {
source = "./modules/kubernetes-cluster"
availability_zone = var.az
prefix = "dev"
private_network_cidr = var.private_network_cidr
instance_key_name = var.instance_key_name
instances_cp = var.instances_cp
instances_wk = var.instances_wk
image_name = var.image_name
instance_type_bn = var.instance_type_bn
instance_type_cp = var.instance_type_cp
instance_type_wk = var.instance_type_wk
private_ip_bn = var.private_ip_bn
additional_lb_filter = [var.working_instance_ip]
}
resource "nifcloud_security_group_rule" "ssh_from_bastion" {
security_group_names = [
module.kubernetes_cluster.security_group_name.bastion
]
type = "IN"
from_port = 22
to_port = 22
protocol = "TCP"
cidr_ip = var.working_instance_ip
}

View File

@@ -0,0 +1,301 @@
#################################################
##
## Local variables
##
locals {
# e.g. east-11 is 11
az_num = reverse(split("-", var.availability_zone))[0]
# e.g. east-11 is e11
az_short_name = "${substr(reverse(split("-", var.availability_zone))[1], 0, 1)}${local.az_num}"
# Port used by the protocol
port_ssh = 22
port_kubectl = 6443
port_kubelet = 10250
# calico: https://docs.tigera.io/calico/latest/getting-started/kubernetes/requirements#network-requirements
port_bgp = 179
port_vxlan = 4789
port_etcd = 2379
}
#################################################
##
## General
##
# data
data "nifcloud_image" "this" {
image_name = var.image_name
}
# private lan
resource "nifcloud_private_lan" "this" {
private_lan_name = "${var.prefix}lan"
availability_zone = var.availability_zone
cidr_block = var.private_network_cidr
accounting_type = var.accounting_type
}
#################################################
##
## Bastion
##
resource "nifcloud_security_group" "bn" {
group_name = "${var.prefix}bn"
description = "${var.prefix} bastion"
availability_zone = var.availability_zone
}
resource "nifcloud_instance" "bn" {
instance_id = "${local.az_short_name}${var.prefix}bn01"
security_group = nifcloud_security_group.bn.group_name
instance_type = var.instance_type_bn
user_data = templatefile("${path.module}/templates/userdata.tftpl", {
private_ip_address = var.private_ip_bn
ssh_port = local.port_ssh
hostname = "${local.az_short_name}${var.prefix}bn01"
})
availability_zone = var.availability_zone
accounting_type = var.accounting_type
image_id = data.nifcloud_image.this.image_id
key_name = var.instance_key_name
network_interface {
network_id = "net-COMMON_GLOBAL"
}
network_interface {
network_id = nifcloud_private_lan.this.network_id
ip_address = "static"
}
# The image_id changes when the OS image type is demoted from standard to public.
lifecycle {
ignore_changes = [
image_id,
user_data,
]
}
}
#################################################
##
## Control Plane
##
resource "nifcloud_security_group" "cp" {
group_name = "${var.prefix}cp"
description = "${var.prefix} control plane"
availability_zone = var.availability_zone
}
resource "nifcloud_instance" "cp" {
for_each = var.instances_cp
instance_id = "${local.az_short_name}${var.prefix}${each.key}"
security_group = nifcloud_security_group.cp.group_name
instance_type = var.instance_type_cp
user_data = templatefile("${path.module}/templates/userdata.tftpl", {
private_ip_address = each.value.private_ip
ssh_port = local.port_ssh
hostname = "${local.az_short_name}${var.prefix}${each.key}"
})
availability_zone = var.availability_zone
accounting_type = var.accounting_type
image_id = data.nifcloud_image.this.image_id
key_name = var.instance_key_name
network_interface {
network_id = "net-COMMON_GLOBAL"
}
network_interface {
network_id = nifcloud_private_lan.this.network_id
ip_address = "static"
}
# The image_id changes when the OS image type is demoted from standard to public.
lifecycle {
ignore_changes = [
image_id,
user_data,
]
}
}
resource "nifcloud_load_balancer" "this" {
load_balancer_name = "${local.az_short_name}${var.prefix}cp"
accounting_type = var.accounting_type
balancing_type = 1 // Round-Robin
load_balancer_port = local.port_kubectl
instance_port = local.port_kubectl
instances = [for v in nifcloud_instance.cp : v.instance_id]
filter = concat(
[for k, v in nifcloud_instance.cp : v.public_ip],
[for k, v in nifcloud_instance.wk : v.public_ip],
var.additional_lb_filter,
)
filter_type = 1 // Allow
}
#################################################
##
## Worker
##
resource "nifcloud_security_group" "wk" {
group_name = "${var.prefix}wk"
description = "${var.prefix} worker"
availability_zone = var.availability_zone
}
resource "nifcloud_instance" "wk" {
for_each = var.instances_wk
instance_id = "${local.az_short_name}${var.prefix}${each.key}"
security_group = nifcloud_security_group.wk.group_name
instance_type = var.instance_type_wk
user_data = templatefile("${path.module}/templates/userdata.tftpl", {
private_ip_address = each.value.private_ip
ssh_port = local.port_ssh
hostname = "${local.az_short_name}${var.prefix}${each.key}"
})
availability_zone = var.availability_zone
accounting_type = var.accounting_type
image_id = data.nifcloud_image.this.image_id
key_name = var.instance_key_name
network_interface {
network_id = "net-COMMON_GLOBAL"
}
network_interface {
network_id = nifcloud_private_lan.this.network_id
ip_address = "static"
}
# The image_id changes when the OS image type is demoted from standard to public.
lifecycle {
ignore_changes = [
image_id,
user_data,
]
}
}
#################################################
##
## Security Group Rule: Kubernetes
##
# ssh
resource "nifcloud_security_group_rule" "ssh_from_bastion" {
security_group_names = [
nifcloud_security_group.wk.group_name,
nifcloud_security_group.cp.group_name,
]
type = "IN"
from_port = local.port_ssh
to_port = local.port_ssh
protocol = "TCP"
source_security_group_name = nifcloud_security_group.bn.group_name
}
# kubectl
resource "nifcloud_security_group_rule" "kubectl_from_worker" {
security_group_names = [
nifcloud_security_group.cp.group_name,
]
type = "IN"
from_port = local.port_kubectl
to_port = local.port_kubectl
protocol = "TCP"
source_security_group_name = nifcloud_security_group.wk.group_name
}
# kubelet
resource "nifcloud_security_group_rule" "kubelet_from_worker" {
security_group_names = [
nifcloud_security_group.cp.group_name,
]
type = "IN"
from_port = local.port_kubelet
to_port = local.port_kubelet
protocol = "TCP"
source_security_group_name = nifcloud_security_group.wk.group_name
}
resource "nifcloud_security_group_rule" "kubelet_from_control_plane" {
security_group_names = [
nifcloud_security_group.wk.group_name,
]
type = "IN"
from_port = local.port_kubelet
to_port = local.port_kubelet
protocol = "TCP"
source_security_group_name = nifcloud_security_group.cp.group_name
}
#################################################
##
## Security Group Rule: calico
##
# vslan
resource "nifcloud_security_group_rule" "vxlan_from_control_plane" {
security_group_names = [
nifcloud_security_group.wk.group_name,
]
type = "IN"
from_port = local.port_vxlan
to_port = local.port_vxlan
protocol = "UDP"
source_security_group_name = nifcloud_security_group.cp.group_name
}
resource "nifcloud_security_group_rule" "vxlan_from_worker" {
security_group_names = [
nifcloud_security_group.cp.group_name,
]
type = "IN"
from_port = local.port_vxlan
to_port = local.port_vxlan
protocol = "UDP"
source_security_group_name = nifcloud_security_group.wk.group_name
}
# bgp
resource "nifcloud_security_group_rule" "bgp_from_control_plane" {
security_group_names = [
nifcloud_security_group.wk.group_name,
]
type = "IN"
from_port = local.port_bgp
to_port = local.port_bgp
protocol = "TCP"
source_security_group_name = nifcloud_security_group.cp.group_name
}
resource "nifcloud_security_group_rule" "bgp_from_worker" {
security_group_names = [
nifcloud_security_group.cp.group_name,
]
type = "IN"
from_port = local.port_bgp
to_port = local.port_bgp
protocol = "TCP"
source_security_group_name = nifcloud_security_group.wk.group_name
}
# etcd
resource "nifcloud_security_group_rule" "etcd_from_worker" {
security_group_names = [
nifcloud_security_group.cp.group_name,
]
type = "IN"
from_port = local.port_etcd
to_port = local.port_etcd
protocol = "TCP"
source_security_group_name = nifcloud_security_group.wk.group_name
}

View File

@@ -0,0 +1,48 @@
output "control_plane_lb" {
description = "The DNS name of LB for control plane"
value = nifcloud_load_balancer.this.dns_name
}
output "security_group_name" {
description = "The security group used in the cluster"
value = {
bastion = nifcloud_security_group.bn.group_name,
control_plane = nifcloud_security_group.cp.group_name,
worker = nifcloud_security_group.wk.group_name,
}
}
output "private_network_id" {
description = "The private network used in the cluster"
value = nifcloud_private_lan.this.id
}
output "bastion_info" {
description = "The basion information in cluster"
value = { (nifcloud_instance.bn.instance_id) : {
instance_id = nifcloud_instance.bn.instance_id,
unique_id = nifcloud_instance.bn.unique_id,
private_ip = nifcloud_instance.bn.private_ip,
public_ip = nifcloud_instance.bn.public_ip,
} }
}
output "worker_info" {
description = "The worker information in cluster"
value = { for v in nifcloud_instance.wk : v.instance_id => {
instance_id = v.instance_id,
unique_id = v.unique_id,
private_ip = v.private_ip,
public_ip = v.public_ip,
} }
}
output "control_plane_info" {
description = "The control plane information in cluster"
value = { for v in nifcloud_instance.cp : v.instance_id => {
instance_id = v.instance_id,
unique_id = v.unique_id,
private_ip = v.private_ip,
public_ip = v.public_ip,
} }
}

View File

@@ -0,0 +1,45 @@
#!/bin/bash
#################################################
##
## IP Address
##
configure_private_ip_address () {
cat << EOS > /etc/netplan/01-netcfg.yaml
network:
version: 2
renderer: networkd
ethernets:
ens192:
dhcp4: yes
dhcp6: yes
dhcp-identifier: mac
ens224:
dhcp4: no
dhcp6: no
addresses: [${private_ip_address}]
EOS
netplan apply
}
configure_private_ip_address
#################################################
##
## SSH
##
configure_ssh_port () {
sed -i 's/^#*Port [0-9]*/Port ${ssh_port}/' /etc/ssh/sshd_config
}
configure_ssh_port
#################################################
##
## Hostname
##
hostnamectl set-hostname ${hostname}
#################################################
##
## Disable swap files genereated by systemd-gpt-auto-generator
##
systemctl mask "dev-sda3.swap"

View File

@@ -0,0 +1,9 @@
terraform {
required_version = ">=1.3.7"
required_providers {
nifcloud = {
source = "nifcloud/nifcloud"
version = ">= 1.8.0, < 2.0.0"
}
}
}

View File

@@ -0,0 +1,81 @@
variable "availability_zone" {
description = "The availability zone"
type = string
}
variable "prefix" {
description = "The prefix for the entire cluster"
type = string
validation {
condition = length(var.prefix) <= 5
error_message = "Must be a less than 5 character long."
}
}
variable "private_network_cidr" {
description = "The subnet of private network"
type = string
validation {
condition = can(cidrnetmask(var.private_network_cidr))
error_message = "Must be a valid IPv4 CIDR block address."
}
}
variable "private_ip_bn" {
description = "Private IP of bastion server"
type = string
}
variable "instances_cp" {
type = map(object({
private_ip = string
}))
}
variable "instances_wk" {
type = map(object({
private_ip = string
}))
}
variable "instance_key_name" {
description = "The key name of the Key Pair to use for the instance"
type = string
}
variable "instance_type_bn" {
description = "The instance type of bastion server"
type = string
}
variable "instance_type_wk" {
description = "The instance type of worker"
type = string
}
variable "instance_type_cp" {
description = "The instance type of control plane"
type = string
}
variable "image_name" {
description = "The name of image"
type = string
}
variable "additional_lb_filter" {
description = "Additional LB filter"
type = list(string)
}
variable "accounting_type" {
type = string
default = "1"
validation {
condition = anytrue([
var.accounting_type == "1", // Monthly
var.accounting_type == "2", // Pay per use
])
error_message = "Must be a 1 or 2."
}
}

View File

@@ -0,0 +1,3 @@
output "kubernetes_cluster" {
value = module.kubernetes_cluster
}

View File

@@ -0,0 +1,22 @@
region = "jp-west-1"
az = "west-11"
instance_key_name = "deployerkey"
instance_type_bn = "e-medium"
instance_type_cp = "e-medium"
instance_type_wk = "e-medium"
private_network_cidr = "192.168.30.0/24"
instances_cp = {
"cp01" : { private_ip : "192.168.30.11/24" }
"cp02" : { private_ip : "192.168.30.12/24" }
"cp03" : { private_ip : "192.168.30.13/24" }
}
instances_wk = {
"wk01" : { private_ip : "192.168.30.21/24" }
"wk02" : { private_ip : "192.168.30.22/24" }
}
private_ip_bn = "192.168.30.10/24"
image_name = "Ubuntu Server 22.04 LTS"

View File

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

View File

@@ -0,0 +1,9 @@
terraform {
required_version = ">=1.3.7"
required_providers {
nifcloud = {
source = "nifcloud/nifcloud"
version = "1.8.0"
}
}
}

View File

@@ -0,0 +1,77 @@
variable "region" {
description = "The region"
type = string
}
variable "az" {
description = "The availability zone"
type = string
}
variable "private_ip_bn" {
description = "Private IP of bastion server"
type = string
}
variable "private_network_cidr" {
description = "The subnet of private network"
type = string
validation {
condition = can(cidrnetmask(var.private_network_cidr))
error_message = "Must be a valid IPv4 CIDR block address."
}
}
variable "instances_cp" {
type = map(object({
private_ip = string
}))
}
variable "instances_wk" {
type = map(object({
private_ip = string
}))
}
variable "instance_key_name" {
description = "The key name of the Key Pair to use for the instance"
type = string
}
variable "instance_type_bn" {
description = "The instance type of bastion server"
type = string
}
variable "instance_type_wk" {
description = "The instance type of worker"
type = string
}
variable "instance_type_cp" {
description = "The instance type of control plane"
type = string
}
variable "image_name" {
description = "The name of image"
type = string
}
variable "working_instance_ip" {
description = "The IP address to connect to bastion server."
type = string
}
variable "accounting_type" {
type = string
default = "2"
validation {
condition = anytrue([
var.accounting_type == "1", // Monthly
var.accounting_type == "2", // Pay per use
])
error_message = "Must be a 1 or 2."
}
}

View File

@@ -281,9 +281,9 @@ For your cluster, edit `inventory/$CLUSTER/cluster.tfvars`.
|`k8s_allowed_remote_ips_ipv6` | List of IPv6 CIDR allowed to initiate a SSH connection, empty by default |
|`k8s_allowed_egress_ipv6_ips` | List of IPv6 CIDRs allowed for egress traffic, `["::/0"]` by default |
|`worker_allowed_ports` | List of ports to open on worker nodes, `[{ "protocol" = "tcp", "port_range_min" = 30000, "port_range_max" = 32767, "remote_ip_prefix" = "0.0.0.0/0"}]` by default |
|`worker_allowed_ports_ipv6` | List of ports to open on worker nodes for IPv6 CIDR blocks, `[{ "protocol" = "tcp", "port_range_min" = 30000, "port_range_max" = 32767, "remote_ip_prefix" = "::/0"}, { "protocol" = "ipv6-icmp", "port_range_min" = 0, "port_range_max" = 0, "remote_ip_prefix" = "::/0"}]` by default |
|`worker_allowed_ports_ipv6` | List of ports to open on worker nodes for IPv6 CIDR blocks, `[{ "protocol" = "tcp", "port_range_min" = 30000, "port_range_max" = 32767, "remote_ip_prefix" = "::/0"}]` by default |
|`master_allowed_ports` | List of ports to open on master nodes, expected format is `[{ "protocol" = "tcp", "port_range_min" = 443, "port_range_max" = 443, "remote_ip_prefix" = "0.0.0.0/0"}]`, empty by default |
|`master_allowed_ports_ipv6` | List of ports to open on master nodes for IPv6 CIDR blocks, `[{ "protocol" = "ipv6-icmp", "port_range_min" = 0, "port_range_max" = 0, "remote_ip_prefix" = "::/0"}]` by default |
|`master_allowed_ports_ipv6` | List of ports to open on master nodes for IPv6 CIDR blocks, expected format is `[{ "protocol" = "tcp", "port_range_min" = 443, "port_range_max" = 443, "remote_ip_prefix" = "::/0"}]`, empty by default |
|`node_root_volume_size_in_gb` | Size of the root volume for nodes, 0 to use ephemeral storage |
|`master_root_volume_size_in_gb` | Size of the root volume for masters, 0 to use ephemeral storage |
|`master_volume_type` | Volume type of the root volume for control_plane, 'Default' by default |
@@ -624,7 +624,7 @@ Edit `inventory/$CLUSTER/group_vars/k8s_cluster/k8s_cluster.yml`:
- **calico** requires [configuring OpenStack Neutron ports](/docs/cloud_controllers/openstack.md) to allow service and pod subnets
```yml
# Choose network plugin (calico or flannel)
# Choose network plugin (calico, weave or flannel)
# Can also be set to 'cloud', which lets the cloud provider setup appropriate routing
kube_network_plugin: flannel
```

View File

@@ -271,14 +271,7 @@ variable "master_allowed_ports" {
variable "master_allowed_ports_ipv6" {
type = list(any)
default = [
{
"protocol" = "ipv6-icmp"
"port_range_min" = 0
"port_range_max" = 0
"remote_ip_prefix" = "::/0"
},
]
default = []
}
variable "worker_allowed_ports" {
@@ -304,12 +297,6 @@ variable "worker_allowed_ports_ipv6" {
"port_range_max" = 32767
"remote_ip_prefix" = "::/0"
},
{
"protocol" = "ipv6-icmp"
"port_range_min" = 0
"port_range_max" = 0
"remote_ip_prefix" = "::/0"
},
]
}

View File

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

View File

@@ -124,9 +124,9 @@ worker_allowed_ports = []
loadbalancer_enabled = false
loadbalancer_plan = "development"
loadbalancer_proxy_protocol = false
loadbalancers = {
# "http" : {
# "proxy_protocol" : false
# "port" : 80,
# "target_port" : 80,
# "backend_servers" : [

View File

@@ -20,8 +20,6 @@ module "kubernetes" {
username = var.username
private_network_cidr = var.private_network_cidr
dns_servers = var.dns_servers
use_public_ips = var.use_public_ips
machines = var.machines
@@ -32,12 +30,12 @@ module "kubernetes" {
firewall_default_deny_out = var.firewall_default_deny_out
master_allowed_remote_ips = var.master_allowed_remote_ips
k8s_allowed_remote_ips = var.k8s_allowed_remote_ips
bastion_allowed_remote_ips = var.bastion_allowed_remote_ips
master_allowed_ports = var.master_allowed_ports
worker_allowed_ports = var.worker_allowed_ports
loadbalancer_enabled = var.loadbalancer_enabled
loadbalancer_plan = var.loadbalancer_plan
loadbalancer_outbound_proxy_protocol = var.loadbalancer_proxy_protocol ? "v2" : ""
loadbalancer_legacy_network = var.loadbalancer_legacy_network
loadbalancers = var.loadbalancers
@@ -54,12 +52,32 @@ module "kubernetes" {
# Generate ansible inventory
#
resource "local_file" "inventory" {
content = templatefile("${path.module}/templates/inventory.tpl", {
master_ip = module.kubernetes.master_ip
worker_ip = module.kubernetes.worker_ip
bastion_ip = module.kubernetes.bastion_ip
username = var.username
})
filename = var.inventory_file
data "template_file" "inventory" {
template = file("${path.module}/templates/inventory.tpl")
vars = {
connection_strings_master = join("\n", formatlist("%s ansible_user=ubuntu ansible_host=%s ip=%s etcd_member_name=etcd%d",
keys(module.kubernetes.master_ip),
values(module.kubernetes.master_ip).*.public_ip,
values(module.kubernetes.master_ip).*.private_ip,
range(1, length(module.kubernetes.master_ip) + 1)))
connection_strings_worker = join("\n", formatlist("%s ansible_user=ubuntu ansible_host=%s ip=%s",
keys(module.kubernetes.worker_ip),
values(module.kubernetes.worker_ip).*.public_ip,
values(module.kubernetes.worker_ip).*.private_ip))
list_master = join("\n", formatlist("%s",
keys(module.kubernetes.master_ip)))
list_worker = join("\n", formatlist("%s",
keys(module.kubernetes.worker_ip)))
}
}
resource "null_resource" "inventories" {
provisioner "local-exec" {
command = "echo '${data.template_file.inventory.rendered}' > ${var.inventory_file}"
}
triggers = {
template = data.template_file.inventory.rendered
}
}

View File

@@ -53,44 +53,6 @@ locals {
# If prefix is set, all resources will be prefixed with "${var.prefix}-"
# Else don't prefix with anything
resource-prefix = "%{if var.prefix != ""}${var.prefix}-%{endif}"
master_ip = {
for instance in upcloud_server.master :
instance.hostname => {
for nic in instance.network_interface :
nic.type => nic.ip_address
if nic.ip_address != null
}
}
worker_ip = {
for instance in upcloud_server.worker :
instance.hostname => {
for nic in instance.network_interface :
nic.type => nic.ip_address
if nic.ip_address != null
}
}
bastion_ip = {
for instance in upcloud_server.bastion :
instance.hostname => {
for nic in instance.network_interface :
nic.type => nic.ip_address
if nic.ip_address != null
}
}
node_user_data = {
for name, machine in var.machines :
name => <<EOF
%{ if ( length(machine.dns_servers != null ? machine.dns_servers : [] ) > 0 ) || ( length(var.dns_servers) > 0 && machine.dns_servers == null ) ~}
#!/bin/bash
echo -e "[Resolve]\nDNS=${ join(" ", length(machine.dns_servers != null ? machine.dns_servers : []) > 0 ? machine.dns_servers : var.dns_servers) }" > /etc/systemd/resolved.conf
systemctl restart systemd-resolved
%{ endif ~}
EOF
}
}
resource "upcloud_network" "private" {
@@ -100,9 +62,6 @@ resource "upcloud_network" "private" {
ip_network {
address = var.private_network_cidr
dhcp_default_route = var.router_enable
# TODO: When support for dhcp_dns for private networks are in, remove the user_data and enable it here.
# See more here https://github.com/UpCloudLtd/terraform-provider-upcloud/issues/562
# dhcp_dns = length(var.private_network_dns) > 0 ? var.private_network_dns : null
dhcp = true
family = "IPv4"
}
@@ -130,8 +89,8 @@ resource "upcloud_server" "master" {
hostname = "${local.resource-prefix}${each.key}"
plan = each.value.plan
cpu = each.value.cpu
mem = each.value.mem
cpu = each.value.plan == null ? null : each.value.cpu
mem = each.value.plan == null ? null : each.value.mem
zone = var.zone
server_group = each.value.server_group == null ? null : upcloud_server_group.server_groups[each.value.server_group].id
@@ -140,13 +99,10 @@ resource "upcloud_server" "master" {
size = each.value.disk_size
}
dynamic "network_interface" {
for_each = each.value.force_public_ip || var.use_public_ips ? [1] : []
content {
# Public network interface
network_interface {
type = "public"
}
}
# Private network interface
network_interface {
@@ -180,9 +136,6 @@ resource "upcloud_server" "master" {
keys = var.ssh_public_keys
create_password = false
}
metadata = local.node_user_data[each.key] != "" ? true : null
user_data = local.node_user_data[each.key] != "" ? local.node_user_data[each.key] : null
}
resource "upcloud_server" "worker" {
@@ -194,8 +147,8 @@ resource "upcloud_server" "worker" {
hostname = "${local.resource-prefix}${each.key}"
plan = each.value.plan
cpu = each.value.cpu
mem = each.value.mem
cpu = each.value.plan == null ? null : each.value.cpu
mem = each.value.plan == null ? null : each.value.mem
zone = var.zone
server_group = each.value.server_group == null ? null : upcloud_server_group.server_groups[each.value.server_group].id
@@ -205,13 +158,10 @@ resource "upcloud_server" "worker" {
size = each.value.disk_size
}
dynamic "network_interface" {
for_each = each.value.force_public_ip || var.use_public_ips ? [1] : []
content {
# Public network interface
network_interface {
type = "public"
}
}
# Private network interface
network_interface {
@@ -245,63 +195,6 @@ resource "upcloud_server" "worker" {
keys = var.ssh_public_keys
create_password = false
}
metadata = local.node_user_data[each.key] != "" ? true : null
user_data = local.node_user_data[each.key] != "" ? local.node_user_data[each.key] : null
}
resource "upcloud_server" "bastion" {
for_each = {
for name, machine in var.machines :
name => machine
if machine.node_type == "bastion"
}
hostname = "${local.resource-prefix}${each.key}"
plan = each.value.plan
cpu = each.value.cpu
mem = each.value.mem
zone = var.zone
server_group = each.value.server_group == null ? null : upcloud_server_group.server_groups[each.value.server_group].id
template {
storage = var.template_name
size = each.value.disk_size
}
# Private network interface
network_interface {
type = "private"
network = upcloud_network.private.id
}
# Private network interface
network_interface {
type = "public"
}
firewall = var.firewall_enabled
dynamic "storage_devices" {
for_each = {
for disk_key_name, disk in upcloud_storage.additional_disks :
disk_key_name => disk
# Only add the disk if it matches the node name in the start of its name
if length(regexall("^${each.key}_.+", disk_key_name)) > 0
}
content {
storage = storage_devices.value.id
}
}
# Include at least one public SSH key
login {
user = var.username
keys = var.ssh_public_keys
create_password = false
}
}
resource "upcloud_firewall_rules" "master" {
@@ -650,53 +543,6 @@ resource "upcloud_firewall_rules" "k8s" {
}
}
resource "upcloud_firewall_rules" "bastion" {
for_each = upcloud_server.bastion
server_id = each.value.id
dynamic "firewall_rule" {
for_each = var.bastion_allowed_remote_ips
content {
action = "accept"
comment = "Allow bastion SSH access from this network"
destination_port_end = "22"
destination_port_start = "22"
direction = "in"
family = "IPv4"
protocol = "tcp"
source_address_end = firewall_rule.value.end_address
source_address_start = firewall_rule.value.start_address
}
}
dynamic "firewall_rule" {
for_each = length(var.bastion_allowed_remote_ips) > 0 ? [1] : []
content {
action = "drop"
comment = "Drop bastion SSH access from other networks"
destination_port_end = "22"
destination_port_start = "22"
direction = "in"
family = "IPv4"
protocol = "tcp"
source_address_end = "255.255.255.255"
source_address_start = "0.0.0.0"
}
}
firewall_rule {
action = var.firewall_default_deny_in ? "drop" : "accept"
direction = "in"
}
firewall_rule {
action = var.firewall_default_deny_out ? "drop" : "accept"
direction = "out"
}
}
resource "upcloud_loadbalancer" "lb" {
count = var.loadbalancer_enabled ? 1 : 0
configured_status = "started"
@@ -737,7 +583,7 @@ resource "upcloud_loadbalancer_backend" "lb_backend" {
loadbalancer = upcloud_loadbalancer.lb[0].id
name = "lb-backend-${each.key}"
properties {
outbound_proxy_protocol = each.value.proxy_protocol ? "v2" : ""
outbound_proxy_protocol = var.loadbalancer_outbound_proxy_protocol
}
}
@@ -776,7 +622,7 @@ resource "upcloud_loadbalancer_static_backend_member" "lb_backend_member" {
backend = upcloud_loadbalancer_backend.lb_backend[each.value.lb_name].id
name = "${local.resource-prefix}${each.key}"
ip = merge(local.master_ip, local.worker_ip)["${local.resource-prefix}${each.value.server_name}"].private
ip = merge(upcloud_server.master, upcloud_server.worker)[each.value.server_name].network_interface[1].ip_address
port = each.value.port
weight = 100
max_sessions = var.loadbalancer_plan == "production-small" ? 50000 : 1000
@@ -816,7 +662,7 @@ resource "upcloud_router" "router" {
resource "upcloud_gateway" "gateway" {
for_each = var.router_enable ? var.gateways : {}
name = "${local.resource-prefix}${each.key}-gateway"
zone = var.private_cloud ? var.public_zone : var.zone
zone = var.zone
features = each.value.features
plan = each.value.plan

View File

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

View File

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

View File

@@ -3,7 +3,7 @@ terraform {
required_providers {
upcloud = {
source = "UpCloudLtd/upcloud"
version = "~>5.29.1"
version = "~>5.9.0"
}
}
required_version = ">= 0.13"

View File

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

View File

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

View File

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

View File

@@ -3,7 +3,7 @@ terraform {
required_providers {
upcloud = {
source = "UpCloudLtd/upcloud"
version = "~>5.29.1"
version = "~>5.9.0"
}
}
required_version = ">= 0.13"

View File

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

View File

@@ -1,13 +1,5 @@
# Cilium
## Unprivileged agent configuration
By default, Cilium is installed with `securityContext.privileged: false`. You need to set the `kube_owner` variable to `root` in the inventory:
```yml
kube_owner: root
```
## IP Address Management (IPAM)
IP Address Management (IPAM) is responsible for the allocation and management of IP addresses used by network endpoints (container and others) managed by Cilium. The default mode is "Cluster Scope".
@@ -62,10 +54,6 @@ cilium_loadbalancer_ip_pools:
- name: "blue-pool"
cidrs:
- "10.0.10.0/24"
ranges:
- start: "20.0.20.100"
stop: "20.0.20.200"
- start: "1.2.3.4"
```
For further information, check [LB IPAM documentation](https://docs.cilium.io/en/stable/network/lb-ipam/)
@@ -245,7 +233,7 @@ cilium_operator_extra_volume_mounts:
## Choose Cilium version
```yml
cilium_version: "1.18.6"
cilium_version: "1.15.9"
```
## Add variable to config

View File

@@ -32,7 +32,7 @@ add `kube_proxy_masquerade_all: true` in `group_vars/all/all.yml`
* Disable nodelocaldns
The nodelocal dns IP is not reachable.
The nodelocal dns IP is not reacheable.
Disable it in `sample/group_vars/k8s_cluster/k8s_cluster.yml`

79
docs/CNI/weave.md Normal file
View File

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

View File

@@ -65,10 +65,11 @@ In kubespray, the default runtime name is "runc", and it can be configured with
containerd_runc_runtime:
name: runc
type: "io.containerd.runc.v2"
engine: ""
root: ""
options:
Root: ""
SystemdCgroup: "false"
BinaryName: /usr/local/bin/my-runc
systemdCgroup: "false"
binaryName: /usr/local/bin/my-runc
base_runtime_spec: cri-base.json
```
@@ -148,11 +149,3 @@ following configuration:
```yaml
nri_enabled: true
```
### Optional : Static Binary
To ensure compatibility with older distributions (such as Debian 11), you can use a static containerd binary. By default, this is static binary if the system's glibc version is less than 2.34; otherwise, it is the default binary.
```yaml
containerd_static_binary: true
```

View File

@@ -80,7 +80,7 @@ The `crio_remap_enable` configures the `/etc/subuid` and `/etc/subgid` files to
By default, 16M uids and gids are reserved for user namespaces (256 pods * 65536 uids/gids) at the end of the uid/gid space.
The `crio_default_capabilities` configure the default containers capabilities for the crio.
Defaults capabilities are:
Defaults capabilties are:
```yaml
crio_default_capabilities:

5
docs/_sidebar.md generated
View File

@@ -6,6 +6,7 @@
* [Downloads](/docs/advanced/downloads.md)
* [Gcp-lb](/docs/advanced/gcp-lb.md)
* [Kubernetes-reliability](/docs/advanced/kubernetes-reliability.md)
* [Mitogen](/docs/advanced/mitogen.md)
* [Netcheck](/docs/advanced/netcheck.md)
* [Ntp](/docs/advanced/ntp.md)
* [Proxy](/docs/advanced/proxy.md)
@@ -22,6 +23,7 @@
* [Aws](/docs/cloud_providers/aws.md)
* [Azure](/docs/cloud_providers/azure.md)
* [Cloud](/docs/cloud_providers/cloud.md)
* [Equinix-metal](/docs/cloud_providers/equinix-metal.md)
* CNI
* [Calico](/docs/CNI/calico.md)
* [Cilium](/docs/CNI/cilium.md)
@@ -31,6 +33,7 @@
* [Kube-router](/docs/CNI/kube-router.md)
* [Macvlan](/docs/CNI/macvlan.md)
* [Multus](/docs/CNI/multus.md)
* [Weave](/docs/CNI/weave.md)
* CRI
* [Containerd](/docs/CRI/containerd.md)
* [Cri-o](/docs/CRI/cri-o.md)
@@ -49,7 +52,9 @@
* [Test Cases](/docs/developers/test_cases.md)
* [Vagrant](/docs/developers/vagrant.md)
* External Storage Provisioners
* [Cephfs Provisioner](/docs/external_storage_provisioners/cephfs_provisioner.md)
* [Local Volume Provisioner](/docs/external_storage_provisioners/local_volume_provisioner.md)
* [Rbd Provisioner](/docs/external_storage_provisioners/rbd_provisioner.md)
* [Scheduler Plugins](/docs/external_storage_provisioners/scheduler_plugins.md)
* Getting Started
* [Comparisons](/docs/getting_started/comparisons.md)

View File

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

View File

@@ -6,7 +6,7 @@
- [Create New TLS Root CA Certificate and Key](#create-new-tls-root-ca-certificate-and-key)
- [Install Cloudflare PKI/TLS `cfssl` Toolkit.](#install-cloudflare-pkitls-cfssl-toolkit)
- [Create Root Certificate Authority (CA) Configuration File](#create-root-certificate-authority-ca-configuration-file)
- [Create Certificate Signing Request (CSR) Configuration File](#create-certificate-signing-request-csr-configuration-file)
- [Create Certficate Signing Request (CSR) Configuration File](#create-certficate-signing-request-csr-configuration-file)
- [Create TLS Root CA Certificate and Key](#create-tls-root-ca-certificate-and-key)
Cert-Manager is a native Kubernetes certificate management controller. It can help with issuing certificates from a variety of sources, such as Lets Encrypt, HashiCorp Vault, Venafi, a simple signing key pair, or self signed. It will ensure certificates are valid and up to date, and attempt to renew certificates at a configured time before expiry.
@@ -134,7 +134,7 @@ $ cat > ca-config.json <<EOF
EOF
```
#### Create Certificate Signing Request (CSR) Configuration File
#### Create Certficate Signing Request (CSR) Configuration File
The TLS certificate `names` details can be updated to your own specific requirements.

View File

@@ -1,4 +1,4 @@
# GCP Load Balancers for type=LoadBalancer of Kubernetes Services
# GCP Load Balancers for type=LoadBalacer of Kubernetes Services
> **Removed**: Since v1.31 (the Kubespray counterpart is v2.27), Kubernetes no longer supports `cloud_provider`. (except external cloud provider)

30
docs/advanced/mitogen.md Normal file
View File

@@ -0,0 +1,30 @@
# Mitogen
*Warning:* Mitogen support is now deprecated in kubespray due to upstream not releasing an updated version to support ansible 4.x (ansible-base 2.11.x) and above. The CI support has been stripped for mitogen and we are no longer validating any support or regressions for it. The supporting mitogen install playbook and integration documentation will be removed in a later version.
[Mitogen for Ansible](https://mitogen.networkgenomics.com/ansible_detailed.html) allow a 1.25x - 7x speedup and a CPU usage reduction of at least 2x, depending on network conditions, modules executed, and time already spent by targets on useful work. Mitogen cannot improve a module once it is executing, it can only ensure the module executes as quickly as possible.
## Install
```ShellSession
ansible-playbook contrib/mitogen/mitogen.yml
```
The above playbook sets the ansible `strategy` and `strategy_plugins` in `ansible.cfg` but you can also enable them if you use your own `ansible.cfg` by setting the environment varialbles:
```ShellSession
export ANSIBLE_STRATEGY=mitogen_linear
export ANSIBLE_STRATEGY_PLUGINS=plugins/mitogen/ansible_mitogen/plugins/strategy
```
... or `ansible.cfg` setup:
```ini
[defaults]
strategy_plugins = plugins/mitogen/ansible_mitogen/plugins/strategy
strategy=mitogen_linear
```
## Limitation
If you are experiencing problems, please see the [documentation](https://mitogen.networkgenomics.com/ansible_detailed.html#noteworthy-differences).

View File

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

View File

@@ -13,7 +13,7 @@ KUBESPRAYDIR=kubespray
python3 -m venv $VENVDIR
source $VENVDIR/bin/activate
cd $KUBESPRAYDIR
pip install -r requirements.txt
pip install -U -r requirements.txt
```
In case you have a similar message when installing the requirements:
@@ -32,7 +32,7 @@ Based on the table below and the available python version for your ansible host
| Ansible Version | Python Version |
|-----------------|----------------|
| >= 2.17.3 | 3.10-3.12 |
| >= 2.16.4 | 3.10-3.12 |
## Customize Ansible vars
@@ -42,10 +42,13 @@ Kubespray expects users to use one of the following variables sources for settin
|----------------------------------------|------------------------------------------------------------------------------|
| inventory vars | |
| - **inventory group_vars** | most used |
| - inventory host_vars | host specific vars overrides, group_vars is usually more practical |
| - inventory host_vars | host specifc vars overrides, group_vars is usually more practical |
| **extra vars** (always win precedence) | override with ``ansible-playbook -e @foo.yml`` |
> Extra vars are best used to override kubespray internal variables, for instances, roles/vars/. Those vars are usually **not expected** (by Kubespray developers) to be modified by end users, and not part of Kubespray interface. Thus they can change, disappear, or break stuff unexpectedly.
[!IMPORTANT]
Extra vars are best used to override kubespray internal variables, for instances, roles/vars/.
Those vars are usually **not expected** (by Kubespray developers) to be modified by end users, and not part of Kubespray
interface. Thus they can change, disappear, or break stuff unexpectedly.
## Ansible tags
@@ -59,9 +62,10 @@ The following tags are defined in playbooks:
| aws-ebs-csi-driver | Configuring csi driver: aws-ebs |
| azure-csi-driver | Configuring csi driver: azure |
| bastion | Setup ssh config for bastion |
| bootstrap_os | Anything related to host OS configuration |
| bootstrap-os | Anything related to host OS configuration |
| calico | Network plugin Calico |
| calico_rr | Configuring Calico route reflector |
| cephfs-provisioner | Configuring CephFS |
| cert-manager | Configuring certificate manager for K8s |
| cilium | Network plugin Cilium |
| cinder-csi-driver | Configuring csi driver: cinder |
@@ -115,11 +119,12 @@ The following tags are defined in playbooks:
| local-path-provisioner | Configure External provisioner: local-path |
| local-volume-provisioner | Configure External provisioner: local-volume |
| macvlan | Network plugin macvlan |
| master (DEPRECATED) | Deprecated - see `control-plane` |
| metallb | Installing and configuring metallb |
| metrics_server | Configuring metrics_server |
| netchecker | Installing netchecker K8s app |
| network | Configuring networking plugins for K8s |
| mounts | Umount kubelet dirs when resetting |
| mounts | Umount kubelet dirs when reseting |
| multus | Network plugin multus |
| nginx | Configuring LB for kube-apiserver instances |
| node | Configuring K8s minion (compute) node role |
@@ -142,6 +147,7 @@ The following tags are defined in playbooks:
| registry | Configuring local docker registry |
| reset | Tasks running doing the node reset |
| resolvconf | Configuring /etc/resolv.conf for hosts/apps |
| rbd-provisioner | Configure External provisioner: rdb |
| services | Remove services (etcd, kubelet etc...) when resetting |
| snapshot | Enabling csi snapshot |
| snapshot-controller | Configuring csi snapshot controller |
@@ -149,16 +155,21 @@ The following tags are defined in playbooks:
| upgrade | Upgrading, f.e. container images/binaries |
| upload | Distributing images/binaries across hosts |
| vsphere-csi-driver | Configuring csi driver: vsphere |
| weave | Network plugin Weave |
| win_nodes | Running windows specific tasks |
| youki | Configuring youki runtime |
Note: Use the ``bash scripts/gen_tags.sh`` command to generate a list of all
tags found in the codebase. New tags will be listed with the empty "Used for"
field.
## Example commands
Example command to filter and apply only DNS configuration tasks and skip
everything else related to host OS configuration and downloading images of containers:
```ShellSession
ansible-playbook -i inventory/sample/hosts.ini cluster.yml --tags preinstall,facts --skip-tags=download,bootstrap_os
ansible-playbook -i inventory/sample/hosts.ini cluster.yml --tags preinstall,facts --skip-tags=download,bootstrap-os
```
And this play only removes the K8s cluster DNS resolver IP from hosts' /etc/resolv.conf files:
@@ -178,13 +189,17 @@ ansible-playbook -i inventory/sample/hosts.ini cluster.yml \
Note: use `--tags` and `--skip-tags` wisely and only if you're 100% sure what you're doing.
## Mitogen
Mitogen support is deprecated, please see [mitogen related docs](/docs/advanced/mitogen.md) for usage and reasons for deprecation.
## Troubleshooting Ansible issues
Having the wrong version of ansible, ansible collections or python dependencies can cause issue.
In particular, Kubespray ship custom modules which Ansible needs to find, for which you should specify [ANSIBLE_LIBRARY](https://docs.ansible.com/ansible/latest/dev_guide/developing_locally.html#adding-a-module-or-plugin-outside-of-a-collection)
In particular, Kubespray ship custom modules which Ansible needs to find, for which you should specify [ANSIBLE_LIBRAY](https://docs.ansible.com/ansible/latest/dev_guide/developing_locally.html#adding-a-module-or-plugin-outside-of-a-collection)
```ShellSession
export ANSIBLE_LIBRARY=<kubespray_dir>/library`
export ANSIBLE_LIBRAY=<kubespray_dir>/library`
```
A simple way to ensure you get all the correct version of Ansible is to use
@@ -193,11 +208,11 @@ You will then need to use [bind mounts](https://docs.docker.com/storage/bind-mou
to access the inventory and SSH key in the container, like this:
```ShellSession
git checkout v2.30.0
docker pull quay.io/kubespray/kubespray:v2.30.0
git checkout v2.27.0
docker pull quay.io/kubespray/kubespray:v2.27.0
docker run --rm -it --mount type=bind,source="$(pwd)"/inventory/sample,dst=/inventory \
--mount type=bind,source="${HOME}"/.ssh/id_rsa,dst=/root/.ssh/id_rsa \
quay.io/kubespray/kubespray:v2.30.0 bash
quay.io/kubespray/kubespray:v2.27.0 bash
# Inside the container you may now run the kubespray playbooks:
ansible-playbook -i /inventory/inventory.ini --private-key /root/.ssh/id_rsa cluster.yml
```

View File

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

View File

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

View File

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

View File

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

View File

@@ -2,14 +2,19 @@
## Pipeline
See [.gitlab-ci.yml](/.gitlab-ci.yml) and the included files for an overview.
1. build: build a docker image to be used in the pipeline
2. unit-tests: fast jobs for fast feedback (linting, etc...)
3. deploy-part1: small number of jobs to test if the PR works with default settings
4. deploy-extended: slow jobs testing different platforms, OS, settings, CNI, etc...
5. deploy-extended: very slow jobs (upgrades, etc...)
## Runners
Kubespray has 2 types of GitLab runners, both deployed on the Kubespray CI cluster (hosted on Oracle Cloud Infrastructure):
Kubespray has 3 types of GitLab runners:
- pods: use the [gitlab-ci kubernetes executor](https://docs.gitlab.com/runner/executors/kubernetes/)
- vagrant: custom executor running in pods with access to the libvirt socket on the nodes
- packet runners: used for E2E jobs (usually long), running on Equinix Metal (ex-packet), on kubevirt managed VMs
- light runners: used for short lived jobs, running on Equinix Metal (ex-packet), as managed pods
- auto scaling runners (managed via docker-machine on Equinix Metal): used for on-demand resources, see [GitLab docs](https://docs.gitlab.com/runner/configuration/autoscale.html) for more info
## Vagrant
@@ -17,17 +22,18 @@ Vagrant jobs are using the [quay.io/kubespray/vagrant](/test-infra/vagrant-docke
## CI Variables
In CI we have a [set of extra vars](/test/common_vars.yml) we use to ensure greater success of our CI jobs and avoid throttling by various APIs we depend on.
In CI we have a set of overrides we use to ensure greater success of our CI jobs and avoid throttling by various APIs we depend on. See:
## CI clusters
- [Docker mirrors](/tests/common/_docker_hub_registry_mirror.yml)
- [Test settings](/tests/common/_kubespray_test_settings.yml)
DISCLAIMER: The following information is not fully up to date, in particular, the CI cluster is now on Oracle Cloud Infrastcture, not Equinix.
## CI Environment
The cluster is deployed with kubespray itself and maintained by the kubespray maintainers.
The CI packet and light runners are deployed on a kubernetes cluster on Equinix Metal. The cluster is deployed with kubespray itself and maintained by the kubespray maintainers.
The following files are used for that inventory:
### cluster.tfvars (OBSOLETE: this section is no longer accurate)
### cluster.tfvars
```ini
# your Kubernetes cluster name here
@@ -156,10 +162,22 @@ kube_feature_gates:
- "NodeSwap=True"
```
## Additional files
## Aditional files
This section documents additional files used to complete a deployment of the kubespray CI, these files sit on the control-plane node and assume a working kubernetes cluster.
### /root/nscleanup.sh
```bash
#!/bin/bash
kubectl=/usr/local/bin/kubectl
$kubectl get ns | grep -P "(\d.+-\d.+)" | awk 'match($3,/[0-9]+d/) {print $1}' | xargs -r $kubectl delete ns
$kubectl get ns | grep -P "(\d.+-\d.+)" | awk 'match($3,/[3-9]+h/) {print $1}' | xargs -r $kubectl delete ns
$kubectl get ns | grep Terminating | awk '{print $1}' | xargs -i $kubectl delete vmi/instance-1 vmi/instance-0 vmi/instance-2 -n {} --force --grace-period=0 &
```
### /root/path-calico.sh
```bash

View File

@@ -6,52 +6,55 @@ To generate this Matrix run `./tests/scripts/md-table/main.py`
| OS / CNI | calico | cilium | custom_cni | flannel | kube-ovn | kube-router | macvlan |
|---| --- | --- | --- | --- | --- | --- | --- |
almalinux8 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
almalinux9 | :white_check_mark: | :x: | :x: | :x: | :white_check_mark: | :x: | :x: |
amazon | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
debian11 | :white_check_mark: | :x: | :white_check_mark: | :x: | :x: | :x: | :white_check_mark: |
debian12 | :white_check_mark: | :white_check_mark: | :white_check_mark: | :x: | :x: | :x: | :x: |
debian13 | :white_check_mark: | :white_check_mark: | :x: | :x: | :x: | :x: | :x: |
fedora39 | :white_check_mark: | :x: | :x: | :x: | :x: | :white_check_mark: | :x: |
fedora40 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
flatcar4081 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
openeuler24 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
rockylinux10 | :white_check_mark: | :white_check_mark: | :x: | :x: | :x: | :x: | :x: |
opensuse15 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
rockylinux8 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
rockylinux9 | :white_check_mark: | :white_check_mark: | :x: | :x: | :x: | :x: | :x: |
ubuntu20 | :white_check_mark: | :white_check_mark: | :x: | :white_check_mark: | :x: | :white_check_mark: | :x: |
ubuntu22 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
ubuntu24 | :white_check_mark: | :white_check_mark: | :x: | :white_check_mark: | :x: | :white_check_mark: | :x: |
ubuntu24 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
## crio
| OS / CNI | calico | cilium | custom_cni | flannel | kube-ovn | kube-router | macvlan |
|---| --- | --- | --- | --- | --- | --- | --- |
almalinux8 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
almalinux9 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
amazon | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
debian11 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
debian12 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
debian13 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
fedora39 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
fedora40 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
flatcar4081 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
fedora40 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
openeuler24 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
rockylinux10 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
opensuse15 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
rockylinux8 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
rockylinux9 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
ubuntu22 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
ubuntu20 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
ubuntu22 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
ubuntu24 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
## docker
| OS / CNI | calico | cilium | custom_cni | flannel | kube-ovn | kube-router | macvlan |
|---| --- | --- | --- | --- | --- | --- | --- |
almalinux8 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
almalinux9 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
amazon | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
debian11 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
debian12 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
debian13 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
fedora39 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
fedora40 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
flatcar4081 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
openeuler24 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
rockylinux10 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
opensuse15 | :x: | :white_check_mark: | :x: | :x: | :x: | :x: | :x: |
rockylinux8 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
rockylinux9 | :x: | :x: | :x: | :x: | :x: | :x: | :x: |
ubuntu20 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
ubuntu22 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |
ubuntu24 | :white_check_mark: | :x: | :x: | :x: | :x: | :x: | :x: |

View File

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

View File

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

View File

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

View File

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

View File

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

View File

@@ -21,12 +21,6 @@ metallb_enabled: true
metallb_speaker_enabled: true
```
By default, MetalLB resources are deployed into the `metallb-system` namespace. You can override this namespace using a variable.
```yaml
metallb_namespace: woodenlb-system
```
By default only the MetalLB BGP speaker is allowed to run on control plane nodes. If you have a single node cluster or a cluster where control plane are also worker nodes you may need to enable tolerations for the MetalLB controller:
```yaml
@@ -41,7 +35,7 @@ metallb_config:
effect: "NoSchedule"
```
If you'd like to set additional nodeSelector and tolerations values, you can do so in the following fashion:
If you'd like to set additional nodeSelector and tolerations values, you can do so in the following fasion:
```yaml
metallb_config:

View File

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

View File

@@ -37,12 +37,4 @@ If you have containers that are using iptables in the host network namespace (`h
you need to ensure they are using iptables-nft.
An example how k8s do the autodetection can be found [in this PR](https://github.com/kubernetes/kubernetes/pull/82966)
The kernel version is lower than the kubernetes 1.32 system validation, please refer to the [kernel requirements](../operations/kernel-requirements.md).
## Rocky Linux 10
(Experimental in Kubespray CI)
The official Rocky Linux 10 cloud image does not include `kernel-module-extra`. Both Kube Proxy and CNI rely on this package, and since it relates to kernel version compatibility (which may require VM reboots, etc.), we haven't found an ideal solution.
However, some users report that it doesn't affect them (minimal version). Therefore, the Kubespray CI Rocky Linux 10 image is built by Kubespray maintainers using `diskimage-builder`. For detailed methods, please refer to [the comments](https://github.com/kubernetes-sigs/kubespray/pull/12355#issuecomment-3705400093).
The kernel version is lower than the kubenretes 1.32 system validation, please refer to the [kernel requirements](../operations/kernel-requirements.md).

Some files were not shown because too many files have changed in this diff Show More