Merge branch 'master' of github.com:kubernetes-incubator/kubespray

.gitignore

@@ -1,6 +1,7 @@
 .vagrant
 *.retry
 inventory/vagrant_ansible_inventory
+inventory/credentials/
 inventory/group_vars/fake_hosts.yml
 inventory/host_vars/
 temp
@@ -23,7 +24,7 @@ __pycache__/
 
 # Distribution / packaging
 .Python
-artifacts/
+inventory/*/artifacts/
 env/
 build/
 credentials/

.gitlab-ci.yml

@@ -109,7 +109,6 @@ before_script:
       ${SSH_ARGS}
       ${LOG_LEVEL}
       -e @${CI_TEST_VARS}
-      -e ansible_python_interpreter=${PYPATH}
       -e ansible_ssh_user=${SSH_USER}
       -e local_release_dir=${PWD}/downloads
       --limit "all:!fake_hosts"
@@ -129,7 +128,6 @@ before_script:
       ${SSH_ARGS}
       ${LOG_LEVEL}
       -e @${CI_TEST_VARS}
-      -e ansible_python_interpreter=${PYPATH}
       -e ansible_ssh_user=${SSH_USER}
       -e local_release_dir=${PWD}/downloads
       --limit "all:!fake_hosts"
@@ -257,10 +255,14 @@ before_script:
 # stage: deploy-special
   MOVED_TO_GROUP_VARS: "true"
 
-.ubuntu_cilium_sep_variables: &ubuntu_cilium_sep_variables
+.coreos_cilium_variables: &coreos_cilium_variables
 # stage: deploy-special
   MOVED_TO_GROUP_VARS: "true"
 
+.ubuntu_cilium_sep_variables: &ubuntu_cilium_sep_variables
+# stage: deploy-special
+  MOVED_TO_GROUP_VARS: "true"
+  
 .rhel7_weave_variables: &rhel7_weave_variables
 # stage: deploy-part1
   MOVED_TO_GROUP_VARS: "true"
@@ -320,16 +322,6 @@ gce_coreos-calico-aio:
   only: [/^pr-.*$/]
 
 ### PR JOBS PART2
-do_ubuntu-canal-ha:
-  stage: deploy-part2
-  <<: *job
-  <<: *do
-  variables:
-    <<: *do_variables
-  when: on_success
-  except: ['triggers']
-  only: [/^pr-.*$/]
-
 gce_centos7-flannel-addons:
   stage: deploy-part2
   <<: *job
@@ -363,7 +355,6 @@ gce_coreos-calico-sep-triggers:
   when: on_success
   only: ['triggers']
 
-
 gce_ubuntu-canal-ha-triggers:
   stage: deploy-part2
   <<: *job
@@ -396,6 +387,16 @@ gce_ubuntu-weave-sep-triggers:
   only: ['triggers']
 
 # More builds for PRs/merges (manual) and triggers (auto)
+do_ubuntu-canal-ha:
+  stage: deploy-part2
+  <<: *job
+  <<: *do
+  variables:
+    <<: *do_variables
+  when: manual
+  except: ['triggers']
+  only: ['master', /^pr-.*$/]
+
 gce_ubuntu-canal-ha:
   stage: deploy-part2
   <<: *job
@@ -460,6 +461,17 @@ gce_ubuntu-contiv-sep:
   except: ['triggers']
   only: ['master', /^pr-.*$/]
 
+gce_coreos-cilium:
+  stage: deploy-special
+  <<: *job
+  <<: *gce
+  variables:
+    <<: *gce_variables
+    <<: *coreos_cilium_variables
+  when: manual
+  except: ['triggers']
+  only: ['master', /^pr-.*$/]
+
 gce_ubuntu-cilium-sep:
   stage: deploy-special
   <<: *job

README.md

@@ -5,7 +5,7 @@ Deploy a Production Ready Kubernetes Cluster
 
 If you have questions, join us on the [kubernetes slack](https://kubernetes.slack.com), channel **\#kubespray**.
 
--   Can be deployed on **AWS, GCE, Azure, OpenStack or Baremetal**
+-   Can be deployed on **AWS, GCE, Azure, OpenStack, vSphere or Baremetal**
 -   **High available** cluster
 -   **Composable** (Choice of the network plugin for instance)
 -   Support most popular **Linux distributions**
@@ -66,24 +66,25 @@ Supported Linux Distributions
 -----------------------------
 
 -   **Container Linux by CoreOS**
--   **Debian** Jessie
+-   **Debian** Jessie, Stretch, Wheezy
 -   **Ubuntu** 16.04
 -   **CentOS/RHEL** 7
+-   **Fedora/CentOS** Atomic
 
 Note: Upstart/SysV init based OS types are not supported.
 
 Versions of supported components
 --------------------------------
 
--   [kubernetes](https://github.com/kubernetes/kubernetes/releases) v1.9.2
+-   [kubernetes](https://github.com/kubernetes/kubernetes/releases) v1.9.5
 -   [etcd](https://github.com/coreos/etcd/releases) v3.2.4
--   [flanneld](https://github.com/coreos/flannel/releases) v0.8.0
+-   [flanneld](https://github.com/coreos/flannel/releases) v0.10.0
--   [calico](https://docs.projectcalico.org/v2.5/releases/) v2.5.0
+-   [calico](https://docs.projectcalico.org/v2.6/releases/) v2.6.8
 -   [canal](https://github.com/projectcalico/canal) (given calico/flannel versions)
--   [cilium](https://github.com/cilium/cilium) v1.0.0-rc4
+-   [cilium](https://github.com/cilium/cilium) v1.0.0-rc8
--   [contiv](https://github.com/contiv/install/releases) v1.0.3
+-   [contiv](https://github.com/contiv/install/releases) v1.1.7
--   [weave](http://weave.works/) v2.0.1
+-   [weave](http://weave.works/) v2.2.1
--   [docker](https://www.docker.com/) v1.13 (see note)
+-   [docker](https://www.docker.com/) v17.03 (see note)
 -   [rkt](https://coreos.com/rkt/docs/latest/) v1.21.0 (see Note 2)
 
 Note: kubernetes doesn't support newer docker versions. Among other things kubelet currently breaks on docker's non-standard version numbering (it no longer uses semantic versioning). To ensure auto-updates don't break your cluster look into e.g. yum versionlock plugin or apt pin).
@@ -150,5 +151,5 @@ CI Tests
 
 [![Build graphs](https://gitlab.com/kubespray-ci/kubernetes-incubator__kubespray/badges/master/build.svg)](https://gitlab.com/kubespray-ci/kubernetes-incubator__kubespray/pipelines)
 
-CI/end-to-end tests sponsored by Google (GCE), DigitalOcean, [teuto.net](https://teuto.net/) (openstack).
+CI/end-to-end tests sponsored by Google (GCE)
 See the [test matrix](docs/test_cases.md) for details.

Vagrantfile

@@ -3,7 +3,7 @@
 
 require 'fileutils'
 
-Vagrant.require_version ">= 1.9.0"
+Vagrant.require_version ">= 2.0.0"
 
 CONFIG = File.join(File.dirname(__FILE__), "vagrant/config.rb")
 
@@ -135,12 +135,6 @@ Vagrant.configure("2") do |config|
 
       config.vm.network :private_network, ip: ip
 
-      # workaround for Vagrant 1.9.1 and centos vm
-      # https://github.com/hashicorp/vagrant/issues/8096
-      if Vagrant::VERSION == "1.9.1" && $os == "centos"
-        config.vm.provision "shell", inline: "service network restart", run: "always"
-      end
-
       # Disable swap for each vm
       config.vm.provision "shell", inline: "swapoff -a"
 
@@ -164,7 +158,7 @@ Vagrant.configure("2") do |config|
           if File.exist?(File.join(File.dirname($inventory), "hosts"))
             ansible.inventory_path = $inventory
           end
-          ansible.sudo = true
+          ansible.become = true
           ansible.limit = "all"
           ansible.host_key_checking = false
           ansible.raw_arguments = ["--forks=#{$num_instances}", "--flush-cache"]

ansible.cfg

@@ -12,3 +12,5 @@ library = ./library
 callback_whitelist = profile_tasks
 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
+jinja2_extensions = jinja2.ext.do

cluster.yml

@@ -21,6 +21,12 @@
   vars:
     ansible_ssh_pipelining: true
   gather_facts: true
+  pre_tasks:
+    - name: gather facts from all instances
+      setup:
+      delegate_to: "{{item}}"
+      delegate_facts: True
+      with_items: "{{ groups['k8s-cluster'] + groups['etcd'] + groups['calico-rr']|default([]) }}"
 
 - hosts: k8s-cluster:etcd:calico-rr
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"
@@ -94,6 +100,8 @@
     - { role: kubespray-defaults}
     - { role: kubernetes-apps/network_plugin, tags: network }
     - { role: kubernetes-apps/policy_controller, tags: policy-controller }
+    - { role: kubernetes-apps/ingress_controller, tags: ingress-controller }
+    - { role: kubernetes-apps/external_provisioner, tags: external-provisioner }
 
 - hosts: calico-rr
   any_errors_fatal: "{{ any_errors_fatal | default(true) }}"

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

@@ -1,6 +1,6 @@
 
 {% for vm in  vm_ip_list %}
-{% if not use_bastion or vm.virtualMachinename == 'bastion' %}
+{% if not use_bastion or vm.virtualMachine.name == 'bastion' %}
 {{ vm.virtualMachine.name }} ansible_ssh_host={{ vm.virtualMachine.network.publicIpAddresses[0].ipAddress }} ip={{ vm.virtualMachine.network.privateIpAddresses[0] }}
 {% else %}
 {{ vm.virtualMachine.name }} ansible_ssh_host={{  vm.virtualMachine.network.privateIpAddresses[0] }}

contrib/packaging/rpm/kubespray.spec

@@ -20,9 +20,10 @@ BuildRequires:  python2-setuptools
 BuildRequires:  python-d2to1
 BuildRequires:  python2-pbr
 
-Requires: ansible
+Requires: ansible >= 2.4.0
 Requires: python-jinja2 >= 2.10
 Requires: python-netaddr
+Requires: python-pbr
 
 %description
 

contrib/terraform/aws/templates/inventory.tpl

@@ -24,4 +24,4 @@ kube-master
 
 
 [k8s-cluster:vars]
-${elb_api_fqdn}
+${elb_api_fqdn}

contrib/terraform/openstack/README.md

@@ -17,32 +17,33 @@ to actually install kubernetes and stand up the cluster.
 
 ### Networking
 The configuration includes creating a private subnet with a router to the
-external net. It will allocate floating-ips from a pool and assign them to the
+external net. It will allocate floating IPs from a pool and assign them to the
 hosts where that makes sense. You have the option of creating bastion hosts
-inside the private subnet to access the nodes there.
+inside the private subnet to access the nodes there.  Alternatively, a node with
+a floating IP can be used as a jump host to nodes without.
 
 ### Kubernetes Nodes
 You can create many different kubernetes topologies by setting the number of
 different classes of hosts. For each class there are options for allocating
-floating ip addresses or not.
+floating IP addresses or not.
-- Master Nodes with etcd
+- Master nodes with etcd
 - Master nodes without etcd
 - Standalone etcd hosts
 - Kubernetes worker nodes
 
-Note that the ansible script will report an invalid configuration if you wind up
+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.
 
-### Gluster FS
+### GlusterFS
-The terraform configuration supports provisioning of an optional GlusterFS
+The Terraform configuration supports provisioning of an optional GlusterFS
 shared file system based on a separate set of VMs. To enable this, you need to
-specify
+specify:
-- the number of gluster hosts
+- the number of Gluster hosts (minimum 2)
 - Size of the non-ephemeral volumes to be attached to store the GlusterFS bricks
 - Other properties related to provisioning the hosts
 
 Even if you are using Container Linux by CoreOS for your cluster, you will still
-need the GlusterFS VMs to be based on either Debian or RedHat based images,
+need the GlusterFS VMs to be based on either Debian or RedHat based images.
 Container Linux by CoreOS cannot serve GlusterFS, but can connect to it through
 binaries available on hyperkube v1.4.3_coreos.0 or higher.
 
@@ -50,9 +51,9 @@ binaries available on hyperkube v1.4.3_coreos.0 or higher.
 
 - [Install Terraform](https://www.terraform.io/intro/getting-started/install.html)
 - [Install Ansible](http://docs.ansible.com/ansible/latest/intro_installation.html)
-- you already have a suitable OS image in glance
+- you already have a suitable OS image in Glance
-- you already have a floating-ip pool created
+- you already have a floating IP pool created
-- you have security-groups enabled
+- you have security groups enabled
 - you have a pair of keys generated that can be used to secure the new hosts
 
 ## Module Architecture
@@ -67,7 +68,7 @@ any external references to the floating IP (e.g. DNS) that would otherwise have
 to be updated.
 
 You can force your existing IPs by modifying the compute variables in
-`kubespray.tf` as
+`kubespray.tf` as follows:
 
 ```
 k8s_master_fips = ["151.101.129.67"]
@@ -75,30 +76,42 @@ k8s_node_fips = ["151.101.129.68"]
 ```
 
 ## Terraform
-Terraform will be used to provision all of the OpenStack resources. It is also
+Terraform will be used to provision all of the OpenStack resources with base software as appropriate.
-used to deploy and provision the software requirements.
 
-### Prep
+### Configuration
 
-#### OpenStack
+#### Inventory files
 
-No provider variables are hard coded inside `variables.tf` because Terraform
+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):
-supports various authentication method for OpenStack, between identity v2 and
+
-v3 API, `openrc` or `clouds.yaml`.
+```ShellSession
+$ cp -LRp contrib/terraform/openstack/sample-inventory inventory/$CLUSTER
+$ cd inventory/$CLUSTER
+$ ln -s ../../contrib/terraform/openstack/hosts
+```
+
+This will be the base for subsequent Terraform commands.
+
+#### OpenStack access and credentials
+
+No provider variables are hardcoded inside `variables.tf` because Terraform
+supports various authentication methods for OpenStack: the older script and 
+environment method (using `openrc`) as well as a newer declarative method, and 
+different OpenStack environments may support Identity API version 2 or 3.
 
 These are examples and may vary depending on your OpenStack cloud provider,
 for an exhaustive list on how to authenticate on OpenStack with Terraform
 please read the [OpenStack provider documentation](https://www.terraform.io/docs/providers/openstack/).
 
-##### Recommended method : clouds.yaml
+##### Declarative method (recommended)
 
-Newer recommended authentication method is to use a `clouds.yaml` file that can be store in :
+The recommended authentication method is to describe credentials in a YAML file `clouds.yaml` that can be stored in:
 
-* `Current Directory`
+* the current directory
 * `~/.config/openstack`
 * `/etc/openstack`
 
-`clouds.yaml` :
+`clouds.yaml`:
 
 ```
 clouds:
@@ -116,18 +129,19 @@ clouds:
 ```
 
 If you have multiple clouds defined in your `clouds.yaml` file you can choose
-the one you want to use with the environment variable `OS_CLOUD` :
+the one you want to use with the environment variable `OS_CLOUD`:
 
 ```
 export OS_CLOUD=mycloud
 ```
 
-##### Deprecated method : openrc
+##### Openrc method (deprecated)
 
 When using classic environment variables, Terraform uses default `OS_*`
-environment variables :
+environment variables.  A script suitable for your environment may be available
+from Horizon under *Project* -> *Compute* -> *Access & Security* -> *API Access*.
 
-With identity v2 :
+With identity v2:
 
 ```
 source openrc
@@ -144,7 +158,7 @@ OS_INTERFACE=public
 OS_IDENTITY_API_VERSION=2
 ```
 
-With identity v3 :
+With identity v3:
 
 ```
 source openrc
@@ -164,7 +178,7 @@ OS_USER_DOMAIN_NAME=Default
 ```
 
 Terraform does not support a mix of DomainName and DomainID, choose one or the
-other :
+other:
 
 ```
 * provider.openstack: You must provide exactly one of DomainID or DomainName to authenticate by Username
@@ -180,14 +194,11 @@ unset OS_PROJECT_DOMAIN_ID
 set OS_PROJECT_DOMAIN_NAME=Default
 ```
 
-### Terraform Variables
+#### Cluster variables
 The construction of the cluster is driven by values found in
 [variables.tf](variables.tf).
 
-The best way to set these values is to create a file in the project's root
+For your cluster, edit `inventory/$CLUSTER/cluster.tf`.
-directory called something like`my-terraform-vars.tfvars`. Many of the
-variables are obvious. Here is a summary of some of the more interesting
-ones:
 
 |Variable | Description |
 |---------|-------------|
@@ -208,9 +219,9 @@ ones:
 |`number_of_gfs_nodes_no_floating_ip` | Number of gluster servers to provision. |
 | `gfs_volume_size_in_gb` | Size of the non-ephemeral volumes to be attached to store the GlusterFS bricks |
 
-### Terraform files
+#### Terraform state files
 
-In the root folder, the following files might be created (either by Terraform
+In the cluster's inventory folder, the following files might be created (either by Terraform
 or manually), to prevent you from pushing them accidentally they are in a
 `.gitignore` file in the `terraform/openstack` directory :
 
@@ -221,49 +232,61 @@ or manually), to prevent you from pushing them accidentally they are in a
 
 You can still add them manually if you want to.
 
-## Initializing Terraform
+### Initialization
 
-Before Terraform can operate on your cluster you need to install required
+Before Terraform can operate on your cluster you need to install the required
-plugins. This is accomplished with the command
+plugins. This is accomplished as follows:
 
-```bash
+```ShellSession
-$ terraform init contrib/terraform/openstack
+$ cd inventory/$CLUSTER
+$ terraform init ../../contrib/terraform/openstack
 ```
 
-## Provisioning Cluster with Terraform
+This should finish fairly quickly telling you Terraform has successfully initialized and loaded necessary modules.
-You can apply the terraform config to your cluster with the following command
+
-issued from the project's root directory
+### Provisioning cluster
-```bash
+You can apply the Terraform configuration to your cluster with the following command
-$ terraform apply -state=contrib/terraform/openstack/terraform.tfstate -var-file=my-terraform-vars.tfvars contrib/terraform/openstack
+issued from your cluster's inventory directory (`inventory/$CLUSTER`):
+```ShellSession
+$ terraform apply -var-file=cluster.tf ../../contrib/terraform/openstack
 ```
 
 if you chose to create a bastion host, this script will create
-`contrib/terraform/openstack/k8s-cluster.yml` with an ssh command for ansible to
+`contrib/terraform/openstack/k8s-cluster.yml` with an ssh command for Ansible to
-be able to access your machines tunneling  through the bastion's ip adress. If
+be able to access your machines tunneling  through the bastion's IP address. If
 you want to manually handle the ssh tunneling to these machines, please delete
 or move that file. If you want to use this, just leave it there, as ansible will
 pick it up automatically.
 
+### Destroying cluster
+You can destroy your new cluster with the following command issued from the cluster's inventory directory:
 
-## Destroying Cluster with Terraform
+```ShellSession
-You can destroy a config deployed to your cluster with the following command
+$ terraform destroy -var-file=cluster.tf ../../contrib/terraform/openstack
-issued from the project's root directory
-```bash
-$ terraform destroy -state=contrib/terraform/openstack/terraform.tfstate -var-file=my-terraform-vars.tfvars contrib/terraform/openstack
 ```
 
-## Debugging Cluster Provisioning
+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
-`OS_DEBUG` to 1 and`TF_LOG` to`DEBUG` before runing the terraform command
+`OS_DEBUG` to 1 and`TF_LOG` to`DEBUG` before running the Terraform command.
 
-## Terraform output
+### Terraform output
 
-Terraform can output useful values that need to be reused if you want to use Kubernetes OpenStack cloud provider with Neutron/Octavia LBaaS or Cinder persistent Volume provisioning:
+Terraform can output values that are useful for configure Neutron/Octavia LBaaS or Cinder persistent volume provisioning as part of your Kubernetes deployment:
 
- - `private_subnet_id`: the subnet where your instances are running, maps to `openstack_lbaas_subnet_id`
+ - `private_subnet_id`: the subnet where your instances are running is used for `openstack_lbaas_subnet_id`
- - `floating_network_id`: the network_id where the floating IP are provisioned, maps to `openstack_lbaas_floating_network_id`
+ - `floating_network_id`: the network_id where the floating IP are provisioned is used for `openstack_lbaas_floating_network_id`
+
+## Ansible
+
+### Node access
+
+#### SSH
 
-# Running the Ansible Script
 Ensure your local ssh-agent is running and your ssh key has been added. This
 step is required by the terraform provisioner:
 
@@ -272,11 +295,22 @@ $ 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`).
 
-Make sure you can connect to the hosts:
+#### Bastion host
+
+If you are not using a bastion host, but not all of your nodes have floating IPs, create a file `inventory/$CLUSTER/group_vars/no-floating.yml` with the following content.  Use one of your nodes with a floating IP (this should have been output at the end of the Terraform step) and the appropriate user for that OS, or if you have another jump host, use that.
 
 ```
-$ ansible -i contrib/terraform/openstack/hosts -m ping all
+ansible_ssh_common_args: '-o ProxyCommand="ssh -o StrictHostKeyChecking=no -W %h:%p -q USER@MASTER_IP"'
+```
+
+#### Test access
+
+Make sure you can connect to the hosts.  Note that Container Linux by CoreOS 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`.
+
+```
+$ ansible -i inventory/$CLUSTER/hosts -m ping all
 example-k8s_node-1 | SUCCESS => {
     "changed": false,
     "ping": "pong"
@@ -291,21 +325,17 @@ example-k8s-master-1 | SUCCESS => {
 }
 ```
 
-if you are deploying a system that needs bootstrapping, like Container Linux by
+If it fails try to connect manually via SSH.  It could be something as simple as a stale host key.
-CoreOS, these might have a state`FAILED` due to Container Linux by CoreOS not
-having python. As long as the state is not`UNREACHABLE`, this is fine.
 
-if it fails try to connect manually via SSH ... it could be something as simple as a stale host key.
+### Configure cluster variables
 
-## Configure Cluster variables
+Edit `inventory/$CLUSTER/group_vars/all.yml`:
-
+- Set variable **bootstrap_os** appropriately for your desired image:
-Edit `inventory/sample/group_vars/all.yml`:
-- Set variable **bootstrap_os** according selected image
 ```
 # Valid bootstrap options (required): ubuntu, coreos, centos, none
 bootstrap_os: coreos
 ```
-- **bin_dir**
+- **bin_dir**:
 ```
 # Directory where the binaries will be installed
 # Default:
@@ -313,20 +343,19 @@ bootstrap_os: coreos
 # For Container Linux by CoreOS:
 bin_dir: /opt/bin
 ```
-- and **cloud_provider**
+- and **cloud_provider**:
 ```
 cloud_provider: openstack
 ```
-Edit `inventory/sample/group_vars/k8s-cluster.yml`:
+Edit `inventory/$CLUSTER/group_vars/k8s-cluster.yml`:
-- Set variable **kube_network_plugin** according selected networking
+- Set variable **kube_network_plugin** to your desired networking plugin.
+  - **flannel** works out-of-the-box
+  - **calico** requires [configuring OpenStack Neutron ports](/docs/openstack.md) to allow service and pod subnets
 ```
 # 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
 ```
-> flannel works out-of-the-box
-
-> calico requires allowing service's and pod's subnets on according OpenStack Neutron ports
 - Set variable **resolvconf_mode**
 ```
 # Can be docker_dns, host_resolvconf or none
@@ -336,18 +365,19 @@ kube_network_plugin: flannel
 resolvconf_mode: host_resolvconf
 ```
 
-For calico configure OpenStack Neutron ports: [OpenStack](/docs/openstack.md)
+### Deploy Kubernetes
-
-## Deploy kubernetes:
 
 ```
-$ ansible-playbook --become -i contrib/terraform/openstack/hosts cluster.yml
+$ ansible-playbook --become -i inventory/$CLUSTER/hosts cluster.yml
 ```
 
-## Set up local kubectl
+This will take some time as there are many tasks to run.
-1. Install kubectl on your workstation:
+
-[Install and Set Up kubectl](https://kubernetes.io/docs/tasks/tools/install-kubectl/)
+## Kubernetes
-2. Add route to internal IP of master node (if needed):
+
+### Set up kubectl
+1. [Install kubectl](https://kubernetes.io/docs/tasks/tools/install-kubectl/) on your workstation
+2. Add a route to the internal IP of a master node (if needed):
 ```
 sudo route add [master-internal-ip] gw [router-ip]
 ```
@@ -355,28 +385,28 @@ or
 ```
 sudo route add -net [internal-subnet]/24 gw [router-ip]
 ```
-3. List Kubernetes certs&keys:
+3. List Kubernetes certificates & keys:
 ```
 ssh [os-user]@[master-ip] sudo ls /etc/kubernetes/ssl/
 ```
-4. Get admin's certs&key:
+4. Get `admin`'s certificates and keys:
 ```
 ssh [os-user]@[master-ip] sudo cat /etc/kubernetes/ssl/admin-[cluster_name]-k8s-master-1-key.pem > admin-key.pem
 ssh [os-user]@[master-ip] sudo cat /etc/kubernetes/ssl/admin-[cluster_name]-k8s-master-1.pem > admin.pem
 ssh [os-user]@[master-ip] sudo cat /etc/kubernetes/ssl/ca.pem > ca.pem
 ```
 5. Configure kubectl:
-```
+```ShellSession
-kubectl config set-cluster default-cluster --server=https://[master-internal-ip]:6443 \
+$ kubectl config set-cluster default-cluster --server=https://[master-internal-ip]:6443 \
     --certificate-authority=ca.pem
 
-kubectl config set-credentials default-admin \
+$ kubectl config set-credentials default-admin \
     --certificate-authority=ca.pem \
     --client-key=admin-key.pem \
     --client-certificate=admin.pem
 
-kubectl config set-context default-system --cluster=default-cluster --user=default-admin
+$ kubectl config set-context default-system --cluster=default-cluster --user=default-admin
-kubectl config use-context default-system
+$ kubectl config use-context default-system
 ```
 7. Check it:
 ```
@@ -393,14 +423,15 @@ You can tell kubectl to ignore this condition by adding the
 
 ## GlusterFS
 GlusterFS is not deployed by the standard`cluster.yml` playbook, see the
-[glusterfs playbook documentation](../../network-storage/glusterfs/README.md)
+[GlusterFS playbook documentation](../../network-storage/glusterfs/README.md)
 for instructions.
 
-Basically you will install gluster as
+Basically you will install Gluster as
-```bash
+```ShellSession
-$ ansible-playbook --become -i contrib/terraform/openstack/hosts ./contrib/network-storage/glusterfs/glusterfs.yml
+$ ansible-playbook --become -i inventory/$CLUSTER/hosts ./contrib/network-storage/glusterfs/glusterfs.yml
 ```
 
 
-# What's next
+## What's next
-[Start Hello Kubernetes Service](https://kubernetes.io/docs/tasks/access-application-cluster/service-access-application-cluster/)
+
+Try out your new Kubernetes cluster with the [Hello Kubernetes service](https://kubernetes.io/docs/tasks/access-application-cluster/service-access-application-cluster/).

contrib/terraform/openstack/ansible_bastion_template.txt

@@ -1 +1 @@
-ansible_ssh_common_args: '-o ProxyCommand="ssh -o StrictHostKeyChecking=no -W %h:%p -q USER@BASTION_ADDRESS"' 
+ansible_ssh_common_args: "-o ProxyCommand='ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null -W %h:%p -q USER@BASTION_ADDRESS {% if ansible_ssh_private_key_file is defined %}-i {{ ansible_ssh_private_key_file }}{% endif %}'"

contrib/terraform/openstack/group_vars

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

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

@@ -1,7 +1,7 @@
 resource "openstack_networking_router_v2" "k8s" {
-  name             = "${var.cluster_name}-router"
+  name                = "${var.cluster_name}-router"
-  admin_state_up   = "true"
+  admin_state_up      = "true"
-  external_gateway = "${var.external_net}"
+  external_network_id = "${var.external_net}"
 }
 
 resource "openstack_networking_network_v2" "k8s" {

contrib/terraform/openstack/modules/network/outputs.tf

@@ -2,6 +2,6 @@ output "router_id" {
   value = "${openstack_networking_router_interface_v2.k8s.id}"
 }
 
-output "network_id" {
+output "subnet_id" {
   value = "${openstack_networking_subnet_v2.k8s.id}"
 }

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

@@ -0,0 +1,45 @@
+# your Kubernetes cluster name here
+cluster_name = "i-didnt-read-the-docs"
+
+# SSH key to use for access to nodes
+public_key_path = "~/.ssh/id_rsa.pub"
+
+# image to use for bastion, masters, standalone etcd instances, and nodes
+image = "<image name>"
+# user on the node (ex. core on Container Linux, ubuntu on Ubuntu, etc.)
+ssh_user = "<cloud-provisioned user>"
+
+# 0|1 bastion nodes
+number_of_bastions = 0
+#flavor_bastion = "<UUID>"
+
+# standalone etcds
+number_of_etcd = 0
+
+# masters
+number_of_k8s_masters = 1
+number_of_k8s_masters_no_etcd = 0
+number_of_k8s_masters_no_floating_ip = 0
+number_of_k8s_masters_no_floating_ip_no_etcd = 0
+flavor_k8s_master = "<UUID>"
+
+# nodes
+number_of_k8s_nodes = 2
+number_of_k8s_nodes_no_floating_ip = 4
+#flavor_k8s_node = "<UUID>"
+
+# GlusterFS
+# either 0 or more than one
+#number_of_gfs_nodes_no_floating_ip = 0
+#gfs_volume_size_in_gb = 150
+# Container Linux does not support GlusterFS
+#image_gfs = "<image name>"
+# May be different from other nodes
+#ssh_user_gfs = "ubuntu"
+#flavor_gfs_node = "<UUID>"
+
+# networking
+network_name = "<network>"
+external_net = "<UUID>"
+floatingip_pool = "<pool>"
+

contrib/terraform/openstack/sample-inventory/group_vars

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

docs/atomic.md

@@ -7,7 +7,7 @@ Note: Flannel is the only plugin that has currently been tested with atomic
 
 ### Vagrant
 
-* For bootstrapping with Vagrant, use box centos/atomic-host 
+* For bootstrapping with Vagrant, use box centos/atomic-host or fedora/atomic-host 
 * Update VagrantFile variable `local_release_dir` to `/var/vagrant/temp`.
 * Update `vm_memory = 2048` and `vm_cpus = 2`
 * Networking on vagrant hosts has to be brought up manually once they are booted.
@@ -17,6 +17,7 @@ Note: Flannel is the only plugin that has currently been tested with atomic
     sudo /sbin/ifup enp0s8
     ```
 
-* For users of vagrant-libvirt download qcow2 format from https://wiki.centos.org/SpecialInterestGroup/Atomic/Download/
+* For users of vagrant-libvirt download centos/atomic-host qcow2 format from https://wiki.centos.org/SpecialInterestGroup/Atomic/Download/
+* For users of vagrant-libvirt download fedora/atomic-host qcow2 format from https://getfedora.org/en/atomic/download/
 
-Then you can proceed to [cluster deployment](#run-deployment)
+Then you can proceed to [cluster deployment](#run-deployment)

docs/dns-stack.md

@@ -62,6 +62,14 @@ other queries are forwardet to the nameservers found in ``upstream_dns_servers``
 This does not install the dnsmasq DaemonSet and instructs kubelet to directly use kubedns/skydns for
 all queries.
 
+#### coredns
+This does not install the dnsmasq DaemonSet and instructs kubelet to directly use CoreDNS for
+all queries.
+
+#### coredns_dual
+This does not install the dnsmasq DaemonSet and instructs kubelet to directly use CoreDNS for
+all queries. It will also deploy a secondary CoreDNS stack
+
 #### manual
 This does not install dnsmasq or kubedns, but allows you to specify
 `manual_dns_server`, which will be configured on nodes for handling Pod DNS.

docs/getting-started.md

@@ -18,11 +18,9 @@ certain threshold. Run `python3 contrib/inventory_builder/inventory.py help` hel
 
 Example inventory generator usage:
 
-```
+    cp -r inventory/sample inventory/mycluster
-cp -r inventory/sample inventory/mycluster
+    declare -a IPS=(10.10.1.3 10.10.1.4 10.10.1.5)
-declare -a IPS=(10.10.1.3 10.10.1.4 10.10.1.5)
+    CONFIG_FILE=inventory/mycluster/hosts.ini python3 contrib/inventory_builder/inventory.py ${IPS[@]}
-CONFIG_FILE=inventory/mycluster/hosts.ini python3 contrib/inventory_builder/inventory.py ${IPS[@]}
-```
 
 Starting custom deployment
 --------------------------
@@ -30,12 +28,10 @@ Starting custom deployment
 Once you have an inventory, you may want to customize deployment data vars
 and start the deployment:
 
-**IMPORTANT: Edit my_inventory/groups_vars/*.yaml to override data vars**
+**IMPORTANT**: Edit my\_inventory/groups\_vars/\*.yaml to override data vars:
 
-```
+    ansible-playbook -i inventory/mycluster/hosts.ini cluster.yml -b -v \
-ansible-playbook -i inventory/mycluster/hosts.ini cluster.yml -b -v \
+      --private-key=~/.ssh/private_key
-  --private-key=~/.ssh/private_key
-```
 
 See more details in the [ansible guide](ansible.md).
 
@@ -44,31 +40,43 @@ Adding nodes
 
 You may want to add **worker** nodes to your existing cluster. This can be done by re-running the `cluster.yml` playbook, or you can target the bare minimum needed to get kubelet installed on the worker and talking to your masters. This is especially helpful when doing something like autoscaling your clusters.
 
-- Add the new worker node to your inventory under kube-node (or utilize a [dynamic inventory](https://docs.ansible.com/ansible/intro_dynamic_inventory.html)).
+-   Add the new worker node to your inventory under kube-node (or utilize a [dynamic inventory](https://docs.ansible.com/ansible/intro_dynamic_inventory.html)).
-- Run the ansible-playbook command, substituting `scale.yml` for `cluster.yml`:
+-   Run the ansible-playbook command, substituting `scale.yml` for `cluster.yml`:
+
+        ansible-playbook -i inventory/mycluster/hosts.ini scale.yml -b -v \
+          --private-key=~/.ssh/private_key
+
+Remove nodes
+------------
+
+You may want to remove **worker** nodes to your existing cluster. This can be done by re-running the `remove-node.yml` playbook. First, all nodes will be drained, then stop some kubernetes services and delete some certificates, and finally execute the kubectl command to delete these nodes. This can be combined with the add node function, This is generally helpful when doing something like autoscaling your clusters. Of course if a node is not working, you can remove the node and install it again.
+
+- Add worker nodes to the list under kube-node if you want to delete them (or utilize a [dynamic inventory](https://docs.ansible.com/ansible/intro_dynamic_inventory.html)).
+- Run the ansible-playbook command, substituting `remove-node.yml`:
 ```
-ansible-playbook -i inventory/mycluster/hosts.ini scale.yml -b -v \
+ansible-playbook -i inventory/mycluster/hosts.ini remove-node.yml -b -v \
   --private-key=~/.ssh/private_key
 ```
 
 Connecting to Kubernetes
 ------------------------
+
 By default, Kubespray configures kube-master hosts with insecure access to
 kube-apiserver via port 8080. A kubeconfig file is not necessary in this case,
-because kubectl will use http://localhost:8080 to connect. The kubeconfig files
+because kubectl will use <http://localhost:8080> to connect. The kubeconfig files
 generated will point to localhost (on kube-masters) and kube-node hosts will
 connect either to a localhost nginx proxy or to a loadbalancer if configured.
 More details on this process are in the [HA guide](ha-mode.md).
 
-Kubespray permits connecting to the cluster remotely on any IP of any 
+Kubespray permits connecting to the cluster remotely on any IP of any
-kube-master host on port 6443 by default. However, this requires 
+kube-master host on port 6443 by default. However, this requires
-authentication. One could generate a kubeconfig based on one installed 
+authentication. One could generate a kubeconfig based on one installed
 kube-master hosts (needs improvement) or connect with a username and password.
 By default, a user with admin rights is created, named `kube`.
-The password can be viewed after deployment by looking at the file 
+The password can be viewed after deployment by looking at the file
-`PATH_TO_KUBESPRAY/credentials/kube_user`. This contains a randomly generated
+`PATH_TO_KUBESPRAY/credentials/kube_user.creds`. This contains a randomly generated
 password. If you wish to set your own password, just precreate/modify this
-file yourself. 
+file yourself.
 
 For more information on kubeconfig and accessing a Kubernetes cluster, refer to
 the Kubernetes [documentation](https://kubernetes.io/docs/tasks/access-application-cluster/configure-access-multiple-clusters/).
@@ -77,29 +85,33 @@ Accessing Kubernetes Dashboard
 ------------------------------
 
 As of kubernetes-dashboard v1.7.x:
-* New login options that use apiserver auth proxying of token/basic/kubeconfig by default
+
-* Requires RBAC in authorization_modes
+-   New login options that use apiserver auth proxying of token/basic/kubeconfig by default
-* Only serves over https
+-   Requires RBAC in authorization\_modes
-* No longer available at https://first_master:6443/ui until apiserver is updated with the https proxy URL
+-   Only serves over https
+-   No longer available at <https://first_master:6443/ui> until apiserver is updated with the https proxy URL
 
 If the variable `dashboard_enabled` is set (default is true), then you can access the Kubernetes Dashboard at the following URL, You will be prompted for credentials:
-https://first_master:6443/api/v1/namespaces/kube-system/services/https:kubernetes-dashboard:/proxy/#!/login
+<https://first_master:6443/api/v1/namespaces/kube-system/services/https:kubernetes-dashboard:/proxy/#!/login>
 
 Or you can run 'kubectl proxy' from your local machine to access dashboard in your browser from:
-http://localhost:8001/api/v1/namespaces/kube-system/services/https:kubernetes-dashboard:/proxy/#!/login
+<http://localhost:8001/api/v1/namespaces/kube-system/services/https:kubernetes-dashboard:/proxy/#!/login>
 
-It is recommended to access dashboard from behind a gateway (like Ingress Controller) that enforces an authentication token. Details and other access options here: https://github.com/kubernetes/dashboard/wiki/Accessing-Dashboard---1.7.X-and-above
+It is recommended to access dashboard from behind a gateway (like Ingress Controller) that enforces an authentication token. Details and other access options here: <https://github.com/kubernetes/dashboard/wiki/Accessing-Dashboard---1.7.X-and-above>
 
 Accessing Kubernetes API
 ------------------------
 
 The main client of Kubernetes is `kubectl`. It is installed on each kube-master
 host and can optionally be configured on your ansible host by setting
-`kubeconfig_localhost: true` in the configuration. If enabled, kubectl and
+`kubectl_localhost: true` and `kubeconfig_localhost: true` in the configuration:
-admin.conf will appear in the artifacts/ directory after deployment. You can
-see a list of nodes by running the following commands:
 
-    cd artifacts/
+-   If `kubectl_localhost` enabled, `kubectl` will download onto `/usr/local/bin/` and setup with bash completion. A helper script `inventory/mycluster/artifacts/kubectl.sh` also created for setup with below `admin.conf`.
-    ./kubectl --kubeconfig admin.conf get nodes
+-   If `kubeconfig_localhost` enabled `admin.conf` will appear in the `inventory/mycluster/artifacts/` directory after deployment.
 
-If desired, copy kubectl to your bin dir and admin.conf to ~/.kube/config.
+You can see a list of nodes by running the following commands:
+
+    cd inventory/mycluster/artifacts
+    ./kubectl.sh get nodes
+
+If desired, copy admin.conf to ~/.kube/config.

docs/large-deployments.md

@@ -3,8 +3,7 @@ Large deployments of K8s
 
 For a large scaled deployments, consider the following configuration changes:
 
-* Tune [ansible settings]
+* Tune [ansible settings](http://docs.ansible.com/ansible/intro_configuration.html)
-  (http://docs.ansible.com/ansible/intro_configuration.html)
   for `forks` and `timeout` vars to fit large numbers of nodes being deployed.
 
 * Override containers' `foo_image_repo` vars to point to intranet registry.
@@ -47,5 +46,8 @@ For a large scaled deployments, consider the following configuration changes:
   section of the Getting started guide for tips on creating a large scale
   Ansible inventory.
 
+* Override the ``etcd_events_cluster_setup: true`` store events in a separate
+  dedicated etcd instance.
+
 For example, when deploying 200 nodes, you may want to run ansible with
 ``--forks=50``, ``--timeout=600`` and define the ``retry_stagger: 60``.

docs/vagrant.md

@@ -1,7 +1,7 @@
 Vagrant Install
 =================
 
-Assuming you have Vagrant (1.9+) installed with virtualbox (it may work
+Assuming you have Vagrant (2.0+) installed with virtualbox (it may work
 with vmware, but is untested) you should be able to launch a 3 node
 Kubernetes cluster by simply running `$ vagrant up`.<br />
 

docs/vars.md

@@ -63,7 +63,8 @@ following default cluster paramters:
   bits in kube_pods_subnet dictates how many kube-nodes can be in cluster.
 * *dns_setup* - Enables dnsmasq
 * *dnsmasq_dns_server* - Cluster IP for dnsmasq (default is 10.233.0.2)
-* *skydns_server* - Cluster IP for KubeDNS (default is 10.233.0.3)
+* *skydns_server* - Cluster IP for DNS (default is 10.233.0.3)
+* *skydns_server_secondary* - Secondary Cluster IP for CoreDNS used with coredns_dual deployment (default is 10.233.0.4)
 * *cloud_provider* - Enable extra Kubelet option if operating inside GCE or
   OpenStack (default is unset)
 * *kube_hostpath_dynamic_provisioner* - Required for use of PetSets type in
@@ -105,9 +106,9 @@ Stack](https://github.com/kubernetes-incubator/kubespray/blob/master/docs/dns-st
 * *http_proxy/https_proxy/no_proxy* - Proxy variables for deploying behind a
   proxy. Note that no_proxy defaults to all internal cluster IPs and hostnames
   that correspond to each node.
-* *kubelet_deployment_type* - Controls which platform to deploy kubelet on. 
+* *kubelet_deployment_type* - Controls which platform to deploy kubelet on.
   Available options are ``host``, ``rkt``, and ``docker``. ``docker`` mode
-  is unlikely to work on newer releases. Starting with Kubernetes v1.7 
+  is unlikely to work on newer releases. Starting with Kubernetes v1.7
   series, this now defaults to ``host``. Before v1.7, the default was Docker.
   This is because of cgroup [issues](https://github.com/kubernetes/kubernetes/issues/43704).
 * *kubelet_load_modules* - For some things, kubelet needs to load kernel modules.  For example,
@@ -117,6 +118,14 @@ Stack](https://github.com/kubernetes-incubator/kubespray/blob/master/docs/dns-st
 * *kubelet_cgroup_driver* - Allows manual override of the
   cgroup-driver option for Kubelet. By default autodetection is used
   to match Docker configuration.
+* *node_labels* - Labels applied to nodes via kubelet --node-labels parameter.
+  For example, labels can be set in the inventory as variables or more widely in group_vars.
+  *node_labels* must be defined as a dict:
+```
+node_labels:
+  label1_name: label1_value
+  label2_name: label2_value
+```
 
 ##### Custom flags for Kube Components
 For all kube components, custom flags can be passed in. This allows for edge cases where users need changes to the default deployment that may not be applicable to all deployments. This can be done by providing a list of flags. Example:
@@ -136,6 +145,6 @@ The possible vars are:
 
 By default, a user with admin rights is created, named `kube`.
 The password can be viewed after deployment by looking at the file
-`PATH_TO_KUBESPRAY/credentials/kube_user`. This contains a randomly generated
+`PATH_TO_KUBESPRAY/credentials/kube_user.creds`. This contains a randomly generated
 password. If you wish to set your own password, just precreate/modify this
 file yourself or change `kube_api_pwd` var.

inventory/sample/group_vars/all.yml

@@ -17,7 +17,7 @@ bin_dir: /usr/local/bin
 ### LOADBALANCING AND ACCESS MODES
 ## Enable multiaccess to configure etcd clients to access all of the etcd members directly
 ## as the "http://hostX:port, http://hostY:port, ..." and ignore the proxy loadbalancers.
-## This may be the case if clients support and loadbalance multiple etcd servers  natively.
+## This may be the case if clients support and loadbalance multiple etcd servers natively.
 #etcd_multiaccess: true
 
 ### ETCD: disable peer client cert authentication.
@@ -42,7 +42,7 @@ bin_dir: /usr/local/bin
 ## for mounting persistent volumes into containers.  These may not be loaded by preinstall kubernetes
 ## processes.  For example, ceph and rbd backed volumes.  Set to true to allow kubelet to load kernel
 ## modules.
-# kubelet_load_modules: false
+#kubelet_load_modules: false
 
 ## Internal network total size. This is the prefix of the
 ## entire network. Must be unused in your environment.
@@ -76,6 +76,7 @@ bin_dir: /usr/local/bin
 #azure_subnet_name:
 #azure_security_group_name:
 #azure_vnet_name:
+#azure_vnet_resource_group:
 #azure_route_table_name:
 
 ## When OpenStack is used, Cinder version can be explicitly specified if autodetection fails (Fixed in 1.9: https://github.com/kubernetes/kubernetes/issues/50461)
@@ -111,7 +112,7 @@ bin_dir: /usr/local/bin
 
 ## Default packages to install within the cluster, f.e:
 #kpm_packages:
-#  - name: kube-system/grafana
+# - name: kube-system/grafana
 
 ## Certificate Management
 ## This setting determines whether certs are generated via scripts or whether a
@@ -128,5 +129,9 @@ bin_dir: /usr/local/bin
 ## Set level of detail for etcd exported metrics, specify 'extensive' to include histogram metrics.
 #etcd_metrics: basic
 
+## Etcd is restricted by default to 512M on systems under 4GB RAM, 512MB is not enough for much more than testing.
+## Set this if your etcd nodes have less than 4GB but you want more RAM for etcd. Set to 0 for unrestricted RAM.
+#etcd_memory_limit: "512M"
+
 # The read-only port for the Kubelet to serve on with no authentication/authorization. Uncomment to enable.
-# kube_read_only_port: 10255
+#kube_read_only_port: 10255

inventory/sample/group_vars/k8s-cluster.yml

@@ -1,12 +1,11 @@
 # Kubernetes configuration dirs and system namespace.
 # Those are where all the additional config stuff goes
-# the kubernetes normally puts in /srv/kubernets.
+# the kubernetes normally puts in /srv/kubernetes.
 # This puts them in a sane location and namespace.
-# Editting those values will almost surely break something.
+# Editing those values will almost surely break something.
 kube_config_dir: /etc/kubernetes
 kube_script_dir: "{{ bin_dir }}/kubernetes-scripts"
 kube_manifest_dir: "{{ kube_config_dir }}/manifests"
-system_namespace: kube-system
 
 # This is where all the cert scripts and certs will be located
 kube_cert_dir: "{{ kube_config_dir }}/ssl"
@@ -20,7 +19,7 @@ kube_users_dir: "{{ kube_config_dir }}/users"
 kube_api_anonymous_auth: true
 
 ## Change this to use another Kubernetes version, e.g. a current beta release
-kube_version: v1.9.2
+kube_version: v1.9.5
 
 # Where the binaries will be downloaded.
 # Note: ensure that you've enough disk space (about 1G)
@@ -29,7 +28,7 @@ local_release_dir: "/tmp/releases"
 retry_stagger: 5
 
 # This is the group that the cert creation scripts chgrp the
-# cert files to. Not really changable...
+# cert files to. Not really changeable...
 kube_cert_group: kube-cert
 
 # Cluster Loglevel configuration
@@ -37,7 +36,7 @@ kube_log_level: 2
 
 # Users to create for basic auth in Kubernetes API via HTTP
 # Optionally add groups for user
-kube_api_pwd: "{{ lookup('password', inventory_dir + '/credentials/kube_user length=15 chars=ascii_letters,digits') }}"
+kube_api_pwd: "{{ lookup('password', inventory_dir + '/credentials/kube_user.creds length=15 chars=ascii_letters,digits') }}"
 kube_users:
   kube:
     pass: "{{kube_api_pwd}}"
@@ -111,14 +110,17 @@ kube_apiserver_insecure_port: 8080 # (http)
 
 # Kube-proxy proxyMode configuration.
 # Can be ipvs, iptables
-kube_proxy_mode: iptables 
+kube_proxy_mode: iptables
+
+## Encrypting Secret Data at Rest (experimental)
+kube_encrypt_secret_data: false
 
 # DNS configuration.
 # Kubernetes cluster name, also will be used as DNS domain
 cluster_name: cluster.local
 # Subdomains of DNS domain to be resolved via /etc/resolv.conf for hostnet pods
 ndots: 2
-# Can be dnsmasq_kubedns, kubedns, manual or none
+# Can be dnsmasq_kubedns, kubedns, coredns, coredns_dual, manual or none
 dns_mode: kubedns
 # Set manual server if using a custom cluster DNS server
 #manual_dns_server: 10.x.x.x
@@ -129,6 +131,7 @@ resolvconf_mode: docker_dns
 deploy_netchecker: false
 # Ip address of the kubernetes skydns service
 skydns_server: "{{ kube_service_addresses|ipaddr('net')|ipaddr(3)|ipaddr('address') }}"
+skydns_server_secondary: "{{ kube_service_addresses|ipaddr('net')|ipaddr(4)|ipaddr('address') }}"
 dnsmasq_dns_server: "{{ kube_service_addresses|ipaddr('net')|ipaddr(2)|ipaddr('address') }}"
 dns_domain: "{{ cluster_name }}"
 
@@ -159,19 +162,30 @@ dashboard_enabled: true
 # Monitoring apps for k8s
 efk_enabled: false
 
-# Helm deployment
+# Helm deployment. Needs for Prometheus Operator, k8s metrics.
 helm_enabled: false
 
+# Prometheus Operator. Needs for k8s metrics. Installed Helm is required.
+prometheus_operator_enabled: false
+
+# K8s cluster metrics. Installed Helm and Prometheus Operator are required.
+k8s_metrics_enabled: false
+
 # Istio deployment
 istio_enabled: false
 
 # Registry deployment
 registry_enabled: false
+# registry_namespace: "{{ system_namespace }}"
+# registry_storage_class: ""
+# registry_disk_size: "10Gi"
 
 # Local volume provisioner deployment
-# deprecated will be removed
+local_volume_provisioner_enabled: false
-local_volumes_enabled: false
+# local_volume_provisioner_namespace: "{{ system_namespace }}"
-local_volume_provisioner_enabled: "{{ local_volumes_enabled }}"
+# local_volume_provisioner_base_dir: /mnt/disks
+# local_volume_provisioner_mount_dir: /mnt/disks
+# local_volume_provisioner_storage_class: local-storage
 
 # CephFS provisioner deployment
 cephfs_provisioner_enabled: false
@@ -185,12 +199,30 @@ cephfs_provisioner_enabled: false
 # cephfs_provisioner_secret: secret
 # cephfs_provisioner_storage_class: cephfs
 
+# Nginx ingress controller deployment
+ingress_nginx_enabled: false
+# ingress_nginx_host_network: false
+# ingress_nginx_namespace: "ingress-nginx"
+# ingress_nginx_insecure_port: 80
+# ingress_nginx_secure_port: 443
+# ingress_nginx_configmap:
+#   map-hash-bucket-size: "128"
+#   ssl-protocols: "SSLv2"
+# ingress_nginx_configmap_tcp_services:
+#   9000: "default/example-go:8080"
+# ingress_nginx_configmap_udp_services:
+#   53: "kube-system/kube-dns:53"
+
+# Cert manager deployment
+cert_manager_enabled: false
+# cert_manager_namespace: "cert-manager"
+
 # Add Persistent Volumes Storage Class for corresponding cloud provider ( OpenStack is only supported now )
 persistent_volumes_enabled: false
 
-# Make a copy of kubeconfig on the host that runs Ansible in GITDIR/artifacts
+# Make a copy of kubeconfig on the host that runs Ansible in {{ inventory_dir }}/artifacts
 # kubeconfig_localhost: false
-# Download kubectl onto the host that runs Ansible in GITDIR/artifacts
+# Download kubectl onto the host that runs Ansible in {{ bin_dir }}
 # kubectl_localhost: false
 
 # dnsmasq

inventory/sample/hosts.ini

@@ -26,6 +26,11 @@
 # node5
 # node6
 
+# [kube-ingress]
+# node2
+# node3
+
 # [k8s-cluster:children]
+# kube-master
 # kube-node
-# kube-master
+# kube-ingress

library/kube.py

@@ -18,7 +18,9 @@ options:
     required: false
     default: null
     description:
-      - The path and filename of the resource(s) definition file.
+      - The path and filename of the resource(s) definition file(s).
+      - To operate on several files this can accept a comma separated list of files or a list of files.
+    aliases: [ 'files', 'file', 'filenames' ]
   kubectl:
     required: false
     default: null
@@ -86,6 +88,15 @@ EXAMPLES = """
 
 - name: test nginx is present
   kube: filename=/tmp/nginx.yml
+
+- name: test nginx and postgresql are present
+  kube: files=/tmp/nginx.yml,/tmp/postgresql.yml
+
+- name: test nginx and postgresql are present
+  kube:
+    files:
+      - /tmp/nginx.yml
+      - /tmp/postgresql.yml
 """
 
 
@@ -112,7 +123,7 @@ class KubeManager(object):
         self.all = module.params.get('all')
         self.force = module.params.get('force')
         self.name = module.params.get('name')
-        self.filename = module.params.get('filename')
+        self.filename = [f.strip() for f in module.params.get('filename') or []]
         self.resource = module.params.get('resource')
         self.label = module.params.get('label')
 
@@ -122,7 +133,7 @@ class KubeManager(object):
             rc, out, err = self.module.run_command(args)
             if rc != 0:
                 self.module.fail_json(
-                    msg='error running kubectl (%s) command (rc=%d): %s' % (' '.join(args), rc, out or err))
+                    msg='error running kubectl (%s) command (rc=%d), out=\'%s\', err=\'%s\'' % (' '.join(args), rc, out, err))
         except Exception as exc:
             self.module.fail_json(
                 msg='error running kubectl (%s) command: %s' % (' '.join(args), str(exc)))
@@ -147,7 +158,7 @@ class KubeManager(object):
         if not self.filename:
             self.module.fail_json(msg='filename required to create')
 
-        cmd.append('--filename=' + self.filename)
+        cmd.append('--filename=' + ','.join(self.filename))
 
         return self._execute(cmd)
 
@@ -161,7 +172,7 @@ class KubeManager(object):
         if not self.filename:
             self.module.fail_json(msg='filename required to reload')
 
-        cmd.append('--filename=' + self.filename)
+        cmd.append('--filename=' + ','.join(self.filename))
 
         return self._execute(cmd)
 
@@ -173,7 +184,7 @@ class KubeManager(object):
         cmd = ['delete']
 
         if self.filename:
-            cmd.append('--filename=' + self.filename)
+            cmd.append('--filename=' + ','.join(self.filename))
         else:
             if not self.resource:
                 self.module.fail_json(msg='resource required to delete without filename')
@@ -197,27 +208,31 @@ class KubeManager(object):
     def exists(self):
         cmd = ['get']
 
-        if not self.resource:
+        if self.filename:
-            return False
+            cmd.append('--filename=' + ','.join(self.filename))
+        else:
+            if not self.resource:
+                self.module.fail_json(msg='resource required without filename')
 
-        cmd.append(self.resource)
+            cmd.append(self.resource)
 
-        if self.name:
+            if self.name:
-            cmd.append(self.name)
+                cmd.append(self.name)
+
+            if self.label:
+                cmd.append('--selector=' + self.label)
+
+            if self.all:
+                cmd.append('--all-namespaces')
 
         cmd.append('--no-headers')
 
-        if self.label:
-            cmd.append('--selector=' + self.label)
-
-        if self.all:
-            cmd.append('--all-namespaces')
-
         result = self._execute_nofail(cmd)
         if not result:
             return False
         return True
 
+    # TODO: This is currently unused, perhaps convert to 'scale' with a replicas param?
     def stop(self):
 
         if not self.force and not self.exists():
@@ -226,7 +241,7 @@ class KubeManager(object):
         cmd = ['stop']
 
         if self.filename:
-            cmd.append('--filename=' + self.filename)
+            cmd.append('--filename=' + ','.join(self.filename))
         else:
             if not self.resource:
                 self.module.fail_json(msg='resource required to stop without filename')
@@ -253,7 +268,7 @@ def main():
     module = AnsibleModule(
         argument_spec=dict(
             name=dict(),
-            filename=dict(),
+            filename=dict(type='list', aliases=['files', 'file', 'filenames']),
             namespace=dict(),
             resource=dict(),
             label=dict(),
@@ -263,7 +278,8 @@ def main():
             all=dict(default=False, type='bool'),
             log_level=dict(default=0, type='int'),
             state=dict(default='present', choices=['present', 'absent', 'latest', 'reloaded', 'stopped']),
-            )
+            ),
+            mutually_exclusive=[['filename', 'list']]
         )
 
     changed = False

remove-node.yml

@@ -0,0 +1,29 @@
+---
+
+- hosts: all
+  gather_facts: true
+
+- hosts: etcd:k8s-cluster:vault:calico-rr
+  vars_prompt:
+    name: "delete_nodes_confirmation"
+    prompt: "Are you sure you want to delete nodes state? Type 'yes' to delete nodes."
+    default: "no"
+    private: no
+
+  pre_tasks:
+    - name: check confirmation
+      fail:
+        msg: "Delete nodes confirmation failed"
+      when: delete_nodes_confirmation != "yes"
+
+- hosts: kube-master
+  roles:
+    - { role: remove-node/pre-remove, tags: pre-remove }
+
+- hosts: kube-node
+  roles:
+    - { role: reset, tags: reset }
+
+- hosts: kube-master
+  roles:
+    - { role: remove-node/post-remove, tags: post-remove }

roles/dnsmasq/tasks/main.yml

@@ -91,7 +91,7 @@
 - name: Start Resources
   kube:
     name: "{{item.item.name}}"
-    namespace: "{{system_namespace}}"
+    namespace: "kube-system"
     kubectl: "{{bin_dir}}/kubectl"
     resource: "{{item.item.type}}"
     filename: "{{kube_config_dir}}/{{item.item.file}}"

roles/dnsmasq/templates/dnsmasq-clusterrolebinding.yml

@@ -3,11 +3,11 @@ kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1beta1
 metadata:
   name: dnsmasq
-  namespace: "{{ system_namespace }}"
+  namespace: "kube-system"
 subjects:
   - kind: ServiceAccount
     name: dnsmasq
-    namespace: "{{ system_namespace}}"
+    namespace: "kube-system"
 roleRef:
   kind: ClusterRole
   name: cluster-admin

roles/dnsmasq/templates/dnsmasq-deploy.yml

@@ -3,7 +3,7 @@ apiVersion: extensions/v1beta1
 kind: Deployment
 metadata:
   name: dnsmasq
-  namespace: "{{system_namespace}}"
+  namespace: "kube-system"
   labels:
     k8s-app: dnsmasq
     kubernetes.io/cluster-service: "true"

roles/dnsmasq/templates/dnsmasq-serviceaccount.yml

@@ -3,6 +3,6 @@ apiVersion: v1
 kind: ServiceAccount
 metadata:
   name: dnsmasq
-  namespace: "{{ system_namespace }}"
+  namespace: "kube-system"
   labels:
     kubernetes.io/cluster-service: "true"

roles/dnsmasq/templates/dnsmasq-svc.yml

@@ -6,7 +6,7 @@ metadata:
     kubernetes.io/cluster-service: 'true'
     k8s-app: dnsmasq
   name: dnsmasq
-  namespace: {{system_namespace}}
+  namespace: kube-system
 spec:
   ports:
     - port: 53

roles/docker/defaults/main.yml

@@ -1,5 +1,6 @@
 ---
 docker_version: '17.03'
+docker_selinux_version: '17.03'
 
 docker_package_info:
   pkgs:
@@ -10,11 +11,31 @@ docker_repo_key_info:
 docker_repo_info:
   repos:
 
+dockerproject_repo_key_info:
+  repo_keys:
+
+dockerproject_repo_info:
+  repos:
+
 docker_dns_servers_strict: yes
 
 docker_container_storage_setup: false
 
-docker_rh_repo_base_url: 'https://yum.dockerproject.org/repo/main/centos/7'
+# Used to override obsoletes=0
-docker_rh_repo_gpgkey: 'https://yum.dockerproject.org/gpg'
+yum_conf: /etc/yum.conf
-docker_apt_repo_base_url: 'https://apt.dockerproject.org/repo'
+docker_yum_conf: /etc/yum_docker.conf
-docker_apt_repo_gpgkey: 'https://apt.dockerproject.org/gpg'
+
+# CentOS/RedHat docker-ce repo
+docker_rh_repo_base_url: 'https://download.docker.com/linux/centos/7/$basearch/stable'
+docker_rh_repo_gpgkey: 'https://download.docker.com/linux/centos/gpg'
+# Ubuntu docker-ce repo
+docker_ubuntu_repo_base_url: "https://download.docker.com/linux/ubuntu"
+docker_ubuntu_repo_gpgkey: 'https://download.docker.com/linux/ubuntu/gpg'
+# Debian docker-ce repo
+docker_debian_repo_base_url: "https://download.docker.com/linux/debian"
+docker_debian_repo_gpgkey: 'https://download.docker.com/linux/debian/gpg'
+# dockerproject repo
+dockerproject_rh_repo_base_url: 'https://yum.dockerproject.org/repo/main/centos/7'
+dockerproject_rh_repo_gpgkey: 'https://yum.dockerproject.org/gpg'
+dockerproject_apt_repo_base_url: 'https://apt.dockerproject.org/repo'
+dockerproject_apt_repo_gpgkey: 'https://apt.dockerproject.org/gpg'

roles/docker/tasks/main.yml

@@ -30,7 +30,9 @@
   tags:
     - facts
 
-- name: ensure docker repository public key is installed
+- import_tasks: pre-upgrade.yml
+
+- name: ensure docker-ce repository public key is installed
   action: "{{ docker_repo_key_info.pkg_key }}"
   args:
     id: "{{item}}"
@@ -41,15 +43,36 @@
   retries: 4
   delay: "{{ retry_stagger | random + 3 }}"
   with_items: "{{ docker_repo_key_info.repo_keys }}"
-  when: not (ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] or is_atomic)
+  when: not (ansible_os_family in ["CoreOS", "Container Linux by CoreOS", "RedHat"] or is_atomic)
 
-- name: ensure docker repository is enabled
+- name: ensure docker-ce repository is enabled
   action: "{{ docker_repo_info.pkg_repo }}"
   args:
     repo: "{{item}}"
     state: present
   with_items: "{{ docker_repo_info.repos }}"
-  when: not (ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] or is_atomic) and (docker_repo_info.repos|length > 0)
+  when: not (ansible_os_family in ["CoreOS", "Container Linux by CoreOS", "RedHat"] or is_atomic) and (docker_repo_info.repos|length > 0)
+
+- name: ensure docker-engine repository public key is installed
+  action: "{{ dockerproject_repo_key_info.pkg_key }}"
+  args:
+    id: "{{item}}"
+    url: "{{dockerproject_repo_key_info.url}}"
+    state: present
+  register: keyserver_task_result
+  until: keyserver_task_result|succeeded
+  retries: 4
+  delay: "{{ retry_stagger | random + 3 }}"
+  with_items: "{{ dockerproject_repo_key_info.repo_keys }}"
+  when: not (ansible_os_family in ["CoreOS", "Container Linux by CoreOS", "RedHat"] or is_atomic)
+
+- name: ensure docker-engine repository is enabled
+  action: "{{ dockerproject_repo_info.pkg_repo }}"
+  args:
+    repo: "{{item}}"
+    state: present
+  with_items: "{{ dockerproject_repo_info.repos }}"
+  when: not (ansible_os_family in ["CoreOS", "Container Linux by CoreOS", "RedHat"] or is_atomic) and (dockerproject_repo_info.repos|length > 0)
 
 - name: Configure docker repository on RedHat/CentOS
   template:
@@ -57,11 +80,27 @@
     dest: "/etc/yum.repos.d/docker.repo"
   when: ansible_distribution in ["CentOS","RedHat"] and not is_atomic
 
+- name: Copy yum.conf for editing
+  copy:
+    src: "{{ yum_conf }}"
+    dest: "{{ docker_yum_conf }}"
+    remote_src: yes
+  when: ansible_distribution in ["CentOS","RedHat"] and not is_atomic
+
+- name: Edit copy of yum.conf to set obsoletes=0
+  lineinfile:
+    path: "{{ docker_yum_conf }}"
+    state: present
+    regexp: '^obsoletes='
+    line: 'obsoletes=0'
+  when: ansible_distribution in ["CentOS","RedHat"] and not is_atomic
+
 - name: ensure docker packages are installed
   action: "{{ docker_package_info.pkg_mgr }}"
   args:
     pkg: "{{item.name}}"
     force: "{{item.force|default(omit)}}"
+    conf_file: "{{item.yum_conf|default(omit)}}"
     state: present
   register: docker_task_result
   until: docker_task_result|succeeded

roles/docker/tasks/pre-upgrade.yml

@@ -0,0 +1,25 @@
+---
+- name: Ensure old versions of Docker are not installed. | Debian
+  package:
+    name: '{{ item }}'
+    state: absent
+  with_items:
+    - docker
+    - docker-engine
+  when:
+    - ansible_os_family == 'Debian'
+    - (docker_versioned_pkg[docker_version | string] | search('docker-ce'))
+
+- name: Ensure old versions of Docker are not installed. | RedHat
+  package:
+    name: '{{ item }}'
+    state: absent
+  with_items:
+    - docker
+    - docker-common
+    - docker-engine
+    - docker-selinux
+  when:
+    - ansible_os_family == 'RedHat'
+    - (docker_versioned_pkg[docker_version | string] | search('docker-ce'))
+    - not is_atomic

roles/docker/tasks/set_facts_dns.yml

@@ -3,8 +3,10 @@
 - name: set dns server for docker
   set_fact:
     docker_dns_servers: |-
-      {%- if dns_mode == 'kubedns' -%}
+      {%- if dns_mode in ['kubedns', 'coredns'] -%}
         {{ [ skydns_server ] }}
+      {%- elif dns_mode == 'coredns_dual' -%}
+        {{ [ skydns_server ] + [ skydns_server_secondary ] }}
       {%- elif dns_mode == 'dnsmasq_kubedns' -%}
         {{ [ dnsmasq_dns_server ] }}
       {%- elif dns_mode == 'manual' -%}
@@ -24,7 +26,7 @@
 - name: add upstream dns servers (only when dnsmasq is not used)
   set_fact:
     docker_dns_servers: "{{ docker_dns_servers + upstream_dns_servers|default([]) }}"
-  when: dns_mode == 'kubedns'
+  when: dns_mode in ['kubedns', 'coredns', 'coreos_dual']
 
 - name: add global searchdomains
   set_fact:

roles/docker/tasks/systemd.yml

@@ -12,7 +12,7 @@
   when: http_proxy is defined or https_proxy is defined
 
 - name: get systemd version
-  command: systemctl --version | head -n 1 | cut -d " " -f 2
+  shell: systemctl --version | head -n 1 | cut -d " " -f 2
   register: systemd_version
   when: not is_atomic
   changed_when: false

roles/docker/templates/docker.service.j2

@@ -31,7 +31,10 @@ LimitNOFILE=1048576
 LimitNPROC=1048576
 LimitCORE=infinity
 TimeoutStartSec=1min
-Restart=on-abnormal
+# restart the docker process if it exits prematurely
+Restart=on-failure
+StartLimitBurst=3
+StartLimitInterval=60s
 
 [Install]
 WantedBy=multi-user.target

roles/docker/templates/rh_docker.repo.j2

@@ -1,7 +1,15 @@
-[dockerrepo]
+[docker-ce]
-name=Docker Repository
+name=Docker-CE Repository
 baseurl={{ docker_rh_repo_base_url }}
 enabled=1
 gpgcheck=1
 gpgkey={{ docker_rh_repo_gpgkey }}
 {% if http_proxy is defined %}proxy={{ http_proxy }}{% endif %}
+
+[docker-engine]
+name=Docker-Engine Repository
+baseurl={{ dockerproject_rh_repo_base_url }}
+enabled=1
+gpgcheck=1
+gpgkey={{ dockerproject_rh_repo_gpgkey }}
+{% if http_proxy is defined %}proxy={{ http_proxy }}{% endif %}

roles/docker/vars/debian.yml

@@ -1,15 +1,16 @@
 ---
 docker_kernel_min_version: '3.10'
 
+# https://download.docker.com/linux/debian/
 # https://apt.dockerproject.org/repo/dists/debian-wheezy/main/filelist
 docker_versioned_pkg:
-  'latest': docker-engine
+  'latest': docker-ce
   '1.11': docker-engine=1.11.2-0~{{ ansible_distribution_release|lower }}
   '1.12': docker-engine=1.12.6-0~debian-{{ ansible_distribution_release|lower }}
   '1.13': docker-engine=1.13.1-0~debian-{{ ansible_distribution_release|lower }}
-  '17.03': docker-engine=17.03.1~ce-0~debian-{{ ansible_distribution_release|lower }}
+  '17.03': docker-ce=17.03.2~ce-0~debian-{{ ansible_distribution_release|lower }}
-  'stable': docker-engine=17.03.1~ce-0~debian-{{ ansible_distribution_release|lower }}
+  'stable': docker-ce=17.03.2~ce-0~debian-{{ ansible_distribution_release|lower }}
-  'edge': docker-engine=17.05.0~ce-0~debian-{{ ansible_distribution_release|lower }}
+  'edge': docker-ce=17.12.1~ce-0~debian-{{ ansible_distribution_release|lower }}
 
 docker_package_info:
   pkg_mgr: apt
@@ -19,14 +20,28 @@ docker_package_info:
 
 docker_repo_key_info:
   pkg_key: apt_key
-  url: '{{ docker_apt_repo_gpgkey }}'
+  url: '{{ docker_debian_repo_gpgkey }}'
   repo_keys:
-    - 58118E89F3A912897C070ADBF76221572C52609D
+    - 9DC858229FC7DD38854AE2D88D81803C0EBFCD88
 
 docker_repo_info:
   pkg_repo: apt_repository
   repos:
     - >
-       deb {{ docker_apt_repo_base_url }}
+       deb {{ docker_debian_repo_base_url }}
+       {{ ansible_distribution_release|lower }}
+       stable
+
+dockerproject_repo_key_info:
+  pkg_key: apt_key
+  url: '{{ dockerproject_apt_repo_gpgkey }}'
+  repo_keys:
+    - 58118E89F3A912897C070ADBF76221572C52609D
+
+dockerproject_repo_info:
+  pkg_repo: apt_repository
+  repos:
+    - >
+       deb {{ dockerproject_apt_repo_base_url }}
        {{ ansible_distribution|lower }}-{{ ansible_distribution_release|lower }}
        main

roles/docker/vars/fedora-20.yml

@@ -1,17 +0,0 @@
----
-docker_kernel_min_version: '0'
-
-# versioning: docker-io itself is pinned at docker 1.5
-
-docker_package_info:
-  pkg_mgr: yum
-  pkgs:
-    - name: docker-io
-
-docker_repo_key_info:
-  pkg_key: ''
-  repo_keys: []
-
-docker_repo_info:
-  pkg_repo: ''
-  repos: []

roles/docker/vars/fedora.yml

@@ -1,28 +0,0 @@
----
-docker_kernel_min_version: '0'
-
-# https://docs.docker.com/engine/installation/linux/fedora/#install-from-a-package
-# https://download.docker.com/linux/fedora/7/x86_64/stable/
-# the package names below are guesses;
-# docs mention `sudo dnf config-manager --enable docker-ce-edge` for edge
-docker_versioned_pkg:
-  'latest': docker
-  '1.11': docker-1:1.11.2
-  '1.12': docker-1:1.12.6
-  '1.13': docker-1.13.1
-  '17.03': docker-17.03.1
-  'stable': docker-ce
-  'edge': docker-ce-edge
-
-docker_package_info:
-  pkg_mgr: dnf
-  pkgs:
-    - name: "{{ docker_versioned_pkg[docker_version | string] }}"
-
-docker_repo_key_info:
-  pkg_key: ''
-  repo_keys: []
-
-docker_repo_info:
-  pkg_repo: ''
-  repos: []

roles/docker/vars/redhat.yml

@@ -1,24 +1,36 @@
 ---
 docker_kernel_min_version: '0'
 
-# https://yum.dockerproject.org/repo/main/centos/7/Packages/
+# https://docs.docker.com/engine/installation/linux/centos/#install-from-a-package
+# https://download.docker.com/linux/centos/7/x86_64/stable/Packages/
+# https://yum.dockerproject.org/repo/main/centos/7
 # or do 'yum --showduplicates list docker-engine'
 docker_versioned_pkg:
-  'latest': docker-engine
+  'latest': docker-ce
   '1.11': docker-engine-1.11.2-1.el7.centos
   '1.12': docker-engine-1.12.6-1.el7.centos
   '1.13': docker-engine-1.13.1-1.el7.centos
-  '17.03': docker-engine-17.03.1.ce-1.el7.centos
+  '17.03': docker-ce-17.03.2.ce-1.el7.centos
-  'stable': docker-engine-17.03.1.ce-1.el7.centos
+  'stable': docker-ce-17.03.2.ce-1.el7.centos
-  'edge': docker-engine-17.05.0.ce-1.el7.centos
+  'edge': docker-ce-17.12.1.ce-1.el7.centos
+
+docker_selinux_versioned_pkg:
+  'latest': docker-ce-selinux
+  '1.11': docker-engine-selinux-1.11.2-1.el7.centos
+  '1.12': docker-engine-selinux-1.12.6-1.el7.centos
+  '1.13': docker-engine-selinux-1.13.1-1.el7.centos
+  '17.03': docker-ce-selinux-17.03.2.ce-1.el7.centos
+  'stable': docker-ce-selinux-17.03.2.ce-1.el7.centos
+  'edge': docker-ce-selinux-17.03.2.ce-1.el7.centos
 
-# https://docs.docker.com/engine/installation/linux/centos/#install-from-a-package
-# https://download.docker.com/linux/centos/7/x86_64/stable/Packages/
 
 docker_package_info:
   pkg_mgr: yum
   pkgs:
+    - name: "{{ docker_selinux_versioned_pkg[docker_selinux_version | string] }}"
+      yum_conf: "{{ docker_yum_conf }}"
     - name: "{{ docker_versioned_pkg[docker_version | string] }}"
+      yum_conf: "{{ docker_yum_conf }}"
 
 docker_repo_key_info:
   pkg_key: ''

roles/docker/vars/ubuntu.yml

@@ -1,15 +1,15 @@
 ---
 docker_kernel_min_version: '3.10'
 
-# https://apt.dockerproject.org/repo/dists/ubuntu-xenial/main/filelist
+# https://download.docker.com/linux/ubuntu/
 docker_versioned_pkg:
-  'latest': docker-engine
+  'latest': docker-ce
-  '1.11': docker-engine=1.11.1-0~{{ ansible_distribution_release|lower }}
+  '1.11': docker-engine=1.11.2-0~{{ ansible_distribution_release|lower }}
   '1.12': docker-engine=1.12.6-0~ubuntu-{{ ansible_distribution_release|lower }}
   '1.13': docker-engine=1.13.1-0~ubuntu-{{ ansible_distribution_release|lower }}
-  '17.03': docker-engine=17.03.1~ce-0~ubuntu-{{ ansible_distribution_release|lower }}
+  '17.03': docker-ce=17.03.2~ce-0~ubuntu-{{ ansible_distribution_release|lower }}
-  'stable': docker-engine=17.03.1~ce-0~ubuntu-{{ ansible_distribution_release|lower }}
+  'stable': docker-ce=17.03.2~ce-0~ubuntu-{{ ansible_distribution_release|lower }}
-  'edge': docker-engine=17.05.0~ce-0~ubuntu-{{ ansible_distribution_release|lower }}
+  'edge': docker-ce=17.12.1~ce-0~ubuntu-{{ ansible_distribution_release|lower }}
 
 docker_package_info:
   pkg_mgr: apt
@@ -19,14 +19,28 @@ docker_package_info:
 
 docker_repo_key_info:
   pkg_key: apt_key
-  url: '{{ docker_apt_repo_gpgkey }}'
+  url: '{{ docker_ubuntu_repo_gpgkey }}'
   repo_keys:
-    - 58118E89F3A912897C070ADBF76221572C52609D
+    - 9DC858229FC7DD38854AE2D88D81803C0EBFCD88
 
 docker_repo_info:
   pkg_repo: apt_repository
   repos:
     - >
-       deb {{ docker_apt_repo_base_url }}
+       deb {{ docker_ubuntu_repo_base_url }}
+       {{ ansible_distribution_release|lower }}
+       stable
+
+dockerproject_repo_key_info:
+  pkg_key: apt_key
+  url: '{{ dockerproject_apt_repo_gpgkey }}'
+  repo_keys:
+    - 58118E89F3A912897C070ADBF76221572C52609D
+
+dockerproject_repo_info:
+  pkg_repo: apt_repository
+  repos:
+    - >
+       deb {{ dockerproject_apt_repo_base_url }}
        {{ ansible_distribution|lower }}-{{ ansible_distribution_release|lower }}
        main

roles/download/defaults/main.yml

@@ -1,5 +1,5 @@
 ---
-local_release_dir: /tmp
+local_release_dir: /tmp/releases
 
 # Used to only evaluate vars from download role
 skip_downloads: false
@@ -24,24 +24,24 @@ download_always_pull: False
 download_delegate: "{% if download_localhost %}localhost{% else %}{{groups['kube-master'][0]}}{% endif %}"
 
 # Versions
-kube_version: v1.9.2
+kube_version: v1.9.5
 kubeadm_version: "{{ kube_version }}"
 etcd_version: v3.2.4
 # TODO(mattymo): Move calico versions to roles/network_plugins/calico/defaults
 # after migration to container download
-calico_version: "v2.6.2"
+calico_version: "v2.6.8"
-calico_ctl_version: "v1.6.1"
+calico_ctl_version: "v1.6.3"
-calico_cni_version: "v1.11.0"
+calico_cni_version: "v1.11.4"
-calico_policy_version: "v1.0.0"
+calico_policy_version: "v1.0.3"
-calico_rr_version: "v0.4.0"
+calico_rr_version: "v0.4.2"
-flannel_version: "v0.9.1"
+flannel_version: "v0.10.0"
 flannel_cni_version: "v0.3.0"
 istio_version: "0.2.6"
 vault_version: 0.8.1
-weave_version: 2.2.0
+weave_version: 2.2.1
 pod_infra_version: 3.0
 contiv_version: 1.1.7
-cilium_version: "v1.0.0-rc4"
+cilium_version: "v1.0.0-rc8"
 
 # Download URLs
 istioctl_download_url: "https://storage.googleapis.com/istio-release/releases/{{ istio_version }}/istioctl/istioctl-linux"
@@ -50,7 +50,7 @@ vault_download_url: "https://releases.hashicorp.com/vault/{{ vault_version }}/va
 
 # Checksums
 istioctl_checksum: fd703063c540b8c0ab943f478c05ab257d88ae27224c746a27d0526ddbf7c370
-kubeadm_checksum: 560b44a2b91747f4fb64ac8754fcf65db9a39a84c6b54d4e6483400ac6c674fc
+kubeadm_checksum: 12b6e9ac1624852b7c978bde70b9bde9ca0e4fc6581d09bddfb117bb41f93c74
 vault_binary_checksum: 3c4d70ba71619a43229e65c67830e30e050eab7a81ac6b28325ff707e5914188
 
 # Containers
@@ -70,8 +70,24 @@ calico_policy_image_repo: "quay.io/calico/kube-controllers"
 calico_policy_image_tag: "{{ calico_policy_version }}"
 calico_rr_image_repo: "quay.io/calico/routereflector"
 calico_rr_image_tag: "{{ calico_rr_version }}"
-hyperkube_image_repo: "quay.io/coreos/hyperkube"
+istio_proxy_image_repo: docker.io/istio/proxy
-hyperkube_image_tag: "{{ kube_version }}_coreos.0"
+istio_proxy_image_tag: "{{ istio_version }}"
+istio_proxy_init_image_repo: docker.io/istio/proxy_init
+istio_proxy_init_image_tag: "{{ istio_version }}"
+istio_ca_image_repo: docker.io/istio/istio-ca
+istio_ca_image_tag: "{{ istio_version }}"
+istio_mixer_image_repo: docker.io/istio/mixer
+istio_mixer_image_tag: "{{ istio_version }}"
+istio_pilot_image_repo: docker.io/istio/pilot
+istio_pilot_image_tag: "{{ istio_version }}"
+istio_proxy_debug_image_repo: docker.io/istio/proxy_debug
+istio_proxy_debug_image_tag: "{{ istio_version }}"
+istio_sidecar_initializer_image_repo: docker.io/istio/sidecar_initializer
+istio_sidecar_initializer_image_tag: "{{ istio_version }}"
+istio_statsd_image_repo: prom/statsd-exporter
+istio_statsd_image_tag: latest
+hyperkube_image_repo: "gcr.io/google-containers/hyperkube"
+hyperkube_image_tag: "{{ kube_version }}"
 pod_infra_image_repo: "gcr.io/google_containers/pause-amd64"
 pod_infra_image_tag: "{{ pod_infra_version }}"
 install_socat_image_repo: "xueshanf/install-socat"
@@ -91,7 +107,6 @@ contiv_auth_proxy_image_repo: "contiv/auth_proxy"
 contiv_auth_proxy_image_tag: "{{ contiv_version }}"
 cilium_image_repo: "docker.io/cilium/cilium"
 cilium_image_tag: "{{ cilium_version }}"
-
 nginx_image_repo: nginx
 nginx_image_tag: 1.13
 dnsmasq_version: 2.78
@@ -100,6 +115,9 @@ dnsmasq_image_tag: "{{ dnsmasq_version }}"
 kubedns_version: 1.14.8
 kubedns_image_repo: "gcr.io/google_containers/k8s-dns-kube-dns-amd64"
 kubedns_image_tag: "{{ kubedns_version }}"
+coredns_version: 1.1.0
+coredns_image_repo: "docker.io/coredns/coredns"
+coredns_image_tag: "{{ coredns_version }}"
 dnsmasq_nanny_image_repo: "gcr.io/google_containers/k8s-dns-dnsmasq-nanny-amd64"
 dnsmasq_nanny_image_tag: "{{ kubedns_version }}"
 dnsmasq_sidecar_image_repo: "gcr.io/google_containers/k8s-dns-sidecar-amd64"
@@ -121,14 +139,30 @@ fluentd_image_tag: "{{ fluentd_version }}"
 kibana_version: "v4.6.1"
 kibana_image_repo: "gcr.io/google_containers/kibana"
 kibana_image_tag: "{{ kibana_version }}"
-
+helm_version: "v2.8.1"
-helm_version: "v2.7.2"
 helm_image_repo: "lachlanevenson/k8s-helm"
 helm_image_tag: "{{ helm_version }}"
 tiller_image_repo: "gcr.io/kubernetes-helm/tiller"
 tiller_image_tag: "{{ helm_version }}"
 vault_image_repo: "vault"
 vault_image_tag: "{{ vault_version }}"
+registry_image_repo: "registry"
+registry_image_tag: "2.6"
+registry_proxy_image_repo: "gcr.io/google_containers/kube-registry-proxy"
+registry_proxy_image_tag: "0.4"
+local_volume_provisioner_image_repo: "quay.io/external_storage/local-volume-provisioner"
+local_volume_provisioner_image_tag: "v2.0.0"
+cephfs_provisioner_image_repo: "quay.io/kubespray/cephfs-provisioner"
+cephfs_provisioner_image_tag: "92295a30"
+ingress_nginx_controller_image_repo: "quay.io/kubernetes-ingress-controller/nginx-ingress-controller"
+ingress_nginx_controller_image_tag: "0.12.0"
+ingress_nginx_default_backend_image_repo: "gcr.io/google_containers/defaultbackend"
+ingress_nginx_default_backend_image_tag: "1.4"
+cert_manager_version: "v0.2.3"
+cert_manager_controller_image_repo: "quay.io/jetstack/cert-manager-controller"
+cert_manager_controller_image_tag: "{{ cert_manager_version }}"
+cert_manager_ingress_shim_image_repo: "quay.io/jetstack/cert-manager-ingress-shim"
+cert_manager_ingress_shim_image_tag: "{{ cert_manager_version }}"
 
 downloads:
   netcheck_server:
@@ -137,18 +171,24 @@ downloads:
     repo: "{{ netcheck_server_img_repo }}"
     tag: "{{ netcheck_server_tag }}"
     sha256: "{{ netcheck_server_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   netcheck_agent:
     enabled: "{{ deploy_netchecker }}"
     container: true
     repo: "{{ netcheck_agent_img_repo }}"
     tag: "{{ netcheck_agent_tag }}"
     sha256: "{{ netcheck_agent_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   etcd:
     enabled: true
     container: true
     repo: "{{ etcd_image_repo }}"
     tag: "{{ etcd_image_tag }}"
     sha256: "{{ etcd_digest_checksum|default(None) }}"
+    groups:
+      - etcd
   kubeadm:
     enabled: "{{ kubeadm_enabled }}"
     file: true
@@ -160,6 +200,8 @@ downloads:
     unarchive: false
     owner: "root"
     mode: "0755"
+    groups:
+      - k8s-cluster
   istioctl:
     enabled: "{{ istio_enabled }}"
     file: true
@@ -171,134 +213,250 @@ downloads:
     unarchive: false
     owner: "root"
     mode: "0755"
+    groups:
+      - kube-master
+  istio_proxy:
+    enabled: "{{ istio_enabled }}"
+    container: true
+    repo: "{{ istio_proxy_image_repo }}"
+    tag: "{{ istio_proxy_image_tag }}"
+    sha256: "{{ istio_proxy_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  istio_proxy_init:
+    enabled: "{{ istio_enabled }}"
+    container: true
+    repo: "{{ istio_proxy_init_image_repo }}"
+    tag: "{{ istio_proxy_init_image_tag }}"
+    sha256: "{{ istio_proxy_init_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  istio_ca:
+    enabled: "{{ istio_enabled }}"
+    container: true
+    repo: "{{ istio_ca_image_repo }}"
+    tag: "{{ istio_ca_image_tag }}"
+    sha256: "{{ istio_ca_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  istio_mixer:
+    enabled: "{{ istio_enabled }}"
+    container: true
+    repo: "{{ istio_mixer_image_repo }}"
+    tag: "{{ istio_mixer_image_tag }}"
+    sha256: "{{ istio_mixer_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  istio_pilot:
+    enabled: "{{ istio_enabled }}"
+    container: true
+    repo: "{{ istio_pilot_image_repo }}"
+    tag: "{{ istio_pilot_image_tag }}"
+    sha256: "{{ istio_pilot_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  istio_proxy_debug:
+    enabled: "{{ istio_enabled }}"
+    container: true
+    repo: "{{ istio_proxy_debug_image_repo }}"
+    tag: "{{ istio_proxy_debug_image_tag }}"
+    sha256: "{{ istio_proxy_debug_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  istio_sidecar_initializer:
+    enabled: "{{ istio_enabled }}"
+    container: true
+    repo: "{{ istio_sidecar_initializer_image_repo }}"
+    tag: "{{ istio_sidecar_initializer_image_tag }}"
+    sha256: "{{ istio_sidecar_initializer_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  istio_statsd:
+    enabled: "{{ istio_enabled }}"
+    container: true
+    repo: "{{ istio_statsd_image_repo }}"
+    tag: "{{ istio_statsd_image_tag }}"
+    sha256: "{{ istio_statsd_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   hyperkube:
     enabled: true
     container: true
     repo: "{{ hyperkube_image_repo }}"
     tag: "{{ hyperkube_image_tag }}"
     sha256: "{{ hyperkube_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   cilium:
     enabled: "{{ kube_network_plugin == 'cilium' }}"
     container: true
     repo: "{{ cilium_image_repo }}"
     tag: "{{ cilium_image_tag }}"
     sha256: "{{ cilium_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   flannel:
     enabled: "{{ kube_network_plugin == 'flannel' or kube_network_plugin == 'canal' }}"
     container: true
     repo: "{{ flannel_image_repo }}"
     tag: "{{ flannel_image_tag }}"
     sha256: "{{ flannel_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   flannel_cni:
     enabled: "{{ kube_network_plugin == 'flannel' }}"
     container: true
     repo: "{{ flannel_cni_image_repo }}"
     tag: "{{ flannel_cni_image_tag }}"
     sha256: "{{ flannel_cni_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   calicoctl:
     enabled: "{{ kube_network_plugin == 'calico' or kube_network_plugin == 'canal' }}"
     container: true
     repo: "{{ calicoctl_image_repo }}"
     tag: "{{ calicoctl_image_tag }}"
     sha256: "{{ calicoctl_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   calico_node:
     enabled: "{{ kube_network_plugin == 'calico' or kube_network_plugin == 'canal' }}"
     container: true
     repo: "{{ calico_node_image_repo }}"
     tag: "{{ calico_node_image_tag }}"
     sha256: "{{ calico_node_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   calico_cni:
     enabled: "{{ kube_network_plugin == 'calico' or kube_network_plugin == 'canal' }}"
     container: true
     repo: "{{ calico_cni_image_repo }}"
     tag: "{{ calico_cni_image_tag }}"
     sha256: "{{ calico_cni_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   calico_policy:
     enabled: "{{ enable_network_policy or kube_network_plugin == 'canal' }}"
     container: true
     repo: "{{ calico_policy_image_repo }}"
     tag: "{{ calico_policy_image_tag }}"
     sha256: "{{ calico_policy_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   calico_rr:
-    enabled: "{{ peer_with_calico_rr is defined and peer_with_calico_rr}} and kube_network_plugin == 'calico'"
+    enabled: "{{ peer_with_calico_rr is defined and peer_with_calico_rr and kube_network_plugin == 'calico' }}"
     container: true
     repo: "{{ calico_rr_image_repo }}"
     tag: "{{ calico_rr_image_tag }}"
     sha256: "{{ calico_rr_digest_checksum|default(None) }}"
+    groups:
+      - calico-rr
   weave_kube:
     enabled: "{{ kube_network_plugin == 'weave' }}"
     container: true
     repo: "{{ weave_kube_image_repo }}"
     tag: "{{ weave_kube_image_tag }}"
     sha256: "{{ weave_kube_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   weave_npc:
     enabled: "{{ kube_network_plugin == 'weave' }}"
     container: true
     repo: "{{ weave_npc_image_repo }}"
     tag: "{{ weave_npc_image_tag }}"
     sha256: "{{ weave_npc_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   contiv:
     enabled: "{{ kube_network_plugin == 'contiv' }}"
     container: true
     repo: "{{ contiv_image_repo }}"
     tag: "{{ contiv_image_tag }}"
     sha256: "{{ contiv_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   contiv_auth_proxy:
     enabled: "{{ kube_network_plugin == 'contiv' }}"
     container: true
     repo: "{{ contiv_auth_proxy_image_repo }}"
     tag: "{{ contiv_auth_proxy_image_tag }}"
     sha256: "{{ contiv_auth_proxy_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   pod_infra:
     enabled: true
     container: true
     repo: "{{ pod_infra_image_repo }}"
     tag: "{{ pod_infra_image_tag }}"
     sha256: "{{ pod_infra_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   install_socat:
     enabled: "{{ ansible_os_family in ['CoreOS', 'Container Linux by CoreOS'] }}"
     container: true
     repo: "{{ install_socat_image_repo }}"
     tag: "{{ install_socat_image_tag }}"
     sha256: "{{ install_socat_digest_checksum|default(None) }}"
+    groups:
+      - k8s-cluster
   nginx:
-    enabled: true
+    enabled: "{{ loadbalancer_apiserver_localhost }}"
     container: true
     repo: "{{ nginx_image_repo }}"
     tag: "{{ nginx_image_tag }}"
     sha256: "{{ nginx_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   dnsmasq:
     enabled: "{{ dns_mode == 'dnsmasq_kubedns' }}"
     container: true
     repo: "{{ dnsmasq_image_repo }}"
     tag: "{{ dnsmasq_image_tag }}"
     sha256: "{{ dnsmasq_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   kubedns:
-    enabled: true
+    enabled: "{{ dns_mode in ['kubedns', 'dnsmasq_kubedns'] }}"
     container: true
     repo: "{{ kubedns_image_repo }}"
     tag: "{{ kubedns_image_tag }}"
     sha256: "{{ kubedns_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  coredns:
+    enabled: "{{ dns_mode in ['coredns', 'coredns_dual'] }}"
+    container: true
+    repo: "{{ coredns_image_repo }}"
+    tag: "{{ coredns_image_tag }}"
+    sha256: "{{ coredns_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   dnsmasq_nanny:
-    enabled: true
+    enabled: "{{ dns_mode in ['kubedns', 'dnsmasq_kubedns'] }}"
     container: true
     repo: "{{ dnsmasq_nanny_image_repo }}"
     tag: "{{ dnsmasq_nanny_image_tag }}"
     sha256: "{{ dnsmasq_nanny_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   dnsmasq_sidecar:
-    enabled: true
+    enabled: "{{ dns_mode in ['kubedns', 'dnsmasq_kubedns'] }}"
     container: true
     repo: "{{ dnsmasq_sidecar_image_repo }}"
     tag: "{{ dnsmasq_sidecar_image_tag }}"
     sha256: "{{ dnsmasq_sidecar_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   kubednsautoscaler:
-    enabled: true
+    enabled: "{{ dns_mode in ['kubedns', 'dnsmasq_kubedns'] }}"
     container: true
     repo: "{{ kubednsautoscaler_image_repo }}"
     tag: "{{ kubednsautoscaler_image_tag }}"
     sha256: "{{ kubednsautoscaler_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   testbox:
-    enabled: true
+    enabled: false
     container: true
     repo: "{{ test_image_repo }}"
     tag: "{{ test_image_tag }}"
@@ -309,30 +467,40 @@ downloads:
     repo: "{{ elasticsearch_image_repo }}"
     tag: "{{ elasticsearch_image_tag }}"
     sha256: "{{ elasticsearch_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   fluentd:
     enabled: "{{ efk_enabled }}"
     container: true
     repo: "{{ fluentd_image_repo }}"
     tag: "{{ fluentd_image_tag }}"
     sha256: "{{ fluentd_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   kibana:
     enabled: "{{ efk_enabled }}"
     container: true
     repo: "{{ kibana_image_repo }}"
     tag: "{{ kibana_image_tag }}"
     sha256: "{{ kibana_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   helm:
     enabled: "{{ helm_enabled }}"
     container: true
     repo: "{{ helm_image_repo }}"
     tag: "{{ helm_image_tag }}"
     sha256: "{{ helm_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   tiller:
     enabled: "{{ helm_enabled }}"
     container: true
     repo: "{{ tiller_image_repo }}"
     tag: "{{ tiller_image_tag }}"
     sha256: "{{ tiller_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
   vault:
     enabled: "{{ cert_management == 'vault' }}"
     container: "{{ vault_deployment_type != 'host' }}"
@@ -347,6 +515,72 @@ downloads:
     unarchive: true
     url: "{{ vault_download_url }}"
     version: "{{ vault_version }}"
+    groups:
+      - vault
+  registry:
+    enabled: "{{ registry_enabled }}"
+    container: true
+    repo: "{{ registry_image_repo }}"
+    tag: "{{ registry_image_tag }}"
+    sha256: "{{ registry_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  registry_proxy:
+    enabled: "{{ registry_enabled }}"
+    container: true
+    repo: "{{ registry_proxy_image_repo }}"
+    tag: "{{ registry_proxy_image_tag }}"
+    sha256: "{{ registry_proxy_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  local_volume_provisioner:
+    enabled: "{{ local_volume_provisioner_enabled }}"
+    container: true
+    repo: "{{ local_volume_provisioner_image_repo }}"
+    tag: "{{ local_volume_provisioner_image_tag }}"
+    sha256: "{{ local_volume_provisioner_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  cephfs_provisioner:
+    enabled: "{{ cephfs_provisioner_enabled }}"
+    container: true
+    repo: "{{ cephfs_provisioner_image_repo }}"
+    tag: "{{ cephfs_provisioner_image_tag }}"
+    sha256: "{{ cephfs_provisioner_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  ingress_nginx_controller:
+    enabled: "{{ ingress_nginx_enabled }}"
+    container: true
+    repo: "{{ ingress_nginx_controller_image_repo }}"
+    tag: "{{ ingress_nginx_controller_image_tag }}"
+    sha256: "{{ ingress_nginx_controller_digest_checksum|default(None) }}"
+    groups:
+      - kube-ingress
+  ingress_nginx_default_backend:
+    enabled: "{{ ingress_nginx_enabled }}"
+    container: true
+    repo: "{{ ingress_nginx_default_backend_image_repo }}"
+    tag: "{{ ingress_nginx_default_backend_image_tag }}"
+    sha256: "{{ ingress_nginx_default_backend_digest_checksum|default(None) }}"
+    groups:
+      - kube-ingress
+  cert_manager_controller:
+    enabled: "{{ cert_manager_enabled }}"
+    container: true
+    repo: "{{ cert_manager_controller_image_repo }}"
+    tag: "{{ cert_manager_controller_image_tag }}"
+    sha256: "{{ cert_manager_controller_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
+  cert_manager_ingress_shim:
+    enabled: "{{ cert_manager_enabled }}"
+    container: true
+    repo: "{{ cert_manager_ingress_shim_image_repo }}"
+    tag: "{{ cert_manager_ingress_shim_image_tag }}"
+    sha256: "{{ cert_manager_ingress_shim_digest_checksum|default(None) }}"
+    groups:
+      - kube-node
 
 download_defaults:
   container: false

roles/download/tasks/download_container.yml

@@ -7,6 +7,7 @@
   when:
     - download.enabled
     - download.container
+    - group_names | intersect(download.groups) | length
   tags:
     - facts
 
@@ -23,6 +24,7 @@
     - download.enabled
     - download.container
     - pull_required|default(download_always_pull)
+    - group_names | intersect(download.groups) | length
   delegate_to: "{{ download_delegate }}"
   delegate_facts: yes
   run_once: yes
@@ -38,3 +40,4 @@
     - download.enabled
     - download.container
     - pull_required|default(download_always_pull)
+    - group_names | intersect(download.groups) | length

roles/download/tasks/download_file.yml

@@ -13,6 +13,7 @@
   when:
     - download.enabled
     - download.file
+    - group_names | intersect(download.groups) | length
 
 - name: file_download | Download item
   get_url:
@@ -28,6 +29,7 @@
   when:
     - download.enabled
     - download.file
+    - group_names | intersect(download.groups) | length
 
 - name: file_download | Extract archives
   unarchive:
@@ -40,3 +42,4 @@
     - download.enabled
     - download.file
     - download.unarchive|default(False)
+    - group_names | intersect(download.groups) | length

roles/download/tasks/sync_container.yml

@@ -7,6 +7,7 @@
   when:
     - download.enabled
     - download.container
+    - group_names | intersect(download.groups) | length
   tags:
     - facts
 
@@ -17,6 +18,7 @@
     - download.enabled
     - download.container
     - download_run_once
+    - group_names | intersect(download.groups) | length
   tags:
     - facts
 
@@ -27,6 +29,7 @@
     - download.enabled
     - download.container
     - download_run_once
+    - group_names | intersect(download.groups) | length
 
 - name: "container_download | Update the 'container_changed' fact"
   set_fact:
@@ -36,6 +39,7 @@
     - download.container
     - download_run_once
     - pull_required|default(download_always_pull)
+    - group_names | intersect(download.groups) | length
   run_once: "{{ download_run_once }}"
   tags:
     - facts
@@ -53,6 +57,7 @@
     - download.enabled
     - download.container
     - download_run_once
+    - group_names | intersect(download.groups) | length
   tags:
     - facts
 
@@ -68,6 +73,7 @@
     - download_run_once
     - (ansible_os_family not in ["CoreOS", "Container Linux by CoreOS"] or download_delegate == "localhost")
     - (container_changed or not img.stat.exists)
+    - group_names | intersect(download.groups) | length
 
 - name: container_download | copy container images to ansible host
   synchronize:
@@ -87,6 +93,7 @@
     - inventory_hostname == download_delegate
     - download_delegate != "localhost"
     - saved.changed
+    - group_names | intersect(download.groups) | length
 
 - name: container_download | upload container images to nodes
   synchronize:
@@ -108,6 +115,7 @@
     - (ansible_os_family not in ["CoreOS", "Container Linux by CoreOS"] and
       inventory_hostname != download_delegate or
       download_delegate == "localhost")
+    - group_names | intersect(download.groups) | length
   tags:
     - upload
     - upgrade
@@ -120,6 +128,7 @@
     - download_run_once
     - (ansible_os_family not in ["CoreOS", "Container Linux by CoreOS"] and
       inventory_hostname != download_delegate or download_delegate == "localhost")
+    - group_names | intersect(download.groups) | length
   tags:
     - upload
     - upgrade

roles/etcd/defaults/main.yml

@@ -4,6 +4,7 @@ etcd_cluster_setup: true
 
 etcd_backup_prefix: "/var/backups"
 etcd_data_dir: "/var/lib/etcd"
+etcd_events_data_dir: "/var/lib/etcd-events"
 
 etcd_config_dir: /etc/ssl/etcd
 etcd_cert_dir: "{{ etcd_config_dir }}/ssl"
@@ -11,9 +12,9 @@ etcd_cert_group: root
 # Note: This does not set up DNS entries. It simply adds the following DNS
 # entries to the certificate
 etcd_cert_alt_names:
-  - "etcd.{{ system_namespace }}.svc.{{ dns_domain }}"
+  - "etcd.kube-system.svc.{{ dns_domain }}"
-  - "etcd.{{ system_namespace }}.svc"
+  - "etcd.kube-system.svc"
-  - "etcd.{{ system_namespace }}"
+  - "etcd.kube-system"
   - "etcd"
 
 etcd_script_dir: "{{ bin_dir }}/etcd-scripts"
@@ -21,6 +22,13 @@ etcd_script_dir: "{{ bin_dir }}/etcd-scripts"
 etcd_heartbeat_interval: "250"
 etcd_election_timeout: "5000"
 
+# etcd_snapshot_count: "10000"
+
+# Parameters for ionice
+# -c takes an integer between 0 and 3 or one of the strings none, realtime, best-effort or idle.
+# -n takes an integer between 0 (highest priority) and 7 (lowest priority)
+# etcd_ionice: "-c2 -n0"
+
 etcd_metrics: "basic"
 
 # Limits

roles/etcd/files/make-ssl-etcd.sh

@@ -65,7 +65,7 @@ if [ -e "$SSLDIR/ca-key.pem" ]; then
     cp $SSLDIR/{ca.pem,ca-key.pem} .
 else
     openssl genrsa -out ca-key.pem 2048 > /dev/null 2>&1
-    openssl req -x509 -new -nodes -key ca-key.pem -days 10000 -out ca.pem -subj "/CN=etcd-ca" > /dev/null 2>&1
+    openssl req -x509 -new -nodes -key ca-key.pem -days 36500 -out ca.pem -subj "/CN=etcd-ca" > /dev/null 2>&1
 fi
 
 # ETCD member
@@ -75,12 +75,12 @@ if [ -n "$MASTERS" ]; then
         # Member key
         openssl genrsa -out member-${host}-key.pem 2048 > /dev/null 2>&1
         openssl req -new -key member-${host}-key.pem -out member-${host}.csr -subj "/CN=etcd-member-${cn}" -config ${CONFIG} > /dev/null 2>&1
-        openssl x509 -req -in member-${host}.csr -CA ca.pem -CAkey ca-key.pem -CAcreateserial -out member-${host}.pem -days 3650 -extensions ssl_client -extfile ${CONFIG} > /dev/null 2>&1
+        openssl x509 -req -in member-${host}.csr -CA ca.pem -CAkey ca-key.pem -CAcreateserial -out member-${host}.pem -days 36500 -extensions ssl_client -extfile ${CONFIG} > /dev/null 2>&1
 
         # Admin key
         openssl genrsa -out admin-${host}-key.pem 2048 > /dev/null 2>&1
         openssl req -new -key admin-${host}-key.pem -out admin-${host}.csr -subj "/CN=etcd-admin-${cn}" > /dev/null 2>&1
-        openssl x509 -req -in admin-${host}.csr -CA ca.pem -CAkey ca-key.pem -CAcreateserial -out admin-${host}.pem -days 3650 -extensions ssl_client  -extfile ${CONFIG} > /dev/null 2>&1
+        openssl x509 -req -in admin-${host}.csr -CA ca.pem -CAkey ca-key.pem -CAcreateserial -out admin-${host}.pem -days 36500 -extensions ssl_client  -extfile ${CONFIG} > /dev/null 2>&1
     done
 fi
 
@@ -90,7 +90,7 @@ if [ -n "$HOSTS" ]; then
         cn="${host%%.*}"
         openssl genrsa -out node-${host}-key.pem 2048 > /dev/null 2>&1
         openssl req -new -key node-${host}-key.pem -out node-${host}.csr -subj "/CN=etcd-node-${cn}" > /dev/null 2>&1
-        openssl x509 -req -in node-${host}.csr -CA ca.pem -CAkey ca-key.pem -CAcreateserial -out node-${host}.pem -days 3650 -extensions ssl_client  -extfile ${CONFIG} > /dev/null 2>&1
+        openssl x509 -req -in node-${host}.csr -CA ca.pem -CAkey ca-key.pem -CAcreateserial -out node-${host}.pem -days 36500 -extensions ssl_client  -extfile ${CONFIG} > /dev/null 2>&1
     done
 fi
 

roles/etcd/handlers/backup.yml

@@ -48,7 +48,7 @@
       snapshot save {{ etcd_backup_directory }}/snapshot.db
   environment:
     ETCDCTL_API: 3
-    ETCDCTL_CERT: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}.pem"
+    ETCDCTL_CERT: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
-    ETCDCTL_KEY: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}-key.pem"
+    ETCDCTL_KEY: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
   retries: 3
   delay: "{{ retry_stagger | random + 3 }}"

roles/etcd/handlers/main.yml

@@ -7,17 +7,33 @@
     - reload etcd
     - wait for etcd up
 
+- name: restart etcd-events
+  command: /bin/true
+  notify:
+    - etcd-events | reload systemd
+    - reload etcd-events
+    - wait for etcd-events up
+
 - import_tasks: backup.yml
 
 - name: etcd | reload systemd
   command: systemctl daemon-reload
 
+- name: etcd-events | reload systemd
+  command: systemctl daemon-reload
+
 - name: reload etcd
   service:
     name: etcd
     state: restarted
   when: is_etcd_master
 
+- name: reload etcd-events
+  service:
+    name: etcd-events
+    state: restarted
+  when: is_etcd_master
+
 - name: wait for etcd up
   uri:
     url: "https://{% if is_etcd_master %}{{ etcd_address }}{% else %}127.0.0.1{% endif %}:2379/health"
@@ -29,6 +45,17 @@
   retries: 10
   delay: 5
 
+- name: wait for etcd-events up
+  uri:
+    url: "https://{% if is_etcd_master %}{{ etcd_address }}{% else %}127.0.0.1{% endif %}:2381/health"
+    validate_certs: no
+    client_cert: "{{ etcd_cert_dir }}/member-{{ inventory_hostname }}.pem"
+    client_key: "{{ etcd_cert_dir }}/member-{{ inventory_hostname }}-key.pem"
+  register: result
+  until: result.status is defined and result.status == 200
+  retries: 10
+  delay: 5
+
 - name: set etcd_secret_changed
   set_fact:
     etcd_secret_changed: true

roles/etcd/tasks/configure.yml

@@ -1,5 +1,5 @@
 ---
-- name: Configure | Check if member is in cluster
+- name: Configure | Check if member is in etcd cluster
   shell: "{{ bin_dir }}/etcdctl --no-sync --endpoints={{ etcd_access_addresses }} member list | grep -q {{ etcd_access_address }}"
   register: etcd_member_in_cluster
   ignore_errors: true
@@ -9,8 +9,21 @@
   tags:
     - facts
   environment:
-    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}.pem"
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
-    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}-key.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
+
+- name: Configure | Check if member is in etcd-events cluster
+  shell: "{{ bin_dir }}/etcdctl --no-sync --endpoints={{ etcd_events_access_addresses }} member list | grep -q {{ etcd_access_address }}"
+  register: etcd_events_member_in_cluster
+  ignore_errors: true
+  changed_when: false
+  check_mode: no
+  when: is_etcd_master and etcd_events_cluster_setup
+  tags:
+    - facts
+  environment:
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
 
 - name: Configure | Copy etcd.service systemd file
   template:
@@ -20,11 +33,36 @@
   when: is_etcd_master
   notify: restart etcd
 
-- name: Configure | Join member(s) to cluster one at a time
+- name: Configure | Copy etcd-events.service systemd file
-  include_tasks: join_member.yml
+  template:
+    src: "etcd-events-host.service.j2"
+    dest: /etc/systemd/system/etcd-events.service
+    backup: yes
+  when: is_etcd_master and etcd_deployment_type == "host" and etcd_events_cluster_setup
+  notify: restart etcd-events
+
+- name: Configure | Copy etcd-events.service systemd file
+  template:
+    src: "etcd-events-docker.service.j2"
+    dest: /etc/systemd/system/etcd-events.service
+    backup: yes
+  when: is_etcd_master and etcd_deployment_type == "docker" and etcd_events_cluster_setup
+  notify: restart etcd-events
+
+- name: Configure | Join member(s) to etcd cluster one at a time
+  include_tasks: join_etcd_member.yml
   vars:
     target_node: "{{ item }}"
   loop_control:
     pause: 10
   with_items: "{{ groups['etcd'] }}"
   when: inventory_hostname == item and etcd_member_in_cluster.rc != 0 and etcd_cluster_is_healthy.rc == 0
+
+- name: Configure | Join member(s) to etcd-events cluster one at a time
+  include_tasks: join_etcd-evetns_member.yml
+  vars:
+    target_node: "{{ item }}"
+  loop_control:
+    pause: 10
+  with_items: "{{ groups['etcd'] }}"
+  when: inventory_hostname == item and etcd_events_cluster_setup and etcd_events_member_in_cluster.rc != 0 and etcd_events_cluster_is_healthy.rc == 0

roles/etcd/tasks/install_docker.yml

@@ -18,3 +18,13 @@
     mode: 0755
     backup: yes
   notify: restart etcd
+
+- name: Install etcd-events launch script
+  template:
+    src: etcd-events.j2
+    dest: "{{ bin_dir }}/etcd-events"
+    owner: 'root'
+    mode: 0755
+    backup: yes
+  when: etcd_events_cluster_setup
+  notify: restart etcd-events

roles/etcd/tasks/join_etcd-events_member.yml

@@ -0,0 +1,47 @@
+---
+- name: Join Member | Add member to cluster
+  shell: "{{ bin_dir }}/etcdctl --endpoints={{ etcd_events_access_addresses }} member add {{ etcd_member_name }} {{ etcd_events_peer_url }}"
+  register: member_add_result
+  until: member_add_result.rc == 0
+  retries: 4
+  delay: "{{ retry_stagger | random + 3 }}"
+  when: target_node == inventory_hostname
+  environment:
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
+
+- include_tasks: refresh_config.yml
+  vars:
+    etcd_events_peer_addresses: >-
+      {% for host in groups['etcd'] -%}
+        {%- if hostvars[host]['etcd_events_member_in_cluster'].rc == 0 -%}
+          {{ "etcd"+loop.index|string }}=https://{{ hostvars[host].access_ip | default(hostvars[host].ip | default(hostvars[host].ansible_default_ipv4['address'])) }}:2382,
+        {%- endif -%}
+        {%- if loop.last -%}
+          {{ etcd_member_name }}={{ etcd_events_peer_url }}
+        {%- endif -%}
+      {%- endfor -%}
+  when: target_node == inventory_hostname
+
+- name: Join Member | reload systemd
+  command: systemctl daemon-reload
+  when: target_node == inventory_hostname
+
+- name: Join Member | Ensure etcd-events is running
+  service:
+    name: etcd-events
+    state: started
+    enabled: yes
+  when: target_node == inventory_hostname
+
+- name: Join Member | Ensure member is in etcd-events cluster
+  shell: "{{ bin_dir }}/etcdctl --no-sync --endpoints={{ etcd_events_access_addresses }} member list | grep -q {{ etcd_events_access_address }}"
+  register: etcd_events_member_in_cluster
+  changed_when: false
+  check_mode: no
+  tags:
+    - facts
+  when: target_node == inventory_hostname
+  environment:
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"

roles/etcd/tasks/join_etcd_member.yml

@@ -0,0 +1,47 @@
+---
+- name: Join Member | Add member to cluster
+  shell: "{{ bin_dir }}/etcdctl --endpoints={{ etcd_access_addresses }} member add {{ etcd_member_name }} {{ etcd_peer_url }}"
+  register: member_add_result
+  until: member_add_result.rc == 0
+  retries: 4
+  delay: "{{ retry_stagger | random + 3 }}"
+  when: target_node == inventory_hostname
+  environment:
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
+
+- include_tasks: refresh_config.yml
+  vars:
+    etcd_peer_addresses: >-
+      {% for host in groups['etcd'] -%}
+        {%- if hostvars[host]['etcd_member_in_cluster'].rc == 0 -%}
+          {{ "etcd"+loop.index|string }}=https://{{ hostvars[host].access_ip | default(hostvars[host].ip | default(hostvars[host].ansible_default_ipv4['address'])) }}:2380,
+        {%- endif -%}
+        {%- if loop.last -%}
+          {{ etcd_member_name }}={{ etcd_peer_url }}
+        {%- endif -%}
+      {%- endfor -%}
+  when: target_node == inventory_hostname
+
+- name: Join Member | reload systemd
+  command: systemctl daemon-reload
+  when: target_node == inventory_hostname
+
+- name: Join Member | Ensure etcd is running
+  service:
+    name: etcd
+    state: started
+    enabled: yes
+  when: target_node == inventory_hostname
+
+- name: Join Member | Ensure member is in cluster
+  shell: "{{ bin_dir }}/etcdctl --no-sync --endpoints={{ etcd_access_addresses }} member list | grep -q {{ etcd_access_address }}"
+  register: etcd_member_in_cluster
+  changed_when: false
+  check_mode: no
+  tags:
+    - facts
+  when: target_node == inventory_hostname
+  environment:
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"

roles/etcd/tasks/join_member.yml

@@ -7,8 +7,8 @@
   delay: "{{ retry_stagger | random + 3 }}"
   when: target_node == inventory_hostname
   environment:
-    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}.pem"
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
-    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}-key.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
 
 - include_tasks: refresh_config.yml
   vars:
@@ -43,5 +43,5 @@
     - facts
   when: target_node == inventory_hostname
   environment:
-    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}.pem"
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
-    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}-key.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"

roles/etcd/tasks/main.yml

@@ -29,13 +29,13 @@
   tags:
     - upgrade
 
-- import_tasks: set_cluster_health.yml
+- include_tasks: set_cluster_health.yml
   when: is_etcd_master and etcd_cluster_setup
 
-- import_tasks: configure.yml
+- include_tasks: configure.yml
   when: is_etcd_master and etcd_cluster_setup
 
-- import_tasks: refresh_config.yml
+- include_tasks: refresh_config.yml
   when: is_etcd_master and etcd_cluster_setup
 
 - name: Restart etcd if certs changed
@@ -43,6 +43,11 @@
   notify: restart etcd
   when: is_etcd_master and etcd_secret_changed|default(false)
 
+- name: Restart etcd-events if certs changed
+  command: /bin/true
+  notify: restart etcd
+  when: is_etcd_master and etcd_events_cluster_setup and etcd_secret_changed|default(false)
+
 # reload-systemd
 - meta: flush_handlers
 
@@ -53,11 +58,18 @@
     enabled: yes
   when: is_etcd_master and etcd_cluster_setup
 
+- name: Ensure etcd-events is running
+  service:
+    name: etcd-events
+    state: started
+    enabled: yes
+  when: is_etcd_master and etcd_events_cluster_setup
+
 # After etcd cluster is assembled, make sure that
 # initial state of the cluster is in `existing`
 # state insted of `new`.
-- import_tasks: set_cluster_health.yml
+- include_tasks: set_cluster_health.yml
   when: is_etcd_master and etcd_cluster_setup
 
-- import_tasks: refresh_config.yml
+- include_tasks: refresh_config.yml
   when: is_etcd_master and etcd_cluster_setup

roles/etcd/tasks/refresh_config.yml

@@ -5,3 +5,10 @@
     dest: /etc/etcd.env
   notify: restart etcd
   when: is_etcd_master
+
+- name: Refresh config | Create etcd-events config file
+  template:
+    src: etcd-events.env.j2
+    dest: /etc/etcd-events.env
+  notify: restart etcd-events
+  when: is_etcd_master and etcd_events_cluster_setup

roles/etcd/tasks/set_cluster_health.yml

@@ -1,5 +1,5 @@
 ---
-- name: Configure | Check if cluster is healthy
+- name: Configure | Check if etcd cluster is healthy
   shell: "{{ bin_dir }}/etcdctl --endpoints={{ etcd_access_addresses }} cluster-health | grep -q 'cluster is healthy'"
   register: etcd_cluster_is_healthy
   ignore_errors: true
@@ -9,5 +9,18 @@
   tags:
     - facts
   environment:
-    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}.pem"
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
-    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}-key.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"
+
+- name: Configure | Check if etcd-events cluster is healthy
+  shell: "{{ bin_dir }}/etcdctl --endpoints={{ etcd_events_access_addresses }} cluster-health | grep -q 'cluster is healthy'"
+  register: etcd_events_cluster_is_healthy
+  ignore_errors: true
+  changed_when: false
+  check_mode: no
+  when: is_etcd_master and etcd_events_cluster_setup
+  tags:
+    - facts
+  environment:
+    ETCDCTL_CERT_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}.pem"
+    ETCDCTL_KEY_FILE: "{{ etcd_cert_dir }}/admin-{{ inventory_hostname }}-key.pem"

roles/etcd/templates/etcd-events-docker.service.j2

@@ -0,0 +1,18 @@
+[Unit]
+Description=etcd docker wrapper
+Wants=docker.socket
+After=docker.service
+
+[Service]
+User=root
+PermissionsStartOnly=true
+EnvironmentFile=-/etc/etcd-events.env
+ExecStart={{ bin_dir }}/etcd-events
+ExecStartPre=-{{ docker_bin_dir }}/docker rm -f {{ etcd_member_name }}-events
+ExecStop={{ docker_bin_dir }}/docker stop {{ etcd_member_name }}-events
+Restart=always
+RestartSec=15s
+TimeoutStartSec=30s
+
+[Install]
+WantedBy=multi-user.target

roles/etcd/templates/etcd-events-host.service.j2

@@ -0,0 +1,16 @@
+[Unit]
+Description=etcd
+After=network.target
+
+[Service]
+Type=notify
+User=root
+EnvironmentFile=/etc/etcd-events.env
+ExecStart={{ bin_dir }}/etcd
+NotifyAccess=all
+Restart=always
+RestartSec=10s
+LimitNOFILE=40000
+
+[Install]
+WantedBy=multi-user.target

roles/etcd/templates/etcd-events.env.j2

@@ -0,0 +1,29 @@
+ETCD_DATA_DIR={{ etcd_events_data_dir }}
+ETCD_ADVERTISE_CLIENT_URLS={{ etcd_events_client_url }}
+ETCD_INITIAL_ADVERTISE_PEER_URLS={{ etcd_events_peer_url }}
+ETCD_INITIAL_CLUSTER_STATE={% if etcd_cluster_is_healthy.rc != 0 | bool %}new{% else %}existing{% endif %}
+
+ETCD_METRICS={{ etcd_metrics }}
+ETCD_LISTEN_CLIENT_URLS=https://{{ etcd_address }}:2381,https://127.0.0.1:2381
+ETCD_ELECTION_TIMEOUT={{ etcd_election_timeout }}
+ETCD_HEARTBEAT_INTERVAL={{ etcd_heartbeat_interval }}
+ETCD_INITIAL_CLUSTER_TOKEN=k8s_events_etcd
+ETCD_LISTEN_PEER_URLS=https://{{ etcd_address }}:2382
+ETCD_NAME={{ etcd_member_name }}-events
+ETCD_PROXY=off
+ETCD_INITIAL_CLUSTER={{ etcd_events_peer_addresses }}
+ETCD_AUTO_COMPACTION_RETENTION={{ etcd_compaction_retention }}
+{% if etcd_snapshot_count is defined %}
+ETCD_SNAPSHOT_COUNT={{ etcd_snapshot_count }}
+{% endif %}
+
+# TLS settings
+ETCD_TRUSTED_CA_FILE={{ etcd_cert_dir }}/ca.pem
+ETCD_CERT_FILE={{ etcd_cert_dir }}/member-{{ inventory_hostname }}.pem
+ETCD_KEY_FILE={{ etcd_cert_dir }}/member-{{ inventory_hostname }}-key.pem
+ETCD_CLIENT_CERT_AUTH={{ etcd_secure_client | lower}}
+
+ETCD_PEER_TRUSTED_CA_FILE={{ etcd_cert_dir }}/ca.pem
+ETCD_PEER_CERT_FILE={{ etcd_cert_dir }}/member-{{ inventory_hostname }}.pem
+ETCD_PEER_KEY_FILE={{ etcd_cert_dir }}/member-{{ inventory_hostname }}-key.pem
+ETCD_PEER_CLIENT_CERT_AUTH={{ etcd_peer_client_auth }}

roles/etcd/templates/etcd-events.j2

@@ -0,0 +1,21 @@
+#!/bin/bash
+{{ docker_bin_dir }}/docker run \
+  --restart=on-failure:5 \
+  --env-file=/etc/etcd-events.env \
+  --net=host \
+  -v /etc/ssl/certs:/etc/ssl/certs:ro \
+  -v {{ etcd_cert_dir }}:{{ etcd_cert_dir }}:ro \
+  -v {{ etcd_events_data_dir }}:{{ etcd_events_data_dir }}:rw \
+  {% if etcd_memory_limit is defined %}
+  --memory={{ etcd_memory_limit|regex_replace('Mi', 'M') }} \
+  {% endif %}
+  {% if etcd_cpu_limit is defined %}
+  --cpu-shares={{ etcd_cpu_limit|regex_replace('m', '') }} \
+  {% endif %}
+  {% if etcd_blkio_weight is defined %}
+  --blkio-weight={{ etcd_blkio_weight }} \
+  {% endif %}
+  --name={{ etcd_member_name }}-events \
+  {{ etcd_image_repo }}:{{ etcd_image_tag }} \
+  /usr/local/bin/etcd \
+  "$@"

roles/etcd/templates/etcd.env.j2

@@ -13,6 +13,9 @@ ETCD_NAME={{ etcd_member_name }}
 ETCD_PROXY=off
 ETCD_INITIAL_CLUSTER={{ etcd_peer_addresses }}
 ETCD_AUTO_COMPACTION_RETENTION={{ etcd_compaction_retention }}
+{% if etcd_snapshot_count is defined %}
+ETCD_SNAPSHOT_COUNT={{ etcd_snapshot_count }}
+{% endif %}
 
 # TLS settings
 ETCD_TRUSTED_CA_FILE={{ etcd_cert_dir }}/ca.pem

roles/etcd/templates/etcd.j2

@@ -6,17 +6,19 @@
   -v /etc/ssl/certs:/etc/ssl/certs:ro \
   -v {{ etcd_cert_dir }}:{{ etcd_cert_dir }}:ro \
   -v {{ etcd_data_dir }}:{{ etcd_data_dir }}:rw \
-  {% if etcd_memory_limit is defined %}
+{% if etcd_memory_limit is defined %}
   --memory={{ etcd_memory_limit|regex_replace('Mi', 'M') }} \
-  {% endif %}
+{% endif %}
-  --oom-kill-disable \
+{% if etcd_cpu_limit is defined %}
-  {% if etcd_cpu_limit is defined %}
   --cpu-shares={{ etcd_cpu_limit|regex_replace('m', '') }} \
-  {% endif %}
+{% endif %}
-  {% if etcd_blkio_weight is defined %}
+{% if etcd_blkio_weight is defined %}
   --blkio-weight={{ etcd_blkio_weight }} \
-  {% endif %}
+{% endif %}
   --name={{ etcd_member_name | default("etcd") }} \
   {{ etcd_image_repo }}:{{ etcd_image_tag }} \
+{% if etcd_ionice is defined %}
+  /bin/ionice {{ etcd_ionice }} \
+{% endif %}
   /usr/local/bin/etcd \
   "$@"

roles/etcd/templates/openssl.conf.j2

@@ -1,4 +1,4 @@
-[req]
+{% set counter = {'dns': 2,'ip': 1,} %}{% macro increment(dct, key, inc=1)%}{% if dct.update({key: dct[key] + inc}) %} {% endif %}{% endmacro %}[req]
 req_extensions = v3_req
 distinguished_name = req_distinguished_name
 
@@ -25,19 +25,18 @@ authorityKeyIdentifier=keyid:always,issuer
 [alt_names]
 DNS.1 = localhost
 {% for host in groups['etcd'] %}
-DNS.{{ 1 + loop.index }} = {{ host }}
+DNS.{{ counter["dns"] }} = {{ host }}{{ increment(counter, 'dns') }}
 {% endfor %}
-{% if loadbalancer_apiserver is defined %}
+{% if apiserver_loadbalancer_domain_name is defined %}
-{% set idx =  groups['etcd'] | length | int + 2 %}
+DNS.{{ counter["dns"] }} = {{ apiserver_loadbalancer_domain_name }}{{ increment(counter, 'dns') }}
-DNS.{{ idx | string }} = {{ apiserver_loadbalancer_domain_name }}
 {% endif %}
-{% set idx =  groups['etcd'] | length | int + 3 %}
 {% for etcd_alt_name in etcd_cert_alt_names %}
-DNS.{{ idx + 1 + loop.index }} = {{ etcd_alt_name }}
+DNS.{{ counter["dns"] }} = {{ etcd_alt_name }}{{ increment(counter, 'dns') }}
 {% endfor %}
 {% for host in groups['etcd'] %}
-IP.{{ 2 * loop.index - 1 }} = {{ hostvars[host]['access_ip'] | default(hostvars[host]['ansible_default_ipv4']['address']) }}
+{% if hostvars[host]['access_ip'] is defined  %}
-IP.{{ 2 * loop.index }} = {{ hostvars[host]['ip'] | default(hostvars[host]['ansible_default_ipv4']['address']) }}
+IP.{{ counter["ip"] }} = {{ hostvars[host]['access_ip'] }}{{ increment(counter, 'ip') }}
+{% endif %}
+IP.{{ counter["ip"] }} = {{ hostvars[host]['ip'] | default(hostvars[host]['ansible_default_ipv4']['address']) }}{{ increment(counter, 'ip') }}
 {% endfor %}
-{% set idx =  groups['etcd'] | length | int * 2 + 1 %}
+IP.{{ counter["ip"] }} = 127.0.0.1
-IP.{{ idx }} = 127.0.0.1

roles/kubernetes-apps/ansible/defaults/main.yml

@@ -10,6 +10,9 @@ dns_memory_requests: 70Mi
 kubedns_min_replicas: 2
 kubedns_nodes_per_replica: 10
 
+# CoreDNS
+coredns_replicas: 2
+
 # Images
 kubedns_image_repo: "gcr.io/google_containers/k8s-dns-kube-dns-amd64"
 kubedns_image_tag: "{{ kubedns_version }}"
@@ -41,9 +44,7 @@ netchecker_server_memory_requests: 64M
 # Dashboard
 dashboard_enabled: true
 dashboard_image_repo: gcr.io/google_containers/kubernetes-dashboard-amd64
-dashboard_image_tag: v1.8.1
+dashboard_image_tag: v1.8.3
-dashboard_init_image_repo: gcr.io/google_containers/kubernetes-dashboard-init-amd64
-dashboard_init_image_tag: v1.0.1
 
 # Limits for dashboard
 dashboard_cpu_limit: 100m

roles/kubernetes-apps/ansible/tasks/cleanup_dns.yml

@@ -0,0 +1,54 @@
+---
+- name: Kubernetes Apps | Delete old CoreDNS resources
+  kube:
+    name: "coredns"
+    namespace: "kube-system"
+    kubectl: "{{ bin_dir }}/kubectl"
+    resource: "{{ item }}"
+    state: absent
+  with_items:
+    - 'deploy'
+    - 'configmap'
+    - 'svc'
+  tags:
+    - upgrade
+
+- name: Kubernetes Apps | Delete kubeadm CoreDNS
+  kube:
+    name: "coredns"
+    namespace: "kube-system"
+    kubectl: "{{ bin_dir }}/kubectl"
+    resource: "deploy"
+    state: absent
+  when:
+    - kubeadm_enabled|default(false)
+    - kubeadm_init.changed|default(false)
+    - inventory_hostname == groups['kube-master'][0]
+
+- name: Kubernetes Apps | Delete old KubeDNS resources
+  kube:
+    name: "kube-dns"
+    namespace: "kube-system"
+    kubectl: "{{ bin_dir }}/kubectl"
+    resource: "{{ item }}"
+    state: absent
+  with_items:
+    - 'deploy'
+    - 'svc'
+  tags:
+    - upgrade
+
+- name: Kubernetes Apps | Delete kubeadm KubeDNS
+  kube:
+    name: "kube-dns"
+    namespace: "kube-system"
+    kubectl: "{{ bin_dir }}/kubectl"
+    resource: "{{ item }}"
+    state: absent
+  with_items:
+    - 'deploy'
+    - 'svc'
+  when:
+    - kubeadm_enabled|default(false)
+    - kubeadm_init.changed|default(false)
+    - inventory_hostname == groups['kube-master'][0]

roles/kubernetes-apps/ansible/tasks/coredns.yml

@@ -0,0 +1,39 @@
+---
+- name: Kubernetes Apps | Lay Down CoreDNS Template
+  template:
+    src: "{{ item.file }}.j2"
+    dest: "{{ kube_config_dir }}/{{ item.file }}"
+  with_items:
+    - { name: coredns, file: coredns-config.yml, type: configmap }
+    - { name: coredns, file: coredns-sa.yml, type: sa }
+    - { name: coredns, file: coredns-deployment.yml, type: deployment }
+    - { name: coredns, file: coredns-svc.yml, type: svc }
+    - { name: coredns, file: coredns-clusterrole.yml, type: clusterrole }
+    - { name: coredns, file: coredns-clusterrolebinding.yml, type: clusterrolebinding }
+  register: coredns_manifests
+  vars:
+    clusterIP: "{{ skydns_server }}"
+  when:
+    - dns_mode in ['coredns', 'coredns_dual']
+    - inventory_hostname == groups['kube-master'][0]
+    - rbac_enabled or item.type not in rbac_resources
+  tags:
+    - coredns
+
+- name: Kubernetes Apps | Lay Down Secondary CoreDNS Template
+  template:
+    src: "{{ item.src }}.j2"
+    dest: "{{ kube_config_dir }}/{{ item.file }}"
+  with_items:
+    - { name: coredns, src: coredns-deployment.yml, file: coredns-deployment-secondary.yml, type: deployment }
+    - { name: coredns, src: coredns-svc.yml, file: coredns-svc-secondary.yml, type: svc }
+  register: coredns_secondary_manifests
+  vars:
+    clusterIP: "{{ skydns_server_secondary }}"
+    coredns_ordinal_suffix: "-secondary"
+  when:
+    - dns_mode == 'coredns_dual'
+    - inventory_hostname == groups['kube-master'][0]
+    - rbac_enabled or item.type not in rbac_resources
+  tags:
+    - coredns

roles/kubernetes-apps/ansible/tasks/dashboard.yml

@@ -22,7 +22,7 @@
 - name: Kubernetes Apps | Start dashboard
   kube:
     name: "{{ item.item.name }}"
-    namespace: "{{ system_namespace }}"
+    namespace: "kube-system"
     kubectl: "{{ bin_dir }}/kubectl"
     resource: "{{ item.item.type }}"
     filename: "{{ kube_config_dir }}/{{ item.item.file }}"

roles/kubernetes-apps/ansible/tasks/kubedns.yml

@@ -0,0 +1,41 @@
+---
+
+- name: Kubernetes Apps | Lay Down KubeDNS Template
+  template:
+    src: "{{ item.file }}.j2"
+    dest: "{{ kube_config_dir }}/{{ item.file }}"
+  with_items:
+    - { name: kube-dns, file: kubedns-sa.yml, type: sa }
+    - { name: kube-dns, file: kubedns-deploy.yml, type: deployment }
+    - { name: kube-dns, file: kubedns-svc.yml, type: svc }
+    - { name: kubedns-autoscaler, file: kubedns-autoscaler-sa.yml, type: sa }
+    - { name: kubedns-autoscaler, file: kubedns-autoscaler-clusterrole.yml, type: clusterrole }
+    - { name: kubedns-autoscaler, file: kubedns-autoscaler-clusterrolebinding.yml, type: clusterrolebinding }
+    - { name: kubedns-autoscaler, file: kubedns-autoscaler.yml, type: deployment }
+  register: kubedns_manifests
+  when:
+    - dns_mode in ['kubedns','dnsmasq_kubedns']
+    - inventory_hostname == groups['kube-master'][0]
+    - rbac_enabled or item.type not in rbac_resources
+  tags:
+    - dnsmasq
+
+# see https://github.com/kubernetes/kubernetes/issues/45084, only needed for "old" kube-dns
+- name: Kubernetes Apps | Patch system:kube-dns ClusterRole
+  command: >
+    {{ bin_dir }}/kubectl patch clusterrole system:kube-dns
+    --patch='{
+               "rules": [
+                 {
+                   "apiGroups" : [""],
+                   "resources" : ["endpoints", "services"],
+                   "verbs": ["list", "watch", "get"]
+                 }
+               ]
+             }'
+  when:
+    - dns_mode in ['kubedns', 'dnsmasq_kubedns']
+    - inventory_hostname == groups['kube-master'][0]
+    - rbac_enabled and kubedns_version|version_compare("1.11.0", "<", strict=True)
+  tags:
+    - dnsmasq

roles/kubernetes-apps/ansible/tasks/main.yml

@@ -11,82 +11,49 @@
   delay: 2
   when: inventory_hostname == groups['kube-master'][0]
 
-- name: Kubernetes Apps | Delete old kubedns resources
+- name: Kubernetes Apps | Cleanup DNS
-  kube:
+  import_tasks: tasks/cleanup_dns.yml
-    name: "kubedns"
+  when:
-    namespace: "{{ system_namespace }}"
+    - inventory_hostname == groups['kube-master'][0]
-    kubectl: "{{ bin_dir }}/kubectl"
-    resource: "{{ item }}"
-    state: absent
-  with_items:
-    - 'deploy'
-    - 'svc'
   tags:
     - upgrade
 
-- name: Kubernetes Apps | Delete kubeadm kubedns
+- name: Kubernetes Apps | CoreDNS
-  kube:
+  import_tasks: "tasks/coredns.yml"
-    name: "kubedns"
-    namespace: "{{ system_namespace }}"
-    kubectl: "{{ bin_dir }}/kubectl"
-    resource: "deploy"
-    state: absent
   when:
-    - kubeadm_enabled|default(false)
+    - dns_mode in ['coredns', 'coredns_dual']
-    - kubeadm_init.changed|default(false)
     - inventory_hostname == groups['kube-master'][0]
-
-- name: Kubernetes Apps | Lay Down KubeDNS Template
-  template:
-    src: "{{ item.file }}.j2"
-    dest: "{{ kube_config_dir }}/{{ item.file }}"
-  with_items:
-    - { name: kube-dns, file: kubedns-sa.yml, type: sa }
-    - { name: kube-dns, file: kubedns-deploy.yml, type: deployment }
-    - { name: kube-dns, file: kubedns-svc.yml, type: svc }
-    - { name: kubedns-autoscaler, file: kubedns-autoscaler-sa.yml, type: sa }
-    - { name: kubedns-autoscaler, file: kubedns-autoscaler-clusterrole.yml, type: clusterrole }
-    - { name: kubedns-autoscaler, file: kubedns-autoscaler-clusterrolebinding.yml, type: clusterrolebinding }
-    - { name: kubedns-autoscaler, file: kubedns-autoscaler.yml, type: deployment }
-  register: manifests
-  when:
-    - dns_mode != 'none' and inventory_hostname == groups['kube-master'][0]
-    - rbac_enabled or item.type not in rbac_resources
   tags:
-    - dnsmasq
+    - coredns
 
-# see https://github.com/kubernetes/kubernetes/issues/45084, only needed for "old" kube-dns
+- name: Kubernetes Apps | KubeDNS
-- name: Kubernetes Apps | Patch system:kube-dns ClusterRole
+  import_tasks: "tasks/kubedns.yml"
-  command: >
-    {{ bin_dir }}/kubectl patch clusterrole system:kube-dns
-    --patch='{
-               "rules": [
-                 {
-                   "apiGroups" : [""],
-                   "resources" : ["endpoints", "services"],
-                   "verbs": ["list", "watch", "get"]
-                 }
-               ]
-             }'
   when:
-    - dns_mode != 'none' and inventory_hostname == groups['kube-master'][0]
+    - dns_mode in ['kubedns', 'dnsmasq_kubedns']
-    - rbac_enabled and kubedns_version|version_compare("1.11.0", "<", strict=True)
+    - inventory_hostname == groups['kube-master'][0]
   tags:
     - dnsmasq
 
 - name: Kubernetes Apps | Start Resources
   kube:
     name: "{{ item.item.name }}"
-    namespace: "{{ system_namespace }}"
+    namespace: "kube-system"
     kubectl: "{{ bin_dir }}/kubectl"
     resource: "{{ item.item.type }}"
     filename: "{{ kube_config_dir }}/{{ item.item.file }}"
     state: "latest"
-  with_items: "{{ manifests.results }}"
+  with_items:
+    - "{{ kubedns_manifests.results | default({}) }}"
+    - "{{ coredns_manifests.results | default({}) }}"
+    - "{{ coredns_secondary_manifests.results | default({}) }}"
   when:
     - dns_mode != 'none'
     - inventory_hostname == groups['kube-master'][0]
     - not item|skipped
+  register: resource_result
+  until: resource_result|succeeded
+  retries: 4
+  delay: 5
   tags:
     - dnsmasq
 

roles/kubernetes-apps/ansible/templates/coredns-clusterrole.yml.j2

@@ -0,0 +1,19 @@
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  labels:
+    kubernetes.io/bootstrapping: rbac-defaults
+    addonmanager.kubernetes.io/mode: Reconcile
+  name: system:coredns
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - endpoints
+  - services
+  - pods
+  - namespaces
+  verbs:
+  - list
+  - watch

roles/kubernetes-apps/ansible/templates/coredns-clusterrolebinding.yml.j2

@@ -0,0 +1,18 @@
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRoleBinding
+metadata:
+  annotations:
+    rbac.authorization.kubernetes.io/autoupdate: "true"
+  labels:
+    kubernetes.io/bootstrapping: rbac-defaults
+    addonmanager.kubernetes.io/mode: EnsureExists
+  name: system:coredns
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: system:coredns
+subjects:
+- kind: ServiceAccount
+  name: coredns
+  namespace: kube-system

roles/kubernetes-apps/ansible/templates/coredns-config.yml.j2

@@ -0,0 +1,22 @@
+---
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: coredns
+  namespace: kube-system
+  labels:
+    addonmanager.kubernetes.io/mode: EnsureExists
+data:
+  Corefile: |
+    .:53 {
+        errors
+        health
+        kubernetes {{ cluster_name }} in-addr.arpa ip6.arpa {
+          pods insecure
+          upstream /etc/resolv.conf
+          fallthrough in-addr.arpa ip6.arpa
+        }
+        prometheus :9153
+        proxy . /etc/resolv.conf
+        cache 30
+    }

roles/kubernetes-apps/ansible/templates/coredns-deployment.yml.j2

@@ -0,0 +1,81 @@
+---
+apiVersion: extensions/v1beta1
+kind: Deployment
+metadata:
+  name: coredns{{ coredns_ordinal_suffix | default('') }}
+  namespace: kube-system
+  labels:
+    k8s-app: coredns{{ coredns_ordinal_suffix | default('') }}
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    kubernetes.io/name: "CoreDNS"
+spec:
+  replicas: {{ coredns_replicas }}
+  strategy:
+    type: RollingUpdate
+    rollingUpdate:
+      maxUnavailable: 0
+      maxSurge: 10%
+  selector:
+    matchLabels:
+      k8s-app: coredns{{ coredns_ordinal_suffix | default('') }}
+  template:
+    metadata:
+      labels:
+        k8s-app: coredns{{ coredns_ordinal_suffix | default('') }}
+      annotations:
+        scheduler.alpha.kubernetes.io/critical-pod: ''
+    spec:
+{% if rbac_enabled %}
+      serviceAccountName: coredns
+{% endif %}
+      tolerations:
+        - key: node-role.kubernetes.io/master
+          effect: NoSchedule
+        - key: "CriticalAddonsOnly"
+          operator: "Exists"
+      containers:
+      - name: coredns
+        image: "{{ coredns_image_repo }}:{{ coredns_image_tag }}"
+        imagePullPolicy: {{ k8s_image_pull_policy }}
+        resources:
+          # TODO: Set memory limits when we've profiled the container for large
+          # clusters, then set request = limit to keep this container in
+          # guaranteed class. Currently, this container falls into the
+          # "burstable" category so the kubelet doesn't backoff from restarting it.
+          limits:
+            memory: {{ dns_memory_limit }}
+          requests:
+            cpu: {{ dns_cpu_requests }}
+            memory: {{ dns_memory_requests }}
+        args: [ "-conf", "/etc/coredns/Corefile" ]
+        volumeMounts:
+        - name: config-volume
+          mountPath: /etc/coredns
+        ports:
+        - containerPort: 53
+          name: dns
+          protocol: UDP
+        - containerPort: 53
+          name: dns-tcp
+          protocol: TCP
+        - containerPort: 9153
+          name: metrics
+          protocol: TCP
+        livenessProbe:
+          httpGet:
+            path: /health
+            port: 8080
+            scheme: HTTP
+          initialDelaySeconds: 60
+          timeoutSeconds: 5
+          successThreshold: 1
+          failureThreshold: 5
+      dnsPolicy: Default
+      volumes:
+        - name: config-volume
+          configMap:
+            name: coredns
+            items:
+            - key: Corefile
+              path: Corefile

roles/kubernetes-apps/ansible/templates/coredns-sa.yml.j2

@@ -0,0 +1,9 @@
+---
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: coredns
+  namespace: kube-system
+  labels:
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile

roles/kubernetes-apps/ansible/templates/coredns-svc.yml.j2

@@ -0,0 +1,22 @@
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: coredns{{ coredns_ordinal_suffix | default('') }}
+  namespace: kube-system
+  labels:
+    k8s-app: coredns{{ coredns_ordinal_suffix | default('') }}
+    kubernetes.io/cluster-service: "true"
+    addonmanager.kubernetes.io/mode: Reconcile
+    kubernetes.io/name: "CoreDNS"
+spec:
+  selector:
+    k8s-app: coredns{{ coredns_ordinal_suffix | default('') }}
+  clusterIP: {{ clusterIP }}
+  ports:
+  - name: dns
+    port: 53
+    protocol: UDP
+  - name: dns-tcp
+    port: 53
+    protocol: TCP

roles/kubernetes-apps/ansible/templates/dashboard.yml.j2

@@ -25,7 +25,7 @@ metadata:
   labels:
     k8s-app: kubernetes-dashboard
   name: kubernetes-dashboard-certs
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 type: Opaque
 
 ---
@@ -37,7 +37,7 @@ metadata:
   labels:
     k8s-app: kubernetes-dashboard
   name: kubernetes-dashboard
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 
 ---
 # ------------------- Dashboard Role & Role Binding ------------------- #
@@ -46,7 +46,7 @@ kind: Role
 apiVersion: rbac.authorization.k8s.io/v1
 metadata:
   name: kubernetes-dashboard-minimal
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 rules:
   # Allow Dashboard to create 'kubernetes-dashboard-key-holder' secret.
 - apiGroups: [""]
@@ -81,7 +81,7 @@ apiVersion: rbac.authorization.k8s.io/v1
 kind: RoleBinding
 metadata:
   name: kubernetes-dashboard-minimal
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: Role
@@ -89,7 +89,7 @@ roleRef:
 subjects:
 - kind: ServiceAccount
   name: kubernetes-dashboard
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 
 ---
 # ------------------- Gross Hack For anonymous auth through api proxy ------------------- #
@@ -103,7 +103,7 @@ rules:
   resources: ["services/proxy"]
   resourceNames: ["https:kubernetes-dashboard:"]
   verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
-- nonResourceURLs: ["/ui", "/ui/*", "/api/v1/namespaces/{{ system_namespace }}/services/https:kubernetes-dashboard:/proxy/*"]
+- nonResourceURLs: ["/ui", "/ui/*", "/api/v1/namespaces/kube-system/services/https:kubernetes-dashboard:/proxy/*"]
   verbs: ["get", "list", "watch", "create", "update", "patch", "delete"]
 
 ---
@@ -128,7 +128,7 @@ metadata:
   labels:
     k8s-app: kubernetes-dashboard
   name: kubernetes-dashboard
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 spec:
   replicas: 1
   revisionHistoryLimit: 10
@@ -200,7 +200,7 @@ metadata:
   labels:
     k8s-app: kubernetes-dashboard
   name: kubernetes-dashboard
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 spec:
   ports:
     - port: 443

roles/kubernetes-apps/ansible/templates/kubedns-autoscaler-clusterrole.yml.j2

@@ -17,7 +17,7 @@ kind: ClusterRole
 apiVersion: rbac.authorization.k8s.io/v1beta1
 metadata:
   name: cluster-proportional-autoscaler
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 rules:
   - apiGroups: [""]
     resources: ["nodes"]

roles/kubernetes-apps/ansible/templates/kubedns-autoscaler-clusterrolebinding.yml.j2

@@ -17,11 +17,11 @@ kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1beta1
 metadata:
   name: cluster-proportional-autoscaler
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 subjects:
   - kind: ServiceAccount
     name: cluster-proportional-autoscaler
-    namespace: {{ system_namespace }}
+    namespace: kube-system
 roleRef:
   kind: ClusterRole
   name: cluster-proportional-autoscaler

roles/kubernetes-apps/ansible/templates/kubedns-autoscaler-sa.yml.j2

@@ -17,4 +17,4 @@ kind: ServiceAccount
 apiVersion: v1
 metadata:
   name: cluster-proportional-autoscaler
-  namespace: {{ system_namespace }}
+  namespace: kube-system

roles/kubernetes-apps/ansible/templates/kubedns-autoscaler.yml.j2

@@ -17,7 +17,7 @@ apiVersion: extensions/v1beta1
 kind: Deployment
 metadata:
   name: kubedns-autoscaler
-  namespace: {{ system_namespace }}
+  namespace: kube-system
   labels:
     k8s-app: kubedns-autoscaler
     kubernetes.io/cluster-service: "true"
@@ -40,7 +40,7 @@ spec:
             memory: "10Mi"
         command:
         - /cluster-proportional-autoscaler
-        - --namespace={{ system_namespace }}
+        - --namespace=kube-system
         - --configmap=kubedns-autoscaler
         # Should keep target in sync with cluster/addons/dns/kubedns-controller.yaml.base
         - --target=Deployment/kube-dns

roles/kubernetes-apps/ansible/templates/kubedns-deploy.yml.j2

@@ -3,7 +3,7 @@ apiVersion: extensions/v1beta1
 kind: Deployment
 metadata:
   name: kube-dns
-  namespace: "{{system_namespace}}"
+  namespace: kube-system
   labels:
     k8s-app: kube-dns
     kubernetes.io/cluster-service: "true"

roles/kubernetes-apps/ansible/templates/kubedns-sa.yml.j2

@@ -3,6 +3,6 @@ apiVersion: v1
 kind: ServiceAccount
 metadata:
   name: kube-dns
-  namespace: {{ system_namespace }}
+  namespace: kube-system
   labels:
     kubernetes.io/cluster-service: "true"

roles/kubernetes-apps/ansible/templates/kubedns-svc.yml.j2

@@ -3,7 +3,7 @@ apiVersion: v1
 kind: Service
 metadata:
   name: kube-dns
-  namespace: {{ system_namespace }}
+  namespace: kube-system
   labels:
     k8s-app: kube-dns
     kubernetes.io/cluster-service: "true"

roles/kubernetes-apps/cluster_roles/tasks/main.yml

@@ -16,11 +16,13 @@
     src: "node-crb.yml.j2"
     dest: "{{ kube_config_dir }}/node-crb.yml"
   register: node_crb_manifest
-  when: rbac_enabled
+  when:
+    - rbac_enabled
+    - inventory_hostname == groups['kube-master'][0]
 
 - name: Apply workaround to allow all nodes with cert O=system:nodes to register
   kube:
-    name: "system:node"
+    name: "kubespray:system:node"
     kubectl: "{{bin_dir}}/kubectl"
     resource: "clusterrolebinding"
     filename: "{{ kube_config_dir }}/node-crb.yml"
@@ -28,32 +30,101 @@
   when:
     - rbac_enabled
     - node_crb_manifest.changed
+    - inventory_hostname == groups['kube-master'][0]
 
-# This is not a cluster role, but should be run after kubeconfig is set on master
+- name: Kubernetes Apps | Add webhook ClusterRole that grants access to proxy, stats, log, spec, and metrics on a kubelet
-- name: Write kube system namespace manifest
   template:
-    src: namespace.j2
+    src: "node-webhook-cr.yml.j2"
-    dest: "{{kube_config_dir}}/{{system_namespace}}-ns.yml"
+    dest: "{{ kube_config_dir }}/node-webhook-cr.yml"
-  when: inventory_hostname == groups['kube-master'][0]
+  register: node_webhook_cr_manifest
-  tags:
+  when:
-    - apps
+    - rbac_enabled
+    - kubelet_authorization_mode_webhook
+    - inventory_hostname == groups['kube-master'][0]
+  tags: node-webhook
 
-- name: Check if kube system namespace exists
+- name: Apply webhook ClusterRole
-  command: "{{ bin_dir }}/kubectl get ns {{system_namespace}}"
+  kube:
-  register: 'kubesystem'
+    name: "system:node-webhook"
-  changed_when: False
+    kubectl: "{{bin_dir}}/kubectl"
-  failed_when: False
+    resource: "clusterrole"
-  when: inventory_hostname == groups['kube-master'][0]
+    filename: "{{ kube_config_dir }}/node-webhook-cr.yml"
-  tags:
+    state: latest
-    - apps
+  when:
+    - rbac_enabled
+    - kubelet_authorization_mode_webhook
+    - node_webhook_cr_manifest.changed
+    - inventory_hostname == groups['kube-master'][0]
+  tags: node-webhook
 
-- name: Create kube system namespace
+- name: Kubernetes Apps | Add ClusterRoleBinding for system:nodes to webhook ClusterRole
-  command: "{{ bin_dir }}/kubectl create -f {{kube_config_dir}}/{{system_namespace}}-ns.yml"
+  template:
-  retries: 4
+    src: "node-webhook-crb.yml.j2"
-  delay: "{{ retry_stagger | random + 3 }}"
+    dest: "{{ kube_config_dir }}/node-webhook-crb.yml"
-  register: create_system_ns
+  register: node_webhook_crb_manifest
-  until: create_system_ns.rc == 0
+  when:
-  changed_when: False
+    - rbac_enabled
-  when: inventory_hostname == groups['kube-master'][0] and kubesystem.rc != 0
+    - kubelet_authorization_mode_webhook
-  tags:
+    - inventory_hostname == groups['kube-master'][0]
-    - apps
+  tags: node-webhook
+
+- name: Grant system:nodes the webhook ClusterRole
+  kube:
+    name: "system:node-webhook"
+    kubectl: "{{bin_dir}}/kubectl"
+    resource: "clusterrolebinding"
+    filename: "{{ kube_config_dir }}/node-webhook-crb.yml"
+    state: latest
+  when:
+    - rbac_enabled
+    - kubelet_authorization_mode_webhook
+    - node_webhook_crb_manifest.changed
+    - inventory_hostname == groups['kube-master'][0]
+  tags: node-webhook
+
+- name: Check if vsphere-cloud-provider ClusterRole exists
+  command: "{{ bin_dir }}/kubectl get clusterroles system:vsphere-cloud-provider"
+  register: vsphere_cloud_provider
+  ignore_errors: true
+  when:
+    - rbac_enabled
+    - cloud_provider is defined
+    - cloud_provider == 'vsphere'
+    - kube_version | version_compare('v1.9.0', '>=')
+    - kube_version | version_compare('v1.9.3', '<=')
+    - inventory_hostname == groups['kube-master'][0]
+  tags: vsphere
+
+- name: Write vsphere-cloud-provider ClusterRole manifest
+  template:
+    src: "vsphere-rbac.yml.j2"
+    dest: "{{ kube_config_dir }}/vsphere-rbac.yml"
+  register: vsphere_rbac_manifest
+  when:
+    - rbac_enabled
+    - cloud_provider is defined
+    - cloud_provider == 'vsphere'
+    - vsphere_cloud_provider.rc is defined
+    - vsphere_cloud_provider.rc != 0
+    - kube_version | version_compare('v1.9.0', '>=')
+    - kube_version | version_compare('v1.9.3', '<=')
+    - inventory_hostname == groups['kube-master'][0]
+  tags: vsphere
+
+- name: Apply vsphere-cloud-provider ClusterRole
+  kube:
+    name: "system:vsphere-cloud-provider"
+    kubectl: "{{bin_dir}}/kubectl"
+    resource: "clusterrolebinding"
+    filename: "{{ kube_config_dir }}/vsphere-rbac.yml"
+    state: latest
+  when:
+    - rbac_enabled
+    - cloud_provider is defined
+    - cloud_provider == 'vsphere'
+    - vsphere_cloud_provider.rc is defined
+    - vsphere_cloud_provider.rc != 0
+    - kube_version | version_compare('v1.9.0', '>=')
+    - kube_version | version_compare('v1.9.3', '<=')
+    - inventory_hostname == groups['kube-master'][0]
+  tags: vsphere

roles/kubernetes-apps/cluster_roles/templates/namespace.j2

@@ -1,4 +1,4 @@
 apiVersion: v1
 kind: Namespace
 metadata:
-  name: "{{system_namespace}}"
+  name: "kube-system"

roles/kubernetes-apps/cluster_roles/templates/node-crb.yml.j2

@@ -6,7 +6,7 @@ metadata:
     rbac.authorization.kubernetes.io/autoupdate: "true"
   labels:
     kubernetes.io/bootstrapping: rbac-defaults
-  name: system:node
+  name: kubespray:system:node
 roleRef:
   apiGroup: rbac.authorization.k8s.io
   kind: ClusterRole

roles/kubernetes-apps/cluster_roles/templates/node-webhook-cr.yml.j2

@@ -0,0 +1,20 @@
+---
+apiVersion: rbac.authorization.k8s.io/v1beta1
+kind: ClusterRole
+metadata:
+  annotations:
+    rbac.authorization.kubernetes.io/autoupdate: "true"
+  labels:
+    kubernetes.io/bootstrapping: rbac-defaults
+  name: system:node-webhook
+rules:
+  - apiGroups:
+      - ""
+    resources:
+      - nodes/proxy
+      - nodes/stats
+      - nodes/log
+      - nodes/spec
+      - nodes/metrics
+    verbs:
+      - "*"

roles/kubernetes-apps/cluster_roles/templates/node-webhook-crb.yml.j2

@@ -0,0 +1,17 @@
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  annotations:
+    rbac.authorization.kubernetes.io/autoupdate: "true"
+  labels:
+    kubernetes.io/bootstrapping: rbac-defaults
+  name: system:node-webhook
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: system:node-webhook
+subjects:
+- apiGroup: rbac.authorization.k8s.io
+  kind: Group
+  name: system:nodes

roles/kubernetes-apps/cluster_roles/templates/vsphere-rbac.yml.j2

@@ -0,0 +1,35 @@
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: system:vsphere-cloud-provider
+rules:
+- apiGroups:
+  - ""
+  resources:
+  - nodes
+  verbs:
+  - get
+  - list
+  - watch
+- apiGroups:
+  - ""
+  resources:
+  - events
+  verbs:
+  - create
+  - patch
+  - update
+
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: system:vsphere-cloud-provider
+roleRef:
+  kind: ClusterRole
+  name: system:vsphere-cloud-provider
+  apiGroup: rbac.authorization.k8s.io
+subjects:
+- kind: ServiceAccount
+  name: vsphere-cloud-provider
+  namespace: kube-system

roles/kubernetes-apps/efk/elasticsearch/tasks/main.yml

@@ -10,7 +10,7 @@
   when: rbac_enabled
 
 - name: "ElasticSearch | Create Serviceaccount and Clusterrolebinding (RBAC)"
-  command: "{{ bin_dir }}/kubectl apply -f {{ kube_config_dir }}/{{ item }} -n {{ system_namespace }}"
+  command: "{{ bin_dir }}/kubectl apply -f {{ kube_config_dir }}/{{ item }} -n kube-system"
   with_items:
     - "efk-sa.yml"
     - "efk-clusterrolebinding.yml"
@@ -24,7 +24,7 @@
   register: es_deployment_manifest
 
 - name: "ElasticSearch | Create ES deployment"
-  command: "{{ bin_dir }}/kubectl apply -f {{ kube_config_dir }}/elasticsearch-deployment.yaml -n {{ system_namespace }}"
+  command: "{{ bin_dir }}/kubectl apply -f {{ kube_config_dir }}/elasticsearch-deployment.yaml -n kube-system"
   run_once: true
   when: es_deployment_manifest.changed
 
@@ -35,6 +35,6 @@
   register: es_service_manifest
 
 - name: "ElasticSearch | Create ES service"
-  command: "{{ bin_dir }}/kubectl apply -f {{ kube_config_dir }}/elasticsearch-service.yaml -n {{ system_namespace }}"
+  command: "{{ bin_dir }}/kubectl apply -f {{ kube_config_dir }}/elasticsearch-service.yaml -n kube-system"
   run_once: true
   when: es_service_manifest.changed

roles/kubernetes-apps/efk/elasticsearch/templates/efk-clusterrolebinding.yml

@@ -3,11 +3,11 @@ kind: ClusterRoleBinding
 apiVersion: rbac.authorization.k8s.io/v1beta1
 metadata:
   name: efk
-  namespace: {{ system_namespace }}
+  namespace: kube-system
 subjects:
   - kind: ServiceAccount
     name: efk
-    namespace: {{ system_namespace }}
+    namespace: kube-system
 roleRef:
   kind: ClusterRole
   name: cluster-admin

roles/kubernetes-apps/efk/elasticsearch/templates/efk-sa.yml

@@ -3,6 +3,6 @@ apiVersion: v1
 kind: ServiceAccount
 metadata:
   name: efk
-  namespace: {{ system_namespace }}
+  namespace: kube-system
   labels:
     kubernetes.io/cluster-service: "true"

roles/kubernetes-apps/efk/elasticsearch/templates/elasticsearch-deployment.yml.j2

@@ -4,7 +4,7 @@ apiVersion: extensions/v1beta1
 kind: Deployment
 metadata:
   name: elasticsearch-logging-v1
-  namespace: "{{ system_namespace }}"
+  namespace: kube-system
   labels:
     k8s-app: elasticsearch-logging
     version: "{{ elasticsearch_image_tag }}"

roles/kubernetes-apps/efk/elasticsearch/templates/elasticsearch-service.yml.j2

@@ -3,7 +3,7 @@ apiVersion: v1
 kind: Service
 metadata:
   name: elasticsearch-logging
-  namespace: "{{ system_namespace }}"
+  namespace: "kube-system"
   labels:
     k8s-app: elasticsearch-logging
     kubernetes.io/cluster-service: "true"

roles/kubernetes-apps/efk/fluentd/tasks/main.yml

@@ -17,6 +17,6 @@
   register: fluentd_ds_manifest
 
 - name: "Fluentd | Create fluentd daemonset"
-  command: "{{ bin_dir }}/kubectl apply -f {{ kube_config_dir }}/fluentd-ds.yaml -n {{ system_namespace }}"
+  command: "{{ bin_dir }}/kubectl apply -f {{ kube_config_dir }}/fluentd-ds.yaml -n kube-system"
   run_once: true
   when: fluentd_ds_manifest.changed

roles/kubernetes-apps/efk/fluentd/templates/fluentd-config.yml.j2

@@ -2,7 +2,7 @@ apiVersion: v1
 kind: ConfigMap
 metadata:
   name: fluentd-config
-  namespace: "{{ system_namespace }}"
+  namespace: "kube-system"
 data:
   {{ fluentd_config_file }}: |
     # This configuration file for Fluentd / td-agent is used