Merge pull request #874 from bogdando/fix

Fix docs formatting

.github/ISSUE_TEMPLATE.md

@@ -0,0 +1,47 @@
+<!-- Thanks for filing an issue! Before hitting the button, please answer these questions.-->
+
+**Is this a BUG REPORT or FEATURE REQUEST?** (choose one):
+
+<!--
+If this is a BUG REPORT, please:
+  - Fill in as much of the template below as you can.  If you leave out
+    information, we can't help you as well.
+
+If this is a FEATURE REQUEST, please:
+  - Describe *in detail* the feature/behavior/change you'd like to see.
+
+In both cases, be ready for followup questions, and please respond in a timely
+manner.  If we can't reproduce a bug or think a feature already exists, we
+might close your issue.  If we're wrong, PLEASE feel free to reopen it and
+explain why.
+-->
+
+**Environment**:
+- **Cloud provider or hardware configuration:**
+
+- **OS (`printf "$(uname -srm)\n$(cat /etc/os-release)\n"`):**
+
+- **Version of Ansible** (`ansible --version`):
+
+
+**Kargo version (commit) (`git rev-parse --short HEAD`):**
+
+
+**Network plugin used**:
+
+
+**Copy of your inventory file:**
+
+
+**Command used to invoke ansible**:
+
+
+**Output of ansible run**:
+<!-- We recommend using snippets services like https://gist.github.com/ etc. -->
+
+**Anything else do we need to know**:
+<!-- By running scripts/collect-info.yaml you can get a lot of useful informations.
+Script can be started by:
+ansible-playbook -i <inventory_file_path> -u <ssh_user> -e ansible_ssh_user=<ssh_user> -b --become-user=root -e dir=`pwd` scripts/collect-info.yaml
+(If you using CoreOS remember to add '-e ansible_python_interpreter=/opt/bin/python').
+After running this command you can find logs in `pwd`/logs.tar.gz. You can even upload somewhere entire file and paste link here.-->

.gitlab-ci.yml

@@ -48,8 +48,12 @@ before_script:
   GS_SECRET_ACCESS_KEY: $GS_SECRET
   ANSIBLE_KEEP_REMOTE_FILES: "1"
   BOOTSTRAP_OS: none
+  RESOLVCONF_MODE: docker_dns
   LOG_LEVEL: "-vv"
-
+  ETCD_DEPLOYMENT: "docker"
+  KUBELET_DEPLOYMENT: "docker"
+  MAGIC: "ci check this"
+  
 .gce: &gce
   <<: *job
   <<: *docker_service
@@ -101,7 +105,10 @@ before_script:
       -e download_run_once=true
       -e download_localhost=true
       -e deploy_netchecker=true
+      -e resolvconf_mode=${RESOLVCONF_MODE}
       -e local_release_dir=${PWD}/downloads
+      -e etcd_deployment_type=${ETCD_DEPLOYMENT}
+      -e kubelet_deployment_type=${KUBELET_DEPLOYMENT}
       cluster.yml
 
 
@@ -136,6 +143,7 @@ before_script:
   CLOUD_REGION: us-west1-b
   CLUSTER_MODE: separated
   BOOTSTRAP_OS: coreos
+  RESOLVCONF_MODE: host_resolvconf # This is required as long as the CoreOS stable channel uses docker < 1.12
 
 .debian8_canal_ha_variables: &debian8_canal_ha_variables
 # stage: deploy-gce-part1
@@ -172,6 +180,7 @@ before_script:
   CLOUD_REGION: us-east1-b
   CLUSTER_MODE: default
   BOOTSTRAP_OS: coreos
+  RESOLVCONF_MODE: host_resolvconf # This is required as long as the CoreOS stable channel uses docker < 1.12
 
 .rhel7_canal_sep_variables: &rhel7_canal_sep_variables
 # stage: deploy-gce-special
@@ -202,7 +211,16 @@ before_script:
   CLUSTER_MODE: ha
   BOOTSTRAP_OS: coreos
 
-# Builds for PRs only (auto) and triggers (auto)
+.ubuntu_rkt_sep_variables: &ubuntu_rkt_sep_variables
+# stage: deploy-gce-part1
+  KUBE_NETWORK_PLUGIN: flannel
+  CLOUD_IMAGE: ubuntu-1604-xenial
+  CLOUD_REGION: us-central1-b
+  CLUSTER_MODE: separated
+  ETCD_DEPLOYMENT: rkt
+  KUBELET_DEPLOYMENT: rkt
+
+# Builds for PRs only (premoderated by unit-tests step) and triggers (auto)
 coreos-calico-sep:
   stage: deploy-gce-part1
   <<: *job
@@ -405,12 +423,27 @@ coreos-alpha-weave-ha:
   except: ['triggers']
   only: ['master', /^pr-.*$/]
 
+ubuntu-rkt-sep:
+  stage: deploy-gce-part1
+  <<: *job
+  <<: *gce
+  variables:
+    <<: *gce_variables
+    <<: *ubuntu_rkt_sep_variables
+  when: manual
+  except: ['triggers']
+  only: ['master', /^pr-.*$/]
+
+# Premoderated with manual actions
 syntax-check:
   <<: *job
   stage: unit-tests
+  before_script:
+    - apt-get -y install jq
   script:
     - ansible-playbook -i inventory/local-tests.cfg -u root -e ansible_ssh_user=root  -b --become-user=root cluster.yml -vvv  --syntax-check
-  except: ['triggers']
+    - /bin/sh scripts/premoderator.sh
+  except: ['triggers', 'master']
 
 tox-inventory-builder:
   stage: unit-tests
@@ -419,4 +452,4 @@ tox-inventory-builder:
     - pip install tox
     - cd contrib/inventory_builder && tox
   when: manual
-  except: ['triggers']
+  except: ['triggers', 'master']

README.md

@@ -1,4 +1,4 @@
-![Kubespray Logo](http://s9.postimg.org/md5dyjl67/kubespray_logoandkubespray_small.png)
+![Kubernetes Logo](https://s28.postimg.org/lf3q4ocpp/k8s.png)
 
 ##Deploy a production ready kubernetes cluster
 
@@ -14,75 +14,88 @@ If you have questions, join us on the [kubernetes slack](https://slack.k8s.io),
 To deploy the cluster you can use :
 
 [**kargo-cli**](https://github.com/kubespray/kargo-cli) <br>
-**Ansible** usual commands <br>
+**Ansible** usual commands and [**inventory builder**](https://github.com/kubernetes-incubator/kargo/blob/master/contrib/inventory_builder/inventory.py) <br>
 **vagrant** by simply running `vagrant up` (for tests purposes) <br>
 
 
 *  [Requirements](#requirements)
+*  [Kargo vs ...](docs/comparisons.md)
 *  [Getting started](docs/getting-started.md)
+*  [Ansible inventory and tags](docs/ansible.md)
+*  [Deployment data variables](docs/vars.md)
+*  [DNS stack](docs/dns-stack.md)
+*  [HA mode](docs/ha-mode.md)
+*  [Network plugins](#network-plugins)
 *  [Vagrant install](docs/vagrant.md)
 *  [CoreOS bootstrap](docs/coreos.md)
-*  [Ansible variables](docs/ansible.md)
+*  [Downloaded artifacts](docs/downloads.md)
 *  [Cloud providers](docs/cloud.md)
 *  [OpenStack](docs/openstack.md)
 *  [AWS](docs/aws.md)
 *  [Azure](docs/azure.md)
-*  [Network plugins](#network-plugins)
+*  [Large deployments](docs/large-deployments.md)
+*  [Upgrades basics](docs/upgrades.md)
 *  [Roadmap](docs/roadmap.md)
 
 Supported Linux distributions
 ===============
 
-* **CoreOS**
+* **Container Linux by CoreOS**
-* **Debian** Wheezy, Jessie
+* **Debian** Jessie
-* **Ubuntu** 14.10, 15.04, 15.10, 16.04
+* **Ubuntu** 16.04
-* **Fedora** 23
 * **CentOS/RHEL** 7
 
-Versions
+Note: Upstart/SysV init based OS types are not supported.
---------------
 
-[kubernetes](https://github.com/kubernetes/kubernetes/releases) v1.4.6 <br>
+Versions of supported components
+--------------------------------
+
+[kubernetes](https://github.com/kubernetes/kubernetes/releases) v1.5.1 <br>
 [etcd](https://github.com/coreos/etcd/releases) v3.0.6 <br>
 [flanneld](https://github.com/coreos/flannel/releases) v0.6.2 <br>
-[calicoctl](https://github.com/projectcalico/calico-docker/releases) v0.22.0 <br>
+[calicoctl](https://github.com/projectcalico/calico-docker/releases) v0.23.0 <br>
+[canal](https://github.com/projectcalico/canal) (given calico/flannel versions) <br>
 [weave](http://weave.works/) v1.6.1 <br>
-[docker](https://www.docker.com/) v1.10.3 <br>
+[docker](https://www.docker.com/) v1.12.5 <br>
+[rkt](https://coreos.com/rkt/docs/latest/) v1.21.0 <br>
 
+Note: rkt support as docker alternative is limited to control plane (etcd and
+kubelet). Docker is still used for Kubernetes cluster workloads and network
+plugins' related OS services. Also note, only one of the supported network
+plugins can be deployed for a given single cluster.
 
 Requirements
 --------------
 
 * The target servers must have **access to the Internet** in order to pull docker images.
 * The **firewalls are not managed**, you'll need to implement your own rules the way you used to.
-in order to avoid any issue during deployment you should disable your firewall
+in order to avoid any issue during deployment you should disable your firewall.
+* The target servers are configured to allow **IPv4 forwarding**.
 * **Copy your ssh keys** to all the servers part of your inventory.
-* **Ansible v2.x and python-netaddr**
+* **Ansible v2.2 (or newer) and python-netaddr**
 
 
 ## Network plugins
-You can choose between 3 network plugins. (default: `flannel` with vxlan backend)
+You can choose between 4 network plugins. (default: `flannel` with vxlan backend)
 
 * [**flannel**](docs/flannel.md): gre/vxlan (layer 2) networking.
 
 * [**calico**](docs/calico.md): bgp (layer 3) networking.
 
+* [**canal**](https://github.com/projectcalico/canal): a composition of calico and flannel plugins.
+
 * **weave**: Weave is a lightweight container overlay network that doesn't require an external K/V database cluster. <br>
-(Please refer to `weave` [troubleshooting documentation](http://docs.weave.works/weave/latest_release/troubleshooting.html))
+(Please refer to `weave` [troubleshooting documentation](http://docs.weave.works/weave/latest_release/troubleshooting.html)).
-
-The choice is defined with the variable `kube_network_plugin`
 
+The choice is defined with the variable `kube_network_plugin`. There is also an
+option to leverage built-in cloud provider networking instead.
+See also [Network checker](docs/netcheck.md).
 
 ## CI Tests
 
-[![Build Status](https://travis-ci.org/kubernetes-incubator/kargo.svg)](https://travis-ci.org/kubernetes-incubator/kargo) </br>
+![Gitlab Logo](https://s27.postimg.org/wmtaig1wz/gitlabci.png)
 
-### Google Compute Engine
+[![Build graphs](https://gitlab.com/kargo-ci/kubernetes-incubator__kargo/badges/master/build.svg)](https://gitlab.com/kargo-ci/kubernetes-incubator__kargo/pipelines) </br>
 
-              | Calico        | Flannel       | Weave         |
+CI/end-to-end tests sponsored by Google (GCE), and [teuto.net](https://teuto.net/) for OpenStack.
-------------- | ------------- | ------------- | ------------- |
+See the [test matrix](docs/test_cases.md) for details.
-Ubuntu Xenial |[![Build Status](https://ci.kubespray.io/job/kargo-gce-xenial-calico/badge/icon)](https://ci.kubespray.io/job/kargo-gce-xenial-calico/)|[![Build Status](https://ci.kubespray.io/job/kargo-gce-xenial-flannel/badge/icon)](https://ci.kubespray.io/job/kargo-gce-xenial-flannel/)|[![Build Status](https://ci.kubespray.io/job/kargo-gce-xenial-weave/badge/icon)](https://ci.kubespray.io/job/kargo-gce-xenial-weave)|
-CentOS 7      |[![Build Status](https://ci.kubespray.io/job/kargo-gce-centos7-calico/badge/icon)](https://ci.kubespray.io/job/kargo-gce-centos7-calico/)|[![Build Status](https://ci.kubespray.io/job/kargo-gce-centos7-flannel/badge/icon)](https://ci.kubespray.io/job/kargo-gce-centos7-flannel/)|[![Build Status](https://ci.kubespray.io/job/kargo-gce-centos7-weave/badge/icon)](https://ci.kubespray.io/job/kargo-gce-centos7-weave/)|
-CoreOS (stable) |[![Build Status](https://ci.kubespray.io/job/kargo-gce-coreos-calico/badge/icon)](https://ci.kubespray.io/job/kargo-gce-coreos-calico/)|[![Build Status](https://ci.kubespray.io/job/kargo-gce-coreos-flannel/badge/icon)](https://ci.kubespray.io/job/kargo-gce-coreos-flannel/)|[![Build Status](https://ci.kubespray.io/job/kargo-gce-coreos-weave/badge/icon)](https://ci.kubespray.io/job/kargo-gce-coreos-weave/)|
-
-CI tests sponsored by Google (GCE), and [teuto.net](https://teuto.net/) for OpenStack.

cluster.yml

@@ -28,6 +28,7 @@
   roles:
     - { role: kubernetes/preinstall, tags: preinstall }
     - { role: docker, tags: docker }
+    - { role: rkt, tags: rkt, when: "'rkt' in [ etcd_deployment_type, kubelet_deployment_type ]" }
 
 - hosts: etcd:!k8s-cluster
   any_errors_fatal: true
@@ -56,8 +57,8 @@
 - hosts: k8s-cluster
   any_errors_fatal: true
   roles:
-    - { role: dnsmasq, tags: dnsmasq }
+    - { role: dnsmasq, when: "dns_mode == 'dnsmasq_kubedns'", tags: dnsmasq }
-    - { role: kubernetes/preinstall, tags: resolvconf }
+    - { role: kubernetes/preinstall, when: "dns_mode != 'none' and resolvconf_mode == 'host_resolvconf'", tags: resolvconf }
 
 - hosts: kube-master[0]
   any_errors_fatal: true

contrib/terraform/openstack/README.md

@@ -36,7 +36,7 @@ Ensure your OpenStack credentials are loaded in environment variables. This can
 $ source ~/.stackrc
 ```
 
-You will need two networks before installing, an internal network and 
+You will need two networks before installing, an internal network and
 an external (floating IP Pool) network. The internet network can be shared as
 we use security groups to provide network segregation. Due to the many
 differences between OpenStack installs the Terraform does not attempt to create
@@ -97,7 +97,7 @@ gfs_volume_size_in_gb = "50"
 ssh_user_gfs = "ubuntu"
 ```
 
-If these variables are provided, this will give rise to a new ansible group called `gfs-cluster`, for which we have added ansible roles to execute in the ansible provisioning step. If you are using CoreOS, these GlusterFS VM necessarily need to be either Debian or RedHat based VMs, CoreOS cannot serve GlusterFS, but can connect to it through binaries available on hyperkube v1.4.3_coreos.0 or higher.
+If these variables are provided, this will give rise to a new ansible group called `gfs-cluster`, for which we have added ansible roles to execute in the ansible provisioning step. If you are using Container Linux by CoreOS, these GlusterFS VM necessarily need to be either Debian or RedHat based VMs, Container Linux by CoreOS cannot serve GlusterFS, but can connect to it through binaries available on hyperkube v1.4.3_coreos.0 or higher.
 
 
 # Provision a Kubernetes Cluster on OpenStack
@@ -133,20 +133,20 @@ Make sure you can connect to the hosts:
 ```
 $ ansible -i contrib/terraform/openstack/hosts -m ping all
 example-k8s_node-1 | SUCCESS => {
-    "changed": false, 
+    "changed": false,
     "ping": "pong"
 }
 example-etcd-1 | SUCCESS => {
-    "changed": false, 
+    "changed": false,
     "ping": "pong"
 }
 example-k8s-master-1 | SUCCESS => {
-    "changed": false, 
+    "changed": false,
     "ping": "pong"
 }
 ```
 
-if you are deploying a system that needs bootstrapping, like CoreOS, these might have a state `FAILED` due to CoreOS not having python. As long as the state is not `UNREACHABLE`, this is fine.
+if you are deploying a system that needs bootstrapping, like Container Linux by 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 somthing as simple as a stale host key.
 

contrib/terraform/openstack/group_vars/all.yml

@@ -10,7 +10,7 @@ local_release_dir: "/tmp/releases"
 # Random shifts for retrying failed ops like pushing/downloading
 retry_stagger: 5
 
-# Uncomment this line for CoreOS only.
+# Uncomment this line for Container Linux by CoreOS only.
 # Directory where python binary is installed
 # ansible_python_interpreter: "/opt/bin/python"
 
@@ -105,21 +105,21 @@ kube_apiserver_insecure_port: 8080 # (http)
 # into appropriate IP addresses. It's highly advisable to run such DNS server,
 # as it greatly simplifies configuration of your applications - you can use
 # service names instead of magic environment variables.
-# You still must manually configure all your containers to use this DNS server,
-# Kubernetes won't do this for you (yet).
 
-# Do not install additional dnsmasq
+# Can be dnsmasq_kubedns, kubedns or none
-skip_dnsmasq: false
+dns_mode: dnsmasq_kubedns
-# Upstream dns servers used by dnsmasq
+
+# Can be docker_dns, host_resolvconf or none
+resolvconf_mode: docker_dns
+
+## Upstream dns servers used by dnsmasq
 #upstream_dns_servers:
 #  - 8.8.8.8
 #  - 8.8.4.4
-#
+
-# # Use dns server : https://github.com/ansibl8s/k8s-skydns/blob/master/skydns-README.md
-dns_setup: true
 dns_domain: "{{ cluster_name }}"
-#
+
-# # Ip address of the kubernetes skydns service
+# Ip address of the kubernetes skydns service
 skydns_server: "{{ kube_service_addresses|ipaddr('net')|ipaddr(3)|ipaddr('address') }}"
 dns_server: "{{ kube_service_addresses|ipaddr('net')|ipaddr(2)|ipaddr('address') }}"
 

docs/ansible.md

@@ -45,9 +45,37 @@ kube-master
 etcd
 ```
 
-Group vars
+Group vars and overriding variables precedence
---------------
+----------------------------------------------
-The main variables to change are located in the directory ```inventory/group_vars/all.yml```.
+
+The group variables to control main deployment options are located in the directory ``inventory/group_vars``.
+
+There are also role vars for docker, rkt, kubernetes preinstall and master roles.
+According to the [ansible docs](http://docs.ansible.com/ansible/playbooks_variables.html#variable-precedence-where-should-i-put-a-variable),
+those cannot be overriden from the group vars. In order to override, one should use
+the `-e ` runtime flags (most simple way) or other layers described in the docs.
+
+Kargo uses only a few layers to override things (or expect them to
+be overriden for roles):
+
+Layer | Comment
+------|--------
+**role defaults** | provides best UX to override things for Kargo deployments
+inventory vars | Unused
+**inventory group_vars** | Expects users to use ``all.yml``,``k8s-cluster.yml`` etc. to override things
+inventory host_vars | Unused
+playbook group_vars | Unuses
+playbook host_vars | Unused
+**host facts** | Kargo overrides for internal roles' logic, like state flags
+play vars | Unused
+play vars_prompt | Unused
+play vars_files | Unused
+registered vars | Unused
+set_facts | Kargo overrides those, for some places
+**role and include vars** | Provides bad UX to override things! Use extra vars to enforce
+block vars (only for tasks in block) | Kargo overrides for internal roles' logic
+task vars (only for the task) | Unused for roles, but only for helper scripts
+**extra vars** (always win precedence) | override with ``ansible-playbook -e @foo.yml``
 
 Ansible tags
 ------------
@@ -132,5 +160,5 @@ bastion host.
 bastion ansible_ssh_host=x.x.x.x
 ```
 
-For more information about Ansible and bastion hosts, read 
+For more information about Ansible and bastion hosts, read
-[Running Ansible Through an SSH Bastion Host](http://blog.scottlowe.org/2015/12/24/running-ansible-through-ssh-bastion-host/)
+[Running Ansible Through an SSH Bastion Host](http://blog.scottlowe.org/2015/12/24/running-ansible-through-ssh-bastion-host/)

docs/comparisons.md

@@ -0,0 +1,25 @@
+Kargo vs [Kops](https://github.com/kubernetes/kops)
+---------------
+
+Kargo runs on bare metal and most clouds, using Ansible as its substrate for
+provisioning and orchestration. Kops performs the provisioning and orchestration
+itself, and as such is less flexible in deployment platforms. For people with
+familiarity with Ansible, existing Ansible deployments or the desire to run a
+Kubernetes cluster across multiple platforms, Kargo is a good choice. Kops,
+however, is more tightly integrated with the unique features of the clouds it
+supports so it could be a better choice if you know that you will only be using
+one platform for the foreseeable future.
+
+Kargo vs [Kubeadm](https://github.com/kubernetes/kubeadm)
+------------------
+
+Kubeadm provides domain Knowledge of Kubernetes clusters' life cycle
+management, including self-hosted layouts, dynamic discovery services and so
+on. Had it belong to the new [operators world](https://coreos.com/blog/introducing-operators.html),
+it would've likely been named a "Kubernetes cluster operator". Kargo however,
+does generic configuration management tasks from the "OS operators" ansible
+world, plus some initial K8s clustering (with networking plugins included) and
+control plane bootstrapping. Kargo [strives](https://github.com/kubernetes-incubator/kargo/issues/553)
+to adopt kubeadm as a tool in order to consume life cycle management domain
+knowledge from it and offload generic OS configuration things from it, which
+hopefully benefits both sides.

docs/dns-stack.md

@@ -9,47 +9,14 @@ to serve as an authoritative DNS server for a given ``dns_domain`` and its
 Other nodes in the inventory, like external storage nodes or a separate etcd cluster
 node group, considered non-cluster and left up to the user to configure DNS resolve.
 
-Note, custom ``ndots`` values affect only the dnsmasq daemon set (explained below).
-While the kubedns has the ``ndots=5`` hardcoded, which is not recommended due to
-[DNS performance reasons](https://github.com/kubernetes/kubernetes/issues/14051).
-You can use config maps for the kubedns app to workaround the issue, which is
-yet in the Kargo scope.
 
-Additional search (sub)domains may be defined in the ``searchdomains``
+DNS variables
-and ``ndots`` vars. And additional recursive DNS resolvers in the `` upstream_dns_servers``,
+=============
-``nameservers`` vars. Intranet/cloud provider DNS resolvers should be specified
-in the first place, followed by external resolvers, for example:
 
-```
+There are several global variables which can be used to modify DNS settings:
-skip_dnsmasq: true
-nameservers: [8.8.8.8]
-upstream_dns_servers: [172.18.32.6]
-```
-or
-```
-skip_dnsmasq: false
-upstream_dns_servers: [172.18.32.6, 172.18.32.7, 8.8.8.8, 8.8.8.4]
-```
-The vars are explained below. For the early cluster deployment stage, when there
-is yet K8s cluster and apps exist, a user may expect local repos to be
-accessible via authoritative intranet resolvers. For that case, if none custom vars
-was specified, the default resolver is set to either the cloud provider default
-or `8.8.8.8`. And domain is set to the default ``dns_domain`` value as well.
-Later, the nameservers will be reconfigured to the DNS service IP that Kargo
-configures for K8s cluster.
 
-Also note, existing records will be purged from the `/etc/resolv.conf`,
+#### ndots
-including resolvconf's base/head/cloud-init config files and those that come from dhclient.
+ndots value to be used in ``/etc/resolv.conf``
-This is required for hostnet pods networking and for [kubelet to not exceed search domains
-limits](https://github.com/kubernetes/kubernetes/issues/9229).
-
-Instead, new domain, search, nameserver records and options will be defined from the
-aforementioned vars:
-* Superseded via dhclient's DNS update hook.
-* Generated via cloud-init (CoreOS only).
-* Statically defined in the `/etc/resolv.conf`, if none of above is applicable.
-* Resolvconf's head/base files are disabled from populating anything into the
-  `/etc/resolv.conf`.
 
 It is important to note that multiple search domains combined with high ``ndots``
 values lead to poor performance of DNS stack, so please choose it wisely.
@@ -58,48 +25,97 @@ replies for [bogus internal FQDNS](https://github.com/kubernetes/kubernetes/issu
 before it even hits the kubedns app. This enables dnsmasq to serve as a
 protective, but still recursive resolver in front of kubedns.
 
-DNS configuration details
+#### searchdomains
--------------------------
+Custom search domains to be added in addition to the cluster search domains (``default.svc.{{ dns_domain }}, svc.{{ dns_domain }}``).
 
-Here is an approximate picture of how DNS things working and
+Most Linux systems limit the total number of search domains to 6 and the total length of all search domains
-being configured by Kargo ansible playbooks:
+to 256 characters. Depending on the length of ``dns_domain``, you're limitted to less then the total limit.
 
-![Image](figures/dns.jpeg?raw=true)
+Please note that ``resolvconf_mode: docker_dns`` will automatically add your systems search domains as
+additional search domains. Please take this into the accounts for the limits.
 
-Note that an additional dnsmasq daemon set is installed by Kargo
+#### nameservers
-by default. Kubelet will configure DNS base of all pods to use the
+This variable is only used by ``resolvconf_mode: host_resolvconf``. These nameservers are added to the hosts
-given dnsmasq cluster IP, which is defined via the ``dns_server`` var.
+``/etc/resolv.conf`` *after* ``upstream_dns_servers`` and thus serve as backup nameservers. If this variable
-The dnsmasq forwards requests for a given cluster ``dns_domain`` to
+is not set, a default resolver is chosen (depending on cloud provider or 8.8.8.8 when no cloud provider is specified).
-Kubedns's SkyDns service. The SkyDns server is configured to be an
-authoritative DNS server for the given cluser domain (and its subdomains
-up to ``ndots:5`` depth). Note: you should scale its replication controller
-up, if SkyDns chokes. These two layered DNS forwarders provide HA for the
-DNS cluster IP endpoint, which is a critical moving part for Kubernetes apps.
 
-Nameservers are as well configured in the hosts' ``/etc/resolv.conf`` files,
+#### upstream_dns_servers
-as the given DNS cluster IP merged with ``nameservers`` values. While the
+DNS servers to be added *after* the cluster DNS. Used by all ``resolvconf_mode`` modes. These serve as backup
-DNS cluster IP merged with the ``upstream_dns_servers`` defines additional
+DNS servers in early cluster deployment when no cluster DNS is available yet. These are also added as upstream
-nameservers for the aforementioned nsmasq daemon set running on all hosts.
+DNS servers used by ``dnsmasq`` (when deployed with ``dns_mode: dnsmasq_kubedns``).
-This mitigates existing Linux limitation of max 3 nameservers in the
-``/etc/resolv.conf`` and also brings an additional caching layer for the
-clustered DNS services.
 
-You can skip the dnsmasq daemon set install steps by setting the
+DNS modes supported by kargo
-``skip_dnsmasq: true``. This may be the case, if you're fine with
+============================
-the nameservers limitation. Sadly, there is no way to work around the
+
-search domain limitations of a 256 chars and 6 domains. Thus, you can
+You can modify how kargo sets up DNS for your cluster with the variables ``dns_mode`` and ``resolvconf_mode``.
-use the ``searchdomains`` var to define no more than a three custom domains.
+
-Remaining three slots are reserved for K8s cluster default subdomains.
+## dns_mode
+``dns_mode`` configures how kargo will setup cluster DNS. There are three modes available:
+
+#### dnsmasq_kubedns (default)
+This installs an additional dnsmasq DaemonSet which gives more flexibility and lifts some
+limitations (e.g. number of nameservers). Kubelet is instructed to use dnsmasq instead of kubedns/skydns.
+It is configured to forward all DNS queries belonging to cluster services to kubedns/skydns. All
+other queries are forwardet to the nameservers found in ``upstream_dns_servers`` or ``default_resolver``
+
+#### kubedns
+This does not install the dnsmasq DaemonSet and instructs kubelet to directly use kubedns/skydns for
+all queries.
+
+#### none
+This does not install any of dnsmasq and kubedns/skydns. This basically disables cluster DNS completely and
+leaves you with a non functional cluster.
+
+## resolvconf_mode
+``resolvconf_mode`` configures how kargo will setup DNS for ``hostNetwork: true`` PODs and non-k8s containers.
+There are three modes available:
+
+#### docker_dns (default)
+This sets up the docker daemon with additional --dns/--dns-search/--dns-opt flags.
+
+The following nameservers are added to the docker daemon (in the same order as listed here):
+* cluster nameserver (depends on dns_mode)
+* content of optional upstream_dns_servers variable
+* host system nameservers (read from hosts /etc/resolv.conf)
+
+The following search domains are added to the docker daemon (in the same order as listed here):
+* cluster domains (``default.svc.{{ dns_domain }}``, ``svc.{{ dns_domain }}``)
+* content of optional searchdomains variable
+* host system search domains (read from hosts /etc/resolv.conf)
+
+The following dns options are added to the docker daemon
+* ndots:{{ ndots }}
+* timeout:2
+* attempts:2
+
+For normal PODs, k8s will ignore these options and setup its own DNS settings for the PODs, taking
+the --cluster_dns (either dnsmasq or kubedns, depending on dns_mode) kubelet option into account.
+For ``hostNetwork: true`` PODs however, k8s will let docker setup DNS settings. Docker containers which
+are not started/managed by k8s will also use these docker options.
+
+The host system name servers are added to ensure name resolution is also working while cluster DNS is not
+running yet. This is especially important in early stages of cluster deployment. In this early stage,
+DNS queries to the cluster DNS will timeout after a few seconds, resulting in the system nameserver being
+used as a backup nameserver. After cluster DNS is running, all queries will be answered by the cluster DNS
+servers, which in turn will forward queries to the system nameserver if required.
+
+#### host_resolvconf
+This activates the classic kargo behaviour that modifies the hosts ``/etc/resolv.conf`` file and dhclient
+configuration to point to the cluster dns server (either dnsmasq or kubedns, depending on dns_mode).
+
+As cluster DNS is not available on early deployment stage, this mode is split into 2 stages. In the first
+stage (``dns_early: true``), ``/etc/resolv.conf`` is configured to use the DNS servers found in ``upstream_dns_servers``
+and ``nameservers``. Later, ``/etc/resolv.conf`` is reconfigured to use the cluster DNS server first, leaving
+the other nameservers as backups.
+
+Also note, existing records will be purged from the `/etc/resolv.conf`,
+including resolvconf's base/head/cloud-init config files and those that come from dhclient.
+
+#### none
+Does nothing regarding ``/etc/resolv.conf``. This leaves you with a cluster that works as expected in most cases.
+The only exception is that ``hostNetwork: true`` PODs and non-k8s managed containers will not be able to resolve
+cluster service names.
 
-When dnsmasq skipped, Kargo redefines the DNS cluster IP to point directly
-to SkyDns cluster IP ``skydns_server`` and configures Kubelet's
-``--dns_cluster`` to use that IP as well. While this greatly simplifies
-things, it comes by the price of limited nameservers though. As you know now,
-the DNS cluster IP takes a slot in the ``/etc/resolv.conf``, thus you can
-specify no more than a two nameservers for infra and/or external use.
-Those may be specified either in ``nameservers`` or ``upstream_dns_servers``
-and will be merged together with the ``skydns_server`` IP into the hots'
-``/etc/resolv.conf``.
 
 Limitations
 -----------

inventory/group_vars/all.yml

@@ -14,9 +14,6 @@ kube_script_dir: "{{ bin_dir }}/kubernetes-scripts"
 kube_manifest_dir: "{{ kube_config_dir }}/manifests"
 system_namespace: kube-system
 
-# Logging directory (sysvinit systems)
-kube_log_dir: "/var/log/kubernetes"
-
 # This is where all the cert scripts and certs will be located
 kube_cert_dir: "{{ kube_config_dir }}/ssl"
 
@@ -136,21 +133,21 @@ kube_apiserver_insecure_port: 8080 # (http)
 # into appropriate IP addresses. It's highly advisable to run such DNS server,
 # as it greatly simplifies configuration of your applications - you can use
 # service names instead of magic environment variables.
-# You still must manually configure all your containers to use this DNS server,
-# Kubernetes won't do this for you (yet).
 
-# Do not install additional dnsmasq
+# Can be dnsmasq_kubedns, kubedns or none
-skip_dnsmasq: false
+dns_mode: dnsmasq_kubedns
-# Upstream dns servers used by dnsmasq
+
+# Can be docker_dns, host_resolvconf or none
+resolvconf_mode: docker_dns
+
+## Upstream dns servers used by dnsmasq
 #upstream_dns_servers:
 #  - 8.8.8.8
 #  - 8.8.4.4
-#
+
-# # Use dns server : https://github.com/ansibl8s/k8s-skydns/blob/master/skydns-README.md
-dns_setup: true
 dns_domain: "{{ cluster_name }}"
-#
+
-# # Ip address of the kubernetes skydns service
+# Ip address of the kubernetes skydns service
 skydns_server: "{{ kube_service_addresses|ipaddr('net')|ipaddr(3)|ipaddr('address') }}"
 dns_server: "{{ kube_service_addresses|ipaddr('net')|ipaddr(2)|ipaddr('address') }}"
 
@@ -200,3 +197,8 @@ k8s_image_pull_policy: IfNotPresent
 # default packages to install within the cluster
 kpm_packages: []
 #  - name: kube-system/grafana
+
+# Settings for containerized control plane (etcd/kubelet)
+rkt_version: 1.21.0
+etcd_deployment_type: docker
+kubelet_deployment_type: docker

roles/dnsmasq/defaults/main.yml

@@ -18,9 +18,6 @@ dnsmasq_version: 2.72
 dnsmasq_image_repo: "andyshinn/dnsmasq"
 dnsmasq_image_tag: "{{ dnsmasq_version }}"
 
-# Skip dnsmasq setup
-skip_dnsmasq: false
-
 # Limits for dnsmasq/kubedns apps
 dns_cpu_limit: 100m
 dns_memory_limit: 170Mi

roles/dnsmasq/meta/main.yml

@@ -2,5 +2,5 @@
 dependencies:
   - role: download
     file: "{{ downloads.dnsmasq }}"
-    when: not skip_dnsmasq|default(false) and download_localhost|default(false)
+    when: dns_mode == 'dnsmasq_kubedns' and download_localhost|default(false)
     tags: [download, dnsmasq]

roles/dnsmasq/templates/01-kube-dns.conf.j2

@@ -15,15 +15,17 @@ local=/{{ bogus_domains }}
 {% for srv in upstream_dns_servers %}
 server={{ srv }}
 {% endfor %}
-{% else %}
+no-resolv
+{% elif resolvconf_mode == 'host_resolvconf' %}
+{# The default resolver is only needed when the hosts resolv.conf was modified by us. If it was not modified, we can rely on dnsmasq to reuse the systems resolv.conf #}
 server={{ default_resolver }}
+no-resolv
 {% endif %}
 
 {% if kube_log_level == '4' %}
 log-queries
 {% endif %}
 bogus-priv
-no-resolv
 no-negcache
 cache-size=1000
 max-cache-ttl=10

roles/docker/defaults/main.yml

@@ -1,4 +1,4 @@
-docker_version: '1.10'
+docker_version: '1.12'
 
 docker_package_info:
   pkgs:

roles/docker/handlers/main.yml

@@ -10,13 +10,12 @@
 
 - name : Docker | reload systemd
   shell: systemctl daemon-reload
-  when: ansible_service_mgr == "systemd"
 
 - name: Docker | reload docker.socket
   service:
     name: docker.socket
     state: restarted
-  when: ansible_os_family == 'CoreOS'
+  when: ansible_os_family in ['CoreOS', 'Container Linux by CoreOS']
 
 - name: Docker | reload docker
   service:

roles/docker/tasks/main.yml

@@ -14,13 +14,17 @@
       skip: true
   tags: facts
 
+- include: set_facts_dns.yml
+  when: dns_mode != 'none' and resolvconf_mode == 'docker_dns'
+  tags: facts
+
 - name: check for minimum kernel version
   fail:
     msg: >
           docker requires a minimum kernel version of
           {{ docker_kernel_min_version }} on
           {{ ansible_distribution }}-{{ ansible_distribution_version }}
-  when: (ansible_os_family != "CoreOS") and (ansible_kernel|version_compare(docker_kernel_min_version, "<"))
+  when: (not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]) and (ansible_kernel|version_compare(docker_kernel_min_version, "<"))
   tags: facts
 
 - name: ensure docker repository public key is installed
@@ -34,7 +38,7 @@
   retries: 4
   delay: "{{ retry_stagger | random + 3 }}"
   with_items: "{{ docker_repo_key_info.repo_keys }}"
-  when: ansible_os_family != "CoreOS"
+  when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
 - name: ensure docker repository is enabled
   action: "{{ docker_repo_info.pkg_repo }}"
@@ -42,14 +46,13 @@
     repo: "{{item}}"
     state: present
   with_items: "{{ docker_repo_info.repos }}"
-  when: (ansible_os_family != "CoreOS") and (docker_repo_info.repos|length > 0)
+  when: (not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]) and (docker_repo_info.repos|length > 0)
 
 - name: Configure docker repository on RedHat/CentOS
   copy:
     src: "rh_docker.repo"
     dest: "/etc/yum.repos.d/docker.repo"
-  when: ansible_distribution in ["CentOS","RedHat"] and
+  when: ansible_distribution in ["CentOS","RedHat"]
-        ansible_distribution_major_version >= 7
 
 - name: ensure docker packages are installed
   action: "{{ docker_package_info.pkg_mgr }}"
@@ -62,15 +65,17 @@
   retries: 4
   delay: "{{ retry_stagger | random + 3 }}"
   with_items: "{{ docker_package_info.pkgs }}"
-  when: (ansible_os_family != "CoreOS") and (docker_package_info.pkgs|length > 0)
+  when: (not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]) and (docker_package_info.pkgs|length > 0)
 
-- name: Set docker upstart and sysvinit config
+- name: check minimum docker version for docker_dns mode. You need at least docker version >= 1.12 for resolvconf_mode=docker_dns
-  include: non-systemd.yml
+  shell: docker version -f "{{ '{{' }}.Client.Version{{ '}}' }}"
-  when: ansible_service_mgr in ["sysvinit","upstart"]
+  register: docker_version
+  failed_when: docker_version.stdout|version_compare('1.12', '<')
+  changed_when: false
+  when: dns_mode != 'none' and resolvconf_mode == 'docker_dns'
 
 - name: Set docker systemd config
   include: systemd.yml
-  when: ansible_service_mgr == "systemd"
 
 - name: ensure docker service is started and enabled
   service:

roles/docker/tasks/non-systemd.yml

@@ -1,66 +0,0 @@
----
-# This uses lineinfile instead of templates for idempotency in files that may be modified by different roles
-- name: Set docker options config file path
-  set_fact:
-    docker_options_file: >-
-      {%- if ansible_os_family == "Debian" -%}/etc/default/docker{%- elif ansible_os_family == "RedHat" -%}/etc/sysconfig/docker{%- endif -%}
-  tags: facts
-
-- name: Set docker options config variable name
-  set_fact:
-    docker_options_name: >-
-      {%- if ansible_os_family == "Debian" -%}DOCKER_OPTS{%- elif ansible_os_family == "RedHat" -%}other_args{%- endif -%}
-  tags: facts
-
-- name: Set docker options config value to be written
-  set_fact:
-    docker_options_value: '"{{ docker_options }} $DOCKER_NETWORK_OPTIONS $DOCKER_STORAGE_OPTIONS $INSECURE_REGISTRY"'
-  tags: facts
-
-- name: Set docker options config line to be written
-  set_fact:
-    docker_options_line: "{{ docker_options_name }}={{ docker_options_value }}"
-  tags: facts
-
-- name: Set docker proxy lines to be written
-  set_fact:
-    docker_proxy_lines:
-     - { name: "HTTP_PROXY", value: '"{{ http_proxy }}"' }
-     - { name: "HTTPS_PROXY", value: '"{{ https_proxy }}"' }
-     - { name: "NO_PROXY", value: '"{{ no_proxy }}"' }
-  tags: facts
-
-- name: Remove docker daemon proxy config lines that don't match desired lines
-  lineinfile:
-    dest: "{{ docker_options_file }}"
-    regexp: "^{{ item.name }}=(?!{{ item.value|regex_escape() }})"
-    state: absent
-  with_items: "{{ docker_proxy_lines|default([]) }}"
-  when: item.value is defined and (item.value | trim != '')
-
-- name: Write docker daemon proxy config lines
-  lineinfile:
-    dest: "{{ docker_options_file }}"
-    line: "{{ item.name }}={{ item.value }}"
-    owner: root
-    group: root
-    mode: 0644
-  with_items: "{{ docker_proxy_lines|default([]) }}"
-  when: item.value is defined and (item.value | trim != '')
-
-- name: Remove docker daemon options lines that don't match desired line
-  lineinfile:
-    dest: "{{ docker_options_file }}"
-    regexp: "^(DOCKER_OPTS|OPTIONS|other_args)=(?!{{ docker_options_value|regex_escape() }})"
-    state: absent
-
-- name: Write docker daemon options line
-  lineinfile:
-    dest: "{{ docker_options_file }}"
-    line: "{{ docker_options_line }}"
-    owner: root
-    group: root
-    mode: 0644
-  notify: restart docker
-
-- meta: flush_handlers

roles/docker/tasks/set_facts_dns.yml

@@ -0,0 +1,61 @@
+---
+
+- name: set dns server for docker
+  set_fact:
+    docker_dns_servers: |-
+      {%- if dns_mode == 'kubedns' -%}
+        {{ [ skydns_server ] }}
+      {%- elif dns_mode == 'dnsmasq_kubedns' -%}
+        {{ [ dns_server ] }}
+      {%- endif -%}
+
+- name: set base docker dns facts
+  set_fact:
+    docker_dns_search_domains:
+      - 'default.svc.{{ dns_domain }}'
+      - 'svc.{{ dns_domain }}'
+    docker_dns_options:
+      - ndots:{{ ndots }}
+      - timeout:2
+      - attempts:2
+
+- 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'
+
+- name: add global searchdomains
+  set_fact:
+    docker_dns_search_domains: "{{ docker_dns_search_domains + searchdomains|default([]) }}"
+
+- name: check system nameservers
+  shell: grep "^nameserver" /etc/resolv.conf | sed 's/^nameserver\s*//'
+  changed_when: False
+  register: system_nameservers
+
+- name: check system search domains
+  shell: grep "^search" /etc/resolv.conf | sed 's/^search\s*//'
+  changed_when: False
+  register: system_search_domains
+
+- name: add system nameservers to docker options
+  set_fact:
+    docker_dns_servers: "{{ docker_dns_servers | union(system_nameservers.stdout_lines) | unique }}"
+  when: system_nameservers.stdout != ""
+
+- name: add system search domains to docker options
+  set_fact:
+    docker_dns_search_domains: "{{ docker_dns_search_domains | union(system_search_domains.stdout.split(' ')|default([])) | unique }}"
+  when: system_search_domains.stdout != "" 
+
+- name: check number of nameservers
+  fail: msg="Too many nameservers"
+  when: docker_dns_servers|length > 3
+
+- name: check number of search domains
+  fail: msg="Too many search domains"
+  when: docker_dns_search_domains|length > 6
+
+- name: check length of search domains
+  fail: msg="Search domains exceeded limit of 256 characters"
+  when: docker_dns_search_domains|join(' ')|length > 256

roles/docker/tasks/systemd.yml

@@ -13,7 +13,7 @@
     src: docker.service.j2
     dest: /etc/systemd/system/docker.service
   register: docker_service_file
-  when: ansible_os_family != "CoreOS"
+  when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
 - name: Write docker options systemd drop-in
   template:
@@ -21,4 +21,11 @@
     dest: "/etc/systemd/system/docker.service.d/docker-options.conf"
   notify: restart docker
 
+- name: Write docker dns systemd drop-in
+  template:
+    src: docker-dns.conf.j2
+    dest: "/etc/systemd/system/docker.service.d/docker-dns.conf"
+  notify: restart docker
+  when: dns_mode != 'none' and resolvconf_mode == 'docker_dns'
+
 - meta: flush_handlers

roles/docker/templates/docker-dns.conf.j2

@@ -0,0 +1,6 @@
+[Service]
+Environment="DOCKER_DNS_OPTIONS=\
+    {% for d in docker_dns_servers %}--dns {{ d }} {% endfor %} \
+    {% for d in docker_dns_search_domains %}--dns-search {{ d }} {% endfor %} \
+    {% for o in docker_dns_options %}--dns-opt {{ o }} {% endfor %} \
+"

roles/docker/templates/docker.service.j2

@@ -22,6 +22,7 @@ ExecStart={{ docker_bin_dir }}/docker daemon \
           $DOCKER_OPTS \
           $DOCKER_STORAGE_OPTIONS \
           $DOCKER_NETWORK_OPTIONS \
+          $DOCKER_DNS_OPTIONS \
           $INSECURE_REGISTRY
 TasksMax=infinity
 LimitNOFILE=1048576

roles/docker/vars/centos-6.yml

@@ -1,16 +0,0 @@
-docker_kernel_min_version: '2.6.32-431'
-
-# 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/debian.yml

@@ -1,10 +1,8 @@
-docker_kernel_min_version: '3.2'
+docker_kernel_min_version: '3.10'
 
 # https://apt.dockerproject.org/repo/dists/debian-wheezy/main/filelist
 docker_versioned_pkg:
   'latest': docker-engine
-  '1.9': docker-engine=1.9.1-0~{{ ansible_distribution_release|lower }}
-  '1.10': docker-engine=1.10.3-0~{{ ansible_distribution_release|lower }}
   '1.11': docker-engine=1.11.2-0~{{ ansible_distribution_release|lower }}
   '1.12': docker-engine=1.12.5-0~debian-{{ ansible_distribution_release|lower }}
 

roles/docker/vars/fedora.yml

@@ -2,8 +2,6 @@ docker_kernel_min_version: '0'
 
 docker_versioned_pkg:
   'latest': docker
-  '1.9': docker-1:1.9.1
-  '1.10': docker-1:1.10.1
   '1.11': docker-1:1.11.2
   '1.12': docker-1:1.12.5
 

roles/docker/vars/ubuntu-16.04.yml

@@ -1,29 +0,0 @@
----
-docker_version: '1.11'
-docker_kernel_min_version: '3.2'
-
-# https://apt.dockerproject.org/repo/dists/ubuntu-xenial/main/filelist
-docker_versioned_pkg:
-  'latest': docker-engine
-  '1.11': docker-engine=1.11.1-0~{{ ansible_distribution_release|lower }}
-  '1.12': docker-engine=1.12.5-0~ubuntu-{{ ansible_distribution_release|lower }}
-
-docker_package_info:
-  pkg_mgr: apt
-  pkgs:
-    - name: "{{ docker_versioned_pkg[docker_version | string] }}"
-      force: yes
-
-docker_repo_key_info:
-  pkg_key: apt_key
-  keyserver: hkp://p80.pool.sks-keyservers.net:80
-  repo_keys:
-    - 58118E89F3A912897C070ADBF76221572C52609D
-
-docker_repo_info:
-  pkg_repo: apt_repository
-  repos:
-    - >
-       deb https://apt.dockerproject.org/repo
-       {{ ansible_distribution|lower }}-{{ ansible_distribution_release|lower }}
-       main

roles/docker/vars/ubuntu.yml

@@ -1,11 +1,10 @@
+---
+docker_version: '1.12'
+docker_kernel_min_version: '3.10'
 
-docker_kernel_min_version: '3.2'
+# https://apt.dockerproject.org/repo/dists/ubuntu-xenial/main/filelist
-
-# https://apt.dockerproject.org/repo/dists/ubuntu-trusty/main/filelist
 docker_versioned_pkg:
   'latest': docker-engine
-  '1.9': docker-engine=1.9.0-0~{{ ansible_distribution_release|lower }}
-  '1.10': docker-engine=1.10.3-0~{{ ansible_distribution_release|lower }}
   '1.11': docker-engine=1.11.1-0~{{ ansible_distribution_release|lower }}
   '1.12': docker-engine=1.12.5-0~ubuntu-{{ ansible_distribution_release|lower }}
 

roles/download/defaults/main.yml

@@ -2,14 +2,14 @@
 local_release_dir: /tmp
 
 # if this is set to true will only download files once. Doesn't work
-# on CoreOS unless the download_localhost is true and localhost
+# on Container Linux by CoreOS unless the download_localhost is true and localhost
 # is running another OS type. Default compress level is 9 (best).
 download_run_once: False
 download_compress: 9
 
 # if this is set to true, uses the localhost for download_run_once mode
 # (requires docker and sudo to access docker). You may want this option for
-# local caching of docker images or for CoreOS cluster nodes.
+# local caching of docker images or for Container Linux by CoreOS cluster nodes.
 # Otherwise, uses the first node in the kube-master group to store images
 # in the download_run_once mode.
 download_localhost: False
@@ -21,8 +21,8 @@ download_always_pull: False
 etcd_version: v3.0.6
 #TODO(mattymo): Move calico versions to roles/network_plugins/calico/defaults
 # after migration to container download
-calico_version: v1.0.0-beta
+calico_version: "v1.0.0"
-calico_cni_version: v1.4.2
+calico_cni_version: "v1.5.5"
 weave_version: v1.6.1
 flannel_version: v0.6.2
 pod_infra_version: 3.0
@@ -43,15 +43,13 @@ etcd_image_tag: "{{ etcd_version }}"
 flannel_image_repo: "quay.io/coreos/flannel"
 flannel_image_tag: "{{ flannel_version }}"
 calicoctl_image_repo: "calico/ctl"
-# TODO(apanchenko): v1.0.0-beta can't execute `node run` from Docker container
+calicoctl_image_tag: "{{ calico_version }}"
-# for details see https://github.com/projectcalico/calico-containers/issues/1291
-calicoctl_image_tag: "v1.0.0-rc3"
 calico_node_image_repo: "calico/node"
 calico_node_image_tag: "{{ calico_version }}"
 calico_cni_image_repo: "calico/cni"
 calico_cni_image_tag: "{{ calico_cni_version }}"
 calico_policy_image_repo: "calico/kube-policy-controller"
-calico_policy_image_tag: latest
+calico_policy_image_tag: "v0.5.1"
 # TODO(adidenko): switch to "calico/routereflector" when
 # https://github.com/projectcalico/calico-bird/pull/27 is merged
 calico_rr_image_repo: "quay.io/l23network/routereflector"
@@ -115,13 +113,13 @@ downloads:
     version: "{{etcd_version}}"
     dest: "etcd/etcd-{{ etcd_version }}-linux-amd64.tar.gz"
     sha256: >-
-      {%- if etcd_deployment_type == 'docker' -%}{{etcd_digest_checksum|default(None)}}{%- else -%}{{etcd_checksum}}{%- endif -%}
+      {%- if etcd_deployment_type in [ 'docker', 'rkt' ] -%}{{etcd_digest_checksum|default(None)}}{%- else -%}{{etcd_checksum}}{%- endif -%}
     source_url: "{{ etcd_download_url }}"
     url: "{{ etcd_download_url }}"
     unarchive: true
     owner: "etcd"
     mode: "0755"
-    container: "{{ etcd_deployment_type == 'docker' }}"
+    container: "{{ etcd_deployment_type in [ 'docker', 'rkt' ] }}"
     repo: "{{ etcd_image_repo }}"
     tag: "{{ etcd_image_tag }}"
   hyperkube:

roles/download/tasks/main.yml

@@ -48,7 +48,7 @@
   when: "{{ download.enabled|bool and download.container|bool }}"
   tags: bootstrap-os
 
-# This is required for the download_localhost delegate to work smooth with CoreOS cluster nodes
+# This is required for the download_localhost delegate to work smooth with Container Linux by CoreOS cluster nodes
 - name: Hack python binary path for localhost
   raw: sh -c "mkdir -p /opt/bin; ln -sf /usr/bin/python /opt/bin/python"
   when: "{{ download_delegate == 'localhost' }}"
@@ -119,7 +119,7 @@
   delegate_to: "{{ download_delegate }}"
   register: saved
   run_once: true
-  when: (ansible_os_family != "CoreOS" or download_delegate == "localhost") and download_run_once|bool and download.enabled|bool and download.container|bool and (container_changed|bool or not img.stat.exists)
+  when: (not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] or download_delegate == "localhost") and download_run_once|bool and download.enabled|bool and download.container|bool and (container_changed|bool or not img.stat.exists)
 
 - name: Download | copy container images to ansible host
   synchronize:
@@ -128,7 +128,7 @@
     mode: pull
   delegate_to: localhost
   become: false
-  when: ansible_os_family != "CoreOS" and inventory_hostname == groups['kube-master'][0] and download_delegate != "localhost" and download_run_once|bool and download.enabled|bool and download.container|bool and saved.changed
+  when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] and inventory_hostname == groups['kube-master'][0] and download_delegate != "localhost" and download_run_once|bool and download.enabled|bool and download.container|bool and saved.changed
 
 - name: Download | upload container images to nodes
   synchronize:
@@ -141,10 +141,10 @@
   until: get_task|success
   retries: 4
   delay: "{{ retry_stagger | random + 3 }}"
-  when: (ansible_os_family != "CoreOS" and inventory_hostname != groups['kube-master'][0] or download_delegate == "localhost") and download_run_once|bool and download.enabled|bool and download.container|bool
+  when: (not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] and inventory_hostname != groups['kube-master'][0] or download_delegate == "localhost") and download_run_once|bool and download.enabled|bool and download.container|bool
   tags: [upload, upgrade]
 
 - name: Download | load container images
   shell: "{{ docker_bin_dir }}/docker load < {{ fname }}"
-  when: (ansible_os_family != "CoreOS" and inventory_hostname != groups['kube-master'][0] or download_delegate == "localhost") and download_run_once|bool and download.enabled|bool and download.container|bool
+  when: (not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] and inventory_hostname != groups['kube-master'][0] or download_delegate == "localhost") and download_run_once|bool and download.enabled|bool and download.container|bool
   tags: [upload, upgrade]

roles/etcd/handlers/main.yml

@@ -8,7 +8,6 @@
 
 - name: etcd | reload systemd
   command: systemctl daemon-reload
-  when: ansible_service_mgr == "systemd"
 
 - name: reload etcd
   service:

roles/etcd/meta/main.yml

@@ -2,7 +2,7 @@
 dependencies:
   - role: adduser
     user: "{{ addusers.etcd }}"
-    when: ansible_os_family != 'CoreOS'
+    when: not ansible_os_family in ['CoreOS', 'Container Linux by CoreOS']
   - role: download
     file: "{{ downloads.etcd }}"
     tags: download

roles/etcd/tasks/configure.yml

@@ -16,14 +16,5 @@
     src: "etcd-{{ etcd_deployment_type }}.service.j2"
     dest: /etc/systemd/system/etcd.service
     backup: yes
-  when: ansible_service_mgr == "systemd" and is_etcd_master
+  when: is_etcd_master
-  notify: restart etcd
-
-- name: Configure | Write etcd initd script
-  template:
-    src: "deb-etcd-{{ etcd_deployment_type }}.initd.j2"
-    dest: /etc/init.d/etcd
-    owner: root
-    mode: 0755
-  when: ansible_service_mgr in ["sysvinit","upstart"] and ansible_os_family == "Debian" and is_etcd_master
   notify: restart etcd

roles/etcd/tasks/gen_certs.yml

@@ -40,7 +40,7 @@
                     {{ m }}
                   {% endif %}
                 {% endfor %}"
-    - HOSTS: "{% for h in groups['k8s-cluster'] %}
+    - HOSTS: "{% for h in (groups['k8s-cluster'] + groups['calico-rr']|default([]))|unique %}
                 {% if hostvars[h].sync_certs|default(false) %}
                     {{ h }}
                 {% endif %}
@@ -65,7 +65,7 @@
                      'member-{{ inventory_hostname }}-key.pem'
                      ]
     all_node_certs: "['ca.pem',
-                    {% for node in groups['k8s-cluster'] %}
+                    {% for node in (groups['k8s-cluster'] + groups['calico-rr']|default([]))|unique %}
                     'node-{{ node }}.pem',
                     'node-{{ node }}-key.pem',
                     {% endfor %}]"
@@ -73,7 +73,9 @@
   tags: facts
 
 - name: Gen_certs | Gather etcd master certs
-  shell: "tar cfz - -C {{ etcd_cert_dir }} {{ my_master_certs|join(' ') }} {{ all_node_certs|join(' ') }}| base64 --wrap=0"
+  shell: "tar cfz - -C {{ etcd_cert_dir }} -T /dev/stdin <<< {{ my_master_certs|join(' ') }} {{ all_node_certs|join(' ') }} | base64 --wrap=0"
+  args:
+    executable: /bin/bash
   register: etcd_master_cert_data
   delegate_to: "{{groups['etcd'][0]}}"
   when: inventory_hostname in groups['etcd'] and sync_certs|default(false) and
@@ -81,21 +83,28 @@
   notify: set etcd_secret_changed
 
 - name: Gen_certs | Gather etcd node certs
-  shell: "tar cfz - -C {{ etcd_cert_dir }} {{ my_node_certs|join(' ') }} | base64 --wrap=0"
+  shell: "tar cfz - -C {{ etcd_cert_dir }} -T /dev/stdin <<< {{ my_node_certs|join(' ') }} | base64 --wrap=0"
+  args:
+    executable: /bin/bash
   register: etcd_node_cert_data
   delegate_to: "{{groups['etcd'][0]}}"
-  when: inventory_hostname in groups['k8s-cluster'] and sync_certs|default(false) and
+  when: (('calico-rr' in groups and inventory_hostname in groups['calico-rr']) or
-        inventory_hostname not in groups['etcd']
+        inventory_hostname in groups['k8s-cluster']) and
+        sync_certs|default(false) and inventory_hostname not in groups['etcd']
   notify: set etcd_secret_changed
 
 - name: Gen_certs | Copy certs on masters
-  shell: "echo '{{etcd_master_cert_data.stdout|quote}}' | base64 -d | tar xz -C {{ etcd_cert_dir }}"
+  shell: "base64 -d <<< '{{etcd_master_cert_data.stdout|quote}}' | tar xz -C {{ etcd_cert_dir }}"
+  args:
+    executable: /bin/bash
   changed_when: false
   when: inventory_hostname in groups['etcd'] and sync_certs|default(false) and
         inventory_hostname != groups['etcd'][0]
 
 - name: Gen_certs | Copy certs on nodes
-  shell: "echo '{{etcd_node_cert_data.stdout|quote}}' | base64 -d | tar xz -C {{ etcd_cert_dir }}"
+  shell: "base64 -d <<< '{{etcd_node_cert_data.stdout|quote}}' | tar xz -C {{ etcd_cert_dir }}"
+  args:
+    executable: /bin/bash
   changed_when: false
   when: sync_certs|default(false) and
         inventory_hostname not in groups['etcd']
@@ -121,7 +130,7 @@
       /usr/local/share/ca-certificates/etcd-ca.crt
       {%- elif ansible_os_family == "RedHat" -%}
       /etc/pki/ca-trust/source/anchors/etcd-ca.crt
-      {%- elif ansible_os_family == "CoreOS" -%}
+      {%- elif ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] -%}
       /etc/ssl/certs/etcd-ca.pem
       {%- endif %}
   tags: facts
@@ -133,9 +142,9 @@
     remote_src: true
   register: etcd_ca_cert
 
-- name: Gen_certs | update ca-certificates (Debian/Ubuntu/CoreOS)
+- name: Gen_certs | update ca-certificates (Debian/Ubuntu/Container Linux by CoreOS)
   command: update-ca-certificates
-  when: etcd_ca_cert.changed and ansible_os_family in ["Debian", "CoreOS"]
+  when: etcd_ca_cert.changed and ansible_os_family in ["Debian", "Container Linux by CoreOS"]
 
 - name: Gen_certs | update ca-certificates (RedHat)
   command: update-ca-trust extract

roles/etcd/tasks/install_docker.yml

@@ -1,17 +1,6 @@
 ---
-- name: Install | Copy etcd binary from downloaddir
-  command: rsync -piu "{{ etcd_bin_dir }}/etcd" "{{ bin_dir }}/etcd"
-  when: etcd_deployment_type == "host"
-  register: etcd_copy
-  changed_when: false
-
-- name: Install | Copy etcdctl binary from downloaddir
-  command: rsync -piu "{{ etcd_bin_dir }}/etcdctl" "{{ bin_dir }}/etcdctl"
-  when: etcd_deployment_type == "host"
-  changed_when: false
-
 #Plan A: no docker-py deps
-- name: Install | Copy etcdctl binary from container
+- name: Install | Copy etcdctl binary from docker container
   command: sh -c "{{ docker_bin_dir }}/docker rm -f etcdctl-binarycopy;
            {{ docker_bin_dir }}/docker create --name etcdctl-binarycopy {{ etcd_image_repo }}:{{ etcd_image_tag }} &&
            {{ docker_bin_dir }}/docker cp etcdctl-binarycopy:{{ etcd_container_bin_dir }}etcdctl {{ bin_dir }}/etcdctl &&

roles/etcd/tasks/install_host.yml

@@ -0,0 +1,9 @@
+---
+- name: Install | Copy etcd binary from downloaddir
+  command: rsync -piu "{{ etcd_bin_dir }}/etcd" "{{ bin_dir }}/etcd"
+  register: etcd_copy
+  changed_when: false
+
+- name: Install | Copy etcdctl binary from downloaddir
+  command: rsync -piu "{{ etcd_bin_dir }}/etcdctl" "{{ bin_dir }}/etcdctl"
+  changed_when: false

roles/etcd/tasks/install_rkt.yml

@@ -0,0 +1,26 @@
+---
+- name: Trust etcd container
+  command: >-
+    /usr/bin/rkt trust
+    --skip-fingerprint-review
+    --root
+    https://quay.io/aci-signing-key
+  register: etcd_rkt_trust_result
+  until: etcd_rkt_trust_result.rc == 0
+  retries: 4
+  delay: "{{ retry_stagger | random + 3 }}"
+  changed_when: false
+
+- name: Install | Copy etcdctl binary from rkt container
+  command: >-
+    /usr/bin/rkt run
+    --volume=bin-dir,kind=host,source={{ bin_dir}},readOnly=false
+    --mount=volume=bin-dir,target=/host/bin
+    {{ etcd_image_repo }}:{{ etcd_image_tag }}
+    --name=etcdctl-binarycopy
+    --exec=/bin/cp -- {{ etcd_container_bin_dir }}/etcdctl /host/bin/etcdctl
+  register: etcd_task_result
+  until: etcd_task_result.rc == 0
+  retries: 4
+  delay: "{{ retry_stagger | random + 3 }}"
+  changed_when: false

roles/etcd/tasks/main.yml

@@ -5,7 +5,7 @@
   tags: [etcd-secrets, facts]
 - include: gen_certs.yml
   tags: etcd-secrets
-- include: install.yml
+- include: "install_{{ etcd_deployment_type }}.yml"
   when: is_etcd_master
   tags: upgrade
 - include: set_cluster_health.yml

roles/etcd/templates/deb-etcd-docker.initd.j2

@@ -1,120 +0,0 @@
-#!/bin/sh
-set -a
-
-### BEGIN INIT INFO
-# Provides:   etcd
-# Required-Start:    $local_fs $network $syslog
-# Required-Stop:
-# Default-Start:     2 3 4 5
-# Default-Stop:      0 1 6
-# Short-Description: etcd distributed k/v store
-# Description:
-#   etcd is a distributed, consistent key-value store for shared configuration and service discovery
-### END INIT INFO
-
-PATH=/sbin:/usr/sbin:/bin/:/usr/bin
-DESC="etcd k/v store"
-NAME=etcd
-DAEMON={{ docker_bin_dir }}/docker
-DAEMON_EXEC=`basename $DAEMON`
-DAEMON_ARGS="run --restart=on-failure:5 --env-file=/etc/etcd.env \
---net=host \
--v /etc/ssl/certs:/etc/ssl/certs:ro \
--v /var/lib/etcd:/var/lib/etcd:rw \
--v {{ etcd_cert_dir }}:{{ etcd_cert_dir }}:ro \
---name={{ etcd_member_name | default("etcd") }} \
-{{ etcd_image_repo }}:{{ etcd_image_tag }} \
-{% if etcd_after_v3 %}
-{{ etcd_container_bin_dir }}etcd
-{% endif %}"
-
-SCRIPTNAME=/etc/init.d/$NAME
-DAEMON_USER=root
-STOP_SCHEDULE="${STOP_SCHEDULE:-QUIT/5/TERM/5/KILL/5}"
-PID=/var/run/etcd.pid
-
-# Exit if the binary is not present
-[ -x "$DAEMON" ] || exit 0
-
-# Define LSB log_* functions.
-# Depend on lsb-base (>= 3.2-14) to ensure that this file is present
-# and status_of_proc is working.
-. /lib/lsb/init-functions
-
-do_status()
-{
-    status_of_proc -p $PID "$DAEMON" "$NAME" && exit 0 || exit $?
-}
-
-# Function that starts the daemon/service
-#
-do_start()
-{
-    {{ docker_bin_dir }}/docker rm -f {{ etcd_member_name | default("etcd") }} &>/dev/null || true
-    sleep 1
-    start-stop-daemon --background --start --quiet --make-pidfile --pidfile $PID --user $DAEMON_USER --exec $DAEMON -- \
-        $DAEMON_ARGS \
-        || return 2
-}
-
-#
-# Function that stops the daemon/service
-#
-do_stop()
-{
-    start-stop-daemon --stop --quiet --retry=$STOP_SCHEDULE --pidfile $PID --name $DAEMON_EXEC
-    RETVAL="$?"
-
-    sleep 1
-    return "$RETVAL"
-}
-
-
-case "$1" in
-  start)
-        log_daemon_msg "Starting $DESC" "$NAME"
-        do_start
-        case "$?" in
-                0|1) log_end_msg 0 || exit 0 ;;
-                2) log_end_msg 1 || exit 1 ;;
-        esac
-        ;;
-  stop)
-        log_daemon_msg "Stopping $DESC" "$NAME"
-        if do_stop; then
-            log_end_msg 0
-        else
-            log_failure_msg "Can't stop etcd"
-            log_end_msg 1
-        fi
-        ;;
-  status)
-        if do_status; then
-            log_end_msg 0
-        else
-            log_failure_msg "etcd is not running"
-            log_end_msg 1
-        fi
-        ;;
-
-  restart|force-reload)
-        log_daemon_msg "Restarting $DESC" "$NAME"
-        if do_stop; then
-            if do_start; then
-                log_end_msg 0
-                exit 0
-            else
-                rc="$?"
-            fi
-        else
-           rc="$?"
-        fi
-        log_failure_msg "Can't restart etcd"
-        log_end_msg ${rc}
-        ;;
-  *)
-        echo "Usage: $SCRIPTNAME {start|stop|status|restart|force-reload}" >&2
-        exit 3
-        ;;
-esac
-

roles/etcd/templates/deb-etcd-host.initd.j2

@@ -1,109 +0,0 @@
-#!/bin/sh
-set -a
-
-### BEGIN INIT INFO
-# Provides:   etcd
-# Required-Start:    $local_fs $network $syslog
-# Required-Stop:
-# Default-Start:     2 3 4 5
-# Default-Stop:      0 1 6
-# Short-Description: etcd distributed k/v store
-# Description:
-#   etcd is a distributed, consistent key-value store for shared configuration and service discovery
-### END INIT INFO
-
-PATH=/sbin:/usr/sbin:/bin:/usr/bin
-DESC="etcd k/v store"
-NAME=etcd
-DAEMON={{ bin_dir }}/etcd
-SCRIPTNAME=/etc/init.d/$NAME
-DAEMON_USER=etcd
-STOP_SCHEDULE="${STOP_SCHEDULE:-QUIT/5/TERM/5/KILL/5}"
-PID=/var/run/etcd.pid
-
-# Exit if the binary is not present
-[ -x "$DAEMON" ] || exit 0
-
-# Read configuration variable file if it is present
-[ -f /etc/etcd.env ] && . /etc/etcd.env
-
-# Define LSB log_* functions.
-# Depend on lsb-base (>= 3.2-14) to ensure that this file is present
-# and status_of_proc is working.
-. /lib/lsb/init-functions
-
-do_status()
-{
-    status_of_proc -p $PID "$DAEMON" "$NAME" && exit 0 || exit $?
-}
-
-# Function that starts the daemon/service
-#
-do_start()
-{
-    start-stop-daemon --background --start --quiet --make-pidfile --pidfile $PID --user $DAEMON_USER --exec $DAEMON -- \
-        $DAEMON_ARGS \
-        || return 2
-}
-
-#
-# Function that stops the daemon/service
-#
-do_stop()
-{
-    start-stop-daemon --stop --quiet --retry=$STOP_SCHEDULE --pidfile $PID --name $NAME
-    RETVAL="$?"
-
-    sleep 1
-    return "$RETVAL"
-}
-
-
-case "$1" in
-  start)
-        log_daemon_msg "Starting $DESC" "$NAME"
-        do_start
-        case "$?" in
-                0|1) log_end_msg 0 || exit 0 ;;
-                2) log_end_msg 1 || exit 1 ;;
-        esac
-        ;;
-  stop)
-        log_daemon_msg "Stopping $DESC" "$NAME"
-        if do_stop; then
-            log_end_msg 0
-        else
-            log_failure_msg "Can't stop etcd"
-            log_end_msg 1
-        fi
-        ;;
-  status)
-        if do_status; then
-            log_end_msg 0
-        else
-            log_failure_msg "etcd is not running"
-            log_end_msg 1
-        fi
-        ;;
-
-  restart|force-reload)
-        log_daemon_msg "Restarting $DESC" "$NAME"
-        if do_stop; then
-            if do_start; then
-                log_end_msg 0
-                exit 0
-            else
-                rc="$?"
-            fi
-        else
-           rc="$?"
-        fi
-        log_failure_msg "Can't restart etcd"
-        log_end_msg ${rc}
-        ;;
-  *)
-        echo "Usage: $SCRIPTNAME {start|stop|status|restart|force-reload}" >&2
-        exit 3
-        ;;
-esac
-

roles/etcd/templates/etcd-rkt.service.j2

@@ -0,0 +1,29 @@
+[Unit]
+Description=etcd rkt wrapper
+Documentation=https://github.com/coreos/etcd
+Wants=network.target
+
+[Service]
+Restart=on-failure
+RestartSec=10s
+TimeoutStartSec=0
+LimitNOFILE=40000
+
+ExecStart=/usr/bin/rkt run \
+--uuid-file-save=/var/run/etcd.uuid \
+--volume=etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
+--mount=volume=etc-ssl-certs,target=/etc/ssl/certs \
+--volume=etcd-cert-dir,kind=host,source={{ etcd_cert_dir }},readOnly=true \
+--mount=volume=etcd-cert-dir,target={{ etcd_cert_dir }} \
+--volume=var-lib-etcd,kind=host,source=/var/lib/etcd,readOnly=false \
+--mount=volume=var-lib-etcd,target=/var/lib/etcd \
+--set-env-file=/etc/etcd.env \
+--stage1-from-dir=stage1-fly.aci \
+{{ etcd_image_repo }}:{{ etcd_image_tag }} \
+--name={{ etcd_member_name | default("etcd") }}
+
+ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/run/etcd.uuid
+ExecStop=-/usr/bin/rkt stop --uuid-file=/var/run/etcd.uuid
+
+[Install]
+WantedBy=multi-user.target

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

@@ -17,8 +17,6 @@ kubednsmasq_image_repo: "gcr.io/google_containers/kube-dnsmasq-amd64"
 kubednsmasq_image_tag: "{{ kubednsmasq_version }}"
 exechealthz_image_repo: "gcr.io/google_containers/exechealthz-amd64"
 exechealthz_image_tag: "{{ exechealthz_version }}"
-calico_policy_image_repo: "calico/kube-policy-controller"
-calico_policy_image_tag: latest
 
 # Limits for calico apps
 calico_policy_controller_cpu_limit: 100m
@@ -31,9 +29,9 @@ deploy_netchecker: false
 netchecker_port: 31081
 agent_report_interval: 15
 netcheck_namespace: default
-agent_img: "quay.io/l23network/mcp-netchecker-agent:v0.1"
+agent_img: "{{ netcheck_agent_img_repo }}:{{ netcheck_tag }}"
-server_img: "quay.io/l23network/mcp-netchecker-server:v0.1"
+server_img: "{{ netcheck_server_img_repo }}:{{ netcheck_tag }}"
-kubectl_image: "gcr.io/google_containers/kubectl:v0.18.0-120-gaeb4ac55ad12b1-dirty"
+kubectl_image: "{{ netcheck_kubectl_img_repo }}:{{ netcheck_kubectl_tag }}"
 
 # Limits for netchecker apps
 netchecker_agent_cpu_limit: 30m
@@ -51,3 +49,5 @@ netchecker_kubectl_memory_requests: 64M
 
 # SSL
 etcd_cert_dir: "/etc/ssl/etcd/ssl"
+calico_cert_dir: "/etc/calico/certs"
+canal_cert_dir: "/etc/canal/certs"

roles/kubernetes-apps/ansible/tasks/calico-policy-controller.yml

@@ -1,8 +1,13 @@
+---
+- set_fact:
+    calico_cert_dir: "{{ canal_cert_dir }}"
+  when: kube_network_plugin == 'canal'
+  tags: facts
+
 - name: Write calico-policy-controller yaml
   template: src=calico-policy-controller.yml.j2 dest={{kube_config_dir}}/calico-policy-controller.yml
   when: inventory_hostname == groups['kube-master'][0]
 
-
 - name: Start of Calico policy controller
   kube:
     name: "calico-policy-controller"

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

@@ -12,7 +12,7 @@
     - {file: kubedns-rc.yml, type: rc}
     - {file: kubedns-svc.yml, type: svc}
   register: manifests
-  when: inventory_hostname == groups['kube-master'][0]
+  when: dns_mode != 'none' and inventory_hostname == groups['kube-master'][0]
   tags: dnsmasq
 
 - name: Kubernetes Apps | Start Resources
@@ -24,7 +24,7 @@
     filename: "{{kube_config_dir}}/{{item.item.file}}"
     state: "{{item.changed | ternary('latest','present') }}"
   with_items: "{{ manifests.results }}"
-  when: inventory_hostname == groups['kube-master'][0]
+  when: dns_mode != 'none' and inventory_hostname == groups['kube-master'][0]
   tags: dnsmasq
 
 - include: tasks/calico-policy-controller.yml

roles/kubernetes-apps/ansible/templates/calico-policy-controller.yml.j2

@@ -36,11 +36,11 @@ spec:
             - name: ETCD_ENDPOINTS
               value: "{{ etcd_access_endpoint }}"
             - name: ETCD_CA_CERT_FILE
-              value: "{{ etcd_cert_dir }}/ca.pem"
+              value: "{{ calico_cert_dir }}/ca_cert.crt"
             - name: ETCD_CERT_FILE
-              value: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}.pem"
+              value: "{{ calico_cert_dir }}/cert.crt"
             - name: ETCD_KEY_FILE
-              value: "{{ etcd_cert_dir }}/node-{{ inventory_hostname }}-key.pem"
+              value: "{{ calico_cert_dir }}/key.pem"
             # Location of the Kubernetes API - this shouldn't need to be
             # changed so long as it is used in conjunction with
             # CONFIGURE_ETC_HOSTS="true".
@@ -53,10 +53,10 @@ spec:
             - name: CONFIGURE_ETC_HOSTS
               value: "true"
           volumeMounts:
-          - mountPath: {{ etcd_cert_dir }}
+          - mountPath: {{ calico_cert_dir }}
             name: etcd-certs
             readOnly: true
       volumes:
       - hostPath:
-          path: {{ etcd_cert_dir }}
+          path: {{ calico_cert_dir }}
         name: etcd-certs

roles/kubernetes-apps/meta/main.yaml

@@ -1,3 +1,20 @@
 dependencies:
+  - role: download
+    file: "{{ downloads.calico_policy }}"
+    when: ( enable_network_policy is defined and enable_network_policy == True ) or
+      ( kube_network_plugin == 'canal' )
+    tags: [download, network, canal]
+  - role: download
+    file: "{{ downloads.netcheck_server }}"
+    when: deploy_netchecker
+    tags: [download, netchecker]
+  - role: download
+    file: "{{ downloads.netcheck_agent }}"
+    when: deploy_netchecker
+    tags: [download, netchecker]
+  - role: download
+    file: "{{ downloads.netcheck_kubectl }}"
+    when: deploy_netchecker
+    tags: [download, netchecker]
   - {role: kubernetes-apps/ansible, tags: apps}
   - {role: kubernetes-apps/kpm, tags: [apps, kpm]}

roles/kubernetes/master/handlers/main.yml

@@ -15,7 +15,6 @@
 
 - name: Master | reload systemd
   command: systemctl daemon-reload
-  when: ansible_service_mgr == "systemd"
 
 - name: Master | reload kubelet
   service:

roles/kubernetes/node/handlers/main.yml

@@ -7,7 +7,6 @@
 
 - name: Kubelet | reload systemd
   command: systemctl daemon-reload
-  when: ansible_service_mgr == "systemd"
 
 - name: Kubelet | reload kubelet
   service:

roles/kubernetes/node/tasks/install.yml

@@ -1,19 +1,31 @@
 ---
+- name: Trust kubelet container
+  command: >-
+    /usr/bin/rkt trust
+    --skip-fingerprint-review
+    --root
+    {{ item }}
+  register: kubelet_rkt_trust_result
+  until: kubelet_rkt_trust_result.rc == 0
+  with_items:
+    - "https://quay.io/aci-signing-key"
+    - "https://coreos.com/dist/pubkeys/aci-pubkeys.gpg"
+  retries: 4
+  delay: "{{ retry_stagger | random + 3 }}"
+  changed_when: false
+  when: kubelet_deployment_type == "rkt"
+
+- name: create kubelet working directory
+  file:
+    state: directory
+    path: /var/lib/kubelet
+  when: kubelet_deployment_type == "rkt"
+
 - name: install | Write kubelet systemd init file
-  template: src=kubelet.service.j2 dest=/etc/systemd/system/kubelet.service backup=yes
+  template: "src=kubelet.{{ kubelet_deployment_type }}.service.j2 dest=/etc/systemd/system/kubelet.service backup=yes"
-  when: ansible_service_mgr == "systemd"
-  notify: restart kubelet
-
-- name: install | Write kubelet initd script
-  template: src=deb-kubelet.initd.j2 dest=/etc/init.d/kubelet owner=root mode=0755 backup=yes
-  when: ansible_service_mgr in ["sysvinit","upstart"] and ansible_os_family == "Debian"
-  notify: restart kubelet
-
-- name: install | Write kubelet initd script
-  template: src=rh-kubelet.initd.j2 dest=/etc/init.d/kubelet owner=root mode=0755 backup=yes
-  when: ansible_service_mgr in ["sysvinit","upstart"] and ansible_os_family == "RedHat"
   notify: restart kubelet
 
 - name: install | Install kubelet launch script
   template: src=kubelet-container.j2 dest="{{ bin_dir }}/kubelet" owner=kube mode=0755 backup=yes
   notify: restart kubelet
+  when: kubelet_deployment_type == "docker"

roles/kubernetes/node/templates/deb-kubelet.initd.j2

@@ -1,121 +0,0 @@
-#!/bin/bash
-#
-### BEGIN INIT INFO
-# Provides:   kubelet
-# Required-Start:    $local_fs $network $syslog
-# Required-Stop:
-# Default-Start:     2 3 4 5
-# Default-Stop:      0 1 6
-# Short-Description: The Kubernetes node container manager
-# Description:
-#   The Kubernetes container manager maintains docker state against a state file.
-### END INIT INFO
-
-
-# PATH should only include /usr/* if it runs after the mountnfs.sh script
-PATH=/sbin:/usr/sbin:/bin:/usr/bin
-DESC="The Kubernetes container manager"
-NAME=kubelet
-DAEMON={{ bin_dir }}/kubelet
-DAEMON_ARGS=""
-DAEMON_LOG_FILE=/var/log/$NAME.log
-PIDFILE=/var/run/$NAME.pid
-SCRIPTNAME=/etc/init.d/$NAME
-DAEMON_USER=root
-
-# Exit if the package is not installed
-[ -x "$DAEMON" ] || exit 0
-
-# Read configuration variable file if it is present
-[ -r {{kube_config_dir}}/$NAME.env ] && . {{kube_config_dir}}/$NAME.env
-
-# Define LSB log_* functions.
-# Depend on lsb-base (>= 3.2-14) to ensure that this file is present
-# and status_of_proc is working.
-. /lib/lsb/init-functions
-
-#
-# Function that starts the daemon/service
-#
-do_start()
-{
-        {{ docker_bin_dir }}/docker rm -f kubelet &>/dev/null || true
-        sleep 1
-        # Return
-        #   0 if daemon has been started
-        #   1 if daemon was already running
-        #   2 if daemon could not be started
-        start-stop-daemon --start --quiet --background --no-close \
-                --make-pidfile --pidfile $PIDFILE \
-                --exec $DAEMON -c $DAEMON_USER --test > /dev/null \
-                || return 1
-        start-stop-daemon --start --quiet --background --no-close \
-                --make-pidfile --pidfile $PIDFILE \
-                --exec $DAEMON -c $DAEMON_USER -- \
-                $DAEMON_ARGS >> $DAEMON_LOG_FILE 2>&1 \
-                || return 2
-}
-
-#
-# Function that stops the daemon/service
-#
-do_stop()
-{
-        # Return
-        #   0 if daemon has been stopped
-        #   1 if daemon was already stopped
-        #   2 if daemon could not be stopped
-        #   other if a failure occurred
-        start-stop-daemon --stop --quiet --retry=TERM/30/KILL/5 --pidfile $PIDFILE --name $NAME
-        RETVAL="$?"
-        [ "$RETVAL" = 2 ] && return 2
-        # Many daemons don't delete their pidfiles when they exit.
-        rm -f $PIDFILE
-        return "$RETVAL"
-}
-
-
-case "$1" in
-  start)
-        log_daemon_msg "Starting $DESC" "$NAME"
-        do_start
-        case "$?" in
-                0|1) log_end_msg 0 || exit 0 ;;
-                2) log_end_msg 1 || exit 1 ;;
-        esac
-        ;;
-  stop)
-        log_daemon_msg "Stopping $DESC" "$NAME"
-        do_stop
-        case "$?" in
-                0|1) log_end_msg 0 ;;
-                2) exit 1 ;;
-        esac
-        ;;
-  status)
-        status_of_proc -p $PIDFILE "$DAEMON" "$NAME" && exit 0 || exit $?
-        ;;
-
-  restart|force-reload)
-        log_daemon_msg "Restarting $DESC" "$NAME"
-        do_stop
-        case "$?" in
-          0|1)
-                do_start
-                case "$?" in
-                        0) log_end_msg 0 ;;
-                        1) log_end_msg 1 ;; # Old process is still running
-                        *) log_end_msg 1 ;; # Failed to start
-                esac
-                ;;
-          *)
-                # Failed to stop
-                log_end_msg 1
-                ;;
-        esac
-        ;;
-  *)
-        echo "Usage: $SCRIPTNAME {start|stop|status|restart|force-reload}" >&2
-        exit 3
-        ;;
-esac

roles/kubernetes/node/templates/kubelet.j2

@@ -1,10 +1,5 @@
-{% if ansible_service_mgr in ["sysvinit","upstart"] %}
-# Logging directory
-KUBE_LOGGING="--log-dir={{ kube_log_dir }} --logtostderr=true"
-{% else %}
 # logging to stderr means we get it in the systemd journal
 KUBE_LOGGING="--logtostderr=true"
-{% endif %}
 KUBE_LOG_LEVEL="--v={{ kube_log_level }}"
 # The address for the info server to serve on (set to 0.0.0.0 or "" for all interfaces)
 KUBELET_ADDRESS="--address={{ ip | default("0.0.0.0") }}"
@@ -17,9 +12,9 @@ KUBELET_HOSTNAME="--hostname-override={{ ansible_hostname }}"
 {% set kubelet_args_base %}--pod-manifest-path={{ kube_manifest_dir }} --pod-infra-container-image={{ pod_infra_image_repo }}:{{ pod_infra_image_tag }}{% endset %}
 
 {# DNS settings for kubelet #}
-{% if dns_setup|bool and skip_dnsmasq|bool %}
+{% if dns_mode == 'kubedns' %}
 {% set kubelet_args_cluster_dns %}--cluster_dns={{ skydns_server }}{% endset %}
-{% elif dns_setup|bool %}
+{% elif dns_mode == 'dnsmasq_kubedns' %}
 {% set kubelet_args_cluster_dns %}--cluster_dns={{ dns_server }}{% endset %}
 {% else %}
 {% set kubelet_args_cluster_dns %}{% endset %}
@@ -51,8 +46,3 @@ KUBELET_CLOUDPROVIDER="--cloud-provider={{ cloud_provider }}"
 {% else %}
 KUBELET_CLOUDPROVIDER=""
 {% endif %}
-{% if ansible_service_mgr in ["sysvinit","upstart"] %}
-DAEMON_ARGS="$KUBE_LOGGING $KUBE_LOG_LEVEL $KUBE_ALLOW_PRIV $KUBELET_API_SERVER $KUBELET_ADDRESS \
-$KUBELET_HOSTNAME $KUBELET_ARGS $DOCKER_SOCKET $KUBELET_ARGS $KUBELET_NETWORK_PLUGIN \
-$KUBELET_CLOUDPROVIDER"
-{% endif %}

roles/kubernetes/node/templates/kubelet.rkt.service.j2

@@ -0,0 +1,58 @@
+[Unit]
+Description=Kubernetes Kubelet Server
+Documentation=https://github.com/GoogleCloudPlatform/kubernetes
+{% if kube_network_plugin is defined and kube_network_plugin == "calico" %}
+After=calico-node.service
+Wants=network.target calico-node.service
+{% else %}
+Wants=network.target
+{% endif %}
+
+[Service]
+Restart=on-failure
+RestartSec=10s
+TimeoutStartSec=0
+LimitNOFILE=40000
+
+ExecStartPre=-/usr/bin/rkt rm --uuid-file=/var/run/kubelet.uuid
+ExecStartPre=-/bin/mkdir -p /var/lib/kubelet
+
+EnvironmentFile={{kube_config_dir}}/kubelet.env
+# stage1-fly mounts /proc /sys /dev so no need to duplicate the mounts
+ExecStart=/usr/bin/rkt run \
+        --volume var-log,kind=host,source=/var/log \
+        --volume dns,kind=host,source=/etc/resolv.conf \
+        --volume etc-kubernetes,kind=host,source={{ kube_config_dir }},readOnly=false \
+        --volume etc-ssl-certs,kind=host,source=/etc/ssl/certs,readOnly=true \
+        --volume usr-share-certs,kind=host,source=/usr/share/ca-certificates,readOnly=true \
+        --volume var-lib-docker,kind=host,source={{ docker_daemon_graph }},readOnly=false \
+	--volume var-lib-kubelet,kind=host,source=/var/lib/kubelet,readOnly=false \
+        --volume run,kind=host,source=/run,readOnly=false \
+        --mount volume=var-log,target=/var/log \
+        --mount volume=dns,target=/etc/resolv.conf \
+        --mount volume=etc-kubernetes,target={{ kube_config_dir }} \
+        --mount volume=etc-ssl-certs,target=/etc/ssl/certs \
+        --mount volume=usr-share-certs,target=/usr/share/ca-certificates \
+        --mount volume=var-lib-docker,target=/var/lib/docker \
+        --mount volume=var-lib-kubelet,target=/var/lib/kubelet \
+        --mount volume=run,target=/run \
+        --stage1-from-dir=stage1-fly.aci \
+        {{ hyperkube_image_repo }}:{{ hyperkube_image_tag }} \
+        --uuid-file-save=/var/run/kubelet.uuid \
+        --debug --exec=/kubelet -- \
+                $KUBE_LOGTOSTDERR \
+                $KUBE_LOG_LEVEL \
+                $KUBELET_API_SERVER \
+                $KUBELET_ADDRESS \
+                $KUBELET_PORT \
+                $KUBELET_HOSTNAME \
+                $KUBE_ALLOW_PRIV \
+                $KUBELET_ARGS \
+                $DOCKER_SOCKET \
+                $KUBELET_REGISTER_NODE \
+                $KUBELET_NETWORK_PLUGIN
+
+ExecStop=-/usr/bin/rkt stop --uuid-file=/var/run/kubelet.uuid
+
+[Install]
+WantedBy=multi-user.target

roles/kubernetes/node/templates/rh-kubelet.initd.j2

@@ -1,129 +0,0 @@
-#!/bin/bash
-#
-#       /etc/rc.d/init.d/kubelet
-#
-# chkconfig:   2345 95 95
-# description: Daemon for kubelet (kubernetes.io)
-
-### BEGIN INIT INFO
-# Provides:       kubelet
-# Required-Start: $local_fs $network $syslog cgconfig
-# Required-Stop:
-# Should-Start:
-# Should-Stop:
-# Default-Start: 2 3 4 5
-# Default-Stop:  0 1 6
-# Short-Description: start and stop kubelet
-# Description:
-#   The Kubernetes container manager maintains docker state against a state file.
-### END INIT INFO
-
-# Source function library.
-. /etc/rc.d/init.d/functions
-
-prog="kubelet"
-exec="{{ bin_dir }}/$prog"
-pidfile="/var/run/$prog.pid"
-lockfile="/var/lock/subsys/$prog"
-logfile="/var/log/$prog"
-
-[ -e {{kube_config_dir}}/$prog.env ] && . {{kube_config_dir}}/$prog.env
-
-start() {
-    if [ ! -x $exec ]; then
-      if [ ! -e $exec ]; then
-        echo "Docker executable $exec not found"
-      else
-        echo "You do not have permission to execute the Docker executable $exec"
-      fi
-      exit 5
-    fi
-
-    check_for_cleanup
-
-    if ! [ -f $pidfile ]; then
-        printf "Starting $prog:\t"
-        echo "\n$(date)\n" >> $logfile
-        $exec $DAEMON_ARGS &>> $logfile &
-        pid=$!
-        echo $pid >> $pidfile
-        touch $lockfile
-        success
-        echo
-    else
-        failure
-        echo
-        printf "$pidfile still exists...\n"
-        exit 7
-    fi
-}
-
-stop() {
-    echo -n $"Stopping $prog: "
-    killproc -p $pidfile -d 300 $prog
-    retval=$?
-    echo
-    [ $retval -eq 0 ] && rm -f $lockfile
-    return $retval
-}
-
-restart() {
-    stop
-    start
-}
-
-reload() {
-    restart
-}
-
-force_reload() {
-    restart
-}
-
-rh_status() {
-    status -p $pidfile $prog
-}
-
-rh_status_q() {
-    rh_status >/dev/null 2>&1
-}
-
-
-check_for_cleanup() {
-    if [ -f ${pidfile} ]; then
-        /bin/ps -fp $(cat ${pidfile}) > /dev/null || rm ${pidfile}
-    fi
-}
-
-case "$1" in
-    start)
-        rh_status_q && exit 0
-        $1
-        ;;
-    stop)
-        rh_status_q || exit 0
-        $1
-        ;;
-    restart)
-        $1
-        ;;
-    reload)
-        rh_status_q || exit 7
-        $1
-        ;;
-    force-reload)
-        force_reload
-        ;;
-    status)
-        rh_status
-        ;;
-    condrestart|try-restart)
-        rh_status_q || exit 0
-        restart
-        ;;
-    *)
-        echo $"Usage: $0 {start|stop|status|restart|condrestart|try-restart|reload|force-reload}"
-        exit 2
-esac
-
-exit $?

roles/kubernetes/preinstall/defaults/main.yml

@@ -29,6 +29,6 @@ openstack_tenant_id: "{{ lookup('env','OS_TENANT_ID')  }}"
 # All clients access each node individually, instead of using a load balancer.
 etcd_multiaccess: true
 
-# CoreOS cloud init config file to define /etc/resolv.conf content
+# Container Linux by CoreOS cloud init config file to define /etc/resolv.conf content
 # for hostnet pods and infra needs
 resolveconf_cloud_init_conf: /etc/resolveconf_cloud_init.conf

roles/kubernetes/preinstall/handlers/main.yml

@@ -3,7 +3,7 @@
   notify:
     - Preinstall | reload network
     - Preinstall | reload kubelet
-  when: ansible_os_family != "CoreOS"
+  when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
   # FIXME(bogdando) https://github.com/projectcalico/felix/issues/1185
 - name: Preinstall | reload network
@@ -15,18 +15,18 @@
       networking
       {%- endif %}
     state: restarted
-  when: ansible_os_family != "CoreOS" and kube_network_plugin not in ['canal', 'calico']
+  when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] and kube_network_plugin not in ['canal', 'calico']
 
-- name: Preinstall | update resolvconf for CoreOS
+- name: Preinstall | update resolvconf for Container Linux by CoreOS
   command: /bin/true
   notify:
     - Preinstall | apply resolvconf cloud-init
     - Preinstall | reload kubelet
-  when: ansible_os_family == "CoreOS"
+  when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
 - name: Preinstall | apply resolvconf cloud-init
   command: /usr/bin/coreos-cloudinit --from-file {{ resolveconf_cloud_init_conf }}
-  when: ansible_os_family == "CoreOS"
+  when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
 - name: Preinstall | reload kubelet
   service:

roles/kubernetes/preinstall/tasks/etchosts.yml

@@ -3,7 +3,7 @@
   blockinfile:
     dest: /etc/hosts
     block: |-
-      {% for item in groups['all'] -%}{{ hostvars[item]['access_ip'] | default(hostvars[item]['ip'] | default(hostvars[item].ansible_default_ipv4.address)) }}{% if (item != hostvars[item]['ansible_hostname']) %} {{ hostvars[item]['ansible_hostname'] }} {{ hostvars[item]['ansible_hostname'] }}.{{ dns_domain }}{% endif %} {{ item }} {{ item }}.{{ dns_domain }}
+      {% for item in (groups['k8s-cluster'] + groups['etcd'] + groups['calico-rr']|default([]))|unique -%}{{ hostvars[item]['access_ip'] | default(hostvars[item]['ip'] | default(hostvars[item]['ansible_default_ipv4']['address'])) }}{% if (item != hostvars[item]['ansible_hostname']) %} {{ hostvars[item]['ansible_hostname'] }} {{ hostvars[item]['ansible_hostname'] }}.{{ dns_domain }}{% endif %} {{ item }} {{ item }}.{{ dns_domain }}
       {% endfor %}
     state: present
     create: yes

roles/kubernetes/preinstall/tasks/main.yml

@@ -1,8 +1,11 @@
 ---
-- name: Force binaries directory for CoreOS
+- include: pre-upgrade.yml
+  tags: [upgrade,  bootstrap-os]
+
+- name: Force binaries directory for Container Linux by CoreOS
   set_fact:
     bin_dir: "/opt/bin"
-  when: ansible_os_family == "CoreOS"
+  when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
   tags: facts
 
 - name: check bin dir exists
@@ -59,14 +62,6 @@
   when: "{{ inventory_hostname in groups['k8s-cluster'] }}"
   tags: [kubelet, bootstrap-os, master, node]
 
-- name: Create kubernetes logs directory
-  file:
-    path: "{{ kube_log_dir }}"
-    state: directory
-    owner: kube
-  when: ansible_service_mgr in ["sysvinit","upstart"] and "{{ inventory_hostname in groups['k8s-cluster'] }}"
-  tags: [bootstrap-os, master, node]
-
 - name: check cloud_provider value
   fail:
     msg: "If set the 'cloud_provider' var must be set either to 'generic', 'gce', 'aws', 'azure' or 'openstack'"
@@ -122,8 +117,7 @@
 
 - name: Install epel-release on RedHat/CentOS
   shell: rpm -qa | grep epel-release || rpm -ivh {{ epel_rpm_download_url }}
-  when: ansible_distribution in ["CentOS","RedHat"] and
+  when: ansible_distribution in ["CentOS","RedHat"]
-        ansible_distribution_major_version >= 7
   changed_when: False
   tags: bootstrap-os
 
@@ -137,7 +131,7 @@
   retries: 4
   delay: "{{ retry_stagger | random + 3 }}"
   with_items: "{{required_pkgs | default([]) | union(common_required_pkgs|default([]))}}"
-  when: ansible_os_family != "CoreOS"
+  when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
   tags: bootstrap-os
 
 - name: Disable IPv6 DNS lookup
@@ -146,7 +140,7 @@
     line: "precedence ::ffff:0:0/96  100"
     state: present
     backup: yes
-  when: disable_ipv6_dns and ansible_os_family != "CoreOS"
+  when: disable_ipv6_dns and not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
   tags: bootstrap-os
 
 # Todo : selinux configuration
@@ -178,8 +172,9 @@
   tags: [bootstrap-os, etchosts]
 
 - include: resolvconf.yml
+  when: dns_mode != 'none' and resolvconf_mode == 'host_resolvconf'
   tags: [bootstrap-os, resolvconf]
-  
+
 - name: Check if we are running inside a Azure VM
   stat: path=/var/lib/waagent/
   register: azure_check
@@ -187,7 +182,6 @@
 
 - include: growpart-azure-centos-7.yml
   when: azure_check.stat.exists and
-        ansible_distribution in ["CentOS","RedHat"] and
+        ansible_distribution in ["CentOS","RedHat"]
-        ansible_distribution_major_version >= 7
   tags: bootstrap-os
 

roles/kubernetes/preinstall/tasks/pre-upgrade.yml

@@ -0,0 +1,4 @@
+---
+- name: Stop if non systemd OS type
+  assert:
+    that: ansible_service_mgr == "systemd"

roles/kubernetes/preinstall/tasks/resolvconf.yml

@@ -1,7 +1,7 @@
 ---
 - name: create temporary resolveconf cloud init file
   command: cp -f /etc/resolv.conf "{{ resolvconffile }}"
-  when: ansible_os_family == "CoreOS"
+  when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
 - name: Remove search/domain/nameserver options
   lineinfile:
@@ -48,7 +48,7 @@
 - name: get temporary resolveconf cloud init file content
   command: cat {{ resolvconffile }}
   register: cloud_config
-  when: ansible_os_family == "CoreOS"
+  when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
 - name: persist resolvconf cloud init file
   template:
@@ -56,9 +56,9 @@
     src: resolvconf.j2
     owner: root
     mode: 0644
-  notify: Preinstall | update resolvconf for CoreOS
+  notify: Preinstall | update resolvconf for Container Linux by CoreOS
-  when: ansible_os_family == "CoreOS"
+  when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
 - include: dhclient-hooks.yml
-  when: ansible_os_family != "CoreOS"
+  when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
   tags: [bootstrap-os, resolvconf]

roles/kubernetes/preinstall/tasks/set_resolv_facts.yml

@@ -35,11 +35,11 @@
       {%- if resolvconf|bool -%}/etc/resolvconf/resolv.conf.d/base{%- endif -%}
     head: >-
       {%- if resolvconf|bool -%}/etc/resolvconf/resolv.conf.d/head{%- endif -%}
-  when: ansible_os_family != "CoreOS"
+  when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
-- name: target temporary resolvconf cloud init file (CoreOS)
+- name: target temporary resolvconf cloud init file (Container Linux by CoreOS)
   set_fact: resolvconffile=/tmp/resolveconf_cloud_init_conf
-  when: ansible_os_family == "CoreOS"
+  when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
 - name: target dhclient conf/hook files for Red Hat family
   set_fact:
@@ -67,7 +67,7 @@
 - name: pick dnsmasq cluster IP or default resolver
   set_fact:
     dnsmasq_server: |-
-      {%- if skip_dnsmasq|bool and not dns_early|bool -%}
+      {%- if dns_mode == 'kubedns' and not dns_early|bool -%}
         {{ [ skydns_server ] + upstream_dns_servers|default([]) }}
       {%- elif dns_early|bool -%}
         {{ upstream_dns_servers|default([]) }}

roles/kubernetes/secrets/tasks/gen_certs.yml

@@ -74,7 +74,7 @@
       /usr/local/share/ca-certificates/kube-ca.crt
       {%- elif ansible_os_family == "RedHat" -%}
       /etc/pki/ca-trust/source/anchors/kube-ca.crt
-      {%- elif ansible_os_family == "CoreOS" -%}
+      {%- elif ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] -%}
       /etc/ssl/certs/kube-ca.pem
       {%- endif %}
   tags: facts
@@ -86,9 +86,9 @@
     remote_src: true
   register: kube_ca_cert
 
-- name: Gen_certs | update ca-certificates (Debian/Ubuntu/CoreOS)
+- name: Gen_certs | update ca-certificates (Debian/Ubuntu/Container Linux by CoreOS)
   command: update-ca-certificates
-  when: kube_ca_cert.changed and ansible_os_family in ["Debian", "CoreOS"]
+  when: kube_ca_cert.changed and ansible_os_family in ["Debian", "Container Linux by CoreOS"]
 
 - name: Gen_certs | update ca-certificates (RedHat)
   command: update-ca-trust extract

roles/network_plugin/calico/defaults/main.yml

@@ -21,10 +21,6 @@ global_as_num: "64512"
 # calico_mtu: 1500
 
 # Limits for apps
-calico_rr_memory_limit: 1000M
-calico_rr_cpu_limit: 300m
-calico_rr_memory_requests: 500M
-calico_rr_cpu_requests: 150m
 calico_node_memory_limit: 500M
 calico_node_cpu_limit: 300m
 calico_node_memory_requests: 256M

roles/network_plugin/calico/handlers/main.yml

@@ -7,7 +7,6 @@
 
 - name : Calico | reload systemd
   shell: systemctl daemon-reload
-  when: ansible_service_mgr == "systemd"
 
 - name: Calico | reload calico-node
   service:

roles/network_plugin/calico/rr/defaults/main.yml

@@ -5,3 +5,9 @@ global_as_num: "64512"
 
 calico_cert_dir: /etc/calico/certs
 etcd_cert_dir: /etc/ssl/etcd/ssl
+
+# Limits for apps
+calico_rr_memory_limit: 1000M
+calico_rr_cpu_limit: 300m
+calico_rr_memory_requests: 500M
+calico_rr_cpu_requests: 150m

roles/network_plugin/calico/rr/handlers/main.yml

@@ -7,7 +7,6 @@
 
 - name : Calico-rr | reload systemd
   shell: systemctl daemon-reload
-  when: ansible_service_mgr == "systemd"
 
 - name: Calico-rr | reload calico-rr
   service:

roles/network_plugin/calico/rr/meta/main.yml

@@ -1,6 +1,6 @@
 dependencies:
   - role: etcd
   - role: docker
-    when: ansible_os_family != "CoreOS"
+    when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
   - role: download
     file: "{{ downloads.calico_rr }}"

roles/network_plugin/calico/rr/tasks/main.yml

@@ -36,12 +36,10 @@
 
 - name: Calico-rr | Write calico-rr.env for systemd init file
   template: src=calico-rr.env.j2 dest=/etc/calico/calico-rr.env
-  when: ansible_service_mgr == "systemd"
   notify: restart calico-rr
 
 - name: Calico-rr | Write calico-rr systemd init file
   template: src=calico-rr.service.j2 dest=/etc/systemd/system/calico-rr.service
-  when: ansible_service_mgr == "systemd"
   notify: restart calico-rr
 
 - name: Calico-rr | Configure route reflector

roles/network_plugin/calico/tasks/main.yml

@@ -162,33 +162,19 @@
   run_once: true
   when: legacy_calicoctl
 
-- name: Calico | Write /etc/network-environment
-  template: src=network-environment.j2 dest=/etc/network-environment
-  when: ansible_service_mgr in ["sysvinit","upstart"]
-
 - name: Calico (old) | Write calico-node systemd init file
   template: src=calico-node.service.legacy.j2 dest=/etc/systemd/system/calico-node.service
-  when: ansible_service_mgr == "systemd" and legacy_calicoctl
+  when: legacy_calicoctl
   notify: restart calico-node
 
 - name: Calico | Write calico.env for systemd init file
   template: src=calico.env.j2 dest=/etc/calico/calico.env
-  when: ansible_service_mgr == "systemd" and not legacy_calicoctl
+  when: not legacy_calicoctl
   notify: restart calico-node
 
 - name: Calico | Write calico-node systemd init file
   template: src=calico-node.service.j2 dest=/etc/systemd/system/calico-node.service
-  when: ansible_service_mgr == "systemd" and not legacy_calicoctl
+  when: not legacy_calicoctl
-  notify: restart calico-node
-
-- name: Calico | Write calico-node initd script
-  template: src=deb-calico.initd.j2 dest=/etc/init.d/calico-node owner=root mode=0755
-  when: ansible_service_mgr in ["sysvinit","upstart"] and ansible_os_family == "Debian"
-  notify: restart calico-node
-
-- name: Calico | Write calico-node initd script
-  template: src=rh-calico.initd.j2 dest=/etc/init.d/calico-node owner=root mode=0755
-  when: ansible_service_mgr in ["sysvinit","upstart"] and ansible_os_family == "RedHat"
   notify: restart calico-node
 
 - name: Calico | Restart calico-node if secrets changed

roles/network_plugin/calico/templates/calicoctl-container.j2

@@ -2,13 +2,13 @@
 {{ docker_bin_dir }}/docker run -i --privileged --rm \
 --net=host --pid=host \
 -e ETCD_ENDPOINTS={{ etcd_access_endpoint }} \
--e ETCD_CA_CERT_FILE=/etc/calico/certs/ca_cert.crt \
+-e ETCD_CA_CERT_FILE={{ calico_cert_dir }}/ca_cert.crt \
--e ETCD_CERT_FILE=/etc/calico/certs/cert.crt \
+-e ETCD_CERT_FILE={{ calico_cert_dir }}/cert.crt \
--e ETCD_KEY_FILE=/etc/calico/certs/key.pem \
+-e ETCD_KEY_FILE={{ calico_cert_dir }}/key.pem \
 -v {{ docker_bin_dir }}/docker:{{ docker_bin_dir }}/docker \
 -v /var/run/docker.sock:/var/run/docker.sock \
 -v /var/run/calico:/var/run/calico \
--v /etc/calico/certs:/etc/calico/certs:ro \
+-v {{ calico_cert_dir }}:{{ calico_cert_dir }}:ro \
 --memory={{ calicoctl_memory_limit|regex_replace('Mi', 'M') }} --cpu-shares={{ calicoctl_cpu_limit|regex_replace('m', '') }} \
 {{ calicoctl_image_repo }}:{{ calicoctl_image_tag}} \
 $@

roles/network_plugin/calico/templates/deb-calico.initd.j2

@@ -1,124 +0,0 @@
-#!/bin/bash
-#
-### BEGIN INIT INFO
-# Provides:   calico-node
-# Required-Start:    $local_fs $network $syslog
-# Required-Stop:
-# Default-Start:     2 3 4 5
-# Default-Stop:      0 1 6
-# Short-Description: Calico docker container
-# Description:
-#   Runs calico as a docker container
-### END INIT INFO
-set -a
-
-PATH=/sbin:/usr/sbin:/bin:/usr/bin
-DESC="Calico-node Docker"
-NAME=calico-node
-DAEMON={{ bin_dir }}/calicoctl
-DAEMON_ARGS=""
-DOCKER=$(which docker)
-SCRIPTNAME=/etc/init.d/$NAME
-DAEMON_USER=root
-
-# Exit if the binary is not present
-[ -x "$DAEMON" ] || exit 0
-
-# Exit if the docker package is not installed
-[ -x "$DOCKER" ] || exit 0
-
-# Read configuration variable file if it is present
-[ -r /etc/network-environment ] && . /etc/network-environment
-
-# Define LSB log_* functions.
-# Depend on lsb-base (>= 3.2-14) to ensure that this file is present
-# and status_of_proc is working.
-. /lib/lsb/init-functions
-
-do_status()
-{
-    if [ $($DOCKER ps --format "{{.Image}}" | grep -cw 'calico/node') -eq 1 ]; then
-        return 0
-    else
-        return 1
-    fi
-}
-
-# Function that starts the daemon/service
-#
-do_start()
-{
-    do_status
-    retval=$?
-    if [ $retval -ne 0 ]; then
-{% if legacy_calicoctl %}
-        ${DAEMON} node --ip=${DEFAULT_IPV4} >>/dev/null && return 0 || return 2
-{% else %}
-         ${DAEMON} node run --ip=${DEFAULT_IPV4} >>/dev/null && return 0 || return 2
-{% endif %}
-    else
-        return 1
-    fi
-}
-
-#
-# Function that stops the daemon/service
-#
-do_stop()
-{
-{% if legacy_calicoctl %}
-    ${DAEMON} node stop >> /dev/null || ${DAEMON} node stop --force >> /dev/null
-{% else %}
-    echo "Current version of ${DAEMON} doesn't support 'node stop' command!"
-    return 1
-{% endif %}
-}
-
-
-case "$1" in
-  start)
-        log_daemon_msg "Starting $DESC" "$NAME"
-        do_start
-        case "$?" in
-                0|1) log_end_msg 0 || exit 0 ;;
-                2) log_end_msg 1 || exit 1 ;;
-        esac
-        ;;
-  stop)
-        log_daemon_msg "Stopping $DESC" "$NAME"
-        if do_stop; then
-            log_end_msg 0
-        else
-            log_failure_msg "Can't stop calico-node"
-            log_end_msg 1
-        fi
-        ;;
-  status)
-        if do_status; then
-            log_end_msg 0
-        else
-            log_failure_msg "Calico-node is not running"
-            log_end_msg 1
-        fi
-        ;;
-
-  restart|force-reload)
-        log_daemon_msg "Restarting $DESC" "$NAME"
-        if do_stop; then
-            if do_start; then
-                log_end_msg 0
-                exit 0
-            else
-                rc="$?"
-            fi
-        else
-           rc="$?"
-        fi
-        log_failure_msg "Can't restart Calico-node"
-        log_end_msg ${rc}
-        ;;
-  *)
-        echo "Usage: $SCRIPTNAME {start|stop|status|restart|force-reload}" >&2
-        exit 3
-        ;;
-esac

roles/network_plugin/calico/templates/network-environment.j2

@@ -1,12 +0,0 @@
-# This host's IPv4 address (the source IP address used to reach other nodes
-# in the Kubernetes cluster).
-DEFAULT_IPV4={{ip | default(ansible_default_ipv4.address) }}
-
-# The Kubernetes master IP
-KUBERNETES_MASTER={{ kube_apiserver_endpoint }}
-
-# IP and port of etcd instance used by Calico
-ETCD_ENDPOINTS={{ etcd_access_endpoint }}
-ETCD_CA_CERT_FILE=/etc/calico/certs/ca_cert.crt
-ETCD_CERT_FILE=/etc/calico/certs/cert.crt
-ETCD_KEY_FILE=/etc/calico/certs/key.pem

roles/network_plugin/calico/templates/rh-calico.initd.j2

@@ -1,140 +0,0 @@
-#!/bin/bash
-#
-#       /etc/rc.d/init.d/calico-node
-#
-# chkconfig:   2345 95 95
-# description: Daemon for calico-node (http://www.projectcalico.org/)
-set -a
-
-### BEGIN INIT INFO
-# Provides:       calico-node
-# Required-Start: $local_fs $network $syslog cgconfig
-# Required-Stop:
-# Should-Start:
-# Should-Stop:
-# Default-Start: 2 3 4 5
-# Default-Stop:  0 1 6
-# Short-Description: start and stop calico-node
-# Description:
-#   Manage calico-docker container
-### END INIT INFO
-
-# Source function library.
-. /etc/rc.d/init.d/functions
-
-prog="calicoctl"
-exec="{{ bin_dir }}/$prog"
-dockerexec="$(which docker)"
-logfile="/var/log/$prog"
-
-[ -e /etc/network-environment ] && for i in $(cat /etc/network-environment | egrep '(^$|^#)'); do export $i; done
-
-do_status()
-{
-    if [ $($dockerexec ps --format "{{.Image}}" | grep -cw 'calico/node') -ne 1 ]; then
-        return 1
-    fi
-}
-
-do_start() {
-    if [ ! -x $exec ]; then
-      if [ ! -e $exec ]; then
-        echo "calico-node executable $exec not found"
-      else
-        echo "You do not have permission to execute the calico-node executable $exec"
-      fi	      
-      exit 5
-    fi
-
-    [ -x "$dockerexec" ] || exit 0
-
-    do_status
-    retval=$?
-    if [ $retval -ne 0 ]; then
-        printf "Starting $prog:\t"
-        echo "\n$(date)\n" >> $logfile
-{% if legacy_calicoctl %}
-        $exec node --ip=${DEFAULT_IPV4} &>>$logfile
-{% else %}
-        $exec node run --ip=${DEFAULT_IPV4} &>>$logfile
-{% endif %}
-        success
-        echo
-    else
-        echo -n "calico-node's already running"
-        success
-        exit 0
-    fi
-}
-
-do_stop() {
-    echo -n $"Stopping $prog: "
-{% if legacy_calicoctl %}
-    $exec node stop >> /dev/null || $exec node stop --force >> /dev/null
-{% else %}
-    echo "Current version of ${exec} doesn't support 'node stop' command!"
-    return 1
-{% endif %}
-    retval=$?
-    echo
-    return $retval
-}
-
-restart() {
-    do_stop
-    do_start
-}
-
-reload() {
-    restart
-}
-
-force_reload() {
-    restart
-}
-
-case "$1" in
-    start)
-        do_start
-        case "$?" in
-                0|1) success || exit 0 ;;
-                2) failure || exit 1 ;;
-        esac
-        ;;
-    stop)
-        echo -n "Stopping $DESC" "$NAME"
-        if do_stop; then
-            success
-            echo
-        else
-            echo -n "Can't stop calico-node"
-            failure
-            echo
-        fi
-        ;;
-    restart)
-        $1
-        ;;
-    reload)
-        $1
-        ;;
-    force-reload)
-        force_reload
-        ;;
-    status)
-        if do_status; then
-            echo -n "Calico-node is running"
-            success
-            echo
-        else
-            echo -n "Calico-node is not running"
-            failure
-            echo
-        fi
-        ;;
-    *)
-        echo $"Usage: $0 {start|stop|status|restart|reload|force-reload}"
-        exit 2
-esac
-
-exit $?

roles/network_plugin/flannel/defaults/main.yml

@@ -16,3 +16,6 @@ flannel_memory_limit: 500M
 flannel_cpu_limit: 300m
 flannel_memory_requests: 256M
 flannel_cpu_requests: 150m
+
+flannel_cert_dir: /etc/flannel/certs
+etcd_cert_dir: /etc/ssl/etcd/ssl

roles/network_plugin/flannel/handlers/main.yml

@@ -15,13 +15,12 @@
 
 - name : Flannel | reload systemd
   shell: systemctl daemon-reload
-  when: ansible_service_mgr == "systemd"
 
 - name: Flannel | reload docker.socket
   service:
     name: docker.socket
     state: restarted
-  when: ansible_os_family == 'CoreOS'
+  when: ansible_os_family in ['CoreOS', 'Container Linux by CoreOS']
 
 - name: Flannel | reload docker
   service:

roles/network_plugin/flannel/tasks/main.yml

@@ -7,6 +7,25 @@
   delegate_to: "{{groups['etcd'][0]}}"
   run_once: true
 
+- name: Flannel | Create flannel certs directory
+  file:
+    dest: "{{ flannel_cert_dir }}"
+    state: directory
+    mode: 0750
+    owner: root
+    group: root
+
+- name: Flannel | Link etcd certificates for flanneld
+  file:
+    src: "{{ etcd_cert_dir }}/{{ item.s }}"
+    dest: "{{ flannel_cert_dir }}/{{ item.d }}"
+    state: hard
+    force: yes
+  with_items:
+    - {s: "ca.pem", d: "ca_cert.crt"}
+    - {s: "node-{{ inventory_hostname }}.pem", d: "cert.crt"}
+    - {s: "node-{{ inventory_hostname }}-key.pem", d: "key.pem"}
+
 - name: Flannel | Create flannel pod manifest
   template:
     src: flannel-pod.yml
@@ -51,31 +70,11 @@
     docker_network_options: '"--bip={{ flannel_subnet }} --mtu={{ flannel_mtu }}"'
   tags: facts
 
-- name: Flannel | Remove non-systemd docker daemon network options that don't match desired line
-  lineinfile:
-    dest: "{{ docker_options_file }}"
-    regexp: "^DOCKER_NETWORK_OPTIONS=(?!{{ docker_network_options|regex_escape() }})"
-    state: absent
-  when: ansible_service_mgr in ["sysvinit","upstart"]
-
-- name: Flannel | Set non-systemd docker daemon network options
-  lineinfile:
-    dest: "{{ docker_options_file }}"
-    line: DOCKER_NETWORK_OPTIONS={{ docker_network_options }}
-    insertbefore: ^{{ docker_options_name }}=
-    owner: root
-    group: root
-    mode: 0644
-  notify:
-    - Flannel | restart docker
-  when: ansible_service_mgr in ["sysvinit","upstart"]
-
 - name: Flannel | Ensure path for docker network systemd drop-in
   file:
     path: "/etc/systemd/system/docker.service.d"
     state: directory
     owner: root
-  when: ansible_service_mgr == "systemd"
 
 - name: Flannel | Create docker network systemd drop-in
   template:
@@ -83,6 +82,3 @@
     dest: "/etc/systemd/system/docker.service.d/flannel-options.conf"
   notify:
     - Flannel | restart docker
-  when: ansible_service_mgr == "systemd"
-
-- meta: flush_handlers

roles/network_plugin/flannel/templates/flannel-options.conf.j2

@@ -1,5 +1,5 @@
 [Service]
-{% if ansible_os_family == "CoreOS" %}
+{% if ansible_os_family in ["CoreOS", "Container Linux by CoreOS"] %}
 Environment="DOCKER_OPT_BIP=--bip={{ flannel_subnet }} --mtu={{ flannel_mtu }}"
 {% else %}
 Environment="DOCKER_NETWORK_OPTIONS=--bip={{ flannel_subnet }} --mtu={{ flannel_mtu }}"

roles/network_plugin/flannel/templates/flannel-pod.yml

@@ -14,7 +14,7 @@
           path: "/run/flannel"
       - name: "etcd-certs"
         hostPath:
-          path: "{{ etcd_cert_dir }}"
+          path: "{{ flannel_cert_dir }}"
     containers:
       - name: "flannel-container"
         image: "{{ flannel_image_repo }}:{{ flannel_image_tag }}"
@@ -29,7 +29,7 @@
         command:
           - "/bin/sh"
           - "-c"
-          - "/opt/bin/flanneld -etcd-endpoints {{ etcd_access_endpoint }} -etcd-prefix /{{ cluster_name }}/network -etcd-cafile {{ etcd_cert_dir }}/ca.pem -etcd-certfile {{ etcd_cert_dir }}/node-{{ inventory_hostname }}.pem -etcd-keyfile {{ etcd_cert_dir }}/node-{{ inventory_hostname }}-key.pem {% if flannel_interface is defined %}-iface {{ flannel_interface }}{% endif %} {% if flannel_public_ip is defined %}-public-ip {{ flannel_public_ip }}{% endif %}"
+          - "/opt/bin/flanneld -etcd-endpoints {{ etcd_access_endpoint }} -etcd-prefix /{{ cluster_name }}/network -etcd-cafile {{ flannel_cert_dir }}/ca_cert.crt -etcd-certfile {{ flannel_cert_dir }}/cert.crt -etcd-keyfile {{ flannel_cert_dir }}/key.pem {% if flannel_interface is defined %}-iface {{ flannel_interface }}{% endif %} {% if flannel_public_ip is defined %}-public-ip {{ flannel_public_ip }}{% endif %}"
         ports:
           - hostPort: 10253
             containerPort: 10253
@@ -37,7 +37,7 @@
           - name: "subnetenv"
             mountPath: "/run/flannel"
           - name: "etcd-certs"
-            mountPath: "{{ etcd_cert_dir }}"
+            mountPath: "{{ flannel_cert_dir }}"
             readOnly: true
         securityContext:
           privileged: true

roles/network_plugin/weave/handlers/main.yml

@@ -7,7 +7,6 @@
 
 - name : Weave | reload systemd
   shell: systemctl daemon-reload
-  when: ansible_service_mgr == "systemd"
 
 - name: restart weaveproxy
   command: /bin/true

roles/network_plugin/weave/tasks/main.yml

@@ -31,17 +31,14 @@
 
 - name: Weave | Write weave systemd init file
   template: src=weave.service.j2 dest=/etc/systemd/system/weave.service
-  when: ansible_service_mgr == "systemd"
   notify: restart weave
 
 - name: Weave | Write weaveproxy systemd init file
   template: src=weaveproxy.service.j2 dest=/etc/systemd/system/weaveproxy.service
-  when: ansible_service_mgr == "systemd"
   notify: restart weaveproxy
 
 - name: Weave | Write weaveexpose systemd init file
   template: src=weaveexpose.service.j2 dest=/etc/systemd/system/weaveexpose.service
-  when: ansible_service_mgr == "systemd"
   notify: restart weaveexpose
 
 - meta: flush_handlers

roles/reset/tasks/main.yml

@@ -1,7 +1,7 @@
 ---
 
 - name: reset | stop services
-  service: name={{item}} state=stopped
+  service: name={{ item }} state=stopped
   with_items:
     - kubelet
     - etcd
@@ -16,13 +16,26 @@
     - etcd
   register: services_removed
 
+- name: reset | remove docker dropins
+  file:
+    path: "/etc/systemd/system/docker.service.d/{{ item }}"
+    state: absent
+  with_items:
+    - docker-dns.conf
+    - docker-options.conf
+  register: docker_dropins_removed
+
 - name: reset | systemctl daemon-reload
   command: systemctl daemon-reload
-  when: ansible_service_mgr == "systemd" and services_removed.changed
+  when: services_removed.changed or docker_dropins_removed.changed
 
 - name: reset | remove all containers
   shell: "{{ docker_bin_dir }}/docker ps -aq | xargs -r docker rm -fv"
 
+- name: reset | restart docker if needed
+  service: name=docker state=restarted
+  when: docker_dropins_removed.changed
+
 - name: reset | gather mounted kubelet dirs
   shell: mount | grep /var/lib/kubelet | awk '{print $3}' | tac
   register: mounted_dirs
@@ -42,6 +55,40 @@
     - /etc/cni
     - /etc/nginx
     - /etc/dnsmasq.d
+    - /etc/dnsmasq.conf
+    - /etc/dnsmasq.d-available
     - /etc/etcd.env
     - /etc/calico
     - /opt/cni
+    - /etc/dhcp/dhclient.d/zdnsupdate.sh
+    - /etc/dhcp/dhclient-exit-hooks.d/zdnsupdate
+    - "{{ bin_dir }}/kubelet"
+
+- name: reset | remove dns settings from dhclient.conf
+  blockinfile:
+    dest: "{{ item }}"
+    state: absent
+    follow: yes
+    marker: "# Ansible entries {mark}"
+  failed_when: false
+  with_items:
+    - /etc/dhclient.conf
+    - /etc/dhcp/dhclient.conf
+
+- name: reset | remove host entries from /etc/hosts
+  blockinfile:
+    dest: "/etc/hosts"
+    state: absent
+    follow: yes
+    marker: "# Ansible inventory hosts {mark}"
+
+- name: reset | Restart network
+  service:
+    name: >-
+      {% if ansible_os_family == "RedHat" -%}
+      network
+      {%- elif ansible_os_family == "Debian" -%}
+      networking
+      {%- endif %}
+    state: restarted
+  when: ansible_os_family != "CoreOS"

roles/rkt/defaults/main.yml

@@ -0,0 +1,6 @@
+---
+
+rkt_version: 1.12.0
+rkt_pkg_version: "{{ rkt_version }}-1"
+rkt_download_src: https://github.com/coreos/rkt
+rkt_download_url: "{{ rkt_download_src }}/releases/download/v{{ rkt_version }}"

roles/rkt/tasks/install.yml

@@ -0,0 +1,35 @@
+---
+- name: gather os specific variables for rkt
+  include_vars: "{{ item }}"
+  with_first_found:
+    - files:
+      - "{{ ansible_distribution|lower }}-{{ ansible_distribution_version|lower|replace('/', '_') }}.yml"
+      - "{{ ansible_distribution|lower }}-{{ ansible_distribution_release }}.yml"
+      - "{{ ansible_distribution|lower }}-{{ ansible_distribution_major_version|lower|replace('/', '_') }}.yml"
+      - "{{ ansible_distribution|lower }}.yml"
+      - "{{ ansible_os_family|lower }}.yml"
+      - defaults.yml
+      paths:
+      - ../vars
+      skip: true
+  tags: facts
+
+- name: install rkt pkg on ubuntu
+  apt:
+    deb: "{{ rkt_download_url }}/{{ rkt_pkg_name }}"
+    state: present
+  register: rkt_task_result
+  until: rkt_task_result|success
+  retries: 4
+  delay: "{{ retry_stagger | random + 3 }}"
+  when: ansible_os_family == "Debian"
+
+- name: install rkt pkg on centos
+  yum:
+    pkg: "{{ rkt_download_url }}/{{ rkt_pkg_name }}"
+    state: present
+  register: rkt_task_result
+  until: rkt_task_result|success
+  retries: 4
+  delay: "{{ retry_stagger | random + 3 }}"
+  when: ansible_os_family == "RedHat"

roles/rkt/tasks/main.yml

@@ -0,0 +1,4 @@
+---
+
+- name: Install rkt
+  include: install.yml

roles/rkt/vars/debian.yml

@@ -0,0 +1,2 @@
+---
+rkt_pkg_name: "rkt_{{ rkt_pkg_version }}_amd64.deb"

roles/rkt/vars/fedora.yml

@@ -0,0 +1,2 @@
+---
+rkt_pkg_name: "rkt-{{ rkt_pkg_version }}.x86_64.rpm"

roles/rkt/vars/redhat.yml

@@ -0,0 +1,2 @@
+---
+rkt_pkg_name: "rkt-{{ rkt_pkg_version }}.x86_64.rpm"

scripts/premoderator.sh

@@ -0,0 +1,15 @@
+#!/bin/sh -eux -o pipefail
+# A naive premoderation script to allow Gitlab CI pipeline on a specific PRs' comment
+# Exits with 0, if the pipeline is good to go
+
+CURL_ARGS="-fs --connect-timeout 5 --max-time 5 --retry-max-time 20 --retry 4 --retry-delay 5"
+MAGIC="${MAGIC:-ci check this}"
+
+# Get PR number from CI_BUILD_REF_NAME
+issue=$(echo ${CI_BUILD_REF_NAME} | perl -ne '/^pr-(\d+)-\S+$/ && print $1')
+# Get the user name from the PR comments with the wanted magic incantation casted
+user=$(curl ${CURL_ARGS} "https://api.github.com/repos/kubernetes-incubator/kargo/issues/${issue}/comments" \
+  | jq -M "map(select(.body | contains (\"$MAGIC\"))) | .[0] .user.login" | tr -d '"')
+# Check for the required user group membership to allow (exit 0) or decline (exit >0) the pipeline
+[ "$user" != "null" ] || exit 1
+curl ${CURL_ARGS} "https://api.github.com/orgs/kubernetes-incubator/members/${user}"

tests/cloud_playbooks/create-gce.yml

@@ -24,7 +24,7 @@
         instance_names: "{{instance_names}}"
         machine_type: "{{ cloud_machine_type }}"
         image: "{{ cloud_image }}"
-        preemptible: yes
+        preemptible: no
         service_account_email: "{{ gce_service_account_email }}"
         pem_file: "{{ gce_pem_file | default(omit)}}"
         credentials_file: "{{gce_credentials_file | default(omit)}}"

tests/testcases/020_check-create-pod.yml

@@ -7,14 +7,14 @@
 
   tasks:
 
-  - name: Force binaries directory for CoreOS
+  - name: Force binaries directory for Container Linux by CoreOS
     set_fact:
       bin_dir: "/opt/bin"
-    when: ansible_os_family == "CoreOS"
+    when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
   - set_fact:
       bin_dir: "/usr/local/bin"
-    when: ansible_os_family != "CoreOS"
+    when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
   - name: Run a replica controller composed of 2 pods
     shell: "{{bin_dir}}/kubectl run test --image={{test_image_repo}}:{{test_image_tag}} --replicas=2 --command -- tail -f /dev/null"

tests/testcases/030_check-network.yml

@@ -3,14 +3,14 @@
 
   tasks:
 
-  - name: Force binaries directory for CoreOS
+  - name: Force binaries directory for Container Linux by CoreOS
     set_fact:
       bin_dir: "/opt/bin"
-    when: ansible_os_family == "CoreOS"
+    when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
   - set_fact:
       bin_dir: "/usr/local/bin"
-    when: ansible_os_family != "CoreOS"
+    when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
   - name: Get pod names
     shell: "{{bin_dir}}/kubectl get pods -o json"

tests/testcases/040_check-network-adv.yml

@@ -12,14 +12,14 @@
     netchecker_port: 31081
 
   tasks:
-    - name: Force binaries directory for CoreOS
+    - name: Force binaries directory for Container Linux by CoreOS
       set_fact:
         bin_dir: "/opt/bin"
-      when: ansible_os_family == "CoreOS"
+      when: ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
     - set_fact:
         bin_dir: "/usr/local/bin"
-      when: ansible_os_family != "CoreOS"
+      when: not ansible_os_family in ["CoreOS", "Container Linux by CoreOS"]
 
     - name: Wait for netchecker server
       shell: "{{ bin_dir }}/kubectl get pods --namespace {{netcheck_namespace}} | grep ^netchecker-server"