diff --git a/README.md b/README.md
index 6a856fe5..fb4e9953 100644
--- a/README.md
+++ b/README.md
@@ -59,6 +59,7 @@ Name | Description
[kubernetes.core.k8s](https://github.com/ansible-collections/kubernetes.core/blob/main/docs/kubernetes.core.k8s_module.rst)|Manage Kubernetes (K8s) objects
[kubernetes.core.k8s_cluster_info](https://github.com/ansible-collections/kubernetes.core/blob/main/docs/kubernetes.core.k8s_cluster_info_module.rst)|Describe Kubernetes (K8s) cluster, APIs available and their respective versions
[kubernetes.core.k8s_cp](https://github.com/ansible-collections/kubernetes.core/blob/main/docs/kubernetes.core.k8s_cp_module.rst)|Copy files and directories to and from pod.
+[kubernetes.core.k8s_drain](https://github.com/ansible-collections/kubernetes.core/blob/main/docs/kubernetes.core.k8s_drain_module.rst)|Drain, Cordon, or Uncordon node in k8s cluster
[kubernetes.core.k8s_exec](https://github.com/ansible-collections/kubernetes.core/blob/main/docs/kubernetes.core.k8s_exec_module.rst)|Execute command in Pod
[kubernetes.core.k8s_info](https://github.com/ansible-collections/kubernetes.core/blob/main/docs/kubernetes.core.k8s_info_module.rst)|Describe Kubernetes (K8s) objects
[kubernetes.core.k8s_json_patch](https://github.com/ansible-collections/kubernetes.core/blob/main/docs/kubernetes.core.k8s_json_patch_module.rst)|Apply JSON patch operations to existing objects
diff --git a/docs/kubernetes.core.k8s_cp_module.rst b/docs/kubernetes.core.k8s_cp_module.rst
index adad5213..5637cb01 100644
--- a/docs/kubernetes.core.k8s_cp_module.rst
+++ b/docs/kubernetes.core.k8s_cp_module.rst
@@ -8,7 +8,7 @@ kubernetes.core.k8s_cp
**Copy files and directories to and from pod.**
-Version added: 2.1.0
+Version added: 2.2.0
.. contents::
:local:
@@ -221,11 +221,14 @@ Parameters
no_preserve
- string
+ boolean
- Default:
"no"
+
|
The copied file/directory's ownership and permissions will not be preserved in the container.
@@ -452,6 +455,7 @@ Notes
-----
.. note::
+ - the tar binary is required on the container when copying from local filesystem to pod.
- To avoid SSL certificate validation errors when ``validate_certs`` is *True*, the full certificate chain for the API server must be provided via ``ca_cert`` or in the kubeconfig file.
@@ -463,7 +467,7 @@ Examples
# kubectl cp /tmp/foo some-namespace/some-pod:/tmp/bar
- name: Copy /tmp/foo local file to /tmp/bar in a remote pod
- kubernetes.core.k8s:
+ kubernetes.core.k8s_cp:
namespace: some-namespace
pod: some-pod
remote_path: /tmp/bar
@@ -471,7 +475,7 @@ Examples
# kubectl cp /tmp/foo_dir some-namespace/some-pod:/tmp/bar_dir
- name: Copy /tmp/foo_dir local directory to /tmp/bar_dir in a remote pod
- kubernetes.core.k8s:
+ kubernetes.core.k8s_cp:
namespace: some-namespace
pod: some-pod
remote_path: /tmp/bar_dir
@@ -479,7 +483,7 @@ Examples
# kubectl cp /tmp/foo some-namespace/some-pod:/tmp/bar -c some-container
- name: Copy /tmp/foo local file to /tmp/bar in a remote pod in a specific container
- kubernetes.core.k8s:
+ kubernetes.core.k8s_cp:
namespace: some-namespace
pod: some-pod
container: some-container
@@ -490,7 +494,7 @@ Examples
# kubectl cp some-namespace/some-pod:/tmp/foo /tmp/bar
- name: Copy /tmp/foo from a remote pod to /tmp/bar locally
- kubernetes.core.k8s:
+ kubernetes.core.k8s_cp:
namespace: some-namespace
pod: some-pod
remote_path: /tmp/foo
@@ -499,7 +503,7 @@ Examples
# copy content into a file in the remote pod
- name: Copy /tmp/foo from a remote pod to /tmp/bar locally
- kubernetes.core.k8s:
+ kubernetes.core.k8s_cp:
state: to_pod
namespace: some-namespace
pod: some-pod
diff --git a/docs/kubernetes.core.k8s_drain_module.rst b/docs/kubernetes.core.k8s_drain_module.rst
new file mode 100644
index 00000000..741b632c
--- /dev/null
+++ b/docs/kubernetes.core.k8s_drain_module.rst
@@ -0,0 +1,559 @@
+.. _kubernetes.core.k8s_drain_module:
+
+
+*************************
+kubernetes.core.k8s_drain
+*************************
+
+**Drain, Cordon, or Uncordon node in k8s cluster**
+
+
+
+.. contents::
+ :local:
+ :depth: 1
+
+
+Synopsis
+--------
+- Drain node in preparation for maintenance same as kubectl drain.
+- Cordon will mark the node as unschedulable.
+- Uncordon will mark the node as schedulable.
+- The given node will be marked unschedulable to prevent new pods from arriving.
+- Then drain deletes all pods except mirror pods (which cannot be deleted through the API server).
+
+
+
+Requirements
+------------
+The below requirements are needed on the host that executes this module.
+
+- python >= 3.6
+- kubernetes >= 12.0.0
+
+
+Parameters
+----------
+
+.. raw:: html
+
+
+
+ | Parameter |
+ Choices/Defaults |
+ Comments |
+
+
+ |
+
+ api_key
+
+
+ string
+
+ |
+
+ |
+
+ Token used to authenticate with the API. Can also be specified via K8S_AUTH_API_KEY environment variable.
+ |
+
+
+ |
+
+ ca_cert
+
+
+ path
+
+ |
+
+ |
+
+ Path to a CA certificate used to authenticate with the API. The full certificate chain must be provided to avoid certificate validation errors. Can also be specified via K8S_AUTH_SSL_CA_CERT environment variable.
+
aliases: ssl_ca_cert
+ |
+
+
+ |
+
+ client_cert
+
+
+ path
+
+ |
+
+ |
+
+ Path to a certificate used to authenticate with the API. Can also be specified via K8S_AUTH_CERT_FILE environment variable.
+
aliases: cert_file
+ |
+
+
+ |
+
+ client_key
+
+
+ path
+
+ |
+
+ |
+
+ Path to a key file used to authenticate with the API. Can also be specified via K8S_AUTH_KEY_FILE environment variable.
+
aliases: key_file
+ |
+
+
+ |
+
+ context
+
+
+ string
+
+ |
+
+ |
+
+ The name of a context found in the config file. Can also be specified via K8S_AUTH_CONTEXT environment variable.
+ |
+
+
+ |
+
+ delete_options
+
+
+ dictionary
+
+ |
+
+ |
+
+ Specify options to delete pods.
+ This option has effect only when state is set to drain.
+ |
+
+
+ |
+
+
+ disable_eviction
+
+
+ boolean
+
+ |
+
+
+ |
+
+ Forces drain to use delete rather than evict.
+ |
+
+
+ |
+
+
+ force
+
+
+ boolean
+
+ |
+
+
+ |
+
+ Continue even if there are pods not managed by a ReplicationController, Job, or DaemonSet.
+ |
+
+
+ |
+
+
+ ignore_daemonsets
+
+
+ boolean
+
+ |
+
+
+ |
+
+ Ignore DaemonSet-managed pods.
+ |
+
+
+ |
+
+
+ terminate_grace_period
+
+
+ integer
+
+ |
+
+ |
+
+ Specify how many seconds to wait before forcefully terminating.
+ If not specified, the default grace period for the object type will be used.
+ The value zero indicates delete immediately.
+ |
+
+
+ |
+
+
+ wait_sleep
+
+
+ integer
+
+ |
+
+ Default:
5
+ |
+
+ Number of seconds to sleep between checks.
+ Ignored if wait_timeout is not set.
+ |
+
+
+ |
+
+
+ wait_timeout
+
+
+ integer
+
+ |
+
+ |
+
+ The length of time to wait in seconds for pod to be deleted before giving up, zero means infinite.
+ |
+
+
+
+ |
+
+ host
+
+
+ string
+
+ |
+
+ |
+
+ Provide a URL for accessing the API. Can also be specified via K8S_AUTH_HOST environment variable.
+ |
+
+
+ |
+
+ kubeconfig
+
+
+ path
+
+ |
+
+ |
+
+ Path to an existing Kubernetes config file. If not provided, and no other connection options are provided, the Kubernetes client will attempt to load the default configuration file from ~/.kube/config. Can also be specified via K8S_AUTH_KUBECONFIG environment variable.
+ |
+
+
+ |
+
+ name
+
+
+ string
+ / required
+
+ |
+
+ |
+
+ The name of the node.
+ |
+
+
+ |
+
+ password
+
+
+ string
+
+ |
+
+ |
+
+ Provide a password for authenticating with the API. Can also be specified via K8S_AUTH_PASSWORD environment variable.
+ Please read the description of the username option for a discussion of when this option is applicable.
+ |
+
+
+ |
+
+ persist_config
+
+
+ boolean
+
+ |
+
+
+ |
+
+ Whether or not to save the kube config refresh tokens. Can also be specified via K8S_AUTH_PERSIST_CONFIG environment variable.
+ When the k8s context is using a user credentials with refresh tokens (like oidc or gke/gcloud auth), the token is refreshed by the k8s python client library but not saved by default. So the old refresh token can expire and the next auth might fail. Setting this flag to true will tell the k8s python client to save the new refresh token to the kube config file.
+ Default to false.
+ Please note that the current version of the k8s python client library does not support setting this flag to True yet.
+ The fix for this k8s python library is here: https://github.com/kubernetes-client/python-base/pull/169
+ |
+
+
+ |
+
+ proxy
+
+
+ string
+
+ |
+
+ |
+
+ The URL of an HTTP proxy to use for the connection. Can also be specified via K8S_AUTH_PROXY environment variable.
+ Please note that this module does not pick up typical proxy settings from the environment (e.g. HTTP_PROXY).
+ |
+
+
+ |
+
+ proxy_headers
+
+
+ dictionary
+
+ added in 2.0.0
+ |
+
+ |
+
+ The Header used for the HTTP proxy.
+
+ |
+
+
+ |
+
+
+ basic_auth
+
+
+ string
+
+ |
+
+ |
+
+ Colon-separated username:password for basic authentication header.
+ Can also be specified via K8S_AUTH_PROXY_HEADERS_BASIC_AUTH environment.
+ |
+
+
+ |
+
+
+ proxy_basic_auth
+
+
+ string
+
+ |
+
+ |
+
+ Colon-separated username:password for proxy basic authentication header.
+ Can also be specified via K8S_AUTH_PROXY_HEADERS_PROXY_BASIC_AUTH environment.
+ |
+
+
+ |
+
+
+ user_agent
+
+
+ string
+
+ |
+
+ |
+
+ String representing the user-agent you want, such as foo/1.0.
+ Can also be specified via K8S_AUTH_PROXY_HEADERS_USER_AGENT environment.
+ |
+
+
+
+ |
+
+ state
+
+
+ string
+
+ |
+
+ Choices:
+ - cordon
+ drain ← - uncordon
+
+ |
+
+ Determines whether to drain, cordon, or uncordon node.
+ |
+
+
+ |
+
+ username
+
+
+ string
+
+ |
+
+ |
+
+ Provide a username for authenticating with the API. Can also be specified via K8S_AUTH_USERNAME environment variable.
+ Please note that this only works with clusters configured to use HTTP Basic Auth. If your cluster has a different form of authentication (e.g. OAuth2 in OpenShift), this option will not work as expected and you should look into the community.okd.k8s_auth module, as that might do what you need.
+ |
+
+
+ |
+
+ validate_certs
+
+
+ boolean
+
+ |
+
+
+ |
+
+ Whether or not to verify the API server's SSL certificates. Can also be specified via K8S_AUTH_VERIFY_SSL environment variable.
+
aliases: verify_ssl
+ |
+
+
+
+
+
+Notes
+-----
+
+.. note::
+ - To avoid SSL certificate validation errors when ``validate_certs`` is *True*, the full certificate chain for the API server must be provided via ``ca_cert`` or in the kubeconfig file.
+
+
+
+Examples
+--------
+
+.. code-block:: yaml
+
+ - name: Drain node "foo", even if there are pods not managed by a ReplicationController, Job, or DaemonSet on it.
+ kubernetes.core.k8s_drain:
+ state: drain
+ name: foo
+ force: yes
+
+ - name: Drain node "foo", but abort if there are pods not managed by a ReplicationController, Job, or DaemonSet, and use a grace period of 15 minutes.
+ kubernetes.core.k8s_drain:
+ state: drain
+ name: foo
+ delete_options:
+ terminate_grace_period: 900
+
+ - name: Mark node "foo" as schedulable.
+ kubernetes.core.k8s_drain:
+ state: uncordon
+ name: foo
+
+ - name: Mark node "foo" as unschedulable.
+ kubernetes.core.k8s_drain:
+ state: cordon
+ name: foo
+
+
+
+Return Values
+-------------
+Common return values are documented `here `_, the following are the fields unique to this module:
+
+.. raw:: html
+
+
+
+ | Key |
+ Returned |
+ Description |
+
+
+ |
+
+ result
+
+
+ string
+
+ |
+ success |
+
+ The node status and the number of pods deleted.
+
+ |
+
+
+
+
+
+Status
+------
+
+
+Authors
+~~~~~~~
+
+- Aubin Bikouo (@abikouo)
diff --git a/molecule/default/molecule.yml b/molecule/default/molecule.yml
index 5f060d58..8b36c3fc 100644
--- a/molecule/default/molecule.yml
+++ b/molecule/default/molecule.yml
@@ -13,7 +13,7 @@ provisioner:
log: true
config_options:
inventory:
- enable_plugins: kubernetes.core.k8s
+ enable_plugins: kubernetes.core.k8s,yaml
lint: {}
inventory:
hosts:
diff --git a/molecule/default/prepare.yml b/molecule/default/prepare.yml
index d1f8072e..5853460e 100644
--- a/molecule/default/prepare.yml
+++ b/molecule/default/prepare.yml
@@ -6,45 +6,7 @@
collections:
- kubernetes.core
- vars:
- node_taints:
- - "node.kubernetes.io/not-ready"
- - "node.kubernetes.io/unreachable"
- - "node.kubernetes.io/unschedulable"
- kind_bin_path: "/usr/local/bin/kind"
-
tasks:
- # We are spawning k8s cluster using kind executable and we ensure that the cluster is up
- # and node is ready, if this is not validated we may face issue later on when running tests
- - name: Check if kind binary is available or not
- stat:
- path: "{{ kind_bin_path }}"
- register: r
-
- - name: Download kind if not available
- get_url:
- url: https://kind.sigs.k8s.io/dl/v0.11.1/kind-linux-amd64
- dest: "{{ kind_bin_path }}"
- when: not r.stat.exists
-
- - name: Make kind executable
- file:
- path: "{{ kind_bin_path }}"
- mode: '0755'
-
- - name: Check if Kind cluster exists
- command: "{{ kind_bin_path }} get clusters"
- register: r
- ignore_errors: true
-
- - name: Create cluster
- command: "{{ kind_bin_path }} create cluster"
- when: r.stdout == ''
-
- - name: Assert that nodes are ready
- k8s_info:
- kind: Node
- retries: 10
- delay: 30
- register: nodes
- until: nodes.resources | selectattr("spec.taints", "defined") | map(attribute="spec.taints") | list | length == 0
+ - name: Include drain.yml
+ include_tasks:
+ file: tasks/drain.yml
diff --git a/molecule/default/tasks/drain.yml b/molecule/default/tasks/drain.yml
new file mode 100644
index 00000000..baf52a80
--- /dev/null
+++ b/molecule/default/tasks/drain.yml
@@ -0,0 +1,219 @@
+---
+- block:
+ - name: Set common facts
+ set_fact:
+ drain_namespace: "drain"
+ drain_daemonset_name: "promotheus-dset"
+ drain_pod_name: "pod-drain"
+
+ - name: Create {{ drain_namespace }} namespace
+ k8s:
+ kind: Namespace
+ name: '{{ drain_namespace }}'
+
+ - name: list cluster nodes
+ k8s_info:
+ kind: node
+ register: nodes
+
+ - name: Select uncordoned nodes
+ set_fact:
+ uncordoned_nodes: "{{ nodes.resources | selectattr('spec.unschedulable', 'undefined') | map(attribute='metadata.name') | list}}"
+
+ - name: Assert that at least one node is schedulable
+ assert:
+ that:
+ - uncordoned_nodes | length > 0
+
+ - name: select node to drain
+ set_fact:
+ node_to_drain: '{{ uncordoned_nodes[0] }}'
+
+ - name: Deploy daemonset on cluster
+ k8s:
+ namespace: '{{ drain_namespace }}'
+ definition:
+ apiVersion: apps/v1
+ kind: DaemonSet
+ metadata:
+ name: '{{ drain_daemonset_name }}'
+ spec:
+ affinity:
+ nodeAffinity:
+ requiredDuringSchedulingIgnoredDuringExecution:
+ nodeSelectorTerms:
+ - matchFields:
+ - key: metadata.name
+ operator: In
+ values:
+ - '{{ node_to_drain }}'
+ selector:
+ matchLabels:
+ name: prometheus-exporter
+ template:
+ metadata:
+ labels:
+ name: prometheus-exporter
+ spec:
+ containers:
+ - name: prometheus
+ image: prom/node-exporter
+ ports:
+ - containerPort: 80
+
+ - name: Create Pods not managed by ReplicationController, ReplicaSet, Job, DaemonSet or StatefulSet.
+ k8s:
+ namespace: '{{ drain_namespace }}'
+ wait: yes
+ definition:
+ apiVersion: v1
+ kind: Pod
+ metadata:
+ name: '{{ drain_pod_name }}'
+ spec:
+ affinity:
+ nodeAffinity:
+ requiredDuringSchedulingIgnoredDuringExecution:
+ nodeSelectorTerms:
+ - matchFields:
+ - key: metadata.name
+ operator: In
+ values:
+ - '{{ node_to_drain }}'
+ containers:
+ - name: c0
+ image: busybox
+ command:
+ - /bin/sh
+ - -c
+ - while true;do date;sleep 5; done
+
+ - name: Cordon node
+ k8s_drain:
+ state: cordon
+ name: '{{ node_to_drain }}'
+ register: cordon
+
+ - name: assert that cordon is changed
+ assert:
+ that:
+ - cordon is changed
+
+ - name: Test cordon idempotency
+ k8s_drain:
+ state: cordon
+ name: '{{ node_to_drain }}'
+ register: cordon
+
+ - name: assert that cordon is not changed
+ assert:
+ that:
+ - cordon is not changed
+
+ - name: Get pods
+ k8s_info:
+ kind: Pod
+ namespace: '{{ drain_namespace }}'
+ register: Pod
+
+ - name: assert that pods are running on cordoned node
+ assert:
+ that:
+ - "{{ Pod.resources | selectattr('status.phase', 'equalto', 'Running') | selectattr('spec.nodeName', 'equalto', node_to_drain) | list | length > 0 }}"
+
+ - name: Uncordon node
+ k8s_drain:
+ state: uncordon
+ name: '{{ node_to_drain }}'
+ register: uncordon
+
+ - name: assert that uncordon is changed
+ assert:
+ that:
+ - uncordon is changed
+
+ - name: Test uncordon idempotency
+ k8s_drain:
+ state: uncordon
+ name: '{{ node_to_drain }}'
+ register: uncordon
+
+ - name: assert that uncordon is not changed
+ assert:
+ that:
+ - uncordon is not changed
+
+ - name: Drain node
+ k8s_drain:
+ state: drain
+ name: '{{ node_to_drain }}'
+ ignore_errors: true
+ register: drain_result
+
+ - name: assert that drain failed due to DaemonSet managed Pods
+ assert:
+ that:
+ - drain_result is failed
+ - '"cannot delete DaemonSet-managed Pods" in drain_result.msg'
+ - '"cannot delete Pods not managed by ReplicationController, ReplicaSet, Job, DaemonSet or StatefulSet" in drain_result.msg'
+
+ - name: Drain node using ignore_daemonsets and force options
+ k8s_drain:
+ state: drain
+ name: '{{ node_to_drain }}'
+ delete_options:
+ force: true
+ ignore_daemonsets: true
+ wait_timeout: 0
+ register: drain_result
+
+ - name: assert that node has been drained
+ assert:
+ that:
+ - drain_result is changed
+ - '"node {{ node_to_drain }} marked unschedulable." in drain_result.result'
+
+ - name: assert that unmanaged pod were deleted
+ k8s_info:
+ namespace: '{{ drain_namespace }}'
+ kind: Pod
+ register: _result
+ failed_when: _result.resources | selectattr("metadata.ownerReferences", "undefined") | length > 0
+
+ - name: Test drain idempotency
+ k8s_drain:
+ state: drain
+ name: '{{ node_to_drain }}'
+ delete_options:
+ force: true
+ ignore_daemonsets: true
+ register: drain_result
+
+ - name: Check idempotency
+ assert:
+ that:
+ - drain_result is not changed
+
+ - name: Get DaemonSet
+ k8s_info:
+ kind: DaemonSet
+ namespace: '{{ drain_namespace }}'
+ name: '{{ drain_daemonset_name }}'
+ register: dset_result
+
+ - name: assert that daemonset managed pods were not removed
+ assert:
+ that:
+ - dset_result.resources | list | length > 0
+
+ - name: Uncordon node
+ k8s_drain:
+ state: uncordon
+ name: '{{ node_to_drain }}'
+
+ always:
+ - name: delete namespace
+ k8s:
+ state: absent
+ kind: namespace
+ name: '{{ drain_namespace }}'
diff --git a/plugins/modules/k8s_drain.py b/plugins/modules/k8s_drain.py
new file mode 100644
index 00000000..25148986
--- /dev/null
+++ b/plugins/modules/k8s_drain.py
@@ -0,0 +1,409 @@
+#!/usr/bin/python
+# -*- coding: utf-8 -*-
+
+# Copyright (c) 2021, Aubin Bikouo <@abikouo>
+# GNU General Public License v3.0+ (see COPYING or https://www.gnu.org/licenses/gpl-3.0.txt)
+
+from __future__ import absolute_import, division, print_function
+
+__metaclass__ = type
+
+
+DOCUMENTATION = r'''
+
+module: k8s_drain
+
+short_description: Drain, Cordon, or Uncordon node in k8s cluster
+
+author: Aubin Bikouo (@abikouo)
+
+description:
+ - Drain node in preparation for maintenance same as kubectl drain.
+ - Cordon will mark the node as unschedulable.
+ - Uncordon will mark the node as schedulable.
+ - The given node will be marked unschedulable to prevent new pods from arriving.
+ - Then drain deletes all pods except mirror pods (which cannot be deleted through the API server).
+
+extends_documentation_fragment:
+ - kubernetes.core.k8s_auth_options
+
+options:
+ state:
+ description:
+ - Determines whether to drain, cordon, or uncordon node.
+ type: str
+ default: drain
+ choices: [ cordon, drain, uncordon ]
+ name:
+ description:
+ - The name of the node.
+ required: true
+ type: str
+ delete_options:
+ type: dict
+ description:
+ - Specify options to delete pods.
+ - This option has effect only when C(state) is set to I(drain).
+ suboptions:
+ terminate_grace_period:
+ description:
+ - Specify how many seconds to wait before forcefully terminating.
+ - If not specified, the default grace period for the object type will be used.
+ - The value zero indicates delete immediately.
+ required: false
+ type: int
+ force:
+ description:
+ - Continue even if there are pods not managed by a ReplicationController, Job, or DaemonSet.
+ type: bool
+ default: False
+ ignore_daemonsets:
+ description:
+ - Ignore DaemonSet-managed pods.
+ type: bool
+ default: False
+ disable_eviction:
+ description:
+ - Forces drain to use delete rather than evict.
+ type: bool
+ default: False
+ wait_timeout:
+ description:
+ - The length of time to wait in seconds for pod to be deleted before giving up, zero means infinite.
+ type: int
+ wait_sleep:
+ description:
+ - Number of seconds to sleep between checks.
+ - Ignored if C(wait_timeout) is not set.
+ default: 5
+ type: int
+
+requirements:
+ - python >= 3.6
+ - kubernetes >= 12.0.0
+'''
+
+EXAMPLES = r'''
+- name: Drain node "foo", even if there are pods not managed by a ReplicationController, Job, or DaemonSet on it.
+ kubernetes.core.k8s_drain:
+ state: drain
+ name: foo
+ force: yes
+
+- name: Drain node "foo", but abort if there are pods not managed by a ReplicationController, Job, or DaemonSet, and use a grace period of 15 minutes.
+ kubernetes.core.k8s_drain:
+ state: drain
+ name: foo
+ delete_options:
+ terminate_grace_period: 900
+
+- name: Mark node "foo" as schedulable.
+ kubernetes.core.k8s_drain:
+ state: uncordon
+ name: foo
+
+- name: Mark node "foo" as unschedulable.
+ kubernetes.core.k8s_drain:
+ state: cordon
+ name: foo
+
+'''
+
+RETURN = r'''
+result:
+ description:
+ - The node status and the number of pods deleted.
+ returned: success
+ type: str
+'''
+import copy
+from datetime import datetime
+import time
+from ansible_collections.kubernetes.core.plugins.module_utils.ansiblemodule import AnsibleModule
+from ansible_collections.kubernetes.core.plugins.module_utils.args_common import AUTH_ARG_SPEC
+from ansible.module_utils._text import to_native
+
+try:
+ from kubernetes.client.api import core_v1_api
+ from kubernetes.client.models import V1beta1Eviction, V1DeleteOptions
+ from kubernetes.client.exceptions import ApiException
+except ImportError:
+ # ImportError are managed by the common module already.
+ pass
+
+
+def filter_pods(pods, force, ignore_daemonset):
+ k8s_kind_mirror = "kubernetes.io/config.mirror"
+ daemonSet, unmanaged, mirror, localStorage, to_delete = [], [], [], [], []
+ for pod in pods:
+ # check mirror pod: cannot be delete using API Server
+ if pod.metadata.annotations and k8s_kind_mirror in pod.metadata.annotations:
+ mirror.append((pod.metadata.namespace, pod.metadata.name))
+ continue
+
+ # Any finished pod can be deleted
+ if pod.status.phase in ('Succeeded', 'Failed'):
+ to_delete.append((pod.metadata.namespace, pod.metadata.name))
+ continue
+
+ # Pod with local storage cannot be deleted
+ # TODO: support new option delete-emptydatadir in order to allow deletion of such pod
+ if pod.spec.volumes and any([vol.empty_dir for vol in pod.spec.volumes]):
+ localStorage.append((pod.metadata.namespace, pod.metadata.name))
+ continue
+
+ # Check replicated Pod
+ owner_ref = pod.metadata.owner_references
+ if not owner_ref:
+ unmanaged.append((pod.metadata.namespace, pod.metadata.name))
+ else:
+ for owner in owner_ref:
+ if owner.kind == "DaemonSet":
+ daemonSet.append((pod.metadata.namespace, pod.metadata.name))
+ else:
+ to_delete.append((pod.metadata.namespace, pod.metadata.name))
+
+ warnings, errors = [], []
+ if unmanaged:
+ pod_names = ','.join([pod[0] + "/" + pod[1] for pod in unmanaged])
+ if not force:
+ errors.append("cannot delete Pods not managed by ReplicationController, ReplicaSet, Job,"
+ " DaemonSet or StatefulSet (use option force set to yes): {0}.".format(pod_names))
+ else:
+ # Pod not managed will be deleted as 'force' is true
+ warnings.append("Deleting Pods not managed by ReplicationController, ReplicaSet, Job, DaemonSet or StatefulSet: {0}.".format(pod_names))
+ to_delete += unmanaged
+
+ # mirror pods warning
+ if mirror:
+ pod_names = ','.join([pod[0] + "/" + pod[1] for pod in mirror])
+ warnings.append("cannot delete mirror Pods using API server: {0}.".format(pod_names))
+
+ # local storage
+ if localStorage:
+ errors.append("cannot delete Pods with local storage: {0}.".format(pod_names))
+
+ # DaemonSet managed Pods
+ if daemonSet:
+ pod_names = ','.join([pod[0] + "/" + pod[1] for pod in daemonSet])
+ if not ignore_daemonset:
+ errors.append("cannot delete DaemonSet-managed Pods (use option ignore_daemonset set to yes): {0}.".format(pod_names))
+ else:
+ warnings.append("Ignoring DaemonSet-managed Pods: {0}.".format(pod_names))
+ return to_delete, warnings, errors
+
+
+class K8sDrainAnsible(object):
+
+ def __init__(self, module):
+ from ansible_collections.kubernetes.core.plugins.module_utils.common import (
+ K8sAnsibleMixin, get_api_client)
+
+ self._module = module
+ self._k8s_ansible_mixin = K8sAnsibleMixin(module)
+ self._k8s_ansible_mixin.client = get_api_client(module=self._module)
+
+ self._k8s_ansible_mixin.module = self._module
+ self._k8s_ansible_mixin.argspec = self._module.argument_spec
+ self._k8s_ansible_mixin.check_mode = self._module.check_mode
+ self._k8s_ansible_mixin.params = self._module.params
+ self._k8s_ansible_mixin.fail_json = self._module.fail_json
+ self._k8s_ansible_mixin.fail = self._module.fail_json
+ self._k8s_ansible_mixin.exit_json = self._module.exit_json
+ self._k8s_ansible_mixin.warn = self._module.warn
+ self._k8s_ansible_mixin.warnings = []
+
+ self._api_instance = core_v1_api.CoreV1Api(self._k8s_ansible_mixin.client.client)
+ self._k8s_ansible_mixin.check_library_version()
+
+ # delete options
+ self._drain_options = module.params.get('delete_options', {})
+ self._delete_options = None
+ if self._drain_options.get('terminate_grace_period'):
+ self._delete_options = {}
+ self._delete_options.update({'apiVersion': 'v1'})
+ self._delete_options.update({'kind': 'DeleteOptions'})
+ self._delete_options.update({'gracePeriodSeconds': self._drain_options.get('terminate_grace_period')})
+
+ self._changed = False
+
+ def wait_for_pod_deletion(self, pods, wait_timeout, wait_sleep):
+ start = datetime.now()
+
+ def _elapsed_time():
+ return (datetime.now() - start).seconds
+
+ response = None
+ pod = pods.pop()
+ while (_elapsed_time() < wait_timeout or wait_timeout == 0) and pods:
+ if not pod:
+ pod = pods.pop()
+ try:
+ response = self._api_instance.read_namespaced_pod(namespace=pod[0], name=pod[1])
+ if not response:
+ pod = None
+ time.sleep(wait_sleep)
+ except ApiException as exc:
+ if exc.reason != "Not Found":
+ self._module.fail_json(msg="Exception raised: {0}".format(exc.reason))
+ pod = None
+ except Exception as e:
+ self._module.fail_json(msg="Exception raised: {0}".format(to_native(e)))
+ if not pods:
+ return None
+ return "timeout reached while pods were still running."
+
+ def evict_pods(self, pods):
+ for namespace, name in pods:
+ definition = {
+ 'metadata': {
+ 'name': name,
+ 'namespace': namespace
+ }
+ }
+ if self._delete_options:
+ definition.update({'delete_options': self._delete_options})
+ try:
+ if self._drain_options.get('disable_eviction'):
+ body = V1DeleteOptions(**definition)
+ self._api_instance.delete_namespaced_pod(name=name, namespace=namespace, body=body)
+ else:
+ body = V1beta1Eviction(**definition)
+ self._api_instance.create_namespaced_pod_eviction(name=name, namespace=namespace, body=body)
+ self._changed = True
+ except ApiException as exc:
+ if exc.reason != "Not Found":
+ self._module.fail_json(msg="Failed to delete pod {0}/{1} due to: {2}".format(namespace, name, exc.reason))
+ except Exception as exc:
+ self._module.fail_json(msg="Failed to delete pod {0}/{1} due to: {2}".format(namespace, name, to_native(exc)))
+
+ def delete_or_evict_pods(self, node_unschedulable):
+ # Mark node as unschedulable
+ result = []
+ if not node_unschedulable:
+ self.patch_node(unschedulable=True)
+ result.append("node {0} marked unschedulable.".format(self._module.params.get('name')))
+ self._changed = True
+ else:
+ result.append("node {0} already marked unschedulable.".format(self._module.params.get('name')))
+
+ def _revert_node_patch():
+ if self._changed:
+ self._changed = False
+ self.patch_node(unschedulable=False)
+
+ try:
+ field_selector = "spec.nodeName={name}".format(name=self._module.params.get('name'))
+ pod_list = self._api_instance.list_pod_for_all_namespaces(field_selector=field_selector)
+ # Filter pods
+ force = self._drain_options.get('force', False)
+ ignore_daemonset = self._drain_options.get('ignore_daemonsets', False)
+ pods, warnings, errors = filter_pods(pod_list.items, force, ignore_daemonset)
+ if errors:
+ _revert_node_patch()
+ self._module.fail_json(msg="Pod deletion errors: {0}".format(" ".join(errors)))
+ except ApiException as exc:
+ if exc.reason != "Not Found":
+ _revert_node_patch()
+ self._module.fail_json(msg="Failed to list pod from node {name} due to: {reason}".format(
+ name=self._module.params.get('name'), reason=exc.reason), status=exc.status)
+ pods = []
+ except Exception as exc:
+ _revert_node_patch()
+ self._module.fail_json(msg="Failed to list pod from node {name} due to: {error}".format(
+ name=self._module.params.get('name'), error=to_native(exc)))
+
+ # Delete Pods
+ if pods:
+ self.evict_pods(pods)
+ number_pod = len(pods)
+ if self._drain_options.get('wait_timeout') is not None:
+ warn = self.wait_for_pod_deletion(pods,
+ self._drain_options.get('wait_timeout'),
+ self._drain_options.get('wait_sleep'))
+ if warn:
+ warnings.append(warn)
+ result.append("{0} Pod(s) deleted from node.".format(number_pod))
+ if warnings:
+ return dict(result=' '.join(result), warnings=warnings)
+ return dict(result=' '.join(result))
+
+ def patch_node(self, unschedulable):
+
+ body = {
+ 'spec': {'unschedulable': unschedulable}
+ }
+ try:
+ self._api_instance.patch_node(name=self._module.params.get('name'), body=body)
+ except Exception as exc:
+ self._module.fail_json(msg="Failed to patch node due to: {0}".format(to_native(exc)))
+
+ def execute_module(self):
+
+ state = self._module.params.get('state')
+ name = self._module.params.get('name')
+ try:
+ node = self._api_instance.read_node(name=name)
+ except ApiException as exc:
+ if exc.reason == "Not Found":
+ self._module.fail_json(msg="Node {0} not found.".format(name))
+ self._module.fail_json(msg="Failed to retrieve node '{0}' due to: {1}".format(name, exc.reason), status=exc.status)
+ except Exception as exc:
+ self._module.fail_json(msg="Failed to retrieve node '{0}' due to: {1}".format(name, to_native(exc)))
+
+ result = {}
+ if state == "cordon":
+ if node.spec.unschedulable:
+ self._module.exit_json(result="node {0} already marked unschedulable.".format(name))
+ self.patch_node(unschedulable=True)
+ result['result'] = "node {0} marked unschedulable.".format(name)
+ self._changed = True
+
+ elif state == "uncordon":
+ if not node.spec.unschedulable:
+ self._module.exit_json(result="node {0} already marked schedulable.".format(name))
+ self.patch_node(unschedulable=False)
+ result['result'] = "node {0} marked schedulable.".format(name)
+ self._changed = True
+
+ else:
+ # drain node
+ # Delete or Evict Pods
+ ret = self.delete_or_evict_pods(node_unschedulable=node.spec.unschedulable)
+ result.update(ret)
+
+ self._module.exit_json(changed=self._changed, **result)
+
+
+def argspec():
+ argument_spec = copy.deepcopy(AUTH_ARG_SPEC)
+ argument_spec.update(
+ dict(
+ state=dict(default="drain", choices=["cordon", "drain", "uncordon"]),
+ name=dict(required=True),
+ delete_options=dict(
+ type='dict',
+ default={},
+ options=dict(
+ terminate_grace_period=dict(type='int'),
+ force=dict(type='bool', default=False),
+ ignore_daemonsets=dict(type='bool', default=False),
+ disable_eviction=dict(type='bool', default=False),
+ wait_timeout=dict(type='int'),
+ wait_sleep=dict(type='int', default=5),
+ )
+ ),
+ )
+ )
+ return argument_spec
+
+
+def main():
+ module = AnsibleModule(argument_spec=argspec())
+
+ k8s_drain = K8sDrainAnsible(module)
+ k8s_drain.execute_module()
+
+
+if __name__ == '__main__':
+ main()
diff --git a/tox.ini b/tox.ini
index 361d0c7a..7d71a811 100644
--- a/tox.ini
+++ b/tox.ini
@@ -30,6 +30,10 @@ passenv =
commands=
ansible-test integration --docker -v --color --retry-on-error --diff --coverage --continue-on-error --python {posargs}
+[testenv:add_docs]
+deps = git+https://github.com/ansible-network/collection_prep
+commands = collection_prep_add_docs -p .
+
[testenv:linters]
deps = yamllint
flake8
|