starlingx/ansible-playbooks
Code Issues Proposed changes

Ansible update to support remote subcloud restore

Browse Source 
In this commit:
  - Common code to validate target is updated to include additional
    host check options (system readiness, load version, bootstrap ip,
    and patches).
  - A new playbook is added to perform host check for various
    use cases (remote install, pre subcloud restore, pre subcloud
    upgrade, etc...).
  - Install playbook is updated to make use of the new playbook.
  - A new role which performs generic user input validation for all
    restore playbooks is added.
  - A new B&R parameter is added to indicate where the backup data
    can be found, on the host itself (on-box) or on another
    machine (off-box).
  - Platform, user images and openstack restore playbooks are
    updated to a) make use of the on_box_data parameter,
    b) use the same target_backup_dir for both local and remote
    playbook execution for consistent behavior.
  - Host override file is extracted only on the target.
  - Patches restore is skipped if requested by the caller. Default
    behavior is to restore patches.
  - Various subtle bugs are fixed.
  - Ansible version is specified in Zuul test requirements.

Tests:
  - Deployment of a Redfish capable subcloud
  - Remote restore a simplex with various options: a) without patches
    b) skip patches restore, c) with patches restore, d) on-box backup
    tarball, e) off-box backup tarball
  - Local restore of a simplex with 2 options: a) without patches and
    b) skip patches restore
  - Simplex fresh install
  - Restore user images
  - Restore OpenStack
  - Error cases

Task: 41725
Story: 2008573
Change-Id: Ica2b9010a73854a01216e2e16b581484d182264e
Signed-off-by: Tee Ngo <tee.ngo@windriver.com>
This commit is contained in:
Tee Ngo
2021-02-09 23:08:32 -05:00
parent aec355e9b1
commit 9c62c83536
15 changed files with 376 additions and 155 deletions
Download Patch File Download Diff File Expand all files Collapse all files

190
playbookconfig/src/playbooks/roles/restore-platform/prepare-env/tasks/main.yml
View File

@@ -1,26 +1,34 @@
---
#
# Copyright (c) 2019 Wind River Systems, Inc.
# Copyright (c) 2019-2021 Wind River Systems, Inc.
#
# SPDX-License-Identifier: Apache-2.0
#
# ROLE DESCRIPTION:
# This role performs following tasks:
# 1. Retrieve the override file from the backup tarball
# required for the controller bootstrap.
# 2. Verify if platform restore should proceed
# This role performs the following tasks:
# 1. Validate user input.
# 2. Verify that the target is in the right state for platform restore.
# 3. Transfer the backup tarball to the target if it is off-box, otherwise
# copy it to the designated staging directory (/scratch).
# 4. Extract the host override file from the tarball and load bootstrap
# parameters in memory.
# 5. Create restore_in_progress flag.
#
# Note that due to Ansible mishandling of boolean values via extra-vars we are
# adding supplementary validation here
# See: https://github.com/ansible/ansible/issues/17193
- name: Check for Ceph data wipe flag
fail:
msg: "wipe_ceph_osds is misconfigured. Valid value is either 'true' or 'false'"
when: (not wipe_ceph_osds | type_debug == 'bool') and
(wipe_ceph_osds != 'true') and
(wipe_ceph_osds != 'false')
- name: Perform generic user input validation for restore
import_role:
name: backup-restore/validate-input
- block:
- name: Fail if backup_filename is not defined or set
fail:
msg: "Mandatory configuration parameter backup_filename is not defined or set."
when: backup_filename is not defined or backup_filename is none
- name: Fail if initial_backup_dir is not defined or set
fail:
msg: "Mandatory configuration parameter initial_backup_dir is not defined or set."
when: initial_backup_dir is not defined or initial_backup_dir is none
- name: Look for override backup file in the backup tarball
shell: "tar -tf {{ initial_backup_dir }}/{{ backup_filename }} | grep '_override_backup.yml'"
args:
@@ -28,57 +36,13 @@
failed_when: false
register: search_result
# Note that due to Ansible mishandling of boolean values via extra-vars we are
# adding supplementary validation here.
# See: https://github.com/ansible/ansible/issues/17193
- name: Check for Ceph data wipe flag
fail:
msg: "wipe_ceph_osds is misconfigured. Valid value is either 'true' or 'false'"
when: (not wipe_ceph_osds | type_debug == 'bool') and
(wipe_ceph_osds != 'true') and
(wipe_ceph_osds != 'false')
- block:
- name: Extract override file from backup tarball
shell: >-
tar -C {{ override_files_dir }} -xf {{ initial_backup_dir }}/{{ backup_filename }} --transform='s,.*/,,'
{{ search_result.stdout_lines[0] }}
args:
warn: false
- name: Prepare to rename override file
set_fact:
override_filename: restore_platform_overrides.yml
- name: Rename override file for bootstrap
command: >-
mv -f {{ override_files_dir }}/{{ (search_result.stdout_lines[0] | basename) }}
{{ override_files_dir }}/{{ override_filename }}
- name: Include override data
include_vars: "{{ override_files_dir }}/{{ override_filename }}"
when: search_result.rc == 0
- name: Fail if override file is missing
fail:
msg: >-
msg: >
Cannot find {{ initial_backup_dir }}/{{ backup_filename }}
or the override file is missing in the backup tarball!
when: search_result.rc != 0
delegate_to: localhost
- name: Set archive parameters for bootstrap
set_fact:
archive_puppet_permdir: "opt/platform/puppet/{{ software_version }}/hieradata"
archive_ssh_config_permdir: "opt/platform/config/{{ software_version }}/ssh_config"
archive_config_permdir: "opt/platform/config/{{ software_version }}"
archive_keyring_permdir: "opt/platform/.keyring/{{ software_version }}/python_keyring"
archive_branding_permdir: "opt/platform/config/{{ software_version }}/branding"
archive_banner_permdir: "opt/platform/config/{{ software_version }}/banner/etc"
archive_deploy_permdir: "opt/platform/deploy/{{ software_version }}"
archive_helm_permdir: "opt/platform/helm/{{ software_version }}"
delegate_to: "{{ inspection_target }}"
- block:
# Bail if the host has been unlocked
@@ -102,24 +66,104 @@
msg: " Restore is already in progress!"
when: restore_in_progress.stat.exists
- name: Create {{ restore_in_progress_flag }} flag file
file:
path: "{{ restore_in_progress_flag }}"
state: touch
- name: For remote play set target_backup_dir to /scratch
# Set the restore staging directory to scratch so it's a consistent
# behavior regardless of where the restore playbook is executed (locally vs remotely)
- name: Set restore staging directory to /scratch
set_fact:
target_backup_dir: /scratch
when: inventory_hostname != "localhost"
- name: For local play set target_backup_dir to initial_backup_dir
set_fact:
target_backup_dir: "{{ initial_backup_dir }}"
when: inventory_hostname == "localhost"
- name: Set restore file parameter
set_fact:
restore_data_file: "{{ target_backup_dir }}/{{ backup_filename }}"
- name: Transfer backup tarball to target if the file is off-box
include_role:
name: backup-restore/transfer-file
when: on_box_data|bool == false
- name: Copy the backup tarball to {{ target_backup_dir }} if the file is already on-box
copy:
src: "{{ initial_backup_dir }}/{{ backup_filename }}"
dest: "{{ target_backup_dir }}"
remote_src: yes
when: on_box_data|bool == true
- name: Extract override file from backup tarball
command: >
tar -C {{ target_backup_dir }} -xf {{ target_backup_dir }}/{{ backup_filename }} --transform='s,.*/,,'
{{ search_result.stdout_lines[0] }}
register: extract_result
failed_when: false
args:
warn: false
- name: Fail if host override file cannot be extracted from the backup tar file
fail:
msg: >
Failed to extract the host override file {{ search_result.stdout_lines[0] }}.
If the backup tar file is not on the host that is being restored, please either
transfer the tar file to the target or set on_box_data parameter to false and
try again.
when: extract_result.rc != 0
- name: Prepare to rename override file
set_fact:
override_filename: restore_platform_overrides.yml
- name: Rename override file for bootstrap
command: >
mv -f {{ target_backup_dir }}/{{ (search_result.stdout_lines[0] | basename) }}
{{ target_backup_dir }}/{{ override_filename }}
- name: Load override data (local execution)
include_vars: "{{ target_backup_dir }}/{{ override_filename }}"
when: inventory_hostname == "localhost"
- block:
- name: Create a temporary file
tempfile:
state: file
register: host_override_tmp_file
- name: Fetch override file to temp file to Ansible control host
fetch:
src: "{{ target_backup_dir }}/{{ override_filename }}"
dest: "{{ host_override_tmp_file.path }}"
flat: yes
- name: Load override data (remote execution)
include_vars: "{{ host_override_tmp_file.path }}"
- name: Remove override temp file on target
file:
path: "{{ host_override_tmp_file.path }}"
state: absent
delegate_to: "{{ inventory_hostname }}"
- name: Remove override temp file on Ansible control host
file:
path: "{{ host_override_tmp_file.path }}"
state: absent
delegate_to: localhost
# In case the ansible user does not have sudo privilege on Ansible control machine
become: no
when: inventory_hostname != "localhost"
- name: Create {{ restore_in_progress_flag }} flag file
file:
path: "{{ restore_in_progress_flag }}"
state: touch
become: yes
become_user: root
- name: Set archive parameters for bootstrap
set_fact:
archive_puppet_permdir: "opt/platform/puppet/{{ software_version }}/hieradata"
archive_ssh_config_permdir: "opt/platform/config/{{ software_version }}/ssh_config"
archive_config_permdir: "opt/platform/config/{{ software_version }}"
archive_keyring_permdir: "opt/platform/.keyring/{{ software_version }}/python_keyring"
archive_branding_permdir: "opt/platform/config/{{ software_version }}/branding"
archive_banner_permdir: "opt/platform/config/{{ software_version }}/banner/etc"
archive_deploy_permdir: "opt/platform/deploy/{{ software_version }}"
archive_helm_permdir: "opt/platform/helm/{{ software_version }}"