Mohammed Naser | ab3d88b | 2023-04-09 17:27:05 -0400 | [diff] [blame] | 1 | # Copyright (c) 2023 VEXXHOST, Inc. |
| 2 | # |
| 3 | # Licensed under the Apache License, Version 2.0 (the "License"); you may |
| 4 | # not use this file except in compliance with the License. You may obtain |
| 5 | # a copy of the License at |
| 6 | # |
| 7 | # http://www.apache.org/licenses/LICENSE-2.0 |
| 8 | # |
| 9 | # Unless required by applicable law or agreed to in writing, software |
| 10 | # distributed under the License is distributed on an "AS IS" BASIS, WITHOUT |
| 11 | # WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the |
| 12 | # License for the specific language governing permissions and limitations |
| 13 | # under the License. |
| 14 | |
| 15 | - name: Install package for "community.general.pids" |
| 16 | ansible.builtin.package: |
| 17 | name: python3-psutil |
| 18 | |
| 19 | # NOTE(mnaser): These are all processes that we do not currently have a way to |
| 20 | # safely evacuate *yet*. We should remove these as we add ways |
| 21 | # to evacuate them. |
| 22 | - name: Get process IDs for critical services |
| 23 | community.general.pids: |
| 24 | pattern: "{{ item }}" |
| 25 | loop: |
| 26 | - ceph-mgr |
| 27 | - ceph-mon |
| 28 | - ceph-osd |
| 29 | - mysqld |
| 30 | - neutron-l3-agent |
| 31 | - qemu |
| 32 | - rabbitmq-server |
| 33 | - radosgw |
| 34 | register: _reboots_pids |
| 35 | |
| 36 | - name: Assert that none of these processes are running |
| 37 | ansible.builtin.assert: |
| 38 | quiet: true |
| 39 | that: |
| 40 | - item.pids | length == 0 |
| 41 | fail_msg: >- |
| 42 | The following processes are running: {{ item.item }} ({{ item.pids | join(', ') }}) |
| 43 | loop: "{{ _reboots_pids.results }}" |
| 44 | loop_control: |
| 45 | label: "{{ item.item }}" |
| 46 | |
| 47 | - name: Create a silence and reboot the host |
| 48 | block: |
| 49 | # TODO(mnaser): Create a silence inside AlertManager |
| 50 | - name: Reboot the host |
| 51 | ansible.builtin.reboot: |
| 52 | always: [] |
| 53 | # TODO(mnaser): Remove the silence from AlertManager |