Skip to content

Miscellaneous resilience improvements #2358

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 7 commits into
base: master
Choose a base branch
from
Draft

Miscellaneous resilience improvements #2358

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
dda17c6
Remove us-central1-c zone from ansible playbooks
Molter73 Aug 18, 2025
db576c1
Use break_when when looping zones in ansible
Molter73 Aug 18, 2025
163dc8c
Ensure VM is removed on failure
Molter73 Aug 18, 2025
b42cb48
Update Python version in integration tests
Molter73 Aug 18, 2025
5c46d2c
Revert "Update Python version in integration tests"
Molter73 Aug 18, 2025
ad194a6
Revert "Use break_when when looping zones in ansible"
Molter73 Aug 18, 2025
031a347
Remove unneeded register
Molter73 Aug 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 0 additions & 1 deletion ansible/ci/group_vars/all.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,6 @@ gcp_instance_prefix: ci
gcp_available_zones:
- us-central1-a
- us-central1-b
- us-central1-c
- us-central1-f
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
- us-central1-f
- us-central1-f
- us-central1-d

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more. 

$ gcloud compute machine-types list --filter="name=t2a-standard-2 AND zone~'^us-'" --format="value(zone)"
us-central1-a
us-central1-b
us-central1-f
us-central1-d

ansible_user: runner
gcp_network_name: collector-ci
Expand Down
1 change: 0 additions & 1 deletion ansible/dev/group_vars/all.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,7 +8,6 @@ gcp_instance_prefix: "{{ lookup('env', 'USER') }}-dev"
gcp_available_zones:
- us-central1-a
- us-central1-b
- us-central1-c
- us-central1-f
ansible_user: "{{ lookup('env', 'USER') }}"
gcp_network_name: default
Expand Down
34 changes: 34 additions & 0 deletions ansible/roles/create-vm/tasks/create-gcp-instance.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,34 @@
---
- name: Safely create GCP compute instance
block:
- name: Create compute instance
google.cloud.gcp_compute_instance:
name: "{{ vm_name }}"
project: "{{ gcp_project }}"
auth_kind: "{{ gcp_auth_kind }}"
service_account_file: "{{ gcp_service_account_file }}"
zone: "{{ gcp_zone }}"
machine_type: "{{ vm_machine_type | default('e2-standard-2') }}"
disks:
- auto_delete: true
boot: true
initialize_params:
disk_size_gb: "{{ vm_disk_size | default(20) }}"
source_image: "{{ gcp_source_image }}"
network_interfaces:
- network: "{{ network }}"
access_configs:
- name: External NAT
type: ONE_TO_ONE_NAT
labels: "{{ gcp_default_labels | combine(gcp_extra_labels) }}"
metadata: "{{ gcp_meta_data | default({}) }}"
register: instance_result
rescue:
- name: Remove failed GCP compute instance
google.cloud.gcp_compute_instance:
name: "{{ vm_name }}"
project: "{{ gcp_project }}"
auth_kind: "{{ gcp_auth_kind }}"
service_account_file: "{{ gcp_service_account_file }}"
zone: "{{ gcp_zone }}"
state: absent
24 changes: 2 additions & 22 deletions ansible/roles/create-vm/tasks/create-gcp-vm.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,26 +51,8 @@
register: network

- name: Create GCP VM
google.cloud.gcp_compute_instance:
name: "{{ vm_name }}"
project: "{{ gcp_project }}"
auth_kind: "{{ gcp_auth_kind }}"
service_account_file: "{{ gcp_service_account_file }}"
zone: "{{ gcp_zone }}"
machine_type: "{{ vm_machine_type | default('e2-standard-2') }}"
disks:
- auto_delete: true
boot: true
initialize_params:
disk_size_gb: "{{ vm_disk_size | default(20) }}"
source_image: "{{ gcp_source_image }}"
network_interfaces:
- network: "{{ network }}"
access_configs:
- name: External NAT
type: ONE_TO_ONE_NAT
labels: "{{ gcp_default_labels | combine(gcp_extra_labels) }}"
metadata: "{{ gcp_meta_data | default({}) }}"
ansible.builtin.include_tasks:
file: create-gcp-instance.yml

# This looks like a lot, and its mostly because ansible support
# for "breaking" from a loop is not all that great at the moment.
Expand All @@ -80,9 +62,7 @@
loop: "{{ vm_available_zones }}"
loop_control:
loop_var: gcp_zone
register: instance_result
when: >
(vm_arch == "amd64" or vm_arch == "arm64") and not condition and excluded == false
vars:
condition: "{{ (instance_result | default({'changed': false})).changed }}"

Loading