Skip to content

Updates to OpenHPC role and source image #324

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.

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

Merged
merged 7 commits into from
Oct 27, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
10 changes: 0 additions & 10 deletions ansible/bootstrap.yml
Original file line number Diff line number Diff line change
Expand Up @@ -112,16 +112,6 @@
tasks_from: config.yml
tags: config

- name: Setup EESSI
hosts: eessi
tags: eessi
become: true
gather_facts: false
tasks:
- name: Install and configure EESSI
import_role:
name: eessi

- hosts: update
gather_facts: false
become: yes
Expand Down
13 changes: 12 additions & 1 deletion ansible/extras.yml
Original file line number Diff line number Diff line change
@@ -1,4 +1,15 @@
- hosts: cuda
- name: Setup EESSI
hosts: eessi
tags: eessi
become: true
gather_facts: false
tasks:
- name: Install and configure EESSI
import_role:
name: eessi

- name: Setup CUDA
hosts: cuda
become: yes
gather_facts: no
tags: cuda
Expand Down
2 changes: 1 addition & 1 deletion environments/.stackhpc/ARCUS.pkrvars.hcl
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ volume_size = 10 # GB
image_disk_format = "qcow2"
networks = ["4b6b2722-ee5b-40ec-8e52-a6610e14cc51"] # portal-internal (DNS broken on ilab-60)
source_image_name = "openhpc-230804-1754-80b8d714" # https://github.com/stackhpc/ansible-slurm-appliance/pull/298
fatimage_source_image_name = "Rocky-8-GenericCloud-8.6.20220702.0.x86_64.qcow2"
fatimage_source_image_name = "Rocky-8-GenericCloud-Base-8.8-20230518.0.x86_64.qcow2"
ssh_keypair_name = "slurm-app-ci"
ssh_private_key_file = "~/.ssh/id_rsa"
security_groups = ["default", "SSH"]
Expand Down
2 changes: 1 addition & 1 deletion environments/.stackhpc/SMS.pkrvars.hcl
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
flavor = "general.v1.tiny"
networks = ["26023e3d-bc8e-459c-8def-dbd47ab01756"] # stackhpc-ipv4-geneve
source_image_name = "openhpc-230503-0944-bf8c3f63" # https://github.com/stackhpc/ansible-slurm-appliance/pull/252
fatimage_source_image_name = "Rocky-8-GenericCloud-8.6.20220702.0.x86_64.qcow2"
fatimage_source_image_name = "Rocky-8-GenericCloud-Base-8.8-20230518.0.x86_64.qcow2"
ssh_keypair_name = "slurm-app-ci"
ssh_private_key_file = "~/.ssh/id_rsa"
security_groups = ["default", "SSH"]
Expand Down
16 changes: 16 additions & 0 deletions environments/.stackhpc/hooks/post-bootstrap.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
- hosts: podman:!builder
become: yes
gather_facts: false
tags: podman
tasks:
- name: Configure container image registry for unqualified searches to avoid docker.io ratelimits
copy:
dest: /etc/containers/registries.conf.d/003-arcus-unqualfied-overrides.conf
content: |
unqualified-search-registries = ['{{ podman_registry_address | split('/') | first }}', 'registry.access.redhat.com', 'registry.redhat.io', 'docker.io']

[[registry]]
prefix = "{{ podman_registry_address }}"
location = "{{ podman_registry_address }}"
insecure = true
when: "ci_cloud == 'ARCUS'"
8 changes: 0 additions & 8 deletions environments/.stackhpc/hooks/post.yml

This file was deleted.

17 changes: 0 additions & 17 deletions environments/.stackhpc/hooks/pre.yml
Original file line number Diff line number Diff line change
Expand Up @@ -15,20 +15,3 @@
- "{{ lookup('env', 'APPLIANCES_ENVIRONMENT_ROOT') }}/inventory/hosts"
- "{{ lookup('env', 'APPLIANCES_ENVIRONMENT_ROOT') }}/inventory/group_vars/all/secrets.yml"
- "{{ lookup('env', 'APPLIANCES_ENVIRONMENT_ROOT') }}/inventory/group_vars/all/test_user.yml"

- hosts: all:!builder
become: yes
gather_facts: false
tags: podman
tasks:
- name: Configure container image registry for unqualified searches to avoid docker.io ratelimits
copy:
dest: /etc/containers/registries.conf.d/003-arcus-unqualfied-overrides.conf
content: |
unqualified-search-registries = ['{{ podman_registry_address | split('/') | first }}', 'registry.access.redhat.com', 'registry.redhat.io', 'docker.io']

[[registry]]
prefix = "{{ podman_registry_address }}"
location = "{{ podman_registry_address }}"
insecure = true
when: "ci_cloud == 'ARCUS'"
5 changes: 2 additions & 3 deletions environments/.stackhpc/terraform/main.tf
Original file line number Diff line number Diff line change
Expand Up @@ -13,9 +13,8 @@ variable "cluster_name" {
variable "cluster_image" {
description = "single image for all cluster nodes - a convenience for CI"
type = string
default = "openhpc-231020-1357-b5d8b056" # https://github.com/stackhpc/ansible-slurm-appliance/pull/320
# default = "Rocky-8-GenericCloud-Base-8.7-20221130.0.x86_64.qcow2"
# default = "Rocky-8-GenericCloud-8.6.20220702.0.x86_64.qcow2"
default = "openhpc-231027-0916-893570de" # https://github.com/stackhpc/ansible-slurm-appliance/pull/324
# default = "Rocky-8-GenericCloud-Base-8.8-20230518.0.x86_64.qcow2"
}

variable "cluster_net" {}
Expand Down
2 changes: 1 addition & 1 deletion requirements.yml
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ roles:
- src: stackhpc.nfs
version: v22.9.1
- src: https://github.com/stackhpc/ansible-role-openhpc.git
version: v0.20.0 # Allow multiple empty partitions by @sjpb in #156
version: v0.23.0 # https://github.com/stackhpc/ansible-role-openhpc/pull/165
name: stackhpc.openhpc
- src: https://github.com/stackhpc/ansible-node-exporter.git
version: feature/no-install
Expand Down