Merge remote-tracking branch 'origin/main' into ci/enable-linting

Author: maxstack

ansible/fatimage.yml

@@ -265,8 +265,8 @@
         name: grafana-dashboards
 
 - name: Add support for NVIDIA GPU auto detection to Slurm
-  hosts: cuda
-  become: true
+  hosts: slurm_recompile
+  become: yes
   tasks:
     - name: Recompile slurm
       ansible.builtin.import_role:

ansible/roles/dnf_repos/defaults/main.yml

@@ -48,7 +48,8 @@ dnf_repos_openhpc_repolist:
     file: OpenHPC
     base_url: "{{ dnf_repos_pulp_content_url }}/{{ appliances_pulp_repos.openhpc_updates[ansible_distribution_major_version] | appliances_repo_to_subpath }}"
 
-dnf_repos_repolist: "{{ dnf_repos_default_repolist + (dnf_repos_openhpc_repolist if (openhpc_install_type | default('ohpc')) == 'ohpc' else []) }}"
+dnf_repos_extra_repolist: []
+dnf_repos_repolist: "{{ dnf_repos_default_repolist + (dnf_repos_openhpc_repolist if (openhpc_install_type | default('ohpc')) == 'ohpc' else []) + dnf_repos_extra_repolist }}"
 
 dnf_repos_epel_baseurl: "{{ dnf_repos_pulp_content_url }}/{{ appliances_pulp_repos.epel[ansible_distribution_major_version] | appliances_repo_to_subpath }}"
 dnf_repos_epel_description: "epel"

ansible/roles/proxy/defaults/main.yml

@@ -1,7 +1,7 @@
 ---
 # proxy_http_proxy:
 proxy_https_proxy: "{{ proxy_http_proxy }}"
-proxy_no_proxy_defaults: "{{ ['localhost', '127.0.0.1'] + groups['all'] + hostvars.values() | map(attribute='ansible_host') }}"
+proxy_no_proxy_defaults: "{{ ['localhost', '127.0.0.1', '169.254.169.254'] + groups['all'] + hostvars.values() | map(attribute='ansible_host') }}"
 proxy_no_proxy_extras: []
 proxy_no_proxy: "{{ (proxy_no_proxy_defaults + proxy_no_proxy_extras) | unique | sort | join(',') }}"
 proxy_dnf: true

environments/common/inventory/groups

@@ -118,6 +118,9 @@ freeipa_client
 [cuda]
 # Hosts to install NVIDIA CUDA on - see ansible/roles/cuda/README.md
 
+[slurm_recompile]
+# Hosts to recompile Slurm for - allows supporting Slurm autodetection method 'nvml'
+
 [vgpu]
 # Hosts where vGPU/MIG should be configured - see docs/mig.md
 

environments/common/layouts/everything

@@ -65,6 +65,10 @@ cluster
 [cuda]
 # Hosts to install NVIDIA CUDA on - see ansible/roles/cuda/README.md
 
+[slurm_recompile:children]
+# Hosts to recompile Slurm for - allows supporting Slurm autodetection method 'nvml'
+cuda
+
 [eessi:children]
 # Hosts on which EESSI stack should be configured
 openhpc