Update configurations

Still seeing issues with decrypting messages.

.gitea/workflows/deployLibvirt.yaml

@@ -0,0 +1,22 @@
+name: deployLibvirtGuests
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install Ansible
+        run: |
+          apt update -y
+          apt install python3-pip -y
+          python3 -m pip install ansible
+
+      - name: Run playbook
+        uses: dawidd6/action-ansible-playbook@v2
+        with:
+          playbook: libvirtGuests.yaml
+          key: ${{secrets.SSH_PRIVATE_KEY}}
+          vault_password: ${{secrets.VAULT_PASSWORD}}
+          options: |
+            --inventory inventories/eom.dev.yaml

.gitmodules

@@ -19,3 +19,6 @@
 [submodule "roles/ericomeehan.libvirt-guest"]
 	path = roles/ericomeehan.libvirt-guest
 	url = git@gitea.eom.dev:DevOps/ansible-role-libvirt-guest.git
+[submodule "roles/ericomeehan.matrix-stack"]
+	path = roles/ericomeehan.matrix-stack
+	url = git@gitea.eom.dev:DevOps/ansible-role-matrix-stack.git

host_vars/alpha-worker-0.yaml

@@ -1 +1,2 @@
 name: alpha-worker-0
+nvidia_driver_needed: true

inventories/eom.dev.yml

@@ -4,13 +4,13 @@ all:
     workstations:
       hosts:
         latitude-7230:
+        latitude-7424:
         inspiron-3670:
-        imac:
-        raspberrypi:
 
     hypervisors:
       hosts:
         poweredge-r350:
+        poweredge-r720:
         poweredge-t640:
 
     vms:

libvirtGuests.yaml

@@ -0,0 +1,10 @@
+---
+# playbook for libvirtGuests.yaml
+- name: Libvirt guests
+  hosts: poweredge-r720
+  become: true
+  roles:
+    - role: ericomeehan.libvirtguest
+      vars:
+        libvirt_networks: {}
+        libvirt_guests: {}

main.yaml

@@ -40,147 +40,15 @@
         - /data/gamma
         - /data/eric
 
-- name: Prepare virtualization environments
-  hosts: hypervisors
-  become: true
-  tasks:
-    - name: Install packages for virtualization
-      apt:
-        update_cache: yes
-        name: 
-          - bridge-utils
-          - genisoimage
-          - qemu-utils
-          - qemu-system-x86
-          - libvirt-daemon-system
-          - prometheus-libvirt-exporter
-          - python3-libvirt
-          - python3-lxml
-        state: present
-
-    - name: Enable IPv4 packet forwarding
-      lineinfile:
-        path: /etc/sysctl.conf
-        line: 'net.ipv4.ip_forward = 1'
-        state: present
-
-    - name: Enable IPv6 packet forwarding
-      lineinfile:
-        path: /etc/sysctl.conf
-        line: 'net.ipv6.conf.all.forwarding = 1'
-        state: present
-
-    - name: Copy interfaces template
-      template:
-        src: interfaces.j2
-        dest: /etc/network/interfaces
-
-    - name: Reload sysctl configuration
-      command: sysctl --system
-
-    - name: Reload network service
-      service:
-        name: networking
-        state: restarted
-
-- name: Deploy virtual machines
+- name: Setup virtualization
   hosts: hypervisors
   become: true
   vars_files:
     - ../secrets.yaml
-  tasks:
-    - name: Define libvirt networks
-      community.libvirt.virt_net:
-        name: "{{ item.name }}"
-        command: define
-        xml: "{{ lookup('template', 'libvirt-network.xml.j2') }}"
-      loop: "{{ libvirt_networks }}"
-
-    - name: Create libvirt networks
-      community.libvirt.virt_net:
-        name: "{{ item.name }}"
-        command: create
-      loop: "{{ libvirt_networks }}"
-
-    - name: Autostart libvirt networks
-      community.libvirt.virt_net:
-        name: "{{ item.name }}"
-        autostart: true
-      loop: "{{ libvirt_networks }}"
-
-    - name: Download base image
-      get_url:
-        url: https://cloud.debian.org/images/cloud/bookworm/latest/debian-12-generic-amd64.qcow2
-        dest: /var/lib/libvirt/images/debian-12-generic-amd64.qcow2
-        force: true
-
-    - name: Copy base image
-      copy:
-        src: /var/lib/libvirt/images/debian-12-generic-amd64.qcow2
-        remote_src: true
-        dest: "/var/lib/libvirt/images/{{ item }}.qcow2"
-        force: true
-      loop: "{{ libvirt_guests }}"
-
-    - name: Resize images
-      command: "qemu-img resize -f qcow2 /var/lib/libvirt/images/{{ item }}.qcow2 16G"
-      loop: "{{ libvirt_guests }}"
-
-    - name: Create cloud-config directory
-      file:
-        path: "/tmp/{{ item }}"
-        state: directory
-      loop: "{{ libvirt_guests }}"
-
-    - name: Copy cloud-config user-data template
-      template:
-        src: user-data.j2
-        dest: "/tmp/{{ domain.name }}/user-data"
-        force: true
-      loop: "{{ libvirt_guests }}"
+  roles:
+    - role: ericomeehan.libvirt_guests
       vars:
-        domain: "{{ hostvars[item] }}"
-
-    - name: Copy cloud-config meta-data template
-      template:
-        src: meta-data.j2
-        dest: "/tmp/{{ domain.name }}/meta-data"
-        force: true
-      loop: "{{ libvirt_guests }}"
-      vars:
-        domain: "{{ hostvars[item] }}"
-
-    - name: Generate iso
-      command: "genisoimage -output /var/lib/libvirt/images/{{ item }}.iso -volid cidata -joliet -rock /tmp/{{ item }}/user-data /tmp/{{ item }}/meta-data"
-      loop: "{{ libvirt_guests }}"
-
-    - name: Define libvirt virtual machine
-      community.libvirt.virt:
-        command: define
-        xml: "{{ lookup('template', 'libvirt-vm.xml.j2') }}"
-      loop: "{{ libvirt_guests }}"
-      vars:
-        domain: "{{ hostvars[item] }}"
-
-    - name: Create libvirt virtual machine
-      community.libvirt.virt:
-        name: "{{ item }}"
-        command: create
-      loop: "{{ libvirt_guests }}"
-
-    - name: Autostart libvirt virtual machines
-      community.libvirt.virt:
-        name: "{{ item }}"
-        autostart: true
-      loop: "{{ libvirt_guests }}"
-
-    - name: Wait for guest initialization
-      wait_for:
-        timeout: 300
-
-    - name: Reset libvirt virtual machines for filesystem resize
-      command: "virsh reset {{ item }}"
-      loop: "{{ libvirt_guests }}"
+        doSetup: true
 
 - name: Wait for manual tasks 
   hosts: localhost
@@ -196,6 +64,8 @@
     - ../secrets.yaml
   roles:
     - role: ericomeehan.ericomeehan
+    - role: ericomeehan.nvidia_driver
+      when: nvidia_driver_needed == true
 
 - name: Initialize Kubernetes clusters
   hosts: clusters
@@ -285,6 +155,11 @@
         name: bitnami
         repo_url: https://charts.bitnami.com/bitnami
 
+    - name: Add nvidia repository
+      kubernetes.core.helm_repository:
+        name: nvidia
+        repo_url: https://helm.ngc.nvidia.com/nvidia
+
     - name: Update Helm repos
       command: helm repo update
 
@@ -393,6 +268,18 @@
                     ingress:
                       ingressClassName: nginx
 
+    - name: Deploy nvidia gpu operator
+      kubernetes.core.helm:
+        name: gpu-operator
+        chart_ref: nvidia/gpu-operator
+        release_namespace: gpu-operator
+        create_namespace: true
+        values:
+          driver:
+            enabled: false
+          toolkit:
+            enabled: false
+
 - name: Port forward HTTP(S) to Ingress Controllers
   hosts: localhost
   tasks:

nvidia-device-plugin.yaml

@@ -0,0 +1,23 @@
+- name: Deploy nvdp
+  hosts: control_planes
+  become: true
+  tasks:
+    - name: Add nvdp repository
+      kubernetes.core.helm_repository:
+        name: nvidia
+        repo_url: https://helm.ngc.nvidia.com/nvidia
+
+    - name: Update Helm repos
+      command: helm repo update
+
+    - name: Deploy nvidia gpu operator
+      kubernetes.core.helm:
+        name: gpu-operator
+        chart_ref: nvidia/gpu-operator
+        release_namespace: gpu-operator
+        create_namespace: true
+        values:
+          driver:
+            enabled: false
+          toolkit:
+            enabled: false

roles/ericomeehan.eom

@@ -1 +1 @@
-Subproject commit 81b3f7827715a1433bb74ea4e53e60eec69ec9ac
+Subproject commit 148f933eb51b158e673dd41e21c631c925ab3899

roles/ericomeehan.ericomeehan

@@ -1 +1 @@
-Subproject commit 4dc7f7917edb012b15268a4e94c81b55592130a5
+Subproject commit 969a46feb589453ec8b1a4fc803cdf6bb3ffd77d

roles/ericomeehan.gondwana

@@ -1 +1 @@
-Subproject commit d5681a95e437b86347c624abb6bb74c427444698
+Subproject commit db0d438c699f33b2d143fd2fdfc3c314958932d5

roles/ericomeehan.kraken-bot

@@ -1 +1 @@
-Subproject commit 45c0352dde33deab8c7a1a62f0d289014c617154
+Subproject commit 439661f40be5d5cb2ab167c44602a2792d450727

roles/ericomeehan.matrix-stack

@@ -0,0 +1 @@
+Subproject commit eed66cd1834e81e7eb7c341f4f06d0354ce00f82

roles/ericomeehan.nvidia_driver

@@ -1 +1 @@
-Subproject commit 7a3c04febc0ab5d6370da362ab80d862bfc3dd39
+Subproject commit 4b9534a27ef2c7a096f58959d9762647f524b96d

test.yaml

@@ -4,4 +4,6 @@
   vars_files:
     - ../secrets.yaml
   roles:
-    - role: ericomeehan.eom
+    - role: ericomeehan.matrix-stack
+      vars:
+        server_name: eom.dev