Cloud VM (#7)

- Nextcloud & potentially other "cloud" stuff VM

Reviewed-on: #7

.github/workflows/infra.yaml

@@ -4,7 +4,7 @@ on:
     branches:
       - main
     paths:
-      - infra/**-playbook.yaml
+      - infra/**playbook.yaml
       - .github/workflows/infra.yaml
   push:
     branches:
@@ -23,20 +23,17 @@ jobs:
         with:
           fetch-depth: ${{ env.DEPLOY == 'some' && 2 || 1 }}
 
-      - name: Setup Python
-        uses: actions/setup-python@v4
-        with:
-          python-version: "3.11"
-
       - name: Install dependencies
         run: |
+          apt update
+          apt install -y python3-pip
           pip3 install -r requirements.txt
           ansible-galaxy collection install community.general
 
       - name: Check playbooks
         run: |
-          for file in $(find . -wholename "*/infra/*-playbook.yaml" -type f); do
+          for file in $(find . -wholename "*/infra/*playbook.yaml" -type f); do
-            ansible-playbook --inventory ./inventory --check "$file"
+            ansible-playbook --inventory ./inventory --syntax-check "$file"
           done
 
       - name: Get changed playbooks
@@ -44,7 +41,7 @@ jobs:
         if: env.DEPLOY == 'some'
         uses: tj-actions/changed-files@v38
         with:
-          files: infra/**/*-playbook.yaml
+          files: infra/**/*playbook.yaml
 
       - name: Get playbooks
         id: playbooks
@@ -53,12 +50,19 @@ jobs:
           if [[ "${{ env.DEPLOY }}" == "some" ]]; then
             export TO_RUN="${{ steps.files.outputs.all_changed_files }}"
           else
-            export TO_RUN="$(find . -wholename './infra/*-playbook.yaml' -type f)"
+            export TO_RUN="$(find . -wholename './infra/*playbook.yaml' -type f)"
           fi
           export TO_RUN="$( echo -n $TO_RUN | tr ' ' '\n' | sort | tr '\n' ' ' )" # run things in order :)
           echo "will run playbooks: $TO_RUN"
           echo "to_run=$TO_RUN" >> "$GITHUB_OUTPUT"
 
+      - name: Setup environment
+        if: env.DEPLOY != 'none' && steps.playbooks.outputs.to_run != ''
+        run: |
+          mkdir -p -m 700 ~/.ssh
+          echo "${{ secrets.SSH_PRIVATE }}" > ~/.ssh/id_rsa
+          chmod 600 ~/.ssh/id_rsa
+
       - name: Run playbooks
         if: env.DEPLOY != 'none' && steps.playbooks.outputs.to_run != ''
         env:
@@ -66,4 +70,5 @@ jobs:
           PROXMOX_USER: ${{ secrets.PROXMOX_USER }}
           PROXMOX_TOKEN_ID: ${{ secrets.PROXMOX_TOKEN_ID }}
           PROXMOX_TOKEN_SECRET: ${{ secrets.PROXMOX_TOKEN_SECRET }}
-        run: ansible-playbook --inventory ./inventory ${{ steps.playbooks.outputs.to_run }}
+          SSH_PUBLIC: ${{ secrets.SSH_PUBLIC }}
+        run: ansible-playbook --inventory ./inventory ${{ steps.playbooks.outputs.to_run }} -vv

README.md

@@ -7,4 +7,4 @@ This repository contains any automations used in deploying *.koval.net services.
 All 'managed' infrastructure is deployed and provisioned with [Ansible](https://www.ansible.com/).
 However, some 'unmanaged' (manually managed) resources also exist - primarily everything required for this repository to work (I don't want to make a dependency loop).
 
-Ansible playbooks are ran in alphanumerical order and are expected idempotent.
+Ansible playbooks are ran in alphanumerical order and are expected to be idempotent.

infra/cloud/0000_proxmox_playbook.yaml

@@ -0,0 +1,110 @@
+- name: Provision cloud Proxmox VM
+  hosts: cloud
+  connection: ansible.builtin.local
+  gather_facts: false
+  vars:
+    api_user: "{{ lookup('ansible.builtin.env', 'PROXMOX_USER') }}"
+    api_host: "{{ lookup('ansible.builtin.env', 'PROXMOX_HOST' ) }}"
+    api_token_id: "{{ lookup('ansible.builtin.env', 'PROXMOX_TOKEN_ID') }}"
+    api_token_secret: "{{ lookup('ansible.builtin.env', 'PROXMOX_TOKEN_SECRET') }}"
+    ssh_public: "{{ lookup('ansible.builtin.env', 'SSH_PUBLIC') }}"
+    vmname: "{{ inventory_hostname | regex_replace('^([^\\.]+)\\..+$', '\\1') }}"
+    node: pve
+  module_defaults:
+    community.general.proxmox_kvm:
+      api_user: "{{ api_user }}"
+      api_host: "{{ api_host }}"
+      api_token_id: "{{ api_token_id }}"
+      api_token_secret: "{{ api_token_secret }}"
+      name: "{{ vmname }}"
+      node: "{{ node }}"
+    community.general.proxmox_nic:
+      api_user: "{{ api_user }}"
+      api_host: "{{ api_host }}"
+      api_token_id: "{{ api_token_id }}"
+      api_token_secret: "{{ api_token_secret }}"
+      name: "{{ vmname }}"
+    community.general.proxmox_disk:
+      api_user: "{{ api_user }}"
+      api_host: "{{ api_host }}"
+      api_token_id: "{{ api_token_id }}"
+      api_token_secret: "{{ api_token_secret }}"
+      name: "{{ vmname }}"
+  tasks:
+    # Initial setup
+    - name: Create VM
+      community.general.proxmox_kvm:
+        clone: "{{ node }}-debian-12"
+        storage: nvme
+      register: create
+    - name: Wait for status
+      community.general.proxmox_kvm:
+        state: current
+      register: vm
+      retries: 30
+      delay: 10
+      until: vm.status is defined
+
+    # Networking and initial config
+    - name: Add PUB NIC
+      community.general.proxmox_nic:
+        interface: net0
+        firewall: false
+        bridge: PUB
+    - name: Add SRV NIC
+      community.general.proxmox_nic:
+        interface: net1
+        firewall: false
+        bridge: SRV
+    - name: Configure cloud-init
+      community.general.proxmox_kvm:
+        update: true
+        ciuser: debian
+        sshkeys: "{{ ssh_public }}"
+        ipconfig:
+          ipconfig0: ip=dhcp,ip6=auto
+          ipconfig1: ip=dhcp
+
+    # Initial boot
+    # For some reason debian cloud images don't use
+    # cloud-init for networking on first boot (cloud-init files
+    # are regenerated AFTER networking starts). But we need the
+    # hostname to be registered with DHCP later on so ¯\_(ツ)_/¯
+    - name: Initial boot
+      when: create.changed is true
+      block:
+        - name: Start
+          community.general.proxmox_kvm:
+            state: started
+          register: start
+        - name: Wait 1.5 min # Initial apt update, apt upgrade, cloud-init
+          ansible.builtin.wait_for:
+            timeout: 90
+
+    # VM Configuration
+    - name: Resize root disk
+      community.general.proxmox_disk:
+        disk: scsi0
+        size: 16G
+        state: resized
+    - name: Create data disk
+      community.general.proxmox_disk:
+        disk: scsi1
+        backup: true
+        storage: nvme
+        size: 2048
+    - name: Update VM
+      community.general.proxmox_kvm:
+        update: true
+        agent: enabled=1
+        tags:
+          - debian-12
+          - managed
+        onboot: true
+        cores: 16
+        memory: 32768
+
+    - name: Retart VM
+      community.general.proxmox_kvm:
+        state: restarted
+        timeout: 60

infra/cloud/0001_initialise_playbook.yaml

@@ -0,0 +1,48 @@
+- name: Initialise VM
+  hosts: cloud
+  gather_facts: false
+  tasks:
+    - name: Wait for connection
+      ansible.builtin.wait_for_connection:
+        timeout: 300
+    - name: Install system packages
+      ansible.builtin.apt:
+        update_cache: true
+        pkg:
+          - qemu-guest-agent
+          - parted
+      become: true
+    - name: Enable qemu-guest-agent
+      ansible.builtin.systemd:
+        name: qemu-guest-agent
+        state: started
+        enabled: true
+      become: true
+
+    - name: Create data partition
+      community.general.parted:
+        device: /dev/disk/by-path/pci-0000:00:05.0-scsi-0:0:0:1
+        label: gpt
+        name: data
+        number: 1
+        state: present
+      become: true
+    - name: Create data filesystem
+      community.general.filesystem:
+        dev: /dev/disk/by-path/pci-0000:00:05.0-scsi-0:0:0:1-part1
+        fstype: ext4
+      become: true
+    - name: Mount data partition
+      ansible.posix.mount:
+        src: /dev/disk/by-path/pci-0000:00:05.0-scsi-0:0:0:1-part1
+        path: /mnt/data
+        fstype: ext4
+        opts: rw,errors=remount-ro,x-systemd.growfs
+        state: mounted
+      become: true
+    - name: Set data partition permissions
+      ansible.builtin.file:
+        path: /mnt/data
+        owner: debian
+        group: debian
+      become: true

infra/cloud/0002_docker_playbook.yaml

@@ -0,0 +1,47 @@
+- name: Install software
+  hosts: cloud
+  gather_facts: false
+  tasks:
+    - name: Wait for connection
+      ansible.builtin.wait_for_connection:
+        timeout: 300
+    - name: Install dependencies
+      ansible.builtin.apt:
+        update_cache: true
+        pkg:
+          - curl
+          - python3-apt
+          - gpg
+      become: true
+    - name: Add docker key
+      ansible.builtin.apt_key:
+        url: https://download.docker.com/linux/debian/gpg
+        keyring: /etc/apt/keyrings/docker.gpg
+      become: true
+    - name: Add docker repo
+      ansible.builtin.apt_repository:
+        repo: deb [arch=amd64 signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/debian bookworm stable
+      become: true
+    - name: Install docker
+      ansible.builtin.apt:
+        update_cache: true
+        pkg:
+          - docker-ce
+          - docker-ce-cli
+          - containerd.io
+          - docker-buildx-plugin
+          - docker-compose-plugin
+      become: true
+    - name: Add user to docker group
+      ansible.builtin.user:
+        user: debian
+        groups:
+          - docker
+        append: true
+      become: true
+    - name: Enable docker
+      ansible.builtin.systemd:
+        name: docker
+        state: started
+        enabled: true
+      become: true

infra/cloud/0003_nextcloud_playbook.yaml

@@ -0,0 +1,22 @@
+- name: Deploy app
+  hosts: cloud
+  gather_facts: false
+  vars:
+    app: nextcloud
+  tasks:
+    - name: Wait for connection
+      ansible.builtin.wait_for_connection:
+        timeout: 300
+    - name: Get user
+      ansible.builtin.user:
+        name: debian
+      register: user
+    - name: Copy project
+      ansible.builtin.copy:
+        src: ./{{ app }}
+        dest: "{{ user.home }}"
+        mode: "0744"
+    - name: Re-deploy
+      ansible.builtin.command: bash all-in-one.sh
+      args:
+        chdir: "{{ user.home }}/{{ app }}"

infra/cloud/0004_immich_playbook.yaml

@@ -0,0 +1,27 @@
+- name: Deploy app
+  hosts: cloud
+  gather_facts: false
+  vars:
+    app: immich
+  tasks:
+    - name: Wait for connection
+      ansible.builtin.wait_for_connection:
+        timeout: 300
+    - name: Get user
+      ansible.builtin.user:
+        name: debian
+      register: user
+    # - name: Docker compose down
+    #   ansible.builtin.command: docker compose down
+    #   args:
+    #     chdir: "{{ user.home }}/{{ app }}"
+    #   ignore_errors: true
+    # - name: Copy project
+    #   ansible.builtin.copy:
+    #     src: ./{{ app }}
+    #     dest: "{{ user.home }}"
+    #     mode: "0744"
+    # - name: Docker compose up -d
+    #   ansible.builtin.command: docker compose up -d
+    #   args:
+    #     chdir: "{{ user.home }}/{{ app }}"

infra/cloud/immich/docker-compose.yaml

@@ -0,0 +1,93 @@
+version: "3"
+
+services:
+  immich-server:
+    container_name: immich_server
+    image: ghcr.io/immich-app/immich-server:${IMMICH_VERSION:-release}
+    command: [ "start.sh", "immich" ]
+    volumes:
+      - ${UPLOAD_LOCATION}:/usr/src/app/upload
+    env_file:
+      - .env
+    depends_on:
+      - redis
+      - database
+      - typesense
+    restart: always
+
+  immich-microservices:
+    container_name: immich_microservices
+    image: ghcr.io/immich-app/immich-server:${IMMICH_VERSION:-release}
+    # extends:
+    #   file: hwaccel.yml
+    #   service: hwaccel
+    command: [ "start.sh", "microservices" ]
+    volumes:
+      - ${UPLOAD_LOCATION}:/usr/src/app/upload
+    env_file:
+      - .env
+    depends_on:
+      - redis
+      - database
+      - typesense
+    restart: always
+
+  immich-machine-learning:
+    container_name: immich_machine_learning
+    image: ghcr.io/immich-app/immich-machine-learning:${IMMICH_VERSION:-release}
+    volumes:
+      - /mnt/data/immich-model-cache:/cache
+    env_file:
+      - .env
+    restart: always
+
+  immich-web:
+    container_name: immich_web
+    image: ghcr.io/immich-app/immich-web:${IMMICH_VERSION:-release}
+    env_file:
+      - .env
+    restart: always
+
+  typesense:
+    container_name: immich_typesense
+    image: typesense/typesense:0.24.1@sha256:9bcff2b829f12074426ca044b56160ca9d777a0c488303469143dd9f8259d4dd
+    environment:
+      - TYPESENSE_API_KEY=${TYPESENSE_API_KEY}
+      - TYPESENSE_DATA_DIR=/data
+      # remove this to get debug messages
+      - GLOG_minloglevel=1
+    volumes:
+      - /mnt/data/immich-typesense:/data
+    restart: always
+
+  redis:
+    container_name: immich_redis
+    image: redis:6.2-alpine@sha256:70a7a5b641117670beae0d80658430853896b5ef269ccf00d1827427e3263fa3
+    restart: always
+
+  database:
+    container_name: immich_postgres
+    image: postgres:14-alpine@sha256:28407a9961e76f2d285dc6991e8e48893503cc3836a4755bbc2d40bcc272a441
+    env_file:
+      - .env
+    environment:
+      POSTGRES_PASSWORD: ${DB_PASSWORD}
+      POSTGRES_USER: ${DB_USERNAME}
+      POSTGRES_DB: ${DB_DATABASE_NAME}
+    volumes:
+      - /mnt/data/immich-pgdata:/var/lib/postgresql/data
+    restart: always
+
+  immich-proxy:
+    container_name: immich_proxy
+    image: ghcr.io/immich-app/immich-proxy:${IMMICH_VERSION:-release}
+    environment:
+      # Make sure these values get passed through from the env file
+      - IMMICH_SERVER_URL
+      - IMMICH_WEB_URL
+    ports:
+      - 2283:8080
+    depends_on:
+      - immich-server
+      - immich-web
+    restart: always

infra/cloud/nextcloud/all-in-one.sh

@@ -0,0 +1,21 @@
+#!/bin/bash
+
+docker stop nextcloud-aio-mastercontainer || true
+docker rm nextcloud-aio-mastercontainer || true
+
+docker run \
+--init \
+--sig-proxy=false \
+--name nextcloud-aio-mastercontainer \
+--restart unless-stopped \
+--publish 8080:8080 \
+--env NEXTCLOUD_DATADIR=/mnt/data/nextcloud \
+--env NEXTCLOUD_UPLOAD_LIMIT=16G \
+--env NEXTCLOUD_MAX_TIME=7200 \
+--env APACHE_PORT=11000 \
+--env APACHE_IP_BINDING=0.0.0.0 \
+--env TZ=Europe/London \
+--env AIO_DISABLE_BACKUP_SECTION=true \
+--volume nextcloud_aio_mastercontainer:/mnt/docker-aio-config \
+--volume /var/run/docker.sock:/var/run/docker.sock:ro \
+-d nextcloud/all-in-one:latest

inventory/proxmox.yaml

@@ -7,6 +7,13 @@ proxmox:
             pve.mgmt.home.local.koval.net:
             pve2.mgmt.home.local.koval.net:
         managed:
+          children:
+            cloud:
               hosts:
+                cloud.srv.home.local.koval.net:
+          vars:
+            ansible_user: debian
+            ansible_ssh_private_key_file: ~/.ssh/id_rsa
+            ansible_ssh_common_args: -o StrictHostKeyChecking=accept-new # TODO: Improve this
         unmanaged:
           hosts: