COCOS-346 - Explore cloud init for Cloud setup (#357)

* Add qemu cloud init Signed-off-by: Jilks Smith <smithjilks@gmail.com> * Update qemu cloud init Signed-off-by: Jilks Smith <smithjilks@gmail.com> * Add qemu cloud init Signed-off-by: Jilks Smith <smithjilks@gmail.com> * Update qemu cloud init Signed-off-by: Jilks Smith <smithjilks@gmail.com> * Update qemu cloud config * Update cloud init Signed-off-by: Jilks Smith <smithjilks@gmail.com> * Update cloud init Signed-off-by: Jilks Smith <smithjilks@gmail.com> * Add cloud init README.md Signed-off-by: Jilks Smith <smithjilks@gmail.com> * Add cocos release workflow Signed-off-by: Jilks Smith <smithjilks@gmail.com> --------- Signed-off-by: Jilks Smith <smithjilks@gmail.com>
2026-06-23 04:10:25 +00:00 · 2025-01-31 17:48:26 +03:00
parent 5969ae3bcb
commit da88fe1e45
6 changed files with 518 additions and 8 deletions
@@ -1,9 +1,9 @@
-name: Build and Release
+name: Build and Release Hal

 on:
  push:
    tags:
-      - '*'
+      - "*"

 jobs:
  build:
@@ -32,8 +32,8 @@ jobs:
        with:
          root-reserve-mb: 35000
          swap-size-mb: 1024
-          remove-dotnet: 'true'
-          remove-android: 'true'
+          remove-dotnet: "true"
+          remove-android: "true"
      - name: Check free space
        run: |
          echo "Free space:"
@@ -48,26 +48,33 @@ jobs:
      - name: Checkout cocos
        uses: actions/checkout@v4
        with:
-          repository: 'ultravioletrs/cocos'
+          repository: "ultravioletrs/cocos"
          path: cocos

      - name: Checkout buildroot
        uses: actions/checkout@v4
        with:
-          repository: 'buildroot/buildroot'
+          repository: "buildroot/buildroot"
          path: buildroot
          ref: 2024.11-rc2

-      - name: Build
+      - name: Build hal
        run: |
          cd buildroot
          make BR2_EXTERNAL=../cocos/hal/linux cocos_defconfig
          make

+      - name: Build cocos
+        run: |
+          cd cocos
+          make
+
      - name: Release
        uses: softprops/action-gh-release@v2
        with:
          files: |
            buildroot/output/images/bzImage
            buildroot/output/images/rootfs.cpio.gz
-
+            cocos/build/cocos-agent  
+            cocos/build/cocos-cli  
+            cocos/build/cocos-manager
@@ -0,0 +1,89 @@
+####  memory config
+MEMORY_SIZE=2048M
+MEMORY_SLOTS=5
+MAX_MEMORY=30G
+
+
+####  ovmf code config
+OVMF_CODE_IF=pflash
+OVMF_CODE_FORMAT=raw
+OVMF_CODE_UNIT=0
+OVMF_CODE_FILE=/usr/share/OVMF/OVMF_CODE.fd
+OVMF_CODE_READONLY=on
+OVMF_VERSION=
+
+####  ovmf vars config
+OVMF_VARS_IF=pflash
+OVMF_VARS_FORMAT=raw
+OVMF_VARS_UNIT=1
+OVMF_VARS_FILE=/usr/share/OVMF/OVMF_VARS.fd
+
+####  net dev config
+NET_DEV_ID=vmnic
+NET_DEV_HOST_FWD_AGENT=7020
+NET_DEV_GUEST_FWD_AGENT=7002
+
+####  Virtio Net Pci Config
+VIRTIO_NET_PCI_DISABLE_LEGACY=on
+VIRTIO_NET_PCI_IOMMU_PLATFORM=true
+VIRTIO_NET_PCI_ADDR=0x2
+VIRTIO_NET_PCI_ROMFILE=
+
+####  Disk image config
+DISK_IMG_KERNEL_FILE=
+DISK_IMG_ROOTFS_FILE=
+
+KERNEL_COMMAND_LINE="quiet console=null"
+
+####  Sev Config
+SEV_ID=sev0
+SEV_CBIT_POS=51
+SEV_REDUCED_PHYS_BITS=1
+SEV_HOST_DATA=
+
+#### VSock Config
+VSOCK_ID=vhost-vsock-pci0
+VSOCK_GUEST_CID=3
+
+BIN_PATH=qemu-system-x86_64
+USE_SUDO=false
+ENABLE_SEV=false
+ENABLE_SEV_SNP=false
+
+ENABLE_KVM=true
+
+MACHINE=q35
+CPU=EPYC
+SMP_COUNT=8
+SMP_MAXCPUS=64
+MEM_ID=ram1
+
+KERNEL_HASH=false
+
+NO_GRAPHIC=true
+MONITOR=pty
+HOST_FWD_RANGE=6100-6200
+CERTS_MOUNT=/etc/cocos/certs
+ENV_MOUNT=/etc/cocos/environment
+
+COCOS_AGENT_VERSION=v0.3.1
+
+#### Base image URL and names
+BASE_IMAGE_URL=https://cloud-images.ubuntu.com/noble/current/noble-server-cloudimg-amd64.img
+BASE_IMAGE=ubuntu-base.qcow2
+CUSTOM_IMAGE=ubuntu-custom.qcow2
+
+#### Paths for OVMF firmware
+OVMF_CODE=/usr/share/ovmf/x64/OVMF_CODE.4m.fd
+OVMF_VARS=/usr/share/ovmf/x64/OVMF_VARS.4m.fd
+
+#### VM parameters
+VM_NAME=cocos-vm
+RAM=16G
+DISK_SIZE=10G # Size for root filesystem
+QEMU_BINARY=qemu-system-x86_64
+
+AGENT_GRPC_SERVER_CERT=/etc/cocos/certs/server.pem
+AGENT_GRPC_SERVER_KEY=/etc/cocos/certs/key.pem
+AGENT_GRPC_SERVER_CA_CERTS=/etc/cocos/ca.pem
+AGENT_GRPC_CLIENT_CA_CERTS=/etc/cocos/ca.pem
@@ -0,0 +1,114 @@
+# Agent Cloud Init Setup
+
+## Overview
+
+The `hal/cloud` directory contains essential files required for setting up a virtual machine (VM) with cloud-init. This setup ensures the automated installation of dependencies, configuration of the environment, and deployment of the Cocos agent as a systemd service.
+
+### Directory Contents
+
+- **`config.yaml`**: This YAML file provides configuration instructions for the cloud image.
+- **`meta-data`**: Contains VM metadata, such as instance-specific details and identifiers.
+- **`qemu.sh`**: A Bash script for downloading and configuring a cloud image, running QEMU to simulate a VM with the cloud-init configuration.
+- **`.env`**: Contains environment variables for starting the VM in different modes, configuring disk space, memory allocation, and other parameters.
+
+## Configuration
+
+### Preparing the Cloud-Config File
+
+The `config.yaml` file defines system configurations, including user creation, package installations, file management, and command execution.
+Ensure that the cloud-config file is set up with the following configurations:
+
+- **User Credentials**: Specify the default username and password.
+- **Certificates and Keys**: Certificate files for agent for secure communication.
+- **Environment Variables**: Configuration parameters required by the system.
+
+The `config.yaml` file is divided into multiple sections, each addressing a specific aspect of the setup process.
+
+### 1. User Configuration
+
+This section creates a default user with specific permissions and configurations:
+
+- Creates a user named **`cocos_user`**.
+- Adds `cocos_user` to the `sudo` and `docker` groups.
+- Sets a default password (should be changed for production use).
+- Configures the user’s shell as `/bin/bash`.
+
+### 2. Package Installation
+
+Installs essential system packages required for various operations:
+
+- **`curl`**: For downloading files from the web.
+- **`make`**: A utility for building software.
+- **`git`**: Version control system for managing code repositories.
+- **`python3` and `python3-dev`**: Required for running Python-based tools.
+- **`net-tools`**: Provides networking utilities such as `ifconfig` and `route`.
+
+### 3. File Management (write_files)
+
+Creates and configures critical files required for the setup:
+
+- **Certificates**: Cert files (`cert.pem`, `ca.pem`, `key.pem`) located at `/etc/cocos/certs/`.
+- **Environment Variables**: An env file stored at `/etc/cocos/environment`.
+- **Systemd Service File**: Cocos agent service configuration file at `/etc/systemd/system/cocos-agent.service` for managing the Cocos agent.
+- **Agent Scripts**:
+  - `agent_setup.sh`: Configures network interfaces and resizes the root filesystem.
+  - `agent_start_script.sh`: Sets up Docker and starts the Cocos agent.
+
+### 4. Execution of Commands (runcmd)
+
+A sequence of commands is executed to finalize the setup:
+
+- Creates necessary directories: `/cocos`, `/cocos_init`, `/var/log/cocos`, `/etc/cocos`.
+- Downloads and installs the Cocos agent binary.
+- Installs **Wasmtime** and configures its environment variables.
+- Installs **Docker** and adds `cocos_user` to the Docker group.
+- Reloads systemd and enables the Cocos agent service.
+
+## Running the Agent
+
+To test the cloud-init configuration, execute the `qemu.sh` script to bring up a VM using QEMU:
+
+```bash
+sudo ./qemu.sh
+```
+
+**Important:** The script must be executed as root.
+
+Once the QEMU boots the VM, the Cocos agent will run as a systemd service. The service is configured to start automatically on boot and restart in case of failure.
+
+## Debugging and Monitoring
+
+For troubleshooting and monitoring the Cocos agent service, use the following commands within the VM:
+
+### Manually Start the Service
+
+To manually start the agent service, execute:
+
+```bash
+sudo systemctl start cocos-agent.service
+```
+
+### Verify Service Status
+
+To check if the service is running properly, use:
+
+```bash
+sudo systemctl status cocos-agent.service
+```
+
+### View Service Logs
+
+To inspect logs generated by the agent service, execute:
+
+```bash
+journalctl -u cocos-agent.service
+```
+
+### Check Standard Output and Error Logs
+
+To check logs stored in the system, use:
+
+```bash
+cat /var/log/cocos/agent.stdout.log
+cat /var/log/cocos/agent.stderr.log
+```
@@ -0,0 +1,174 @@
+#cloud-config
+package_update: true
+package_upgrade: false
+
+users:
+  - default
+  - name: cocos_user
+    gecos: Default User
+    groups:
+      - sudo
+      - docker # Add cocos user to the docker group
+    sudo:
+      - ALL=(ALL:ALL) ALL
+    shell: /bin/bash
+
+chpasswd:
+  list: |
+    cocos_user:password
+  expire: False
+
+ssh_pwauth: True
+
+packages:
+  - curl
+  - make
+  - git
+  - python3
+  - python3-dev
+  - net-tools # Add net-tools to install the 'route' command
+
+write_files:
+  - path: /etc/cocos/certs/cert.pem
+    content: |
+      # Add certificate content here
+    permissions: "0644"
+
+  - path: /etc/cocos/certs/ca.pem
+    content: |
+      # Add CA certificate content here
+    permissions: "0644"
+
+  - path: /etc/cocos/certs/key.pem
+    content: |
+      # Add private key content here
+    permissions: "0600"
+
+  - path: /etc/cocos/environment
+    content: |
+      # Add environment variables here
+    permissions: "0644"
+
+  - path: /etc/systemd/system/cocos-agent.service
+    content: |
+      [Unit]
+      Description=Cocos AI agent
+      After=network.target
+      Before=docker.service
+
+      [Service]
+      WorkingDirectory=/cocos
+      StandardOutput=file:/var/log/cocos/agent.stdout
+      StandardError=file:/var/log/cocos/agent.stderr
+      EnvironmentFile=/etc/cocos/environment
+      ExecStartPre=/cocos_init/agent_setup.sh
+      ExecStart=/cocos_init/agent_start_script.sh
+      Restart=always
+
+      [Install]
+      WantedBy=default.target
+    permissions: "0644"
+
+  # Agent setup script
+  - path: /cocos_init/agent_setup.sh
+    content: |
+      #!/bin/sh
+
+      WORK_DIR="/cocos"
+
+      # IFACES are all network interfaces excluding lo (LOOPBACK) and sit interfaces
+      IFACES=$(ip link show | grep -vE 'LOOPBACK|sit*' | awk -F': ' '{print $2}')
+
+      # This for loop brings up all network interfaces in IFACES and dhclient obtains an IP address for the every interface
+      for IFACE in $IFACES; do
+          STATE=$(ip link show $IFACE | grep DOWN)
+          if [ -n "$STATE" ]; then
+              ip link set $IFACE up
+          fi
+
+          IP_ADDR=$(ip addr show $IFACE | grep 'inet ')
+          if [ -z "$IP_ADDR" ]; then
+              dhclient $IFACE
+          fi
+      done
+
+      if [ ! -d "$WORK_DIR" ]; then
+          mkdir -p $WORK_DIR
+      fi
+
+      # Resize the root filesystem to 100% of available space
+      ROOT_DEV=$(findmnt / -o SOURCE -n)  # Get the root filesystem device
+      resize2fs "$ROOT_DEV" && echo "Root filesystem resized successfully" || echo "Failed to resize root filesystem"
+    permissions: "0755"
+
+  # Agent start script
+  - path: /cocos_init/agent_start_script.sh
+    content: |
+      #!/bin/sh
+
+      # Change the docker.service file to allow Docker to run in RAM
+      mkdir -p /etc/systemd/system/docker.service.d
+
+      # Create or overwrite the override.conf file with the new Environment variable
+      tee /etc/systemd/system/docker.service.d/override.conf > /dev/null <<EOF
+      [Service]
+      Environment=DOCKER_RAMDISK=true
+      EOF
+
+      systemctl daemon-reload
+
+      NUM_OF_PERMITED_IFACE=1
+
+      NUM_OF_IFACE=$(ip route | grep -Eo 'dev [a-z0-9]+' | awk '{ print $2 }' | grep -v '^docker' | sort | uniq | wc -l)
+
+      if [ $NUM_OF_IFACE -gt $NUM_OF_PERMITED_IFACE ]; then
+          echo "More than one network interface in the VM"
+          exit 1
+      fi
+
+      DEFAULT_IFACE=$(route | grep '^default' | grep -o '[^ ]*$')
+      AGENT_GRPC_HOST=$(ip -4 addr show $DEFAULT_IFACE | grep inet | awk '{print $2}' | cut -d/ -f1)
+
+      export AGENT_GRPC_HOST
+
+      exec /bin/cocos-agent
+    permissions: "0755"
+
+runcmd:
+  # Create necessary directories
+  - mkdir -p /cocos
+  - mkdir -p /cocos_init
+  - mkdir -p /var/log/cocos
+  - mkdir -p /etc/cocos
+
+  # Download the cocos-agent binary
+  - echo "[ COCOS AGENT SETUP ] Downloading the cocos-agent binary..."
+  - curl -L -O -J https://github.com/smithjilks/cocos/releases/download/v1.0.0/cocos-agent --progress-bar && echo "[ COCOS AGENT SETUP ] cocos-agent binary downloaded successfully" || echo "Failed to download cocos-agent binary"
+
+  # Install the agent binary
+  - echo "[ COCOS AGENT SETUP ] Installing cocos-agent binary..."
+  - install -D -m 0755 cocos-agent /bin/cocos-agent && echo "[ COCOS AGENT SETUP ] cocos-agent binary installed successfully" || echo "[ COCOS AGENT SETUP ] Failed to install cocos-agent binary"
+
+  # Install Wasmtime
+  - echo "Installing Wasmtime runtime..."
+  - curl https://wasmtime.dev/install.sh -sSf | bash && echo "Wasmtime installed successfully" || echo "Failed to install Wasmtime"
+  - echo "Configuring Wasmtime environment variables..."
+  - echo "export WASMTIME_HOME=$HOME/.wasmtime" >> /etc/profile.d/wasm_env.sh
+  - echo "export PATH=\$WASMTIME_HOME/bin:\$PATH" >> /etc/profile.d/wasm_env.sh
+  - . /etc/profile.d/wasm_env.sh && echo "Wasmtime environment variables configured successfully" || echo "Failed to configure Wasmtime environment variables"
+
+  # Install Docker
+  - echo "Starting Docker installation..."
+  - curl -fsSL https://get.docker.com -o get-docker.sh && echo "Docker install script downloaded successfully" || echo "Failed to download Docker install script"
+  - sh ./get-docker.sh && echo "Docker installed successfully" || echo "Failed to install Docker"
+  - usermod -aG docker cocos_user && echo "Added cocos_user to the docker group" || echo "Failed to add cocos_user to the docker group"
+
+  # Reload systemd and enable the service
+  - echo "[ COCOS AGENT SETUP ] Reloading systemd daemon..."
+  - systemctl daemon-reload && echo "[ COCOS AGENT SETUP ] Systemd daemon reloaded successfully" || echo "[ COCOS AGENT SETUP ] Failed to reload systemd daemon"
+  - echo "[ COCOS AGENT SETUP ] Enabling cocos-agent.service..."
+  - systemctl enable cocos-agent.service && echo "[ COCOS AGENT SETUP ] cocos-agent.service enabled successfully" || echo "[ COCOS AGENT SETUP ] Failed to enable cocos-agent.service"
+  - echo "[ COCOS AGENT SETUP ] Starting cocos-agent.service..."
+  - systemctl start cocos-agent.service && echo "[ COCOS AGENT SETUP ] cocos-agent.service started successfully" || echo "[ COCOS AGENT SETUP ] Failed to start cocos-agent.service"
+
+final_message: "Cocos agent setup complete. Verify logs to confirm successful service startup."
@@ -0,0 +1,2 @@
+instance-id: iid-cocos-vm
+local-hostname: cocos-vm
@@ -0,0 +1,124 @@
+#!/bin/bash
+
+# Source environment variables
+source ./.env
+
+# Required commands
+REQUIRED_CMDS=("wget" "cloud-localds" "$QEMU_BINARY" "qemu-img")
+
+# Check for required commands
+for cmd in "${REQUIRED_CMDS[@]}"; do
+    if ! command -v "$cmd" &> /dev/null; then
+        echo "Error: $cmd is not installed. Please install it and try again."
+        exit 1
+    fi
+done
+
+# Ensure script is run as root
+if [[ $EUID -ne 0 ]]; then
+    echo "Error: This script must be run as root."
+    exit 1
+fi
+
+# Create the root filesystem image if it doesn't exist
+if [ ! -f "$BASE_IMAGE" ]; then
+  echo "Downloading base Ubuntu image..."
+  wget -q "$BASE_IMAGE_URL" -O "$BASE_IMAGE" --show-progress
+fi
+
+# Create custom image
+echo "Creating custom QEMU image..."
+qemu-img create -f qcow2 -b "$BASE_IMAGE" -F qcow2 "$CUSTOM_IMAGE" "$DISK_SIZE"
+
+# Cloud-init configuration files
+CLOUD_CONFIG="config.yaml"
+META_DATA="meta-data"
+SEED_IMAGE="seed.img"
+
+# Create seed image for cloud-init
+echo "Creating seed image..."
+cloud-localds "$SEED_IMAGE" "$CLOUD_CONFIG" "$META_DATA"
+
+# Construct QEMU arguments from environment variables
+construct_qemu_args() {
+    args=()
+
+    args+=("-name" "$VM_NAME")
+
+    # Virtualization (Enable KVM)
+    if [ "$ENABLE_KVM" == "true" ]; then
+        args+=("-enable-kvm")
+    fi
+
+    # Machine, CPU, RAM
+    if [ -n "$MACHINE" ]; then
+        args+=("-machine" "$MACHINE")
+    fi
+
+    if [ -n "$CPU" ]; then
+        args+=("-cpu" "$CPU")
+    fi
+
+    args+=("-boot" "d")
+    args+=("-smp" "$SMP_COUNT,maxcpus=$SMP_MAXCPUS")
+    args+=("-m" "$MEMORY_SIZE,slots=$MEMORY_SLOTS,maxmem=$MAX_MEMORY")
+
+    # OVMF (if applicable)
+    if [ "$ENABLE_SEV_SNP" != "true" ]; then
+        args+=("-drive" "if=$OVMF_CODE_IF,format=$OVMF_CODE_FORMAT,unit=$OVMF_CODE_UNIT,file=$OVMF_CODE,readonly=$OVMF_CODE_READONLY")
+        args+=("-drive" "if=$OVMF_VARS_IF,format=$OVMF_VARS_FORMAT,unit=$OVMF_VARS_UNIT,file=$OVMF_VARS")
+    fi
+
+    # Network configuration
+    args+=("-netdev" "user,id=$NET_DEV_ID,hostfwd=tcp::$NET_DEV_HOST_FWD_AGENT-:$NET_DEV_GUEST_FWD_AGENT")
+    args+=("-device" "virtio-net-pci,disable-legacy=$VIRTIO_NET_PCI_DISABLE_LEGACY,iommu_platform=$VIRTIO_NET_PCI_IOMMU_PLATFORM,netdev=$NET_DEV_ID,addr=$VIRTIO_NET_PCI_ADDR,romfile=$VIRTIO_NET_PCI_ROMFILE")
+    args+=("-device" "vhost-vsock-pci,id=$VSOCK_ID,guest-cid=$VSOCK_GUEST_CID")
+
+    # SEV (if enabled)
+    if [ "$ENABLE_SEV" == "true" ] || [ "$ENABLE_SEV_SNP" == "true" ]; then
+        sev_type="sev-guest"
+        kernel_hash=""
+        host_data=""
+
+        args+=("-machine" "confidential-guest-support=$SEV_ID,memory-backend=$MEM_ID")
+
+        if [ "$ENABLE_SEV_SNP" == "true" ]; then
+            args+=("-bios" "$OVMF_CODE_FILE")
+            sev_type="sev-snp-guest"
+
+            if [ -n "$SEV_HOST_DATA" ]; then
+                host_data=",host-data=$SEV_HOST_DATA"
+            fi
+        fi
+
+        if [ "$ENABLE_KERNEL_HASH" == "true" ]; then
+            kernel_hash=",kernel-hashes=on"
+        fi
+
+        args+=("-object" "memory-backend-memfd,id=$MEM_ID,size=$MEMORY_SIZE,share=true,prealloc=false")
+        args+=("-object" "$sev_type,id=$SEV_ID,cbitpos=$SEV_CBIT_POS,reduced-phys-bits=$SEV_REDUCED_PHYS_BITS$kernel_hash$host_data")
+    fi
+
+    # Disk image configuration
+    args+=("-drive" "file=$SEED_IMAGE,media=cdrom")
+    args+=("-drive" "file=$CUSTOM_IMAGE,if=none,id=disk0,format=qcow2")
+    args+=("-device" "virtio-scsi-pci,id=scsi,disable-legacy=on,iommu_platform=true")
+    args+=("-device" "scsi-hd,drive=disk0")
+
+    # Display options
+    if [ "$NO_GRAPHIC" == "true" ]; then
+        args+=("-nographic")
+    fi
+
+    args+=("-monitor" "$MONITOR")
+    args+=("-no-reboot")
+    args+=("-vnc" ":9")
+
+    echo "${args[@]}"
+}
+
+qemu_args=$(construct_qemu_args)
+
+echo "Running QEMU with the following arguments: $qemu_args"
+echo "Starting QEMU VM..."
+$QEMU_BINARY $qemu_args