add Mesa Vulkan drivers for GPU compute workloads

Enables Vulkan-based GPU acceleration for containerized workloads
like ollama/llama.cpp on Radeon 780M iGPUs without needing ROCm.

.gitignore

@@ -5,7 +5,8 @@ images/
 # Boot file artifacts (but keep boot.ipxe configuration)
 http/*
 !http/boot.ipxe
-tftp/
+tftp/*
+!tftp/ipxe.efi
 
 # Generated metadata
 *.img

.sops.yaml

@@ -0,0 +1,3 @@
+creation_rules:
+  - path_regex: secrets/.*\.yaml$
+    age: age1gausnystsln7fpenw7arw7x79xe22z22697jnauj38npy0usayqqxqc7td2y

AGENTS.md

@@ -0,0 +1 @@
+CLAUDE.md

CLAUDE.md

@@ -1,6 +1,6 @@
-# CLAUDE.md
+# AGENTS.md
 
-This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+This file provides guidance to AI coding assistants when working with code in this repository.
 
 ## Project Overview
 
@@ -69,6 +69,14 @@ Located in `initramfs/` directory, passed to `mkinitramfs` with `-d` flag:
   - Mounts squashfs read-only
   - If `overlayroot=tmpfs`, creates overlay with tmpfs upper layer for writes
 
+### Dracut Module (Alternative)
+
+Located in `dracut-module/90netboot/`, an alternative initramfs approach using dracut:
+
+- **module-setup.sh** - Dracut module setup and dependencies
+- **parse-netboot.sh** - Parses kernel command line for netboot parameters
+- **mount-netboot.sh** - Handles HTTP squashfs download and mounting
+
 ### iPXE Boot Configuration
 
 **http/boot.ipxe** - iPXE script that:
@@ -83,7 +91,7 @@ Located in `initramfs/` directory, passed to `mkinitramfs` with `-d` flag:
 
 Built systems are configured with:
 - Norwegian keyboard layout (nb_NO.UTF-8 + en_US.UTF-8 locales)
-- Root SSH access with specific authorized keys (see build-image.sh:138-141)
+- Root SSH access with specific authorized keys (see build-image.sh around line 160)
 - Password auth disabled, pubkey only
 - Network via netplan with DHCP (systemd-networkd)
 - Ephemeral tmpfs mounts: /tmp (2G), /var/tmp (1G), /var/log (1G), /run (512M)
@@ -103,20 +111,36 @@ Built systems are configured with:
 - Skips full debootstrap/package installation
 - **Hardcoded paths:** `/srv/netboot/*` - update if repo moves
 
+**verify-image.sh** - Validate built image completeness
+- Checks all required files exist (vmlinuz, initrd, squashfs, boot.ipxe)
+- Validates file types (kernel, cpio archive, squashfs)
+- Verifies file permissions (644 for HTTP serving)
+- Inspects initramfs for custom netboot script and required binaries
+- Checks squashfs for critical directories and configurations
+- Validates iPXE configuration references correct files
+- Run with `./verify-image.sh` after `make build`
+
 ## File Structure
 
 ```
 .
 ├── build-image.sh          # Main build script
 ├── Makefile                # Build/deploy automation
-├── boot.ipxe               # iPXE boot configuration (in http/)
+├── verify-image.sh         # Image validation script
-├── initramfs/              # Custom initramfs configuration
+├── chroot-rootfs.sh        # Chroot helper (hardcoded paths)
+├── rebuild-squashfs.sh     # Rebuild helper (hardcoded paths)
+├── AGENTS.md               # AI assistant guidance (this file)
+├── CLAUDE.md               # Claude-specific guidance
+├── initramfs/              # Custom initramfs configuration (mkinitramfs)
 │   ├── initramfs.conf      # mkinitramfs config
 │   ├── modules             # Extra kernel modules
 │   ├── hooks/netboot       # Binary copying hook
 │   └── scripts/netboot     # HTTP root mounting logic
-├── chroot-rootfs.sh        # Chroot helper (hardcoded paths)
+├── dracut-module/          # Alternative initramfs (dracut)
-├── rebuild-squashfs.sh     # Rebuild helper (hardcoded paths)
+│   └── 90netboot/
+│       ├── module-setup.sh
+│       ├── parse-netboot.sh
+│       └── mount-netboot.sh
 ├── build/                  # Build artifacts (gitignored)
 │   └── rootfs/             # debootstrap rootfs
 ├── images/                 # Versioned builds (gitignored)
@@ -140,6 +164,6 @@ Built systems are configured with:
 - 15-30 minute build time
 - ~1GB disk space for build artifacts
 
-**SSH key management:** Root SSH keys are embedded in build-image.sh:138-141. Update these before building images for new environments.
+**SSH key management:** Root SSH keys are embedded in build-image.sh around line 160. Update these before building images for new environments.
 
 **Network driver:** RTL8125 (r8125) driver is explicitly loaded in initramfs for 2.5GbE NICs. If different NICs are used, update `initramfs/modules` and `initramfs/scripts/netboot`.

Makefile

@@ -1,9 +1,19 @@
-.PHONY: build deploy clean help
+.PHONY: deploy clean help check-nas all
 
 NAS_HOST=phoenix
 NAS_PATH=/srv/netboot
 SCRIPT_DIR=$(shell dirname $(realpath $(firstword $(MAKEFILE_LIST))))
 
+# Source files that trigger a rebuild
+BUILD_SOURCES := $(SCRIPT_DIR)/build-image.sh \
+                 $(wildcard $(SCRIPT_DIR)/initramfs/*) \
+                 $(wildcard $(SCRIPT_DIR)/initramfs/*/*) \
+                 $(wildcard $(SCRIPT_DIR)/files/*) \
+                 $(wildcard $(SCRIPT_DIR)/secrets/*.yaml)
+
+# Build artifact (used as target for dependency tracking)
+BUILD_ARTIFACT := $(SCRIPT_DIR)/http/filesystem.squashfs
+
 help:
 	@echo "Netboot image build and deployment"
 	@echo ""
@@ -23,7 +33,8 @@ check-nas:
 	@echo "Checking NAS connectivity..."
 	@ping -c 1 $(NAS_HOST) > /dev/null 2>&1 && echo "✓ NAS is reachable" || (echo "✗ Cannot reach $(NAS_HOST)"; exit 1)
 
-build:
+# Build depends on source files - only rebuilds if sources changed
+$(BUILD_ARTIFACT): $(BUILD_SOURCES)
 	@echo "Building netboot image..."
 	@echo "This will take 15-30 minutes..."
 	sudo $(SCRIPT_DIR)/build-image.sh
@@ -32,10 +43,14 @@ build:
 	@echo "Artifacts ready in $(SCRIPT_DIR)/http/"
 	@du -sh $(SCRIPT_DIR)/http/*
 
+build: $(BUILD_ARTIFACT)
+
 deploy: check-nas
 	@echo "Deploying to NAS ($(NAS_HOST):$(NAS_PATH))..."
 	@echo "Syncing http/ directory..."
 	rsync -avz --delete $(SCRIPT_DIR)/http/ $(NAS_HOST):$(NAS_PATH)/http/
+	@echo "Syncing tftp/ directory (iPXE bootloader)..."
+	rsync -avz $(SCRIPT_DIR)/tftp/ $(NAS_HOST):$(NAS_PATH)/tftp/
 	@echo ""
 	@echo "✓ Deployment complete!"
 	@echo "Images are now live on $(NAS_HOST)"

OPERATIONS.md

@@ -0,0 +1,333 @@
+# Netboot Operations Guide
+
+This document covers day-to-day operations for the netboot K3s cluster system.
+
+## Quick Reference
+
+```bash
+# Build new image (15-30 min, requires sudo)
+cd /home/lindahl/git/netboot
+sudo ./build-image.sh
+make deploy
+
+# Rebuild initramfs only (faster, ~2 min)
+sudo ./rebuild-initramfs.sh
+make deploy
+
+# SSH to a node
+ssh root@192.168.100.51
+
+# Check node storage
+ssh root@192.168.100.51 "lsblk && df -h /var/lib/containerd /var/lib/longhorn"
+```
+
+## Architecture Overview
+
+```
+┌─────────────────┐     HTTP (8800)      ┌──────────────────┐
+│  Phoenix NAS    │◄────────────────────►│   K3s Nodes      │
+│  192.168.100.1  │                      │  192.168.100.5x  │
+├─────────────────┤                      ├──────────────────┤
+│ /srv/netboot/   │                      │ RAM (overlay)    │
+│   http/         │                      │   └─ / (root)    │
+│     vmlinuz     │                      │ NVMe (persistent)│
+│     initrd-netboot.img                 │   ├─ containerd  │
+│     filesystem.squashfs                │   └─ longhorn    │
+│     boot.ipxe   │                      └──────────────────┘
+└─────────────────┘
+```
+
+**Boot sequence:**
+1. Node PXE boots → loads iPXE
+2. iPXE fetches `boot.ipxe` from phoenix
+3. Downloads kernel + initramfs
+4. Initramfs downloads squashfs root over HTTP
+5. Mounts squashfs read-only with tmpfs overlay
+6. `setup-node-storage.service` partitions/mounts local NVMe
+7. System starts, K3s joins cluster
+
+## Building Images
+
+### Full Build
+
+Builds everything from scratch: debootstrap, packages, initramfs, squashfs.
+
+```bash
+cd /home/lindahl/git/netboot
+sudo ./build-image.sh
+make deploy
+```
+
+**Time:** 15-30 minutes
+**When to use:** Package changes, kernel updates, major configuration changes
+
+### Initramfs-Only Rebuild
+
+Faster rebuild when only changing boot/network logic.
+
+```bash
+sudo ./rebuild-initramfs.sh
+make deploy
+```
+
+**Time:** ~2 minutes
+**When to use:** Changes to `initramfs/` scripts or hooks
+
+### Verify Build
+
+Check that all components are present and valid:
+
+```bash
+./verify-image.sh
+```
+
+## Secret Management
+
+Secrets are encrypted with [sops](https://github.com/getsops/sops) using age encryption. The age key lives on phoenix.
+
+### Encrypted Files
+
+| File | Contents |
+|------|----------|
+| `secrets/netboot.sops.yaml` | Root password hash for console login |
+
+### Viewing Secrets
+
+```bash
+# From any machine with SSH access to phoenix
+cat secrets/netboot.sops.yaml | ssh phoenix "sops -d --input-type yaml --output-type yaml /dev/stdin"
+```
+
+### Updating Root Password
+
+1. Generate new password hash:
+   ```bash
+   ssh phoenix "echo 'newpassword' | openssl passwd -6 -stdin"
+   ```
+
+2. Update the encrypted file:
+   ```bash
+   ssh phoenix "cd /path/to/netboot && sops secrets/netboot.sops.yaml"
+   # Edit root_password_hash value, save
+   ```
+
+   Or recreate entirely:
+   ```bash
+   NEW_HASH=$(ssh phoenix "echo 'newpassword' | openssl passwd -6 -stdin")
+   ssh phoenix "echo 'root_password_hash: \"$NEW_HASH\"' | sops --input-type yaml --output-type yaml -e --age age1gausnystsln7fpenw7arw7x79xe22z697jnauj38npy0usayqqxqc7td2y /dev/stdin" > secrets/netboot.sops.yaml
+   ```
+
+3. Rebuild and deploy:
+   ```bash
+   sudo ./build-image.sh
+   make deploy
+   ```
+
+4. Reboot nodes to pick up new password
+
+### Adding New Secrets
+
+Edit `.sops.yaml` to add new file patterns, then create encrypted files on phoenix:
+
+```bash
+ssh phoenix "sops secrets/newfile.sops.yaml"
+```
+
+## Node Storage Setup
+
+Local NVMe is automatically partitioned on first boot by `setup-node-storage.service`.
+
+### Partition Layout
+
+| Partition | Size | Label | Mount Point | Purpose |
+|-----------|------|-------|-------------|---------|
+| nvme0n1p1 | 75GB | containerd | /var/lib/containerd | Container images |
+| nvme0n1p2 | Remaining | longhorn | /var/lib/longhorn | Distributed storage |
+
+### Automatic Behavior
+
+| Drive State | Action |
+|-------------|--------|
+| No partition table | Auto-format (no prompt) |
+| Has our labels (containerd/longhorn) | Mount silently |
+| Has unknown partitions | Prompt on tty1, 120s timeout, skip if no response |
+
+### Manual Intervention
+
+If a node has an unknown drive and you want to format it:
+
+1. Connect to physical console (tty1)
+2. Reboot the node
+3. Press ENTER when prompted (within 120 seconds)
+4. Wait 5 seconds (abort window)
+5. Drive is formatted and mounted
+
+### Checking Storage Status
+
+```bash
+# On node
+journalctl -u setup-node-storage
+cat /var/lib/containerd/.netboot-storage  # marker file with metadata
+lsblk /dev/nvme0n1
+df -h /var/lib/containerd /var/lib/longhorn
+```
+
+## SSH Access
+
+### Authorized Keys
+
+Keys are baked into the image at build time. Current keys:
+
+| Key | Source |
+|-----|--------|
+| `ssh-ed25519 AAAAC3...y1J` | lindahl@lindahl-Legion-5-Pro-16ACH6H |
+| `ssh-ed25519 AAAA...0tX` | lindahl@phoenix.home |
+
+To add/remove keys, edit `build-image.sh` around line 164-167.
+
+### Console Access
+
+Root password is set for physical console login only. SSH remains pubkey-only.
+
+```bash
+# Physical console or IPMI
+login: root
+Password: <from secrets/netboot.sops.yaml>
+```
+
+## Troubleshooting
+
+### Node Won't Boot
+
+1. Check phoenix HTTP server:
+   ```bash
+   ssh phoenix "curl -I http://localhost:8800/boot.ipxe"
+   ssh phoenix "ls -lh /srv/netboot/http/"
+   ```
+
+2. Check nginx is running:
+   ```bash
+   ssh phoenix "systemctl status nginx"
+   ```
+
+3. Verify image integrity:
+   ```bash
+   ./verify-image.sh
+   ```
+
+### Node Boots But No Network
+
+1. Check if initramfs has network driver:
+   ```bash
+   lsinitramfs http/initrd-netboot.img | grep -E "r8169|r8125"
+   ```
+
+2. Check kernel cmdline includes `ip=dhcp`:
+   ```bash
+   cat http/boot.ipxe
+   ```
+
+### Storage Not Mounting
+
+1. Check service status:
+   ```bash
+   ssh root@node "systemctl status setup-node-storage"
+   ssh root@node "journalctl -u setup-node-storage"
+   ```
+
+2. Check if NVMe exists:
+   ```bash
+   ssh root@node "lsblk"
+   ```
+
+3. Check labels:
+   ```bash
+   ssh root@node "blkid -L containerd && blkid -L longhorn"
+   ```
+
+### Overlay Filling Up
+
+The root overlay is only 2GB. If it fills:
+
+```bash
+# Check what's using space
+ssh root@node "du -sh /var/* | sort -h"
+
+# Temporary files should go to NVMe or tmpfs mounts
+# /tmp, /var/tmp, /var/log are separate tmpfs
+```
+
+## File Reference
+
+| File | Purpose |
+|------|---------|
+| `build-image.sh` | Main build script |
+| `rebuild-initramfs.sh` | Quick initramfs rebuild |
+| `verify-image.sh` | Validate built image |
+| `Makefile` | Build/deploy automation |
+| `initramfs/` | Custom initramfs config for mkinitramfs |
+| `initramfs/scripts/netboot` | HTTP root download and overlay mount |
+| `files/setup-node-storage` | NVMe partitioning script |
+| `files/setup-node-storage.service` | Systemd unit for storage setup |
+| `secrets/netboot.sops.yaml` | Encrypted root password |
+| `.sops.yaml` | Sops encryption config |
+| `http/boot.ipxe` | iPXE boot configuration |
+
+## Network Configuration
+
+### IP Address Layout
+
+| Range | Purpose |
+|-------|---------|
+| .1 | phoenix (gateway, DHCP, HTTP) |
+| .2-.19 | Reserved (future infrastructure) |
+| .20-.29 | Infrastructure devices |
+| .50-.59 | Static K3s nodes |
+| .60-.100 | Dynamic DHCP pool |
+
+### Static Assignments
+
+| Host | IP | MAC | Role |
+|------|-----|-----|------|
+| phoenix | 192.168.100.1 | - | NAS, HTTP server, DHCP |
+| usw-flex-2 | 192.168.100.21 | 94:2a:6f:4c:fc:72 | Managed switch |
+| k3s-node-01 | 192.168.100.51 | 78:55:36:04:e7:c8 | K3s worker |
+| k3s-node-02 | 192.168.100.52 | 78:55:36:04:e7:1d | K3s worker |
+
+HTTP server: `http://192.168.100.1:8800/`
+
+### DHCP Reservations
+
+Static IP assignments are configured in `/etc/dnsmasq.d/pxe-netboot.conf` on phoenix:
+
+```
+dhcp-range=192.168.100.60,192.168.100.100,12h
+
+# Static DHCP reservations for K3s nodes
+dhcp-host=78:55:36:04:e7:c8,192.168.100.51,k3s-node-01
+dhcp-host=78:55:36:04:e7:1d,192.168.100.52,k3s-node-02
+
+# Infrastructure
+dhcp-host=94:2a:6f:4c:fc:72,192.168.100.21,usw-flex-2
+```
+
+To add a new node:
+
+1. Boot the node once to get its MAC (check leases):
+   ```bash
+   ssh phoenix "cat /var/lib/misc/dnsmasq.leases"
+   ```
+
+2. Add reservation:
+   ```bash
+   ssh phoenix "sudo tee -a /etc/dnsmasq.d/pxe-netboot.conf << EOF
+   dhcp-host=XX:XX:XX:XX:XX:XX,192.168.100.5X,k3s-node-0X
+   EOF"
+   ```
+
+3. Restart dnsmasq:
+   ```bash
+   ssh phoenix "sudo systemctl restart dnsmasq"
+   ```
+
+To change the boot server IP, edit `http/boot.ipxe` and `initramfs/scripts/netboot`.

build-image.sh

@@ -14,6 +14,22 @@ VERSION=$(date +%Y%m%d-%H%M)
 
 echo "Building netboot image version $VERSION"
 
+# Decrypt secrets from phoenix (requires SSH access as the invoking user, not root)
+echo "Decrypting secrets from phoenix..."
+SECRETS_FILE="$SCRIPT_DIR/secrets/netboot.sops.yaml"
+SUDO_USER_HOME=$(getent passwd "${SUDO_USER:-$USER}" | cut -d: -f6)
+if [ -f "$SECRETS_FILE" ]; then
+    # Run SSH as the original user (not root) to use their SSH keys
+    ROOT_PW_HASH=$(sudo -u "${SUDO_USER:-$USER}" bash -c "cat '$SECRETS_FILE' | ssh phoenix 'sops -d --input-type yaml --output-type yaml /dev/stdin'" | grep root_password_hash | cut -d' ' -f2)
+    if [ -z "$ROOT_PW_HASH" ]; then
+        echo "WARNING: Failed to decrypt root password, console login will be disabled"
+        ROOT_PW_HASH="*"
+    fi
+else
+    echo "WARNING: No secrets file found at $SECRETS_FILE, console login will be disabled"
+    ROOT_PW_HASH="*"
+fi
+
 # Clean previous build - unmount any stray mounts first
 if [ -d "$BUILD_DIR/rootfs" ]; then
     echo "Cleaning up previous build mounts..."
@@ -40,6 +56,17 @@ debootstrap --arch=amd64 --variant=minbase --components=main,universe,multiverse
     noble $BUILD_DIR/rootfs \
     http://archive.ubuntu.com/ubuntu
 
+# Write root password hash to temp file for chroot to read
+# Use /root/ not /tmp/ because systemd installation may mount tmpfs over /tmp
+mkdir -p "$BUILD_DIR/rootfs/root"
+if [ -n "$ROOT_PW_HASH" ] && [ "$ROOT_PW_HASH" != "*" ]; then
+    echo "$ROOT_PW_HASH" > "$BUILD_DIR/rootfs/root/.pw_hash"
+    echo "Root password hash written to rootfs"
+else
+    echo "*" > "$BUILD_DIR/rootfs/root/.pw_hash"
+    echo "WARNING: No valid password hash, console login will be disabled"
+fi
+
 # Chroot and configure
 cat << 'CHROOT_SCRIPT' > $BUILD_DIR/rootfs/setup.sh
 #!/bin/bash
@@ -53,13 +80,27 @@ echo "keyboard-configuration keyboard-configuration/variant select Norwegian" |
 echo "locales locales/default_environment_locale select en_US.UTF-8" | debconf-set-selections
 echo "locales locales/locales_to_be_generated multiselect en_US.UTF-8 UTF-8, nb_NO.UTF-8 UTF-8" | debconf-set-selections
 
-# Update and upgrade
+# Enable noble-updates and noble-security for HWE kernel
+cat > /etc/apt/sources.list.d/ubuntu.sources << 'SOURCES'
+Types: deb
+URIs: http://archive.ubuntu.com/ubuntu
+Suites: noble noble-updates noble-backports
+Components: main universe multiverse
+Signed-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg
+
+Types: deb
+URIs: http://security.ubuntu.com/ubuntu
+Suites: noble-security
+Components: main universe multiverse
+Signed-By: /usr/share/keyrings/ubuntu-archive-keyring.gpg
+SOURCES
+
 apt-get update
 apt-get upgrade -y
 
-# Install essential packages
+# Install HWE kernel (6.14+) for RTL8125BP XID 689 support
 apt-get install -y \
-    linux-image-generic \
+    linux-image-generic-hwe-24.04 \
     linux-firmware \
     busybox-initramfs \
     initramfs-tools \
@@ -89,13 +130,20 @@ apt-get install -y \
     conntrack \
     socat \
     ethtool \
-    nfs-common
+    nfs-common \
+    open-iscsi
 
 # Container runtime prerequisites
 apt-get install -y \
     containerd \
     runc
 
+# Vulkan drivers for GPU compute workloads (ollama, llama.cpp)
+apt-get install -y \
+    mesa-vulkan-drivers \
+    libvulkan1 \
+    vulkan-tools
+
 # Useful tools
 apt-get install -y \
     htop \
@@ -104,7 +152,10 @@ apt-get install -y \
     less \
     rsync \
     git \
-    squashfs-tools
+    squashfs-tools \
+    parted \
+    fdisk \
+    gdisk
 
 # Clean up
 apt-get clean
@@ -112,8 +163,9 @@ rm -rf /var/lib/apt/lists/*
 rm -rf /tmp/*
 rm -rf /var/tmp/*
 
-# Configure hostname (will be overridden by netplan)
+# Don't set static hostname - let DHCP provide it via networkd
-echo "k3s-node" > /etc/hostname
+# Empty /etc/hostname allows transient hostname from DHCP
+echo "" > /etc/hostname
 
 # Configure network with netplan
 cat > /etc/netplan/01-netcfg.yaml <<EOF
@@ -134,11 +186,19 @@ EOF
 systemctl enable systemd-networkd
 systemctl enable systemd-resolved
 
-# Configure SSH
+# Configure SSH - disable socket activation, use traditional daemon
 sed -i 's/#PermitRootLogin.*/PermitRootLogin prohibit-password/' /etc/ssh/sshd_config
 sed -i 's/#PubkeyAuthentication.*/PubkeyAuthentication yes/' /etc/ssh/sshd_config
+# Disable socket activation (Ubuntu 24.04 default) and use traditional sshd
+systemctl disable ssh.socket 2>/dev/null || true
+rm -f /etc/systemd/system/ssh.service.requires/ssh.socket 2>/dev/null || true
+rm -f /etc/systemd/system/sockets.target.wants/ssh.socket 2>/dev/null || true
 systemctl enable ssh
 
+# Fix SSH host key permissions (must be 0600 for private keys, sshd refuses otherwise)
+chmod 600 /etc/ssh/ssh_host_*_key
+chmod 644 /etc/ssh/ssh_host_*_key.pub
+
 # Create SSH directory for root
 mkdir -p /root/.ssh
 chmod 700 /root/.ssh
@@ -151,8 +211,10 @@ SSHKEY
 
 chmod 600 /root/.ssh/authorized_keys
 
-# Disable password authentication completely
+# Set root password from decrypted hash (for console login only)
-echo "root:*" | chpasswd -e
+ROOT_PW_HASH=$(cat /root/.pw_hash)
+echo "root:$ROOT_PW_HASH" | chpasswd -e
+rm -f /root/.pw_hash
 
 # Configure tmpfs mounts for ephemeral data
 cat >> /etc/fstab <<FSTAB
@@ -219,6 +281,45 @@ cp "$INITRAMFS_CONFIG/modules" "$BUILD_DIR/rootfs/etc/initramfs-tools/"
 cp -r "$INITRAMFS_CONFIG/hooks/"* "$BUILD_DIR/rootfs/usr/share/initramfs-tools/hooks/"
 cp -r "$INITRAMFS_CONFIG/scripts/"* "$BUILD_DIR/rootfs/usr/share/initramfs-tools/scripts/"
 
+# Install node storage setup service
+echo "Installing node storage setup service..."
+FILES_DIR="$SCRIPT_DIR/files"
+cp "$FILES_DIR/setup-node-storage" "$BUILD_DIR/rootfs/usr/local/bin/"
+chmod +x "$BUILD_DIR/rootfs/usr/local/bin/setup-node-storage"
+cp "$FILES_DIR/setup-node-storage.service" "$BUILD_DIR/rootfs/etc/systemd/system/"
+# Enable the service (create symlink manually since we can't run systemctl)
+mkdir -p "$BUILD_DIR/rootfs/etc/systemd/system/multi-user.target.wants"
+ln -sf /etc/systemd/system/setup-node-storage.service \
+    "$BUILD_DIR/rootfs/etc/systemd/system/multi-user.target.wants/setup-node-storage.service"
+
+# Install DHCP hostname service
+echo "Installing DHCP hostname service..."
+cp "$FILES_DIR/set-hostname-from-dhcp" "$BUILD_DIR/rootfs/usr/local/bin/"
+chmod +x "$BUILD_DIR/rootfs/usr/local/bin/set-hostname-from-dhcp"
+cp "$FILES_DIR/set-hostname-from-dhcp.service" "$BUILD_DIR/rootfs/etc/systemd/system/"
+ln -sf /etc/systemd/system/set-hostname-from-dhcp.service \
+    "$BUILD_DIR/rootfs/etc/systemd/system/multi-user.target.wants/set-hostname-from-dhcp.service"
+
+# Download and install K3s binary
+echo "Downloading K3s binary..."
+K3S_VERSION="v1.34.3+k3s1"
+curl -sfL "https://github.com/k3s-io/k3s/releases/download/${K3S_VERSION}/k3s" \
+    -o "$BUILD_DIR/rootfs/usr/local/bin/k3s"
+chmod +x "$BUILD_DIR/rootfs/usr/local/bin/k3s"
+echo "K3s $K3S_VERSION installed"
+
+# Install K3s agent service
+echo "Installing K3s agent service..."
+# Create K3s directories first (will be bind-mounted from NVMe at runtime)
+mkdir -p "$BUILD_DIR/rootfs/etc/rancher/k3s"
+mkdir -p "$BUILD_DIR/rootfs/etc/rancher/node"
+mkdir -p "$BUILD_DIR/rootfs/var/lib/rancher/k3s/agent"
+cp "$FILES_DIR/k3s-agent.service" "$BUILD_DIR/rootfs/etc/systemd/system/"
+cp "$FILES_DIR/k3s-agent.env" "$BUILD_DIR/rootfs/etc/rancher/k3s/"
+# Enable the service
+ln -sf /etc/systemd/system/k3s-agent.service \
+    "$BUILD_DIR/rootfs/etc/systemd/system/multi-user.target.wants/k3s-agent.service"
+
 # Build initramfs while /proc/sys/dev are still mounted
 echo "Building custom netboot initramfs..."
 KERNEL_VERSION=$(ls -1 $BUILD_DIR/rootfs/boot/vmlinuz-* | sed 's|.*/vmlinuz-||' | head -1)

files/k3s-agent.env

@@ -0,0 +1,4 @@
+# K3s agent configuration
+# Server URL and token for cluster join
+K3S_URL="https://192.168.100.1:6443"
+K3S_TOKEN="K106e2ea6914f7a019d1222c1fdd19c5065978377364701f60eb1f2a585e8c3924b::server:0a15c4d7a13df65b066f5b8eff710ecd"

files/k3s-agent.service

@@ -0,0 +1,25 @@
+[Unit]
+Description=Lightweight Kubernetes (K3s Agent)
+Documentation=https://k3s.io
+After=network-online.target setup-node-storage.service set-hostname-from-dhcp.service
+Wants=network-online.target
+Requires=setup-node-storage.service set-hostname-from-dhcp.service
+
+[Service]
+Type=notify
+EnvironmentFile=-/etc/rancher/k3s/k3s-agent.env
+ExecStartPre=/sbin/modprobe br_netfilter
+ExecStartPre=/sbin/modprobe overlay
+ExecStart=/usr/local/bin/k3s agent
+KillMode=process
+Delegate=yes
+LimitNOFILE=1048576
+LimitNPROC=infinity
+LimitCORE=infinity
+TasksMax=infinity
+TimeoutStartSec=0
+Restart=always
+RestartSec=5s
+
+[Install]
+WantedBy=multi-user.target

files/set-hostname-from-dhcp

@@ -0,0 +1,28 @@
+#!/bin/bash
+# Set hostname from DHCP lease
+# Runs before k3s-agent to ensure proper node name
+
+set -euo pipefail
+
+log() { echo "[hostname] $*"; logger -t set-hostname "$*"; }
+
+# Wait for DHCP lease
+MAX_WAIT=60
+for i in $(seq 1 $MAX_WAIT); do
+    # Check for lease files from systemd-networkd
+    for lease in /run/systemd/netif/leases/*; do
+        if [ -f "$lease" ]; then
+            HOSTNAME=$(grep -oP '^HOSTNAME=\K.*' "$lease" 2>/dev/null || true)
+            if [ -n "$HOSTNAME" ]; then
+                log "Found hostname in DHCP lease: $HOSTNAME"
+                hostnamectl set-hostname "$HOSTNAME"
+                log "Hostname set to: $(hostname)"
+                exit 0
+            fi
+        fi
+    done
+    sleep 1
+done
+
+log "Warning: No DHCP hostname found after ${MAX_WAIT}s, using default"
+exit 0

files/set-hostname-from-dhcp.service

@@ -0,0 +1,15 @@
+[Unit]
+Description=Set hostname from DHCP lease
+Documentation=file:///usr/local/bin/set-hostname-from-dhcp
+After=network-online.target systemd-networkd.service
+Wants=network-online.target
+Before=k3s-agent.service
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/set-hostname-from-dhcp
+RemainAfterExit=yes
+TimeoutStartSec=90
+
+[Install]
+WantedBy=multi-user.target

files/setup-node-storage

@@ -0,0 +1,236 @@
+#!/bin/bash
+# Setup local NVMe storage for K3s node
+# Runs at boot via systemd service
+#
+# Logic:
+# - No NVMe: exit cleanly
+# - No partition table: auto-format (new drive)
+# - Has our labels: mount and exit (already configured)
+# - Has other partitions: prompt with 120s timeout (safety)
+
+set -euo pipefail
+
+DEVICE="/dev/nvme0n1"
+CONTAINERD_SIZE="75GiB"
+CONTAINERD_LABEL="containerd"
+LONGHORN_LABEL="longhorn"
+CONTAINERD_MOUNT="/var/lib/containerd"
+LONGHORN_MOUNT="/var/lib/longhorn"
+MARKER_FILE=".netboot-storage"
+PROMPT_TIMEOUT=120
+
+# Colors for console output
+RED='\033[0;31m'
+GREEN='\033[0;32m'
+YELLOW='\033[1;33m'
+CYAN='\033[0;36m'
+NC='\033[0m'
+
+# Log to both console and journald
+log()   { echo -e "${GREEN}[storage]${NC} $*"; logger -t setup-node-storage "$*"; }
+warn()  { echo -e "${YELLOW}[storage]${NC} $*"; logger -t setup-node-storage -p warning "$*"; }
+error() { echo -e "${RED}[storage]${NC} $*"; logger -t setup-node-storage -p err "$*"; }
+
+# Check if NVMe exists
+if [ ! -b "$DEVICE" ]; then
+    log "No NVMe device found at $DEVICE - skipping storage setup"
+    exit 0
+fi
+
+DEVICE_SIZE=$(lsblk -b -d -n -o SIZE "$DEVICE" | awk '{printf "%.0fGB", $1/1000000000}')
+log "Found NVMe: $DEVICE ($DEVICE_SIZE)"
+
+# Get partition names (handles nvme naming with 'p' prefix)
+if [[ "$DEVICE" == *"nvme"* ]]; then
+    PART1="${DEVICE}p1"
+    PART2="${DEVICE}p2"
+else
+    PART1="${DEVICE}1"
+    PART2="${DEVICE}2"
+fi
+
+# Function to mount existing storage
+mount_storage() {
+    log "Mounting existing storage..."
+    
+    mkdir -p "$CONTAINERD_MOUNT" "$LONGHORN_MOUNT"
+    
+    if ! mountpoint -q "$CONTAINERD_MOUNT"; then
+        mount -L "$CONTAINERD_LABEL" "$CONTAINERD_MOUNT" || {
+            error "Failed to mount containerd partition"
+            return 1
+        }
+    fi
+    
+    if ! mountpoint -q "$LONGHORN_MOUNT"; then
+        mount -L "$LONGHORN_LABEL" "$LONGHORN_MOUNT" || {
+            error "Failed to mount longhorn partition"
+            return 1
+        }
+    fi
+    
+    # K3s persistence: bind mount agent data and node identity from NVMe
+    # This allows the node to survive reboots without re-registering
+    setup_k3s_persistence
+    
+    log "Storage mounted:"
+    log "  $CONTAINERD_MOUNT: $(df -h "$CONTAINERD_MOUNT" | tail -1 | awk '{print $2}')"
+    log "  $LONGHORN_MOUNT: $(df -h "$LONGHORN_MOUNT" | tail -1 | awk '{print $2}')"
+    return 0
+}
+
+# Setup K3s persistence directories
+# Bind mounts NVMe directories to k3s paths so node identity survives reboots
+setup_k3s_persistence() {
+    # K3s agent data (containerd, kubelet certs, etc.)
+    # Uses overlayfs internally, so must be on real filesystem, not overlay
+    K3S_AGENT="/var/lib/rancher/k3s/agent"
+    K3S_AGENT_DATA="$CONTAINERD_MOUNT/k3s-agent"
+    mkdir -p "$K3S_AGENT_DATA" "$K3S_AGENT"
+    if ! mountpoint -q "$K3S_AGENT"; then
+        mount --bind "$K3S_AGENT_DATA" "$K3S_AGENT"
+        log "  $K3S_AGENT: bind mount to NVMe"
+    fi
+    
+    # K3s node identity (password file)
+    # Must persist across reboots or node will be rejected
+    K3S_NODE="/etc/rancher/node"
+    K3S_NODE_DATA="$CONTAINERD_MOUNT/k3s-node"
+    mkdir -p "$K3S_NODE_DATA" "$K3S_NODE"
+    if ! mountpoint -q "$K3S_NODE"; then
+        mount --bind "$K3S_NODE_DATA" "$K3S_NODE"
+        log "  $K3S_NODE: bind mount to NVMe"
+    fi
+
+    # Kubelet data (pod volumes, projected tokens, etc.)
+    # Must be on NVMe so kubelet reports real disk capacity, not the 2G tmpfs overlay
+    KUBELET_DIR="/var/lib/kubelet"
+    KUBELET_DATA="$CONTAINERD_MOUNT/kubelet"
+    mkdir -p "$KUBELET_DATA" "$KUBELET_DIR"
+    if ! mountpoint -q "$KUBELET_DIR"; then
+        mount --bind "$KUBELET_DATA" "$KUBELET_DIR"
+        log "  $KUBELET_DIR: bind mount to NVMe"
+    fi
+}
+
+# Function to format the drive
+format_storage() {
+    log "Partitioning $DEVICE..."
+    
+    wipefs -af "$DEVICE"
+    parted -s "$DEVICE" mklabel gpt
+    parted -s "$DEVICE" mkpart primary ext4 1MiB "$CONTAINERD_SIZE"
+    parted -s "$DEVICE" mkpart primary ext4 "$CONTAINERD_SIZE" 100%
+    
+    # Tell kernel to re-read partition table and wait for udev
+    partprobe "$DEVICE"
+    udevadm settle --timeout=10
+    
+    # Verify partitions appeared
+    if [ ! -b "$PART1" ] || [ ! -b "$PART2" ]; then
+        error "Partitions not found after partprobe: $PART1, $PART2"
+        exit 1
+    fi
+    
+    log "Formatting ${PART1} as ext4 (containerd, 75GB)..."
+    mkfs.ext4 -L "$CONTAINERD_LABEL" -q "$PART1"
+    
+    log "Formatting ${PART2} as ext4 (longhorn, remaining)..."
+    mkfs.ext4 -L "$LONGHORN_LABEL" -q "$PART2"
+    
+    # Mount the new partitions
+    mkdir -p "$CONTAINERD_MOUNT" "$LONGHORN_MOUNT"
+    mount "$PART1" "$CONTAINERD_MOUNT"
+    mount "$PART2" "$LONGHORN_MOUNT"
+    
+    # Create marker files with metadata
+    for mount_point in "$CONTAINERD_MOUNT" "$LONGHORN_MOUNT"; do
+        cat > "${mount_point}/${MARKER_FILE}" <<EOF
+# Netboot storage marker - DO NOT DELETE
+formatted_date=$(date -Iseconds)
+formatted_by=setup-node-storage
+hostname=$(hostname)
+device=$DEVICE
+EOF
+    done
+    
+    # K3s persistence: bind mount agent data and node identity from NVMe
+    setup_k3s_persistence
+    
+    log "Storage formatted and mounted successfully"
+    log "  $CONTAINERD_MOUNT: $(df -h "$CONTAINERD_MOUNT" | tail -1 | awk '{print $2}')"
+    log "  $LONGHORN_MOUNT: $(df -h "$LONGHORN_MOUNT" | tail -1 | awk '{print $2}')"
+}
+
+# Check for partition table
+# Method 1: blkid returns empty PTTYPE for unpartitioned drives
+# Method 2: parted error message (locale-dependent fallback)
+has_partition_table() {
+    local pttype
+    pttype=$(blkid -o value -s PTTYPE "$DEVICE" 2>/dev/null)
+    if [ -n "$pttype" ]; then
+        return 0  # has partition table
+    fi
+    # Fallback: check if parted can read it
+    if parted -s "$DEVICE" print &>/dev/null; then
+        return 0  # has partition table
+    fi
+    return 1  # no partition table
+}
+
+if ! has_partition_table; then
+    # No partition table - this is a fresh drive, auto-format
+    log "Empty drive detected (no partition table) - auto-formatting..."
+    format_storage
+    exit 0
+fi
+
+# Has partition table - check if it's ours
+if blkid -L "$CONTAINERD_LABEL" &>/dev/null && blkid -L "$LONGHORN_LABEL" &>/dev/null; then
+    # Check for marker file (belt and suspenders)
+    # Create temp mount to check marker without leaving dangling mount
+    TEMP_MOUNT=$(mktemp -d)
+    if mount -L "$CONTAINERD_LABEL" "$TEMP_MOUNT" 2>/dev/null; then
+        if [ -f "${TEMP_MOUNT}/${MARKER_FILE}" ]; then
+            umount "$TEMP_MOUNT"
+            rmdir "$TEMP_MOUNT"
+            log "Storage already configured (found labels and marker)"
+            mount_storage
+            exit 0
+        else
+            umount "$TEMP_MOUNT"
+            rmdir "$TEMP_MOUNT"
+            # Has our labels but no marker - probably ours, mount it
+            warn "Found labels but no marker file - assuming configured"
+            mount_storage
+            exit 0
+        fi
+    fi
+    rmdir "$TEMP_MOUNT" 2>/dev/null || true
+fi
+
+# Has partitions but not ours - this could contain data!
+warn "NVMe has existing partitions but no netboot labels."
+warn "This drive may contain important data!"
+echo ""
+lsblk "$DEVICE"
+echo ""
+
+# Prompt on console with timeout
+echo -e "${CYAN}========================================${NC}"
+echo -e "${CYAN}  Press ENTER within ${PROMPT_TIMEOUT}s to format  ${NC}"
+echo -e "${CYAN}  Or wait to skip (safe default)        ${NC}"
+echo -e "${CYAN}========================================${NC}"
+echo ""
+
+if read -t "$PROMPT_TIMEOUT" -p "Format $DEVICE? [press ENTER to confirm] " response; then
+    echo ""
+    warn "Formatting in 5 seconds... Ctrl+C to abort"
+    sleep 5
+    format_storage
+else
+    echo ""
+    warn "Timeout - skipping storage setup (drive left untouched)"
+    warn "To format manually, reboot and press ENTER when prompted"
+    exit 0
+fi

files/setup-node-storage.service

@@ -0,0 +1,26 @@
+[Unit]
+Description=Setup local NVMe storage for K3s
+Documentation=file:///usr/local/bin/setup-node-storage
+
+# Run early, after devices are available but before container services
+After=local-fs.target systemd-udevd.service
+Before=containerd.service
+
+# Only run if not already mounted
+ConditionPathIsMountPoint=!/var/lib/containerd
+
+[Service]
+Type=oneshot
+ExecStart=/usr/local/bin/setup-node-storage
+RemainAfterExit=yes
+
+# Console access for interactive prompt
+StandardInput=tty
+TTYPath=/dev/tty1
+TTYReset=yes
+
+# Generous timeout for user interaction (3 minutes)
+TimeoutStartSec=180
+
+[Install]
+WantedBy=multi-user.target

http/boot.ipxe

@@ -1,10 +1,5 @@
 #!ipxe
-echo Booting Ubuntu Noble K3s Node via iPXE
+echo Configuring network via DHCP...
-echo Loading kernel...
+dhcp
-kernel http://192.168.100.1:8800/vmlinuz
+echo Chaining to dynamic boot script...
-echo Loading initramfs...
+chain http://192.168.100.1:8800/netboot.ipxe
-initrd http://192.168.100.1:8800/initrd-netboot.img
-echo Setting kernel arguments for HTTP root mounting
-imgargs vmlinuz initrd=initrd-netboot.img boot=netboot root=http://192.168.100.1:8800/filesystem.squashfs rootfstype=squashfs overlayroot=tmpfs ip=dhcp console=tty0 console=ttyS0,115200 loglevel=7
-echo Booting system...
-boot

initramfs/initramfs.conf

@@ -68,3 +68,6 @@ FSTYPE=auto
 
 # Disable hibernation
 RESUME=none
+
+# Use custom netboot script for HTTP root mounting
+BOOT=netboot

initramfs/scripts/netboot

@@ -1,200 +1,85 @@
 #!/bin/sh
-
+# Netboot HTTP root mounting - HARDCODED VALUES - no cmdline parsing
-# Import standard initramfs functions
-. /scripts/functions
 
 export PATH=/usr/bin:/usr/sbin:/bin:/sbin
+
+# HARDCODED CONFIGURATION
+ROOT_URL="http://192.168.100.1:8800/filesystem.squashfs"
+OVERLAYROOT="tmpfs"
 MOUNTPOINT=/root
-TMPFS_MOUNT=/mnt
+SQUASHFS_MOUNT=/mnt/squashfs
+OVERLAY_TMPFS=/mnt/overlay
 
-# Hook functions for initramfs-tools boot script integration
+# Debug logging to console
-netboot_top()
+log() {
-{
+    echo "$@" > /dev/console 2>&1
-	if [ "${netboot_top_used}" != "yes" ]; then
-		[ "$quiet" != "y" ] && log_begin_msg "Running /scripts/netboot-top"
-		run_scripts /scripts/netboot-top
-		[ "$quiet" != "y" ] && log_end_msg
-	fi
-	netboot_top_used=yes
 }
 
-netboot_premount()
+# Minimal hook functions
-{
+netboot_top() { :; }
-	if [ "${netboot_premount_used}" != "yes" ]; then
+netboot_premount() { :; }
-		[ "$quiet" != "y" ] && log_begin_msg "Running /scripts/netboot-premount"
+netboot_bottom() { :; }
-		run_scripts /scripts/netboot-premount
+mount_top() { :; }
-		[ "$quiet" != "y" ] && log_end_msg
+mount_premount() { :; }
-	fi
+mount_bottom() { :; }
-	netboot_premount_used=yes
-}
-
-netboot_bottom()
-{
-	if [ "${netboot_premount_used}" = "yes" ] || [ "${netboot_top_used}" = "yes" ]; then
-		[ "$quiet" != "y" ] && log_begin_msg "Running /scripts/netboot-bottom"
-		run_scripts /scripts/netboot-bottom
-		[ "$quiet" != "y" ] && log_end_msg
-	fi
-	netboot_premount_used=no
-	netboot_top_used=no
-}
-
-# Parse kernel command line for HTTP root
-parse_cmdline() {
-    for x in $(cat /proc/cmdline); do
-        case $x in
-            root=http://*)
-                export ROOT_URL="${x#root=}" ;;
-            rootfstype=*)
-                export ROOTFSTYPE="${x#rootfstype=}" ;;
-            overlayroot=*)
-                export OVERLAYROOT="${x#overlayroot=}" ;;
-            ip=*)
-                export BOOTIP="${x#ip=}" ;;
-            *)
-                : ;;
-        esac
-    done
-}
 
 mountroot() {
-    rc=1
+    log "NETBOOT: ========================================"
+    log "NETBOOT: mountroot() HARDCODED VERSION"
+    log "NETBOOT: ROOT_URL=${ROOT_URL}"
+    log "NETBOOT: ========================================"
 
-    # Run hook scripts
+    # Load network module
-    netboot_top
+    /sbin/modprobe af_packet
-    netboot_premount
 
-    parse_cmdline
+    # Wait for udev
-
+    wait_for_udev 10
-    if test -z "${ROOT_URL}"; then
-        log_failure_msg "No root URL defined (root=http://... not found)"
-        return ${rc}
-    fi
-
-    # Configure networking before attempting downloads
-    log_begin_msg "Configuring network"
-    modprobe af_packet || log_warning_msg "af_packet load failed"
-
-    # Load RTL8125 driver (already in module list but explicit load for debugging)
-    modprobe r8125 || log_warning_msg "r8125 driver load failed, may use generic driver"
 
+    # Configure networking via DHCP
+    log "NETBOOT: Calling configure_networking..."
     configure_networking
-    udevadm trigger
-    timeout 30 udevadm settle || log_warning_msg "udevadm settle timed out"
-    export DEVICE
-    log_end_msg
 
-    # Validate networking is up
+    # Check we got an IP
-    INTERFACE_UP=0
+    log "NETBOOT: Checking for IP address..."
-    for iface in $(ip link show | grep "^[0-9]" | awk -F: '{print $2}' | tr -d ' '); do
+    if ! ip addr show | grep -q "inet "; then
-        if ip addr show "$iface" | grep -q "inet "; then
+        log "NETBOOT: FATAL - no IP address"
-            INTERFACE_UP=1
+        return 1
-            log_begin_msg "Interface $iface has IP address"
+    fi
-            ip addr show "$iface" | grep "inet " | awk '{print $2}'
+    log "NETBOOT: Network is up"
-            break
-        fi
-    done
 
-    if [ $INTERFACE_UP -eq 0 ]; then
+    # Download squashfs
-        log_failure_msg "No network interface obtained an IP address"
+    log "NETBOOT: Downloading ${ROOT_URL}..."
-        return ${rc}
+    if ! wget -O /filesystem.squashfs "${ROOT_URL}"; then
+        log "NETBOOT: FATAL - wget failed"
+        return 1
+    fi
+    log "NETBOOT: Download complete"
+
+    # Create mount points
+    mkdir -p "${SQUASHFS_MOUNT}" "${OVERLAY_TMPFS}"
+
+    # Mount squashfs
+    log "NETBOOT: Mounting squashfs..."
+    if ! mount -t squashfs /filesystem.squashfs "${SQUASHFS_MOUNT}" -o ro; then
+        log "NETBOOT: FATAL - squashfs mount failed"
+        return 1
     fi
 
-    # Extract filename from URL
+    # Mount tmpfs for overlay
-    FILE_NAME=$(basename "${ROOT_URL}")
+    log "NETBOOT: Mounting tmpfs..."
-    FILE_PATH="/${FILE_NAME}"
+    if ! mount -t tmpfs -o size=2G tmpfs "${OVERLAY_TMPFS}"; then
+        log "NETBOOT: FATAL - tmpfs mount failed"
+        return 1
+    fi
+    mkdir -p "${OVERLAY_TMPFS}/upper" "${OVERLAY_TMPFS}/work"
 
-    # Download the root filesystem with retries and timeouts
+    # Mount overlay
-    log_begin_msg "Downloading root filesystem from ${ROOT_URL}"
+    log "NETBOOT: Mounting overlay..."
-    if wget --timeout=30 --tries=3 --waitretry=5 \
+    if ! mount -t overlay -o "lowerdir=${SQUASHFS_MOUNT},upperdir=${OVERLAY_TMPFS}/upper,workdir=${OVERLAY_TMPFS}/work" overlay "${MOUNTPOINT}"; then
-            --progress=dot:mega \
+        log "NETBOOT: FATAL - overlay mount failed"
-            "${ROOT_URL}" -O "${FILE_PATH}"; then
+        return 1
-        log_end_msg
-    else
-        log_failure_msg "Failed to download from ${ROOT_URL} after retries"
-        rm -f "${FILE_PATH}"
-        return ${rc}
     fi
 
-    # Verify the downloaded file is a valid SquashFS
+    log "NETBOOT: SUCCESS - root mounted at ${MOUNTPOINT}"
-    if ! file "${FILE_PATH}" | grep -q "Squash"; then
+    return 0
-        log_failure_msg "Downloaded file is not a valid SquashFS image"
-        rm -f "${FILE_PATH}"
-        return ${rc}
-    fi
-
-    # Handle SquashFS images with overlay
-    if echo "${FILE_NAME}" | grep -q squashfs; then
-        log_begin_msg "Setting up SquashFS with overlay"
-
-        # Mount read-only SquashFS
-        if ! mount -t squashfs "${FILE_PATH}" "${MOUNTPOINT}" -o ro; then
-            log_failure_msg "Failed to mount SquashFS at ${MOUNTPOINT}"
-            rm -f "${FILE_PATH}"
-            return ${rc}
-        fi
-        log_begin_msg "SquashFS mounted at ${MOUNTPOINT}"
-        log_end_msg
-
-        # Setup overlay if requested
-        if [ -n "${OVERLAYROOT}" ]; then
-            log_begin_msg "Mounting ${OVERLAYROOT} for overlay"
-
-            # Create tmpfs for upper and work directories
-            if ! mount -o size=2G -t "${OVERLAYROOT}" tmpfs_overlay "${TMPFS_MOUNT}"; then
-                log_failure_msg "Failed to mount tmpfs for overlay"
-                umount "${MOUNTPOINT}"
-                rm -f "${FILE_PATH}"
-                return ${rc}
-            fi
-
-            # Create overlay structure
-            mkdir -p "${TMPFS_MOUNT}/upper" "${TMPFS_MOUNT}/work"
-
-            # Mount overlay combining read-only lower + writable upper
-            if ! mount -t overlay \
-                    -o "lowerdir=${MOUNTPOINT},upperdir=${TMPFS_MOUNT}/upper,workdir=${TMPFS_MOUNT}/work" \
-                    overlay_root "${MOUNTPOINT}"; then
-                log_failure_msg "Failed to mount overlay filesystem"
-                umount "${TMPFS_MOUNT}"
-                umount "${MOUNTPOINT}"
-                rm -f "${FILE_PATH}"
-                return ${rc}
-            fi
-
-            log_end_msg
-            log_begin_msg "Overlay mounted successfully"
-            log_end_msg
-
-            # Clean up downloaded image as it's now mounted
-            rm -f "${FILE_PATH}"
-            rc=0
-        else
-            # Direct SquashFS mount without overlay
-            log_begin_msg "Mounted SquashFS without overlay"
-            log_end_msg
-            rc=0
-        fi
-    else
-        log_failure_msg "Unknown filesystem type: ${FILE_NAME}"
-        rm -f "${FILE_PATH}"
-    fi
-
-    return ${rc}
-}
-
-# Standard mount hook wrappers expected by initramfs init
-mount_top()
-{
-	netboot_top
-}
-
-mount_premount()
-{
-	netboot_premount
-}
-
-mount_bottom()
-{
-	netboot_bottom
 }

rebuild-initramfs.sh

@@ -0,0 +1,51 @@
+#!/bin/bash
+# Rebuild initramfs with updated netboot script
+set -e
+
+SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+BUILD_DIR="$SCRIPT_DIR/build"
+ROOTFS="$BUILD_DIR/rootfs"
+HTTP_DIR="$SCRIPT_DIR/http"
+
+if [ ! -d "$ROOTFS" ]; then
+    echo "ERROR: Rootfs not found at $ROOTFS"
+    echo "Run build-image.sh first"
+    exit 1
+fi
+
+echo "=== Copying updated initramfs scripts ==="
+cp "$SCRIPT_DIR/initramfs/scripts/netboot" "$ROOTFS/usr/share/initramfs-tools/scripts/netboot"
+cp "$SCRIPT_DIR/initramfs/hooks/netboot" "$ROOTFS/usr/share/initramfs-tools/hooks/netboot"
+cp "$SCRIPT_DIR/initramfs/initramfs.conf" "$ROOTFS/etc/initramfs-tools/initramfs.conf"
+cp "$SCRIPT_DIR/initramfs/modules" "$ROOTFS/etc/initramfs-tools/modules"
+
+echo "=== Getting kernel version ==="
+KVER=$(ls "$ROOTFS/lib/modules/" | head -1)
+echo "Kernel version: $KVER"
+
+echo "=== Mounting filesystems for chroot ==="
+mount --bind /proc "$ROOTFS/proc"
+mount --bind /sys "$ROOTFS/sys"
+mount --bind /dev "$ROOTFS/dev"
+
+cleanup() {
+    echo "=== Cleaning up mounts ==="
+    umount "$ROOTFS/proc" 2>/dev/null || true
+    umount "$ROOTFS/sys" 2>/dev/null || true
+    umount "$ROOTFS/dev" 2>/dev/null || true
+}
+trap cleanup EXIT
+
+echo "=== Rebuilding initramfs ==="
+chroot "$ROOTFS" mkinitramfs -v -o /boot/initrd-netboot.img "$KVER"
+
+echo "=== Copying to http directory ==="
+cp "$ROOTFS/boot/initrd-netboot.img" "$HTTP_DIR/"
+chmod 644 "$HTTP_DIR/initrd-netboot.img"
+
+echo ""
+echo "=== Done! ==="
+echo "New initramfs: $HTTP_DIR/initrd-netboot.img"
+ls -lh "$HTTP_DIR/initrd-netboot.img"
+echo ""
+echo "Run 'make deploy' to sync to NAS"

secrets/netboot.sops.yaml

@@ -0,0 +1,16 @@
+root_password_hash: ENC[AES256_GCM,data:Oc1Kpg1S3NSG4dDoe0AiDmdWe4wdz9zSMn/WlTvURz3u62HcF9ddZh3yKbsXdc19WbGj/ZJa+MFzucgCg6ChT5OG2k4S+JuAVvRaNmB54XSjyIL2vDkambq8Pt4rg5rVxfv5H6uEd5IWUg==,iv:fO72qW/8JIWGubbfjZYsfhjL3XUq/7RbohGPd1avS+8=,tag:nXP7w2b49iYAcnWxM4WFlA==,type:str]
+sops:
+    age:
+        - recipient: age1gausnystsln7fpenw7arw7x79xe22z697jnauj38npy0usayqqxqc7td2y
+          enc: |
+            -----BEGIN AGE ENCRYPTED FILE-----
+            YWdlLWVuY3J5cHRpb24ub3JnL3YxCi0+IFgyNTUxOSBDS1VrWkNZTmswYlRrVXAv
+            ZC9FemRVWkc2bzlVL1BuQm9FaDlPVmVuVFZvCnUyb2xnaDdwQ3BsVkNmY0NxZktp
+            Zk9qSlZVZk16UUhhOHdGRFN1Zno1V3cKLS0tIHV6YXE1bFBHZjMyVVdMbVZEMXlW
+            YTN1RnJ3SjRkN21MYmhQK0hZZFB5Sk0KfxfMPUdJjZq/JDOE87oD2XBpQebvy0a5
+            IAI5tdpEzNP6tF4oqunmh15fPc61Q0C/5ev+uz0QyHhTlTI13lYpGg==
+            -----END AGE ENCRYPTED FILE-----
+    lastmodified: "2026-02-05T20:16:15Z"
+    mac: ENC[AES256_GCM,data:mTCLM3t35mMv9nLQHba65Gq3yAWnY4UKUDHEncMF22RnZKiVDaTMAV6tiaKGu7hHXdDu9fU/E7wPomR8pirGf6pJBUWxCflCe3Q3ZGK9/Aw3guz5ZD34H9nMaCjXME59r1rQdQdQlWP5aW4o+kqfD/bukFpW1HUY0YT8g8fqCpw=,iv:bG1M8Ghuc8JkMNQfODZ1FkMI/8Qs217xlN5ihDnz7hs=,tag:gCScQi1YYXFH4Xo/8Wq5+g==,type:str]
+    unencrypted_suffix: _unencrypted
+    version: 3.11.0