Files
kubesolo-os/build/scripts/create-disk-image.sh
Adolfo Delorenzo 8d25e1890e feat: add A/B partition updates with GRUB and Go update agent (Phase 3)
Implement atomic OS updates via A/B partition scheme with automatic
rollback. GRUB bootloader manages slot selection with a 3-attempt
boot counter that auto-rolls back on repeated health check failures.

GRUB boot config:
- A/B slot selection with boot_counter/boot_success env vars
- Automatic rollback when counter reaches 0 (3 failed boots)
- Debug, emergency shell, and manual slot-switch menu entries

Disk image (refactored):
- 4-partition GPT layout: EFI + System A + System B + Data
- GRUB EFI/BIOS installation with graceful fallbacks
- Both system partitions populated during image creation

Update agent (Go, zero external deps):
- pkg/grubenv: read/write GRUB env vars (grub-editenv + manual fallback)
- pkg/partition: find/mount/write system partitions by label
- pkg/image: HTTP download with SHA256 verification
- pkg/health: post-boot checks (containerd, API server, node Ready)
- 6 CLI commands: check, apply, activate, rollback, healthcheck, status
- 37 unit tests across all 4 packages

Deployment:
- K8s CronJob for automatic update checks (every 6 hours)
- ConfigMap for update server URL
- Health check Job for post-boot verification

Build pipeline:
- build-update-agent.sh compiles static Linux binary (~5.9 MB)
- inject-kubesolo.sh includes update agent in initramfs
- Makefile: build-update-agent, test-update-agent, test-update targets

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-11 11:12:46 -06:00

191 lines
6.5 KiB
Bash
Executable File

#!/bin/bash
# create-disk-image.sh — Create a raw disk image with A/B system partitions
#
# Partition layout (GPT):
# Part 1: EFI/Boot (256 MB, FAT32) — GRUB + grubenv + A/B boot logic
# Part 2: System A (512 MB, ext4) — vmlinuz + kubesolo-os.gz (active)
# Part 3: System B (512 MB, ext4) — vmlinuz + kubesolo-os.gz (passive)
# Part 4: Data (remaining, ext4) — persistent K8s state
set -euo pipefail
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
PROJECT_ROOT="$(cd "$SCRIPT_DIR/../.." && pwd)"
ROOTFS_DIR="${ROOTFS_DIR:-$PROJECT_ROOT/build/rootfs-work}"
OUTPUT_DIR="${OUTPUT_DIR:-$PROJECT_ROOT/output}"
VERSION="$(cat "$PROJECT_ROOT/VERSION")"
OS_NAME="kubesolo-os"
IMG_OUTPUT="$OUTPUT_DIR/${OS_NAME}-${VERSION}.img"
IMG_SIZE_MB="${IMG_SIZE_MB:-4096}" # 4 GB default (larger for A/B)
VMLINUZ="$ROOTFS_DIR/vmlinuz"
INITRAMFS="$ROOTFS_DIR/kubesolo-os.gz"
GRUB_CFG="$PROJECT_ROOT/build/grub/grub.cfg"
GRUB_ENV_DEFAULTS="$PROJECT_ROOT/build/grub/grub-env-defaults"
for f in "$VMLINUZ" "$INITRAMFS" "$GRUB_CFG" "$GRUB_ENV_DEFAULTS"; do
[ -f "$f" ] || { echo "ERROR: Missing $f"; exit 1; }
done
echo "==> Creating ${IMG_SIZE_MB}MB disk image with A/B partitions..."
mkdir -p "$OUTPUT_DIR"
# Create sparse image
dd if=/dev/zero of="$IMG_OUTPUT" bs=1M count=0 seek="$IMG_SIZE_MB" 2>/dev/null
# Partition (GPT):
# Part 1: 256 MB EFI System Partition (FAT32)
# Part 2: 512 MB System A (Linux filesystem)
# Part 3: 512 MB System B (Linux filesystem)
# Part 4: Remaining — Data (Linux filesystem)
sfdisk "$IMG_OUTPUT" << EOF
label: gpt
# EFI/Boot partition: 256 MB
start=2048, size=524288, type=C12A7328-F81F-11D2-BA4B-00A0C93EC93B, name="EFI"
# System A partition: 512 MB
size=1048576, type=0FC63DAF-8483-4772-8E79-3D69D8477DE4, name="SystemA"
# System B partition: 512 MB
size=1048576, type=0FC63DAF-8483-4772-8E79-3D69D8477DE4, name="SystemB"
# Data partition: remaining
type=0FC63DAF-8483-4772-8E79-3D69D8477DE4, name="Data"
EOF
# Set up loop device
LOOP=$(losetup --show -fP "$IMG_OUTPUT")
echo "==> Loop device: $LOOP"
MNT_EFI=$(mktemp -d)
MNT_SYSA=$(mktemp -d)
MNT_SYSB=$(mktemp -d)
MNT_DATA=$(mktemp -d)
cleanup() {
umount "$MNT_EFI" 2>/dev/null || true
umount "$MNT_SYSA" 2>/dev/null || true
umount "$MNT_SYSB" 2>/dev/null || true
umount "$MNT_DATA" 2>/dev/null || true
losetup -d "$LOOP" 2>/dev/null || true
rm -rf "$MNT_EFI" "$MNT_SYSA" "$MNT_SYSB" "$MNT_DATA" 2>/dev/null || true
}
trap cleanup EXIT
# Format partitions
mkfs.vfat -F 32 -n KSOLOEFI "${LOOP}p1"
mkfs.ext4 -q -L KSOLOA "${LOOP}p2"
mkfs.ext4 -q -L KSOLOB "${LOOP}p3"
mkfs.ext4 -q -L KSOLODATA "${LOOP}p4"
# Mount all partitions
mount "${LOOP}p1" "$MNT_EFI"
mount "${LOOP}p2" "$MNT_SYSA"
mount "${LOOP}p3" "$MNT_SYSB"
mount "${LOOP}p4" "$MNT_DATA"
# --- EFI/Boot Partition ---
echo " Installing GRUB..."
mkdir -p "$MNT_EFI/EFI/BOOT"
mkdir -p "$MNT_EFI/boot/grub"
# Copy GRUB config
cp "$GRUB_CFG" "$MNT_EFI/boot/grub/grub.cfg"
# Create GRUB environment file from defaults
if command -v grub-editenv >/dev/null 2>&1; then
GRUB_EDITENV=grub-editenv
elif command -v grub2-editenv >/dev/null 2>&1; then
GRUB_EDITENV=grub2-editenv
else
GRUB_EDITENV=""
fi
GRUBENV_FILE="$MNT_EFI/boot/grub/grubenv"
if [ -n "$GRUB_EDITENV" ]; then
# Create grubenv with defaults
"$GRUB_EDITENV" "$GRUBENV_FILE" create
while IFS='=' read -r key value; do
# Skip comments and empty lines
case "$key" in
'#'*|'') continue ;;
esac
"$GRUB_EDITENV" "$GRUBENV_FILE" set "$key=$value"
done < "$GRUB_ENV_DEFAULTS"
echo " GRUB environment created with grub-editenv"
else
# Fallback: write grubenv file manually (1024 bytes, padded with '#')
echo " WARN: grub-editenv not found — writing grubenv manually"
{
echo "# GRUB Environment Block"
while IFS='=' read -r key value; do
case "$key" in
'#'*|'') continue ;;
esac
echo "$key=$value"
done < "$GRUB_ENV_DEFAULTS"
} > "$GRUBENV_FILE.tmp"
# Pad to 1024 bytes (GRUB requirement)
truncate -s 1024 "$GRUBENV_FILE.tmp"
mv "$GRUBENV_FILE.tmp" "$GRUBENV_FILE"
fi
# Install GRUB EFI binary if available
if command -v grub-mkimage >/dev/null 2>&1; then
grub-mkimage -O x86_64-efi -o "$MNT_EFI/EFI/BOOT/bootx64.efi" \
-p /boot/grub \
part_gpt ext2 fat normal linux echo all_video test search \
search_fs_uuid search_label configfile loadenv \
2>/dev/null || echo " WARN: grub-mkimage failed — use QEMU -bios flag"
elif command -v grub2-mkimage >/dev/null 2>&1; then
grub2-mkimage -O x86_64-efi -o "$MNT_EFI/EFI/BOOT/bootx64.efi" \
-p /boot/grub \
part_gpt ext2 fat normal linux echo all_video test search \
search_fs_uuid search_label configfile loadenv \
2>/dev/null || echo " WARN: grub2-mkimage failed — use QEMU -bios flag"
else
echo " WARN: grub-mkimage not found — EFI boot image not created"
echo " Install grub2-tools or use QEMU -kernel/-initrd flags"
fi
# For BIOS boot: install GRUB i386-pc modules if available
if command -v grub-install >/dev/null 2>&1; then
grub-install --target=i386-pc --boot-directory="$MNT_EFI/boot" \
--no-floppy "$LOOP" 2>/dev/null || {
echo " WARN: BIOS GRUB install failed — EFI-only or use QEMU -kernel"
}
elif command -v grub2-install >/dev/null 2>&1; then
grub2-install --target=i386-pc --boot-directory="$MNT_EFI/boot" \
--no-floppy "$LOOP" 2>/dev/null || {
echo " WARN: BIOS GRUB install failed — EFI-only or use QEMU -kernel"
}
fi
# --- System A Partition (active) ---
echo " Populating System A (active)..."
cp "$VMLINUZ" "$MNT_SYSA/vmlinuz"
cp "$INITRAMFS" "$MNT_SYSA/kubesolo-os.gz"
echo "$VERSION" > "$MNT_SYSA/version"
# --- System B Partition (passive, initially same as A) ---
echo " Populating System B (passive)..."
cp "$VMLINUZ" "$MNT_SYSB/vmlinuz"
cp "$INITRAMFS" "$MNT_SYSB/kubesolo-os.gz"
echo "$VERSION" > "$MNT_SYSB/version"
# --- Data Partition ---
echo " Preparing data partition..."
for dir in kubesolo containerd etc-kubesolo log usr-local network images; do
mkdir -p "$MNT_DATA/$dir"
done
sync
echo ""
echo "==> Disk image created: $IMG_OUTPUT"
echo " Size: $(du -h "$IMG_OUTPUT" | cut -f1)"
echo " Part 1 (KSOLOEFI): GRUB + A/B boot config"
echo " Part 2 (KSOLOA): System A — kernel + initramfs (active)"
echo " Part 3 (KSOLOB): System B — kernel + initramfs (passive)"
echo " Part 4 (KSOLODATA): Persistent K8s state"
echo ""