andreasandClaude Haiku 4.5
565e8f31ab
Problem: R5C spontaneously rebooted due to hardware watchdog timeout Cause 1: van-gps-owntracks in infinite restart loop (MQTT connect failed) Cause 2: mosquitto only listening on localhost, so clients couldn't connect Solution: - Add restart limits to van-gps-owntracks and van-li3-battery services (max 3 restarts per 5 minutes prevents infinite restart loops) - Configure mosquitto to listen on all interfaces (0.0.0.0:1883) - Deploy mosquitto listener config via deploy.sh - Restart mosquitto during deploy to apply config changes This prevents the system from hitting the 11-second hardware watchdog timeout when services crash and systemd auto-restarts them indefinitely. Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
69 lines
2.3 KiB
Bash
Executable File
69 lines
2.3 KiB
Bash
Executable File
#!/usr/bin/env bash
|
|
# Refresh the USB disk (sda) as a live boot-fallback clone of the
|
|
# running root filesystem. Run manually after a push:
|
|
# sudo ./failover/sync-usb-backup.sh
|
|
#
|
|
# EEPROM BOOT_ORDER falls back to the SD card, then this USB disk, if the
|
|
# primary boot disk (NVMe) doesn't come up. /etc/fstab, /etc/machine-id,
|
|
# and /var/log are excluded from the sync so the clone keeps its own
|
|
# partition identity (PARTUUIDs differ per disk) and boot/journal history
|
|
# instead of inheriting the source disk's — see failover/README or repo
|
|
# memory "sd-fallback-fstab-clobber" for what breaks if those leak across.
|
|
set -euo pipefail
|
|
|
|
[ "$(id -u)" -eq 0 ] || { echo "Run as root (sudo)." >&2; exit 1; }
|
|
|
|
USB_ROOT_PART=/dev/sda2
|
|
MOUNT_POINT=/mnt/usb-backup-root
|
|
MOUNT_POINT=10.42.1.44:/media/andreas/writable-nvme
|
|
|
|
|
|
[[ "$MOUNT_POINT" == *":"* ]]
|
|
LOCAL_MOUNT=$?
|
|
|
|
root_src=$(findmnt -no SOURCE /)
|
|
if [ "$root_src" = "$USB_ROOT_PART" ]; then
|
|
echo "Currently booted from $USB_ROOT_PART — refusing to sync USB onto itself." >&2
|
|
exit 1
|
|
fi
|
|
|
|
if [ $LOCAL_MOUNT -eq 1 ]; then
|
|
mkdir -p "$MOUNT_POINT"
|
|
mounted_here=0
|
|
if ! mountpoint -q "$MOUNT_POINT"; then
|
|
mount "$USB_ROOT_PART" "$MOUNT_POINT"
|
|
mounted_here=1
|
|
else
|
|
mount -o remount,rw "$MOUNT_POINT"
|
|
fi
|
|
|
|
cleanup() {
|
|
if [ "$mounted_here" -eq 1 ]; then
|
|
umount "$MOUNT_POINT"
|
|
fi
|
|
}
|
|
trap cleanup EXIT
|
|
fi
|
|
|
|
# rsync exit 24 ("partial transfer due to vanished source files") is expected on a
|
|
# live root — files like container shm sockets or in-progress logs routinely disappear
|
|
# mid-sync. Tolerate that one code; anything else is a real failure and still aborts.
|
|
rc=0
|
|
rsync -aHAX --numeric-ids --delete \
|
|
--info=progress2 \
|
|
--exclude=/proc/* --exclude=/sys/* --exclude=/dev/* --exclude=/run/* \
|
|
--exclude=/tmp/* --exclude=/mnt/* --exclude=/media/* --exclude=/lost+found \
|
|
--exclude=/boot/firmware/* --exclude=/swapfile \
|
|
--exclude=/etc/fstab --exclude=/etc/machine-id --exclude=/var/log/* \
|
|
--stats / "$MOUNT_POINT/" || rc=$?
|
|
|
|
if [ "$rc" -ne 0 ] && [ "$rc" -ne 24 ]; then
|
|
echo "rsync failed (exit $rc)." >&2
|
|
exit "$rc"
|
|
fi
|
|
if [ "$rc" -eq 24 ]; then
|
|
echo "Note: some files vanished mid-sync (rsync exit 24) — normal on a live root." >&2
|
|
fi
|
|
|
|
echo "USB backup ($USB_ROOT_PART) synced from $root_src."
|