#!/bin/sh
#
# lvcheck

# Released under the GNU General Public License, either version 2 or
#  (at your option) any later version.

# Overview:
#
#  Run this from cron each night.  If the machine is on AC power, it
#  will run the checks; otherwise they will all be skipped.  (If the
#  script can't tell whether the machine is on AC power, a setting in
#  the configuration file (/etc/lvcheck.conf) decides whether it will
#  continue with the checks, or abort.)
#
#  The script will then decide which logical volumes are active, and
#  can therefore be checked via an LVM snapshot.  Each of these LVs
#  will be queried to find its last-check day, and if that was more
#  than $INTERVAL days ago (where INTERVAL is set in the configuration
#  file as well), then the script will take an LVM snapshot of that
#  LV and run fsck on the snapshot.  The snapshot will be set to use
#  all the remaining space in its volume group.  After fsck finishes,
#  the snapshot is destroyed.  (Snapshots are checked serially.)
#
#  Any LV that passes fsck will have its last-check time updated (in
#  the real superblock, not the snapshot's superblock); any LV whose
#  fsck fails will send an email notification to a configurable user
#  ($EMAIL).  This $EMAIL setting is optional, but its use is highly
#  recommended, since if any LV fails, it will need to be checked
#  manually, offline.

function on_ac_power() {
	local any_known=no

	# try sysfs power class first
	if [ -d /sys/class/power_supply ] ; then
		for psu in /sys/class/power_supply/* ; do
			if [ -r "${psu}/type" ] ; then
				type="`cat "${psu}/type"`"

				# ignore batteries
				[ "${type}" = "Battery" ] && continue

				online="`cat "${psu}/online"`"

				[ "${online}" = 1 ] && return 0
				[ "${online}" = 0 ] && any_known=yes
			fi
		done

		[ "${any_known}" = "yes" ] && return 1
	fi

	# else fall back to AC adapters in /proc
	if [ -d /proc/acpi/ac_adapter ] ; then
		for ac in /proc/acpi/ac_adapter/* ; do
			if [ -r "${ac}/state" ] ; then
				grep -q on-line "${ac}/state" && return 0
				grep -q off-line "${ac}/state" && any_known=yes
			elif [ -r "${ac}/status" ] ; then
				grep -q on-line "${ac}/status" && return 0
				grep -q off-line "${ac}/status" && any_known=yes
			fi
		done

		[ "${any_known}" = "yes" ] && return 1
	fi

	if [ "$AC_UNKNOWN" == "CONTINUE" ] ; then
		return 0   # assume on AC power
	elif [ "$AC_UNKNOWN" == "ABORT" ] ; then
		return 1   # assume on battery
	else
		echo "Invalid value for AC_UNKNOWN in the config file" >&2
		exit 1
	fi
}

# attempt to force a check of $1 on the next reboot
function try_force_check() {
	local dev="$1"
	local fstype="$2"

	case "$fstype" in
		ext2|ext3)
		tune2fs -C 16000 -T "19000101" "$dev"
		;;
		reiserfs)
		# ???
		echo "Don't know how to set the last-check time on reiserfs..." >&2
		;;
		*)
		echo "Don't know how to set the last-check time on $fstype..." >&2
		;;
	esac
}

# attempt to set the last-check time on $1 to now, and the mount count to 0.
function try_delay_checks() {
	local dev="$1"
	local fstype="$2"

	case "$fstype" in
		ext2|ext3)
		tune2fs -C 0 -T now "$dev"
		;;
		reiserfs)
		# do nothing?  apparently so...
		;;
		*)
		echo "Don't know how to reset the last-check time on $fstype..." >&2
		;;
	esac
}

# print the date that $1 was last checked, in a format that date(1) will
#  accept, or "Unknown" if we don't know how to find that date.
function try_get_check_date() {
	local dev="$1"
	local fstype="$2"

	case "$fstype" in
		ext2|ext3)
		dumpe2fs -h "$dev" 2>/dev/null | grep 'Last checked:' | \
			sed -e 's/Last checked:[[:space:]]*//'
		;;
		*)
		# TODO: add support for various FSes here
		echo "Unknown"
		;;
	esac
}

# check the FS on $1 passively, printing output to $3.
function perform_check() {
	local dev="$1"
	local fstype="$2"
	local tmpfile="$3"

	case "$fstype" in
		ext2|ext3)
		# the only point in fixing anything is just to see if fsck can.
		nice logsave -as "${tmpfile}" fsck.${fstype} -p -C 0 "$dev" &&
			nice logsave -as "${tmpfile}" fsck.${fstype} -fy -C 0 "$dev"
		return $?
		;;
		reiserfs)
		echo Yes | nice logsave -as "${tmpfile}" fsck.reiserfs --check "$dev"
		# apparently can't fail?  let's hope not...
		return 0
		;;
		*)
		echo "Don't know how to check $fstype filesystems passively..." >&2
		;;
	esac
}

# do everything needed to check and reset dates and counters on /dev/$1/$2.
function check_fs() {
	local vg="$1"
	local lv="$2"
	local fstype="$3"

	local tmpfile=`mktemp -t e2fsck.log.XXXXXXXXXX`
	trap "rm $tmpfile ; trap - RETURN" RETURN

	# only one check happens at a time; using all the free space in the VG
	#  at least won't prevent other checks from happening...
	lvcreate -s -l "100%FREE" -n "${lv}-snap" "${vg}/${lv}"

	if perform_check "/dev/${vg}/${lv}-snap" "${fstype}" "${tmpfile}" ; then
		echo 'Background scrubbing succeeded!'
		try_delay_checks "/dev/${vg}/${lv}" "$fstype"
	else
		echo 'Background scrubbing failed! Reboot to fsck soon!'
		try_force_check "/dev/${vg}/${lv}" "$fstype"

		if test -n "$EMAIL"; then
			mail -s "Fsck of /dev/${vg}/${lv} failed!" $EMAIL < $tmpfile
		fi
	fi

	lvremove -f "${vg}/${lv}-snap"
}

set -e

# pull in configuration -- don't bother with a parser, just use the shell's
. /etc/lvcheck.conf

# check whether the machine is on AC power: if not, skip fsck
on_ac_power || exit 0

# parse up lvscan output
lvscan 2>&1 | grep ACTIVE | awk '{print $2;}' | \
while read DEV ; do
	# remove the single quotes around the device name
	DEV="`echo "$DEV" | tr -d \'`"

	# get the FS type
	FSTYPE="`/lib/udev/vol_id -t "$DEV"`"

	# get the last-check time, throw away the time portion, and
	#  add $INTERVAL days
	check_date=`try_get_check_date "$DEV" "$FSTYPE"`

	# if the date is unknown, run fsck every day.  sigh.
	if [ "$check_date" != "Unknown" ] ; then
		check_day=`date --date="$check_date $INTERVAL days" +'%Y%m%d'`

		# get today's date, and skip the check if it's not within the interval
		today=`date +'%Y%m%d'`
		[ $check_day -gt $today ] && continue
	fi

	# get the free space
	SPACE="`lvs --noheadings -o vg_free "$DEV"`"

	# ensure that some free space exists, at least
	#  ??? -- can lvs print vg_free in plain numbers, or do I have to
	#  figure out what a suffix of "m" means?  skip the check for now.

	# get the volume group and logical volume names
	VG="`lvs --noheadings -o vg_name "$DEV"`"
	LV="`lvs --noheadings -o lv_name "$DEV"`"

	# check it
	check_fs "$VG" "$LV" "$FSTYPE"
done