misc/mdcheck

#!/bin/bash

# Copyright (C) 2014-2017 Neil Brown <neilb@suse.de>
#
#
#    This program is free software; you can redistribute it and/or modify
#    it under the terms of the GNU General Public License as published by
#    the Free Software Foundation; either version 2 of the License, or
#    (at your option) any later version.
#
#    This program is distributed in the hope that it will be useful,
#    but WITHOUT ANY WARRANTY; without even the implied warranty of
#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
#    GNU General Public License for more details.
#
#    Author: Neil Brown
#    Email: <neilb@suse.com>

# This script should be run periodically to automatically
# perform a 'check' on any md arrays.
#
# It supports a 'time budget' such that any incomplete 'check'
# will be checkpointed when that time has expired.
# A subsequent invocation can allow the 'check' to continue.
#
# Options are:
#   --continue    Don't start new checks, only continue old ones.
#   --duration    This is passed to "date --date=$duration" to find out
#		  when to finish
#
# To support '--continue', arrays are identified by UUID and the 'sync_completed'
# value is stored  in /var/lib/mdcheck/$UUID

# convert a /dev/md name into /sys/.../md equivalent
sysname() {
	set `ls -lLd $1`
	maj=${5%,}
	min=$6
	readlink -f /sys/dev/block/$maj:$min
}

args=$(getopt -o hcd: -l help,continue,duration: -n mdcheck -- "$@")
rv=$?
if [ $rv -ne 0 ]; then exit $rv; fi

eval set -- $args

cont=
endtime=
while [ " $1" != " --" ]
do
    case $1 in
	--help )
		echo >&2 'Usage: mdcheck [--continue] [--duration time-offset]'
		echo >&2 '  time-offset must be understood by "date --date"'
		exit 0
		;;
	--continue ) cont=yes ;;
	--duration ) shift; dur=$1
		endtime=$(date --date "$dur" "+%s")
		;;
    esac
    shift
done
shift

# We need a temp file occasionally...
tmp=/var/lib/mdcheck/.md-check-$$
trap 'rm -f "$tmp"' 0 2 3 15


# firstly, clean out really old state files
mkdir -p /var/lib/mdcheck
find /var/lib/mdcheck -name "MD_UUID*" -type f -mtime +180 -exec rm {} \;

# Now look at each md device.
cnt=0
for dev in /dev/md?*
do
	[ -e "$dev" ] || continue
	sys=`sysname $dev`
	if [ ! -f "$sys/md/sync_action" ]
	then # cannot check this array
		continue
	fi
	if [ "`cat $sys/md/sync_action`" != 'idle' ]
	then # This array is busy
		continue
	fi

	mdadm --detail --export "$dev" | grep '^MD_UUID=' > $tmp || continue
	source $tmp
	fl="/var/lib/mdcheck/MD_UUID_$MD_UUID"
	if [ -z "$cont" ]
	then
		start=0
		logger -p daemon.info mdcheck start checking $dev
	elif [ -z "$MD_UUID" -o ! -f "$fl" ]
	then
		# Nothing to continue here
		continue
	else
		start=`cat "$fl"`
		logger -p daemon.info mdcheck continue checking $dev from $start
	fi

	cnt=$[cnt+1]
	eval MD_${cnt}_fl=\$fl
	eval MD_${cnt}_sys=\$sys
	eval MD_${cnt}_dev=\$dev
	echo $start > $fl
	echo $start > $sys/md/sync_min
	echo check > $sys/md/sync_action
done

if [ -z "$endtime" ]
then
	exit 0
fi

while [ `date +%s` -lt $endtime ]
do
	any=
	for i in `eval echo {1..$cnt}`
	do
		eval fl=\$MD_${i}_fl
		eval sys=\$MD_${i}_sys
		eval dev=\$MD_${i}_dev

		if [ -z "$fl" ]; then continue; fi

		if [ "`cat $sys/md/sync_action`" != 'check' ]
		then
			logger -p daemon.info mdcheck finished checking $dev
			eval MD_${i}_fl=
			rm -f $fl
			continue;
		fi
		read a rest < $sys/md/sync_completed
		echo $a > $fl
		any=yes
	done
	if [ -z "$any" ]; then exit 0; fi
	sleep 120
done

# We've waited, and there are still checks running.
# Time to stop them.
for i in `eval echo {1..$cnt}`
do
	eval fl=\$MD_${i}_fl
	eval sys=\$MD_${i}_sys
	eval dev=\$MD_${i}_dev

	if [ -z "$fl" ]; then continue; fi

	if [ "`cat $sys/md/sync_action`" != 'check' ]
	then
		eval MD_${i}_fl=
		rm -f $fl
		continue;
	fi
	echo idle > $sys/md/sync_action
	cat $sys/md/sync_min > $fl
	logger -p daemon.info pause checking $dev at `cat $fl`
done