> The main issue which all proposed solutions share is when
> there's a large array, say, md0, and a small array, say,
> md1, both shares the same set of underlying disks, so md
> subystem will not check/repair them in parallel. In this
> situation, we will never check md1 if checking md0 takes
> more time than we allow in a month (28 days).
What do you think about suggested above solution
(set sync_force_parallel to 1 during cronjobs)? This workaround
is implemented in the updated (attached) patch.
See also: http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=556610#74
BTW, how bad is in general to set
sync_force_parallel to 1 per default? (Cc'd to Neil Brown.)
I think, it would be nice to end (not pause) check if it's reached
sync_max. Perhaps, there is deep reasons why md's interface
doesn't work in this way. Neil, could you explan this a bit?
> I'll think about it all more.
Any news?
--- /etc/cron.d/mdadm.orig 2013-12-25 19:00:14.000000000 +0400
+++ /etc/cron.d/mdadm 2013-12-25 19:01:50.000000000 +0400
@@ -5,8 +5,7 @@
# distributed under the terms of the Artistic Licence 2.0
#
-# By default, run at 00:57 on every Sunday, but do nothing unless the day of
-# the month is less than or equal to 7. Thus, only run on the first Sunday of
-# each month. crontab(5) sucks, unfortunately, in this regard; therefore this
-# hack (see #380425).
-57 0 * * 0 root if [ -x /usr/share/mdadm/checkarray ] && [ $(date +\%d) -le 7 ]; then /usr/share/mdadm/checkarray --cron --all --idle --quiet; fi
+# By default, start (or continue unfinished checks) at 00:57
+# and stop (interrupt) checks at 01:57.
+57 0 * * * root [ -x /usr/share/mdadm/checkarray ] && /usr/share/mdadm/checkarray --cron --all --idle --quiet
+57 1 * * * root [ -x /usr/share/mdadm/checkarray ] && /usr/share/mdadm/checkarray --cron --all --idle --quiet --interrupt
--- /usr/share/mdadm/checkarray.orig 2013-01-24 17:26:51.000000000 +0400
+++ /usr/share/mdadm/checkarray 2013-12-25 18:58:56.000000000 +0400
@@ -27,10 +27,12 @@
-a|--all check all assembled arrays (ignores arrays in command line).
-s|--status print redundancy check status of devices.
-x|--cancel queue a request to cancel a running redundancy check.
+ --interrupt queue a request to interrupt a running redundancy check.
-i|--idle perform check in a lowest scheduling class (idle)
-l|--slow perform check in a lower-than-standard scheduling class
-f|--fast perform check in higher-than-standard scheduling class
--realtime perform check in real-time scheduling class (DANGEROUS!)
+ --split n check next 1/n'th part (n <= 28) of every specified device (override CHECK_SPLIT)
-c|--cron honour AUTOCHECK setting in /etc/default/mdadm.
-q|--quiet suppress informational messages
(use twice to suppress error messages too).
@@ -50,7 +52,7 @@
}
SHORTOPTS=achVqQsxilf
-LONGOPTS=all,cron,help,version,quiet,real-quiet,status,cancel,idle,slow,fast,realtime
+LONGOPTS=all,cron,help,version,quiet,real-quiet,status,cancel,interrupt,idle,slow,fast,realtime,split:
eval set -- $(getopt -o $SHORTOPTS -l $LONGOPTS -n $PROGNAME -- "$@")
@@ -62,20 +64,31 @@
action=check
ionice=
-for opt in $@; do
- case "$opt" in
- -a|--all) all=1;;
- -s|--status) action=status;;
- -x|--cancel) action=idle;;
- -i|--idle) ionice=idle;;
- -l|--slow) ionice=low;;
- -f|--fast) ionice=high;;
- --realtime) ionice=realtime;;
- -c|--cron) cron=1;;
- -q|--quiet) quiet=$(($quiet+1));;
- -Q|--real-quiet) quiet=$(($quiet+2));; # for compatibility
+while true
+do
+ case "$1" in
+ -a|--all) all=1; shift;;
+ -s|--status) action=status; shift;;
+ -x|--cancel) action=cancel; shift;;
+ --interrupt) action=interrupt; shift;;
+ -i|--idle) ionice=idle; shift;;
+ -l|--slow) ionice=low; shift;;
+ -f|--fast) ionice=high; shift;;
+ --realtime) ionice=realtime; shift;;
+ --split) CHECK_SPLIT=$2; shift 2;;
+ -c|--cron) cron=1; shift;;
+ -q|--quiet) quiet=$(($quiet+1)); shift;;
+ -Q|--real-quiet) quiet=$(($quiet+2)); shift;; # for compatibility
-h|--help) usage; exit 0;;
-V|--version) about; exit 0;;
+ --) shift; break;;
+ *) echo "$PROGNAME: E: invalid option: $1. Try --help." >&2; exit 1;;
+ esac
+done
+
+for opt in $@
+do
+ case $opt in
/dev/md/*|md/*) arrays="${arrays:+$arrays }md${opt#*md/}";;
/dev/md*|md*) arrays="${arrays:+$arrays }${opt#/dev/}";;
/sys/block/md*) arrays="${arrays:+$arrays }${opt#/sys/block/}";;
@@ -99,6 +112,20 @@
exit 0
fi
+CHECK_SPLIT=${CHECK_SPLIT:-28}
+
+if [ $CHECK_SPLIT -gt 28 ]
+then
+ CHECK_SPLIT=28
+ echo "$PROGNAME: W: CHECK_SPLIT > 28, reset to 28." >&2
+fi
+
+if [ $CHECK_SPLIT -lt 1 ]
+then
+ CHECK_SPLIT=1
+ echo "$PROGNAME: W: CHECK_SPLIT < 1, reset to 1." >&2
+fi
+
if [ ! -f /proc/mdstat ]; then
[ $quiet -lt 2 ] && echo "$PROGNAME: E: MD subsystem not loaded, or /proc unavailable." >&2
exit 2
@@ -159,10 +186,34 @@
continue
fi
+ chunk_size=$(cat $MDBASE/chunk_size)
+ # set one to safe value if raid level has no chunk_size (e.g., raid 1):
+ [ $chunk_size -lt 1 ] && chunk_size=1
+
+ array_size=$(cat $MDBASE/../size)
+ array_size=$(($array_size >> 1))
+
+ check_size=$(($array_size / $CHECK_SPLIT))
+ # ensure it's of multiple $chunk_size:
+ check_size=$(($check_size - $check_size % $chunk_size))
+ [ $check_size -eq 0 ] && check_size=$chunk_size
+
case "$action" in
- idle)
- echo $action > $MDBASE/sync_action
+ cancel|interrupt)
+ echo 0 > $MDBASE/sync_force_parallel # XXX
+
+ completed=$(cut -d ' ' -f1 $MDBASE/sync_completed)
+ [ $completed = "none" ] && completed=0
+ echo "idle" > $MDBASE/sync_action
[ $quiet -lt 1 ] && echo "$PROGNAME: I: cancel request queued for array $array." >&2
+
+ if [ "$action" = "cancel" ]
+ then
+ completed=0
+ echo max > $MDBASE/sync_max
+ fi
+ # save sync_min, it must be a multiple of chunk_size:
+ echo $(($completed - $completed%$chunk_size)) > $MDBASE/sync_min
;;
check)
@@ -186,6 +237,21 @@
fi
fi
+ echo 1 > $MDBASE/sync_force_parallel # XXX
+
+ sync_min=$(cat $MDBASE/sync_min)
+ sync_max=$(cat $MDBASE/sync_max)
+
+ [ $sync_max = "max" ] && sync_max=0
+
+ if [ $sync_min -eq $sync_max ]
+ then
+ sync_max=$(($sync_max + $check_size))
+ [ $sync_max -ge $array_size ] && sync_max=$array_size
+
+ echo $sync_max > $MDBASE/sync_max
+ fi
+
# queue request for the array. The kernel will make sure that these requests
# are properly queued so as to not kill one of the array.
echo $action > $MDBASE/sync_action
