rpms/mdadm/devel mdadm-raid-check-sysconfig, NONE, 1.1 raid-check, 1.3, 1.4

[Doug Ledford]

Author: dledford

Update of /cvs/extras/rpms/mdadm/devel
In directory cvs1.fedora.phx.redhat.com:/tmp/cvs-serv6658

Modified Files:
	raid-check 
Added Files:
	mdadm-raid-check-sysconfig 
Log Message:
* Fri Jul 24 2009 Doug Ledford <dledford at redhat.com> - 3.0-2
- Improved raid-check script as well as the ability to configure what devices
  get checked
- Endian patch for uuid generation



--- NEW FILE mdadm-raid-check-sysconfig ---
#!/bin/bash
#
# Configuration file for /etc/cron.weekly/raid-check
#
# options:
#	ENABLED - must be yes in order for the raid check to proceed
#	CHECK - can be either check or repair depending on the type of
#		operation the user desires.  A check operation will scan
#		the drives looking for bad sectors and automatically
#		repairing only bad sectors.  If it finds good sectors that
#		contain bad data (meaning that the data in a sector does
#		not agree with what the data from another disk indicates
#		the data should be, for example the parity block + the other
#		data blocks would cause us to think that this data block
#		is incorrect), then it does nothing but increments the
#		counter in the file /sys/block/$dev/md/mismatch_count.
#		This allows the sysadmin to inspect the data in the sector
#		and the data that would be produced by rebuilding the
#		sector from redundant information and pick the correct
#		data to keep.  The repair option does the same thing, but
#		when it encounters a mismatch in the data, it automatically
#		updates the data to be consistent.  However, since we really
#		don't know whether it's the parity or the data block that's
#		correct (or which data block in the case of raid1), it's
#		luck of the draw whether or not the user gets the right
#		data instead of the bad data.  This option is the default
#		option for devices not listed in either CHECK_DEVS or
#		REPAIR_DEVS.
#	CHECK_DEVS - a space delimited list of devs that the user specifically
#		wants to run a check operation on.
#	REPAIR_DEVS - a space delimited list of devs that the user
#		specifically wants to run a repair on.
#	SKIP_DEVS - a space delimited list of devs that should be skipped
#
# Note: the raid-check script intentionaly runs last in the cron.weekly
# sequence.  This is so we can wait for all the resync operations to complete
# and then check the mismatch_count on each array without unduly delaying
# other weekly cron jobs.  If any arrays have a non-0 mismatch_count after
# the check completes, we echo a warning to stdout which will then me emailed
# to the admin as long as mails from cron jobs have not been redirected to
# /dev/null.  We do not wait for repair operations to complete as the
# md stack will correct any mismatch_cnts automatically.
#
# Note2: you can not use symbolic names for the raid devices, such as you
# /dev/md/root.  The names used in this file must match the names seen in
# /proc/mdstat and in /sys/block.

ENABLED=yes
CHECK=check
# To check devs /dev/md0 and /dev/md3, use "md0 md3"
CHECK_DEVS=""
REPAIR_DEVS=""
SKIP_DEVS=""


Index: raid-check
===================================================================
RCS file: /cvs/extras/rpms/mdadm/devel/raid-check,v
retrieving revision 1.3
retrieving revision 1.4
diff -u -p -r1.3 -r1.4
--- raid-check	29 Jun 2009 19:18:19 -0000	1.3
+++ raid-check	24 Jul 2009 17:43:39 -0000	1.4
@@ -1,7 +1,58 @@
 #!/bin/bash
+#
+# This script reads it's configuration from /etc/sysconfig/raid-check
+# Please use that file to enable/disable this script or to set the
+# type of check you wish performed.
 
+[ -f /etc/sysconfig/raid-check ] || exit 0
+. /etc/sysconfig/raid-check
+
+[ "$ENABLED" != "yes" ] && exit 0
+
+case "$CHECK" in
+    check) ;;
+    repair) ;;
+    *) exit 0;;
+esac
+
+dev_list=""
 for dev in `grep "^md.*: active" /proc/mdstat | cut -f 1 -d ' '`; do
-	[ -f /sys/block/$dev/md/sync_action ] && \
-		echo "check" > /sys/block/$dev/md/sync_action
+	echo $SKIP_DEVS | grep -w $dev >/dev/null 2>&1 && continue
+	if [ -f /sys/block/$dev/md/sync_action ]; then
+	    array_state=`cat /sys/block/$dev/md/array_state`
+	    sync_action=`cat /sys/block/$dev/md/sync_action`
+	    # Only perform the checks on idle, healthy arrays
+	    if [ "$array_state" = "clean" -a "$sync_action" = "idle" ]; then
+		check=""
+		echo $REPAIR_DEVS | grep -w $dev >/dev/null 2>&1 && \
+			check="repair"
+		echo $CHECK_DEVS | grep -w $dev >/dev/null 2>&1 \
+			&& check="check"
+		[ -z "$check" ] && check=$CHECK
+		echo "$check" > /sys/block/$dev/md/sync_action
+		[ "$check" = "check" ] && dev_list="$dev_list $dev"
+	    fi
+	fi
 done
 
+if [ -n "$dev_list" ]; then
+	checking=1
+	while [ $checking -ne 0 ]
+	do
+		sleep 3
+		checking=0
+		for dev in $dev_list; do
+			sync_action=`cat /sys/block/$dev/md/sync_action`
+			if [ "$sync_action" != "idle" ]; then
+				checking=1
+			fi
+		done
+	done
+	for dev in $dev_list; do
+		mismatch_cnt=`cat /sys/block/$dev/md/mismatch_cnt`
+		if [ "$mismatch_cnt" -ne 0 ]; then
+			echo "WARNING: mismatch_cnt is not 0 on /dev/$dev"
+		fi
+	done
+fi
+