- Improved raid-check script as well as the ability to configure what

devices get checked
- Endian patch for uuid generation

mdadm-3.0-endian-FAIL.patch

@@ -0,0 +1,15 @@
+diff -up mdadm-3.0-devel3/util.c.foo mdadm-3.0-devel3/util.c
+--- mdadm-3.0-devel3/util.c.foo	2009-07-09 18:57:47.000000000 -0400
++++ mdadm-3.0-devel3/util.c	2009-07-09 18:58:09.000000000 -0400
+@@ -282,7 +282,11 @@ char *fname_from_uuid(struct supertype *
+ 	char *c = buf;
+ 	strcpy(c, "UUID-");
+ 	c += strlen(c);
++#if __BYTE_ORDER == BIG_ENDIAN
++	copy_uuid(uuid, info->uuid, st->ss->swapuuid || !strcmp(st->ss->name,"0.90"));
++#else
+ 	copy_uuid(uuid, info->uuid, st->ss->swapuuid);
++#endif
+ 	for (i = 0; i < 4; i++) {
+ 		id = uuid[i];
+ 		if (i)

mdadm-raid-check-sysconfig

@@ -0,0 +1,53 @@
+#!/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=""

mdadm.spec

@@ -1,12 +1,14 @@
 Summary:     The mdadm program controls Linux md devices (software RAID arrays)
 Name:        mdadm
 Version:     3.0
-Release:     1%{?dist}
+Release:     2%{?dist}
 Source:      http://www.kernel.org/pub/linux/utils/raid/mdadm/mdadm-%{version}.tar.bz2
 Source1:     mdmonitor.init
 Source2:     raid-check
 Source3:     mdadm.rules
+Source4:     mdadm-raid-check-sysconfig
 Patch1:      mdadm-2.5.2-static.patch
+Patch2:      mdadm-3.0-endian-FAIL.patch
 URL:         http://www.kernel.org/pub/linux/utils/raid/mdadm/
 License:     GPLv2+
 Group:       System Environment/Base
@@ -28,21 +30,23 @@ file can be used to help with some common tasks.
 %prep
 %setup -q
 %patch1 -p1 -b .static
+%patch2 -p1 -b .endian
 
 %build
 make %{?_smp_mflags} CXFLAGS="$RPM_OPT_FLAGS -fno-strict-aliasing" SYSCONFDIR="%{_sysconfdir}" mdadm.static mdadm mdmon
 
 %install
-rm -rf $RPM_BUILD_ROOT
-make DESTDIR=$RPM_BUILD_ROOT MANDIR=%{_mandir} BINDIR=/sbin install install-static
-rm -f $RPM_BUILD_ROOT/lib/udev/rules.d/*
-install -Dp -m 755 %{SOURCE1} $RPM_BUILD_ROOT/%{_initrddir}/mdmonitor
-install -Dp -m 755 %{SOURCE2} $RPM_BUILD_ROOT/%{_sysconfdir}/cron.weekly/raid-check
-install -Dp -m 644 %{SOURCE3} $RPM_BUILD_ROOT/lib/udev/rules.d/65-md-incremental.rules
-mkdir -p -m 700 $RPM_BUILD_ROOT/var/run/mdadm
+rm -rf %{buildroot}
+make DESTDIR=%{buildroot} MANDIR=%{_mandir} BINDIR=/sbin install install-static
+rm -f %{buildroot}/lib/udev/rules.d/*
+install -Dp -m 755 %{SOURCE1} %{buildroot}%{_initrddir}/mdmonitor
+install -Dp -m 755 %{SOURCE2} %{buildroot}%{_sysconfdir}/cron.weekly/99-raid-check
+install -Dp -m 644 %{SOURCE3} %{buildroot}/lib/udev/rules.d/65-md-incremental.rules
+install -Dp -m 644 %{SOURCE4} %{buildroot}%{_sysconfdir}/sysconfig/raid-check
+mkdir -p -m 700 %{buildroot}/var/run/mdadm
 
 %clean
-rm -rf $RPM_BUILD_ROOT
+rm -rf %{buildroot}
 
 %post
 if [ "$1" = 1 ]; then
@@ -68,9 +72,15 @@ fi
 %{_initrddir}/*
 %{_mandir}/man*/md*
 %{_sysconfdir}/cron.weekly/*
+%config(noreplace) %{_sysconfdir}/sysconfig/*
 %attr(0700,root,root) %dir /var/run/mdadm
 
 %changelog
+* Fri Jul 24 2009 Doug Ledford <dledford@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
+
 * Mon Jun 29 2009 Doug Ledford <dledford@redhat.com> - 3.0-1
 - Remove stale patches already accepted by upstream
 - Fix the raid-check script to only try and check a device if it is

raid-check

@@ -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
+