mdadm/test
Xiao Ni 62e2991ff9 mdadm/test: Add one test case for raid5 reshape
This case tries to allow raid5 reshape to use backwards direction.
It changes chunksize after reshape and stops the raid. Then starts
the raid again.

Signed-off-by: Xiao Ni <xni@redhat.com>
Suggested-by:  Jes Sorensen <jes.sorensen@gmail.com>
Suggested-by:  Zhilong Liu <zlliu@suse.com>
Suggested-by:  Paul Menzel <pmenzel@molgen.mpg.de>
Signed-off-by: Jes Sorensen <jsorensen@fb.com>
2017-10-10 16:23:14 -04:00

608 lines
14 KiB
Bash
Executable File

#!/bin/bash
#
# run test suite for mdadm
dir=$(pwd)
mdadm=$dir/mdadm
testdir="tests"
targetdir="/var/tmp"
logdir="$targetdir"
config=/tmp/mdadm.conf
savelogs=0
exitonerror=1
prefix='[0-9][0-9]'
# use loop devices by default if doesn't specify --dev
DEVTYPE=loop
INTEGRITY=yes
LVM_VOLGROUP=mdtest
# make sure to test local mdmon, not system one
export MDADM_NO_SYSTEMCTL=1
# assume md0, md1, md2 exist in /dev
md0=/dev/md0
md1=/dev/md1
md2=/dev/md2
mdp0=/dev/md_d0
mdp1=/dev/md_d1
# We test mdadm on loop-back block devices.
# dir for storing files should be settable by command line maybe
size=20000
# super0, round down to multiple of 64 and substract 64
mdsize0=19904
# super00 is nested, subtract 128
mdsize00=19840
# super1.0 round down to multiple of 2, subtract 8
mdsize1=19992
mdsize1a=19988
mdsize12=19988
# super1.2 for linear: round to multiple of 2, subtract 4
mdsize1_l=19996
mdsize2_l=19996
# subtract another 4 for bitmaps
mdsize1b=19988
mdsize11=19992
mdsize11a=19456
mdsize12=19988
# ddf needs bigger devices as 32Meg is reserved!
ddfsize=65536
# $1 is optional parameter, it shows why to save log
save_log() {
status=$1
logfile="$status""$_basename".log
cat $targetdir/stderr >> $targetdir/log
cp $targetdir/log $logdir/$_basename.log
echo "## $HOSTNAME: saving dmesg." >> $logdir/$logfile
dmesg -c >> $logdir/$logfile
$mdadm -As 2> /dev/null
echo "## $HOSTNAME: saving proc mdstat." >> $logdir/$logfile
cat /proc/mdstat >> $logdir/$logfile
array=($(mdadm -Ds | cut -d' ' -f2))
echo "## $HOSTNAME: mdadm -D ${array[@]}" >> $logdir/$logfile
$mdadm -D ${array[@]} >> $logdir/$logfile
[ "$1" == "fail" ] &&
echo "FAILED - see $logdir/$_basename.log and $logdir/$logfile for details"
# ignore saving external(external file, imsm...) bitmap
cat /proc/mdstat | grep -q "linear\|external" && return 0
if [ $DEVTYPE == 'lvm' ]
then
# not supported lvm type yet
echo
elif [ "$DEVTYPE" == 'loop' -o "$DEVTYPE" == 'disk' ]
then
if [ ! -z "$array" -a ${#array[@]} -ge 1 ]
then
md_disks=($($mdadm -D -Y ${array[@]} | grep "/dev/" | cut -d'=' -f2))
cat /proc/mdstat | grep -q "bitmap"
if [ $? -eq 0 ]
then
echo "## $HOSTNAME: mdadm -X ${md_disks[@]}" >> $logdir/$logfile
$mdadm -X ${md_disks[@]} >> $logdir/$logfile
fi
else
echo "## $HOSTNAME: no array assembled!" >> $logdir/$logfile
fi
fi
}
die() {
echo -e "\n\tERROR: $* \n"
save_log fail
exit 2
}
cleanup() {
udevadm settle
$mdadm -Ssq 2> /dev/null
case $DEVTYPE in
loop )
for d in 0 1 2 3 4 5 6 7 8 9 10 11 12 13
do
losetup -d /dev/loop$d
rm -f /dev/disk/by-path/loop*
rm -f /var/tmp/mdtest$d
done
;;
lvm )
for d in 0 1 2 3 4 5 6 7 8 9 10 11 12 13
do
eval "lvremove --quiet -f \$dev$d"
done
;;
disk )
$mdadm --zero ${disks[@]} &> /dev/null
;;
esac
}
ctrl_c() {
exitonerror=1
}
do_setup() {
trap cleanup 0 1 3 15
trap ctrl_c 2
[ -d $logdir ] || mkdir -p $logdir
dmesg -c > /dev/null
devlist=
if [ "$DEVTYPE" == "loop" ]
then
# make sure there are no loop devices remaining.
# udev started things can sometimes prevent them being stopped
# immediately
while grep loop /proc/partitions > /dev/null 2>&1
do
$mdadm -Ssq
losetup -d /dev/loop[0-9]* 2> /dev/null
sleep 0.2
done
elif [ "$DEVTYPE" == "disk" ]
then
if [ ! -z "$disks" ]
then
for d in $(seq 0 ${#disks[@]})
do
eval "dev$d=${disks[$d]}"
eval devlist=\"\$devlist \$dev$d\"
eval devlist$d=\"\$devlist\"
done
$mdadm --zero ${disks[@]} &> /dev/null
else
echo "Forget to provide physical devices for disk mode."
exit 1
fi
fi
for d in 0 1 2 3 4 5 6 7 8 9 10 11 12 13
do
sz=$size
[ $d -gt 7 ] && sz=$ddfsize
case $DEVTYPE in
loop)
[ -f $targetdir/mdtest$d ] ||
dd if=/dev/zero of=$targetdir/mdtest$d count=$sz bs=1K > /dev/null 2>&1
# make sure udev doesn't touch
mdadm --zero $targetdir/mdtest$d 2> /dev/null
[ -b /dev/loop$d ] || mknod /dev/loop$d b 7 $d
if [ $d -eq 7 ]
then
losetup /dev/loop$d $targetdir/mdtest6 # for multipath use
else
losetup /dev/loop$d $targetdir/mdtest$d
fi
eval dev$d=/dev/loop$d
eval file$d=$targetdir/mdtest$d
;;
lvm)
unset MULTIPATH
eval dev$d=/dev/mapper/${LVM_VOLGROUP}-mdtest$d
if ! lvcreate --quiet -L ${sz}K -n mdtest$d $LVM_VOLGROUP
then
trap '' 0 # make sure lvremove is not called
eval echo error creating \$dev$d
exit 129
fi
;;
ram)
unset MULTIPATH
eval dev$d=/dev/ram$d
;;
esac
eval devlist=\"\$devlist \$dev$d\"
eval devlist$d=\"\$devlist\"
#" <-- add this quote to un-confuse vim syntax highlighting
done
path0=$dev6
path1=$dev7
ulimit -c unlimited
[ -f /proc/mdstat ] || modprobe md_mod
echo 2000 > /proc/sys/dev/raid/speed_limit_max
echo 0 > /sys/module/md_mod/parameters/start_ro
}
# mdadm always adds --quiet, and we want to see any unexpected messages
mdadm() {
rm -f $targetdir/stderr
case $* in
*-S* )
udevadm settle
p=`cat /proc/sys/dev/raid/speed_limit_max`
echo 20000 > /proc/sys/dev/raid/speed_limit_max
;;
esac
case $* in
*-C* | *--create* | *-B* | *--build* )
# clear superblock every time once creating or
# building arrays, because it's always creating
# and building array many times in a test case.
for args in $*
do
[[ $args =~ "/dev/" ]] && {
[[ $args =~ "md" ]] ||
$mdadm --zero $args > /dev/null
}
done
$mdadm 2> $targetdir/stderr --quiet "$@" --auto=yes
;;
* )
$mdadm 2> $targetdir/stderr --quiet "$@"
;;
esac
rv=$?
case $* in
*-S* )
udevadm settle
echo $p > /proc/sys/dev/raid/speed_limit_max
;;
esac
cat >&2 $targetdir/stderr
return $rv
}
# check various things
check() {
case $1 in
spares )
spares=$(tr '] ' '\012\012' < /proc/mdstat | grep -c '(S)' || exit 0)
[ $spares -ne $2 ] &&
die "expected $2 spares, found $spares"
;;
raid* | linear )
grep -sq "active $1 " /proc/mdstat ||
die "active $1 not found"
;;
algorithm )
grep -sq " algorithm $2 " /proc/mdstat ||
die "algorithm $2 not found"
;;
resync | recovery | reshape )
cnt=5
while ! grep -sq $1 /proc/mdstat
do
if [ $cnt -gt 0 ] && grep -v idle /sys/block/md*/md/sync_action > /dev/null
then # Something isn't idle - wait a bit
sleep 0.5
cnt=$[cnt-1]
else
die "no $1 happening"
fi
done
;;
nosync )
sleep 0.5
# Since 4.2 we delay the close of recovery until there has been a chance for
# spares to be activated. That means that a recovery that finds nothing
# to do can still take a little longer than expected.
# add an extra check: is sync_completed shows the end is reached, assume
# there is no recovery.
if grep -sq -E '(resync|recovery|reshape) *=' /proc/mdstat
then
incomplete=`grep / /sys/block/md*/md/sync_completed 2> /dev/null | sed '/^ *\([0-9]*\) \/ \1/d'`
[ -n "$incomplete" ] &&
die "resync or recovery is happening!"
fi
;;
wait )
p=`cat /proc/sys/dev/raid/speed_limit_max`
echo 2000000 > /proc/sys/dev/raid/speed_limit_max
sleep 0.1
while grep -Eq '(resync|recovery|reshape|check|repair) *=' /proc/mdstat ||
grep -v idle > /dev/null /sys/block/md*/md/sync_action
do
sleep 0.5
done
echo $p > /proc/sys/dev/raid/speed_limit_max
;;
state )
grep -sq "blocks.*\[$2\]\$" /proc/mdstat ||
die "state $2 not found!"
sleep 0.5
;;
bitmap )
grep -sq bitmap /proc/mdstat ||
die "no bitmap"
;;
nobitmap )
grep -sq "bitmap" /proc/mdstat &&
die "bitmap present"
;;
readonly )
grep -sq "read-only" /proc/mdstat ||
die "array is not read-only!"
;;
inactive )
grep -sq "inactive" /proc/mdstat ||
die "array is not inactive!"
;;
# It only can be used when there is only one raid
chunk )
chunk_size=`awk -F',' '/chunk/{print $2}' /proc/mdstat | awk -F'[a-z]' '{print $1}'`
if [ "$chunk_size" -ne "$2" ] ; then
die "chunksize should be $2, but it's $chunk_size"
fi
;;
* )
die "unknown check $1"
;;
esac
}
no_errors() {
if [ -s $targetdir/stderr ]
then
echo Bad errors from mdadm:
cat $targetdir/stderr
exit 2
fi
}
# basic device test
testdev() {
[ -b $1 ] || die "$1 isn't a block device."
[ "$DEVTYPE" == "disk" ] && return 0
udevadm settle
dev=$1
cnt=$2
dvsize=$3
chunk=$4
if [ -z "$5" ]
then
mkfs.ext3 -F -j $dev > /dev/null 2>&1 && fsck -fn $dev >&2
fi
dsize=$[dvsize/chunk]
dsize=$[dsize*chunk]
rasize=$[dsize*2*cnt]
# rasize is in sectors
if [ -n "$DEV_ROUND_K" ]
then
rasize=$[rasize/DEV_ROUND_K/2]
rasize=$[rasize*DEV_ROUND_K*2]
fi
[ `/sbin/blockdev --getsize $dev` -eq 0 ] && sleep 2
_sz=`/sbin/blockdev --getsize $dev`
[ $rasize -lt $_sz -o $[rasize*4/5] -gt $_sz ] &&
die "size is wrong for $dev: $cnt * $dvsize (chunk=$chunk) = $rasize, not $_sz"
return 0
}
rotest() {
dev=$1
fsck -fn $dev >&2
}
do_test() {
_script=$1
_basename=`basename $_script`
if [ -f "$_script" ]
then
rm -f $targetdir/stderr
# stop all arrays, just incase some script left an array active.
$mdadm -Ssq 2> /dev/null
mdadm --zero $devlist 2> /dev/null
# this might have been reset: restore the default.
echo 2000 > /proc/sys/dev/raid/speed_limit_max
# source script in a subshell, so it has access to our
# namespace, but cannot change it.
echo -ne "$_script... "
if ( set -ex ; . $_script ) &> $targetdir/log
then
dmesg | grep -iq "error\|call trace\|segfault" &&
die "dmesg prints errors when testing $_basename!"
echo "succeeded"
_fail=0
else
save_log fail
_fail=1
fi
[ "$savelogs" == "1" ] &&
mv -f $targetdir/log $logdir/$_basename.log
[ "$_fail" == "1" -a "$exitonerror" == "1" ] && exit 1
fi
}
do_help() {
cat <<-EOF
Usage: $0 [options]
Example for disk mode: ./test --dev=disk --disks=/dev/sda{2..15}
Options:
--tests=test1,test2,... Comma separated list of tests to run
--raidtype= raid0|linear|raid1|raid456|raid10|ddf|imsm
--disable-multipath Disable any tests involving multipath
--disable-integrity Disable slow tests of RAID[56] consistency
--logdir=directory Directory to save all logfiles in
--save-logs Usually use with --logdir together
--keep-going | --no-error Don't stop on error, ie. run all tests
--dev=loop|lvm|ram|disk Use loop devices (default), LVM, RAM or disk
--disks= Provide a bunch of physical devices for test
--volgroup=name LVM volume group for LVM test
setup Setup test environment and exit
cleanup Cleanup test environment
prefix Run tests with <prefix>
--help | -h Print this usage
EOF
}
parse_args() {
for i in $*
do
case $i in
[0-9][0-9] )
prefix=$i
;;
setup )
echo "mdadm test environment setup"
do_setup
trap 0
exit 0
;;
cleanup )
cleanup
exit 0
;;
--tests=* )
TESTLIST=($(echo ${i##*=} | sed -e 's/,/ /g'))
;;
--raidtype=* )
case ${i##*=} in
raid0 )
TESTLIST=($(ls $testdir | grep "[0-9][0-9]r0\|raid0"))
;;
linear )
TESTLIST=($(ls $testdir | grep "linear"))
;;
raid1 )
TESTLIST=($(ls $testdir | grep "[0-9][0-9]r1\|raid1" | grep -vi raid10))
;;
raid456 )
TESTLIST=($(ls $testdir | grep "[0-9][0-9]r[4-6]\|raid[4-6]"))
;;
raid10 )
TESTLIST=($(ls $testdir | grep "[0-9][0-9]r10\|raid10"))
;;
ddf )
TESTLIST=($(ls $testdir | grep "[0-9][0-9]ddf"))
;;
imsm )
TESTLIST=($(ls $testdir | grep "[0-9][0-9]imsm"))
;;
* )
echo "Unknown argument: $i"
do_help
exit 1
;;
esac
;;
--logdir=* )
logdir="${i##*=}"
;;
--save-logs )
savelogs=1
;;
--keep-going | --no-error )
exitonerror=0
;;
--disable-multipath )
unset MULTIPATH
;;
--disable-integrity )
unset INTEGRITY
;;
--dev=* )
case ${i##*=} in
loop )
DEVTYPE=loop
;;
lvm )
DEVTYPE=lvm
;;
ram )
DEVTYPE=ram
;;
disk )
DEVTYPE=disk
;;
* )
echo "Unknown argument: $i"
do_help
exit 1
;;
esac
;;
--disks=* )
disks=(${disks[*]} ${i##*=})
;;
--volgroup=* )
LVM_VOLGROUP=`expr "x$i" : 'x[^=]*=\(.*\)'`
;;
--help | -h )
do_help
exit 0
;;
* )
echo " $0: Unknown argument: $i"
do_help
exit 1
;;
esac
done
}
check_env() {
user=$(id -un)
[ "X$user" != "Xroot" ] && {
echo "test: testing can only be done as 'root'."
exit 1
}
[ -x "raid6check" -a -x $mdadm ] || {
echo "test: please run 'make everything' before perform testing."
exit 1
}
cmds=(mdadm lsblk df udevadm losetup mkfs.ext3 fsck seq)
for cmd in ${cmds[@]}
do
which $cmd > /dev/null || {
echo "$cmd command not found!"
exit 1
}
done
mdadm_src_ver="$($mdadm -V 2>&1)"
mdadm_sbin_ver="$($(which mdadm) -V 2>&1)"
if [ "$mdadm_src_ver" != "$mdadm_sbin_ver" ]
then
# it's nessesary to 'make install' mdadm to /SBIN/DIR,
# such as systemd/mdadm-grow-continue@.service, would
# run as an instance by systemd when reshape happens,
# thus ensure that the correct mdadm is in testing.
echo "test: please run 'make install' before testing."
exit 1
fi
if ! $(df -T . | grep -iq ext)
then
# 'external file' bitmap only supports with ext[2-4] file system
echo "test: please run test suite with ext[2-4] file system."
exit 1
fi
if $(lsblk -a | grep -iq raid)
then
# donot run mdadm -Ss directly if there are RAIDs working.
echo "test: please run test suite without running RAIDs environment."
exit 1
fi
# Check whether to run multipath tests
modprobe multipath 2> /dev/null
grep -sq 'Personalities : .*multipath' /proc/mdstat &&
MULTIPATH="yes"
}
main() {
check_env
do_setup
echo "Testing on linux-$(uname -r) kernel"
[ "$savelogs" == "1" ] &&
echo "Saving logs to $logdir"
if [ "x$TESTLIST" != "x" ]
then
for script in ${TESTLIST[@]}
do
do_test $testdir/$script
done
else
for script in $testdir/$prefix $testdir/$prefix*[^~]
do
do_test $script
done
fi
exit 0
}
parse_args $@
main