[PATCH v2 0/5] Btrfs: RAID 5/6 missing device scrub+replace

[Omar Sandoval <osandov@fb.com>]

Hi,

Here's version 2 of the missing device RAID 5/6 fixes. The original
problem was reported by a user on Bugzilla: the kernel crashed when
attempting to replace a missing device in a RAID 6 filesystem. This is
detailed and fixed in patch 4. After the initial posting, Zhao Lei
reported a similar issue when doing a scrub on a RAID 5 filesystem with
a missing device. This is fixed in the added patch 5.

My new-and-improved-and-overengineered reproducer as well as Zhao Lei's
reproducer can be found below.

Thanks!

v1: http://article.gmane.org/gmane.comp.file-systems.btrfs/45045
v1->v2:
- Add missing scrub_wr_submit() in scrub_missing_raid56_worker()
- Add clarifying comment in dev->missing case of scrub_stripe()
  (Zhaolei)
- Add fix for scrub with missing device (patch 5)

Omar Sandoval (5):
  Btrfs: remove misleading handling of missing device scrub
  Btrfs: count devices correctly in readahead during RAID 5/6 replace
  Btrfs: add RAID 5/6 BTRFS_RBIO_REBUILD_MISSING operation
  Btrfs: fix device replace of a missing RAID 5/6 device
  Btrfs: fix parity scrub of RAID 5/6 with missing device

 fs/btrfs/raid56.c |  87 ++++++++++++++++++++---
 fs/btrfs/raid56.h |  10 ++-
 fs/btrfs/reada.c  |   4 +-
 fs/btrfs/scrub.c  | 202 +++++++++++++++++++++++++++++++++++++++++++++---------
 4 files changed, 259 insertions(+), 44 deletions(-)

Reproducer 1:

----
#!/bin/bash

usage () {
	USAGE_STRING="Usage: $0 [OPTION]...
Options:
  -m    failure mode; MODE is 'eio', 'missing', or 'corrupt' (defaults to
        'missing')
  -n    number of files to write, each twice as big as the last, the first
        being 1M in size (defaults to 4)
  -o    operation to perform; OP is 'replace' or 'scrub' (defaults to
        'replace')
  -r    RAID profile; RAID is 'raid0', 'raid1', 'raid10', 'raid5', or 'raid6'
        (defaults to 'raid5')

Miscellaneous:
  -h    display this help message and exit"

	case "$1" in
		out)
			echo "$USAGE_STRING"
			exit 0
			;;
		err)
			echo "$USAGE_STRING" >&2
			exit 1
			;;
	esac
}

MODE=missing
RAID=raid5
OP=replace
NUM_FILES=4

while getopts "m:n:o:r:h" OPT; do
	case "$OPT" in
		m)
			MODE="$OPTARG"
			;;
		r)
			RAID="$OPTARG"
			;;
		o)
			OP="$OPTARG"
			;;
		n)
			NUM_FILES="$OPTARG"
			if [[ ! "$NUM_FILES" =~ ^[0-9]+$ ]]; then
				usage "err"
			fi
			;;
		h)
			usage "out"
			;;
		*)
			usage "err"
			;;
	esac
done

case "$MODE" in
	eio|missing|corrupt)
		;;
	*)
		usage err
		;;
esac

case "$RAID" in
	raid[01])
		NUM_RAID_DISKS=2
		;;
	raid10)
		NUM_RAID_DISKS=4
		;;
	raid5)
		NUM_RAID_DISKS=3
		;;
	raid6)
		NUM_RAID_DISKS=4
		;;
	*)
		usage err
		;;
esac

case "$OP" in
	replace)
		NUM_DISKS=$((NUM_RAID_DISKS + 1))
		;;
	scrub)
		NUM_DISKS=$NUM_RAID_DISKS
		;;
	*)
		usage err
		;;
esac

echo "Running $OP on $RAID with $MODE"

SRC_DISK=$((NUM_RAID_DISKS - 1))
TARGET_DISK=$((NUM_DISKS - 1))
NUM_SECTORS=$((1024 * 1024))
LOOP_DEVICES=()
DM_DEVICES=()

cleanup () {
	echo "Done. Press enter to cleanup..."
	read
	if findmnt /mnt; then
		umount /mnt
	fi
	for DM in "${DM_DEVICES[@]}"; do
		dmsetup remove "$DM"
	done
	for LOOP in "${LOOP_DEVICES[@]}"; do
		losetup --detach "$LOOP"
	done
	for ((i = 0; i < NUM_DISKS; i++)); do
		rm -f disk${i}.img
	done
}
trap 'cleanup; exit 1' ERR

echo "Creating disk images..."
for ((i = 0; i < NUM_DISKS; i++)); do
	rm -f disk${i}.img
	dd if=/dev/zero of=disk${i}.img bs=512 seek=$NUM_SECTORS count=0
	LOOP_DEVICES+=("$(losetup --find --show disk${i}.img)")
done

echo "Creating loopback devices..."
for LOOP in "${LOOP_DEVICES[@]}"; do
	DM="${LOOP/\/dev\/loop/dm}"
	dmsetup create "$DM" --table "0 $NUM_SECTORS linear $LOOP 0"
	DM_DEVICES+=("$DM")
done

echo "Creating filesystem..."
FS_DEVICES=("${DM_DEVICES[@]:0:$NUM_RAID_DISKS}")
FS_DEVICES=("${FS_DEVICES[@]/#//dev/mapper/}")
echo "${FS_DEVICES[@]}"
MOUNT_DEVICE="${FS_DEVICES[$(((SRC_DISK + 1) % NUM_RAID_DISKS))]}"
mkfs.btrfs -d "$RAID" -m "$RAID" "${FS_DEVICES[@]}"
mount "$MOUNT_DEVICE" /mnt
for ((i = 0; i < NUM_FILES; i++)); do
	dd if=/dev/urandom of=/mnt/file$i bs=1M count=$((1 << $i))
done
sync

case "$MODE" in
	eio)
		echo "Killing disk..."
		dmsetup suspend "${DM_DEVICES[$SRC_DISK]}"
		dmsetup reload "${DM_DEVICES[$SRC_DISK]}" --table "0 $NUM_SECTORS error"
		dmsetup resume "${DM_DEVICES[$SRC_DISK]}"
		;;
	missing)
		echo "Removing disk and remounting degraded..."
		umount /mnt
		dmsetup remove "${DM_DEVICES[$SRC_DISK]}"
		unset DM_DEVICES[$SRC_DISK]
		mount -o degraded "$MOUNT_DEVICE" /mnt
		;;
	corrupt)
		echo "Corrupting disk and remounting degraded..."
		umount /mnt
		dd if=/dev/zero of=/dev/mapper/"${DM_DEVICES[$SRC_DISK]}" bs=1M count=1
		mount -o degraded "$MOUNT_DEVICE" /mnt
		;;
esac

case "$OP" in
	replace)
		echo "Replacing disk..."
		btrfs replace start -B $((SRC_DISK + 1)) /dev/mapper/"${DM_DEVICES[$TARGET_DISK]}" /mnt
		;;
	scrub)
		echo "Scrubbing filesystem..."
		btrfs scrub start -B /mnt
		;;
esac

echo "Scrubbing to double-check..."
btrfs scrub start -Br /mnt

cleanup
----

Reproducer 2:

----
#!/bin/bash

FS_DEVS=(/dev/vdb /dev/vdc /dev/vdd)
PRUNE_DEV=/dev/vdc
MNT=/mnt

do_cmd()
{
	echo "   $*"
	local output
	local ret
	output=$("$@" 2>&1)
	ret="$?"
	[[ "$ret" != 0 ]] && {
		echo "$output"
	}
	return "$ret"
}

mkdir -p "$MNT"
for ((i = 0; i < 10; i++)); do
	umount "$MNT" &>/dev/null
done
dmesg -c >/dev/null

echo "1: Creating filesystem"
do_cmd mkfs.btrfs -f -d raid5 -m raid5 "${FS_DEVS[@]}" || exit 1
do_cmd mount "$FS_DEVS" "$MNT" || exit 1

echo "2: Write some data"
DATA_CNT=4
for ((i = 0; i < DATA_CNT; i++)); do
	size_m="$((1<<i))"
	do_cmd dd bs=1M if=/dev/urandom of="$MNT"/file_"$i" count="$size_m" || exit 1
done

echo "3: Prune a disk in fs"
do_cmd umount "$MNT" || exit 1
do_cmd dd bs=1M if=/dev/zero of="$PRUNE_DEV" count=1
do_cmd mount -o "degraded" "$FS_DEVS" "$MNT" || exit 1

echo "4: Do scrub"
do_cmd btrfs scrub start -B "$MNT"

echo "5: Checking result"
dmesg --color

exit 0
----

-- 
1.8.5.6

--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in