| Message ID | d5ae8704427e156eb6dca0b720847e48665a6340.1742302069.git.jth@kernel.org (mailing list archive) |
|---|---|
| State | New |
| Headers | show |
| Series | [v2] fstests: btrfs: zoned: verify RAID conversion with write pointer mismatch | expand |
On 18.03.25 13:49, Johannes Thumshirn wrote: > From: Johannes Thumshirn <johannes.thumshirn@wdc.com> > > Recently we had a bug report about a kernel crash that happened when the > user was converting a filesystem to use RAID1 for metadata, but for some > reason the device's write pointers got out of sync. > > Test this scenario by manually injecting de-synchronized write pointer > positions and then running conversion to a metadata RAID1 filesystem. > > In the testcase also repair the broken filesystem and check if both system > and metadata block groups are back to the default 'DUP' profile > afterwards. > > Link: https://lore.kernel.org/linux-btrfs/CAB_b4sBhDe3tscz=duVyhc9hNE+gu=B8CrgLO152uMyanR8BEA@mail.gmail.com/ > Signed-off-by: Johannes Thumshirn <johannes.thumshirn@wdc.com> > > --- > Changes to v1: > - Add test description > - Don't redirect stderr to $seqres.full > - Use xfs_io instead of dd > - Use $SCRATCH_MNT instead of hardcoded mount path > - Check that 1st balance command actually fails as it's supposed to > --- > tests/btrfs/329 | 61 +++++++++++++++++++++++++++++++++++++++++++++ > tests/btrfs/329.out | 7 ++++++ > 2 files changed, 68 insertions(+) > create mode 100755 tests/btrfs/329 > create mode 100644 tests/btrfs/329.out > > diff --git a/tests/btrfs/329 b/tests/btrfs/329 > new file mode 100755 > index 000000000000..0cc75bc8156d > --- /dev/null > +++ b/tests/btrfs/329 > @@ -0,0 +1,61 @@ > +#! /bin/bash > +# SPDX-License-Identifier: GPL-2.0 > +# Copyright (c) 2025 Western Digital Corporation. All Rights Reserved. > +# > +# FS QA Test 329 > +# > +# Regression test for a kernel crash when converting a zoned BTRFS from > +# metadata DUP to RAID1 and one of the devices has a non 0 write pointer > +# position in the target zone. > +# > +. ./common/preamble > +_begin_fstest zone quick volume > + > +. ./common/filter > + > +_fixed_by_kernel_commit XXXXXXXXXXXX \ > + "btrfs: zoned: return EIO on RAID1 block group write pointer mismatch" > + > +_require_scratch_dev_pool 2 > +declare -a devs="( $SCRATCH_DEV_POOL )" > +_require_zoned_device ${devs[0]} > +_require_zoned_device ${devs[1]} > +_require_command "$BLKZONE_PROG" blkzone > + > +_scratch_mkfs >> $seqres.full 2>&1 || _fail "mkfs failed" > +_scratch_mount > + > +# Write some data to the FS to dirty it > +$XFS_IO_PROG -fc "pwrite 0 128M" $SCRATCH_MNT/test | _filter_xfs_io > + > +# Add device two to the FS > +$BTRFS_UTIL_PROG device add ${devs[1]} $SCRATCH_MNT >> $seqres.full > + > +# Move write pointers of all empty zones by 4k to simulate write pointer > +# mismatch. > +zones=$($BLKZONE_PROG report ${devs[1]} | $AWK_PROG '/em/ { print $2 }' |\ > + sed 's/,//') > +for zone in $zones; > +do > + # We have to ignore the output here, as a) we don't know the number of > + # zones that have dirtied and b) if we run over the maximal number of > + # active zones, xfs_io will output errors, both we don't care. > + $XFS_IO_PROG -fdc "pwrite $(($zone << 9)) 4096" ${devs[1]} > /dev/null 2>&1 > +done > + > +# expected to fail > +$BTRFS_UTIL_PROG balance start -mconvert=raid1 $SCRATCH_MNT >> $seqres.full > + > +_scratch_unmount > + > +$MOUNT_PROG -t btrfs -odegraded ${devs[0]} $SCRATCH_MNT > + > +$BTRFS_UTIL_PROG device remove --force missing $SCRATCH_MNT >> $seqres.full > +$BTRFS_UTIL_PROG balance start --full-balance $SCRATCH_MNT >> $seqres.full > + > +# Check that both System and Metadata are back to the DUP profile > +$BTRFS_UTIL_PROG filesystem df $SCRATCH_MNT |\ > + grep -o -e "System, DUP" -e "Metadata, DUP" > + > +status=0 > +exit > diff --git a/tests/btrfs/329.out b/tests/btrfs/329.out > new file mode 100644 > index 000000000000..b52b7d90d253 > --- /dev/null > +++ b/tests/btrfs/329.out > @@ -0,0 +1,7 @@ > +QA output created by 329 > +wrote 134217728/134217728 bytes at offset 0 > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > +ERROR: error during balancing '/mnt/scratch': Input/output error Args, that needs to be filtered as well. Saw it too late sorry. > +There may be more info in syslog - try dmesg | tail > +System, DUP > +Metadata, DUP
diff --git a/tests/btrfs/329 b/tests/btrfs/329 new file mode 100755 index 000000000000..0cc75bc8156d --- /dev/null +++ b/tests/btrfs/329 @@ -0,0 +1,61 @@ +#! /bin/bash +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2025 Western Digital Corporation. All Rights Reserved. +# +# FS QA Test 329 +# +# Regression test for a kernel crash when converting a zoned BTRFS from +# metadata DUP to RAID1 and one of the devices has a non 0 write pointer +# position in the target zone. +# +. ./common/preamble +_begin_fstest zone quick volume + +. ./common/filter + +_fixed_by_kernel_commit XXXXXXXXXXXX \ + "btrfs: zoned: return EIO on RAID1 block group write pointer mismatch" + +_require_scratch_dev_pool 2 +declare -a devs="( $SCRATCH_DEV_POOL )" +_require_zoned_device ${devs[0]} +_require_zoned_device ${devs[1]} +_require_command "$BLKZONE_PROG" blkzone + +_scratch_mkfs >> $seqres.full 2>&1 || _fail "mkfs failed" +_scratch_mount + +# Write some data to the FS to dirty it +$XFS_IO_PROG -fc "pwrite 0 128M" $SCRATCH_MNT/test | _filter_xfs_io + +# Add device two to the FS +$BTRFS_UTIL_PROG device add ${devs[1]} $SCRATCH_MNT >> $seqres.full + +# Move write pointers of all empty zones by 4k to simulate write pointer +# mismatch. +zones=$($BLKZONE_PROG report ${devs[1]} | $AWK_PROG '/em/ { print $2 }' |\ + sed 's/,//') +for zone in $zones; +do + # We have to ignore the output here, as a) we don't know the number of + # zones that have dirtied and b) if we run over the maximal number of + # active zones, xfs_io will output errors, both we don't care. + $XFS_IO_PROG -fdc "pwrite $(($zone << 9)) 4096" ${devs[1]} > /dev/null 2>&1 +done + +# expected to fail +$BTRFS_UTIL_PROG balance start -mconvert=raid1 $SCRATCH_MNT >> $seqres.full + +_scratch_unmount + +$MOUNT_PROG -t btrfs -odegraded ${devs[0]} $SCRATCH_MNT + +$BTRFS_UTIL_PROG device remove --force missing $SCRATCH_MNT >> $seqres.full +$BTRFS_UTIL_PROG balance start --full-balance $SCRATCH_MNT >> $seqres.full + +# Check that both System and Metadata are back to the DUP profile +$BTRFS_UTIL_PROG filesystem df $SCRATCH_MNT |\ + grep -o -e "System, DUP" -e "Metadata, DUP" + +status=0 +exit diff --git a/tests/btrfs/329.out b/tests/btrfs/329.out new file mode 100644 index 000000000000..b52b7d90d253 --- /dev/null +++ b/tests/btrfs/329.out @@ -0,0 +1,7 @@ +QA output created by 329 +wrote 134217728/134217728 bytes at offset 0 +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +ERROR: error during balancing '/mnt/scratch': Input/output error +There may be more info in syslog - try dmesg | tail +System, DUP +Metadata, DUP