| Message ID | 1494352571-17199-4-git-send-email-bo.li.liu@oracle.com (mailing list archive) |
|---|---|
| State | Not Applicable |
| Headers | show |
On Tue, May 09, 2017 at 11:56:08AM -0600, Liu Bo wrote: > This case tests whether dio read can repair the bad copy if we have > a good copy. > > Commit 2dabb3248453 ("Btrfs: Direct I/O read: Work on sectorsized blocks") > introduced the regression. > > The upstream fix is > Btrfs: fix invalid dereference in btrfs_retry_endio I noticed this is in upstream now, you can refer to it along with hash tag too. > > Signed-off-by: Liu Bo <bo.li.liu@oracle.com> > --- > tests/btrfs/140 | 115 ++++++++++++++++++++++++++++++++++++++++++++++++++++ > tests/btrfs/140.out | 39 ++++++++++++++++++ > tests/btrfs/group | 1 + > 3 files changed, 155 insertions(+) > create mode 100755 tests/btrfs/140 > create mode 100644 tests/btrfs/140.out > > diff --git a/tests/btrfs/140 b/tests/btrfs/140 > new file mode 100755 > index 0000000..09a9939 > --- /dev/null > +++ b/tests/btrfs/140 > @@ -0,0 +1,115 @@ > +#! /bin/bash > +# FS QA Test 140 > +# > +# Regression test for btrfs DIO read's repair during read. > +# > +# Commit 2dabb3248453 ("Btrfs: Direct I/O read: Work on sectorsized blocks") > +# introduced the regression. > +# The upstream fix is > +# Btrfs: fix invalid dereference in btrfs_retry_endio > +# > +#----------------------------------------------------------------------- > +# Copyright (c) 2017 Liu Bo. All Rights Reserved. > +# > +# This program is free software; you can redistribute it and/or > +# modify it under the terms of the GNU General Public License as > +# published by the Free Software Foundation. > +# > +# This program is distributed in the hope that it would be useful, > +# but WITHOUT ANY WARRANTY; without even the implied warranty of > +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the > +# GNU General Public License for more details. > +# > +# You should have received a copy of the GNU General Public License > +# along with this program; if not, write the Free Software Foundation, > +# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA > +#----------------------------------------------------------------------- > +# > + > +seq=`basename $0` > +seqres=$RESULT_DIR/$seq > +echo "QA output created by $seq" > + > +here=`pwd` > +tmp=/tmp/$$ > +status=1 # failure is the default! > +trap "_cleanup; exit \$status" 0 1 2 3 15 > + > +_cleanup() > +{ > + cd / > + rm -f $tmp.* > +} > + > +# get standard environment, filters and checks > +. ./common/rc > +. ./common/filter > + > +# remove previous $seqres.full before test > +rm -f $seqres.full > + > +# real QA test starts here > + > +# Modify as appropriate. > +_supported_fs btrfs > +_supported_os Linux > +_require_scratch_dev_pool 2 > + > +_require_btrfs_command inspect-internal dump-tree > +_require_command "$FILEFRAG_PROG" filefrag > +_require_odirect > + > +get_physical() > +{ > + # $1 is logical address > + # print chunk tree and find devid 2 which is $SCRATCH_DEV > + $BTRFS_UTIL_PROG inspect-internal dump-tree -t 3 $SCRATCH_DEV | \ > + grep $1 -A 6 | awk '($1 ~ /stripe/ && $3 ~ /devid/ && $4 ~ /1/) { print $6 }' > +} > + > +_scratch_dev_pool_get 2 > +# step 1, create a raid1 btrfs which contains one 128k file. > +echo "step 1......mkfs.btrfs" >>$seqres.full > + > +mkfs_opts="-d raid1 -b 1G" > +_scratch_pool_mkfs $mkfs_opts >>$seqres.full 2>&1 > + > +# -o nospace_cache makes sure data is written to the start position of the data > +# chunk > +_scratch_mount -o nospace_cache > + > +$XFS_IO_PROG -f -d -c "pwrite -S 0xaa -b 128K 0 128K" "$SCRATCH_MNT/foobar" | _filter_xfs_io > + > +# step 2, corrupt the first 64k of one copy (on SCRATCH_DEV which is the first > +# one in $SCRATCH_DEV_POOL > +echo "step 2......corrupt file extent" >>$seqres.full > + > +${FILEFRAG_PROG} -v $SCRATCH_MNT/foobar >> $seqres.full > +logical_in_btrfs=`${FILEFRAG_PROG} -v $SCRATCH_MNT/foobar | _filter_filefrag | cut -d '#' -f 1` > +physical_on_scratch=`get_physical ${logical_in_btrfs}` > + > +_scratch_unmount > +$XFS_IO_PROG -d -c "pwrite -S 0xbb -b 64K $physical_on_scratch 64K" $SCRATCH_DEV | _filter_xfs_io > + > +_scratch_mount > + > +# step 3, 128k dio read (this read can repair bad copy) > +echo "step 3......repair the bad copy" >>$seqres.full > + > +# since raid1 consists of two copies, and the following read may read the good > +# copy directly, so lets loop 10 times here and discard output that dio reads > +# give > +for i in `seq 1 10`; do > + $XFS_IO_PROG -d -c "pread -b 128K 0 128K" "$SCRATCH_MNT/foobar" > /dev/null > + _get_current_dmesg | grep -q -e "csum failed" && break > +done Half of the time I got test failure because pread from SCRATCH_DEV read 0xbb instead of 0xaa on v4.11 kernel (bug should be fixed there), tested on two different hosts and could hit failure on both hosts. Similar failure happened to all the 4 tests randomly. I thought it was because "csum failed" was never hit, so I tried a "while true; do" loop, and that did fix the btrfs/140 failure for me, but then btrfs/141 would loop forever sometimes. On the other hand, the tests from your last post always passed on the same test host, but I didn't see anything particular would make this difference.. Can you please take a look? Thanks! Eryu > + > +_scratch_unmount > + > +# check if the repair works > +$XFS_IO_PROG -d -c "pread -v -b 512 $physical_on_scratch 512" $SCRATCH_DEV | _filter_xfs_io > + > +_scratch_dev_pool_put > +# success, all done > +status=0 > +exit > diff --git a/tests/btrfs/140.out b/tests/btrfs/140.out > new file mode 100644 > index 0000000..c8565f5 > --- /dev/null > +++ b/tests/btrfs/140.out > @@ -0,0 +1,39 @@ > +QA output created by 140 > +wrote 131072/131072 bytes at offset 0 > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > +wrote 65536/65536 bytes at offset 136708096 > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > +08260000: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260010: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260020: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260030: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260040: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260050: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260060: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260070: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260080: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260090: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082600a0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082600b0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082600c0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082600d0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082600e0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082600f0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260100: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260110: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260120: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260130: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260140: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260150: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260160: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260170: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260180: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +08260190: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082601a0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082601b0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082601c0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082601d0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082601e0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +082601f0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > +read 512/512 bytes at offset 136708096 > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > diff --git a/tests/btrfs/group b/tests/btrfs/group > index 9d4b80b..1cb9c98 100644 > --- a/tests/btrfs/group > +++ b/tests/btrfs/group > @@ -141,3 +141,4 @@ > 137 auto quick send > 138 auto compress > 139 auto qgroup > +140 auto quick > -- > 2.5.0 > -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Wed, May 10, 2017 at 06:53:26PM +0800, Eryu Guan wrote: > On Tue, May 09, 2017 at 11:56:08AM -0600, Liu Bo wrote: > > This case tests whether dio read can repair the bad copy if we have > > a good copy. > > > > Commit 2dabb3248453 ("Btrfs: Direct I/O read: Work on sectorsized blocks") > > introduced the regression. > > > > The upstream fix is > > Btrfs: fix invalid dereference in btrfs_retry_endio > > I noticed this is in upstream now, you can refer to it along with hash > tag too. > > > > > Signed-off-by: Liu Bo <bo.li.liu@oracle.com> > > --- > > tests/btrfs/140 | 115 ++++++++++++++++++++++++++++++++++++++++++++++++++++ > > tests/btrfs/140.out | 39 ++++++++++++++++++ > > tests/btrfs/group | 1 + > > 3 files changed, 155 insertions(+) > > create mode 100755 tests/btrfs/140 > > create mode 100644 tests/btrfs/140.out > > > > diff --git a/tests/btrfs/140 b/tests/btrfs/140 > > new file mode 100755 > > index 0000000..09a9939 > > --- /dev/null > > +++ b/tests/btrfs/140 > > @@ -0,0 +1,115 @@ > > +#! /bin/bash > > +# FS QA Test 140 > > +# > > +# Regression test for btrfs DIO read's repair during read. > > +# > > +# Commit 2dabb3248453 ("Btrfs: Direct I/O read: Work on sectorsized blocks") > > +# introduced the regression. > > +# The upstream fix is > > +# Btrfs: fix invalid dereference in btrfs_retry_endio > > +# > > +#----------------------------------------------------------------------- > > +# Copyright (c) 2017 Liu Bo. All Rights Reserved. > > +# > > +# This program is free software; you can redistribute it and/or > > +# modify it under the terms of the GNU General Public License as > > +# published by the Free Software Foundation. > > +# > > +# This program is distributed in the hope that it would be useful, > > +# but WITHOUT ANY WARRANTY; without even the implied warranty of > > +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the > > +# GNU General Public License for more details. > > +# > > +# You should have received a copy of the GNU General Public License > > +# along with this program; if not, write the Free Software Foundation, > > +# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA > > +#----------------------------------------------------------------------- > > +# > > + > > +seq=`basename $0` > > +seqres=$RESULT_DIR/$seq > > +echo "QA output created by $seq" > > + > > +here=`pwd` > > +tmp=/tmp/$$ > > +status=1 # failure is the default! > > +trap "_cleanup; exit \$status" 0 1 2 3 15 > > + > > +_cleanup() > > +{ > > + cd / > > + rm -f $tmp.* > > +} > > + > > +# get standard environment, filters and checks > > +. ./common/rc > > +. ./common/filter > > + > > +# remove previous $seqres.full before test > > +rm -f $seqres.full > > + > > +# real QA test starts here > > + > > +# Modify as appropriate. > > +_supported_fs btrfs > > +_supported_os Linux > > +_require_scratch_dev_pool 2 > > + > > +_require_btrfs_command inspect-internal dump-tree > > +_require_command "$FILEFRAG_PROG" filefrag > > +_require_odirect > > + > > +get_physical() > > +{ > > + # $1 is logical address > > + # print chunk tree and find devid 2 which is $SCRATCH_DEV > > + $BTRFS_UTIL_PROG inspect-internal dump-tree -t 3 $SCRATCH_DEV | \ > > + grep $1 -A 6 | awk '($1 ~ /stripe/ && $3 ~ /devid/ && $4 ~ /1/) { print $6 }' > > +} > > + > > +_scratch_dev_pool_get 2 > > +# step 1, create a raid1 btrfs which contains one 128k file. > > +echo "step 1......mkfs.btrfs" >>$seqres.full > > + > > +mkfs_opts="-d raid1 -b 1G" > > +_scratch_pool_mkfs $mkfs_opts >>$seqres.full 2>&1 > > + > > +# -o nospace_cache makes sure data is written to the start position of the data > > +# chunk > > +_scratch_mount -o nospace_cache > > + > > +$XFS_IO_PROG -f -d -c "pwrite -S 0xaa -b 128K 0 128K" "$SCRATCH_MNT/foobar" | _filter_xfs_io > > + > > +# step 2, corrupt the first 64k of one copy (on SCRATCH_DEV which is the first > > +# one in $SCRATCH_DEV_POOL > > +echo "step 2......corrupt file extent" >>$seqres.full > > + > > +${FILEFRAG_PROG} -v $SCRATCH_MNT/foobar >> $seqres.full > > +logical_in_btrfs=`${FILEFRAG_PROG} -v $SCRATCH_MNT/foobar | _filter_filefrag | cut -d '#' -f 1` > > +physical_on_scratch=`get_physical ${logical_in_btrfs}` > > + > > +_scratch_unmount > > +$XFS_IO_PROG -d -c "pwrite -S 0xbb -b 64K $physical_on_scratch 64K" $SCRATCH_DEV | _filter_xfs_io > > + > > +_scratch_mount > > + > > +# step 3, 128k dio read (this read can repair bad copy) > > +echo "step 3......repair the bad copy" >>$seqres.full > > + > > +# since raid1 consists of two copies, and the following read may read the good > > +# copy directly, so lets loop 10 times here and discard output that dio reads > > +# give > > +for i in `seq 1 10`; do > > + $XFS_IO_PROG -d -c "pread -b 128K 0 128K" "$SCRATCH_MNT/foobar" > /dev/null > > + _get_current_dmesg | grep -q -e "csum failed" && break > > +done > > Half of the time I got test failure because pread from SCRATCH_DEV read > 0xbb instead of 0xaa on v4.11 kernel (bug should be fixed there), tested > on two different hosts and could hit failure on both hosts. > > Similar failure happened to all the 4 tests randomly. I thought it was > because "csum failed" was never hit, so I tried a "while true; do" loop, > and that did fix the btrfs/140 failure for me, but then btrfs/141 would > loop forever sometimes. > > On the other hand, the tests from your last post always passed on the > same test host, but I didn't see anything particular would make this > difference.. > > Can you please take a look? Thanks! > Oh, sorry for the trouble, it's all due to the same reason, that is, the stripe read balance in btrfs simply looks at (current->pid % num_stripes) and picks up a stripe to read from. Since I put the bad data on stripe 1 in raid1 profile, we need an odd $pid to trigger the checksum failures, but I have no idea how to certainly get a task with odd pid number in one shot, so I'll just use "while true; do" for now, and update it later if I find a solution. Thanks, -liubo > Eryu > > > + > > +_scratch_unmount > > + > > +# check if the repair works > > +$XFS_IO_PROG -d -c "pread -v -b 512 $physical_on_scratch 512" $SCRATCH_DEV | _filter_xfs_io > > + > > +_scratch_dev_pool_put > > +# success, all done > > +status=0 > > +exit > > diff --git a/tests/btrfs/140.out b/tests/btrfs/140.out > > new file mode 100644 > > index 0000000..c8565f5 > > --- /dev/null > > +++ b/tests/btrfs/140.out > > @@ -0,0 +1,39 @@ > > +QA output created by 140 > > +wrote 131072/131072 bytes at offset 0 > > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > > +wrote 65536/65536 bytes at offset 136708096 > > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > > +08260000: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260010: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260020: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260030: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260040: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260050: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260060: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260070: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260080: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260090: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082600a0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082600b0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082600c0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082600d0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082600e0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082600f0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260100: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260110: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260120: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260130: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260140: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260150: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260160: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260170: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260180: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +08260190: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082601a0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082601b0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082601c0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082601d0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082601e0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +082601f0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > +read 512/512 bytes at offset 136708096 > > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > > diff --git a/tests/btrfs/group b/tests/btrfs/group > > index 9d4b80b..1cb9c98 100644 > > --- a/tests/btrfs/group > > +++ b/tests/btrfs/group > > @@ -141,3 +141,4 @@ > > 137 auto quick send > > 138 auto compress > > 139 auto qgroup > > +140 auto quick > > -- > > 2.5.0 > > -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Tue, May 16, 2017 at 11:48:46AM -0600, Liu Bo wrote: > On Wed, May 10, 2017 at 06:53:26PM +0800, Eryu Guan wrote: > > On Tue, May 09, 2017 at 11:56:08AM -0600, Liu Bo wrote: [...] > > > + > > > +# step 3, 128k dio read (this read can repair bad copy) > > > +echo "step 3......repair the bad copy" >>$seqres.full > > > + > > > +# since raid1 consists of two copies, and the following read may read the good > > > +# copy directly, so lets loop 10 times here and discard output that dio reads > > > +# give > > > +for i in `seq 1 10`; do > > > + $XFS_IO_PROG -d -c "pread -b 128K 0 128K" "$SCRATCH_MNT/foobar" > /dev/null > > > + _get_current_dmesg | grep -q -e "csum failed" && break > > > +done > > > > Half of the time I got test failure because pread from SCRATCH_DEV read > > 0xbb instead of 0xaa on v4.11 kernel (bug should be fixed there), tested > > on two different hosts and could hit failure on both hosts. > > > > Similar failure happened to all the 4 tests randomly. I thought it was > > because "csum failed" was never hit, so I tried a "while true; do" loop, > > and that did fix the btrfs/140 failure for me, but then btrfs/141 would > > loop forever sometimes. > > > > On the other hand, the tests from your last post always passed on the > > same test host, but I didn't see anything particular would make this > > difference.. > > > > Can you please take a look? Thanks! > > > > Oh, sorry for the trouble, it's all due to the same reason, that > is, the stripe read balance in btrfs simply looks at > (current->pid % num_stripes) and picks up a stripe to read from. > > Since I put the bad data on stripe 1 in raid1 profile, we need an > odd $pid to trigger the checksum failures, but I have no idea how > to certainly get a task with odd pid number in one shot, so I'll > just use "while true; do" for now, and update it later if I find > a solution. > (Originally I thought that 'loop forever' was due to bad luck so that the reader always gets an evenly %pid.) I figured out why running ./check btrfs/14[0-1] would end up looping on 141 forever, it turns out that csum errors got printed by btrfs_warn_rl which has a global rate limit, running 140 will drain the rate limit so running 141 won't have csum errors output in dmesg and it loops forever since 'grep' couldn't find anything. Obviously that forever thing is not acceptable, so..here is the workaround. Since I've put the bad copy on stripe #1 while the good copy lies on stripe #0, in that 'while true; do' loop, the bad copy gets access when (the reader's pid % 2 == 1) is true, thus we could check the reader's pid instead of doing grep in dmesg. It's probably fragile though. Thanks, -liubo > Thanks, > > -liubo > > Eryu > > > > > + > > > +_scratch_unmount > > > + > > > +# check if the repair works > > > +$XFS_IO_PROG -d -c "pread -v -b 512 $physical_on_scratch 512" $SCRATCH_DEV | _filter_xfs_io > > > + > > > +_scratch_dev_pool_put > > > +# success, all done > > > +status=0 > > > +exit > > > diff --git a/tests/btrfs/140.out b/tests/btrfs/140.out > > > new file mode 100644 > > > index 0000000..c8565f5 > > > --- /dev/null > > > +++ b/tests/btrfs/140.out > > > @@ -0,0 +1,39 @@ > > > +QA output created by 140 > > > +wrote 131072/131072 bytes at offset 0 > > > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > > > +wrote 65536/65536 bytes at offset 136708096 > > > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > > > +08260000: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260010: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260020: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260030: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260040: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260050: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260060: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260070: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260080: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260090: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082600a0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082600b0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082600c0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082600d0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082600e0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082600f0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260100: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260110: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260120: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260130: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260140: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260150: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260160: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260170: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260180: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +08260190: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082601a0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082601b0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082601c0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082601d0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082601e0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +082601f0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ > > > +read 512/512 bytes at offset 136708096 > > > +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) > > > diff --git a/tests/btrfs/group b/tests/btrfs/group > > > index 9d4b80b..1cb9c98 100644 > > > --- a/tests/btrfs/group > > > +++ b/tests/btrfs/group > > > @@ -141,3 +141,4 @@ > > > 137 auto quick send > > > 138 auto compress > > > 139 auto qgroup > > > +140 auto quick > > > -- > > > 2.5.0 > > > > -- > To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
diff --git a/tests/btrfs/140 b/tests/btrfs/140 new file mode 100755 index 0000000..09a9939 --- /dev/null +++ b/tests/btrfs/140 @@ -0,0 +1,115 @@ +#! /bin/bash +# FS QA Test 140 +# +# Regression test for btrfs DIO read's repair during read. +# +# Commit 2dabb3248453 ("Btrfs: Direct I/O read: Work on sectorsized blocks") +# introduced the regression. +# The upstream fix is +# Btrfs: fix invalid dereference in btrfs_retry_endio +# +#----------------------------------------------------------------------- +# Copyright (c) 2017 Liu Bo. All Rights Reserved. +# +# This program is free software; you can redistribute it and/or +# modify it under the terms of the GNU General Public License as +# published by the Free Software Foundation. +# +# This program is distributed in the hope that it would be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +# GNU General Public License for more details. +# +# You should have received a copy of the GNU General Public License +# along with this program; if not, write the Free Software Foundation, +# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA +#----------------------------------------------------------------------- +# + +seq=`basename $0` +seqres=$RESULT_DIR/$seq +echo "QA output created by $seq" + +here=`pwd` +tmp=/tmp/$$ +status=1 # failure is the default! +trap "_cleanup; exit \$status" 0 1 2 3 15 + +_cleanup() +{ + cd / + rm -f $tmp.* +} + +# get standard environment, filters and checks +. ./common/rc +. ./common/filter + +# remove previous $seqres.full before test +rm -f $seqres.full + +# real QA test starts here + +# Modify as appropriate. +_supported_fs btrfs +_supported_os Linux +_require_scratch_dev_pool 2 + +_require_btrfs_command inspect-internal dump-tree +_require_command "$FILEFRAG_PROG" filefrag +_require_odirect + +get_physical() +{ + # $1 is logical address + # print chunk tree and find devid 2 which is $SCRATCH_DEV + $BTRFS_UTIL_PROG inspect-internal dump-tree -t 3 $SCRATCH_DEV | \ + grep $1 -A 6 | awk '($1 ~ /stripe/ && $3 ~ /devid/ && $4 ~ /1/) { print $6 }' +} + +_scratch_dev_pool_get 2 +# step 1, create a raid1 btrfs which contains one 128k file. +echo "step 1......mkfs.btrfs" >>$seqres.full + +mkfs_opts="-d raid1 -b 1G" +_scratch_pool_mkfs $mkfs_opts >>$seqres.full 2>&1 + +# -o nospace_cache makes sure data is written to the start position of the data +# chunk +_scratch_mount -o nospace_cache + +$XFS_IO_PROG -f -d -c "pwrite -S 0xaa -b 128K 0 128K" "$SCRATCH_MNT/foobar" | _filter_xfs_io + +# step 2, corrupt the first 64k of one copy (on SCRATCH_DEV which is the first +# one in $SCRATCH_DEV_POOL +echo "step 2......corrupt file extent" >>$seqres.full + +${FILEFRAG_PROG} -v $SCRATCH_MNT/foobar >> $seqres.full +logical_in_btrfs=`${FILEFRAG_PROG} -v $SCRATCH_MNT/foobar | _filter_filefrag | cut -d '#' -f 1` +physical_on_scratch=`get_physical ${logical_in_btrfs}` + +_scratch_unmount +$XFS_IO_PROG -d -c "pwrite -S 0xbb -b 64K $physical_on_scratch 64K" $SCRATCH_DEV | _filter_xfs_io + +_scratch_mount + +# step 3, 128k dio read (this read can repair bad copy) +echo "step 3......repair the bad copy" >>$seqres.full + +# since raid1 consists of two copies, and the following read may read the good +# copy directly, so lets loop 10 times here and discard output that dio reads +# give +for i in `seq 1 10`; do + $XFS_IO_PROG -d -c "pread -b 128K 0 128K" "$SCRATCH_MNT/foobar" > /dev/null + _get_current_dmesg | grep -q -e "csum failed" && break +done + +_scratch_unmount + +# check if the repair works +$XFS_IO_PROG -d -c "pread -v -b 512 $physical_on_scratch 512" $SCRATCH_DEV | _filter_xfs_io + +_scratch_dev_pool_put +# success, all done +status=0 +exit diff --git a/tests/btrfs/140.out b/tests/btrfs/140.out new file mode 100644 index 0000000..c8565f5 --- /dev/null +++ b/tests/btrfs/140.out @@ -0,0 +1,39 @@ +QA output created by 140 +wrote 131072/131072 bytes at offset 0 +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +wrote 65536/65536 bytes at offset 136708096 +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) +08260000: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260010: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260020: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260030: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260040: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260050: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260060: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260070: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260080: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260090: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082600a0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082600b0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082600c0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082600d0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082600e0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082600f0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260100: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260110: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260120: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260130: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260140: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260150: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260160: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260170: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260180: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +08260190: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082601a0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082601b0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082601c0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082601d0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082601e0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +082601f0: aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa aa ................ +read 512/512 bytes at offset 136708096 +XXX Bytes, X ops; XX:XX:XX.X (XXX YYY/sec and XXX ops/sec) diff --git a/tests/btrfs/group b/tests/btrfs/group index 9d4b80b..1cb9c98 100644 --- a/tests/btrfs/group +++ b/tests/btrfs/group @@ -141,3 +141,4 @@ 137 auto quick send 138 auto compress 139 auto qgroup +140 auto quick
This case tests whether dio read can repair the bad copy if we have a good copy. Commit 2dabb3248453 ("Btrfs: Direct I/O read: Work on sectorsized blocks") introduced the regression. The upstream fix is Btrfs: fix invalid dereference in btrfs_retry_endio Signed-off-by: Liu Bo <bo.li.liu@oracle.com> --- tests/btrfs/140 | 115 ++++++++++++++++++++++++++++++++++++++++++++++++++++ tests/btrfs/140.out | 39 ++++++++++++++++++ tests/btrfs/group | 1 + 3 files changed, 155 insertions(+) create mode 100755 tests/btrfs/140 create mode 100644 tests/btrfs/140.out