btrfs: test for deadlock between snapshot delete and other read-write operations

Commit fb235dc06fac ("btrfs: qgroup: Move half of the qgroup
accounting time out of commit trans") could cause ABBA deadlock
between backref lookup with write lock hold (subvolume deletion) and
other read/write operations.

It's going to be fixed by "btrfs: qgroup: Don't trigger backref walk
at delayed ref insert time".

This test will generate pwrite background workload, along with
constant subvolume creation and deletion to trigger the bug.

It needs some time to generate enough files to bump the tree height
to trigger the bug.

In my test environment, with 'unsafe' cache mode for the VM, it
triggers the bug at around 70~90 seconds. So I leave the default
runtime to 120s to make sure the bug will be triggered.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Eryu Guan <guaneryu@gmail.com>
This commit is contained in:
Qu Wenruo
2019-01-11 13:01:51 +08:00
committed by Eryu Guan
parent a4235f29f7
commit 8fc1e7c157
3 changed files with 119 additions and 0 deletions
+116
View File
@@ -0,0 +1,116 @@
#! /bin/bash
# SPDX-License-Identifier: GPL-2.0
# Copyright (C) 2019 SUSE Linux Products GmbH. All Rights Reserved.
#
# FS QA Test 179
#
# Test if btrfs will lockup at subvolume deletion when qgroups are enabled.
#
# This bug is going to be fixed by a patch for the kernel titled
# "btrfs: qgroup: Don't trigger backref walk at delayed ref insert time".
#
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 $seqres.full
# real QA test starts here
# Modify as appropriate.
_supported_fs btrfs
_supported_os Linux
_require_scratch
# default sleep interval
sleep_time=1
# stress test runtime
runtime=120
_scratch_mkfs > /dev/null 2>&1
_scratch_mount
mkdir -p "$SCRATCH_MNT/snapshots"
$BTRFS_UTIL_PROG subvolume create "$SCRATCH_MNT/src" > /dev/null
$BTRFS_UTIL_PROG quota enable "$SCRATCH_MNT" > /dev/null
$BTRFS_UTIL_PROG quota rescan -w "$SCRATCH_MNT" > /dev/null
fill_workload()
{
trap "wait; exit" SIGTERM
local i=0
while true; do
_pwrite_byte 0xcd 0 8K "$SCRATCH_MNT/src/large_$i" > /dev/null
_pwrite_byte 0xcd 0 2K "$SCRATCH_MNT/src/inline_$i" > /dev/null
# Randomly remove some files for every 5 loop
if [ $(( $i % 5 )) -eq 0 ]; then
victim=$(ls "$SCRATCH_MNT/src" | sort -R | head -n1)
rm "$SCRATCH_MNT/src/$victim"
fi
i=$((i + 1))
done
}
snapshot_workload()
{
trap "wait; exit" SIGTERM
local i=0
while true; do
sleep $sleep_time
$BTRFS_UTIL_PROG subvolume snapshot "$SCRATCH_MNT/src" \
"$SCRATCH_MNT/snapshots/$i" > /dev/null
i=$((i + 1))
done
}
delete_workload()
{
trap "wait; exit" SIGTERM
while true; do
sleep $((sleep_time * 2))
victim=$(ls "$SCRATCH_MNT/snapshots" | sort -R | head -n1)
$BTRFS_UTIL_PROG subvolume delete \
"$SCRATCH_MNT/snapshots/$victim" > /dev/null
done
}
fill_workload &
fill_pid=$!
sleep $((sleep_time * 2))
snapshot_workload &
snapshot_pid=$!
delete_workload &
delete_pid=$!
sleep $runtime
kill $fill_pid
wait $fill_pid
kill $snapshot_pid
wait $snapshot_pid
kill $delete_pid
wait $delete_pid
# success, all done
echo "Silence is golden"
status=0
exit
+2
View File
@@ -0,0 +1,2 @@
QA output created by 179
Silence is golden
+1
View File
@@ -181,3 +181,4 @@
176 auto quick swap volume 176 auto quick swap volume
177 auto quick swap balance 177 auto quick swap balance
178 auto quick send 178 auto quick send
179 auto qgroup dangerous