diff mbox series

[v2,3/8] tests: add a regression test for raid10 deadlock

Message ID 20230529132826.2125392-4-yukuai1@huaweicloud.com (mailing list archive)
State Mainlined, archived
Delegated to: Jes Sorensen
Headers show
Series tests: add some regression tests | expand

Commit Message

Yu Kuai May 29, 2023, 1:28 p.m. UTC 
From: Yu Kuai <yukuai3@huawei.com>

The deadlock is described in [1], it's fixed first by [2], however,
it turns out this commit will trigger other problems[3], hence this
commit will be reverted and the deadlock is supposed to be fixed by [1].

[1] https://lore.kernel.org/linux-raid/20230322064122.2384589-5-yukuai1@huaweicloud.com/
[2] https://lore.kernel.org/linux-raid/20220621031129.24778-1-guoqing.jiang@linux.dev/
[3] https://lore.kernel.org/linux-raid/20230322064122.2384589-2-yukuai1@huaweicloud.com/

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
---
 tests/24raid10deadlock              | 88 +++++++++++++++++++++++++++++
 tests/24raid10deadlock.inject_error |  0
 2 files changed, 88 insertions(+)
 create mode 100644 tests/24raid10deadlock
 create mode 100644 tests/24raid10deadlock.inject_error
diff mbox series

Patch

diff --git a/tests/24raid10deadlock b/tests/24raid10deadlock
new file mode 100644
index 00000000..ee330aa9
--- /dev/null
+++ b/tests/24raid10deadlock
@@ -0,0 +1,88 @@ 
+devs="$dev0 $dev1 $dev2 $dev3"
+runtime=120
+pid=""
+action_pid=""
+
+set_up_injection()
+{
+	echo -1 > /sys/kernel/debug/fail_make_request/times
+	echo 1 > /sys/kernel/debug/fail_make_request/probability
+	echo 0 > /sys/kernel/debug/fail_make_request/verbose
+	echo 1 > /sys/block/${1##*/}/make-it-fail
+}
+
+clean_up_injection()
+{
+	echo 0 > /sys/block/${1##*/}/make-it-fail
+	echo 0 > /sys/kernel/debug/fail_make_request/times
+	echo 0 > /sys/kernel/debug/fail_make_request/probability
+	echo 2 > /sys/kernel/debug/fail_make_request/verbose
+}
+
+test_rdev()
+{
+	while true; do
+		mdadm -f $md0 $1 &> /dev/null
+		mdadm -r $md0 $1 &> /dev/null
+		mdadm --zero-superblock $1 &> /dev/null
+		mdadm -a $md0 $1 &> /dev/null
+		sleep $2
+	done
+}
+
+test_write_action()
+{
+	while true; do
+		echo frozen > /sys/block/md0/md/sync_action
+		echo idle > /sys/block/md0/md/sync_action
+		sleep 0.1
+	done
+}
+
+set_up_test()
+{
+	fio -h &> /dev/null || die "fio not found"
+
+	# create a simple raid10
+	mdadm -Cv -R -n 4 -l10 $md0 $devs || die "create raid10 failed"
+}
+
+clean_up_test()
+{
+	clean_up_injection $dev0
+	pkill -9 fio
+	kill -9 $pid
+	kill -9 $action_pid
+
+	sleep 1
+
+	if ps $action_pid | tail -1 | awk '{print $3}' | grep D; then
+		die "thread that is writing sysfs is stuck in D state, deadlock is triggered"
+	fi
+	mdadm -S $md0
+}
+
+cat /sys/kernel/debug/fail_make_request/times || die "fault injection is not enabled"
+
+trap 'clean_up_test' EXIT
+
+set_up_test || die "set up test failed"
+
+# backgroup io pressure
+fio -filename=$md0 -rw=randwrite -direct=1 -name=test -bs=4k -numjobs=16 -iodepth=16 &
+
+# trigger add/remove device by io failure
+set_up_injection $dev0
+test_rdev $dev0 2 &
+pid="$pid $!"
+
+# add/remove device directly
+test_rdev $dev3 10 &
+pid="$pid $!"
+
+test_write_action &
+action_pid="$!"
+
+sleep $runtime
+
+exit 0
diff --git a/tests/24raid10deadlock.inject_error b/tests/24raid10deadlock.inject_error
new file mode 100644
index 00000000..e69de29b