All of lore.kernel.org
 help / color / mirror / Atom feed
* Re: [block] 658f2fb7d2: fxmark.hdd_f2fs_dbench_client_72_directio.works/sec -21.4% regression
@ 2021-04-29  5:37 Chien Nguyenmau
  0 siblings, 0 replies; 7+ messages in thread
From: Chien Nguyenmau @ 2021-04-29  5:37 UTC (permalink / raw)
  To: lkp

[-- Attachment #1: Type: text/plain, Size: 2 bytes --]



[-- Attachment #2: attachment.htm --]
[-- Type: text/html, Size: 23 bytes --]

^ permalink raw reply	[flat|nested] 7+ messages in thread
* [PATCH] block: fix io hung by block throttle
@ 2021-04-14 21:18 Junxiao Bi
  2021-04-23  2:55   ` kernel test robot
  0 siblings, 1 reply; 7+ messages in thread
From: Junxiao Bi @ 2021-04-14 21:18 UTC (permalink / raw)
  To: linux-block, linux-kernel; +Cc: axboe

There is a race bug which can cause io hung when multiple processes
run parallel in rq_qos_wait().
Let assume there were 4 processes P1/P2/P3/P4, P1/P2 were at the entry
of rq_qos_wait, and P3/P4 were waiting for io done, 2 io were inflight,
the inflight io limit was 2. See race below.

void rq_qos_wait()
{
	...
    bool has_sleeper;

	>>>> P3/P4 were in sleeper list, has_sleeper was true for both P1 and P2.
    has_sleeper = wq_has_sleeper(&rqw->wait);
    if (!has_sleeper && acquire_inflight_cb(rqw, private_data))
        return;

	>>>> 2 inflight io done, P3/P4 were waken up to issue 2 new io.
	>>>> 2 new io done, no inflight io.

	>>>> P1/P2 were added to the sleeper list, 2 entry in the list
    prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE);

	>>>> P1/P2 were in the sleeper list, has_sleeper was true for P1/P2.
    has_sleeper = !wq_has_single_sleeper(&rqw->wait);
    do {
        /* The memory barrier in set_task_state saves us here. */
        if (data.got_token)
            break;
        if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) {
            finish_wait(&rqw->wait, &data.wq);

            /*
             * We raced with wbt_wake_function() getting a token,
             * which means we now have two. Put our local token
             * and wake anyone else potentially waiting for one.
             */
            smp_rmb();
            if (data.got_token)
                cleanup_cb(rqw, private_data);
            break;
        }

	>>>> P1/P2 hung here forever. New io requests will also hung here.
        io_schedule();
        has_sleeper = true;
        set_current_state(TASK_UNINTERRUPTIBLE);
    } while (1);
    finish_wait(&rqw->wait, &data.wq);
}

Cc: stable@vger.kernel.org
Signed-off-by: Junxiao Bi <junxiao.bi@oracle.com>
---
 block/blk-rq-qos.c | 9 +++------
 1 file changed, 3 insertions(+), 6 deletions(-)

diff --git a/block/blk-rq-qos.c b/block/blk-rq-qos.c
index 656460636ad3..04d888c99bc0 100644
--- a/block/blk-rq-qos.c
+++ b/block/blk-rq-qos.c
@@ -260,19 +260,17 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data,
 		.cb = acquire_inflight_cb,
 		.private_data = private_data,
 	};
-	bool has_sleeper;
 
-	has_sleeper = wq_has_sleeper(&rqw->wait);
-	if (!has_sleeper && acquire_inflight_cb(rqw, private_data))
+	if (!wq_has_sleeper(&rqw->wait)
+		&& acquire_inflight_cb(rqw, private_data))
 		return;
 
 	prepare_to_wait_exclusive(&rqw->wait, &data.wq, TASK_UNINTERRUPTIBLE);
-	has_sleeper = !wq_has_single_sleeper(&rqw->wait);
 	do {
 		/* The memory barrier in set_task_state saves us here. */
 		if (data.got_token)
 			break;
-		if (!has_sleeper && acquire_inflight_cb(rqw, private_data)) {
+		if (acquire_inflight_cb(rqw, private_data)) {
 			finish_wait(&rqw->wait, &data.wq);
 
 			/*
@@ -286,7 +284,6 @@ void rq_qos_wait(struct rq_wait *rqw, void *private_data,
 			break;
 		}
 		io_schedule();
-		has_sleeper = true;
 		set_current_state(TASK_UNINTERRUPTIBLE);
 	} while (1);
 	finish_wait(&rqw->wait, &data.wq);
-- 
2.24.3 (Apple Git-128)


^ permalink raw reply related	[flat|nested] 7+ messages in thread
end of thread, other threads:[~2021-04-29  5:37 UTC | newest]

Thread overview: 7+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2021-04-29  5:37 [block] 658f2fb7d2: fxmark.hdd_f2fs_dbench_client_72_directio.works/sec -21.4% regression Chien Nguyenmau
  -- strict thread matches above, loose matches on Subject: below --
2021-04-14 21:18 [PATCH] block: fix io hung by block throttle Junxiao Bi
2021-04-23  2:55 ` [block] 658f2fb7d2: fxmark.hdd_f2fs_dbench_client_72_directio.works/sec -21.4% regression kernel test robot
2021-04-23  2:55   ` kernel test robot
2021-04-23  5:26   ` Junxiao Bi
2021-04-23  5:26     ` Junxiao Bi
2021-04-28 21:08   ` Junxiao Bi
2021-04-28 21:08     ` Junxiao Bi

This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.