* [PATCH] block: fix potential IO hang when turning off io_poll
@ 2021-02-22 6:54 Jeffle Xu
2021-02-22 7:12 ` Joseph Qi
2021-02-22 13:40 ` Jens Axboe
0 siblings, 2 replies; 4+ messages in thread
From: Jeffle Xu @ 2021-02-22 6:54 UTC (permalink / raw)
To: axboe; +Cc: linux-block, io-uring, joseph.qi
QUEUE_FLAG_POLL flag will be cleared when turning off 'io_poll', while
at that moment there may be IOs stuck in hw queue uncompleted. The
following polling routine won't help reap these IOs, since blk_poll()
will return immediately because of cleared QUEUE_FLAG_POLL flag. Thus
these IOs will hang until they finnaly time out. The hang out can be
observed by 'fio --engine=io_uring iodepth=1', while turning off
'io_poll' at the same time.
To fix this, freeze and flush the request queue first when turning off
'io_poll'.
Signed-off-by: Jeffle Xu <[email protected]>
---
block/blk-sysfs.c | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index b513f1683af0..10d74741c002 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -430,8 +430,11 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
if (poll_on)
blk_queue_flag_set(QUEUE_FLAG_POLL, q);
- else
+ else {
+ blk_mq_freeze_queue(q);
blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
+ blk_mq_unfreeze_queue(q);
+ }
return ret;
}
--
2.27.0
^ permalink raw reply related [flat|nested] 4+ messages in thread* Re: [PATCH] block: fix potential IO hang when turning off io_poll
2021-02-22 6:54 [PATCH] block: fix potential IO hang when turning off io_poll Jeffle Xu
@ 2021-02-22 7:12 ` Joseph Qi
2021-02-22 7:46 ` JeffleXu
2021-02-22 13:40 ` Jens Axboe
1 sibling, 1 reply; 4+ messages in thread
From: Joseph Qi @ 2021-02-22 7:12 UTC (permalink / raw)
To: Jeffle Xu, axboe; +Cc: linux-block, io-uring
On 2/22/21 2:54 PM, Jeffle Xu wrote:
> QUEUE_FLAG_POLL flag will be cleared when turning off 'io_poll', while
> at that moment there may be IOs stuck in hw queue uncompleted. The
> following polling routine won't help reap these IOs, since blk_poll()
> will return immediately because of cleared QUEUE_FLAG_POLL flag. Thus
> these IOs will hang until they finnaly time out. The hang out can be
> observed by 'fio --engine=io_uring iodepth=1', while turning off
> 'io_poll' at the same time.
>
> To fix this, freeze and flush the request queue first when turning off
> 'io_poll'.
>
> Signed-off-by: Jeffle Xu <[email protected]>
> ---
> block/blk-sysfs.c | 5 ++++-
> 1 file changed, 4 insertions(+), 1 deletion(-)
>
> diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
> index b513f1683af0..10d74741c002 100644
> --- a/block/blk-sysfs.c
> +++ b/block/blk-sysfs.c
> @@ -430,8 +430,11 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
>
> if (poll_on)
> blk_queue_flag_set(QUEUE_FLAG_POLL, q);
> - else
> + else {
> + blk_mq_freeze_queue(q);
> blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
> + blk_mq_unfreeze_queue(q);
> + }
>
> return ret;
> }
>
Better to place brace to 'if' as well.
Thanks,
Joseph
^ permalink raw reply [flat|nested] 4+ messages in thread* Re: [PATCH] block: fix potential IO hang when turning off io_poll
2021-02-22 7:12 ` Joseph Qi
@ 2021-02-22 7:46 ` JeffleXu
0 siblings, 0 replies; 4+ messages in thread
From: JeffleXu @ 2021-02-22 7:46 UTC (permalink / raw)
To: Joseph Qi, axboe; +Cc: linux-block, io-uring
On 2/22/21 3:12 PM, Joseph Qi wrote:
>
>
> On 2/22/21 2:54 PM, Jeffle Xu wrote:
>> QUEUE_FLAG_POLL flag will be cleared when turning off 'io_poll', while
>> at that moment there may be IOs stuck in hw queue uncompleted. The
>> following polling routine won't help reap these IOs, since blk_poll()
>> will return immediately because of cleared QUEUE_FLAG_POLL flag. Thus
>> these IOs will hang until they finnaly time out. The hang out can be
>> observed by 'fio --engine=io_uring iodepth=1', while turning off
>> 'io_poll' at the same time.
>>
>> To fix this, freeze and flush the request queue first when turning off
>> 'io_poll'.
>>
>> Signed-off-by: Jeffle Xu <[email protected]>
>> ---
>> block/blk-sysfs.c | 5 ++++-
>> 1 file changed, 4 insertions(+), 1 deletion(-)
>>
>> diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
>> index b513f1683af0..10d74741c002 100644
>> --- a/block/blk-sysfs.c
>> +++ b/block/blk-sysfs.c
>> @@ -430,8 +430,11 @@ static ssize_t queue_poll_store(struct request_queue *q, const char *page,
>>
>> if (poll_on)
>> blk_queue_flag_set(QUEUE_FLAG_POLL, q);
>> - else
>> + else {
>> + blk_mq_freeze_queue(q);
>> blk_queue_flag_clear(QUEUE_FLAG_POLL, q);
>> + blk_mq_unfreeze_queue(q);
>> + }
>>
>> return ret;
>> }
>>
>
> Better to place brace to 'if' as well.
Got it, thanks.
--
Thanks,
Jeffle
^ permalink raw reply [flat|nested] 4+ messages in thread
* Re: [PATCH] block: fix potential IO hang when turning off io_poll
2021-02-22 6:54 [PATCH] block: fix potential IO hang when turning off io_poll Jeffle Xu
2021-02-22 7:12 ` Joseph Qi
@ 2021-02-22 13:40 ` Jens Axboe
1 sibling, 0 replies; 4+ messages in thread
From: Jens Axboe @ 2021-02-22 13:40 UTC (permalink / raw)
To: Jeffle Xu; +Cc: linux-block, io-uring, joseph.qi
On 2/21/21 11:54 PM, Jeffle Xu wrote:
> QUEUE_FLAG_POLL flag will be cleared when turning off 'io_poll', while
> at that moment there may be IOs stuck in hw queue uncompleted. The
> following polling routine won't help reap these IOs, since blk_poll()
> will return immediately because of cleared QUEUE_FLAG_POLL flag. Thus
> these IOs will hang until they finnaly time out. The hang out can be
> observed by 'fio --engine=io_uring iodepth=1', while turning off
> 'io_poll' at the same time.
>
> To fix this, freeze and flush the request queue first when turning off
> 'io_poll'.
Applied, thanks. Fixed up the braces.
--
Jens Axboe
^ permalink raw reply [flat|nested] 4+ messages in thread
end of thread, other threads:[~2021-02-22 13:44 UTC | newest]
Thread overview: 4+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2021-02-22 6:54 [PATCH] block: fix potential IO hang when turning off io_poll Jeffle Xu
2021-02-22 7:12 ` Joseph Qi
2021-02-22 7:46 ` JeffleXu
2021-02-22 13:40 ` Jens Axboe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox