* [PATCH] block: drop the cached plug time when blk_add_rq_to_plug() flushes
@ 2026-09-30 14:32 Vasileios Almpanis
2026-10-01 14:43 ` Jens Axboe
0 siblings, 1 reply; 2+ messages in thread
From: Vasileios Almpanis @ 2026-09-30 14:32 UTC (permalink / raw)
To: Jens Axboe, Johannes Thumshirn
Cc: linux-block, linux-kernel, stable, Vasileios Almpanis
blk_time_get_ns() caches the current time in the task's plug. The idea
is that the cache lives for one plug and is dropped when the plug is
flushed. __blk_flush_plug() and finish_task_switch() do that.
blk_add_rq_to_plug() also flushes, when the plug has too many requests
or the last request is at least BLK_PLUG_FLUSH_SIZE. But it calls
blk_mq_flush_plug_list() directly and never drops the cached time. So
a task that keeps submitting without sleeping stamps every request
after that with the time first cached in the plug. start_time_ns and
io_start_time_ns are stale and the disk stats charge each request for
the whole time since the plug began.
Drop the cached time after the flush, same as __blk_flush_plug() does.
Fixes: da4c8c3d0975 ("block: cache current nsec time in struct blk_plug")
Cc: stable@vger.kernel.org
Signed-off-by: Vasileios Almpanis <vasileios.almpanis@virtuozzo.com>
---
block/blk-mq.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/block/blk-mq.c b/block/blk-mq.c
index a26a11c73ee3..7a37d9f1647d 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -1384,6 +1384,7 @@ static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
(!blk_queue_nomerges(rq->q) &&
blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
blk_mq_flush_plug_list(plug, false);
+ blk_plug_invalidate_ts();
last = NULL;
trace_block_plug(rq->q);
}
---
base-commit: 551c722f40809618230001baccf219193e22fc5a
change-id: 20260930-blk-plug-ts-flush-365cde9630d8
--
Best regards, Vasileios Almpanis
Software Developer, Virtuozzo.
^ permalink raw reply [flat|nested] 2+ messages in thread* Re: [PATCH] block: drop the cached plug time when blk_add_rq_to_plug() flushes
2026-09-30 14:32 [PATCH] block: drop the cached plug time when blk_add_rq_to_plug() flushes Vasileios Almpanis
@ 2026-10-01 14:43 ` Jens Axboe
0 siblings, 0 replies; 2+ messages in thread
From: Jens Axboe @ 2026-10-01 14:43 UTC (permalink / raw)
To: Johannes Thumshirn, Vasileios Almpanis; +Cc: linux-block, linux-kernel, stable
On Wed, 30 Sep 2026 14:32:26 +0000, Vasileios Almpanis wrote:
> blk_time_get_ns() caches the current time in the task's plug. The idea
> is that the cache lives for one plug and is dropped when the plug is
> flushed. __blk_flush_plug() and finish_task_switch() do that.
>
> blk_add_rq_to_plug() also flushes, when the plug has too many requests
> or the last request is at least BLK_PLUG_FLUSH_SIZE. But it calls
> blk_mq_flush_plug_list() directly and never drops the cached time. So
> a task that keeps submitting without sleeping stamps every request
> after that with the time first cached in the plug. start_time_ns and
> io_start_time_ns are stale and the disk stats charge each request for
> the whole time since the plug began.
>
> [...]
Applied, thanks!
[1/1] block: drop the cached plug time when blk_add_rq_to_plug() flushes
commit: e0f2224433b15a57125d6ac5d46182f99c6c9d08
Best regards,
--
Jens Axboe
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2026-10-01 14:43 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2026-09-30 14:32 [PATCH] block: drop the cached plug time when blk_add_rq_to_plug() flushes Vasileios Almpanis
2026-10-01 14:43 ` Jens Axboe
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®