diff mbox series

[SRU,j:linux-gke,1/1] blk-mq: fix blk_mq_hw_ctx active request accounting

Message ID 20241030155034.87362-2-ian.whitfield@canonical.com
State New
Headers show
Series fix blk_mq_hw_ctx active request | expand

Commit Message

Ian Whitfield Oct. 30, 2024, 3:50 p.m. UTC 
From: Tian Lan <tian.lan@twosigma.com>

The nr_active counter continues to increase over time which causes the
blk_mq_get_tag to hang until the thread is rescheduled to a different
core despite there are still tags available.

kernel-stack

  INFO: task inboundIOReacto:3014879 blocked for more than 2 seconds
  Not tainted 6.1.15-amd64 #1 Debian 6.1.15~debian11
  "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
  task:inboundIOReacto state:D stack:0  pid:3014879 ppid:4557 flags:0x00000000
    Call Trace:
    <TASK>
    __schedule+0x351/0xa20
    scheduler+0x5d/0xe0
    io_schedule+0x42/0x70
    blk_mq_get_tag+0x11a/0x2a0
    ? dequeue_task_stop+0x70/0x70
    __blk_mq_alloc_requests+0x191/0x2e0

kprobe output showing RQF_MQ_INFLIGHT bit is not cleared before
__blk_mq_free_request being called.

  320    320  kworker/29:1H __blk_mq_free_request rq_flags 0x220c0 in-flight 1
         b'__blk_mq_free_request+0x1 [kernel]'
         b'bt_iter+0x50 [kernel]'
         b'blk_mq_queue_tag_busy_iter+0x318 [kernel]'
         b'blk_mq_timeout_work+0x7c [kernel]'
         b'process_one_work+0x1c4 [kernel]'
         b'worker_thread+0x4d [kernel]'
         b'kthread+0xe6 [kernel]'
         b'ret_from_fork+0x1f [kernel]'

Signed-off-by: Tian Lan <tian.lan@twosigma.com>
Fixes: 2e315dc07df0 ("blk-mq: grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter")
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20230513221227.497327-1-tilan7663@gmail.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
(backported from commit ddad59331a4e16088468ca0ad228a9fe32d7955a)
[ijwhitfield: Context adjusted due to missing commits:
9a14d6ce4135 ("block: remove debugfs blk_mq_ctx dispatched/merged/completed attributes")
222ee581b845 ("block: move the remaining elv.icq handling to the I/O scheduler")]
Signed-off-by: Ian Whitfield <ian.whitfield@canonical.com>
---
 block/blk-mq.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

Comments

Jian Hui Lee Nov. 4, 2024, 2:41 a.m. UTC | #1 
Hi Ian,

Missing the bug link in the patch description. Please add it while
committing the change.
Other than that,
Acked-by: Jian Hui Lee <jianhui.lee@canonical.com>

On Wed, Oct 30, 2024 at 11:51 PM Ian Whitfield
<ian.whitfield@canonical.com> wrote:
>
> From: Tian Lan <tian.lan@twosigma.com>
>
> The nr_active counter continues to increase over time which causes the
> blk_mq_get_tag to hang until the thread is rescheduled to a different
> core despite there are still tags available.
>
> kernel-stack
>
>   INFO: task inboundIOReacto:3014879 blocked for more than 2 seconds
>   Not tainted 6.1.15-amd64 #1 Debian 6.1.15~debian11
>   "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
>   task:inboundIOReacto state:D stack:0  pid:3014879 ppid:4557 flags:0x00000000
>     Call Trace:
>     <TASK>
>     __schedule+0x351/0xa20
>     scheduler+0x5d/0xe0
>     io_schedule+0x42/0x70
>     blk_mq_get_tag+0x11a/0x2a0
>     ? dequeue_task_stop+0x70/0x70
>     __blk_mq_alloc_requests+0x191/0x2e0
>
> kprobe output showing RQF_MQ_INFLIGHT bit is not cleared before
> __blk_mq_free_request being called.
>
>   320    320  kworker/29:1H __blk_mq_free_request rq_flags 0x220c0 in-flight 1
>          b'__blk_mq_free_request+0x1 [kernel]'
>          b'bt_iter+0x50 [kernel]'
>          b'blk_mq_queue_tag_busy_iter+0x318 [kernel]'
>          b'blk_mq_timeout_work+0x7c [kernel]'
>          b'process_one_work+0x1c4 [kernel]'
>          b'worker_thread+0x4d [kernel]'
>          b'kthread+0xe6 [kernel]'
>          b'ret_from_fork+0x1f [kernel]'
>
> Signed-off-by: Tian Lan <tian.lan@twosigma.com>
> Fixes: 2e315dc07df0 ("blk-mq: grab rq->refcount before calling ->fn in blk_mq_tagset_busy_iter")
> Reviewed-by: Ming Lei <ming.lei@redhat.com>
> Link: https://lore.kernel.org/r/20230513221227.497327-1-tilan7663@gmail.com
> Signed-off-by: Jens Axboe <axboe@kernel.dk>
> (backported from commit ddad59331a4e16088468ca0ad228a9fe32d7955a)
> [ijwhitfield: Context adjusted due to missing commits:
> 9a14d6ce4135 ("block: remove debugfs blk_mq_ctx dispatched/merged/completed attributes")
> 222ee581b845 ("block: move the remaining elv.icq handling to the I/O scheduler")]
> Signed-off-by: Ian Whitfield <ian.whitfield@canonical.com>
> ---
>  block/blk-mq.c | 8 ++++----
>  1 file changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/block/blk-mq.c b/block/blk-mq.c
> index d80ebba16778..79030318e821 100644
> --- a/block/blk-mq.c
> +++ b/block/blk-mq.c
> @@ -506,6 +506,10 @@ static void __blk_mq_free_request(struct request *rq)
>         blk_crypto_free_request(rq);
>         blk_pm_mark_last_busy(rq);
>         rq->mq_hctx = NULL;
> +
> +       if (rq->rq_flags & RQF_MQ_INFLIGHT)
> +               __blk_mq_dec_active_requests(hctx);
> +
>         if (rq->tag != BLK_MQ_NO_TAG)
>                 blk_mq_put_tag(hctx->tags, ctx, rq->tag);
>         if (sched_tag != BLK_MQ_NO_TAG)
> @@ -519,7 +523,6 @@ void blk_mq_free_request(struct request *rq)
>         struct request_queue *q = rq->q;
>         struct elevator_queue *e = q->elevator;
>         struct blk_mq_ctx *ctx = rq->mq_ctx;
> -       struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
>
>         if (rq->rq_flags & RQF_ELVPRIV) {
>                 if (e && e->type->ops.finish_request)
> @@ -531,9 +534,6 @@ void blk_mq_free_request(struct request *rq)
>         }
>
>         ctx->rq_completed[rq_is_sync(rq)]++;
> -       if (rq->rq_flags & RQF_MQ_INFLIGHT)
> -               __blk_mq_dec_active_requests(hctx);
> -
>         if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
>                 laptop_io_completion(q->disk->bdi);
>
> --
> 2.43.0
>
>
> --
> kernel-team mailing list
> kernel-team@lists.ubuntu.com
> https://lists.ubuntu.com/mailman/listinfo/kernel-team
diff mbox series

Patch

diff --git a/block/blk-mq.c b/block/blk-mq.c
index d80ebba16778..79030318e821 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -506,6 +506,10 @@  static void __blk_mq_free_request(struct request *rq)
 	blk_crypto_free_request(rq);
 	blk_pm_mark_last_busy(rq);
 	rq->mq_hctx = NULL;
+
+	if (rq->rq_flags & RQF_MQ_INFLIGHT)
+		__blk_mq_dec_active_requests(hctx);
+
 	if (rq->tag != BLK_MQ_NO_TAG)
 		blk_mq_put_tag(hctx->tags, ctx, rq->tag);
 	if (sched_tag != BLK_MQ_NO_TAG)
@@ -519,7 +523,6 @@  void blk_mq_free_request(struct request *rq)
 	struct request_queue *q = rq->q;
 	struct elevator_queue *e = q->elevator;
 	struct blk_mq_ctx *ctx = rq->mq_ctx;
-	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
 
 	if (rq->rq_flags & RQF_ELVPRIV) {
 		if (e && e->type->ops.finish_request)
@@ -531,9 +534,6 @@  void blk_mq_free_request(struct request *rq)
 	}
 
 	ctx->rq_completed[rq_is_sync(rq)]++;
-	if (rq->rq_flags & RQF_MQ_INFLIGHT)
-		__blk_mq_dec_active_requests(hctx);
-
 	if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
 		laptop_io_completion(q->disk->bdi);