Re: [PATCH v3] blk-mq: fix io hung due to missing commit_rqs

From: Yu Kuai
Date: Sat Aug 13 2022 - 02:00:47 EST


在 2022/07/29 14:35, Yu Kuai 写道:
Hi, Jens

Can you please consider this patch for v5.20?

friendly ping ...
Thanks,
Kuai

在 2022/07/27 11:08, Ming Lei 写道:
On Tue, Jul 26, 2022 at 08:22:24PM +0800, Yu Kuai wrote:
From: Yu Kuai <yukuai3@xxxxxxxxxx>

Currently, in virtio_scsi, if 'bd->last' is not set to true while
dispatching request, such io will stay in driver's queue, and driver
will wait for block layer to dispatch more rqs. However, if block
layer failed to dispatch more rq, it should trigger commit_rqs to
inform driver.

There is a problem in blk_mq_try_issue_list_directly() that commit_rqs
won't be called:

// assume that queue_depth is set to 1, list contains two rq
blk_mq_try_issue_list_directly
  blk_mq_request_issue_directly
  // dispatch first rq
  // last is false
   __blk_mq_try_issue_directly
    blk_mq_get_dispatch_budget
    // succeed to get first budget
    __blk_mq_issue_directly
     scsi_queue_rq
      cmd->flags |= SCMD_LAST
       virtscsi_queuecommand
        kick = (sc->flags & SCMD_LAST) != 0
        // kick is false, first rq won't issue to disk
  queued++

  blk_mq_request_issue_directly
  // dispatch second rq
   __blk_mq_try_issue_directly
    blk_mq_get_dispatch_budget
    // failed to get second budget
  ret == BLK_STS_RESOURCE
   blk_mq_request_bypass_insert
  // errors is still 0

  if (!list_empty(list) || errors && ...)
   // won't pass, commit_rqs won't be called

In this situation, first rq relied on second rq to dispatch, while
second rq relied on first rq to complete, thus they will both hung.

Fix the problem by also treat 'BLK_STS_*RESOURCE' as 'errors' since
it means that request is not queued successfully.

Same problem exists in blk_mq_dispatch_rq_list(), 'BLK_STS_*RESOURCE'
can't be treated as 'errors' here, fix the problem by calling
commit_rqs if queue_rq return 'BLK_STS_*RESOURCE'.

Fixes: d666ba98f849 ("blk-mq: add mq_ops->commit_rqs()")
Signed-off-by: Yu Kuai <yukuai3@xxxxxxxxxx>

Reviewed-by: Ming Lei <ming.lei@xxxxxxxxxx>

Thanks,
Ming

.


.