[PATCH v5 2/6] block: wire-up support for passthrough plugging

[Ming Lei]

On Thu, May 12, 2022 at 05:20:47PM +0530, Anuj Gupta wrote:
> On Thu, May 12, 2022 at 01:25:24PM +0800, Ming Lei wrote:
> > Hello,
> > 
> > On Wed, May 11, 2022 at 11:17:46AM +0530, Kanchan Joshi wrote:
> > > From: Jens Axboe <axboe at kernel.dk>
> > > 
> > > Add support for plugging in passthrough path. When plugging is enabled, the
> > > requests are added to a plug instead of getting dispatched to the driver.
> > > And when the plug is finished, the whole batch gets dispatched via
> > > ->queue_rqs which turns out to be more efficient. Otherwise dispatching
> > > used to happen via ->queue_rq, one request at a time.
> > > 
> > > Signed-off-by: Jens Axboe <axboe at kernel.dk>
> > > Reviewed-by: Christoph Hellwig <hch at lst.de>
> > > ---
> > >  block/blk-mq.c | 73 +++++++++++++++++++++++++++-----------------------
> > >  1 file changed, 39 insertions(+), 34 deletions(-)
> > > 
> > > diff --git a/block/blk-mq.c b/block/blk-mq.c
> > > index 84d749511f55..2cf011b57cf9 100644
> > > --- a/block/blk-mq.c
> > > +++ b/block/blk-mq.c
> > > @@ -2340,6 +2340,40 @@ void __blk_mq_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
> > >  	blk_mq_hctx_mark_pending(hctx, ctx);
> > >  }
> > >  
> > > +/*
> > > + * Allow 2x BLK_MAX_REQUEST_COUNT requests on plug queue for multiple
> > > + * queues. This is important for md arrays to benefit from merging
> > > + * requests.
> > > + */
> > > +static inline unsigned short blk_plug_max_rq_count(struct blk_plug *plug)
> > > +{
> > > +	if (plug->multiple_queues)
> > > +		return BLK_MAX_REQUEST_COUNT * 2;
> > > +	return BLK_MAX_REQUEST_COUNT;
> > > +}
> > > +
> > > +static void blk_add_rq_to_plug(struct blk_plug *plug, struct request *rq)
> > > +{
> > > +	struct request *last = rq_list_peek(&plug->mq_list);
> > > +
> > > +	if (!plug->rq_count) {
> > > +		trace_block_plug(rq->q);
> > > +	} else if (plug->rq_count >= blk_plug_max_rq_count(plug) ||
> > > +		   (!blk_queue_nomerges(rq->q) &&
> > > +		    blk_rq_bytes(last) >= BLK_PLUG_FLUSH_SIZE)) {
> > > +		blk_mq_flush_plug_list(plug, false);
> > > +		trace_block_plug(rq->q);
> > > +	}
> > > +
> > > +	if (!plug->multiple_queues && last && last->q != rq->q)
> > > +		plug->multiple_queues = true;
> > > +	if (!plug->has_elevator && (rq->rq_flags & RQF_ELV))
> > > +		plug->has_elevator = true;
> > > +	rq->rq_next = NULL;
> > > +	rq_list_add(&plug->mq_list, rq);
> > > +	plug->rq_count++;
> > > +}
> > > +
> > >  /**
> > >   * blk_mq_request_bypass_insert - Insert a request at dispatch list.
> > >   * @rq: Pointer to request to be inserted.
> > > @@ -2353,7 +2387,12 @@ void blk_mq_request_bypass_insert(struct request *rq, bool at_head,
> > >  				  bool run_queue)
> > >  {
> > >  	struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
> > > +	struct blk_plug *plug = current->plug;
> > >  
> > > +	if (plug) {
> > > +		blk_add_rq_to_plug(plug, rq);
> > > +		return;
> > > +	}
> > 
> > This way may cause nested plugging, and breaks xfstests generic/131.
> > Also may cause io hang since request can't be polled before flushing
> > plug in blk_execute_rq().
> >
> Hi Ming,
> Could you please share your test setup.
> I tried test 131 with xfs and it passed.
> 
> I followed these steps:
> 1) mkfs.xfs -f /dev/nvme0n1
> 2) mount /dev/nvme0n1 /mnt/test
> 3) ./check tests/generic/131

It is triggered when I run xfstests over UBD & xfs:

https://github.com/ming1/linux/tree/my_for-5.18-ubd-devel_v2
https://github.com/ming1/ubdsrv/tree/devel-v2



Thanks,
Ming