| Message ID | 20181128133538.20329-8-axboe@kernel.dk (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | block plugging improvements | expand |
On Wed, Nov 28, 2018 at 06:35:38AM -0700, Jens Axboe wrote: > If we have that hook, we know the driver handles bd->last == true in > a smart fashion. If it does, even for multiple hardware queues, it's > a good idea to flush batches of requests to the device, if we have > batches of requests from the submitter. > > Signed-off-by: Jens Axboe <axboe@kernel.dk> > --- > block/blk-mq.c | 7 ++++++- > 1 file changed, 6 insertions(+), 1 deletion(-) > > diff --git a/block/blk-mq.c b/block/blk-mq.c > index 9e1045152e45..091557a43d53 100644 > --- a/block/blk-mq.c > +++ b/block/blk-mq.c > @@ -1945,7 +1945,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) > /* bypass scheduler for flush rq */ > blk_insert_flush(rq); > blk_mq_run_hw_queue(data.hctx, true); > - } else if (plug && q->nr_hw_queues == 1) { > + } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) { > + /* > + * Use plugging if we have a ->commit_rqs() hook as well, > + * as we know the driver uses bd->last in a smart > + * fashion. > + */ > unsigned int request_count = plug->rq_count; > struct request *last = NULL; > > -- > 2.17.1 > Reviewed-by: Ming Lei <ming.lei@redhat.com> thanks, Ming
> + /* > + * Use plugging if we have a ->commit_rqs() hook as well, > + * as we know the driver uses bd->last in a smart > + * fashion. > + */ Nipick: this could flow on just two lines: /* * Use plugging if we have a ->commit_rqs() hook as well, as we * know the driver uses bd->last in a smart fashion. */
On Thu, Nov 29, 2018 at 07:49:59AM -0800, Christoph Hellwig wrote: > > + /* > > + * Use plugging if we have a ->commit_rqs() hook as well, > > + * as we know the driver uses bd->last in a smart > > + * fashion. > > + */ > > Nipick: this could flow on just two lines: > > /* > * Use plugging if we have a ->commit_rqs() hook as well, as we > * know the driver uses bd->last in a smart fashion. > */ But of course otherwise this looks fine: Reviewed-by: Christoph Hellwig <hch@lst.de>
On 11/29/18 8:49 AM, Christoph Hellwig wrote: >> + /* >> + * Use plugging if we have a ->commit_rqs() hook as well, >> + * as we know the driver uses bd->last in a smart >> + * fashion. >> + */ > > Nipick: this could flow on just two lines: > > /* > * Use plugging if we have a ->commit_rqs() hook as well, as we > * know the driver uses bd->last in a smart fashion. > */ Fixed up.
Reviewed-by: Sagi Grimberg <sagi@grimberg.me>
diff --git a/block/blk-mq.c b/block/blk-mq.c index 9e1045152e45..091557a43d53 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1945,7 +1945,12 @@ static blk_qc_t blk_mq_make_request(struct request_queue *q, struct bio *bio) /* bypass scheduler for flush rq */ blk_insert_flush(rq); blk_mq_run_hw_queue(data.hctx, true); - } else if (plug && q->nr_hw_queues == 1) { + } else if (plug && (q->nr_hw_queues == 1 || q->mq_ops->commit_rqs)) { + /* + * Use plugging if we have a ->commit_rqs() hook as well, + * as we know the driver uses bd->last in a smart + * fashion. + */ unsigned int request_count = plug->rq_count; struct request *last = NULL;
If we have that hook, we know the driver handles bd->last == true in a smart fashion. If it does, even for multiple hardware queues, it's a good idea to flush batches of requests to the device, if we have batches of requests from the submitter. Signed-off-by: Jens Axboe <axboe@kernel.dk> --- block/blk-mq.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)