On Wed, May 24, 2017 at 02:58:43AM -0700, Christoph Hellwig wrote:
> On Tue, May 23, 2017 at 07:47:36PM +0800, Ming Lei wrote:
> > Because what the per-sw-queue bio merge does is basically same with
> > scheduler's .bio_merge(), this patch makes per-sw-queue bio merge
> > as the default .bio_merge if no scheduler is used or io scheduler
> > doesn't provide .bio_merge().
> >
> > Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
> > ---
> > block/blk-mq-sched.c | 62 +++++++++++++++++++++++++++++++++++++++++++++----
> > block/blk-mq-sched.h | 4 +---
> > block/blk-mq.c | 65 ----------------------------------------------------
> > 3 files changed, 58 insertions(+), 73 deletions(-)
> >
> > diff --git a/block/blk-mq-sched.c b/block/blk-mq-sched.c
> > index 1f5b692526ae..c4e2afb9d12d 100644
> > --- a/block/blk-mq-sched.c
> > +++ b/block/blk-mq-sched.c
> > @@ -221,19 +221,71 @@ bool blk_mq_sched_try_merge(struct request_queue *q, struct bio *bio,
> > }
> > EXPORT_SYMBOL_GPL(blk_mq_sched_try_merge);
> >
> > +/*
> > + * Reverse check our software queue for entries that we could potentially
> > + * merge with. Currently includes a hand-wavy stop count of 8, to not spend
> > + * too much time checking for merges.
> > + */
> > +static bool blk_mq_attempt_merge(struct request_queue *q,
> > + struct blk_mq_ctx *ctx, struct bio *bio)
> > +{
> > + struct request *rq;
> > + int checked = 8;
> > +
> > + list_for_each_entry_reverse(rq, &ctx->rq_list, queuelist) {
> > + bool merged = false;
> > +
> > + if (!checked--)
> > + break;
> > +
> > + if (!blk_rq_merge_ok(rq, bio))
> > + continue;
> > +
> > + switch (blk_try_merge(rq, bio)) {
> > + case ELEVATOR_BACK_MERGE:
> > + if (blk_mq_sched_allow_merge(q, rq, bio))
> > + merged = bio_attempt_back_merge(q, rq, bio);
> > + break;
> > + case ELEVATOR_FRONT_MERGE:
> > + if (blk_mq_sched_allow_merge(q, rq, bio))
> > + merged = bio_attempt_front_merge(q, rq, bio);
> > + break;
> > + case ELEVATOR_DISCARD_MERGE:
> > + merged = bio_attempt_discard_merge(q, rq, bio);
> > + break;
> > + default:
> > + continue;
> > + }
> > +
> > + if (merged)
> > + ctx->rq_merged++;
> > + return merged;
> > + }
> > +
> > + return false;
> > +}
> > +
> > bool __blk_mq_sched_bio_merge(struct request_queue *q, struct bio *bio)
> > {
> > struct elevator_queue *e = q->elevator;
> > + struct blk_mq_ctx *ctx = blk_mq_get_ctx(q);
> > + struct blk_mq_hw_ctx *hctx = blk_mq_map_queue(q, ctx->cpu);
> > + bool ret = false;
> >
> > + if (e && e->type->ops.mq.bio_merge) {
> > blk_mq_put_ctx(ctx);
> > return e->type->ops.mq.bio_merge(hctx, bio);
> > }
> >
> > + if (hctx->flags & BLK_MQ_F_SHOULD_MERGE) {
> > + /* default per sw-queue merge */
> > + spin_lock(&ctx->lock);
> > + ret = blk_mq_attempt_merge(q, ctx, bio);
> > + spin_unlock(&ctx->lock);
> > + }
> > +
> > + blk_mq_put_ctx(ctx);
> > + return ret;
>
> I'd rather move __blk_mq_sched_bio_merge/blk_mq_sched_bio_merge into
> blk-mq.c (and dropping the sched in the name) rather than moving
> blk_mq_attempt_merge out.
Looked at the code further, maybe it isn't good to move
__blk_mq_sched_bio_merge() to blk-mq.c because the stuff of
'e && e->type->ops.mq.*' has never been put into blk-mq.c.
So how about not moving blk_mq_attempt_merge() and just define it as
global?
Thanks,
Ming
