On Mon, 2015-07-13 at 11:35 -0400, Mike Snitzer wrote: > I will do additional review to answer 1 and 2 above. And Jeff Moyer > told me he'd test the patchset on one of his testbeds. Hi Jeff, FYI, here is a fix for patch 1. Or you can pull from my tree. https://git.kernel.org/cgit/linux/kernel/git/mlin/linux.git/log/?h=block-generic-req diff --git a/block/blk-mq.c b/block/blk-mq.c index 40d08e3..181f343 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -1287,12 +1287,12 @@ static void blk_mq_make_request(struct request_queue *q, struct bio *bio) return; } + blk_queue_split(q, &bio, q->bio_split); + if (!is_flush_fua && !blk_queue_nomerges(q) && blk_attempt_plug_merge(q, bio, &request_count, &same_queue_rq)) return; - blk_queue_split(q, &bio, q->bio_split); - rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) return; @@ -1374,12 +1374,12 @@ static void blk_sq_make_request(struct request_queue *q, struct bio *bio) return; } + blk_queue_split(q, &bio, q->bio_split); + if (!is_flush_fua && !blk_queue_nomerges(q) && blk_attempt_plug_merge(q, bio, &request_count, NULL)) return; - blk_queue_split(q, &bio, q->bio_split); - rq = blk_mq_map_request(q, bio, &data); if (unlikely(!rq)) return; -- dm-devel mailing list dm-devel@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/dm-devel
