summaryrefslogtreecommitdiffstats
path: root/drivers/md
diff options
context:
space:
mode:
authorMing Lei <ming.lei@redhat.com>2018-01-17 11:25:57 -0500
committerJens Axboe <axboe@kernel.dk>2018-01-17 09:46:54 -0700
commit396eaf21ee17c476e8f66249fb1f4a39003d0ab4 (patch)
tree20b146db746cc279c734fd937128c45cb8ed5c76 /drivers/md
parent0f95549c0ea1e8075ae049202088b2c6a0cb40ad (diff)
downloadlinux-396eaf21ee17c476e8f66249fb1f4a39003d0ab4.tar.bz2
blk-mq: improve DM's blk-mq IO merging via blk_insert_cloned_request feedback
blk_insert_cloned_request() is called in the fast path of a dm-rq driver (e.g. blk-mq request-based DM mpath). blk_insert_cloned_request() uses blk_mq_request_bypass_insert() to directly append the request to the blk-mq hctx->dispatch_list of the underlying queue. 1) This way isn't efficient enough because the hctx spinlock is always used. 2) With blk_insert_cloned_request(), we completely bypass underlying queue's elevator and depend on the upper-level dm-rq driver's elevator to schedule IO. But dm-rq currently can't get the underlying queue's dispatch feedback at all. Without knowing whether a request was issued or not (e.g. due to underlying queue being busy) the dm-rq elevator will not be able to provide effective IO merging (as a side-effect of dm-rq currently blindly destaging a request from its elevator only to requeue it after a delay, which kills any opportunity for merging). This obviously causes very bad sequential IO performance. Fix this by updating blk_insert_cloned_request() to use blk_mq_request_direct_issue(). blk_mq_request_direct_issue() allows a request to be issued directly to the underlying queue and returns the dispatch feedback (blk_status_t). If blk_mq_request_direct_issue() returns BLK_SYS_RESOURCE the dm-rq driver will now use DM_MAPIO_REQUEUE to _not_ destage the request. Whereby preserving the opportunity to merge IO. With this, request-based DM's blk-mq sequential IO performance is vastly improved (as much as 3X in mpath/virtio-scsi testing). Signed-off-by: Ming Lei <ming.lei@redhat.com> [blk-mq.c changes heavily influenced by Ming Lei's initial solution, but they were refactored to make them less fragile and easier to read/review] Signed-off-by: Mike Snitzer <snitzer@redhat.com> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'drivers/md')
-rw-r--r--drivers/md/dm-rq.c19
1 files changed, 16 insertions, 3 deletions
diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
index c28357f5cb0e..b7d175e94a02 100644
--- a/drivers/md/dm-rq.c
+++ b/drivers/md/dm-rq.c
@@ -395,7 +395,7 @@ static void end_clone_request(struct request *clone, blk_status_t error)
dm_complete_request(tio->orig, error);
}
-static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
+static blk_status_t dm_dispatch_clone_request(struct request *clone, struct request *rq)
{
blk_status_t r;
@@ -404,9 +404,10 @@ static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
clone->start_time = jiffies;
r = blk_insert_cloned_request(clone->q, clone);
- if (r)
+ if (r != BLK_STS_OK && r != BLK_STS_RESOURCE)
/* must complete clone in terms of original request */
dm_complete_request(rq, r);
+ return r;
}
static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
@@ -476,8 +477,10 @@ static int map_request(struct dm_rq_target_io *tio)
struct mapped_device *md = tio->md;
struct request *rq = tio->orig;
struct request *clone = NULL;
+ blk_status_t ret;
r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
+check_again:
switch (r) {
case DM_MAPIO_SUBMITTED:
/* The target has taken the I/O to submit by itself later */
@@ -492,7 +495,17 @@ static int map_request(struct dm_rq_target_io *tio)
/* The target has remapped the I/O so dispatch it */
trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
blk_rq_pos(rq));
- dm_dispatch_clone_request(clone, rq);
+ ret = dm_dispatch_clone_request(clone, rq);
+ if (ret == BLK_STS_RESOURCE) {
+ blk_rq_unprep_clone(clone);
+ tio->ti->type->release_clone_rq(clone);
+ tio->clone = NULL;
+ if (!rq->q->mq_ops)
+ r = DM_MAPIO_DELAY_REQUEUE;
+ else
+ r = DM_MAPIO_REQUEUE;
+ goto check_again;
+ }
break;
case DM_MAPIO_REQUEUE:
/* The target wants to requeue the I/O */