[PATCH AUTOSEL for 4.14 033/161] dm mpath: return DM_MAPIO_REQUEUE on blk-mq rq allocation failure

[Sasha Levin]

From: Ming Lei 

[ Upstream commit 050af08ffb1b62af69196d61c22a0755f9a3cdbd ]

blk-mq will rerun queue via RESTART or dispatch wake after one request
is completed, so not necessary to wait random time for requeuing, we
should trust blk-mq to do it.

More importantly, we need to return BLK_STS_RESOURCE to blk-mq so that
dequeuing from the I/O scheduler can be stopped, this results in
improved I/O merging.

Signed-off-by: Ming Lei 
Signed-off-by: Mike Snitzer 
Signed-off-by: Sasha Levin 
---
 drivers/md/dm-mpath.c | 14 +-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 2704a55f8b6e..8b7328666eaa 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -502,8 +502,20 @@ static int multipath_clone_and_map(struct dm_target *ti, 
struct request *rq,
if (queue_dying) {
atomic_inc(>pg_init_in_progress);
activate_or_offline_path(pgpath);
+   return DM_MAPIO_DELAY_REQUEUE;
}
-   return DM_MAPIO_DELAY_REQUEUE;
+
+   /*
+* blk-mq's SCHED_RESTART can cover this requeue, so we
+* needn't deal with it by DELAY_REQUEUE. More importantly,
+* we have to return DM_MAPIO_REQUEUE so that blk-mq can
+* get the queue busy feedback (via BLK_STS_RESOURCE),
+* otherwise I/O merging can suffer.
+*/
+   if (q->mq_ops)
+   return DM_MAPIO_REQUEUE;
+   else
+   return DM_MAPIO_DELAY_REQUEUE;
}
clone->bio = clone->biotail = NULL;
clone->rq_disk = bdev->bd_disk;
-- 
2.15.1

[PATCH AUTOSEL for 4.14 033/161] dm mpath: return DM_MAPIO_REQUEUE on blk-mq rq allocation failure

[Sasha Levin]

From: Ming Lei 

[ Upstream commit 050af08ffb1b62af69196d61c22a0755f9a3cdbd ]

blk-mq will rerun queue via RESTART or dispatch wake after one request
is completed, so not necessary to wait random time for requeuing, we
should trust blk-mq to do it.

More importantly, we need to return BLK_STS_RESOURCE to blk-mq so that
dequeuing from the I/O scheduler can be stopped, this results in
improved I/O merging.

Signed-off-by: Ming Lei 
Signed-off-by: Mike Snitzer 
Signed-off-by: Sasha Levin 
---
 drivers/md/dm-mpath.c | 14 +-
 1 file changed, 13 insertions(+), 1 deletion(-)

diff --git a/drivers/md/dm-mpath.c b/drivers/md/dm-mpath.c
index 2704a55f8b6e..8b7328666eaa 100644
--- a/drivers/md/dm-mpath.c
+++ b/drivers/md/dm-mpath.c
@@ -502,8 +502,20 @@ static int multipath_clone_and_map(struct dm_target *ti, 
struct request *rq,
if (queue_dying) {
atomic_inc(>pg_init_in_progress);
activate_or_offline_path(pgpath);
+   return DM_MAPIO_DELAY_REQUEUE;
}
-   return DM_MAPIO_DELAY_REQUEUE;
+
+   /*
+* blk-mq's SCHED_RESTART can cover this requeue, so we
+* needn't deal with it by DELAY_REQUEUE. More importantly,
+* we have to return DM_MAPIO_REQUEUE so that blk-mq can
+* get the queue busy feedback (via BLK_STS_RESOURCE),
+* otherwise I/O merging can suffer.
+*/
+   if (q->mq_ops)
+   return DM_MAPIO_REQUEUE;
+   else
+   return DM_MAPIO_DELAY_REQUEUE;
}
clone->bio = clone->biotail = NULL;
clone->rq_disk = bdev->bd_disk;
-- 
2.15.1