From: Ming Lei <ming.lei@xxxxxxxxxx>
commit 245a489e81e13dd55ae46d27becf6d5901eb7828 upstream.
elevator_init_mq() is only called before adding disk, when there isn't
any FS I/O, only passthrough requests can be queued, so freezing queue
plus canceling dispatch work is enough to drain any dispatch activities,
then we can avoid synchronize_srcu() in blk_mq_quiesce_queue().
Long boot latency issue can be fixed in case of lots of disks added
during booting.
Fixes: 737eb78e82d5 ("block: Delay default elevator initialization")
Reported-by: yangerkun <yangerkun@xxxxxxxxxx>
Cc: Damien Le Moal <damien.lemoal@xxxxxxx>
Signed-off-by: Ming Lei <ming.lei@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20211117115502.1600950-1-ming.lei@xxxxxxxxxx
Signed-off-by: Jens Axboe <axboe@xxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
block/elevator.c | 10 ++++++++--
1 file changed, 8 insertions(+), 2 deletions(-)
--- a/block/elevator.c
+++ b/block/elevator.c
@@ -694,12 +694,18 @@ void elevator_init_mq(struct request_que
if (!e)
return;
+ /*
+ * We are called before adding disk, when there isn't any FS I/O,
+ * so freezing queue plus canceling dispatch work is enough to
+ * drain any dispatch activities originated from passthrough
+ * requests, then no need to quiesce queue which may add long boot
+ * latency, especially when lots of disks are involved.
+ */
blk_mq_freeze_queue(q);
- blk_mq_quiesce_queue(q);
+ blk_mq_cancel_work_sync(q);
err = blk_mq_init_sched(q, e);
- blk_mq_unquiesce_queue(q);
blk_mq_unfreeze_queue(q);
if (err) {
