diff options
| author | Ming Lei <ming.lei@redhat.com> | 2021-12-03 14:15:32 +0100 |
|---|---|---|
| committer | Jens Axboe <axboe@kernel.dk> | 2021-12-03 22:51:29 +0100 |
| commit | 704b914f15fb7daaf517e3acc4bed472b50ca19e (patch) | |
| tree | 5fffc1140fef4ddceeaae58e44fbb65333c33861 /block/blk-sysfs.c | |
| parent | blk-mq: remove hctx_lock and hctx_unlock (diff) | |
| download | linux-704b914f15fb7daaf517e3acc4bed472b50ca19e.tar.xz linux-704b914f15fb7daaf517e3acc4bed472b50ca19e.zip | |
blk-mq: move srcu from blk_mq_hw_ctx to request_queue
In case of BLK_MQ_F_BLOCKING, per-hctx srcu is used to protect dispatch
critical area. However, this srcu instance stays at the end of hctx, and
it often takes standalone cacheline, often cold.
Inside srcu_read_lock() and srcu_read_unlock(), WRITE is always done on
the indirect percpu variable which is allocated from heap instead of
being embedded, srcu->srcu_idx is read only in srcu_read_lock(). It
doesn't matter if srcu structure stays in hctx or request queue.
So switch to per-request-queue srcu for protecting dispatch, and this
way simplifies quiesce a lot, not mention quiesce is always done on the
request queue wide.
Signed-off-by: Ming Lei <ming.lei@redhat.com>
Link: https://lore.kernel.org/r/20211203131534.3668411-3-ming.lei@redhat.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Diffstat (limited to 'block/blk-sysfs.c')
| -rw-r--r-- | block/blk-sysfs.c | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c index 4622da4bb992..3e6357321225 100644 --- a/block/blk-sysfs.c +++ b/block/blk-sysfs.c @@ -735,7 +735,8 @@ static void blk_free_queue_rcu(struct rcu_head *rcu_head) { struct request_queue *q = container_of(rcu_head, struct request_queue, rcu_head); - kmem_cache_free(blk_requestq_cachep, q); + + kmem_cache_free(blk_get_queue_kmem_cache(blk_queue_has_srcu(q)), q); } /* Unconfigure the I/O scheduler and dissociate from the cgroup controller. */ |