Pavel Begunkov 2b85edfc0c io_uring: batch getting pcpu references
percpu_ref_tryget() has its own overhead. Instead getting a reference
for each request, grab a bunch once per io_submit_sqes().

~5% throughput boost for a "submit and wait 128 nops" benchmark.

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>

__io_req_free_empty() -> __io_req_do_free()

Signed-off-by: Jens Axboe <axboe@kernel.dk>
2020-01-20 17:04:02 -07:00
..
2019-09-27 15:10:34 -07:00
2020-01-17 11:21:05 -08:00
2019-09-19 09:42:37 -07:00
2019-12-09 10:36:44 -08:00
2019-07-12 17:37:53 -07:00
2019-12-11 12:25:32 -08:00
2019-11-11 09:21:59 -05:00
\n
2019-11-30 11:16:07 -08:00
2019-12-05 13:20:11 -08:00
2019-09-19 09:42:37 -07:00
2019-09-19 09:42:37 -07:00
2019-12-14 11:13:54 -08:00
2019-09-19 09:42:37 -07:00
2019-12-09 10:36:44 -08:00
2019-12-01 14:00:59 -08:00
2019-12-02 14:46:22 -08:00
2019-11-30 10:44:49 -08:00
2019-08-07 21:51:47 -04:00
2019-12-02 14:46:22 -08:00
2019-10-14 15:04:01 -07:00