public inbox for [email protected]
 help / color / mirror / Atom feed
* [PATCH 00/16] squeeze more performance
@ 2021-10-04 19:02 Pavel Begunkov
  2021-10-04 19:02 ` [PATCH 01/16] io_uring: optimise kiocb layout Pavel Begunkov
                   ` (16 more replies)
  0 siblings, 17 replies; 19+ messages in thread
From: Pavel Begunkov @ 2021-10-04 19:02 UTC (permalink / raw)
  To: io-uring; +Cc: Jens Axboe, asml.silence

fio/t/io_uring -s32 -d32 -c32 -N1

          | baseline  | 0-15      | 0-16        | diff
setup 1:  | 34 MIOPS  | 42 MIOPS  | 42.2  MIOPS | 25 %
setup 2:  | 31 MIOPS  | 31 MIOPS  | 32    MIOPS | ~3 $

Setup 1 gets 25% performance improvement, which is unexpected and a
share of it should be accounted as compiler/HW magic. Setup 2 is just
3%, but the catch is that some of the patches _very_ unexpectedly sink
performance, so it's more like 31 MIOPS -> 29 -> 30 -> 29 -> 31 -> 32

I'd suggest to leave 16/16 aside, maybe for future consideration and
refinement. The end result is not very clear, I'd expect probably
around 3-5% with a more stable setup for nops32, and a better win
for io_cqring_ev_posted() intensive cases like BPF.

Pavel Begunkov (16):
  io_uring: optimise kiocb layout
  io_uring: add more likely/unlikely() annotations
  io_uring: delay req queueing into compl-batch list
  io_uring: optimise request allocation
  io_uring: optimise INIT_WQ_LIST
  io_uring: don't wake sqpoll in io_cqring_ev_posted
  io_uring: merge CQ and poll waitqueues
  io_uring: optimise ctx referencing by requests
  io_uring: mark cold functions
  io_uring: optimise io_free_batch_list()
  io_uring: control ->async_data with a REQ_F flag
  io_uring: remove struct io_completion
  io_uring: inline io_req_needs_clean()
  io_uring: inline io_poll_complete
  io_uring: correct fill events helpers types
  io_uring: mark hot functions

 fs/io-wq.h    |   1 -
 fs/io_uring.c | 390 ++++++++++++++++++++++++++------------------------
 2 files changed, 205 insertions(+), 186 deletions(-)

-- 
2.33.0


^ permalink raw reply	[flat|nested] 19+ messages in thread

end of thread, other threads:[~2021-10-04 20:33 UTC | newest]

Thread overview: 19+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2021-10-04 19:02 [PATCH 00/16] squeeze more performance Pavel Begunkov
2021-10-04 19:02 ` [PATCH 01/16] io_uring: optimise kiocb layout Pavel Begunkov
2021-10-04 19:02 ` [PATCH 02/16] io_uring: add more likely/unlikely() annotations Pavel Begunkov
2021-10-04 19:02 ` [PATCH 03/16] io_uring: delay req queueing into compl-batch list Pavel Begunkov
2021-10-04 19:02 ` [PATCH 04/16] io_uring: optimise request allocation Pavel Begunkov
2021-10-04 19:02 ` [PATCH 05/16] io_uring: optimise INIT_WQ_LIST Pavel Begunkov
2021-10-04 19:02 ` [PATCH 06/16] io_uring: don't wake sqpoll in io_cqring_ev_posted Pavel Begunkov
2021-10-04 19:02 ` [PATCH 07/16] io_uring: merge CQ and poll waitqueues Pavel Begunkov
2021-10-04 19:02 ` [PATCH 08/16] io_uring: optimise ctx referencing by requests Pavel Begunkov
2021-10-04 19:02 ` [PATCH 09/16] io_uring: mark cold functions Pavel Begunkov
2021-10-04 19:02 ` [PATCH 10/16] io_uring: optimise io_free_batch_list() Pavel Begunkov
2021-10-04 19:02 ` [PATCH 11/16] io_uring: control ->async_data with a REQ_F flag Pavel Begunkov
2021-10-04 19:02 ` [PATCH 12/16] io_uring: remove struct io_completion Pavel Begunkov
2021-10-04 19:02 ` [PATCH 13/16] io_uring: inline io_req_needs_clean() Pavel Begunkov
2021-10-04 19:02 ` [PATCH 14/16] io_uring: inline io_poll_complete Pavel Begunkov
2021-10-04 19:03 ` [PATCH 15/16] io_uring: correct fill events helpers types Pavel Begunkov
2021-10-04 19:03 ` [PATCH 16/16] io_uring: mark hot functions Pavel Begunkov
2021-10-04 20:19 ` [PATCH 00/16] squeeze more performance Jens Axboe
2021-10-04 20:33   ` Jens Axboe

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox