The patch below does not apply to the 5.15-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable@xxxxxxxxxxxxxxx>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 8a796565cec3601071cbbd27d6304e202019d014 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable@xxxxxxxxxxxxxxx>' --in-reply-to '2023071622-exhale-throwing-6c38@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: 8a796565cec3 ("io_uring: Use io_schedule* in cqring wait") d33a39e57768 ("io_uring: keep timeout in io_wait_queue") 46ae7eef44f6 ("io_uring: optimise non-timeout waiting") 846072f16eed ("io_uring: mimimise io_cqring_wait_schedule") 3fcf19d592d5 ("io_uring: parse check_cq out of wq waiting") 12521a5d5cb7 ("io_uring: fix CQ waiting timeout handling") 52ea806ad983 ("io_uring: finish waiting before flushing overflow entries") 35d90f95cfa7 ("io_uring: include task_work run after scheduling in wait for events") 1b346e4aa8e7 ("io_uring: don't check overflow flush failures") a85381d8326d ("io_uring: skip overflow CQE posting for dying ring") c0e0d6ba25f1 ("io_uring: add IORING_SETUP_DEFER_TASKRUN") b4c98d59a787 ("io_uring: introduce io_has_work") 78a861b94959 ("io_uring: add sync cancelation API through io_uring_register()") c34398a8c018 ("io_uring: remove __io_req_task_work_add") ed5ccb3beeba ("io_uring: remove priority tw list optimisation") 4a0fef62788b ("io_uring: optimize io_uring_task layout") 253993210bd8 ("io_uring: introduce locking helpers for CQE posting") 305bef988708 ("io_uring: hide eventfd assumptions in eventfd paths") affa87db9010 ("io_uring: fix multi ctx cancellation") d9dee4302a7c ("io_uring: remove ->flush_cqes optimisation") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ >From 8a796565cec3601071cbbd27d6304e202019d014 Mon Sep 17 00:00:00 2001 From: Andres Freund <andres@xxxxxxxxxxx> Date: Fri, 7 Jul 2023 09:20:07 -0700 Subject: [PATCH] io_uring: Use io_schedule* in cqring wait I observed poor performance of io_uring compared to synchronous IO. That turns out to be caused by deeper CPU idle states entered with io_uring, due to io_uring using plain schedule(), whereas synchronous IO uses io_schedule(). The losses due to this are substantial. On my cascade lake workstation, t/io_uring from the fio repository e.g. yields regressions between 20% and 40% with the following command: ./t/io_uring -r 5 -X0 -d 1 -s 1 -c 1 -p 0 -S$use_sync -R 0 /mnt/t2/fio/write.0.0 This is repeatable with different filesystems, using raw block devices and using different block devices. Use io_schedule_prepare() / io_schedule_finish() in io_cqring_wait_schedule() to address the difference. After that using io_uring is on par or surpassing synchronous IO (using registered files etc makes it reliably win, but arguably is a less fair comparison). There are other calls to schedule() in io_uring/, but none immediately jump out to be similarly situated, so I did not touch them. Similarly, it's possible that mutex_lock_io() should be used, but it's not clear if there are cases where that matters. Cc: stable@xxxxxxxxxxxxxxx # 5.10+ Cc: Pavel Begunkov <asml.silence@xxxxxxxxx> Cc: io-uring@xxxxxxxxxxxxxxx Cc: linux-kernel@xxxxxxxxxxxxxxx Signed-off-by: Andres Freund <andres@xxxxxxxxxxx> Link: https://lore.kernel.org/r/20230707162007.194068-1-andres@xxxxxxxxxxx [axboe: minor style fixup] Signed-off-by: Jens Axboe <axboe@xxxxxxxxx> diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index e8096d502a7c..7505de2428e0 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2489,6 +2489,8 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx) static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { + int token, ret; + if (unlikely(READ_ONCE(ctx->check_cq))) return 1; if (unlikely(!llist_empty(&ctx->work_llist))) @@ -2499,11 +2501,20 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, return -EINTR; if (unlikely(io_should_wake(iowq))) return 0; + + /* + * Use io_schedule_prepare/finish, so cpufreq can take into account + * that the task is waiting for IO - turns out to be important for low + * QD IO. + */ + token = io_schedule_prepare(); + ret = 0; if (iowq->timeout == KTIME_MAX) schedule(); else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS)) - return -ETIME; - return 0; + ret = -ETIME; + io_schedule_finish(token); + return ret; } /*
