All of lore.kernel.org
 help / color / mirror / Atom feed
From: Pavel Begunkov <asml.silence@gmail.com>
To: Jens Axboe <axboe@kernel.dk>, io-uring@vger.kernel.org
Subject: [PATCH 06/12] io_uring: optimise completion timeout flushing
Date: Mon, 14 Jun 2021 23:37:25 +0100	[thread overview]
Message-ID: <e4892ec68b71a69f92ffbea4a1499be3ec0d463b.1623709150.git.asml.silence@gmail.com> (raw)
In-Reply-To: <cover.1623709150.git.asml.silence@gmail.com>

io_commit_cqring() might be very hot and we definitely don't want to
touch ->timeout_list there, because 1) it's shared with the submission
side so might lead to cache bouncing and 2) may need to load an extra
cache line, especially for IRQ completions.

We're interested in it at the completion side only when there are
offset-mode timeouts, which are not so popular. Replace
list_empty(->timeout_list) hot path check with a new one-way flag, which
is set when we prepare the first offset-mode timeout.

note: the flag sits in the same line as briefly used after ->rings

Signed-off-by: Pavel Begunkov <asml.silence@gmail.com>
---
 fs/io_uring.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/fs/io_uring.c b/fs/io_uring.c
index 6dd14f4aa5f1..fbf3b2149a4c 100644
--- a/fs/io_uring.c
+++ b/fs/io_uring.c
@@ -351,6 +351,7 @@ struct io_ring_ctx {
 		unsigned int		drain_next: 1;
 		unsigned int		eventfd_async: 1;
 		unsigned int		restricted: 1;
+		unsigned int		off_timeout_used: 1;
 	} ____cacheline_aligned_in_smp;
 
 	/* submission data */
@@ -1318,12 +1319,12 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 {
 	u32 seq;
 
-	if (list_empty(&ctx->timeout_list))
+	if (likely(!ctx->off_timeout_used))
 		return;
 
 	seq = ctx->cached_cq_tail - atomic_read(&ctx->cq_timeouts);
 
-	do {
+	while (!list_empty(&ctx->timeout_list)) {
 		u32 events_needed, events_got;
 		struct io_kiocb *req = list_first_entry(&ctx->timeout_list,
 						struct io_kiocb, timeout.list);
@@ -1345,8 +1346,7 @@ static void io_flush_timeouts(struct io_ring_ctx *ctx)
 
 		list_del_init(&req->timeout.list);
 		io_kill_timeout(req, 0);
-	} while (!list_empty(&ctx->timeout_list));
-
+	}
 	ctx->cq_last_tm_flush = seq;
 }
 
@@ -5651,6 +5651,8 @@ static int io_timeout_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		return -EINVAL;
 
 	req->timeout.off = off;
+	if (unlikely(off && !req->ctx->off_timeout_used))
+		req->ctx->off_timeout_used = true;
 
 	if (!req->async_data && io_alloc_async_data(req))
 		return -ENOMEM;
-- 
2.31.1


  parent reply	other threads:[~2021-06-14 22:38 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-06-14 22:37 [PATCH 5.14 00/12] for-next optimisations Pavel Begunkov
2021-06-14 22:37 ` [PATCH 01/12] io_uring: keep SQ pointers in a single cacheline Pavel Begunkov
2021-06-14 22:37 ` [PATCH 02/12] io_uring: move ctx->flags from SQ cacheline Pavel Begunkov
2021-06-14 22:37 ` [PATCH 03/12] io_uring: shuffle more fields into SQ ctx section Pavel Begunkov
2021-06-14 22:37 ` [PATCH 04/12] io_uring: refactor io_get_sqe() Pavel Begunkov
2021-06-14 22:37 ` [PATCH 05/12] io_uring: don't cache number of dropped SQEs Pavel Begunkov
2021-06-14 22:37 ` Pavel Begunkov [this message]
2021-06-14 22:37 ` [PATCH 07/12] io_uring: small io_submit_sqe() optimisation Pavel Begunkov
2021-06-14 22:37 ` [PATCH 08/12] io_uring: clean up check_overflow flag Pavel Begunkov
2021-06-14 22:37 ` [PATCH 09/12] io_uring: wait heads renaming Pavel Begunkov
2021-06-14 22:37 ` [PATCH 10/12] io_uring: move uring_lock location Pavel Begunkov
2021-06-14 22:37 ` [PATCH 11/12] io_uring: refactor io_req_defer() Pavel Begunkov
2021-06-14 22:37 ` [PATCH 12/12] io_uring: optimise non-drain path Pavel Begunkov
2021-06-15 12:27 ` [PATCH 5.14 00/12] for-next optimisations Pavel Begunkov
2021-06-15 21:38 ` Jens Axboe

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=e4892ec68b71a69f92ffbea4a1499be3ec0d463b.1623709150.git.asml.silence@gmail.com \
    --to=asml.silence@gmail.com \
    --cc=axboe@kernel.dk \
    --cc=io-uring@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.