From: Jens Axboe <axboe@kernel.dk>
To: linux-fsdevel@vger.kernel.org, linux-aio@kvack.org
Cc: hch@lst.de, viro@zeniv.linux.org.uk, Jens Axboe <axboe@kernel.dk>
Subject: [PATCH 4/7] aio: only use blk plugs for > 2 depth submissions
Date: Sun, 16 Dec 2018 10:01:13 -0700 [thread overview]
Message-ID: <20181216170116.16944-5-axboe@kernel.dk> (raw)
In-Reply-To: <20181216170116.16944-1-axboe@kernel.dk>
Plugging is meant to optimize submission of a string of IOs, if we don't
have more than 2 being submitted, don't bother setting up a plug.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
fs/aio.c | 18 ++++++++++++++----
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/fs/aio.c b/fs/aio.c
index 522c04864d82..ed6c3914477a 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -69,6 +69,12 @@ struct aio_ring {
struct io_event io_events[0];
}; /* 128 bytes + ring size */
+/*
+ * Plugging is meant to work with larger batches of IOs. If we don't
+ * have more than the below, then don't bother setting up a plug.
+ */
+#define AIO_PLUG_THRESHOLD 2
+
#define AIO_RING_PAGES 8
struct kioctx_table {
@@ -1919,7 +1925,8 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
if (nr > ctx->nr_events)
nr = ctx->nr_events;
- blk_start_plug(&plug);
+ if (nr > AIO_PLUG_THRESHOLD)
+ blk_start_plug(&plug);
for (i = 0; i < nr; i++) {
struct iocb __user *user_iocb;
@@ -1932,7 +1939,8 @@ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr,
if (ret)
break;
}
- blk_finish_plug(&plug);
+ if (nr > AIO_PLUG_THRESHOLD)
+ blk_finish_plug(&plug);
percpu_ref_put(&ctx->users);
return i ? i : ret;
@@ -1959,7 +1967,8 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
if (nr > ctx->nr_events)
nr = ctx->nr_events;
- blk_start_plug(&plug);
+ if (nr > AIO_PLUG_THRESHOLD)
+ blk_start_plug(&plug);
for (i = 0; i < nr; i++) {
compat_uptr_t user_iocb;
@@ -1972,7 +1981,8 @@ COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id,
if (ret)
break;
}
- blk_finish_plug(&plug);
+ if (nr > AIO_PLUG_THRESHOLD)
+ blk_finish_plug(&plug);
percpu_ref_put(&ctx->users);
return i ? i : ret;
--
2.17.1
next prev parent reply other threads:[~2018-12-16 17:01 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-12-16 17:01 [PATCHSET] aio cleanups and optimizations for 4.21 Jens Axboe
2018-12-16 17:01 ` [PATCH 1/7] aio: use assigned completion handler Jens Axboe
2018-12-16 17:01 ` [PATCH 2/7] aio: separate out ring reservation from req allocation Jens Axboe
2018-12-16 17:01 ` [PATCH 3/7] aio: don't zero entire aio_kiocb aio_get_req() Jens Axboe
2018-12-16 17:01 ` Jens Axboe [this message]
2018-12-16 17:01 ` [PATCH 5/7] aio: use iocb_put() instead of open coding it Jens Axboe
2018-12-16 17:01 ` [PATCH 6/7] aio: split out iocb copy from io_submit_one() Jens Axboe
2018-12-16 17:01 ` [PATCH 7/7] aio: abstract out io_event filler helper Jens Axboe
2018-12-21 19:30 ` [PATCHSET] aio cleanups and optimizations for 4.21 Jeff Moyer
2018-12-22 15:26 ` 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=20181216170116.16944-5-axboe@kernel.dk \
--to=axboe@kernel.dk \
--cc=hch@lst.de \
--cc=linux-aio@kvack.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=viro@zeniv.linux.org.uk \
/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.