From: Christoph Hellwig <hch@infradead.org>
To: Jens Axboe <axboe@kernel.dk>
Cc: linux-block@vger.kernel.org
Subject: Re: [PATCH 3/8] block/mq-deadline: skip expensive merge lookups if contended
Date: Wed, 24 Jan 2024 01:32:29 -0800 [thread overview]
Message-ID: <ZbDZLUDwA8ObY+9O@infradead.org> (raw)
In-Reply-To: <20240123174021.1967461-4-axboe@kernel.dk>
On Tue, Jan 23, 2024 at 10:34:15AM -0700, Jens Axboe wrote:
> We do several stages of merging in the block layer - the most likely one
> to work is also the cheap one, merging direct in the per-task plug when
> IO is submitted. Getting merges outside of that is a lot less likely,
> but IO schedulers may still maintain internal data structures to
> facilitate merge lookups outside of the plug.
>
> Make mq-deadline skip expensive merge lookups if the queue lock is
> already contended. The likelihood of getting a merge here is not very
> high, hence it should not be a problem skipping the attempt in the also
> unlikely event that the queue is already contended.
I'm curious if you tried benchmarking just removing these extra
merges entirely?
next prev parent reply other threads:[~2024-01-24 9:32 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-01-23 17:34 [PATCHSET v3] mq-deadline and BFQ scalability improvements Jens Axboe
2024-01-23 17:34 ` [PATCH 1/8] block/mq-deadline: pass in queue directly to dd_insert_request() Jens Axboe
2024-01-24 9:21 ` Johannes Thumshirn
2024-01-23 17:34 ` [PATCH 2/8] block/mq-deadline: serialize request dispatching Jens Axboe
2024-01-23 18:36 ` Bart Van Assche
2024-01-23 19:13 ` Jens Axboe
2024-01-24 9:31 ` Christoph Hellwig
2024-01-24 15:00 ` Jens Axboe
2024-01-24 9:29 ` Johannes Thumshirn
2024-01-23 17:34 ` [PATCH 3/8] block/mq-deadline: skip expensive merge lookups if contended Jens Axboe
2024-01-24 9:31 ` Johannes Thumshirn
2024-01-24 9:32 ` Christoph Hellwig [this message]
2024-01-24 15:02 ` Jens Axboe
2024-01-23 17:34 ` [PATCH 4/8] block/mq-deadline: use separate insertion lists Jens Axboe
2024-01-23 18:37 ` Bart Van Assche
2024-01-24 9:42 ` Johannes Thumshirn
2024-01-23 17:34 ` [PATCH 5/8] block/bfq: pass in queue directly to bfq_insert_request() Jens Axboe
2024-01-23 18:38 ` Bart Van Assche
2024-01-24 9:46 ` Johannes Thumshirn
2024-01-23 17:34 ` [PATCH 6/8] block/bfq: serialize request dispatching Jens Axboe
2024-01-23 18:40 ` Bart Van Assche
2024-01-23 19:14 ` Jens Axboe
2024-01-23 17:34 ` [PATCH 7/8] block/bfq: skip expensive merge lookups if contended Jens Axboe
2024-01-23 18:44 ` Bart Van Assche
2024-01-23 19:14 ` Jens Axboe
2024-01-23 17:34 ` [PATCH 8/8] block/bfq: use separate insertion lists Jens Axboe
2024-01-23 18:47 ` Bart Van Assche
2024-01-23 19:18 ` Jens Axboe
2024-01-23 20:03 ` [PATCHSET v3] mq-deadline and BFQ scalability improvements Oleksandr Natalenko
2024-01-23 22:14 ` 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=ZbDZLUDwA8ObY+9O@infradead.org \
--to=hch@infradead.org \
--cc=axboe@kernel.dk \
--cc=linux-block@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.