Re: [PATCH v5 2/5] block: loop: set QUEUE_FLAG_NOMERGES for request queue of loop

From	Ming Lei <ming.lei@canonical.com>
Newsgroups	linux.kernel
Subject	Re: [PATCH v5 2/5] block: loop: set QUEUE_FLAG_NOMERGES for request queue of loop
Date	2015-06-22 08:40 +0200
Message-ID	<pE3yG-4bg-25@gated-at.bofh.it> (permalink)
References	<pzs4G-8fW-17@gated-at.bofh.it> <pzsem-8tG-35@gated-at.bofh.it> <pzIMb-7NG-35@gated-at.bofh.it>
Organization	linux.* mail to news gateway

Show all headers | View raw

On Wed, Jun 10, 2015 at 3:36 PM, Christoph Hellwig <hch@infradead.org> wrote:
> On Tue, Jun 09, 2015 at 09:49:23PM +0800, Ming Lei wrote:
>> It doesn't make sense to enable merge because the I/O
>> submitted to backing file is handled page by page.
>
> Looks fine, but does it make any difference?

Looks no, see the following result, please:

- iops tested by fio: loop over image on HDD.
                         patched  vs. non-patched
    randread     158        161
    read             8716        8784
    randwrite     6076        5893
    write             21896        22066

Thanks,
Ming
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
Please read the FAQ at  http://www.tux.org/lkml/

Back to linux.kernel | Previous | Next | Find similar | Unroll thread

Thread

Re: [PATCH v5 2/5] block: loop: set QUEUE_FLAG_NOMERGES for request  queue of loop Ming Lei <ming.lei@canonical.com> - 2015-06-22 08:40 +0200

csiph-web