From: Christoph Hellwig <hch@lst.de>
To: Bart Van Assche <bvanassche@acm.org>
Cc: Christoph Hellwig <hch@lst.de>, Jens Axboe <axboe@kernel.dk>,
linux-block@vger.kernel.org, Jaegeuk Kim <jaegeuk@kernel.org>,
Ming Lei <ming.lei@redhat.com>,
Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>,
Martijn Coenen <maco@android.com>
Subject: Re: [PATCH v2 2/3] loop: Select I/O scheduler 'none' from inside add_disk()
Date: Thu, 5 Aug 2021 08:39:19 +0200 [thread overview]
Message-ID: <20210805063919.GA32686@lst.de> (raw)
In-Reply-To: <c6337526-8f25-7efc-96ff-fbfe054fe9c0@acm.org>
On Wed, Aug 04, 2021 at 10:58:01AM -0700, Bart Van Assche wrote:
> On 8/3/21 10:35 PM, Christoph Hellwig wrote:
>> On Tue, Aug 03, 2021 at 11:23:03AM -0700, Bart Van Assche wrote:
>>> We noticed that the user interface of Android devices becomes very slow
>>> under memory pressure. This is because Android uses the zram driver on top
>>> of the loop driver for swapping,
>>
>> Sorry, but that is just amazingly stupid. If you really want to swap
>> to compressed files introduce that support in the swap code instead of
>> coming up with dumb driver stacks from hell.
>
> Hi Christoph,
>
> That's an interesting suggestion. We can look into adding compression
> support in the swap code.
As a short term fix you might also just look into having a file
backing for the zram writeback mode, which should not need more than
100-200 lines of code.
> Independent of the use case of this patch, is it acceptable to change the
> default I/O scheduler of loop devices from mq-deadline into none (patches 1
> and 2 of this series)?
Yes, that might not be a bad idea in general.
next prev parent reply other threads:[~2021-08-05 6:39 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-03 18:23 [PATCH v2 0/3] Improve loop driver I/O scheduler and QD selection Bart Van Assche
2021-08-03 18:23 ` [PATCH v2 1/3] blk-mq: Introduce the BLK_MQ_F_NO_SCHED_BY_DEFAULT flag Bart Van Assche
2021-08-03 18:23 ` [PATCH v2 2/3] loop: Select I/O scheduler 'none' from inside add_disk() Bart Van Assche
2021-08-04 2:39 ` Ming Lei
2021-08-04 17:43 ` Bart Van Assche
2021-08-05 3:26 ` Ming Lei
2021-08-05 16:49 ` Bart Van Assche
2021-08-04 17:58 ` Jens Axboe
2021-08-04 5:35 ` Christoph Hellwig
2021-08-04 17:58 ` Bart Van Assche
2021-08-04 18:04 ` Jens Axboe
2021-08-05 6:39 ` Christoph Hellwig [this message]
2021-08-03 18:23 ` [PATCH v2 3/3] loop: Add the default_queue_depth kernel module parameter Bart Van Assche
2021-08-04 6:07 ` Greg KH
2021-08-04 17:38 ` Bart Van Assche
2021-08-04 19:33 ` Greg KH
2021-08-05 6:14 ` Chaitanya Kulkarni
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=20210805063919.GA32686@lst.de \
--to=hch@lst.de \
--cc=axboe@kernel.dk \
--cc=bvanassche@acm.org \
--cc=jaegeuk@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=maco@android.com \
--cc=ming.lei@redhat.com \
--cc=penguin-kernel@I-love.SAKURA.ne.jp \
/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.