From: Daniel Pittman <daniel@rimspace.net>
To: Jens Axboe <axboe@suse.de>
Cc: Linux Kernel <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] deadline io scheduler
Date: Fri, 27 Sep 2002 09:23:39 +1000 [thread overview]
Message-ID: <873crw5o90.fsf@enki.rimspace.net> (raw)
In-Reply-To: <20020926082925.GK12862@suse.de> (Jens Axboe's message of "Thu, 26 Sep 2002 10:29:25 +0200")
On Thu, 26 Sep 2002, Jens Axboe wrote:
> On Thu, Sep 26 2002, Daniel Pittman wrote:
>> On Thu, 26 Sep 2002, Jens Axboe wrote:
>> > On Wed, Sep 25 2002, Andrew Morton wrote:
>>
>> [...]
>>
>> > writes_starved. This controls how many times reads get preferred
>> > over writes. The default is 2, which means that we can serve two
>> > batches of reads over one write batch. A value of 4 would mean that
>> > reads could skip ahead of writes 4 times. A value of 1 would give
>> > you 1:1 read:write, ie no read preference. A silly value of 0 would
>> > give you write preference, always.
>>
>> Actually, a value of zero doesn't sound completely silly to me, right
>> now, since I have been doing a lot of thinking about video capture
>> recently.
>>
>> How much is it going to hurt a filesystem like ext[23] if that value
>> is set to zero while doing large streaming writes -- something like
>> (almost) uncompressed video at ten to twenty meg a second, for
>> gigabytes?
>
> You are going to stalll all reads indefinately :-)
Which has some potentially fatal consequences, really, if any of the
capture code gets paged out before the streaming write starts, or if the
filesystem needs to read a bitmap block or so, as Rik points out.
>> This is a situation where, for a dedicated machine, delaying reads
>> almost forever is actually a valuable thing. At least, valuable until
>> it stops the writes from being able to proceed.
>
> Well 0 should achieve that quite fine
Would you consider allowing something akin to 'writes_starved = -4' to
allow writes to bypass reads only 4 times -- a preference for writes,
but not forever?
That's going to express the bias I (think I) want for this case, but
it's not going to be able to stall a read forever...
Daniel
--
It is quite humbling to realize that the storage occupied by the longest line
from a typical Usenet posting is sufficient to provide a state space so vast
that all the computation power in the world can not conquer it.
-- Dave Wallace
next prev parent reply other threads:[~2002-09-26 23:18 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2002-09-25 17:20 [PATCH] deadline io scheduler Jens Axboe
2002-09-26 6:15 ` Andrew Morton
2002-09-26 6:27 ` David S. Miller
2002-09-26 6:44 ` Jens Axboe
2002-09-26 6:59 ` Jens Axboe
2002-09-26 7:06 ` William Lee Irwin III
2002-09-26 7:06 ` David S. Miller
2002-09-26 7:16 ` Jeff Garzik
2002-09-26 7:13 ` David S. Miller
2002-09-26 7:33 ` Jeff Garzik
2002-09-26 7:35 ` David S. Miller
2002-09-26 8:15 ` Michael Clark
2002-09-26 8:18 ` William Lee Irwin III
2002-09-26 17:41 ` Mike Anderson
2002-09-26 18:03 ` Jeff Garzik
2002-09-26 19:21 ` Mike Anderson
2002-09-27 5:41 ` Andrew Vasquez
2002-09-27 5:57 ` Jeff Garzik
2002-09-27 16:58 ` Mike Anderson
2002-09-26 22:41 ` Matt Porter
2002-09-26 22:35 ` Mark Bellon
2002-09-26 20:21 ` Thomas Tonino
2002-09-26 7:41 ` Jeff Garzik
2002-09-26 7:23 ` William Lee Irwin III
2002-09-26 7:11 ` Jeff Garzik
2002-09-26 7:14 ` William Lee Irwin III
2002-09-26 15:54 ` Patrick Mansfield
2002-09-30 8:15 ` Jens Axboe
2002-09-30 15:39 ` Patrick Mansfield
2002-09-30 16:08 ` Jens Axboe
2002-09-26 8:28 ` Daniel Pittman
2002-09-26 8:29 ` Jens Axboe
2002-09-26 23:23 ` Daniel Pittman [this message]
2002-09-30 8:10 ` Jens Axboe
2002-09-26 15:09 ` Rik van Riel
2002-09-26 7:12 ` Andrew Morton
2002-09-26 7:17 ` Jens Axboe
2002-09-26 7:34 ` Jens Axboe
2002-09-30 7:45 ` Pavel Machek
2002-10-02 5:35 ` Jens Axboe
2002-09-27 16:01 Andrew Vasquez
2002-09-27 17:07 ` Mike Anderson
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=873crw5o90.fsf@enki.rimspace.net \
--to=daniel@rimspace.net \
--cc=axboe@suse.de \
--cc=linux-kernel@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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).