From: Con Kolivas <kernel@kolivas.org>
To: Marcelo Tosatti <marcelo.tosatti@cyclades.com>
Cc: Nick Piggin <piggin@cyberone.com.au>,
Andrew Morton <akpm@osdl.org>,
raybry@sgi.com, linux-kernel@vger.kernel.org, linux-mm@kvack.org,
riel@redhat.com, mbligh@aracnet.com
Subject: Re: swapping and the value of /proc/sys/vm/swappiness
Date: Thu, 09 Sep 2004 11:12:46 +1000 [thread overview]
Message-ID: <413FAE0E.40304@kolivas.org> (raw)
In-Reply-To: <20040908164549.GA4284@logos.cnet>
[-- Attachment #1: Type: text/plain, Size: 1817 bytes --]
Marcelo Tosatti wrote:
> On Tue, Sep 07, 2004 at 08:56:47PM +1000, Con Kolivas wrote:
>
>>Nick Piggin wrote:
>>
>>>
>>>Marcelo Tosatti wrote:
>>>
>>>
>>>>Hi kernel fellows,
>>>>
>>>>I volunteer. I'll try something tomorrow to compare swappiness of
>>>>older kernels like 2.6.5 and 2.6.6, which were fine on SGI's Altix
>>>>tests, up to current newer kernels (on small memory boxes of course).
>>>>
>>>
>>>Hi Marcelo,
>>>
>>>Just a suggestion - I'd look at the thrashing control patch first.
>>>I bet that's the cause.
>>
>>Good point!
>>
>>I recall one of my users found his workload which often hit swap lightly
>>was swapping much heavier and his performance dropped dramatically until
>>I stopped including the swap thrash control patch. I informed Rik about
>>it some time back so I'm not sure if he addressed it in the meantime.
>
>
> Swap thrashing code doesnt affect anything, at least on my simple contained test.
> With the same test, the amount of swapped out memory with 2.6.6/2.6.7 is 100-150MB,
> while 2.6.8/2.6.9-mm* swaps out around 250MB.
>
> I tried 2.6.7's "vmscan.c" on 2.6.8 without noticeable difference, I wonder why.
>
> What I've noticed before with the swap token code is total crap interactivity
> when memory hog is running. Which doesnt happen without it.
>
> Con, I've seen your hard swappiness patch, why do you remove the current
> swap_tendency calculation? Can you give us some insight into it?
Sure. It was painfully simple. The swap tendency worked basically the
same but did not take into account distress. ie It made the "swappiness"
knob purely dependant on mapped ratio. For whatever reason, if the
swappiness value is the same in later kernels but swaps more, there is
more "distress" meaning we are priority scanning much more aggressively.
Cheers,
Con
[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 256 bytes --]
next prev parent reply other threads:[~2004-09-09 1:12 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2004-09-06 19:11 Ray Bryant
2004-09-06 20:10 ` Andrew Morton
2004-09-06 21:22 ` Ray Bryant
2004-09-06 21:36 ` Andrew Morton
2004-09-06 22:37 ` William Lee Irwin III
2004-09-06 23:51 ` Nick Piggin
2004-09-07 0:31 ` Ray Bryant
2004-09-06 22:48 ` William Lee Irwin III
2004-09-06 23:09 ` Con Kolivas
2004-09-06 23:27 ` Andrew Morton
2004-09-06 23:34 ` Con Kolivas
2004-09-07 0:03 ` Marcelo Tosatti
2004-09-07 1:34 ` Con Kolivas
2004-09-07 10:38 ` Nick Piggin
2004-09-07 10:56 ` Con Kolivas
2004-09-08 16:45 ` Marcelo Tosatti
2004-09-09 1:12 ` Con Kolivas [this message]
2004-09-07 17:03 ` Ray Bryant
2004-09-07 21:20 ` Marcelo Tosatti
2004-09-08 2:18 ` Marcelo Tosatti
2004-09-08 14:20 ` Ray Bryant
2004-09-08 16:54 ` Marcelo Tosatti
2004-09-08 19:35 ` Ray Bryant
2004-09-08 19:30 ` Marcelo Tosatti
2004-09-09 3:06 ` Ray Bryant
2004-09-09 2:14 ` Marcelo Tosatti
2004-09-09 14:21 ` Ray Bryant
2004-09-09 3:09 ` William Lee Irwin III
2004-09-09 14:16 ` Ray Bryant
2004-09-09 17:23 ` William Lee Irwin III
2004-09-28 1:54 ` Ray Bryant
2004-09-28 3:36 ` Nick Piggin
2004-09-29 0:36 ` Nick Piggin
2004-09-29 4:23 ` Ray Bryant
2004-09-30 17:15 ` Ray Bryant
2004-09-08 17:31 ` Martin J. Bligh
2004-09-08 18:04 ` Rik van Riel
2004-09-08 19:50 ` Diego Calleja
2004-09-08 21:10 ` Martin J. Bligh
2004-09-08 21:55 ` Diego Calleja
2004-09-08 22:20 ` Martin J. Bligh
2004-09-08 23:22 ` Rik van Riel
2004-09-08 22:28 ` Alan Cox
2004-09-08 23:42 ` Martin J. Bligh
2004-09-08 19:54 ` Ray Bryant
2004-09-08 15:19 ` Ray Bryant
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=413FAE0E.40304@kolivas.org \
--to=kernel@kolivas.org \
--cc=akpm@osdl.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=marcelo.tosatti@cyclades.com \
--cc=mbligh@aracnet.com \
--cc=piggin@cyberone.com.au \
--cc=raybry@sgi.com \
--cc=riel@redhat.com \
/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