User: Password:
|
|
Subscribe / Log in / New account

Re: [PATCH] free swap space of (re)activated pages

From:  Con Kolivas <kernel-AT-kolivas.org>
To:  Rik van Riel <riel-AT-redhat.com>, ck list <ck-AT-vds.kolivas.org>
Subject:  Re: [PATCH] free swap space of (re)activated pages
Date:  Sat, 3 Mar 2007 14:04:20 +1100
Cc:  Andrew Morton <akpm-AT-linux-foundation.org>, linux-kernel <linux-kernel-AT-vger.kernel.org>, linux-mm <linux-mm-AT-kvack.org>
Archive-link:  Article, Thread

On Saturday 03 March 2007 12:31, Rik van Riel wrote:
> Andrew Morton wrote:
> > On Fri, 02 Mar 2007 15:31:19 -0500
> >
> > Rik van Riel <riel@redhat.com> wrote:
> >> the attached patch frees the swap space of already resident pages
> >> when swap space starts getting tight, instead of only freeing up
> >> the swap space taken up by newly swapped in pages.
> >>
> >> This should result in the swap space of pages that remain resident
> >> in memory being freed, allowing kswapd more chances to actually swap
> >> a page out (instead of rotating it back onto the active list).
> >
> > Fair enough.   How do we work out if this helps things?
>
> I suspect it should mostly help on desktop systems that slowly
> fill up (and run out of) swap.  I'm not sure how to create that
> synthetically.

Ooh you have a vm patch that helps swap on the desktop! I can help you here 
with my experience from swap prefetch.

1. Get it reviewed and have noone show any evidence it harms
2. Find hundreds of users who can testify it helps
3. Find a way of quantifying it.
4. ...
5. Merge into mainline.


There, that should get you as far as 4. 

I haven't figured out what 4 is yet. I believe it may be goto 1;

-- 
-ck


(Log in to post comments)

Re: [PATCH] free swap space of (re)activated pages

Posted Mar 8, 2007 9:16 UTC (Thu) by k8to (subscriber, #15413) [Link]

I've submitted my experience that this helps and that I want this to go into the mainline. Is there a real flaw with the swap prefetch patch or is it just not sexy enough?

Re: [PATCH] free swap space of (re)activated pages

Posted Mar 8, 2007 11:09 UTC (Thu) by jospoortvliet (subscriber, #33164) [Link]

Well, read con's statement again... This is why I did mentioned this mail to the LWN editors - what happened to the patch seems to really follow Con's 4-step plan. Discussion about this, and the why and how led to Andrew replying to me about his 'mandatory review mail' which he would send on a 'sufficiently gloomy day' - http://lwn.net/Articles/222174/

In other words, a reason for this might be a lack of hackers willing to review code aimed for inclusion in the kernel.


Copyright © 2007, Eklektix, Inc.
Comments and public postings are copyrighted by their creators.
Linux is a registered trademark of Linus Torvalds