linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Marcelo Tosatti <marcelo@parcelfarce.linux.theplanet.co.uk>
To: andrea@suse.de
Cc: linux-kernel@vger.kernel.org
Subject: Re: Andrea VM changes
Date: Sun, 31 Aug 2003 14:34:27 -0300 (BRT)	[thread overview]
Message-ID: <Pine.LNX.4.44.0308311434040.16240-100000@logos.cnet> (raw)



---------- Forwarded message ----------
Date: Sun, 31 Aug 2003 14:14:06 -0300 (BRT)
From: Marcelo Tosatti <marcelo@parcelfarce.linux.theplanet.co.uk>
To: Andrea Arcangeli <andrea@suse.de>
Cc: Marcelo Tosatti <marcelo@conectiva.com.br>,
     Mike Fedyk <mfedyk@matchmail.com>, Antonio Vargas <wind@cocodriloo.com>,
     lkml <linux-kernel@vger.kernel.org>,
     Marc-Christian Petersen <m.c.p@wolk-project.de>
Subject: Re: Andrea VM changes



On Sat, 30 Aug 2003, Andrea Arcangeli wrote:

> On Sat, Aug 30, 2003 at 12:13:57PM -0300, Marcelo Tosatti wrote:
> > 
> > > You need to integrate with -aa on the VM.  It has been hard enough for
> > > Andrea to get his stuff in, I doubt you will fair any better.
> > 
> > Thats because I never received separate patches which make sense one by
> > one.  Most of Andreas changes are all grouped into few big patches that
> > only he knows the mess. That is not the way to merge things.
> > 
> > I want to work out with him after I merge other stuff to address that.
> 
> that's true for only one patch, the others are pretty orthogonal after
> Andrew helped splitting them:
> 
> 
> 05_vm_03_vm_tunables-4
> 05_vm_05_zone_accounting-2
> 05_vm_06_swap_out-3

Help me understand something about this patch. In try_to_free_pages(), you
set failed_swapout to zero in case we are under __GFP_IO. And
failed_swapout decides whether we swap_out() or not.

So basically with -aa swap_out() is only called by __GFP_IO tasks (which
are throttled by the page laundering code in shrink_cache) and in mainline
non __GFP_IO tasks do swap_out() (and those are not throttled by anything).

Did I understood this right? 

Part 2:

Now in try_to_free_pages_zone() and shrink_cache you have: 

    if (!*failed_swapout)
        *failed_swapout =  !swap_out(classzone);

Which means: Keep trying to swap_out() only in case swap_out()  
successfully desactivates nr_pages pte's. Right? Do you do that to avoid
terrible expensive swap_out() loops which dont successfully free pages?

Thanks






             reply	other threads:[~2003-08-31 17:33 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2003-08-31 17:34 Marcelo Tosatti [this message]
     [not found] <Pine.LNX.4.44.0308311353170.15412-100000@logos.cnet>
2003-09-01 17:27 ` Andrea VM changes Marcelo Tosatti
2003-09-01 17:50   ` Andrea Arcangeli
     [not found] <qL3q.1Pm.3@gated-at.bofh.it>
     [not found] ` <qQ37.2q0.9@gated-at.bofh.it>
2003-09-01  9:15   ` Ihar 'Philips' Filipau
  -- strict thread matches above, loose matches on Subject: below --
2003-09-01  1:02 Dan Kegel
2003-09-01  6:03 ` Rik van Riel
2003-08-31 17:34 Marcelo Tosatti
2003-08-31 22:46 ` Andrea Arcangeli
2003-09-01  6:01 ` Rik van Riel
2003-09-01 15:54   ` Andrea Arcangeli
2003-08-31 15:51 Dan Kegel
2003-08-31 15:48 ` Jörn Engel
2003-08-31 16:19   ` Dan Kegel
2003-08-31 19:08 ` Jonathan Lundell
2003-08-31 19:22 ` Chris Frey
2003-08-31 23:42   ` Jamie Lokier
2003-09-01 11:47     ` Alan Cox
2003-08-30 15:50 Marcelo Tosatti
2003-08-30 19:11 ` Marcelo Tosatti
2003-08-30 19:21   ` Marcelo Tosatti
2003-08-30 23:19     ` Andrea Arcangeli
2003-08-30 23:30       ` Marcelo Tosatti
2003-08-30 23:57         ` Andrea Arcangeli
2003-08-31 14:10       ` Alan Cox
2003-08-31 14:59         ` Andrea Arcangeli
2003-08-31 15:29           ` Alan Cox
2003-08-31 15:59             ` Andrea Arcangeli
2003-09-15  5:16         ` Greg Stark
2003-09-15 10:47           ` Andrea Arcangeli
2003-08-31 11:50     ` Matthias Andree
2003-09-01 19:52       ` Mike Fedyk
2003-09-01 17:59   ` Andrea Arcangeli
2003-08-30 15:13 Marcelo Tosatti
2003-08-30 15:41 ` Andrea Arcangeli
2003-09-01 18:26   ` Marcelo Tosatti
2003-09-01 18:36     ` Andrea Arcangeli
2003-09-01 19:00   ` Marcelo Tosatti
2003-09-01 19:05     ` Andrea Arcangeli
2003-09-02 20:51       ` Marcelo Tosatti

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=Pine.LNX.4.44.0308311434040.16240-100000@logos.cnet \
    --to=marcelo@parcelfarce.linux.theplanet.co.uk \
    --cc=andrea@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).