From: Con Kolivas <kernel@kolivas.org>
To: linux-kernel@vger.kernel.org
Subject: Re: swapper: page allocation failure.
Date: Mon, 22 May 2006 21:17:26 +1000
User-Agent: KMail/1.9.1
Cc: Haar =?iso-8859-1?q?J=E1nos?= <djani22@netcenter.hu>,
       "Nick Piggin" <nickpiggin@yahoo.com.au>, cw@f00f.org
References: <00e901c67cad$fe9a9d90$1800a8c0@dcccs> <44710144.7090105@yahoo.com.au> <00d201c67d73$220d5d10$1800a8c0@dcccs>
In-Reply-To: <00d201c67d73$220d5d10$1800a8c0@dcccs>
MIME-Version: 1.0
Content-Type: text/plain;
  charset="iso-8859-1"
Content-Transfer-Encoding: 8BIT
Content-Disposition: inline
Message-Id: <200605222117.27433.kernel@kolivas.org>
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1087
Lines: 28

On Monday 22 May 2006 17:41, Haar J?nos wrote:
> ----- Original Message -----
> From: "Nick Piggin" <nickpiggin@yahoo.com.au>
> > Yeah, as I said, block device's pagecache (aka buffercache) can't
> > use highmem. If nbd can export regular files as block devices, or
> > you use loop devices from regular files, that might help (or slow
> > things down :P).
>
> Hmm.
> That sounds bad.
> I think, if highmem is unreachable some times that makes lowmem more
> valuable!
> The kernel needs to keep (reserve) it free as much as possible.
> The buffer-cache is an unimportant thing next to keeping lowmem free, but
> it is blocks the performance and wastes the systems resources!
>
> It is possible any workaround?

Try with one of the alternative vmsplit options that gives you more lowmem? 
That might break certain applications though.

-- 
-ck
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/