From owner-freebsd-hackers  Sat Oct 26 14:01:54 1996
Return-Path: owner-hackers
Received: (from root@localhost)
          by freefall.freebsd.org (8.7.5/8.7.3) id OAA10042
          for hackers-outgoing; Sat, 26 Oct 1996 14:01:54 -0700 (PDT)
Received: from critter.tfs.com (disn5.cybercity.dk [194.16.57.5])
          by freefall.freebsd.org (8.7.5/8.7.3) with ESMTP id OAA10028;
          Sat, 26 Oct 1996 14:01:47 -0700 (PDT)
Received: from critter.tfs.com (localhost.tfs.com [127.0.0.1]) by critter.tfs.com (8.7.5/8.7.3) with ESMTP id XAA17641; Sat, 26 Oct 1996 23:02:21 +0200 (MET DST)
cc: Joe Greco <jgreco@solaria.sol.net>, jgreco@ns.sol.net, hackers@FreeBSD.org
Subject: Re: HELP! :-( Hitting datasize limit 
In-reply-to: Your message of "Sat, 26 Oct 1996 20:26:57 +0200."
             <17437.846354417@critter.tfs.com> 
Date: Sat, 26 Oct 1996 23:02:21 +0200
Message-ID: <17639.846363741@critter.tfs.com>
From: Poul-Henning Kamp <phk@critter.tfs.com>
Sender: owner-hackers@FreeBSD.org
X-Loop: FreeBSD.org
Precedence: bulk

>>innd allocates per-channel receive buffers.  When the maximum allowed

Hi Joe,

I looked at the inn port and I think that buffer handling could need
to be brought into the nineties.

If you want to try to improve it, try this:

	Always allocate the buffer at max size.
	After each article is handled do this:

		madvise(buffer, buffersize, MADV_FREE);

You would save a lot of copying around stuff that way, and probably 
use less RAM all in all.

--
Poul-Henning Kamp           | phk@FreeBSD.ORG       FreeBSD Core-team.
http://www.freebsd.org/~phk | phk@login.dknet.dk    Private mailbox.
whois: [PHK]                | phk@ref.tfs.com       TRW Financial Systems, Inc.
Future will arrive by its own means, progress not so.