From owner-freebsd-current  Sun Jan 26 13:10:54 1997
Return-Path: <owner-current>
Received: (from root@localhost)
          by freefall.freebsd.org (8.8.5/8.8.5) id NAA24421
          for current-outgoing; Sun, 26 Jan 1997 13:10:54 -0800 (PST)
Received: from godzilla.zeta.org.au (godzilla.zeta.org.au [203.2.228.19])
          by freefall.freebsd.org (8.8.5/8.8.5) with ESMTP id NAA24413
          for <current@FreeBSD.org>; Sun, 26 Jan 1997 13:10:51 -0800 (PST)
Received: (from bde@localhost) by godzilla.zeta.org.au (8.8.3/8.6.9) id IAA08711; Mon, 27 Jan 1997 08:10:38 +1100
Date: Mon, 27 Jan 1997 08:10:38 +1100
From: Bruce Evans <bde@zeta.org.au>
Message-Id: <199701262110.IAA08711@godzilla.zeta.org.au>
To: bde@zeta.org.au, phk@critter.dk.tfs.com
Subject: Re: exec bug
Cc: current@FreeBSD.org, dg@root.com, swallace@ece.uci.edu
Sender: owner-current@FreeBSD.org
X-Loop: FreeBSD.org
Precedence: bulk

>Well, phkmalloc can be a bit undeterministic in this respect, if you want
>to be almost sure you get a fair picture do this:
>
>	for (i=4;i<12;i++)
>		malloc(1<<i);
>
>That way you know that you have one page of each size ready.

That didn't make much difference, but removing `/etc/malloc.conf -> AJ'
did :-).  Oops.  The memset for the J option is especially expensive for
a malloc size of 4096 and a read size of 32.

Bruce