From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from pippin.tausq.org (gandalf.tausq.org [64.81.244.94]) by dsl2.external.hp.com (Postfix) with ESMTP id 136944891 for ; Wed, 7 Jan 2004 03:06:34 -0700 (MST) Date: Wed, 7 Jan 2004 02:14:07 -0800 From: Randolph Chung To: Riccardo Subject: Re: [parisc-linux] LMBench results on for the C200 for HP-UX 10.20, Linux 2.4.24-pa0, and Linux 2.6.0-pa8 Message-ID: <20040107101406.GS533@tausq.org> References: <1073466464.752.112.camel@laptop.bradetich.net> <3FFBD4DF.ECB0ABBC@tiscalinet.it> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <3FFBD4DF.ECB0ABBC@tiscalinet.it> Cc: ryan_bradetich@hp.com, parisc-linux@lists.parisc-linux.org Reply-To: Randolph Chung List-Id: parisc-linux developers list List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , > HP-UX fork is fast! linux 2.6 seems to bring some relief here. I always > marvel how fast HP-UX is when responding to a telnet login. > Instantaneus. Probably fork() speed compensates the lower latency linux > has in other areas. The reason why fork() is so slow on palinux is that we flush the entire cache for each fork() operation. this is clearly a very bad thing. unfortunately this doesn't seem like a simple thing to fix. From some previous discussions it seems like we don't need to do the cache flushing for fork(), but when i got rid of it the system crashes very quickly. Possibly the per-fork cache flush is masking other bugs in the kernel cache flushing infrastructure. randolph -- Randolph Chung Debian GNU/Linux Developer, hppa/ia64 ports http://www.tausq.org/