From owner-freebsd-questions Wed Oct 27 15: 4: 1 1999 Delivered-To: freebsd-questions@freebsd.org Received: from mail3.atl.bellsouth.net (mail3.atl.bellsouth.net [205.152.0.38]) by hub.freebsd.org (Postfix) with ESMTP id 7C7C614F8E for ; Wed, 27 Oct 1999 15:03:51 -0700 (PDT) (envelope-from wghicks@bellsouth.net) Received: from wghicks.bellsouth.net (host-209-214-77-184.atl.bellsouth.net [209.214.77.184]) by mail3.atl.bellsouth.net (3.3.5alt/0.75.2) with ESMTP id SAA03911; Wed, 27 Oct 1999 18:03:48 -0400 (EDT) Received: from wghicks.bellsouth.net (IDENT:wghicks@localhost [127.0.0.1]) by wghicks.bellsouth.net (8.9.3/8.9.2) with ESMTP id SAA26127; Wed, 27 Oct 1999 18:00:53 -0400 (EDT) (envelope-from wghicks@wghicks.bellsouth.net) Message-Id: <199910272200.SAA26127@bellsouth.net> To: Ilia Chipitsine Cc: questions@FreeBSD.ORG, wghicks@bellsouth.net Subject: Re: why FFS is THAT slower than EXT2 ? In-reply-to: Your message of "Wed, 27 Oct 1999 12:44:42 EDT." Date: Wed, 27 Oct 1999 18:00:53 -0400 From: W Gerald Hicks Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Hmm, was that programmed I/O mode for Linux vs DMA for FreeBSD? One might expect it possible that a device doing programmed I/O might be able to beat out a DMA scheme (for raw throughput) but usually at a cost of being unfair to other processes. A Linux box often "feels" rather jerky to me. Sometimes the numbers it _appears_ to handle might seem very impressive (as do yours) but the story comes out once you put a little processing and I/O load on the system. Put a significant load on your systems and try again ;) Cheers, Jerry Hicks wghicks@bellsouth.net To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message