From owner-freebsd-questions Thu May 17 14:28: 1 2001 Delivered-To: freebsd-questions@freebsd.org Received: from calcon.calcon.net (calcon.net [63.149.52.2]) by hub.freebsd.org (Postfix) with ESMTP id 629B237B42C for ; Thu, 17 May 2001 14:27:58 -0700 (PDT) (envelope-from degan@calcon.net) Received: from calcon.net (vpn1.calcon.net [63.149.52.253]) by calcon.calcon.net (8.11.2/8.11.2) with ESMTP id f4HLRTQ12502; Thu, 17 May 2001 16:27:29 -0500 Message-ID: <3B044256.8709AEE4@calcon.net> Date: Thu, 17 May 2001 16:27:50 -0500 From: Douglas Egan X-Mailer: Mozilla 4.75 [en] (X11; U; NetBSD 1.5 i386) X-Accept-Language: en MIME-Version: 1.0 To: "Jon O." Cc: freebsd-questions@FreeBSD.ORG Subject: Re: FreeBSD benchmark question References: Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk List-ID: X-Loop: FreeBSD.ORG Make sure the filesystems on both machines are mounted the same way. Linux defaults to async, whereas BSD default is metadata sync, data async Not sure if this would affect performance on your specific test, but you should at least compare apples to apples. Mount both as either sync or async explicitly before running the test. Doug "Jon O." wrote: > Hi: > > We are testing a VALinux machine running Red Hat 6.2 against a FreeBSD > machine running 4.3-RELEASE. The test consists of running a genetic search > algorithm on both machines and using time to meaure the result. > > I have found the Linux box is much faster after running the search once > and then firing it off again. So, the first run of the test the two > machines are almost exactly as fast. But, the next time the linux box runs > the test it is vastly faster than the FreeBSD box. I believe this has > something to do with caching, but I don't know the specifics. Can this > type of feature work on FreeBSD? I've enabled softupdates but that only > helps a little. > > Also, the linux box seems to run the CPU up to 100% right off the bat when > starting the test. This probably helps it complete the test quickly. > However, the FreeBSD box runs the CPU up more slowly and never reaches > even 75% usage. Is there a way to get the FreeBSD box to hog the processor > right off the bat? > > > Thanks, > Jon > > To Unsubscribe: send mail to majordomo@FreeBSD.org > with "unsubscribe freebsd-questions" in the body of the message To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message