From owner-freebsd-questions Mon Apr 19 18:32:26 1999 Delivered-To: freebsd-questions@freebsd.org Received: from dsinw.com (dsinw.com [207.149.40.5]) by hub.freebsd.org (Postfix) with ESMTP id 67C4515295 for ; Mon, 19 Apr 1999 18:32:22 -0700 (PDT) (envelope-from hamellr@dsinw.com) Received: (from hamellr@localhost) by dsinw.com (8.8.8/8.7.3) id SAA03023; Mon, 19 Apr 1999 18:26:54 -0700 (PDT) Date: Mon, 19 Apr 1999 18:26:54 -0700 (PDT) From: rick hamell To: cjclark@home.com Cc: FreeBSD Questions Subject: Re: Performance Question In-Reply-To: <199904191956.PAA08664@cc942873-a.ewndsr1.nj.home.com> Message-ID: MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: owner-freebsd-questions@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG > drives in such a role. So my question is, on an all IDE system, how > much of a performance increase does one get by moving the swap from a > partition on the same drive that contains the OS and user data to a > separate, dedicated swap drive? Does the performance depend IMHO, probally enough to make it a worthwhile project. > (significantly) on the way the IDE devices are configured (what is > primary/secondary or master/slave)? Total performace depends on a few things. If you can try to make the drive master on it's own IDE cable, there will be a slight increase in performace this way. Maxtor, certain Seagate Models and most Conner drives really prefer to be Master, they could not work at all, especially paired with another. I.e, never ever put a Seagate as a slave to a Maxtor drive. Rick To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-questions" in the body of the message