From owner-freebsd-hackers@FreeBSD.ORG Sat Oct 23 18:09:34 2004 Return-Path: Delivered-To: freebsd-hackers@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id 2F8BE16A4CE for ; Sat, 23 Oct 2004 18:09:34 +0000 (GMT) Received: from voodoo.oberon.net (voodoo.oberon.net [212.118.165.100]) by mx1.FreeBSD.org (Postfix) with ESMTP id E50CF43D48 for ; Sat, 23 Oct 2004 18:09:33 +0000 (GMT) (envelope-from igor@doom.homeunix.org) Received: from [84.204.7.14] (helo=doom.homeunix.org) by voodoo.oberon.net with esmtps (TLSv1:AES256-SHA:256) (Exim 4.43 (FreeBSD)) id 1CLQJb-00016t-Pr for hackers@freebsd.org; Sat, 23 Oct 2004 20:09:32 +0200 Received: from doom.homeunix.org (localhost [127.0.0.1]) by doom.homeunix.org (8.13.1/8.13.1) with ESMTP id i9NI76gq019084 for ; Sat, 23 Oct 2004 22:07:13 +0400 (MSD) (envelope-from igor@doom.homeunix.org) Received: (from igor@localhost) by doom.homeunix.org (8.13.1/8.13.1/Submit) id i9NI6cuY019083 for hackers@freebsd.org; Sat, 23 Oct 2004 22:06:38 +0400 (MSD) (envelope-from igor) Date: Sat, 23 Oct 2004 22:06:38 +0400 From: Igor Pokrovsky To: hackers@freebsd.org Message-ID: <20041023180638.GA19033@doom.homeunix.org> Mail-Followup-To: hackers@freebsd.org References: <20041022223238.GA12502@tikitechnologies.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20041022223238.GA12502@tikitechnologies.com> User-Agent: Mutt/1.4.2.1i Subject: Re: Relative performance of swap-backed MFS vs. regular UFS? X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.1 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 23 Oct 2004 18:09:34 -0000 On Fri, Oct 22, 2004 at 12:32:40PM -1000, Clifton Royston wrote: > I have seen some conflicting information posted about this in the > past, and I figure this is the best place to get an authoritative > answer. > > For a large temporary file system which must hold short-lived files, > mostly small but occasionally several very large ones (e.g. 100MB+), is > it better for performance and stability if this file system: > > 1) resides on a swap-backed MFS and trusts the OS to swap out > low-priority blocks if needed under RAM pressure, or > > 2) on a regular UFS and trusts the OS to buffer as many blocks as > possible into RAM when RAM is free? You can also use md(4). In my case I use it for /tmp. -ip -- The best shots happen immediately after the last frame is exposed.