From owner-freebsd-current@FreeBSD.ORG Sat Aug 13 22:34:28 2005 Return-Path: X-Original-To: freebsd-current@freebsd.org Delivered-To: freebsd-current@freebsd.org Received: from mx1.FreeBSD.org (mx1.freebsd.org [216.136.204.125]) by hub.freebsd.org (Postfix) with ESMTP id A941F16A41F for ; Sat, 13 Aug 2005 22:34:28 +0000 (GMT) (envelope-from tyler@tamu.edu) Received: from smtp-relay.tamu.edu (smtp-relay.tamu.edu [165.91.143.199]) by mx1.FreeBSD.org (Postfix) with ESMTP id 5B67743D45 for ; Sat, 13 Aug 2005 22:34:28 +0000 (GMT) (envelope-from tyler@tamu.edu) Received: from [192.168.1.102] (disisit.com [24.248.192.101] (may be forged)) (authenticated bits=0) by smtp-relay.tamu.edu (8.13.3/8.13.3/oc) with ESMTP id j7DMYQwP092408 (version=TLSv1/SSLv3 cipher=RC4-SHA bits=128 verify=NO) for ; Sat, 13 Aug 2005 17:34:27 -0500 (CDT) (envelope-from tyler@tamu.edu) Mime-Version: 1.0 (Apple Message framework v733) Content-Transfer-Encoding: 7bit Message-Id: Content-Type: text/plain; charset=US-ASCII; delsp=yes; format=flowed To: freebsd-current@freebsd.org From: "R. Tyler Ballance" Date: Sat, 13 Aug 2005 17:34:41 -0500 X-Mailer: Apple Mail (2.733) Received-SPF: pass (smtp-relay.tamu.edu: 24.248.192.101 is authenticated by a trusted mechanism) Subject: Disk I/O and Peripheral I/O in 6.0-BETA X-BeenThere: freebsd-current@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Discussions about the use of FreeBSD-current List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Sat, 13 Aug 2005 22:34:28 -0000 Howdy, I'm using a source build of 6.0-BETA2 (built over 5.4-STABLE) and I'm still experiencing something I either never experienced, or never noticed on RELENG_5. Whenever I have huge disk related processes running, `rm -rf src obj ports` for example, almost all other forms of I/O suffer. The USB mouse that I use starts to lag terribly, USB flash drive transfers slow tremendously, etc. How are these two different sets of I/O causing interference with one another? Is this a result of me running a uniprocessor board? (given the SMPng enhancements?) Is this just something I'm going to have to cope with, or is there some other way I can give USB I/O higher priority? Cheers, -R. Tyler Ballance