From owner-freebsd-current@FreeBSD.ORG Fri Jul 22 00:46:42 2005 Return-Path: X-Original-To: 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 D9DE016A41F; Fri, 22 Jul 2005 00:46:42 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from cyrus.watson.org (cyrus.watson.org [204.156.12.53]) by mx1.FreeBSD.org (Postfix) with ESMTP id 7763743D55; Fri, 22 Jul 2005 00:46:06 +0000 (GMT) (envelope-from rwatson@FreeBSD.org) Received: from fledge.watson.org (fledge.watson.org [204.156.12.50]) by cyrus.watson.org (Postfix) with ESMTP id E825946B3C; Thu, 21 Jul 2005 20:46:05 -0400 (EDT) Date: Fri, 22 Jul 2005 01:46:37 +0100 (BST) From: Robert Watson X-X-Sender: robert@fledge.watson.org To: Andrey Chernov In-Reply-To: <20050722004021.GB1415@nagual.pp.ru> Message-ID: <20050722014551.G16902@fledge.watson.org> References: <20050721134816.GA8550@nagual.pp.ru> <20050722011556.T16902@fledge.watson.org> <20050722004021.GB1415@nagual.pp.ru> MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: current@FreeBSD.ORG Subject: Re: rl(4) is not ready for mpsafenet net enough? (silent reboots) 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: Fri, 22 Jul 2005 00:46:43 -0000 On Fri, 22 Jul 2005, Andrey Chernov wrote: > On Fri, Jul 22, 2005 at 01:17:52AM +0100, Robert Watson wrote: >> coverage, it's not necessarily a locking problem. Out of curiousity, >> if you take "options PREEMPTION" out, but leave debug.mpsafenet=1, do >> things change? > > I don't have "options PREEMPTION". Is it good to have? It's in GENERIC, so I assumed you were running with it unless you otherwise documented it as part of your bug report. PREEMPTION is good to have, as it dramatically lowers the latency in processing interrupts when running kernel-intensive workloads. Robert N M Watson