From owner-freebsd-stable Thu Mar 29 23:16:59 2001 Delivered-To: freebsd-stable@freebsd.org Received: from hall.mail.mindspring.net (hall.mail.mindspring.net [207.69.200.60]) by hub.freebsd.org (Postfix) with ESMTP id CCD0E37B720 for ; Thu, 29 Mar 2001 23:16:55 -0800 (PST) (envelope-from lists@alzaid.com) Received: from RAMI.alzaid.com (user-38ld89i.dsl.mindspring.com [209.86.161.50]) by hall.mail.mindspring.net (8.9.3/8.8.5) with ESMTP id CAA14246; Fri, 30 Mar 2001 02:16:40 -0500 (EST) Message-Id: <5.1.0.12.2.20010330021234.030aa6e0@mail.alzaid.com> X-Sender: (Unverified) X-Mailer: QUALCOMM Windows Eudora Version 5.1.0.12 (Beta) Date: Fri, 30 Mar 2001 02:16:33 -0500 To: David Malone From: Rami AlZaid Subject: Re: nfsd Benchmark Cc: freebsd-stable@FreeBSD.ORG In-Reply-To: <20010328102955.A92875@walton.maths.tcd.ie> References: <5.1.0.12.2.20010327202300.04c60e10@wheresmymailserver.com> <5.1.0.12.2.20010327202300.04c60e10@wheresmymailserver.com> Mime-Version: 1.0 Content-Type: text/plain; charset="us-ascii"; format=flowed Sender: owner-freebsd-stable@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG I've compiled the debugger into the kernel and read the section about that in the handbook but now after the crash there isn't any dump restored! I tried using the ctl-alt-esc but that doesn't help... when the machined is killed I'm not about to do anything with it at all other than resetting the machine. At 04:29 AM 3/28/2001, you wrote: >On Tue, Mar 27, 2001 at 08:29:35PM -0500, Rami AlZaid wrote: > > I'm currently running 4.3-BETA and I'm trying to benchmark nfsd > > with iozone. When using a Linux machine (2.2.18) as the nfs client and a > > FreeBSD machine as the nfs server, the whole FreeBSD machine hangs when > > trying to benchmark and the only thing I could do is turn it off and turn > > it back on again. The nfsd works fine in normal usage but it just hangs > > when benchmarking. Does anyone know why would nfsd hangs the FreeBSD > > machine when trying to benchmark it? is this a bug? > >Definitely a bug. Linux used to have lousy clustering, which would >result in the NFS server being hit harder during writes, but I >think this has been fixed. It shouldn't kill the server either >way. Have you tried compiling the debugger into the kernel and >using ctl-alt-esc when it is wedged? Rami AlZaid * ICQ # 1071118 WebPages: www.alzaid.com * www.wooyeah.com To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-stable" in the body of the message