From owner-freebsd-hackers@FreeBSD.ORG Tue Jul 25 17:10:58 2006 Return-Path: X-Original-To: freebsd-hackers@freebsd.org 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 3041516A60B; Tue, 25 Jul 2006 17:10:58 +0000 (UTC) (envelope-from scheidell@secnap.net) Received: from mail.secnap.com (mail.secnap.com [204.89.241.129]) by mx1.FreeBSD.org (Postfix) with ESMTP id D03BD43D45; Tue, 25 Jul 2006 17:10:57 +0000 (GMT) (envelope-from scheidell@secnap.net) Received: from [10.70.3.3] (unknown [10.70.3.3]) by mail.secnap.com (Postfix) with ESMTP id A15F1164838; Tue, 25 Jul 2006 13:10:56 -0400 (EDT) Message-ID: <44C6509E.4090708@secnap.net> Date: Tue, 25 Jul 2006 13:10:54 -0400 From: Michael Scheidell Organization: SECNAP Network Security User-Agent: Thunderbird 1.5.0.4 (Macintosh/20060530) MIME-Version: 1.0 To: Tim Kientzle References: <20060725.093429.-1648696470.imp@bsdimp.com> <44C63DD2.9080705@freebsd.org> In-Reply-To: <44C63DD2.9080705@freebsd.org> Content-Type: text/plain; charset=ISO-8859-1; format=flowed Content-Transfer-Encoding: 7bit Cc: freebsd-hackers@freebsd.org Subject: Re: FBSD 5.5 and software timers X-BeenThere: freebsd-hackers@freebsd.org X-Mailman-Version: 2.1.5 Precedence: list List-Id: Technical Discussions relating to FreeBSD List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 25 Jul 2006 17:10:58 -0000 Tim Kientzle wrote: > M. Warner Losh wrote: >> In message: >> "Michael Scheidell" writes: >> : > I presume the servers are all stable (ie not stepping) and : > >> have a reasonably low delay. If so, I suspect your ntpd PLL : > has >> locked up. I've seen problems with some versions of ntpd : : 20 >> different machines? >> >> That would strongly imply a poor choice of upstream server. > > It might also help to set up 1 machine as > your NTP master. Have it sync to the upstream > servers and have the rest of your machines > sync to it. This won't solve the problem, > but might make it easier to solve (once your > NTP master is stable, the rest should follow). > Except that all 20 are on different physical networks, one in a different content. I went back and looked at out 4.11 systems, and didn't see any 'time reset' errors. Internally, here at this physical location, we do have one master ntp server, pulling from (3) servers, not two. All internal systems then pull from this one master. > You can experiment with different upstream > servers, different network settings, different > NTP settings, etc. > only ntp setting that helped was the -x option (adjust once, slew 128m max each other time) One external box is now 30 seconds out of sync (after 24 hours) Again, ntp problem is one thing, but what about the nanosleep() issue? 5.4 worked fine, 5.5 has problems. Did something change in 5.5 with clock() or nanosleep()? Its not documented in the readme for 5.5. -- Michael Scheidell, CTO SECNAP Network Security / www.secnap.com scheidell@secnap.net / 1+561-999-5000, x 1131