From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?ISO-8859-1?Q?D=E2niel?= Fraga Subject: Re: [PATCH] tcp FRTO: in-order-only "TCP proxy" fragility workaround Date: Tue, 16 Sep 2008 11:24:11 -0300 Message-ID: <20080916112411.062fa615@tux> References: <20080819213417.45133573@tux> <20080822183224.2d52f16c@tux> <20080822.143709.65615512.davem@davemloft.net> <20080823111446.06a350a2@tux> <20080824163843.33b4f890@tux> <20080826141812.589848a0@tux> <20080828184919.611dd578@tux> <20080830035650.42be37d7@tux> <20080907051718.58bf133d@tux> <20080908172043.0d25a427@tux> <20080911143006.2f516569@tux> <20080913203117.2a55ea2c@tux> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: David Miller , thomas.jarosch@intra2net.com, billfink@mindspring.com, Netdev , Patrick Hardy , netfilter-devel@vger.kernel.org, kadlec@blackhole.kfki.hu To: "Ilpo =?ISO-8859-1?Q?J=E4rvinen?=" Return-path: Received: from an-out-0708.google.com ([209.85.132.245]:42034 "EHLO an-out-0708.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752583AbYIPOYW (ORCPT ); Tue, 16 Sep 2008 10:24:22 -0400 Received: by an-out-0708.google.com with SMTP id d40so263364and.103 for ; Tue, 16 Sep 2008 07:24:19 -0700 (PDT) In-Reply-To: Sender: netdev-owner@vger.kernel.org List-ID: On Tue, 16 Sep 2008 15:10:33 +0300 (EEST) "Ilpo J=E4rvinen" wrote: > Only thing I know to ask is, do you have any idea if your ntpd is=20 > hard-stepping the time instead of adjusting the clock's rate a bit (t= he=20 > latter should keep the clock monotonious besides potential bugs)? I assume it's adjusting the clock's rate a bit. Anyway, it's a pretty simple config: fraga@teleporto ~$ cat /etc/ntp.conf=20 server ntp.usp.br server ntp.nasa.gov driftfile /etc/ntp.drift And ntpd is running without any special parameters. The log messages are as simple as: Sep 15 03:56:04 teleporto ntpd[2301]: frequency initialized 5.891 PPM f= rom /etc/ntp.drift Sep 15 03:59:25 teleporto ntpd[2304]: frequency initialized 5.891 PPM f= rom /etc/ntp.drift Sep 15 04:03:49 teleporto ntpd[2304]: synchronized to 143.107.255.15, s= tratum 2 Sep 15 04:03:49 teleporto ntpd[2304]: kernel time sync status change 00= 01 Sep 15 04:10:16 teleporto ntpd[2304]: synchronized to 198.123.30.132, s= tratum 1 Sep 15 04:11:58 teleporto ntpd[2301]: frequency initialized 5.891 PPM f= rom /etc/ntp.drift Sep 15 04:16:18 teleporto ntpd[2301]: synchronized to 198.123.30.132, s= tratum 1 Sep 15 04:16:18 teleporto ntpd[2301]: kernel time sync status change 00= 01 Sep 15 12:08:53 teleporto ntpd[2301]: kernel time sync status change 40= 01 Sep 15 12:34:31 teleporto ntpd[2301]: kernel time sync status change 00= 01 Sep 15 14:34:06 teleporto ntpd[2301]: kernel time sync status change 40= 01 Sep 15 14:51:12 teleporto ntpd[2301]: kernel time sync status change 00= 01=20 If I understood correctly what do you mean, ntpd adjusts nicely the ti= me to not=20 cause huge differences in the time. And we're reaching the conclusion that the timer code from 2.6.25 and = above=20 have something wrong, since 2.6.24 and below is ok, which causes those = stalls. But I'll wait some more time to confirm this, although I'm almost sure= it's a timer related bug which has this colateral effect of stalling connections. And just a question: do you use ntpd on your own desktop? =09 Thank you! --=20