From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: Problems obtaining software TX timestamps Date: Thu, 09 Sep 2010 20:58:50 +0200 Message-ID: <1284058730.2298.74.camel@edumazet-laptop> References: <4C877D8A.6040002@edu.uni-klu.ac.at> <1283958771.2748.85.camel@edumazet-laptop> <4C87FE60.7090209@edu.uni-klu.ac.at> <20100909063541.GA3305@riccoc20.at.omicron.at> <4C889A1E.6050405@edu.uni-klu.ac.at> <20100909135716.GA8706@riccoc20.at.omicron.at> <1284040958.2589.178.camel@edumazet-laptop> <20100909173228.GA2657@riccoc20.at.omicron.at> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: Ingo Kofler , netdev@vger.kernel.org To: Richard Cochran Return-path: Received: from mail-wy0-f174.google.com ([74.125.82.174]:33088 "EHLO mail-wy0-f174.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751573Ab0IIS7B (ORCPT ); Thu, 9 Sep 2010 14:59:01 -0400 Received: by wyf22 with SMTP id 22so1750671wyf.19 for ; Thu, 09 Sep 2010 11:58:57 -0700 (PDT) In-Reply-To: <20100909173228.GA2657@riccoc20.at.omicron.at> Sender: netdev-owner@vger.kernel.org List-ID: Le jeudi 09 septembre 2010 =C3=A0 19:32 +0200, Richard Cochran a =C3=A9= crit : > On Thu, Sep 09, 2010 at 04:02:38PM +0200, Eric Dumazet wrote: > > Should drivers call it at start_xmit() time, or at tx completion ti= me ? >=20 > IMHO, it should be done as immediately after the buffer has been > handed off to the hardware. Not all MACs have a completion method, so > that would at least make the "rule" consistent. >=20 Well, all drivers must release skb *somewhere*, either in their ndo_start_xmit() or TX completion ;) > In general, the goals of high volume and timestamp accuracy are in > conflict (unless you have HW timestamping). If users are relying on S= W > timestamping, then they should be aware of the fact that high network > traffic will spoil their fun. >=20 - Full duplex mode wanted - And small TX rings