From mboxrd@z Thu Jan 1 00:00:00 1970 From: Richard Cochran Subject: Re: [PATCH net-next 0/5] PF_PACKET timestamping updates Date: Tue, 23 Apr 2013 20:13:23 +0200 Message-ID: <20130423181322.GC2675@netboy> References: <1366713572-11978-1-git-send-email-dborkman@redhat.com> <5176842F.7040703@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Willem de Bruijn , David Miller , netdev@vger.kernel.org, Paul Chavent To: Daniel Borkmann Return-path: Received: from mail-ea0-f177.google.com ([209.85.215.177]:52239 "EHLO mail-ea0-f177.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756735Ab3DWSNg (ORCPT ); Tue, 23 Apr 2013 14:13:36 -0400 Received: by mail-ea0-f177.google.com with SMTP id q14so385300eaj.8 for ; Tue, 23 Apr 2013 11:13:34 -0700 (PDT) Content-Disposition: inline In-Reply-To: <5176842F.7040703@redhat.com> Sender: netdev-owner@vger.kernel.org List-ID: On Tue, Apr 23, 2013 at 02:53:03PM +0200, Daniel Borkmann wrote: > > Well, for the {RX,TX}_RING there is really no other way except the really > really ugly possibility to introduce yet another tpacket header with 3 > time-stamp fields (sw, sys, raw). I really do not like that. :-) Yep. Your solution with the status bits is nicer than the normal SO_TIMESTAMPING cmsg. I think there is currently no way for the kernel to produce two or three time stamps at the same time, and so the whole timestamp triple is rather pointless. > At least here, if you have traffic from different devices, you either get > what you want (e.g. hw ts), or you'll get a fallback sw ts. That is also > the case in the current code without this patchset. At least this set would > solve this issue of telling the user what ts source he sees. Yes, very good. Thanks, Richard