From mboxrd@z Thu Jan 1 00:00:00 1970 From: Alex Sidorenko Subject: Re: An inconsistency/bug in ingress netem timestamps Date: Thu, 16 Apr 2009 08:09:56 -0400 Message-ID: <200904160809.56228.alexandre.sidorenko@hp.com> References: <20090415195022.GA3322@ami.dom.local> <200904151610.43980.alexandre.sidorenko@hp.com> <20090416.031034.41207844.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7BIT Cc: "jarkao2@gmail.com" , "netdev@vger.kernel.org" To: David Miller Return-path: Received: from g4t0017.houston.hp.com ([15.201.24.20]:5387 "EHLO g4t0017.houston.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753546AbZDPMJ5 convert rfc822-to-8bit (ORCPT ); Thu, 16 Apr 2009 08:09:57 -0400 In-Reply-To: <20090416.031034.41207844.davem@davemloft.net> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: On April 16, 2009 06:10:34 am David Miller wrote: > Since IFB completely bypasses netif_rx() and netif_receive_skb() I > think it should unconditionally set skb->tstamp.tv64 to zero and > invoke net_timestamp() >>From ifb.c (2.6.29): 109 if (from & AT_EGRESS) { 110 dp->st_rx_frm_egr++; 111 dev_queue_xmit(skb); 112 } else if (from & AT_INGRESS) { 113 dp->st_rx_frm_ing++; 114 skb_pull(skb, skb->dev->hard_header_len); 115 netif_rx(skb); 116 } Adding skb->tstamp.tv64 = 0 between lines 114 and 115 made 'ping' report the delay as expected (tested on 2.6.28) Alex -- ------------------------------------------------------------------ Alexandre Sidorenko email: asid@hp.com WTEC Linux Hewlett-Packard (Canada) ------------------------------------------------------------------