From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: tx queue hashing hot-spots and poor performance (multiq, ixgbe) Date: Fri, 01 May 2009 18:48:30 +0200 Message-ID: <49FB27DE.6090002@cosmosbay.com> References: <20090430.070811.260649067.davem@davemloft.net> <606676310904301653w28f3226fsc477dc92b6a7cdbc@mail.gmail.com> <49FA932B.4030405@cosmosbay.com> <20090501.090815.262436244.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: andrew@whydna.net, jelaas@gmail.com, netdev@vger.kernel.org To: David Miller Return-path: Received: from gw1.cosmosbay.com ([212.99.114.194]:55544 "EHLO gw1.cosmosbay.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752399AbZEAQsj convert rfc822-to-8bit (ORCPT ); Fri, 1 May 2009 12:48:39 -0400 In-Reply-To: <20090501.090815.262436244.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: David Miller a =E9crit : > From: Eric Dumazet > Date: Fri, 01 May 2009 08:14:03 +0200 >=20 >> [PATCH] net: skb_tx_hash() improvements >> >> When skb_rx_queue_recorded() is true, we dont want to use jash distr= ibution >> as the device driver exactly told us which queue was selected at RX = time. >> jhash makes a statistical shuffle, but this wont work with 8 static = inputs. >> >> Later improvements would be to compute reciprocal value of real_num_= tx_queues >> to avoid a divide here. But this computation should be done once, >> when real_num_tx_queues is set. This needs a separate patch, and a n= ew >> field in struct net_device. >> >> Reported-by: Andrew Dickinson >> Signed-off-by: Eric Dumazet >=20 > Applied, except that I changed the commit message header line to more > reflect that this is in fact a bug fix. >=20 > BTW, you don't need the reciprocol when num-tx-queues <=3D num-rx-que= ues > (you can just use the RX queue recording as the hash, straight) and > that's the kind of check what I intended to add to net-2.6 had you no= t > beaten me to this patch. >=20 > Also, thanks for giving me absolutely no credit for this whole thing > in your commit message. I know I do that to you all the time :-/ How > can you forget so quickly that I'm the one that even suggested the > exact code change for Andrew to test in the first place? Hoho, your Honor, I am totaly guilty and sorry, sometime I think I am David Miller, silly me ! :) I am not fighting for credit or whatever, certainly not with you.