From mboxrd@z Thu Jan 1 00:00:00 1970 From: Eric Dumazet Subject: Re: [PATCH net-next-2.6] net: Xmit Packet Steering (XPS) Date: Fri, 20 Nov 2009 23:36:22 +0100 Message-ID: <4B0719E6.4060402@gmail.com> References: <4B05D8DC.7020907@gmail.com> <20091120.143218.252563862.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: QUOTED-PRINTABLE Cc: therbert@google.com, netdev@vger.kernel.org To: David Miller Return-path: Received: from gw1.cosmosbay.com ([212.99.114.194]:59613 "EHLO gw1.cosmosbay.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754684AbZKTWgW (ORCPT ); Fri, 20 Nov 2009 17:36:22 -0500 In-Reply-To: <20091120.143218.252563862.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: David Miller a =E9crit : >=20 > I like this work. But as you know it still needs a little bit > more work :-) >=20 > Let's also pick a more decent name for the free function since > tons of drivers are going to call this thing. How about > dev_kfree_tx_skb()? :-) >=20 > I see Jarek and you have come to a mutual understanding about the > locking. Since you need to change it anyways to fix the deadlock, > what using a netchannel like scheme to do remote SKB queueing? >=20 > PAGE_SIZE queue arrays, lockless access to head and tail pointers, an= d > if queue is full we local free. >=20 > I think that's a reasonable policy and the only detail to work out is > to make sure we never race on the IPI send and thus miss processing > the queue. >=20 > What do you think? >=20 Thats good ideas David, I'll work on them next week, and do benchmarks = as well before sending a new version. Thanks