From mboxrd@z Thu Jan 1 00:00:00 1970 From: jamal Subject: Re: [PATCH v3] net: batch skb dequeueing from softnet input_pkt_queue Date: Thu, 22 Apr 2010 08:13:48 -0400 Message-ID: <1271938428.4032.31.camel@bigi> References: <1271238738-8386-1-git-send-email-xiaosuo@gmail.com> <1271891149.7895.3751.camel@edumazet-laptop> Reply-To: hadi@cyberus.ca Mime-Version: 1.0 Content-Type: text/plain Content-Transfer-Encoding: 7bit Cc: Changli Gao , "David S. Miller" , netdev@vger.kernel.org, Tom Herbert To: Eric Dumazet Return-path: Received: from mail-qy0-f179.google.com ([209.85.221.179]:44811 "EHLO mail-qy0-f179.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753528Ab0DVMNv (ORCPT ); Thu, 22 Apr 2010 08:13:51 -0400 Received: by qyk9 with SMTP id 9so11106047qyk.1 for ; Thu, 22 Apr 2010 05:13:51 -0700 (PDT) In-Reply-To: <1271891149.7895.3751.camel@edumazet-laptop> Sender: netdev-owner@vger.kernel.org List-ID: On Thu, 2010-04-22 at 01:05 +0200, Eric Dumazet wrote: > [RFC] net: introduce a batch mode in process_backlog() > > We see a lock contention on input_pkt_queue.lock in RPS benches. > > As suggested by Changli Gao, we can batch several skbs at once in > process_backlog(), so that we dirty input_pkt_queue less often. > Ok, so i grab the latest and greatest net-next and apply this before testing? Let me know.. cheers, jamal