From mboxrd@z Thu Jan 1 00:00:00 1970 From: Ben Greear Subject: Re: Netchannles: first stage has been completed. Further ideas. Date: Thu, 20 Jul 2006 14:21:57 -0700 Message-ID: <44BFF3F5.3040104@candelatech.com> References: <20060719131915.GA21942@ms2.inr.ac.ru> <20060720073223.GA15567@tservice.net.ru> <20060720164100.GA9213@ms2.inr.ac.ru> <20060720210849.GA28715@tservice.net.ru> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii; format=flowed Content-Transfer-Encoding: 7bit Cc: Alexey Kuznetsov , davem@davemloft.net, netdev@vger.kernel.org Return-path: Received: from ns2.lanforge.com ([66.165.47.211]:61581 "EHLO ns2.lanforge.com") by vger.kernel.org with ESMTP id S1030378AbWGTVWa (ORCPT ); Thu, 20 Jul 2006 17:22:30 -0400 To: johnpol@2ka.mipt.ru In-Reply-To: <20060720210849.GA28715@tservice.net.ru> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org Evgeniy Polyakov wrote: >>Backlog is actually not a protection, but a thing equivalent to netchannel. >>The difference is only that it tries to process something immediately, >>when it is safe. You can omit this and push everything to backlog(=netchannel), >>which is processed only by syscalls, if you do not care about latency. > > > If we consider netchannels as how Van Jackobson discribed them, then > mutext is not needed, since it is impossible to have several readers or > writers. But in socket case even if there is only one userspace > consumer, that lock must be held to protect against bh (or introduce > several queues and complicate a lot their's management (ucopy for > example)). Out of curiosity, is it possible to have the single producer logic if you have two+ ethernet interfaces handling frames for a single TCP connection? (I am assuming some sort of multi-path routing logic...) Thanks, Ben -- Ben Greear Candela Technologies Inc http://www.candelatech.com