From mboxrd@z Thu Jan 1 00:00:00 1970 From: David Miller Subject: Re: [RFC][PATCH 0/9] Network receive deadlock prevention for NBD Date: Wed, 09 Aug 2006 16:54:31 -0700 (PDT) Message-ID: <20060809.165431.118952392.davem@davemloft.net> References: <1155127040.12225.25.camel@twins> <20060809130752.GA17953@2ka.mipt.ru> <1155130353.12225.53.camel@twins> Mime-Version: 1.0 Content-Type: Text/Plain; charset=us-ascii Content-Transfer-Encoding: 7bit Cc: johnpol@2ka.mipt.ru, linux-mm@kvack.org, linux-kernel@vger.kernel.org, netdev@vger.kernel.org, phillips@google.com Return-path: Received: from dsl027-180-168.sfo1.dsl.speakeasy.net ([216.27.180.168]:8122 "EHLO sunset.davemloft.net") by vger.kernel.org with ESMTP id S1751345AbWHIXyt (ORCPT ); Wed, 9 Aug 2006 19:54:49 -0400 To: a.p.zijlstra@chello.nl In-Reply-To: <1155130353.12225.53.camel@twins> Sender: netdev-owner@vger.kernel.org List-Id: netdev.vger.kernel.org From: Peter Zijlstra Date: Wed, 09 Aug 2006 15:32:33 +0200 > The idea is to drop all !NFS packets (or even more specific only > keep those NFS packets that belong to the critical mount), and > everybody doing critical IO over layered networks like IPSec or > other tunnel constructs asks for trouble - Just DON'T do that. People are doing I/O over IP exactly for it's ubiquity and flexibility. It seems a major limitation of the design if you cancel out major components of this flexibility. I really can't take this work seriously when I see things like this being said.