From mboxrd@z Thu Jan 1 00:00:00 1970 From: Chris Mason Subject: Re: [PATCH RFC] ipv6_fib limit spinlock hold times for /proc/net/ipv6_route Date: Mon, 28 Apr 2014 13:21:05 -0400 Message-ID: <535E8E01.6070908@fb.com> References: <535918BC.5030708@fb.com> <20140425.160929.1031376209639331549.davem@davemloft.net> <535AC529.4030107@fb.com> <20140426.001134.778620720962127881.davem@davemloft.net> Mime-Version: 1.0 Content-Type: text/plain; charset="ISO-8859-1"; format=flowed Content-Transfer-Encoding: 7bit Cc: To: David Miller Return-path: Received: from mx0a-00082601.pphosted.com ([67.231.145.42]:20294 "EHLO mx0a-00082601.pphosted.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753082AbaD1Tfn (ORCPT ); Mon, 28 Apr 2014 15:35:43 -0400 In-Reply-To: <20140426.001134.778620720962127881.davem@davemloft.net> Sender: netdev-owner@vger.kernel.org List-ID: On 04/26/2014 12:11 AM, David Miller wrote: > From: Chris Mason > Date: Fri, 25 Apr 2014 16:27:21 -0400 > >> Ah ok, so the rtnl mutex can replace rcu_read_lock(). Will it end up >> blocking any traffic? (sorry, filesystem guys are a little slow) > > It stops networking configuration operations. > > BTW, this means that netlink based ipv6 route dumps can be > optimized similarly. Because those code paths implicitly > hold the RTNL mutex. > Ok, the rtnl mutex looks like a much better path. I'll give it a shot this week. If anyone working on patches in this area wants help testing, just let me know. -chris