From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Joonwoo Park" Subject: Re: [PATCH] [IPV4] route: fix locking in rt_run_flush() Date: Thu, 24 Jan 2008 14:06:22 +0900 Message-ID: References: <12009281372201-git-send-email-joonwpark81@gmail.com> <20080121.024043.105024413.davem@davemloft.net> <20080123074320.GB9017@ehus.geninetworks.com> <4797A729.4030006@cosmosbay.com> Mime-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-1 Content-Transfer-Encoding: 7bit Cc: "David Miller" , netdev@vger.kernel.org To: "Eric Dumazet" Return-path: Received: from rv-out-0910.google.com ([209.85.198.185]:28293 "EHLO rv-out-0910.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750714AbYAXFGX (ORCPT ); Thu, 24 Jan 2008 00:06:23 -0500 Received: by rv-out-0910.google.com with SMTP id k20so104404rvb.1 for ; Wed, 23 Jan 2008 21:06:22 -0800 (PST) In-Reply-To: <4797A729.4030006@cosmosbay.com> Content-Disposition: inline Sender: netdev-owner@vger.kernel.org List-ID: 2008/1/24, Eric Dumazet : > > Unfortunatly, your patch doesnt work on CONFIG_SMP=n (softirq will be disabled > for the whole scan of table) > > Also, some machines around there have 2^22 slots in hash table, and NR_CPUS=4, > so softirqs will be disabled for a too long time. > > Please try net-2.6.25 and submit patches on top of it if necessary, since > rt_run_flush() has pending changes, not in net-2.6 > > Note : The 'soft lockup' can be avoided by other means. > > Eric, Thank you for your help. I checked net-2.6.25 in this morining :( And it brought me a conclusion that the fashion of it is the best solution for the all circumstances. I believe that 'cond_resched()' and 'if (!rth) continue' without disable softirq of net-2.6.25 is correct answer. Thanks again! Joonwoo