Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754858AbbHAAKU (ORCPT ); Fri, 31 Jul 2015 20:10:20 -0400 Received: from mail-pa0-f43.google.com ([209.85.220.43]:34892 "EHLO mail-pa0-f43.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754281AbbHAAKS (ORCPT ); Fri, 31 Jul 2015 20:10:18 -0400 Date: Fri, 31 Jul 2015 17:09:23 -0700 (PDT) From: Hugh Dickins X-X-Sender: hugh@eggly.anvils To: Dominique Martinet cc: David Howells , Hugh Dickins , Linus Torvalds , "J. Bruce Fields" , Dominique Martinet , Al Viro , Linux Kernel Mailing List , linux-fsdevel Subject: Re: v4.2-rc dcache regression, probably 75a6f82a0d10 In-Reply-To: <20150731205036.GA3752@nautica> Message-ID: References: <20150731205036.GA3752@nautica> User-Agent: Alpine 2.11 (LSU 23 2013-08-11) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 2381 Lines: 58 On Fri, 31 Jul 2015, Dominique Martinet wrote: > Hugh Dickins wrote on Fri, Jul 31, 2015: > > It will indeed be weird and odd if it confirms that DCACHE_DISCONNECTED > > revert is good. I agree that Dominique's 4bf46a272647 seems now more > > likely, if still unlikely; but that was included in v4.1, and I saw > > no problem with v4.1 once the rmap_walk() skip was fixed. > > I think it could, actually, and that neither commits are actually bad -- > just that they affect timing enough to raise an issue between d_delete > (I guess?) and link_path_walk (see last mail in other thread[1]) > > It's probably an old race that was very hard to hit because of cache > coherency. > Basically, before the wmb/rmb, the dentry was always updated closely to > its flags, so the other CPU would "usually" get both updates at the same > time; the barriers make it so the updates are split and it's possible to > get it, and would explain why I could pick 4bf46a2726 as "the one" > > > I'm not sure why the problem wouldn't arise on tmpfs though. > > Hugh, could you try the reproducer I gave in the other thread[2] on both > filesystems maybe? Sorry, I probably won't get around to that, to be honest: it shouldn't need me to run it anyway. > I need to let the thing run for a while, might need to tune params as > well. I was trying to fine tune cpu affinity with less threads but it's > not getting anywhere. > > I'll also check if it's getting even easier to reproduce with > 75a6f82a0d10 (or a recent kernel), who knows... How fast do you hit the > bug with the commit? "A number of hours". I don't have my records in front of me at the moment, but I think when I was lucky it happened within two hours, but more commonly around ten or twelve hours. I just leave it going and get on with other things: yours may be a _much_ better reproducer. Though once there's a potential fix, we shall both need to try it, to report back if our separate cases are fixed. Hugh > > > Thanks, > -- > Dominique > > [1] https://marc.info/?l=linux-fsdevel&m=143835651005259&w=2 > [2] https://marc.info/?l=linux-fsdevel&m=143825706609188&w=2 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/