From: Andrew Morton Subject: Re: [PATCH] percpu_counter: Fix __percpu_counter_sum() Date: Sun, 7 Dec 2008 09:28:54 -0800 Message-ID: <20081207092854.f6bcbfae.akpm@linux-foundation.org> References: <4936D287.6090206@cosmosbay.com> <4936EB04.8000609@cosmosbay.com> <20081206202233.3b74febc.akpm@linux-foundation.org> <493BCF60.1080409@cosmosbay.com> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: linux kernel , "David S. Miller" , Peter Zijlstra , Mingming Cao , "Theodore Ts'o" , linux-ext4@vger.kernel.org To: Eric Dumazet Return-path: Received: from smtp1.linux-foundation.org ([140.211.169.13]:34336 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752656AbYLGR3c (ORCPT ); Sun, 7 Dec 2008 12:29:32 -0500 In-Reply-To: <493BCF60.1080409@cosmosbay.com> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Sun, 07 Dec 2008 14:28:00 +0100 Eric Dumazet wrote: > Andrew Morton a __crit : > > On Wed, 03 Dec 2008 21:24:36 +0100 Eric Dumazet wrote: > > > >> Eric Dumazet a __crit : > >> > >> 1) __percpu_counter_sum() is buggy, it should not write > >> on per_cpu_ptr(fbc->counters, cpu), or another cpu > >> could get its changes lost. > >> > >> __percpu_counter_sum should be read only (const struct percpu_counter *fbc), > >> and no locking needed. > > > > No, we can't do this - it will break ext4. > > > > Take a closer look at 1f7c14c62ce63805f9574664a6c6de3633d4a354 and at > > e8ced39d5e8911c662d4d69a342b9d053eaaac4e. > > > > I suggest that what we do is to revert both those changes. We can > > worry about the possibly-unneeded spin_lock later, in a separate patch. > > > > It should have been a separate patch anyway. It's conceptually > > unrelated and is not a bugfix, but it was mixed in with a bugfix. > > > > Mingming, this needs urgent consideration, please. Note that I had to > > make additional changes to ext4 due to the subsequent introduction of > > the dirty_blocks counter. > > > > > > Please read the below changelogs carefully and check that I have got my > > head around this correctly - I may not have done. > > > > > Hum... e8ced39d5e8911c662d4d69a342b9d053eaaac4e is probably following > the wrong path, but I see the intent. Even in the 'nr_files' case, it could > help to reduce excessive calls to percpu_counter_sum() > We should fix this in 2.6.28 - right now percpu_counter_sum() is subtly corrupting the counter's value. I sent two revert patches which I hope to merge into 2.6.28. Could you guys please read/review/maybe-test them? They will make ext4 as slow as it was in 2.6.26, but presumably that's not a catastrophe. > What we can do is to use two s64 counters (only in SMP): We can do lots of things in 2.6.29. Including just making ->counters an array of atomic_t.