From: Linus Torvalds Subject: Re: [GIT PULL URGENT] ext4 regression fix for 3.9 Date: Sat, 2 Mar 2013 11:54:37 -0800 Message-ID: References: <20130227172256.GA236@x4> <7BFB2135-A1F0-4B6D-9962-16E75E5560F8@gmail.com> <20130227174553.GA224@x4> <20130227184912.GA19624@thunk.org> <20130227185625.GA224@x4> <20130227191923.GA1121@redhat.com> <20130227192907.GB14253@thunk.org> <20130227201217.GD14253@thunk.org> <20130301033005.GA7081@redhat.com> <20130301040039.GA4452@thunk.org> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8 To: "Theodore Ts'o" , Dave Jones , Linus Torvalds , Markus Trippelsdorf , "gnehzuil.liu" , Zheng Liu , Borislav Petkov , "linux-ext4@vger.kernel.org" , "linux-kernel@vger.kernel.org" Return-path: Received: from mail-ve0-f173.google.com ([209.85.128.173]:62072 "EHLO mail-ve0-f173.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752409Ab3CBTyi (ORCPT ); Sat, 2 Mar 2013 14:54:38 -0500 In-Reply-To: <20130301040039.GA4452@thunk.org> Sender: linux-ext4-owner@vger.kernel.org List-ID: On Thu, Feb 28, 2013 at 8:00 PM, Theodore Ts'o wrote: > > ext4_es_reclaim_extents_count() is getting called out of the slab > shrinker. It's getting called too often when there is significant > memory pressure. We can optimize this so we're not calculating it all > the time. This needs to be fixed or reverted. I traced back some user interaction problems to this same issue. It literally gets so bad that the whole system is choppy, and a profile shows that a lot of time is being spent in the spin-lock protecting these data structures. Called from ext4_es_reclaim_extents_count, ext4_es_lru_add and ext4_es_shrink. We're talking very user-noticeable pauses, so it's not just the spinlock, there's some real badness that comes in with it too. Possibly related to other (sleeping) locks being held while the data structures are then refilled or something. Linus