From: Christoph Lameter Subject: Re: upcoming kerneloops.org item: get_page_from_freelist Date: Mon, 29 Jun 2009 18:35:49 -0400 (EDT) Message-ID: References: <20090624150714.c7264768.akpm@linux-foundation.org> <20090625132544.GB9995@mit.edu> <20090625193806.GA6472@mit.edu> <20090625194423.GB6472@mit.edu> <20090625203743.GD6472@mit.edu> <20090625212628.GO3385@webber.adilger.int> <20090625220504.GG6472@mit.edu> <4A43F60D.2040801@redhat.com> <20090626011155.GI6472@mit.edu> <4A44DE14.2080403@redhat.com> <4A493029.40601@redhat.com> Mime-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII Cc: Pekka J Enberg , Theodore Tso , Andreas Dilger , David Rientjes , Andrew Morton , Linus Torvalds , arjan@infradead.org, linux-kernel@vger.kernel.org, npiggin@suse.de, linux-ext4@vger.kernel.org To: Eric Sandeen Return-path: In-Reply-To: <4A493029.40601@redhat.com> Sender: linux-kernel-owner@vger.kernel.org List-Id: linux-ext4.vger.kernel.org On Mon, 29 Jun 2009, Eric Sandeen wrote: > > Isnt the problem that the slab allocator did not align something that > > you did not request to be aligned? > > Well, maybe that's all I needed. At the risk of exposing myself to > ridicule, here's the commit: > > 7fcba054373d5dfc43d26e243a5c9b92069972ee > > Was there a better way? No. Good patch. Indeed the right way. Page allocations come from the page allocator not from the slab allocator (yes yes there are still issues with the performance of the page allocator that sometimes dictate the use of the slabs but in general I think this is what is needed).