From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751623Ab1GTNPM (ORCPT ); Wed, 20 Jul 2011 09:15:12 -0400 Received: from mail-ew0-f46.google.com ([209.85.215.46]:56740 "EHLO mail-ew0-f46.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750979Ab1GTNPK (ORCPT ); Wed, 20 Jul 2011 09:15:10 -0400 Date: Wed, 20 Jul 2011 16:14:51 +0300 (EEST) From: Pekka Enberg X-X-Sender: penberg@tiger To: Konstantin Khlebnikov cc: Andrew Morton , linux-mm@kvack.org, Christoph Lameter , linux-kernel@vger.kernel.org, Matt Mackall , mgorman@suse.de Subject: Re: [PATCH] mm-slab: allocate kmem_cache with __GFP_REPEAT In-Reply-To: <20110720121612.28888.38970.stgit@localhost6> Message-ID: References: <20110720121612.28888.38970.stgit@localhost6> User-Agent: Alpine 2.00 (DEB 1167 2008-08-23) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Wed, 20 Jul 2011, Konstantin Khlebnikov wrote: > Order of sizeof(struct kmem_cache) can be bigger than PAGE_ALLOC_COSTLY_ORDER, > thus there is a good chance of unsuccessful allocation. > With __GFP_REPEAT buddy-allocator will reclaim/compact memory more aggressively. > > Signed-off-by: Konstantin Khlebnikov > --- > mm/slab.c | 2 +- > 1 files changed, 1 insertions(+), 1 deletions(-) > > diff --git a/mm/slab.c b/mm/slab.c > index d96e223..53bddc8 100644 > --- a/mm/slab.c > +++ b/mm/slab.c > @@ -2304,7 +2304,7 @@ kmem_cache_create (const char *name, size_t size, size_t align, > gfp = GFP_NOWAIT; > > /* Get cache's description obj. */ > - cachep = kmem_cache_zalloc(&cache_cache, gfp); > + cachep = kmem_cache_zalloc(&cache_cache, gfp | __GFP_REPEAT); > if (!cachep) > goto oops; The changelog isn't that convincing, really. This is kmem_cache_create() so I'm surprised we'd ever get NULL here in practice. Does this fix some problem you're seeing? If this is really an issue, I'd blame the page allocator as GFP_KERNEL should just work. Pekka