Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932894AbZFLIos (ORCPT ); Fri, 12 Jun 2009 04:44:48 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1755581AbZFLIok (ORCPT ); Fri, 12 Jun 2009 04:44:40 -0400 Received: from gate.crashing.org ([63.228.1.57]:42647 "EHLO gate.crashing.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753561AbZFLIoj (ORCPT ); Fri, 12 Jun 2009 04:44:39 -0400 Subject: Re: slab: setup allocators earlier in the boot sequence From: Benjamin Herrenschmidt To: Nick Piggin Cc: Pekka Enberg , Linus Torvalds , Linux Kernel list , linux-mm , mingo@elte.hu, cl@linux-foundation.org, akpm@linux-foundation.org In-Reply-To: <20090612080236.GB24044@wotan.suse.de> References: <200906111959.n5BJxFj9021205@hera.kernel.org> <1244770230.7172.4.camel@pasglop> <1244779009.7172.52.camel@pasglop> <1244780756.7172.58.camel@pasglop> <1244783235.7172.61.camel@pasglop> <1244792079.7172.74.camel@pasglop> <1244792745.30512.13.camel@penberg-laptop> <20090612075427.GA24044@wotan.suse.de> <1244793592.30512.17.camel@penberg-laptop> <20090612080236.GB24044@wotan.suse.de> Content-Type: text/plain Date: Fri, 12 Jun 2009 18:44:19 +1000 Message-Id: <1244796259.7172.86.camel@pasglop> Mime-Version: 1.0 X-Mailer: Evolution 2.26.1 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 992 Lines: 24 On Fri, 2009-06-12 at 10:02 +0200, Nick Piggin wrote: > Fair enough, but this can be done right down in the synchronous > reclaim path in the page allocator. This will catch more cases > of code using the page allocator directly, and should be not > as hot as the slab allocator. > Yes except that slab has explicit local_irq_enable() when __GFP_WAIT is set so we also need to deal with that for the boot case. But again, this is a lot less of an issue if you use my proposed patch instead which just applies a mask of "forbidden" bits rather than a conditional branch based on the system state. It will also allow for more fine grained masking out if we decide, for example, that at some stage we want to mask out GFP_IO etc... Cheers, Ben. -- 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/