From mboxrd@z Thu Jan 1 00:00:00 1970 From: Glauber Costa Subject: Re: [PATCH] slub: correctly bootstrap boot caches Date: Fri, 22 Feb 2013 20:11:56 +0400 Message-ID: <512798CC.2080501@parallels.com> References: <1361529030-17462-1-git-send-email-glommer@parallels.com> <0000013d026b4e5f-1b3deecb-7e37-4476-a27b-3a7db8c1f0a8-000000@email.amazonses.com> <51278A12.4000504@parallels.com> <0000013d028eec8e-012456de-9b98-4bcb-9427-2fbee58ecc74-000000@email.amazonses.com> <5127928A.20000@parallels.com> <0000013d02ab8230-de441d64-395f-4c87-89e7-3f2cd2209680-000000@email.amazonses.com> Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Return-path: In-Reply-To: <0000013d02ab8230-de441d64-395f-4c87-89e7-3f2cd2209680-000000-p/GC64/jrecnJqMo6gzdpkEOCMrvLtNR@public.gmane.org> Sender: cgroups-owner-u79uwXL29TY76Z2rM5mHXA@public.gmane.org List-ID: Content-Type: text/plain; charset="us-ascii" To: Christoph Lameter Cc: linux-mm-Bw31MaZKKs3YtjvyW6yDsg@public.gmane.org, cgroups-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, linux-kernel-u79uwXL29TY76Z2rM5mHXA@public.gmane.org, Andrew Morton , Tejun Heo , Pekka Enberg , Kamezawa Hiroyuki On 02/22/2013 08:10 PM, Christoph Lameter wrote: > kmem_cache_node creation runs before PARTIAL and kmem_cache runs > after. So there would be 2 kmem_cache_node structures allocated. Ok so > that would use cpu slabs and therefore remove pages from the partial list. > Pushing that back using the flushing should fix this. But I thought there > was already code that went through the cpu slabs to address this? not in bootstrap(), which is quite primitive. (and should remain so) From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx174.postini.com [74.125.245.174]) by kanga.kvack.org (Postfix) with SMTP id 03DFE6B0008 for ; Fri, 22 Feb 2013 11:11:32 -0500 (EST) Message-ID: <512798CC.2080501@parallels.com> Date: Fri, 22 Feb 2013 20:11:56 +0400 From: Glauber Costa MIME-Version: 1.0 Subject: Re: [PATCH] slub: correctly bootstrap boot caches References: <1361529030-17462-1-git-send-email-glommer@parallels.com> <0000013d026b4e5f-1b3deecb-7e37-4476-a27b-3a7db8c1f0a8-000000@email.amazonses.com> <51278A12.4000504@parallels.com> <0000013d028eec8e-012456de-9b98-4bcb-9427-2fbee58ecc74-000000@email.amazonses.com> <5127928A.20000@parallels.com> <0000013d02ab8230-de441d64-395f-4c87-89e7-3f2cd2209680-000000@email.amazonses.com> In-Reply-To: <0000013d02ab8230-de441d64-395f-4c87-89e7-3f2cd2209680-000000@email.amazonses.com> Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit Sender: owner-linux-mm@kvack.org List-ID: To: Christoph Lameter Cc: linux-mm@kvack.org, cgroups@vger.kernel.org, linux-kernel@vger.kernel.org, Andrew Morton , Tejun Heo , Pekka Enberg , Kamezawa Hiroyuki On 02/22/2013 08:10 PM, Christoph Lameter wrote: > kmem_cache_node creation runs before PARTIAL and kmem_cache runs > after. So there would be 2 kmem_cache_node structures allocated. Ok so > that would use cpu slabs and therefore remove pages from the partial list. > Pushing that back using the flushing should fix this. But I thought there > was already code that went through the cpu slabs to address this? not in bootstrap(), which is quite primitive. (and should remain so) -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757934Ab3BVQLh (ORCPT ); Fri, 22 Feb 2013 11:11:37 -0500 Received: from mx0.parallels.com ([199.115.104.20]:36609 "EHLO mx0.parallels.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1757775Ab3BVQLd (ORCPT ); Fri, 22 Feb 2013 11:11:33 -0500 Message-ID: <512798CC.2080501@parallels.com> Date: Fri, 22 Feb 2013 20:11:56 +0400 From: Glauber Costa User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:17.0) Gecko/20130110 Thunderbird/17.0.2 MIME-Version: 1.0 To: Christoph Lameter CC: , , , Andrew Morton , Tejun Heo , Pekka Enberg , Kamezawa Hiroyuki Subject: Re: [PATCH] slub: correctly bootstrap boot caches References: <1361529030-17462-1-git-send-email-glommer@parallels.com> <0000013d026b4e5f-1b3deecb-7e37-4476-a27b-3a7db8c1f0a8-000000@email.amazonses.com> <51278A12.4000504@parallels.com> <0000013d028eec8e-012456de-9b98-4bcb-9427-2fbee58ecc74-000000@email.amazonses.com> <5127928A.20000@parallels.com> <0000013d02ab8230-de441d64-395f-4c87-89e7-3f2cd2209680-000000@email.amazonses.com> In-Reply-To: <0000013d02ab8230-de441d64-395f-4c87-89e7-3f2cd2209680-000000@email.amazonses.com> Content-Type: text/plain; charset="ISO-8859-1" Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 02/22/2013 08:10 PM, Christoph Lameter wrote: > kmem_cache_node creation runs before PARTIAL and kmem_cache runs > after. So there would be 2 kmem_cache_node structures allocated. Ok so > that would use cpu slabs and therefore remove pages from the partial list. > Pushing that back using the flushing should fix this. But I thought there > was already code that went through the cpu slabs to address this? not in bootstrap(), which is quite primitive. (and should remain so)