From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from psmtp.com (na3sys010amx153.postini.com [74.125.245.153]) by kanga.kvack.org (Postfix) with SMTP id 0F0536B0068 for ; Fri, 28 Sep 2012 03:46:26 -0400 (EDT) Message-ID: <50654F6E.7090000@cn.fujitsu.com> Date: Fri, 28 Sep 2012 15:19:10 +0800 From: Lai Jiangshan MIME-Version: 1.0 Subject: Re: [PATCH 2/3] slub, hotplug: ignore unrelated node's hot-adding and hot-removing References: <1348728470-5580-1-git-send-email-laijs@cn.fujitsu.com> <1348728470-5580-3-git-send-email-laijs@cn.fujitsu.com> <5064CD7F.1040507@gmail.com> <0000013a09dec004-497e7afa-8c0f-46ff-bf8e-056f7df1ed0b-000000@email.amazonses.com> In-Reply-To: <0000013a09dec004-497e7afa-8c0f-46ff-bf8e-056f7df1ed0b-000000@email.amazonses.com> Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset=UTF-8 Sender: owner-linux-mm@kvack.org List-ID: To: Christoph Cc: KOSAKI Motohiro , "linux-kernel@vger.kernel.org" , Christoph Lameter , Pekka Enberg , Matt Mackall , "linux-mm@kvack.org" HI, Christoph, KOSAKI SLAB always allocates kmem_list3 for all nodes(N_HIGH_MEMORY), also node bug/bad things happens. SLUB always requires kmem_cache_node on the correct node, so these fix is needed. SLAB uses for_each_online_node() to travel nodes and do maintain, and it tolerates kmem_list3 on alien nodes. SLUB uses for_each_node_state(node, N_NORMAL_MEMORY) to travel nodes and do maintain, and it does not tolerate kmem_cache_node on alien nodes. Maybe we need to change SLAB future and let it use for_each_node_state(node, N_NORMAL_MEMORY), But I don't want to change SLAB until I find something bad in SLAB. Thanks, Lai On 09/28/2012 06:35 AM, Christoph wrote: > While you are at it: Could you move the code into slab_common.c so that there is only one version to maintain? > > On Sep 27, 2012, at 17:04, KOSAKI Motohiro wrote: > >> (9/27/12 2:47 AM), Lai Jiangshan wrote: >>> SLUB only fucus on the nodes which has normal memory, so ignore the other >>> node's hot-adding and hot-removing. >>> >>> Aka: if some memroy of a node(which has no onlined memory) is online, >>> but this new memory onlined is not normal memory(HIGH memory example), >>> we should not allocate kmem_cache_node for SLUB. >>> >>> And if the last normal memory is offlined, but the node still has memroy, >>> we should remove kmem_cache_node for that node.(current code delay it when >>> all of the memory is offlined) >>> >>> so we only do something when marg->status_change_nid_normal > 0. >>> marg->status_change_nid is not suitable here. >>> >>> Signed-off-by: Lai Jiangshan >>> --- >>> mm/slub.c | 4 ++-- >>> 1 files changed, 2 insertions(+), 2 deletions(-) >>> >>> diff --git a/mm/slub.c b/mm/slub.c >>> index 2fdd96f..2d78639 100644 >>> --- a/mm/slub.c >>> +++ b/mm/slub.c >>> @@ -3577,7 +3577,7 @@ static void slab_mem_offline_callback(void *arg) >>> struct memory_notify *marg = arg; >>> int offline_node; >>> >>> - offline_node = marg->status_change_nid; >>> + offline_node = marg->status_change_nid_normal; >>> >>> /* >>> * If the node still has available memory. we need kmem_cache_node >>> @@ -3610,7 +3610,7 @@ static int slab_mem_going_online_callback(void *arg) >>> struct kmem_cache_node *n; >>> struct kmem_cache *s; >>> struct memory_notify *marg = arg; >>> - int nid = marg->status_change_nid; >>> + int nid = marg->status_change_nid_normal; >>> int ret = 0; >> >> Looks reasonable. I think slab need similar fix too. >> >> >> > -- 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