Re: [PATCH 2/3] slub, hotplug: ignore unrelated node's hot-addingand hot-removing

From: Lai Jiangshan
Date: Fri Sep 28 2012 - 03:46:17 EST


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 <kosaki.motohiro@xxxxxxxxx> 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 <laijs@xxxxxxxxxxxxxx>
>>> ---
>>> 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 from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/