Hi, Christoph, tj,

On 09/11/2015 08:14 AM, Christoph Lameter wrote:

On Thu, 10 Sep 2015, Tejun Heo wrote:

quoted

quoted

Why not just update node_data[]->node_zonelist in the first place?
Also, what's the synchronization rule here?  How are allocators
synchronized against node hot [un]plugs?

Also, shouldn't kmalloc_node() or any public allocator fall back
automatically to a near node w/o GFP_THISNODE?  Why is this failing at
all?  I get that cpu id -> node id mapping changing messes up the
locality but allocations shouldn't fail, right?

Yes. That is the reason we are getting near online node here.

Yes that should occur in the absence of other constraints (mempolicies,
cpusets, cgroups, allocation type). If the constraints do not allow an
allocation then the allocation will fail.

Also: Are the zonelists setup the right way?

zonelist will be rebuilt in __offline_pages() when the zone is not 
populated any more.

Thanks.