Re: [RFC PATCH 2/3] topology: support node_numa_mem() for determining the fallback node

[David Rientjes <rientjes@google.com>]

On Mon, 21 Jul 2014, Nishanth Aravamudan wrote:

> Sorry for bringing up this old thread again, but I had a question for
> you, David. node_to_mem_node(), which does seem like a useful API,
> doesn't seem like it can just node_distance() solely, right? Because
> that just tells us the relative cost (or so I think about it) of using
> resources from that node. But we also need to know if that node itself
> has memory, etc. So using the zonelists is required no matter what? And
> upon memory hotplug (or unplug), the topology can change in a way that
> affects things, so node online time isn't right either?
> 

I think there's two use cases of interest:

 - allocating from a memoryless node where numa_node_id() is memoryless, 
   and

 - using node_to_mem_node() for a possibly-memoryless node for kmalloc().

I believe the first should have its own node_zonelist[0], whether it's 
memoryless or not, that points to a list of zones that start with those 
with the smallest distance.  I think its own node_zonelist[1], for 
__GFP_THISNODE allocations, should point to the node with present memory 
that has the smallest distance.

For sure node_zonelist[0] cannot be NULL since things like 
first_online_pgdat() would break and it should be unnecessary to do 
node_to_mem_node() for all allocations when CONFIG_HAVE_MEMORYLESS_NODES 
since the zonelists should already be defined properly.  All nodes, 
regardless of whether they have memory or not, should probably end up 
having a struct pglist_data unless there's a reason for another level of 
indirection.

--
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: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>