Re: [RFC] NUMA : could we introduce virt_to_nid() ?

From: Christoph Lameter
Date: Fri Mar 23 2007 - 13:20:17 EST


On Fri, 23 Mar 2007, Eric Dumazet wrote:

> Sorry ? page structs are not in cpu cache at all.

They are if they are in any way handled by the VM.

> You carefully commented your alloc() function saying it is touching two cache lines.
> But you omited to say that free() function needs 3 cache lines if CONFIG_NUMA

Yes it needs the third cacheline to check the node of the page in the NUMA
case.

> For SLAB use, page struct is needed because we use lru.{next|prev} to
> store slab/cachep pointers, but for a pure page allocator, unless I
> misread your patch, we dont need it, if virt_to_nid() can do its job
> without it.

The page allocator is only handling page_structs.

-
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/