On Wed, Jan 19, 2011 at 01:59:01PM -0600, Christoph Lameter wrote:
> On Tue, 18 Jan 2011, David Rientjes wrote:
>
> > It depends on the semantics of NUMA_MISS: if no local nodes are allowed by
> > current's cpuset (a pretty poor cpuset config :), then it seems logical
> > that all allocations would be a miss.
>
> NUMA_MISS is defined as an allocations that did not succeed on the node
> the allocation was "intended" for. So far "intended" as been interpreted
> as allocations that are either intended for the closest numa node or the
> preferred node. One could say that the cpuset config is an "intention".
>
> Andi?
cpusets didn't exist when I designed that. But the idea was that
the kernel has a first choice ("hit") and any other node is a "miss"
that may need investigation. So yes I would consider cpuset config as an
intention too and should be counted as hit/miss.
-Andi
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom policy in Canada: sign http://dissolvethecrtc.ca/
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>