Re: [patch] CFS scheduler, v3

[William Lee Irwin III <wli@holomorphy.com>]

Fri, Apr 20, 2007 at 12:24:17PM -0700, Christoph Lameter wrote:
>>> False sharing for a per cpu data structure? Are we updating that 
>>> structure from other processors?

On Fri, 20 Apr 2007, William Lee Irwin III wrote:
>> Primarily in the load balancer, but also in wakeups.

On Fri, Apr 20, 2007 at 12:33:13PM -0700, Christoph Lameter wrote:
> That is fairly rare I think. What other variables that are also writtten 
> frequently would cause false sharing?

I wrote that backward, sorry. Cross-CPU wakeups' frequency depend
heavily on the workload. Probably the only other case I can think of
is io_schedule() but that's not really significant.

I'm not really convinced it's all that worthwhile of an optimization,
essentially for the same reasons as you, but presumably there's a
benchmark result somewhere that says it matters. I've just not seen it.


-- wli