Re: [patch] CFS scheduler, v3

[Christoph Lameter <clameter@sgi.com>]

On Tue, 24 Apr 2007, Siddha, Suresh B wrote:

> > .5% is usually in the noise ratio. Are you consistently seeing an 
> > improvement or is that sporadic?
> 
> No. This is consistent. I am waiting for the perf data on a much much bigger
> NUMA box.
> 
> Anyhow, this is a straight forward optimization and needs to be done. Do you
> have any specific concerns?

Yes there should not be contention on per cpu data in principle. The 
point of per cpu data is for the cpu to have access to contention free 
cachelines.

If the data is contented then it should be moved out of per cpu data and properly 
placed to minimize contention. Otherwise we will get into cacheline 
aliases (__read_mostly in per cpu??) etc etc in the per cpu areas.

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/