[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

[Xen-devel] Re: next->vcpu_dirty_cpumask checking at the top of context_switch()

On 17/04/2009 14:58, "Jan Beulich" <jbeulich@xxxxxxxxxx> wrote:

>>>> Keir Fraser <keir.fraser@xxxxxxxxxxxxx> 04/16/09 6:00 PM >>>
>> How big NR_CPUS are we talking about? Is the overhead measurable, or is this
>> a premature micro-optimisation?
> We're shipping Xen in SLE11 with NR_CPUS=255, and I'm convinced we'll be asked
> to up this further in the service packs.
> Also, micro-optimization reads for me like I was aiming at a performance
> issue, but the goal really just is to get the use of stack space down (and in
> particular, make it as independent as possible from configuration settings).

Well, I'm not against it, at least if it's a reasonably straightforward
patch. Any untangling of cpus_empty() logic should be a separate patch
though. And that should mean that the patch to convert from pass-by-value to
pass-by-pointer is nice and trivial.

 -- Keir

Xen-devel mailing list



Lists.xenproject.org is hosted with RackSpace, monitoring our
servers 24x7x365 and backed by RackSpace's Fanatical Support®.