On 10/23/07, Jeff Dike <jdike@addtoit.com> wrote:
On Tue, Oct 23, 2007 at 04:21:03PM -0300, Hrishikesh wrote:
>> Yes, that double negative was a slipup. I did get some numbers out and they
>> look pretty good. I ran upto 5 instances of UML simultaneously and in the
>> tickful case, each instance adds roughly about 100 wakeups per second.

> HZ == 100, so that makes sense. 

>> So
>> after 5 instances, C3 residency comes down to about 95% when all the
>> instances are simply idling. With NO_HZ applied, the change is minimal with
>> C3 residency still approximately 98%. UML is not even among the top three of
>> the bad-list of wakers-up :-)

> Cool.  I'm suprised that 500 wakeups/sec only brings you down < 5%.

Hmm,  powertop shows  500 wakeups  on  part of UML, but the actual number of wakeups for the processor is much  lesser..  Guess there is  some  batching that  is happening.

> So, things are good, except I need to figure out the !NO_HZ busy loop.
>
>                                Jeff
>
> --
> Work email - jdike at linux dot intel dot com

Hrishi