Re: nice and hyperthreading on atom

Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]
From: Peter Zijlstra
Date: Saturday, September 6, 2008 - 9:31 am

On Sat, 2008-09-06 at 16:43 +0100, Phil Endecott wrote:

Assuming the hardware makes each 'virtual' cpu get a similar share of
the hardware resources, there is nothing the operating system can do.

The OS just sees two cpus, and its impossible to schedule two tasks of
different weight on two cpus so that execution time is fair and work is
conserved - this is called an infeasible weight distribution.

So unless the Atom has some interface to influence how the resources are
distributed between the execution contexts (for which Linux currently
lacks any and all support) there is nothing we can do.


--
Previous message: [thread] [date] [author]
Next message: [thread] [date] [author]

Messages in current thread:
nice and hyperthreading on atom, Phil Endecott, (Sat Sep 6, 8:43 am)
Re: nice and hyperthreading on atom, Peter Zijlstra, (Sat Sep 6, 9:31 am)
Re: nice and hyperthreading on atom, Arjan van de Ven, (Sat Sep 6, 9:42 am)
Re: nice and hyperthreading on atom, Phil Endecott, (Sat Sep 6, 11:24 am)
Re: nice and hyperthreading on atom, Ulrich Drepper, (Sat Sep 6, 11:30 am)
Re: nice and hyperthreading on atom, Peter Zijlstra, (Sun Sep 7, 2:34 am)
Re: nice and hyperthreading on atom, Phil Endecott, (Sun Sep 7, 6:58 am)
Re: nice and hyperthreading on atom, Bill Davidsen, (Sun Sep 7, 6:09 pm)