On Fri, Mar 13, 2009 at 09:38, André Braga <meianoite@xxxxxxxxx> wrote: > I've considered a "pin this CPU to this thread" (as opposed to the usual > other-way-around) option to the affinity settings, but it seems that Axel > didn't like this and wanted the scheduler to be more automagical in this > regard. The default behaviour WILL be to run a thread on the same processor > it ran [LAST], to spawn new treads on the lesser loaded processors, and to > consider load delta between the various processors and topology (buses, > shared caches, performance score (for the AMP case)) as well when balancing > load. Of course I meant *last* and not *less*; and this time it was the spelling corrector playing tricks on me. A.