On Monday 27 February 2006 16:23, Arjan van de Ven wrote:
2) In the "processor/processes" group, 7 tests changed behavior, and the
average of these changes was a performance increase by 10% (!!). The
exception was the signal handling test, which decreased by 6%. This
actually made me feel good, since the original function list was based
on a profile run that didn't do signals much if at all.
How often did you rerun lmbench each time?
In my experience the numbers
are somewhat unstable. Still looks encouraging.