Re: reschedule_idle changes in ac kernels

[Mike Kravetz]

I ran the VolanoMark and TPC-H benchmarks on an 8 CPU system
to observe the differences when changing the value at which
preemptions are triggered.  I used the 2.4.5 kernel as a basis
and only changed the 'max_prio = ' statement in reschedule_idle()
to change the preemption trigger threshold.  In the 2.4.5 kernel
the value of max_prio is set to 1.

The results:

In VolanoMark, changing the preemption trigger from 1 to 0
resulted in a 4% drop in throughput.

In TPC-H there was virtually no difference when going from
1 to 0.  If anything, the results were slightly better with
0 as a threshold value as opposed to 1.

My guess is that the threshold value was changed from 0 to
1 in the 2.4 kernel for better performance with some workload.
Anyone remember what that workload was/is?

-- 
Mike Kravetz                                 [e-mail]
IBM Linux Technology Center