Re: On migrate_disable() and latencies

On Fri, 2011-07-22 at 12:49 +0200, Peter Zijlstra wrote:

quoted

The scenario is on where you stack N migrate-disable tasks on a run
queue (necessarily of increasing priority). Doing this requires all cpus
in the system to be as busy, for otherwise the task would simply be
moved to another cpu.

This implies it requires at least nr-cpus^2 tasks to pull this off. 

OK, scrap that, 2*nr-cpus is enough.