The first statement was a bit in excess of the facts. The problem
arises when the 250 processes are rescheduling themselves frequently.
Your cpu hogs use their entire timeslice, and so are pretty well
behaved. If you got a _lot_ of interactive processing going on, such as
the test program that has N processes banging on the same pipe, your
system would burn down even worse with all your CPU hogs.
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to firstname.lastname@example.org
Please read the FAQ at http://www.tux.org/lkml/