RvR> On 25 Jul 1999, Benny Amorsen wrote:
>> Would it benefit throughput if it was guaranteed that the sleeping
>> process gets to go forward at the expense of the already running
>> process? It would mean that processes get out of kernel mode
>> quicker.
RvR> Please take a look at my SCHED_IDLE patch:
RvR> http://www.nl.linux.org/~riel/patches/
RvR> It does exactly what you describe, or at least I hope so.
>From my reading of the patch, it only affects processes running with a
priority of SCHED_IDLE. I intended to propose that even SCHED_OTHER
processes could get promoted.
Getting the penalty right so it is neither exploitable nor too harsh
might be hard though. Being too harsh to a SCHED_IDLE process isn't a
problem -- we are already as harsh as possible to them.
Benny
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/