Re: scheduler interactivity: timeslice calculation seem wrong
From: Eric St-Laurent
Date: Tue Aug 19 2003 - 00:08:22 EST
> There's a scheduler implementation dating pre 1970 that does this and I am led
> to believe someone is working on an implementation for perhaps 2.7
The first implementation is in 1962 with CTSS if i remember correctly.
Multics initially had something like that too.
http://www.multicians.org/mult-sched.html
Anyway that's pretty standard CS stuff. Multi-level Queues with
feedback, exponentially longer timeslices with lower priority.
I was reading this recently, that's why i wondered why linux calculate
timeslice "inversed" versus what is proposed in theory.
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/