Re: scheduler interactivity: timeslice calculation seem wrong

[Eric St-Laurent]

> 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/