Messages in this thread | | | Date | Mon, 31 Jan 2000 20:05:48 +0100 | From | Giuliano Pochini <> | Subject | Re: A different metric for scheduler optimisation |
| |
> In case your application switches rapidly, it is thrashing the cache, which > is crucial for performance with current CPUs. You simply don't want to do > that, ever. You get best performance by _never_ switching
So MSDOS is the world's best OS ? :-))
IMHO if we change the current behaviour of the scheduler to try to minimize cache trashing it will also lead to higher switching latencies and to a coarser distrubution of CPU time. We can get similer results by decreasing HZ.
Bye.
- 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/
| |