Re: Elevator vs first-come-first-served
kwrohrer@ce.mediaone.net
Tue, 17 Nov 1998 12:24:27 -0600 (EST)
And lo, Robert Minichino saith unto me:
>
> In
> benchmarks on Solaris with raw disk devices and a benchmarking program that
> simulated different ordering algorithms, throughput was highest to the disks
> (behind a cached controller with 64MB) when first-come first-served was used
> to service the randomly generated requests. I can rewrite and re-run the
> benchmark if anyone desires.
>
But what did the load look like? Poisson distributions of requests for
random block numbers? A VM pig, a video recording app, and a teeming
horde of Oracle requests are going to look a lot different from one
another... Do we have any actual traces anywhere of what a couple
hundred "normal" users do to a system?
Keith
--
"The avalanche has already started; |Linux: http://www.linuxhq.com |"Zooty,
it is too late for the pebbles to |KDE: http://www.kde.org | zoot
vote." Kosh, "Believers", Babylon 5 |Keith: kwrohrer@enteract.com | zoot!"
www.midwinter.com/lurk/lurker.html |http://www.enteract.com/~kwrohrer | --Rebo
-
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/