Re: Some very thought-provoking ideas about OS architecture.
Mark H. Wood (mwood@iupui.edu)
Wed, 23 Jun 1999 11:56:21 -0500 (EST)
On Mon, 21 Jun 1999, Mikulas Patocka wrote:
> > Here's another: All disk I/O is huge sequential BLTs done as part of
> > checkpoint operations. You can actually use close to 100% of your
> > controller's bandwidth, as opposed to the 30%-50% typical for
> > explicit-I/O operating systems that are doing seeks a lot of the time.
> > This means the maximum I/O throughput the OS can handle effectively
> > more than doubles. With simpler code. You could even afford the time
> > to verify each checkpoint write...
>
> I believe that you get 100% write throughput, but in many systems read
> requests are much more frequent than writes. I'd be insterested how good
> is read performance. Wouldn't your data get too fragmented? If you
> hadn't ported any applications to Eros yet, I wonder if you get good read
> performance in real enviroment.
I think one source of argument here is that (for examples) OLTP, news
spooling, and software development are almost, but not quite, totally
unlike one another in the ways they use storage, so different folks have
different priorities. It's fairly easy to see how EROS is a win for OLTP,
but this may not be so clear for other activities.
--
Mark H. Wood, Lead System Programmer mwood@IUPUI.Edu
Don't Panic!
-
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/