[Info-vax] The Future of Server Hardware?
Fritz Wuehler
fritz at spamexpire-201210.rodent.frell.theremailer.net
Wed Oct 10 21:42:47 EDT 2012
Stephen Hoffman <seaohveh at hoffmanlabs.invalid> wrote:
> On 2012-10-02 16:32:12 +0000, JF Mezei said:
>
> > Since I am good at asking stupid questions...
> >
> >
> > Assuming, for the sake of discussion that todays's x86 , Power and the
> > architecture that started as the 360 have equal CPU horsepower.
They don't. IBM announced 5.5 GHz clocks on their latest box. And that's
just the clocks. You can't judge horsepower by clock speed. There's no way
to compare things directly, especially CICS vs. RISC, etc. x86 is a CISC
over RISC design, POWER is RISC (don't know if there's any microcode) and
System Z is a hybrid design sometimes called "millicoded" which is many
instructions are native (not microcoded) and others are microcoded.
Stephen's post is good/accurate. The other thing that makes mainframes
"silly fast" is the hardware and software were designed for each other, by
one company that does it all, including fabbing their own chips. No finger
pointing, no portability, no problem.
> Mainframes typically excel at providing high bandwidth and low latency
> into and out of the processors, and not strictly at raw CPU speed.
> Though they're typically no slouches there, either.
>
> Mainframes are centrally designed for error detection and correction;
> what HP calls RAS.
>
> And with the IBM boxes I've worked with, the I/O channels are gonzo fast,
> too.
Yep!
> The older IBM mainframe boxes I've used were painful to set up - you
> had to specify everything, and in detail - but once you had the jobs
> configured, even the small mainframes were silly-fast. Batch was
> screaming fast. (Why "older"? I haven't had to configure DASD and the
> other related tasks in many years, and I suspect that IBM has
> substantially improved here.)
You still need to know what you're doing to configure a mainframe but a lot
of the detail has gone away, compared to yesteryear.
> Few folks will choose to run large-scale web servers and web sites on
> mainframes for that matter, though it is technically possible. Other
> than those folks with very specific requirments or that have a
> willingness to spend far more money on iron than the average, that is.
> There are other (and usually more cost-effective) ways to serve (for
> instance) web requests, though you might well find a mainframe as a
> back-end somewhere.
A webserver is not a demanding application and it would be like delivering
the mail in a Lamborghini, not talking about the reliability aspect since I
never owned one of those! Like Stephen said, nobody does that. There is
webserver support in the OS and program products but nobody runs that as the
main application on a mainframe. They do quite a bit of other types of
online stuff like airline reservation systems and banking ATMs though.
> Mainframes are good for some jobs. Roadrunner or Jaguar at other jobs.
> Racks of x86
like burning up data centers! ;-)
> or ARM boxes at others. And yes, Itanium has its place here, too.
Good post!
More information about the Info-vax
mailing list