Re: It is almost certain now, INTEL will have 64bit x86 !!

From: Rick Jones (foo_at_bar.baz.invalid)
Date: 02/27/04 

Date: Fri, 27 Feb 2004 18:46:49 GMT

Andrew Harrison SUNUK Consultancy <Andrew_No.Harrison_No@nospamn.sun.com> wrote:
> Rick Jones wrote:
>> What about the "MaxCPU" stuff - if I've read the stuff I've been
>> able to find thusfar correctly, those go into IO slots. Doesn't
>> that mean that if one wants Maximum CPU count on the 15K one has to
>> give-up I/O?

> That allows you to have more than 72 CPU's in a F15K if you
> want to lose I/O slots. You seem to have missed the difference
> between this an 8400 which was that you had CPU boards, memory
> boards and I/O boards. If you wanted the maximum number of
> CPU's you could not have the maximum amount of memory etc
> or I/O

And in the 15K if you want the maximum number of CPUs, you cannot have
the maximum ammount of I/O, and you cannot have the maximum quantity
of memory without the maximum (near? I didn't look far enough to see
if the MaxCPU boards had memory) number of CPUs.

> In the F25K the maxcpu option no longer exists.

You need to get in touch with the website maintainers and get them to
update the pages. Their cut and paste job from prevoius pages has
left MaxCPU references in place for the 25K.

>>>Of course but then as you would also know Sun has demonstrated
>>>12.5 GB/s on a table scan from an Oracle DBMS sustained through
>>>the older I/O subsystem for the F15K what can you do
>>
>>
>> The E15K specs *** on www.sun.com claims the IO is "up to 21.6
>> GB/s sustained"

> As it is and as you will also notice this is not the number of
> PCI slots multipled by indevidual bandwidth of the slots.

No, it was some marketroid taking 80% of that figure, and _still_
getting it wrong because they took the PCI slot count and not the PCI
bus count, and the sum of the PCI bus count is 13.5 GB/s.

Perhaps I make a math mistake somewhere, but can you tell me how it is
possible to have up to 21.5 GB/s of sustained I/O rate when the peak
marketing bandwidth of the I/O busses on the system aren't much more
than 1/2 that?

> So what sort of I/O rate can you sustain through an Oracle DBMS on a
> SuperDome ?

No idea. I suppose that if someone were to poke around various
benchmark disclsoures some guesstimates of I/O rates for _those_
workloads could be made. To my knowledge, HP haven't done "just" an
"Oracle table scan" and published numbers. BTW, I would be curious to
know more of the details of that table scan, if you would please
provide a URL with the details that would be great.

> You seem to have spent an inordinate ammount of time not answering
> the question, the fruits of which I have cut

Which question was that? Superdome I/O rate wasn't queried in your
retort to my asserion that there were similar (I don't think I said
identical) tradeoffs in high-end SunFire systems.

> Again this is incorrect. The E25K and E20K do not have any tradeoffs

The "if you want the RAM you have to have the CPUs" tradeoff seems to
remain from the 15K.

rick jones 

-- 
denial, anger, bargaining, depression, acceptance, rebirth...
                                     where do you want to be today?
these opinions are mine, all mine; HP might not want them anyway... :)
feel free to post, OR email to raj in cup.hp.com  but NOT BOTH...
Quantcast