Re: big iron mainframe vs. x86 servers
- From: rkuebbin@xxxxxxxx (Kirk Talman)
- Date: 20 Oct 2009 12:55:20 -0700
I asked because the pretty slide show linked to by the original post I
replied to used that number (1500) on the 13th and last slide with no
indication of scale factor or context.
After 48 yrs in IT I have an appreciation for the issues raised by the
replies, both explicit and implicit. I was wondering from the practical
point of view. Where is the cross-over point where one considers z10 vs
squatty box? on power? on space? on software licences? admin bodies? is
the issue to complicated without doing a full tca/tco?
This was on my mind because I have the misfortune to have inherited
support of a mainframe application connected to a squatty box using custom
code and a token ring conenction to the mainframe. every time it burps i
get indigestion. replacing it means using smtp to replace telephony --
swapping one poisonous snake for another breed.
As an aside, what is a good abbreviation for mainframe than m_f? I would
like to reserve that for M$, Office and InfoPath at the moment.
IBM Mainframe Discussion List <IBM-MAIN@xxxxxxxxxxx> wrote on 10/20/2009
02:54:30 PM:
-----Original Message-----
[mailto:IBM-MAIN@xxxxxxxxxxx] On Behalf Of Hal Merritt
Interesting. I'd think the number could be less than one.
[mailto:IBM-MAIN@xxxxxxxxxxx] On Behalf Of Chase, John
-----Original Message-----
From: IBM Mainframe Discussion List On Behalf Of Kirk Talman
How many Mainframe engines = 1500 x86 boxes?
"It depends". Could be as few as one.
In this case, I would bet it depends on what those x86 servers are
doing. If they are a Beowulf supercomputer cluster, then the z10 is
NOT going to beat it. But if they are Web servers? Or even
application servers?
Speaking of such. The z10 is said, by IBM, to be the "fastest"
(clock time) CISC processor. So, does that mean that a single IFL
processor could outperform any single x86 (Xeon?) single threaded
processor around for something which is CPU intensive, such as
numeric computation? To be "fair", let us assume that this
computation is being done in Java by using the identical .class
file. I know that isn't "fair" since the JVMs are not identical. But
it is about as fair as I can think of. Or perhaps the same C code
compiled and run on Linux using the same version of GCC.
John McKown
-----------------------------------------
The information contained in this communication (including any
attachments hereto) is confidential and is intended solely for the
personal and confidential use of the individual or entity to whom
it is addressed. If the reader of this message is not the intended
recipient or an agent responsible for delivering it to the intended
recipient, you are hereby notified that you have received this
communication in error and that any review, dissemination, copying,
or unauthorized use of this information, or the taking of any
action in reliance on the contents of this information is strictly
prohibited. If you have received this communication in error,
please notify us immediately by e-mail, and delete the original
message. Thank you
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to listserv@xxxxxxxxxxx with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
.
- Follow-Ups:
- Re: big iron mainframe vs. x86 servers
- From: Clark Morris
- Re: big iron mainframe vs. x86 servers
- References:
- Re: big iron mainframe vs. x86 servers
- From: McKown, John
- Re: big iron mainframe vs. x86 servers
- Prev by Date: Re: Fwd: Is There Such a Thing as a Mainframe Monopoly?
- Next by Date: Re: Fwd: Is There Such a Thing as a Mainframe Monopoly?
- Previous by thread: Re: big iron mainframe vs. x86 servers
- Next by thread: Re: big iron mainframe vs. x86 servers
- Index(es):
Relevant Pages
|
