"Mark Zelden" <[EMAIL PROTECTED]> wrote in message
news:<[EMAIL PROTECTED]>...
> On Thu, 20 Dec 2007 08:54:51 +0100, Vernooy, C.P. - SPLXM
> <[EMAIL PROTECTED]> wrote:
> 
> 
> >>
> >> Yes - of course with a shared CF engine.   But with current
hardware
> >(link
> >> technology, z9 engines) the links are once again faster.  YMMV.
> >>
> >> Mark
> >
> >I was at a Parallel Sysplex and Performance training earlier this
month
> >and the teacher told us, that CTCs ourperform CF signalling paths,
> >because of the multiple step (write, notify, read) approach for the
CF
> >path versus the single step (what is written is synchronously read at
> >the other side) approach for the CTC path. And as I said: if the CTCs
> >for our production sysplex are going to perform as they do now in our
> >testsysplex, and I so no reason why not, then they will double the
XCF
> >signalling performance.
> >
> 
> Ahhh... a teacher at a class told you.  Then it must be true!  :-)

Come on, give me some credits, I have been running around in this arena
long enough not trip into this, but he gave me an interesting item to
dig into.

> 
> I understand that (this is the way I heard it explained once) "a
direct pipe is
> quicker than a mail box".   But there are a lot of factors that go
into 
> "YMMV" with this.  Type of links, how many, speed of the CF CPs,
average 
> message size, rate of signaling, etc.  For example, for small messages
(1K)

......

> 
> But what really matters for you is the results in your environment
using
> your hardware.  So I'm not disagreeing that CTCs are faster for _you_.
> 
> BTW, can you say what your HW config is (CF, type of links, FICON EX
or
> FICON EX2, etc.)?
> 
> Mark

2 z9 machines, each with a dedicated ICF for CF and z/OS LPARs, ISC3
links, Ficon ex2 links. 
CF engines for the testsysplex are shared CPs, hence the obvious
improvement.

Of course YMMV and I will wait for the production figures, but I have
good expectations as I said before.

Kees.
**********************************************************************
For information, services and offers, please visit our web site:
http://www.klm.com. This e-mail and any attachment may contain
confidential and privileged material intended for the addressee
only. If you are not the addressee, you are notified that no part
of the e-mail or any attachment may be disclosed, copied or
distributed, and that any other action related to this e-mail or
attachment is strictly prohibited, and may be unlawful. If you have
received this e-mail by error, please notify the sender immediately
by return e-mail, and delete this message. 

Koninklijke Luchtvaart Maatschappij NV (KLM), its subsidiaries
and/or its employees shall not be liable for the incorrect or
incomplete transmission of this e-mail or any attachments, nor
responsible for any delay in receipt.
Koninklijke Luchtvaart Maatschappij N.V. (also known as KLM Royal
Dutch Airlines) is registered in Amstelveen, The Netherlands, with
registered number 33014286 
**********************************************************************

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Reply via email to