John Kim wrote:
Ed,
I wonder have you turned on 'HIPERDISPATCH=YES' and what the performance
looks like with this option?
Funny you mention that. Yesterday, I logged on and noticed the following:
IEAVEH071E HiperDispatch is expected to be enabled but it is disabled
So, I added HIPERDISPATCH=YES to IEAOPTxx. Once I issued T OPT=xx, the
system(s) responded with:
N 0040000 MVSA0 08342 15:29:07.45 00000090 IRA860I
HIPERDISPATCH MODE IS NOW ACTIVE
Book affinity is obviously not important for a single-book machines. Of
course, so-called "short" CPs can exist on most n-way machines. Ours is
only a 4-way.
We'll try some empirical testing over the next few weeks to see if we
notice any change with HiperDispatch enabled or disabled.
We are also going to have a z10-BC soon, but haven't decided yet to turn
on.
Because lots of pros and cons out there. We have 3 LPARs; one production
and two tiny tests.
What kind of cons? Due to implementation "bugs" that have been found? Or
something more fundamental?
--
Edward E Jaffe
Phoenix Software International, Inc
5200 W Century Blvd, Suite 800
Los Angeles, CA 90045
310-338-0400 x318
[EMAIL PROTECTED]
http://www.phoenixsoftware.com/
----------------------------------------------------------------------
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
