Hi,
This is the HSA section from our most recent Microcode Letter.
===================================================================
HSA
Account teams and Customers should be aware that changes to the system
MAY affect the HSA size. This means configuration changes to:
Driver (MicroCode level, # of MCLs, Enabled Functions)
Model (PU/CP, SAPs, ICF, IFL)
LPAR (# of partitions, Image CP/storage sizes, enabled functions)
Channel (IOCDS, # of channels/STI's, # of LCSS's, Chan. types, cages
added)
Memory (Size of card, Type of card, # of cards)
Profiles (Enabled functions selected in activation profiles)
Debug (Tracing - normally seen while in PEMODE)
Note: Refer to the PR/SM Planning Guide SB10-7036-00 for more
information. Reference Document SA22-1032-00a for more information on
zSeries 990 System Overview for HSA specifics (Chapter 3 - Memory). This
is true for all Server Group CMOS based processors today and in the
future.
Note: The HSA Estimator tool should be run do determine accurate HSA
sizes.
Note: Enhanced Driver Maintenance to transition from Driver 63J to
Driver 67L will not change HSA size.
========================================================================
==
My consideration is that HSA has grown significantly because of added
functionality and that is the cost of doing zbusiness. I find a
gigabyte or two of memory for HSA instead of 300M reasonable if IBM
continues to improve reliability and serviceability (especially
concurrent service) and add new feature and function. It has become
increasingly difficult to get standalone time for a Power On Reset as
the processors get larger and our business requirements for availability
increase. We cannot very well advocate with IBM to eliminate the need
to POR and then complain that HSA has grown to support all this dynamic
function.
For comparison some HSA sizes here
1024MB Ext CF 2086
2240MB 2094's
Consider that your 2094 will do a whole lot more than your 9672 ever
could. Small matter of programming of course but lots of the new
function is not small or simple.
Maybe if IBM renamed it people would mind less. Perhaps
CFFHASRADHCSA.... Customer Focused Functionality High Availability Super
Reliability Allows Dynamic Hardware Changes Storage Area?
Best Regards,
Sam Knutson, GEICO
System z Performance and Availability Management
mailto:[EMAIL PROTECTED]
(office) 301.986.3574
"Think big, act bold, start simple, grow fast..."
-----Original Message-----
From: IBM Mainframe Discussion List [mailto:[EMAIL PROTECTED] On
Behalf Of Pinnacle
Sent: Saturday, August 04, 2007 1:15 PM
To: IBM-MAIN@BAMA.UA.EDU
Subject: Why is HSA so ridiculous on a z9 at z/OS V1R8?
The HSA on our 9672 running OS/390 V2R10 is a whopping 64M, compared to
1344M on the z9 at z/OS V1R8. We eliminated the DYNAMIC attribute on
1024
DASD devices, and that dropped HSA to 1024M. WTF is HSA so ridiculously
large on the current hardware/software, for essentially the same I/O
config?
Regards,
Tom Conley
====================
This email/fax message is for the sole use of the intended
recipient(s) and may contain confidential and privileged information.
Any unauthorized review, use, disclosure or distribution of this
email/fax is prohibited. If you are not the intended recipient, please
destroy all paper and electronic copies of the original message.
----------------------------------------------------------------------
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
