On Wed, 2 Aug 2006 16:35:56 +0200, Vernooy, C.P. - SPLXM
<[EMAIL PROTECTED]> wrote:


>I was wondering if and why CTConly is faster than Dasdonly. We use Ficon
>and ESS and have no I/O queing and 100% cache hit ratio for the control
>file. In the Dasdonly configuration each system has to
>waitfor-read-writeback the control file, in a CTConly each system,
>except the Master, must request-update-sendback the controlfile, in both
>cases on Ficon speed. The Master will of course benefit from owning the
>VCF, but do the clients benefit substantially from CTC mode?

I would think the answer is HARDWARE RESERVE. Hardware reserve is 
still slow (FSVO of slow).   That is why in a GRS STAR (or MIM in CF)
configuration, the old ROTs go out the window for what is okay to
leave as a reserve. 

>
>With "allowable load" I refer to the MII activity rate that will not
>impact performance. I remember we removed SYSIGGV2 from converting to
>global enq when the Dasd control file was still on Escon chached disk,
>because this amount of activity in MIM was noticable in the system
>performance.

You're lucky you didn't end up with a deadlock then.  SYSIGGV2 should
be converted.  SYSVVDS / SYSVTOC should not be.  If you convert one
of them, you must convert both. 

>
>The CA doc seems outdated. It mentions 3088's and Escon but no Ficon and
>the reported cycletimes seem rather high to me for current hardware: 6
>msec cycletime for CTC and XCF, our Dasd cycletime is 3 - 4 msec.  Maybe
>Norman can trigger some updates on this matter?
>

Contact CA.

Cheers,

Mark
--
Mark Zelden
Sr. Software and Systems Architect - z/OS Team Lead
Zurich North America / Farmers Insurance Group
mailto: [EMAIL PROTECTED]
z/OS and OS390 expert at http://searchDataCenter.com/ateExperts/
Mark's MVS Utilities: http://home.flash.net/~mzelden/mvsutil.html

----------------------------------------------------------------------
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