On Wed, 13 Aug 2014 14:06:12 -0400 zMan <[email protected]> wrote:
:>Given up to 30% variability run over run with z/OS, I wouldn't find 1% :>statistically significant... It was repeatable. :>On Wed, Aug 13, 2014 at 10:05 AM, Binyamin Dissen < :>[email protected]> wrote: :> :>> On Wed, 13 Aug 2014 13:45:14 +0000 DASDBILL2 <[email protected]> :>> wrote: :>> :>> :>How much is "slightly more"? Ten to the minus 2 power of one percent? :>> Ten to the minus 5 power of one percent? Perhaps you could display the raw :>> numbers before and after. :>> :>> The section of code which does other stuff than just examining this storage :>> took about 1% more cpu. I have not tried a more specific test case. The :>> CPU is :>> 1% less when a key8 subpool is used. :>> :>> :>----- Original Message ----- :>> :> :>> :>From: "Binyamin Dissen" <[email protected]> :>> :>To: [email protected] :>> :>Sent: Wednesday, August 13, 2014 5:16:17 AM :>> :>Subject: Is there a CPU cost to using key9 storage while running with :>> key8 :>> :> :>> :>I allocated some storage in key9 so that one need not switch keys to :>> :>access/update. It seems to cause the code to use slightly more CPU. -- Binyamin Dissen <[email protected]> http://www.dissensoftware.com Director, Dissen Software, Bar & Grill - Israel Should you use the mailblocks package and expect a response from me, you should preauthorize the dissensoftware.com domain. I very rarely bother responding to challenge/response systems, especially those from irresponsible companies. ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN
