Mark wrote: >I suspect the workload you're running would see little or no improvement if >all of the OS were recompiled with -march and -mtune set higher. If your >middleware were all recompiled, that would likely be very different.
I suspect you are correct (what's new :).. When a WAS service pack cuts CPU in 1/2 for a particular app (but only that one for us) , one assumes there might be room for improvement... I think one can contribute all this inefficient code to distributed (i.e. I got my own who cares) boxes. I can raise the severity of open problems. I can't change contracts or withhold $. Just not high enough in the food chain ;) I have be able to fill out a vendor report card.. which goes back to contracts... Long cycle though. Marcy This message may contain confidential and/or privileged information. If you are not the addressee or authorized to receive this for the addressee, you must not use, copy, disclose, or take any action based on this message or any information herein. If you have received this message in error, please advise the sender immediately by reply e-mail and delete this message. Thank you for your cooperation. -----Original Message----- From: The IBM z/VM Operating System [mailto:IBMVM@LISTSERV.UARK.EDU] On Behalf Of Mark Post Sent: Tuesday, March 29, 2011 10:30 PM To: IBMVM@LISTSERV.UARK.EDU Subject: Re: [IBMVM] SLES 9 on a z/196? >>> On 3/30/2011 at 01:24 AM, Marcy Cortes <marcy.d.cor...@wellsfargo.com> >>> wrote: > Now if it were compiled for later than a z9 maybe it could exploit these > shiny new boxes better :) I suspect the workload you're running would see little or no improvement if all of the OS were recompiled with -march and -mtune set higher. If your middleware were all recompiled, that would likely be very different. > And if we could only get some of those other sw vendors to support sles > 11... Money talks. Stop paying them to be recalcitrant. You get the behavior you reward. Mark Post
