And they use the small cocktail napkins not the large lap covering napkins Bob Lawrence DBA Boscovs Dept Stores LLC
-----Original Message----- From: Linux on 390 Port [mailto:[EMAIL PROTECTED] On Behalf Of Alan Altmark Sent: Friday, July 20, 2007 3:16 PM To: [email protected] Subject: Re: zSeries IFL speed rating On Friday, 07/20/2007 at 10:51 EDT, "McKown, John" <[EMAIL PROTECTED]> wrote: > Good point. The <bleep> marketing people took a very good measure of > performance, which was originally designed to rationalize "work" across > multiple different processors and royally <bleep> <bleep> <bleep>. I am > really beginning to HATE software vendors and their marketing > techniques. Nah. What you hate is that technology has surpassed our collective ability to rationalize it. When MHz had a linear correlation to MIPS and no one had heard of NUMA or pipelining, life was good. We went from measurements that reflected cycle time (MHz) to instruction execution power (MIPS), even though it was best expressed as a range, to one that tries to represent computing capacity and throughput (MSUs). Why? As was said, to bring some sanity to software pricing. Allowing our bosses to believe they can do capacity planning on the back of a paper napkin borders on professsional suicide. They will ultimately make the wrong decision using bad or misleading data and <bleep> rolls downhill. [BTW, paper napkins are de rigeur for all significant planning exercises. Beware.] If the boss wants to know how much money she needs to budget in 2007 to allow for organic growth and new projects, help her. If she wants to know the cycle time of the CPU, ask why. While it's an entertaining trivia question asked at all the *best* cocktail parties thrown by engineers, it's like nails on a chalkboard to hear an IT manager ask it. (Correct answer: "For what model?", resulting in knowing nods from around the room. Depending on how much the party-goers get out, you might even quip "Laden or unladen?".) I'm trying to get folks to quite charging for each CPU-minute a z/VM guest consumes. It doesn't accurately (or even remotely) measure the IT resources (people, power, space, machines) it really does chew up. And buying newer, faster machines just spins the meter dial faster, ultimately making the user go buy their own system. "There's a hole in my bucket, dear Liza...." It ain't 1980 any more and it hasn't been for quite a while. :-) Alan Altmark & Co. ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390 ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
