Re: What About Price vs. Performance?

We have a simple technique.  You take a video camera, a tripod and a
stop watch.

Place the camera looking over the operators shoulder and hang the stop
watch over the screen in an out of the way location.  Focus the camera
so that the screen, especially the input inhibited indicator, and watch
are recorded.

Perform whatever action you want, then play back the video frame by
frame and note the stop watch time at the point the input is inhibited
until not inhibited.

That is the only time that matters.  User response time.

So the arguement that it really doesn't take five times as long because
we are pushing twice the data doesn't hold water.  To the user it's five
times the wait.

Any other measure is to hunt down bottle necks.


Joe Pluta wrote:
> 
> Leif, how are you measuring your time?  
<<snip>>
> 
> I got MY results by doing a WRKSYSACT, recording the elapsed CPU of the job,
> paging up and down 200 times, and rerecording the elapsed CPU.  How did you
> measure your time?
> 
> There are lies, damn lies and statistics.
>
+---
| This is the Midrange System Mailing List!
| To submit a new message, send your mail to MIDRANGE-L@midrange.com.
| To subscribe to this list send email to MIDRANGE-L-SUB@midrange.com.
| To unsubscribe from this list send email to MIDRANGE-L-UNSUB@midrange.com.
| Questions should be directed to the list owner/operator: david@midrange.com
+---