HP3000-L Archives

February 2003, Week 4

HP3000-L@RAVEN.UTC.EDU

Options: Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Stan Sieler <[log in to unmask]>
Reply To:
Stan Sieler <[log in to unmask]>
Date:
Wed, 26 Feb 2003 17:18:44 -0800
Content-Type:
text/plain
Parts/Attachments:
text/plain (37 lines)
Re:
> They migrated their programs to NM mode (but not their data, still recorded
> in 16bits format in their DB). They gained better performance of course,
> but for a short time : performances were soon as bad as before. The reason

Sounds like a "third bear of IMAGE" problem should be considered.

BTW, I agree with Gavin and Craig L's posts.

It looks like you need a real performance analysis.  Don't forget
the usefulness of SPT/iX, BTW.

Also, during your busy times ... what does the "speedometer" say
your CPU utilization is?  If it's less than, say, 70 or 80%,
then you're probably waiting on disk.

speedometer:
   At the hardware console, press control-B. That should start a display,
   at the bottom left of the screen, of four-digit hex numbers.
   If the system is still somewhat alive, there should be a pair of
   hex numbers alternating between FFFF and F#FF (e.g., F7FF).
   We're interested in that F#FF, not the FFFF.
   The '#' is the percent busy, divided by 10.  Thus, F5FF is 50% busy.
   And FAFF is 100% busy (hex A is 10).

Out of curiousity, what MPE/iX version were you running on your
9x7 systems?  (It clearly wasn't 7.5 ... thanks to HP Marketing)


--
Stan Sieler
[log in to unmask]
www.allegro.com/sieler/wanted/index.html

* To join/leave the list, search archives, change list settings, *
* etc., please visit http://raven.utc.edu/archives/hp3000-l.html *

ATOM RSS1 RSS2