Jerry -

I looked with interest at Steve's reply and I saw some things a little
differently so I'll have to put in my 2¢ here.

I agree that one minute (or even on hour) is not an adequate sample to use
to tune your system.  Performance tuning is somewhat of an art and you
should at least compare your first shift workload vs. your overnight
workload.  I would recommend that you have at least a week's worth of data
before making any changes.  

45,000 jobs is a large number.  If you are not cleaning up joblogs you
should start.  If you're cleaning up joblogs after 30 days you should
consider reducing that to 7 days.  If you truly need to keep that many
production spooled files around you should look into some kind of spooled
file archiving utility.  In the event of a major system crash or D/R
situation you'll more than likely lose these anyway.

Do you have QPFRADJ set to 2 or 3?  If not do you have a compelling reason
for not using this?  Most shops have a significant difference between their
day-shift and night-shift workloads.  QPFRADJ can take the guesswork out of
this for you.  If nothing else turn it on for a little while, watch what it
does, and see if it helps your performance.

The only way to tune your system accurately is to look closely at your
workload, but I'll take a stab at it.  My guess (and it's just a guess) is
that your memory is OK, check your Wait -> Inel and Active -> Inel on
WRKSYSSTS to be sure but I'll bet that those are all 0's.

You did have some paging in pool two that might concern me.  Do your batch
jobs run in the *BASE pool?  See:
http://www-912.ibm.com/s_dir/slkbase.nsf/3cdf5d853ca698198625680b00020369/56
28f38ef557e22f86256d6c00698fd9?OpenDocument

Also, pool 5 has 6 MB of memory??  Is this actually being used or is it left
over from somthing that is no longer being used?

Are you actually experiencing any performance problems?  What is your
average response time during a peak period?  Do your batch jobs complete in
"reasonable" time frames?

Regards,

Scott Ingvaldson
AS/400 System Administrator
GuideOne Insurance Group


-----Original Message-----
date: Mon, 29 Mar 2004 09:05:15 -0800
from: Jerry <jdraper@xxxxxxxxxxxxx>
subject: wrksyssts non DB-fault paging

Here are some snapshots of wrksyssts on our 803 over a period of about one
minute.  
My concern is with the Non-DB Fault column which shows the system paging out
to

the disk...perhaps unncessarily.  

The question is how to remedy this situation.  Is more memory required?  We
have
8GB.

Jerry
   
This message and accompanying documents are covered by the Electronic
Communications Privacy Act, 18 U.S.C. §§ 2510-2521, and contains information
intended for the specified individual(s) only. This information is
confidential. If you are not the intended recipient or an agent responsible
for delivering it to the intended recipient, you are hereby notified that
you have received this document in error and that any review, dissemination,
copying, or the taking of any action based on the contents of this
information is strictly prohibited. If you have received this communication
in error, please notify us immediately by e-mail, and delete the original
message.


As an Amazon Associate we earn from qualifying purchases.

This thread ...


Follow On AppleNews
Return to Archive home page | Return to MIDRANGE.COM home page

This mailing list archive is Copyright 1997-2022 by midrange.com and David Gibbs as a compilation work. Use of the archive is restricted to research of a business or technical nature. Any other uses are prohibited. Full details are available on our policy page. If you have questions about this, please contact [javascript protected email address].

Operating expenses for this site are earned using the Amazon Associate program and Google Adsense.