RE: Auto Tuning

["Graap, Ken" <keg@xxxxxxxxxxxxx>]

>- Therefore, it is the AL that is more important than the TS in 
>determining the effect of increasing the TS for a job and its affect on 
>jobs in other or the same subsystem. Increasing the TS affects other jobs 
>in the system to a minor extent only, because there is an internal 500ms 
>limit. Adding more AL to a subsystem (with jobs to fill the levels) 
>affects processor time for a job more than the increase of TS.


Thank you everyone for you input on this topic ... 

If I understand what IBM is saying in this Knowledge Base article, then
maybe increasing the activity level is a "good" thing and that is why the
"tuner" is doing it...

I think the statement above may mean that if you have enough memory (W/I
A/I transitions very low or zero) and there are jobs (and threads???)
available for processing, then increasing the activity level will result in
better throughput. Do you agree or disagree?

I also tend to agree with Scott when he said "Speaking only for myself, I
will never turn off QPFRADJ." ....

Our environment is USER driven. That is, the user decides what they are
going to run and when they are going to run it. Therefore I would think that
static tuning doesn't make sense. I've set up separate subsystems/memory
pools for similar types of jobs and then I allow OS/400 to allocate activity
levels and memory.

 Kenneth 

-----Original Message-----
From: Vern Hamberg [mailto:vhamberg@xxxxxxxxxxxxxxxxxxxxxxxxx]
Sent: Tuesday, February 03, 2004 10:28 AM
To: Midrange Systems Technical Discussion
Subject: Re: Auto Tuning


The following is from an article in the Registered Knowledge Base -t ake it 
for what it's worth. It says it's for all releases of OS/400 (5763, 5769, 
5722) so I guess that's all RISC boxes.

...