First, are these page in or page out operations? Page out operations are 
asynchronous and therefore of no concern. 

I'd dig a little deeper, and, if the average page in rate is zero, I'd rest 
easy. 

My $0.02 

-----Original Message-----
From: IBM Mainframe Discussion List [mailto:[email protected]] On Behalf Of 
Peter Kvernes
Sent: Tuesday, February 24, 2009 7:15 AM
To: [email protected]
Subject: Bursts of high paging

Hi,
We have a z/os 1.8 system experiencing bursts of "high paging". This is most 
noteably seen by using SDSF Display Active and using "sort paging d
(escending)". It is only swappable adresspaces that pages.
Does SRM still do "working set trimming" before doing a logical swap? 

This last only a few seconds, and then there is a new burst with some other 
adrspaces.  

Is there a way to avoid this without making everything Nonswappable?
The adrspaces that is paging is typically MQCFG and USS ardspaces.

In general, the paging rate overall is close to zero. 

Appreciate any feedback.

Rgds Peter

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
NOTICE: This electronic mail message and any files transmitted with it are 
intended
exclusively for the individual or entity to which it is addressed. The message, 
together with any attachment, may contain confidential and/or privileged 
information.
Any unauthorized review, use, printing, saving, copying, disclosure or 
distribution 
is strictly prohibited. If you have received this message in error, please 
immediately advise the sender by reply email and delete all copies.

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Reply via email to