Anthony,
I read with interest your post because we have your same environment (3 z/OS
1.7 LPARs in a
basic sysplex) and the performance of GRS ring is not the best. Specifically, I
see XCF delays using
RMF PM, the average value is about 7-8% on the PROD lpar, on the others it goes
over 20 %. But the
other 2 LPARs have a lot less resources as far as CP and weight are concerned.
So I was looking for a way to improve the performance of the ring, and read
your post.
If I understand well what you said, you tried to set RESMIL to OFF and, while
the performance
improved, you saw higher CPU consumption in XCFAS. Then you set RESMIL to 0,
which seemed to
reduce CPU consumption on all other LPARs.
Would you recommend to set RESMIL to 0 on all LPARs to improve GRS performance ?
How is the RESMIL on all your LPARS now ? How *was* RESMIL before the change ?
Thanks in advance
Walter Marguccio
z/OS Systems Programmer
Munich - Germany
___________________________________________________________
Rise to the challenge for Sport Relief with Yahoo! For Good
http://uk.promotions.yahoo.com/forgood/
----------------------------------------------------------------------
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
