The results presently:
ind
AVGPROC-007% 01
MDC READS-000033/SEC WRITES-000001/SEC HIT RATIO-099%
STORAGE-042% PAGING-0001/SEC STEAL-000%
Q0-00001(00000) DORMANT-00103
Q1-00001(00000) E1-00000(00000)
Q2-00000(00000) EXPAN-001 E2-00000(00000)
Q3-00000(00000) EXPAN-001 E3-00000(00000)
PROC 0000-007%
LIMITED-00000
Ready; T=0.01/0.01 12:20:43
q alloc page
EXTENT EXTENT TOTAL PAGES HIGH %
VOLID RDEV START END PAGES IN USE PAGE USED
------ ---- ---------- ---------- ------ ------ ------ ----
510PAG F005 1 3338 600840 332523 443499 55%
PAG002 F008 1 3337 600660 0 0 0%
PAG003 F00A 1 3337 600660 0 0 0%
------ ------ ----
SUMMARY 1760K 332523 18%
USABLE 1760K 332523 18%
Ready; T=0.01/0.01 12:21:38
MDC READS is now 33/SEC... Could the percentage used be stuck at the high
water mark? On the first level system the percentage of page space used does
drop after the paging rate drops. How would I determine what is driving the
page space utilization?
To be able to have unique volume labels:
Cyl Function
0 Volume label for first level system
1 Volume label for second level system
The 510PAG volume is what came with z/VM 5.1. Eventually, we will remove the
510PAG volume and replace it with a PAG001 volume with just 3337 cylinders
available for paging.
Thank you.
Cecelia Dusha
-----Original Message-----
From: Rob van der Heij [mailto:[EMAIL PROTECTED]
Sent: Monday, September 11, 2006 12:09 PM
To: IBMVM@LISTSERV.UARK.EDU
Subject: Re: z/VM 5.1 Paging
On 9/11/06, Dusha, Cecelia Ms. WHS/ITMD <[EMAIL PROTECTED]> wrote:
> Are you saying the MDC READS - 142/SEC could be driving the page space used
> to 55%? The paging rate itself is 1/SEC... We added 2 paging volumes to
> ensure the system does not run out of paging space.
I'm not sure he implied that, but it is certainly true. With the
default MDC settings CP is often too agressive in using MDC that it
actually causes paging to occur. Paging with 2000 per second is quite
impressive with just a single page pack... Maybe on your previous
system your backup was held back more than it did not cause MDC to
grow that fast.
You'd want to know what portion of real memory was used by MDC when
you were paging that much. A performance monitor allows you to review
various metrics during the event to understand what happened. Going
from z/VM 3.1 to z/VM 5.1 is a giant step, and most likely even more
changed at the same time. It's very hard to do this right with just a
few CP commands after the thing happened.
> Our production system is a guest system under z/VM 5.1. I don't know if
> this would matter in the explanation as to why the system had a 55% paging
> space utilization...
That's probably a wise thing to do. BTW did someone steal a cylinder
from you? ;-)
--
Rob van der Heij
Velocity Software, Inc
http://velocitysoftware.com/
