RE: Concurrent I/O (AIX 5.2)
- From: "Allen, Brandon" <Brandon.Allen@xxxxxxxxxxx>
- To: <Gsais@xxxxxxxxxxxxxxxxxxx>, <oracle-l@xxxxxxxxxxxxx>, "Stuart Clowes" <stuart.clowes@xxxxxxxxx>
- Date: Thu, 29 Jun 2006 09:34:08 -0700
I second that recommendation - we have done that here as well. But I
wouldn't say that *alone* is where I would start - there are several
other critical factors that must be considered as well, as I previously
mentioned: increasing db_cache_size to compensate for the buffering
you're taking away from AIX, setting agblksize=512 for redologs to align
the block size with size of Oracle's I/O requests (otherswise it reverts
back to regular buffered I/O regardless of your CIO settings), and
mounting the filesystems with o=cio if you're on 9i (not necessary in
10g). We also increased minservers and maxservers - and implemented the
SGA in large pages (16MB) and pinned them in memory (lock_sga=true &
v_pinshm=1).
________________________________
From: oracle-l-bounce@xxxxxxxxxxxxx
[mailto:oracle-l-bounce@xxxxxxxxxxxxx] On Behalf Of Gene Sais
Sent: Thursday, June 29, 2006 5:08 AM
To: oracle-l@xxxxxxxxxxxxx; Stuart Clowes
Subject: Re: Concurrent I/O (AIX 5.2)
Have you looked at vmo parameters that affect page stealing. I have
mine set to:
vmo -p -o minperm%=5 # Was 20
vmo -p -o maxclient%=10 # Was 80
vmo -p -o maxperm%=10 # Was 80
This alone is the first place I would start.
Privileged/Confidential Information may be contained in this message or
attachments hereto. Please advise immediately if you or your employer do not
consent to Internet email for messages of this kind. Opinions, conclusions and
other information in this message that do not relate to the official business
of this company shall be understood as neither given nor endorsed by it.
Other related posts:
