RE: HP-UX

There's potentially a bunch of kernel/FS parameters to tweak.  

What filesystem are you using? Or raw?  

What are the mountpoint parameters?  

Check kernel tunables according to the Oracle install docs. Also check your kernel vx* tunables and make sure that fs_async is set to 0 (Oracle apparently doesn't like that set on HPUX -- should be a doc on MetaLink about that, but I don't know how up-to-date it is).

Not that it's particularly helpful, but a tool like HP's SAM may help. Without much more info, my first suspect is the IO subsystem (SAN). It's like sending a mechanic an email saying your car goes "ka-chug" and doesn't accelerate fast -- it's too general a symptom to pinpoint the cause.  

HTH! GL!   Rich  

From: oracle-l-bounce_at_freelists.org [mailto:oracle-l-bounce_at_freelists.org] On Behalf Of Alfonso León Sent: Monday, August 14, 2006 2:28 PM
To: oracle-l
Subject: HP-UX

Hi Every one:
we went online today with full load, until last week we were 20% loaded, and CPU Utilization with less 10%. We have a HPUX with 10 cpus and a Hitachi SAN. Oracle 9.2.0.6. CPU utilization is now 40%.  

Today the performance was way more less than expected.  

these are the top wait event

Top 5 Timed Events

~~~~~~~~~~~~~~~~~~ % Total

Event Waits Time (s) Ela Time

• ------------ ----------- --------

db file sequential read                      1,768,294       38,259     39.69

log file sync                                    71,190      30,065     31.19

free buffer waits                                12,212      11,351      11.78

buffer busy waits                               360,596       8,773      9.10

CPU time                                                      2,736      2.84

db file scattered read                          382,133       1,691      1.75

db file parallel read                             2,958       1,199      1.24

log file parallel write                           5,193       1,073      1.11

enqueue                                           1,649         698       .72 

SQL*Net message from dblink                      54,991         141       .15

As you can see i'm waiting on disk, the path utilization of the san is less than 20% and the CPU utilization is less than 40%. almost all the processes are sleeping.  

On the HP-UX monitor says that peak disk utilization is 100% the rest of the parameters are normal and sub-used.  

Does anybody know if there is parameter in kernel that limit the disk request?  

Any idea would be appreciated.  

Alfonso Leon

--

http://www.freelists.org/webpage/oracle-l Received on Tue Aug 15 2006 - 15:15:49 CDT