Oracle FAQ Your Portal to the Oracle Knowledge Grid
HOME | ASK QUESTION | ADD INFO | SEARCH | E-MAIL US
 

Home -> Community -> Mailing Lists -> Oracle-L -> Re: CPU Usage % on 2-Node RAC Run versus Single Node RAC Run .... Benchmarking

Re: CPU Usage % on 2-Node RAC Run versus Single Node RAC Run .... Benchmarking

From: Alex Gorbachev <ag_at_oracloid.com>
Date: Thu, 11 Oct 2007 20:03:54 -0400
Message-ID: <c2213f680710111703x4dc65bcep93990adec7f4d64b@mail.gmail.com>


I'm a little late on that but about 2 years ago I worked on similar assessment for 9i and my results were similar. We had lots of conf calls with Oracle and in the end everyone agreed that it's normal to have increased CPU consumption moving to RAC but not double. In our case we had 70% not almost 100% but still too high. Those DBs are still running in Primary/Secondary configuration with one node active.

A lot of CPU consumption can be attributed to LMS processes - you can verify that. Also, a lot of increase way SYS time so we thought that this is related to "expensive" IP stack. I retried the tests using LLT for interconnect but results were similar to UDP so I can't prove that.

You will have to dig much deeper than statspack reports to find more details.

On 9/26/07, VIVEK_SHARMA <VIVEK_SHARMA_at_infosys.com> wrote:
>
> Folks
>
>
>
> *CASE 1** -* When Executing a FULL Set of Transactions on Node 1, with the
> 2nd Node's RAC instance in SHUTDOWN Condition
>
> CPU Usage of Node 1-ASMDBR1 = 20 %
>
> CPU Usage of Node 2-ASMDBR2 = 0 %
>
>
>
>
>
> *CASE 2* - When Executing a FULL Set of Transactions on Node 1(ASMDBR1
> instance), with the 2nd Node's RAC instance ASMDBR2 Simply UP & NO
> Application transactions Fired to it
>
>
>
> CPU Usage of Node 1-ASMDBR1 = 20 %
>
> CPU Usage of Unused Node 2-ASMDBR2 = 26 %
>
>
>
> *ASMDBR2 UNUSED Node:-*
>
> *Qs How can the following Waits be Reduced?*
>
>
>
> Top 5 Timed Events Avg
> %Total
>
> ~~~~~~~~~~~~~~~~~~
> wait Call
>
> Event Waits Time (s)
> (ms) Time
>
> ----------------------------------------- ------------ ----------- ------
> ------
>
> CPU time
> 2 29.3
>
> control file sequential read 1,746 2
> 1 23.8
>
> reliable message 5 1
> 269 20.8
>
> control file parallel write 104 0
> 3 5.3
>
> name-service call wait 3 0
> 96 4.4
>
> -------------------------------------------------------------
>
>
>
> *CASE** 3* - When Executing approx Half the above Number of Transactions
> on Node 1, & the Other Half on Node 2 (by setting LOAD_BALANCE = yes in
> tnsnames.ora)
>
> CPU Usage of Node 1 = 18 %
>
> CPU Usage of Node 2 = 19 %
>
>
>
> Will Share Statspack Reports, if asked for.
>
>
>
> Cheers & Thanks
>
>
> **************** CAUTION - Disclaimer *****************
> This e-mail contains PRIVILEGED AND CONFIDENTIAL INFORMATION intended
> solely for the use of the addressee(s). If you are not the intended
> recipient, please notify the sender by e-mail and delete the original
> message. Further, you are not to copy, disclose, or distribute this e-mail
> or its contents to any other person and any such actions are unlawful. This
> e-mail may contain viruses. Infosys has taken every reasonable precaution to
> minimize this risk, but is not liable for any damage you may sustain as a
> result of any virus in this e-mail. You should carry out your own virus
> checks before opening the e-mail or attachment. Infosys reserves the right
> to monitor and review the content of all messages sent to or from this
> e-mail address. Messages sent to or from this e-mail address may be stored
> on the Infosys e-mail system.
> ***INFOSYS******** End of Disclaimer ********INFOSYS***
>

-- 
Alex Gorbachev, Oracle DBA Brewer, The Pythian Group
http://www.pythian.com/blogs/author/alex http://www.oracloid.com
BAAG party - www.BattleAgainstAnyGuess.com

--
http://www.freelists.org/webpage/oracle-l
Received on Thu Oct 11 2007 - 19:03:54 CDT

Original text of this message

HOME | ASK QUESTION | ADD INFO | SEARCH | E-MAIL US