> could you please provide also all init parameters for the databases
> in attached file?
not a problem at all (see attachment)

PS The 8kb DB is having Standby DB. Not sure if it makes any difference :)

Yury Velikanov
Oracle [Apps] DBA

The Pythian Group (Sydney Office) - www.pythian.com
http://timeanddat...

From Sydney:
+61 (0)280147452 or +61 (0)280149235 x 277 - office
+61 (0)414252591 - cell

From US & Canada
+1 [masked]  x 277 - office

---------------------------------
IMs:
---------------------------------
Skype 	j.velikanovs 	
AIM 	pythianvelikanov 		
GTalk 	[address removed] 	
MSN 	[address removed] 	
Y! 	[address removed]
---------------------------------
Web resources:
---------------------------------
http://otn.oracle...
http://au.linkedi...
---------------------------------




On 4 June 2010 15:10, Andrey Goryunov <[address removed]> wrote:
> Yuri,
>
> could you please provide also all init parameters for the databases
> in attached file?
>
> Cheers,
> Andrey
>
> On 4 June 2010 13:33, Yury Velikanov <[address removed]> wrote:
>> Hello Everyone,
>>
>> Just to follow up on the issue.
>> The investigation is still in process. I work on that as time permits
>> (as client doesn't complain and have other priorities). However this
>> definitely looks like a technical challenge. And who but us Oracle
>> DBAs like technical challenges :)
>>
>> Last thing that I did was to compare all LATCHes and STATs in between
>> EXACTLY the same executions on both databases (4k and 8k) on that
>> particular server.
>> The statistics doesn't revile anything specific but additional
>> confirmation that 8k database spends 2-3 time more time on that
>> particular host to execute the test.
>>
>> I have executed the same test on other servers (11GR2 to make it a
>> close as possible to that case) and received the expected results. 8k
>> databases over performed 4k databases by up to 10%. This specific
>> issue is related to that particular setup only.
>>
>> This case additional justification for the simple CPU test execution
>> on your systems (databases) and comparison with other platforms.
>> I found in that cases that one of the DBes have weird configuration.
>> Addressing that issue we potentiality can improve the overall
>> application performance 3 times :)
>> The only problem is to find what is wrong in that particular case.
>>
>> Next action that I have in mind is as suggested to create a 8k cache
>> pool  in 4k database, create 8k tablespace and run the test to compare
>> the execution time. This test will allow us to find out is it a
>> particular DB setup (8k DB) in charge of it or HW (Intel(R) Xeon(R)
>> CPU X5550 / cache) and 4K/8K block issue.
>>
>> Stay tuned and see you tonight,
>>
>> Yury Velikanov
>> Oracle [Apps] DBA
>>
>> The Pythian Group (Sydney Office) - www.pythian.com
>> http://timeanddat...
>>
>> From Sydney:
>> +61 (0)280147452 or +61 (0)280149235 x 277 - office
>> +61 (0)414252591 - cell
>>
>> From US & Canada
>> +1 [masked]  x 277 - office
>>
>> ---------------------------------
>> IMs:
>> ---------------------------------
>> Skype   j.velikanovs
>> AIM     pythianvelikanov
>> GTalk   [address removed]
>> MSN     [address removed]
>> Y!      [address removed]
>> ---------------------------------
>> Web resources:
>> ---------------------------------
>> http://otn.oracle...
>> http://au.linkedi...
>> ---------------------------------
>>
>>
>>
>>
>> On 26 May 2010 14:40, Nuno Pinto do Souto
>> <[address removed]> wrote:
>>> Bugger, I don't have access to any RHLinux system at the moment...
>>> A couple of things to check, from a vague memory:
>>> 1- What file system block size for each db
>>> 2- Are datafiles for all dbs on same file system
>>> 3- What is the value of filesystemio_options for each db.
>>> 4- In sqlplus, what does this produce on each db:
>>> show parameter priority
>>> 5- Check and compare SGA memory-related sizes for each db.
>>>
>>> Cheers
>>> Nuno Pinto do Souto
>>> DBA Team, Australia/NZ
>>>
>>> -----Original Message-----
>>> From: [address removed]
>>> [mailto:[address removed]] On Behalf Of Yury Velikanov
>>> Sent: Wednesday, 26 May 2010 11:18 AM
>>> To: [address removed]
>>> Subject: [Sydney-Oracle] I need you help. Odd performance difference
>>> comparing 4k data block size and 8k databases
>>>
>>> Hello everyone,
>>>
>>> I need any idea that may came you your head to find out the reason for
>>> the following problem. Please do not hesitate to through any
>>> suggestions and I will  check those for you.
>>> This is a super-duper new Dell server, 11GR2, Red Hat Enterprise Linux
>>> Server release 5.4.
>>>
>>> ______________________________________________________
>>>    CONFIDENTIALITY NOTICE
>>> This electronic mail message, including any and/or all attachments, is for the sole use of the intended recipient(s), and may contain confidential and/or privileged information, pertaining to business conducted under the direction and supervision of the sending organization. All electronic mail messages, which may have been established as expressed views and/or opinions (stated either within the electronic mail message or any of its attachments), are left to the sole responsibility of that of the sender, and are not necessarily attributed to the sending organization. Unauthorized interception, review, use, disclosure or distribution of any such information contained within this electronic mail message and/or its attachment(s), is (are) strictly prohibited. If you are not the intended recipient, please contact the sender by replying to this electronic mail message, along with the destruction all copies of the original electronic mail message (along with any attachments).
>>> ______________________________________________________
>>>
>>>
>>>
>>> --
>>> Please Note: If you hit "REPLY", your message will be sent to everyone on this mailing list ([address removed])
>>> http://www.sydney...
>>> This message was sent by Nuno Pinto do Souto ([address removed]) from Sydney Oracle Meetup.
>>> To learn more about Nuno Pinto do Souto, visit his/her member profile: http://www.sydney...
>>> To unsubscribe or to update your mailing list settings, click here: http://www.sydney...
>>> Meetup, PO Box 4668 #37895 New York, New York 10163-4668 | [address removed]
>>>
>>>
>>
>> --
>> Catch Alex & Sheeri at ODTUG/Kaleidoscope - June 27 - July 1.
>> Hear Sheeri speak or email [address removed] to meet with Pythian.
>>
>>
>>
>> --
>> Please Note: If you hit "REPLY", your message will be sent to everyone on this mailing list ([address removed])
>> http://www.sydney...
>> This message was sent by Yury Velikanov ([address removed]) from Sydney Oracle Meetup.
>> To learn more about Yury Velikanov, visit his/her member profile: http://www.sydney...
>> To unsubscribe or to update your mailing list settings, click here: http://www.sydney...
>> Meetup, PO Box 4668 #37895 New York, New York 10163-4668 | [address removed]
>>
>
>
>
> --
> Sincerely,
> Andrey Goryunov.
>
>
>
> --
> Please Note: If you hit "REPLY", your message will be sent to everyone on this mailing list ([address removed])
> http://www.sydney...
> This message was sent by Andrey Goryunov ([address removed]) from Sydney Oracle Meetup.
> To learn more about Andrey Goryunov, visit his/her member profile: http://www.sydney...
> To unsubscribe or to update your mailing list settings, click here: http://www.sydney...
> Meetup, PO Box 4668 #37895 New York, New York 10163-4668 | [address removed]
>
>

--
Catch Alex & Sheeri at ODTUG/Kaleidoscope - June 27 - July 1. 
Hear Sheeri speak or email [address removed] to meet with Pythian.