Scott, Although the redbook on Implementing Siebel recommends raw devices, I didn't find any benchmarks referenced in it.If you go to www.redbooks.ibm.com and search SG24-6211-00 you should find it. The DB2 UDB V71 Performance Tuning Guide indicates many benchmarks have been run. If you search the DB2 home page you may find some or they might be in the older DB2 redbook on implementing DB2and Oracle on AIX. Most benchmarks have shown an improviemnt in disk I/O of 10-35 percent when using device containers versus JFS file systems. However, the results you get will depend on your environment. HTH Phil
Philip K. Gunning
Sr. Systems Consultant
Quest Software, Inc
[EMAIL PROTECTED]
1.800.306.9329x2809
http://www.quest-pipelines.com/Pipelines/DB2/index.htm
-----Original Message-----
From: Scott Saunders [mailto:[EMAIL PROTECTED]]
Sent: Thursday, January 10, 2002 8:40 AM
To: [EMAIL PROTECTED]
Cc: [EMAIL PROTECTED]
Subject: [DB2EUG] FW: DB2EUG: Benchmarks for Raw Devices Vs. File System
Performanc e
Arnoud;
Here is my original question. I copied the list in case it was a temporary
problem preventing me from posting yesterday.
Many thanks to you for running this list for us. We all really appreciate
what you have done for us.
Scott Saunders
> -----Original Message-----
> From: Scott Saunders
> Sent: Tuesday, January 08, 2002 6:02 AM
> To: DB2EUG (E-mail)
> Subject: DB2EUG: Benchmarks for Raw Devices Vs. File System
> Performance
>
> Hello;
> Does anyone have any actual comparisons of performance for these storage
> options? The manuals indicate that raw devices are faster. Can anyone
> confirm this and is it enough faster to justify the additional
> administrative effort in your opinion?
>
> Regards,
> Scott Saunders
> Siebel Systems, Inc.
>
> Opinions expressed are my own and not those of my employer.
-
::: When replying to the list, please use 'Reply-All' and make sure
::: a copy goes to the list ([EMAIL PROTECTED]).
*** You are subscribed to [EMAIL PROTECTED]
*** To unsubscribe, send 'unsubscribe' to [EMAIL PROTECTED]
