Re: Surprising Performance Changes with Oracle 11.2.0.1 (Long Post)
From: Robert Klemme <shortcutter_at_googlemail.com>
Date: Sat, 05 Sep 2009 12:41:53 +0200
Message-ID: <7getjpF2pj742U3_at_mid.individual.net>
On 05.09.2009 08:04, Jonathan Lewis wrote:
>
> ...
>
>
> Charles,
>
> Interesting figures.
> A couple of follow-on questions:
> How much memory in the machine ?
> How many CPUs
> Were you running the client locally - ipc or tcp
> How much CPU usage "outside" Oracle in each test
> Any significant variation in 'prefetch' blocks
> Any other significant variation in stats
Date: Sat, 05 Sep 2009 12:41:53 +0200
Message-ID: <7getjpF2pj742U3_at_mid.individual.net>
On 05.09.2009 08:04, Jonathan Lewis wrote:
>> "Charles Hooper" <hooperc2000_at_yahoo.com> wrote in message >> news:1ea99c67-8713-4ece-a0f5-85f66851b016_at_v2g2000vbb.googlegroups.com... >> I am working on an Oracle performance related project, so I thought >> that I would compare the performance of Oracle database 11.1.0.6 (on >> 64 bit Linux), 11.1.0.7 (on 64 bit Windows), and 11.2.0.1 (on 64 bit >> Linux).
>
> ...
>
>
> Charles,
>
> Interesting figures.
> A couple of follow-on questions:
> How much memory in the machine ?
> How many CPUs
> Were you running the client locally - ipc or tcp
> How much CPU usage "outside" Oracle in each test
> Any significant variation in 'prefetch' blocks
> Any other significant variation in stats
I am also wondering about table and index stats. Charles, I see you only mention system stats with NOWORKLOAD. What about stats for the table and what about system stats gathered with INTERVAL and / or START/STOP? Kind regards
robert
-- remember.guy do |as, often| as.you_can - without end http://blog.rubybestpractices.com/Received on Sat Sep 05 2009 - 05:41:53 CDT