Re: ORACLE on Linux - IO bottleneck

Mladen Gogala wrote:
>
> Definitely a good article. I was surprised about the large drop
> in the max response time when going from 4K --> 8K:
>
> TPS: 24,82
> kBPS: 50.409
> Total executions: 5584
> Total Rows: 67179
> Total kBytes: 11338,879
> Average response time: 0.034
> Maximum response time: 0.464
>
> TEST8K:
>
> TPS: 24,72
> kBPS: 50.090
> Total executions: 5564
> Total Rows: 66809
> Total kBytes: 11272,059
> Average response time: 0.036
> Maximum response time: 0.246
>
> Throughput was larger with the 4K block. Strange.

Hi Mladen,
yes, that value is strange.
I can only speculate but since the average response time is practical the same on the two tests the only reasons I can think at the moment are: - some spurious values in the first test, - a strange Gaussian distribution for the 4K test.

As Nuno I'm for the sooner.
The latter could lead to a too strange conclusion.

Regards

-- 
Fabrizio Magni

fabrizio.magni_at_mycontinent.com

replace mycontinent with europe