Re: Oracle Web performance advert

"Jacqui caren" <Jacqui.Caren_at_ig.co.uk> wrote in message news:Xns91B28F624BFF5JacquiCarenigcouk_at_195.8.69.161...
> In a recent issue of computing Oracle took out a full page advert
> 'bragging' about how quick they were when compared with other
> dynamic web servers.
>
> see http://www.oracle.com/java for details.
>
> What has me so irate is that they seem to be proud about ~600ms
> per hit, compared to 1.2 seconds per hit for thier 'worst'
> competitor (thier figures).
>
> Given that I am currently unhappy with our average performance
> of 200ms per hit (250 to 170) on live servers runnig on low end
> (antique) linux boxes with 128m ram and single 00mz Athlon and
> am realistically aiming for less than 50ms per hit on more
> commercial platforms with a bit more performance work on the
> underlying technology, how can someone be *proud* that they take
> over half a second to process a single web page request?
>
> This means that if a single page consist of HTML + three
> inline dynamic graphs it takes over two seconds to render
> (as far as the user is concerned) the entire page.
>
> Any comments on what people think a decent dynapage hit
> rate should be? Hopefully they prefer 50 rather that 500ms :-)

Hi Jacqui

It seems to me that you have a misconception of what they are claiming. What they are saying is that the sun benchmark app (the petstore) took 1/2 a second per page request on average on a quad 400mhz intel machine with a gig of ram under a load of 600 users. That does not equate to saying that dynamic content takes 1/2 a second on average to render, it merely indicates how the benchmark application runs on specific hardware under a specific load. If one looks at ms for example they claim that the same app rewritten in .net runs a whole lot quicker. They are almost certainly right. None of this proves anything at all other than the performance you would get if your website were the sun benchmark and it was running on that specific hardware. This is why benchmark marketing is evil and insidious. It cannot possibly be applied to anyones actual on except in broad terms and with wild caveats.

As to you last question I'd obviously prefer the second performance figure but what am I summarising on my hypothetical page 200mb of data or 450TB? and across how many variables? Did another user just request the same info or is each enquiry unique?

--
Niall Litchfield
Oracle DBA
Audit Commission UK
*****************************************
Please include version and platform
and SQL where applicable
It makes life easier and increases the
likelihood of a good answer

******************************************