> My point being that 1/3 slowdown seems to be about worst case, given
> the construction of your benchmark. The test was both designed to
> exploit lock contention (which does increase in overhead non-linearly
> under usage due to the queueing issues involved) and to measure only
> the overhead of the mechanism (by using a script which did nothing
> else). I'm not disputing your results, just saying you should be more
> honest about how you interpret them.
>
Sure. But what Wez said was that it only affected you when you got 150
req/s, which is not true. And I am being honest. Over the period of
25000 requests, it is likely that you will have *more* than 300
sessions, not less. This would further prove my argument. 300 Unique
users in 25000 requests to a PHP script is not an unreasonable
benchmark, it favors sqlite more than it should.
> Oh, and you can't have a '300% slowdown' it's a 66% slowdown. But
> that's semantics.
Yeah, its a 300% speedup to use files. :)
-Sterling
>
> George
--
"Science is like sex: sometimes something useful comes out,
but that is not the reason we are doing it."
- Richard Feynman
--
PHP Internals - PHP Runtime Development Mailing List
To unsubscribe, visit: http://www.php.net/unsub.php
