Re: [eAccelerator-developers] eAccelerator scales towards useless

[dormando <dor...@ry...>]

Hey,

I'm appreciative of your optimization pointers, but this isn't really 
about that.

Our architecture is *very* highly tuned. Our databases are near idle all 
day, and our webservers and network are very highly tuned top to bottom. 
Our load balancing architecture is modeled after the best, and this 
latest inquiry is in my interest of further pushing the limits; we have 
hundreds of servers, every percentage point I can push in speed saves us 
thousands of dollars.

In this particular case, eA is doing something that should very well be 
fixable, so I am hoping that it is.

As my original e-mail already states, in pages that are almost pure-CPU 
loads we have a 75% performance gain by using eA. After the cache is 
loaded, that performance gain drops to 60% for the *same page loads*. As 
we add more pages and more data to cache, I expect that initial 
performance increase to drop further.

I know everyone wants to insist that my configuration is bumpkus, but 
that's why I spent four hours running tests all over eA's configuration. 
I was also very careful to state most of the setup in the original 
e-mail. To those who insist on "stick with the defaults" - I would, but 
those were even slower. Also, *please* understand that this was as far 
from a synthetic test as I could make it. I'm testing our real code, 
doing many, many iterations through real pageviews; not trying to 
include as many files as possible and timing it.

have fun,
-Dormando

megaciudad megaciudad wrote:
> Estimate Dormando:
> 
> We have three cpanel servers with a mixture of xNukes, oscommerces,
> pure perl and pure html sites, and we have noticed:

[...]