Irrational Exuberance

You are writing a comment about Measuring Single and Multi Server Performance, here is a quick summary:

Here is a first for my blog: an experiment conducted using something approaching the scientific method. In other ways it wasn't a first for my blog, because it was essentially a complete failure. Damn it.

You are responding to this comment written by Graham Dumpleton on February 20th 2009, 21:06.

What is not explained in your post and is an important factor is the nature of the WSGI application tested. If you used one of the large frameworks then startup costs need to be taken into consideration and as necessary the application preloaded to ensure you aren't counting that startup cost as part of the times take for a request.

Please be aware that comment forms go stale after one hour.

@@ ruby
def a (b, c):
  b * c
end
@@

 ### This is an h3 title
#### This is an h4 title
**this is bold**
*this is italics*

1. This is an
2. ordered list

* And an unordered
* list too

[this is a link](http://www.lethain.com/ "Lethain")