[cgiapp] Re: Benchmark of CGI::Application, HTTP::Engine, Catalyst, Mojo and others when used in a CGI environment.

[Mark Stosberg]

On Wed, 19 Nov 2008 13:18:42 -0500
Michael Peters <mpeters at plusthree.com> wrote:

> Michael Peters wrote:
> 
> >> No big surprises, but perhaps interesting to take a look
> 
> Another surprise for me is that Titanium has a startup time of .14s where C::A has .21s. Isn't 
> Titanium just C::A under the hood? How can it be faster?
> 
> Also you don't mention how many times you ran each benchmark and whether you
> averaged those times.  It's possible that OS caching of files, etc could help
> Titanium startup faster if it was 2nd and both were run only once.

That is almost certainly a mistake, due to the laws of physics involved. I
realized late in the process that my laptop was "Speedstepping" the processor,
so that some earlier benchmarks had run at 733 Mhz, while later ones ran at 1.1
Ghz. Once I noticed that, I thought I re-ran everything explicitly at 1.1 Ghz.
However, my process was not particulary scientific. I ran "time -p" several
times and eyeballed and everage. Sometimes I would get exactly the same time
everytime, and other times things would flucuate 0.20s between runs.

However, generally the relative differences between the different tools
involved remained constant (in terms of their order of speed execution).

    Mark


-- 
 . . . . . . . . . . . . . . . . . . . . . . . . . . . 
   Mark Stosberg            Principal Developer  
   mark at summersault.com     Summersault, LLC     
   765-939-9301 ext 202     database driven websites
 . . . . . http://www.summersault.com/ . . . . . . . .