Re: Benchmark for fastcgi

> Do any of you have any data on benchmarking of fastcgi. What I am 
> primerily
> interested in is sending 5k html data embedded in C printf statements 
> in a C
> fcgi application. From what I have read fastcgi could even be faster 
> than direct
> seb server API. Is this true? From the benchmark below it does not 
> seem true.

I think an Apache C module would be faster than a FastCGI C module.  
FastCGI does have overhead.  OTOH, there are also advantages to using 
FastCGI over an Apache module, such as:

- Being able to run your app on a different server than the web server
- Being able to run your app under web server software other than Apache
- If your app crashes, it won't take down the web server
etc.

> I have seen this benchmark,
> http://chamas.com/bench/
> There it states [Apache server],
> 214 byte output:
> C Apache API                 4285.2 hits/sec
> mod_php PHP                  1601.2 hits/sec
> mod_fastcgi                  911.9 hits/sec
>
> As you can see php is actually faster! What I wonder from these 
> results is if
> how the fastcgi app was done, was it a perl interpreted page or was it 
> a C
> application?

It  describes this test as:

mod_fastcgi CGI::Fast

CGI::Fast is a perl module, part of the (rather bloated) CGI.pm family. 
If you download the source to the module you'll see the contents of 
hello.fastcgi:

#!/usr/local/bin/perl

use strict;
use CGI::Fast;

while (my $cgi = new CGI::Fast) {
     print $cgi->header();
     print "Hello";
     print " World";
}

  A better test of FastCGI under perl would have been mod_fastcgi with 
FCGI.pm.  My guess is that, in general,  a C FastCGI app would far out 
pace PHP.  Of course "Hello World" is hardly a good benchmark.

- Max

___________________________________
fastcgi-developers mailing list
http://fastcgi.com/fastcgi-developers/