You are viewing a plain text version of this content. The canonical link for it is here.
Posted to modperl@perl.apache.org by Joshua Chamas <jo...@chamas.com> on 2000/06/21 02:05:10 UTC

Re: hello world benchmarks...

Thanks Rudy!  Any way you could throw some
of the others into the mix, like Apache::ASP,
Embperl, Mason, Registry CGI ?  The more
data there is, the more useful the benchmarks
are, since some of the greatest value comes
from how they compare on the same system.

I understand if not since these benchmarks take
a crazy amount of time to run.

--Joshua

_________________________________________________________________
Joshua Chamas			        Chamas Enterprises Inc.
NodeWorks >> free web link monitoring	Huntington Beach, CA  USA 
http://www.nodeworks.com                1-714-625-4051

Rudy wrote:
> 
> Here are some new stats for Joshua's benchmarks:
> http://www.chamas.com/bench/index.html
> ------------------------------------------
> Machine:
> OS: FreeBSD 4.0-STABLE
> cpu: PII-300
> session: no
> client: ab
> From: local
> Notes:  I had to tune the TCP/IP stack...
>   FreeBSD straight off the web does not
>   have settings good for ab tests or high
>   traffice websites. Here are some of the
>   tweaks I made:
> 
> http://www.freebsd.org/cgi/getmsg.cgi?fetch=131178+134382+/usr/local/www/db/text/1999/freebsd-net/19990725.freebsd-net
> ------------------------------------------
> 
> ------------------------------------------
> Test one:
> webserver: Apache 1.3.12/mod_perl 1.23
> application: mod_perl
> ------------------------------------------
> Server Software:        Apache/1.3.12
> Server Hostname:        localhost
> Server Port:            80
> 
> Document Path:          /hello
> Document Length:        11 bytes
> 
> Concurrency Level:      5
> Time taken for tests:   30.008 seconds
> Complete requests:      10540
> Failed requests:        0
> Total transferred:      1634165 bytes
> HTML transferred:       115973 bytes
> Requests per second:    351.24
> Transfer rate:          54.46 kb/s received
> 
> Connnection Times (ms)
>               min   avg   max
> Connect:        0     3    12
> Processing:     6    10    51
> Total:          6    13    63
> 
> ------------------------------------------
> Test two:
> webserver: Apache 1.3.12/mod_perl 1.23
> application: static_html
> ------------------------------------------
> Server Software:        Apache/1.3.12
> Server Hostname:        localhost
> Server Port:            80
> 
> Document Path:          /h.htm
> Document Length:        12 bytes
> 
> Concurrency Level:      5
> Time taken for tests:   30.003 seconds
> Complete requests:      19603
> Failed requests:        0
> Total transferred:      5803968 bytes
> HTML transferred:       235296 bytes
> Requests per second:    653.37
> Transfer rate:          193.45 kb/s received
> 
> Connnection Times (ms)
>               min   avg   max
> Connect:        0     1    10
> Processing:     4     6    17
> Total:          4     7    27
> 
> ------------------------------------------
> Test three:
> webserver: Apache 1.3.12 (different httpd with no mod_perl!)
> application: static_html
> ------------------------------------------
> Server Software:        Apache/1.3.12
> Server Hostname:        localhost
> Server Port:            80
> 
> Document Path:          /h.htm
> Document Length:        12 bytes
> 
> Concurrency Level:      5
> Time taken for tests:   30.004 seconds
> Complete requests:      20605
> Failed requests:        0
> Total transferred:      5275648 bytes
> HTML transferred:       247296 bytes
> Requests per second:    686.74
> Transfer rate:          175.83 kb/s received
> 
> Connnection Times (ms)
>               min   avg   max
> Connect:        0     1    26
> Processing:     3     5     7
> Total:          3     6    33

Re: hello world benchmarks...

Posted by Stas Bekman <st...@stason.org>.
> Thanks Rudy!  Any way you could throw some
> of the others into the mix, like Apache::ASP,
> Embperl, Mason, Registry CGI ?  The more
> data there is, the more useful the benchmarks
> are, since some of the greatest value comes
> from how they compare on the same system.
> 
> I understand if not since these benchmarks take
> a crazy amount of time to run.

It takes no time at all if you use Apache::Benchmark. I still didn't have
a chance to release it on CPAN. In fact you can prepare a complete setup
for other users to run and all they will have to do is to push the button
and voila all the results are printed without you doing a thing.

At this moment you can grab it from 
http://stason.org/works/modules/Apache-Benchmark-0.01.tar.gz

_____________________________________________________________________
Stas Bekman              JAm_pH     --   Just Another mod_perl Hacker
http://stason.org/       mod_perl Guide  http://perl.apache.org/guide 
mailto:stas@stason.org   http://perl.org     http://stason.org/TULARC
http://singlesheaven.com http://perlmonth.com http://sourcegarden.org