Benchmark: Apache2 vs. Lighttpd (Static HTML Files) - Page 2

ab -n 100 -c 50 http://localhost/test.html

Apache: 469,47 requests/second

Lighttpd: 501,45 requests/second (+ 6,81%)

 

ab -n 1000 -c 50 http://localhost/test.html

Apache: 583,74 requests/second

Lighttpd: 708,13 requests/second (+ 21,31%)

 

ab -n 10000 -c 50 http://localhost/test.html

Apache: 827,41 requests/second

Lighttpd: 1058,69 requests/second (+ 27,95%)

 

ab -n 100 -c 100 http://localhost/test.html

Apache: 423,09 requests/second

Lighttpd: 494,61 requests/second (+ 16,90%)

 

ab -n 1000 -c 100 http://localhost/test.html

Apache: 547,59 requests/second

Lighttpd: 706,53 requests/second (+ 29,03%)

 

ab -n 10000 -c 100 http://localhost/test.html

Apache: 790,74 requests/second

Lighttpd: 924,52 requests/second (+ 16,92%)

 

Complete Graph

Share this page:

10 Comment(s)

Add comment

Comments

From: at: 2008-09-23 03:13:31

The apache is from the latest verion of WHM, without any twisting, and the concurrency request is 500, it's also too large to most of common websites. It's not a performance benchmark bwteen apache and lighttpd, but may proved the following two things:

- The default configured apache that provided by hosting providers is not a good choice, some twisting is needed.

- *Seems* that lighttpd with PHP running in FastCGI mode is a little better than working with some addtional memory management tools.(maybe wrong, need some further testings)

Thanks

-joseph

From: at: 2008-09-19 16:30:52

I also did a benchmark among apache-2.63, lighttpd-1.4.19( PHP in FastCGI with eAccelerator), lighttpd-1.4.19( PHP in FastCGI without eAccelerator):

It's here: http://admon.org/uploads/doc/Apache-Lighttpd-with-FastCGI-Benchmark.html

Additionlly, three types of files are tested:

1, Dynamic PHP files with single command phpinfo();

2, Median size HTML file, 24KB

3, Large size JPG file, 188KB

Details is here

From: Anonymous at: 2008-09-22 14:41:51

You seem to have a problem in your test since all apache2 fields are filled with "apr_socket error" And I frankly would not believe that it is Apache2 is guilty that your test failed.

From: dim at: 2008-09-22 07:50:29

You should use other tools for HTTP testing, 'ab' has a very limited scalability!

As workaround, you may start more 'ab' processes to reach higher workload, but using other tool anyway will give you a more realistic view...

Rgds,

-dim

From: admin at: 2008-09-18 23:50:18

I did it with OpenOffice Calc.

From: at: 2008-09-18 21:30:18

What program you used for creating of charts ?

From: ZebX at: 2008-09-18 18:46:54

ab do not represent human comportment and test other limits than web server during this simple test...

From: Anonymous at: 2008-09-19 05:53:03

can you repeat apache tests with worker-mpm ?

From: Christian Folini at: 2008-09-19 07:45:06

This is not a very elaborate, but it gives a clear understanding of raw performance on static files.

I expected to see more difference, now I know more.

Thank you for your work, Falko.

From: Nuno at: 2008-09-25 10:18:21

But i dont understand, what you have better performance? And with php file which is better?