-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Peter,

Since my ears (eyes?) are burning...

On 11/24/2009 6:09 AM, Peter Crowther wrote:
> 2009/11/24 TheGrailer <ken...@gmail.com>:
>> The most compelling argument from the "Apache2 and Tomcat 6"-friend was
>> indeed the static content part.
> 
> http://tomcat.markmail.org/message/il33wqqjb2dok6xz might be
> illuminating - along with the discussion around it on that thread.  I
> suspect Chris will be making his own comments on this thread, as he
> knows his benchmarking results better than anyone!

Yes, I'm getting ready to get back into that benchmarking... that field
has laid fallow for quite a while and I just freed-up a dev server to do
some testing, so I'm basically formalizing everything, properly
documenting it so that my tests can easily be repeated, and upgrading to
Tomcat 6.0.20 for all testing, etc.

Anyhow, the upshot from all the testing I've done is that if you are
using small files (< 32KiB), all connectors (in Tomcat) in all
configurations perform about the same: this includes using Tomcat-native
(aka APR, which is the httpd code mentioned elsewhere).

If the argument is that httpd is faster by definition, then using the
APR connector with Tomcat ought to be just as fast, so you get no
discernible performance boost by using httpd out front. My data has
httpd versus Tomcat+APR+sendFile in a dead heat for nearly all file
sizes, with Tomcat+APR winning at certain points, losing at others. I
suspect this is just noisy data that can be attributed to a cron job or
two running during the tests.

If you want my advice, use the APR Connector and make sure you specify
sendFile="true" and you'll be able to prove your httpd fanboy wrong. :)

- -chris
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.10 (MingW32)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/

iEYEARECAAYFAksYHVgACgkQ9CaO5/Lv0PDnWwCgrGi12feuuHICV0QB8TGDg7aG
ppsAniVmIsuzEHDPOD6LlqJlVi/vHkRE
=OANy
-----END PGP SIGNATURE-----

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscr...@tomcat.apache.org
For additional commands, e-mail: users-h...@tomcat.apache.org

Reply via email to