Actually, I was thinking more of disabling the AccessLog in httpd, to
see how much impact that had.
(That's also less additional tests to run ;-))
Christopher Schultz wrote:
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
André,
On 5/19/2009 2:28 PM, André Warnier wrote:
Christopher Schultz w
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
André,
On 5/19/2009 2:28 PM, André Warnier wrote:
> Christopher Schultz wrote:
> ...
> Thanks for the work. At least it may put to rest some gross
> misconceptions.
>
> Now just a question : in the httpd tests, did you have an AccessLog
> enabled ?
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Gregor,
On 5/19/2009 12:59 PM, Gregor Schneider wrote:
> I'm a bit puzzled:
>
> In your previous tests it looked like that Apache is "outperforming"
> (ok, not really) Coyote w APR when the files grew bigger.
I disagree with that conclusion. My inte
Christopher Schultz wrote:
...
Thanks for the work. At least it may put to rest some gross misconceptions.
Now just a question : in the httpd tests, did you have an AccessLog
enabled ? I would imagine you did not have an AccessLogValve enabled in
Tomcat, and I wonder if it makes any practical
> From: Caldarale, Charles R
> Subject: RE: Apache httpd vs Tomcat static content performance [some
> results]
>
> > In your last results I can't see that pattern - actually, I don't see
> > /any/ pattern...
>
> Quantum mechanics?
More seriously, we may
> From: Gregor Schneider [mailto:rc4...@googlemail.com]
> Subject: Re: Apache httpd vs Tomcat static content performance [some
> results]
>
> In your last results I can't see that pattern - actually, I don't see
> /any/ pattern...
Quantum mechanics?
- Chuck
TH
I'm a bit puzzled:
In your previous tests it looked like that Apache is "outperforming"
(ok, not really) Coyote w APR when the files grew bigger.
In your last results I can't see that pattern - actually, I don't see
/any/ pattern...
Any idea how come?
Cheers
Gregor
--
just because your parano
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
All,
So, I have some data from last night. It's about what you'd expect,
except that the NIO+sendfile connector test failed most of the time: the
client got something like "apr_connect: Connection reset by peer" when
it tried to connect to the server.