Ok, will try to search after the relevant attributes in jconsole, for the
mean time I ran ab against a load balancer connected to 3 Tomcat on 3
different boxes and the scenario repeated it self:

[ad...@ltse1 ~]$ ab -n 20000 -k -c 1500 "
http://lbmachine/scale/ctx1?cc=123456";
This is ApacheBench, Version 2.0.40-dev <$Revision: 1.146 $> apache-2.0
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Copyright 2006 The Apache Software Foundation, http://www.apache.org/
Benchmarking *lbmachine* (be patient)
Completed 2000 requests
Completed 4000 requests
Completed 6000 requests
apr_socket_recv: Connection reset by peer (104)
Total of 6576 requests completed

On Tue, Feb 3, 2009 at 3:48 PM, Mark Thomas <ma...@apache.org> wrote:

> Barak Yaish wrote:
> > How can I determine that? I haven't seen any exception in catalina.out
>
> Monitor the current thread usage (eg with LambdaProbe, JMC console, manager
> app)
>
> > regarding out of threads...
>
> There is a proposal to log a message when this happens but with current
> versions
> you won't see anything in the logs.
>
> Mark
>
> >
> > On Tue, Feb 3, 2009 at 6:35 AM, Mark Thomas <ma...@apache.org> wrote:
> >
> >> Barak Yaish wrote:
> >>
> >>> I've records the traffic using Wireshark (http://www.wireshark.org),
> and
> >>> I've noticed that Tomcat send TCP Reset to the client, before it writes
> >> the
> >>> reponse to the stream.
> >>>
> >>> Can you please assist understanding this behavior and tuning Tomcat in
> >> order
> >>> to avoid these problems?
> >> Did you run out of threads and fill the accept queue?
> >>
> >> Mark
> >>
> >>
> >>
> >> ---------------------------------------------------------------------
> >> To unsubscribe, e-mail: users-unsubscr...@tomcat.apache.org
> >> For additional commands, e-mail: users-h...@tomcat.apache.org
> >>
> >>
> >
>
>
>
> ---------------------------------------------------------------------
> To unsubscribe, e-mail: users-unsubscr...@tomcat.apache.org
> For additional commands, e-mail: users-h...@tomcat.apache.org
>
>

Reply via email to