Caldarale, Charles R wrote:
Run jstack several times during the delay, and then let's compare the set of
thread dumps.
What is the CPU utilization during the delay?
OK, done. The CPU utilization during the delay is tiny, 1% or less. I've run jstack before, during, and after I've
done a first request on my tiny offending test JSP. Since the jstack output is lengthy (I've got several sites running
on this public server, unavoidably), I've thrown the resulting output on my server for easier viewing.
jstack.0.txt ran BEFORE my test request.
jstack.1-11.txt ran DURING the long wait.
jstack.12,13.txt ran AFTER the response was received.
http://ims.net/jstack/jstack.0.txt
http://ims.net/jstack/jstack.1.txt
http://ims.net/jstack/jstack.2.txt
http://ims.net/jstack/jstack.3.txt
http://ims.net/jstack/jstack.4.txt
http://ims.net/jstack/jstack.5.txt
http://ims.net/jstack/jstack.6.txt
http://ims.net/jstack/jstack.7.txt
http://ims.net/jstack/jstack.8.txt
http://ims.net/jstack/jstack.9.txt
http://ims.net/jstack/jstack.10.txt
http://ims.net/jstack/jstack.11.txt
http://ims.net/jstack/jstack.12.txt
http://ims.net/jstack/jstack.13.txt
I wish I could divine something informative from these. Perhaps one of you can.
I'm also trying to use Wireshark to see if there is some specific net activity that's going on during the long wait, as
suggested by David Smith.
---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscr...@tomcat.apache.org
For additional commands, e-mail: users-h...@tomcat.apache.org
