my dog learned polymorphism*
The moose likes JBoss/WildFly and the fly likes Wierd problem when  performance testing a web application Big Moose Saloon
  Search | Java FAQ | Recent Topics | Flagged Topics | Hot Topics | Zero Replies
Register / Login


Win a copy of Android Security Essentials Live Lessons this week in the Android forum!
JavaRanch » Java Forums » Products » JBoss/WildFly
Bookmark "Wierd problem when  performance testing a web application" Watch "Wierd problem when  performance testing a web application" New topic
Author

Wierd problem when performance testing a web application

dhyan murali
Greenhorn

Joined: Jul 10, 2009
Posts: 8
Hi ,

I have the below code in the controller :



and the method linkDataService.get() looks like below .



when i deploy this in jboss & performance test by sending 100 request persecond -- I see the below log



Can some one tell me why would this happen .. gettime and time to get are technically next instructions to get executed .
I see this mainly when request persecond to that controller is high...
Peter Johnson
author
Bartender

Joined: May 14, 2008
Posts: 5812
    
    7

What, did you think that unrolling a call stack was free? It isn't. (My mainframe compatriots agonize over the machine cycles it takes to build and unroll a call stack, which shocks me every time I work with them...)

Also, it very well could be that a GC happened in between the two log entries. The TimeToGet log entry is building a string dynamically, and if you hit this exact line at the time that eden was full, you would have to wait until GC is complete before you can carry on.


JBoss In Action
 
With a little knowledge, a cast iron skillet is non-stick and lasts a lifetime.
 
subject: Wierd problem when performance testing a web application
 
Similar Threads
SwingWorker blocking(?) GUI
Improving response time
[java.util.logging] recording in log file
Tell me about exec(),biojava...,how to connect database written in c executable file?
Structure Size