[jboss-svn-commits] JBL Code SVN: r33053 - labs/jbosstm/workspace/whitingjr/trunk/performance.

[jboss-svn-commits at lists.jboss.org]

Author: whitingjr
Date: 2010-05-24 13:24:17 -0400 (Mon, 24 May 2010)
New Revision: 33053

Modified:
   labs/jbosstm/workspace/whitingjr/trunk/performance/README.txt
Log:
Updated release history.

Modified: labs/jbosstm/workspace/whitingjr/trunk/performance/README.txt
===================================================================
--- labs/jbosstm/workspace/whitingjr/trunk/performance/README.txt	2010-05-24 17:19:22 UTC (rev 33052)
+++ labs/jbosstm/workspace/whitingjr/trunk/performance/README.txt	2010-05-24 17:24:17 UTC (rev 33053)
@@ -63,17 +63,27 @@
        
 0.7   Provide configuration to bypass the connection pooling implementation. Instead 
       the connection is cached per thread.
+      Using the cached connection and XA resources the enlistment and delistment is
+      handled by extended wrapper classes.
+      Added capturing Dstat metrics during the profiling run.
+      Added charting of the Dstat metrics.
 
+
+
+
 Known issues:
-  The original performance profiling project called Java Interactive Profiler (JIP) was integrated
+
+* The original performance profiling project called Java Interactive Profiler (JIP) was integrated
  with the profiling system. However the JIP profiler affected the performance results excessively
  and was abandoned. Instead the 'wall to wall' time is captured for the 'steady state' run.
  Integration with profilers has not been abandoned and others can be used. An alternative 
  working profiler configuration is JProfiler. Ideally, at a later date another open source
  profiler will be integrated.
 
- The connection pooling performance is possibly a scalability bottleneck. Based on lock 
+* The connection pooling performance is possibly a scalability bottleneck. Based on lock 
  contention (100+ threads) around the pooling code. More investigation required to confirm
  this. To overcome CPU saturation due to saturation have change the ManagedConnectionFactory
  to bypass the pooling and instead cache the connection per thread.
   
+* The current implementation does not release the connection back to the pool when the cached
+ connection feature is used.
\ No newline at end of file