On Thu, Mar 04, 2010 at 11:31:24AM -0500, Carson, Brad wrote: > > I was hoping that someone else had seen this type of issue before > and might provide some more insight. Our application folks keep > wanting to blame z/VM and the z10 hardware instead of looking at > their code.
If your Java huys won't even look at the app server and JVM behaviour you have bigger problems that the app. Barton's suggestion to compare to the app running on an x86 platform is not a bad one - we've found in the past at our site that an app using a four cores on a modern (i.e. Core2 architecture) Intel box will use about 4 IFLs, so that could provide a guideline as to whether Weblogic is misbehaving in some way on the Z. Note that "CPU problems" in Java apps can be from a number of sources - we're currently dealing with one that is due to inadequate memory in the Nursery space of a system causing high GC rates. This shows as high CPU use from a system perspective (including ESAMON), the heap for the Java app isn't fully used - but one of the heap pools is running out. You really want to point some decent Java monitoring tools at your JVM to help you understand what's going on here. -- Rodger Donaldson [email protected] ---------------------------------------------------------------------- For LINUX-390 subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO LINUX-390 or visit http://www.marist.edu/htbin/wlvindex?LINUX-390
