Splunk AppDynamics

How is object allocation rate calculated?

JohnGregg
Path Finder

In the AppD metric browser for Java apps, there is a metric called Allocated-Objects (MB).  I thought I understood what this was, but I'm getting some unexpected results after making a code change.

We had a service that had an allocation rate that was too high for the request volume, IMO, so we took a 1-minute flight recording in a test environment.  Total allocation, according to the flight recording samples, was around 35GB.  Based on where the samples were coming from, we made a code change.  When we retested, the total allocation for the same test over 1-minute was only 9GB, approximately 75% less.

When we deployed the change and re-ran our endurance test, we saw an object allocation rate that was only slightly lower than the baseline.  Dividing the allocation rate by the request volume, the number had only gone down from 12MB/req to 10MB/req.

We do not have verbose GC enabled, so I can't check against that.

What could be causing the numbers to be so similar?  Is the allocation rate reported by AppD reliable?

thanks

 

Labels (1)
0 Karma

JohnGregg
Path Finder

Looks like my calculations were warped by this bug:

https://bugs.openjdk.org/browse/JDK-8307488?force_isolation=true

When I throw out of first sample of each thread, the results make a lot more sense.

0 Karma
Get Updates on the Splunk Community!

Finding Based Detections General Availability

Overview  We’ve come a long way, folks, but here in Enterprise Security 8.4 I’m happy to announce Finding ...

Get Your Hands Dirty (and Your Shoes Comfy): The Splunk Experience

Hands-On Learning and Technical Seminars  Sometimes, you just need to see the code. For those looking for a ...

What’s New in Splunk Observability Cloud: January Feature Highlights & Deep Dives

Splunk Observability Cloud continues to evolve, empowering engineering and operations teams with advanced ...