[
https://issues.apache.org/jira/browse/HDFS-559?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12745890#action_12745890
]
Steve Loughran commented on HDFS-559:
-------------------------------------
There is a way to to do this in the java Instrumentation API:
http://java.sun.com/javase/6/docs/api/java/lang/instrument/Instrumentation.html#getObjectSize%28java.lang.Object%29
It just needs someone to write an instrumentation agent that can be loaded
within Hadoop -even the unit tests- and print out the sizes of various classes;
test this on different JVMs and you would have a table for the cost of the
directory structure on different machines
It would still be good to run the HADOOP-1687 how-much-work-before-OOM
benchmarks, as that is the most realistic test of datastructure size.
> Work out the memory consumption of NN artifacts on a compressed pointer JVM
> ---------------------------------------------------------------------------
>
> Key: HDFS-559
> URL: https://issues.apache.org/jira/browse/HDFS-559
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: name-node
> Affects Versions: 0.21.0
> Environment: 64-bit and 32 bit JVMs, Java6u14 and jdk7 betas, with
> -XX compressed oops enabled/disabled
> Reporter: Steve Loughran
> Assignee: Steve Loughran
> Priority: Minor
>
> Following up HADOOP-1687, it would be nice to know the size of datatypes in
> under the java16u14 JVM, which offers compressed pointers.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
