High level questions about sampling profiler

[Yang Zhang]

Hi, I have a few high-level questions about the internals sample based
profiling.

If I understand correctly, the Netbeans Profiler currently has a
sampling profiler, but instrumentation is still required for some
reason. Why is instrumentation required? Will the Netbeans Profiler
ever feature a pure sampling based profiler?

Currently, when the results show that a method is taking up n% of the
CPU time, does that mean it's appearing in n% of all sampled stack
traces? Or in n% of the samples?

How do you differentiate among stack traces of threads that are
blocking, that are executing, and that are executable but not executing?
How do multiple CPUs factor in?

How does the sampling profiler work - does it use

- Thread.getAllStackTraces(),
- ThreadMXBean (getAllThreadIds(), getThreadInfo()), or
- JVMTI?

If using JVMTI, do you use GetStackTrace() or AsyncGetCallTrace()[1]?

Thanks in advance for any answers!

[1]
http://jeremymanson.blogspot.com/2007/05/profiling-with-jvmtijvmpi-sigprof-and.html
--
Yang Zhang
http://www.mit.edu/~y_z/

---------------------------------------------------------------------
To unsubscribe, e-mail: address-removed
For additional commands, e-mail: address-removed

[SebTardif]

Did you get some answers? I have the same questions.

[preety]

Hi,

Need to know the same, if finding any, do reply us.