[Mono-bugs] [Bug 540857] Call to Futex take close to 2 sec

bugzilla_noreply at novell.com bugzilla_noreply at novell.com
Tue Sep 22 16:04:24 EDT 2009


http://bugzilla.novell.com/show_bug.cgi?id=540857

User sharris at nvidia.com added comment
http://bugzilla.novell.com/show_bug.cgi?id=540857#c3


Sean Harris <sharris at nvidia.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |sharris at nvidia.com




--- Comment #3 from Sean Harris <sharris at nvidia.com>  2009-09-22 14:04:23 MDT ---
Hi Zoltan,

We understand that a futex is a synchronization primitive, that's not why it's
mysterious.  Our code has internal logging that illustrates that our code is
exiting in ~300ms.  After that time, our main function has exited and all of
our threads have terminated.

However, the process just sits waiting doing apparently nothing.  So, the wait
in question is out of our control and not in our code.

Also note that this does not repro on Windows using Mono, but only on SLES10. 
As such, we're convinced that our code has no way to impact this scenario and
thus we are reaching out to you.

In previous versions of Mono, we had experienced issues where Mono would
actually hang permanently when running similar code.  That previous bug is
here:
https://bugzilla.novell.com/show_bug.cgi?id=415608

Can you folks help us to pin down why Mono is behaving this way on Linux only?

Thanks.

Sean Harris
NVIDIA Corporation
(408) 594-1084

-- 
Configure bugmail: http://bugzilla.novell.com/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the QA contact for the bug.
You are the assignee for the bug.


More information about the mono-bugs mailing list