Welcome to MilkyWay@home

Posts by hristo

1) Message boards : News : Nbody Release 1.54 (Message 64299)
Posted 4 Feb 2016 by hristo
Post:
Hello Sidd,

my comment is written here http://milkyway.cs.rpi.edu/milkyway/forum_thread.php?id=3885&postid=64297

about some handles leak in windows xp 64 bit.
2) Message boards : Application Code Discussion : Maybe a bug or very high number of handles opened, please discuss (Message 64298)
Posted 4 Feb 2016 by hristo
Post:
To add

It did finish normally.

For about combine of 8 hours or real 2 hours cpu time.
At 27MB of used memory and

More than 300 000 handles opened.

This is a leak of handles I think.
3) Message boards : Application Code Discussion : Maybe a bug or very high number of handles opened, please discuss (Message 64297)
Posted 4 Feb 2016 by hristo
Post:
I observe that executable milkyway_nbody_1.54_windows_x86_64__mt.exe produces very large number of handles at 55% more than 220000. But it will probably finish normally.

On windows xp 64 bit

On work unit
2/4/2016 9:00:59 PM | Milkyway@Home | Starting task ps_nbody_1_29_16_orphansim_3_v154_1453826702_173800_1



with text in stderr.txt:
///
<search_application> milkyway_nbody 1.54 Windows x86_64 double OpenMP, Crlibm </search_application>
Using OpenMP 4 max threads on a system with 4 processors
Could not load Ktm32.dll (126): The specified module could not be found.
///


This indicate some application programing problem as suggested in

https://blogs.technet.microsoft.com/markrussinovich/2009/09/29/pushing-the-limits-of-windows-handles/

"...Any process that has more than a ten thousand handles open at any given point in time is likely either poorly designed or has a handle leak, so a limit of 16 million is essentially infinite and can simply help prevent a process with a leak from impacting the rest of the system. ..."




©2024 Astroinformatics Group