On Jul 4, 2006, at 1:58 AM, Manal Helal wrote:

sorry for posting too much, I tried running and I got this error, I
assume that this is the stack of the calls before the error

Signal:11 info.si_errno:0(Success) si_code:2(SEGV_ACCERR)
Failing at addr:0x8059b73
[0] func:/usr/local/bin/openmpi/lib/libopal.so.0 [0xb7e76ed0]
[1] func:[0xffffe440]
[2] func:/lib/tls/i686/cmov/libc.so.6(_IO_vfprintf+0x34b1) [0xb7d283a1]
[3] func:/lib/tls/i686/cmov/libc.so.6(vsprintf+0x8b) [0xb7d4041b]
[4] func:/lib/tls/i686/cmov/libc.so.6(sprintf+0x2b) [0xb7d2d76b]
[5] func:./moaDist(mprintf+0x4a) [0x8056e96]
[6] func:./moaDist(processArguments+0x90c) [0x804d60c]
[7] func:./moaDist(main+0x197) [0x804aa4b]
[8] func:/lib/tls/i686/cmov/libc.so.6(__libc_start_main+0xd2)
[0xb7cfeea2]
[9] func:./moaDist [0x804a079]
*** End of error message ***

I am not sure if its an IO error; I tried on the web site to search the mailing archives, but it takes me to google search, and I am not sure if
there is any documentation to understand the error messages,

The error is that the application caused a segmentation fault. From the stack trace, it appears that the error occurred within the internals of sprintf, called from the mprintf function in your application. This doesn't look like an Open MPI error, but something wrong with the application. One common issue when sprintf is involved is not having a big enough buffer for the output string. I'd recommend running your application under a debugger or under a memory checking debugger like Valgrind. That should help find the problem.


Hope this helps,

Brian

--
  Brian Barrett
  Open MPI developer
  http://www.open-mpi.org/


Reply via email to