This unfortunately is characteristic of a memory problem before the
location in the code that actually causes the problem -- i.e., there
was some prior problem that corrupted the heap such that the next time
you call malloc (or the next next time, or the next next next time...),
malloc's internal data structures get hosed and you get a segv or bus
error.
The best step you can do is probably to run this code through a
memory-checking debugger such as Valgrind. This may help you identify
the real memory problem that you're seeing. See the LAM FAQ for
information on general debugging and using memory-checking debuggers.
On Jul 4, 2005, at 7:02 AM, Kalle Happonen wrote:
> Hello all,
> I have a problem running lam 7.1.1. I use the standard debian package
> on an Athlon.
> Since mpich doesn't send the command line arguments to all processes
> and
> my program depends on it, I've written a function where rank 0
> broadcasts the arguments to all other ranks.
>
> For some reason my progam usually segfaults when receiving the
> arguments. I've traced the error to a malloc in my own code, and it is
> the malloc itself that causes the segfault, not a uninitialized pointer
> on my end. This only happens with lam (mpich works fine). Also if I
> vary
> the length of the arguments the program might work or then crash at a
> later time. And it seems like if I allocate something like 1000 bytes /
> argument it doesn't crash at all.
>
> Can anyone shed light on this one?
>
> laminfo output:
>
> LAM/MPI: 7.1.1
> Prefix: /usr/lib/lam
> Architecture: i386-pc-linux-gnu
> Configured by: camm
> Configured on: Tue Mar 22 16:49:24 UTC 2005
> Configure host: intech19
> Memory manager: ptmalloc2
> C bindings: yes
> C++ bindings: yes
> Fortran bindings: yes
> C compiler: i386-linux-gcc
> C++ compiler: i386-linux-g++
> Fortran compiler: g77
> Fortran symbols: double_underscore
> C profiling: yes
> C++ profiling: yes
> Fortran profiling: yes
> C++ exceptions: no
> Thread support: yes
> ROMIO support: yes
> IMPI support: no
> Debug support: no
> Purify clean: no
> SSI boot: globus (API v1.1, Module v0.6)
> SSI boot: rsh (API v1.1, Module v1.1)
> SSI boot: slurm (API v1.1, Module v1.0)
> SSI coll: lam_basic (API v1.1, Module v7.1)
> SSI coll: shmem (API v1.1, Module v1.0)
> SSI coll: smp (API v1.1, Module v1.2)
> SSI rpi: crtcp (API v1.1, Module v1.1)
> SSI rpi: lamd (API v1.0, Module v7.1)
> SSI rpi: sysv (API v1.0, Module v7.1)
> SSI rpi: tcp (API v1.0, Module v7.1)
> SSI rpi: usysv (API v1.0, Module v7.1)
> SSI cr: self (API v1.0, Module v1.0)
>
>
> Thanks,
> Kalle Happonen
> _______________________________________________
> This list is archived at http://www.lam-mpi.org/MailArchives/lam/
>
--
{+} Jeff Squyres
{+} jsquyres_at_[hidden]
{+} http://www.lam-mpi.org/
|
