Learning Forum

[maheshwarj]

I'm trying to run an LS-DYNA simulation on a SLURM-based high-performance cluster (HPC). When I submit my job, the LS-DYNA simulation starts, reads in all the files, and throws a buffer overflow error. The HPC submission script, D3HSP, slurm output files are attached for reference.nPlease let me know how to solve this issue at the earliest!n

[Erik Kostson]

As we are not allowed to open attachments can you put the main error messages inline in a post so our LS-Dyna experts e.g, Array can view them and perhaps provide some feedback.

Thank you

Erik

[maheshwarj]

The error message is as follows:
******************************************************************************************************************
 Memory required to process keyword   : 121241977  
 Additional dynamic memory required   :  63112089  
 MPP execution with   12 procs
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
*** buffer overflow detected ***: ls-dyna_mpp_d_R12_0_0_x64_redhat54_ifort160_sse2_openmpi4.0.0 terminated
forrtl: error (76): Abort trap signal
Image       PC        Routine      Line    Source       
ls-dyna_mpp_d_R12 000000000C326F65 Unknown        Unknown Unknown
ls-dyna_mpp_d_R12 000000000C324B87 Unknown        Unknown Unknown
ls-dyna_mpp_d_R12 000000000C27F104 Unknown        Unknown Unknown
ls-dyna_mpp_d_R12 000000000C27EF16 Unknown        Unknown Unknown
ls-dyna_mpp_d_R12 000000000C2193F6 Unknown        Unknown Unknown
ls-dyna_mpp_d_R12 000000000C21FFB8 Unknown        Unknown Unknown
libpthread.so.0  00007FFFF6583DD0 Unknown        Unknown Unknown
libc.so.6     00007FFFF56FB70F Unknown        Unknown Unknown
libc.so.6     00007FFFF56E5B25 Unknown        Unknown Unknown
libc.so.6     00007FFFF573E897 Unknown        Unknown Unknown
libc.so.6     00007FFFF57D1905 Unknown        Unknown Unknown
libc.so.6     00007FFFF57D1937 Unknown        Unknown Unknown
libc.so.6     00007FFFF57CF8F6 Unknown        Unknown Unknown
libc.so.6     00007FFFF57CEF5F Unknown        Unknown Unknown
libc.so.6     00007FFFF5742CC1 Unknown        Unknown Unknown
libc.so.6     00007FFFF5715158 Unknown        Unknown Unknown
libc.so.6     00007FFFF57CF003 Unknown        Unknown Unknown
libc.so.6     00007FFFF57CEF2E Unknown        Unknown Unknown
--------------------------------------------------------------------------
Primary job terminated normally, but 1 process returned
a non-zero exit code. Per user-direction, the job has been aborted.
--------------------------------------------------------------------------
--------------------------------------------------------------------------
mpirun noticed that process rank 4 with PID 2323243 on node m-4-09 exited on signal 6 (Aborted).
--------------------------------------------------------------------------
******************************************************************************************************************

[maheshwarj]

Array Array
Any updates on this?

[tslavik]

We've seen this occur when trying to force to a background process (i.e., re-direct stdout). If that's what is happening in your case, there is no solution or work-around. Simply, don't do it.

[udoz]

.

Today I had a similar Problem with ls-dyna-mpp. same "buffer overflow" Message.

Found that even just calling

ssh /ls-dyna_smp_d_R12_0_0_x64_redhat65_ifort160 i=xxx.k

had the message

*** buffer overflow detected *** ls-dyna_smp_d_R12_0_0_x64_redhat65_ifort160 terminated

Also true for other versions.

My Solution was changing my ssh-config locally:

echo "RequestTTY force" >> ~/.ssh/config

chmod 600 ~/.ssh/config

Alternative "ssh -t" ...

.