Inconsistent problem running longer tests with SOM on cheyenne with gnu compiler segfault

Open
#20 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Assessment

Difficulty
4/5
Estimated time
3-5 days
Newbie friendliness
25/100
Issue type
Bug
Clarity
Needs clarification
Activity status
Stale
Tech stack
fortran
Domain
hpc

Research direction

Start with the SMS_Lm3_D.f19_g16.H_MML_2000_CAM5_BGC.cheyenne_gnu.clm-global_uniform_g16_SOM configuration and the cesm.log segmentation-fault output. Reproduce the long GNU SOM run and compare it with the reported Intel, debug, and short tests; done means the intermittent segfault is resolved or its cause is isolated and documented.

Written by the indexing model from the issue text.

Description

bug

I'm getting an inconsistent problem with SMS_Lm3_D.f19_g16.H_MML_2000_CAM5_BGC.cheyenne_gnu.clm-global_uniform_g16_SOM. It has segfaulted after running for a short period of time, but at an inconsistent time. The first time was 9-steps and the second was after 2105 timesteps.

I also ran debug and short tests without debug for both intel and gnu that all worked. Including a DEBUG 3-month test.

Here's the error from cesm.log

Program received signal SIGSEGV: Segmentation fault - invalid memory reference.

Backtrace for this error:
#0  0x2b115b7a494f in ???
#1  0x2b116cc1781d in ???
#2  0x2b115c027af3 in ???
#3  0x2b115ae31bcc in ???
#4  0x2b115ae7078e in ???
#5  0x2b115abd4100 in ???
#6  0xcbe0a9 in ???
#7  0xd4d312 in ???
#8  0xd42762 in ???
#9  0xd31728 in ???
#10  0xca0f76 in ???
#11  0xca18ce in ???
#12  0xc2bdff in ???
#13  0x420f2b in ???
#14  0x40a7aa in ???
#15  0x42014b in ???
#16  0x2b115b7906e4 in ???
#17  0x407268 in ???
        at ../sysdeps/x86_64/start.S:118
#18  0xffffffffffffffff in ???
-------------------------------------------------------
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 101 with PID 37244 on node r13i7n32 exited on signal 11 (Segmentation fault).

This is running with d1ed49c24fd6b9e0cc55cb60465ca037cc9838ec which I haven't pushed yet, but will. But, I also don't think it's necessarily anything in the new code which is just removing unused code.

Dominant language
Fortran
Stars
15
Forks
9
PR merge metrics
No merged PRs in 30d

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from ESCOMP/SimpleLand

All issues in ESCOMP/SimpleLand

Similar issues

More HPC issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.