Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Bus errors on mips64el during tests #258

Closed
olebole opened this issue Jan 2, 2021 · 1 comment
Closed

Bus errors on mips64el during tests #258

olebole opened this issue Jan 2, 2021 · 1 comment

Comments

@olebole
Copy link
Member

olebole commented Jan 2, 2021

During recent rebuilds of the sopt Debian package, I observe a number of bus errors when running the tests:

      Start 19: communicator
16/22 Test #19: communicator .....................Bus error***Exception:   0.50 sec
[mipsel-sil-01:23729] *** Process received signal ***
[mipsel-sil-01:23729] Signal: Bus error (10)
[mipsel-sil-01:23729] Signal code:  (128)
[mipsel-sil-01:23729] Failing at address: (nil)
[mipsel-sil-01:23729] *** End of error message ***

      Start 20: serial_vs_parallel_padmm
17/22 Test #20: serial_vs_parallel_padmm .........Bus error***Exception:   0.42 sec
[mipsel-sil-01:23736] *** Process received signal ***
[mipsel-sil-01:23736] Signal: Bus error (10)
[mipsel-sil-01:23736] Signal code:  (128)
[mipsel-sil-01:23736] Failing at address: (nil)
[mipsel-sil-01:23736] *** End of error message ***

      Start 21: mpi_wavelets
18/22 Test #21: mpi_wavelets .....................Bus error***Exception:   0.44 sec
[mipsel-sil-01:23743] *** Process received signal ***
[mipsel-sil-01:23743] Signal: Bus error (10)
[mipsel-sil-01:23743] Signal code:  (128)
[mipsel-sil-01:23743] Failing at address: (nil)
[mipsel-sil-01:23743] *** End of error message ***

      Start 22: mpi_session
19/22 Test #22: mpi_session ......................Bus error***Exception:   0.34 sec
[mipsel-sil-01:23750] *** Process received signal ***
[mipsel-sil-01:23750] Signal: Bus error (10)
[mipsel-sil-01:23750] Signal code:  (128)
[mipsel-sil-01:23750] Failing at address: (nil)
[mipsel-sil-01:23750] *** End of error message ***

Full build log here. I will try to run it in gdb to get more detailed info here. Similarly, I get errors on HP-PA (same tests, but the message is "ILLEGAL").

This is also reported as Debian#979085, with the following additional comment by @zshj:

The failed tests seem all related mpi, so I think it's not related to spdlog or fmtlib. openmpi bumped its version from 4.0.5 to 4.1.0 on 2020-12-21. I guess it's related to this change of openmpi.

@olebole
Copy link
Member Author

olebole commented Jan 5, 2021

It looks like that the problem is in MPI and not in sopt, so I am closing this. See the Debian bug for further development.

@olebole olebole closed this as completed Jan 5, 2021
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant