Bug #87

MPI deadlock when MPI process is killed.

Added by Stefan Blom about 11 years ago. Updated over 6 years ago.

Status:NewStart date:05 Jun 2009
Priority:NormalDue date:
Assignee:Stefan Blom% Done:

0%

Category:toolsSpent time:-
Target version:ltsmin-2.1

Description

If one of the MPI processes is killed then using the current recommended settings for OpenMPI the mpi program will end up in a deadlock situation. This is wrong, if this happens then the whole application shoud terminate.

This is of course a bug in MPI rather than in LTSmin,
but by adding deadlock detection we can make certain
that we terminate.

History

#1 Updated by Stefan Blom about 9 years ago

  • Assignee deleted (Stefan Blom)

#2 Updated by Alfons Laarman about 8 years ago

HREexit / HREabort facilities do not close down the comm channels in hre_pthread

#3 Updated by Alfons Laarman over 7 years ago

  • Category set to tools
  • Target version set to ltsmin-2.1

#4 Updated by Alfons Laarman over 6 years ago

  • Assignee set to Stefan Blom

Also available in: Atom PDF