ulfm-devel / ompi

Open MPI main development repository
https://www.open-mpi.org
Other
0 stars 0 forks source link

nextcid_nb not interrupted by failures/revokes #25

Closed abouteiller closed 6 years ago

abouteiller commented 6 years ago

Original report by Aurelien Bouteiller (Bitbucket: abouteiller, GitHub: abouteiller).


As part of the fix to fix shrink being revoked, I introduced a new bug in which nextcid_nb is not properly stopped by failures.

This manifest with deadlocks in COMM_DUP/SPLIT/SPAWN and friends when a failure pre-exist on the input comm.

abouteiller commented 6 years ago

Original comment by Aurelien Bouteiller (Bitbucket: abouteiller, GitHub: abouteiller).


Revolved by

d04eb935

3ab5df55

2609388a