ofi/common: cannot handle general sessions model #12869
Assignees
Labels
Comments
|
a workaround is to configure ompi with |
|
looks like commit 5432c32 broke sessions support. |
hppritcha
added a commit
to hppritcha/ompi
that referenced
this issue
Oct 18, 2024
With sessions initialization model (section 11.3 of MPI 4 standard) MPI may be initialized and finalized any number of times. This patch refactors code that was assuming a one shot init/finalize sequence for initializing Open MPI and its MCA param space The underlying problem with the replaced code was that an app call MPI_Session_finalize and if there are no more instances active, the MCA param space is destroyed. So if one does not build Open MPI to use dynamically load frameworks, and are using static variables in a way that assumes the MCA param space is always preserved if a static variable is set to some value, then things break if a subsequent MPI_Session_init is invoked. Related to open-mpi#12869 Signed-off-by: Howard Pritchard <[email protected]>
hppritcha
added a commit
to hppritcha/ompi
that referenced
this issue
Oct 18, 2024
With sessions initialization model (section 11.3 of MPI 4 standard) MPI may be initialized and finalized any number of times. This patch refactors code that was assuming a one shot init/finalize sequence for initializing Open MPI and its MCA param space The underlying problem with the replaced code was that when an app calls MPI_Session_finalize and there are no more sessions active, the MCA param space is destroyed. So if one does not build Open MPI to use dynamically load components, and a component is using static variables in a way that assumes the MCA param space is always preserved if a static variable is set to some value, then things break if a subsequent MPI_Session_init is invoked. Related to open-mpi#12869 Signed-off-by: Howard Pritchard <[email protected]>
hppritcha
added a commit
to hppritcha/ompi
that referenced
this issue
Oct 18, 2024
With sessions initialization model (section 11.3 of MPI 4 standard) MPI may be initialized and finalized any number of times. This patch refactors code that was assuming a one shot init/finalize sequence for initializing Open MPI and its MCA param space The underlying problem with the replaced code was that when an app calls MPI_Session_finalize and there are no more sessions active, the MCA param space is destroyed. So if one does not build Open MPI to use dynamically load components, and a component is using static variables in a way that assumes the MCA param space is always preserved if a static variable is set to some value, then things break if a subsequent MPI_Session_init is invoked. Related to open-mpi#12869 Signed-off-by: Howard Pritchard <[email protected]>
hppritcha
added a commit
to hppritcha/ompi
that referenced
this issue
Oct 25, 2024
With sessions initialization model (section 11.3 of MPI 4 standard) MPI may be initialized and finalized any number of times. This patch refactors code that was assuming a one shot init/finalize sequence for initializing Open MPI and its MCA param space The underlying problem with the replaced code was that when an app calls MPI_Session_finalize and there are no more sessions active, the MCA param space is destroyed. So if one does not build Open MPI to use dynamically load components, and a component is using static variables in a way that assumes the MCA param space is always preserved if a static variable is set to some value, then things break if a subsequent MPI_Session_init is invoked. Related to open-mpi#12869 Signed-off-by: Howard Pritchard <[email protected]> (cherry picked from commit 2f4ba1b)
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Looks like some world-model thinking got built into the ofi common code.
See sections 11.2 and 11.3 of the MPI 4.0 standard for a discussion of these two different methods for
initializingMPI.the sessions_init_twice test (https://github.com/open-mpi/ompi-tests/blob/master/ibm/sessions/sessions_init_twice.c) case fails when using OFI MTL currently.
The text was updated successfully, but these errors were encountered: