I see. But in branch v1.8, in 31869, Ralph reverted the commit which moved del_procs after the barrier:
"Revert r31851 until we can resolve how to close these leaks without causing the usnic BTL to fail during disconnect of intercommunicators
Also, we need an rte barrier after del_procs - because otherwise rankA could call pml_finalize() before rankB finishes disconnecting from rankA.
I think the order in finalize should be like this:
Link to this post: http://www.open-mpi.org/community/lists/devel/2014/07/15206.php
From: Nathan Hjelm [mailto:firstname.lastname@example.org]
Sent: Monday, July 21, 2014 8:01 PM
To: Open MPI Developers
Cc: Yossi Etigin
Subject: Re: [OMPI devel] barrier before calling del_procs
I should add that it is an rte barrier and not an MPI barrier for technical reasons.
On Mon, Jul 21, 2014 at 09:42:53AM -0700, Ralph Castain wrote:
> We already have an rte barrier before del procs
> Sent from my iPhone
> On Jul 21, 2014, at 8:21 AM, Yossi Etigin <email@example.com> wrote:
> We get occasional hangs with MTL/MXM during finalize, because a global
> synchronization is needed before calling del_procs.
> e.g rank A may call del_procs() and disconnect from rank B, while rank B
> is still working.
> What do you think about adding an MPI barrier on COMM_WORLD before
> calling del_procs()?
> devel mailing list
> Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/devel
> Link to this post:
devel mailing list