SIGTSTP propagation for 0.80 ?

[David Golden]

On 2005-09-21 08:55:38 +1000, Chris Samuel wrote:
> On Wed, 21 Sep 2005 01:00 am, Pete Wyckoff wrote:
> 
> > The nice thing about mpiexec and other TM-aware launchers is that
> > PBS always retains control of all aspects of the job and can do
> > accounting properly, cleanup on exit nicely, launch quickly, etc.
> 
> I guess the problem is more those launchers that aren't TM aware, and 
> unfortunately they tend to be the ones used in commercial codes that use 
> MPICH.  :-(
>
Indeed. I just posted to torqueusers [1] about signal propagation behaviours 
as queue/job attributes in a bit more depth, such a feature might at 
least solve some such problems, barring that whole horrible 
processes-wandering-out-of-pgrps thing that you probably need 
selinux and/or sgi csa/pagg stuff to deal with on linux.

[1] http://www.supercluster.org/pipermail/torqueusers/2005-September/002176.html