Re: [HTCondor-users] job cannot reconnect to starter running MPI

[Todd L Miller <tlmiller@xxxxxxxxxxx>]

> 06/06/17 19:45:06 (1115.0) (2409): Request to run on <10.1.255.217:47300> <10.1.255.217:47300> was ACCEPTED
> 06/06/17 19:47:52 (1115.0) (2409): Can no longer talk to condor_starter <10.1.255.217:47300>
> 06/06/17 19:47:52 (1115.0) (2409): This job cannot reconnect to starter, so job exiting
> 06/06/17 19:47:52 (1115.0) (2409): ERROR "Can no longer talk to condor_starter <10.1.255.217:47300>" at line 208 in file /slots/11/dir_17560/userdir/src/condor_shadow.V6.1/NTreceivers.cpp

	So what this says is that about two minutes into the job, the 
starter either crashed or hung (or the network went away, but that seems 
unlikely), and the shadow doesn't know why.  At this point, it would make 
sense to look at the execute node(s) -- their startd and starter logs -- 
and see what's going on at the same time.

- ToddM