[mpich-discuss] MPI_Probe exception from Windows cluster

[Feng Yue]

Hi all,

We are experiencing frequent exceptions from MPI_Probe recently. Does anybody know what cause might be for this exception and what I can do to track down the cause?

MPI_Probe(113).......................: MPI_Probe(src=MPI_ANY_SOURCE, tag=MPI_ANY_TAG, comm=0x84000002, status=000000033FA217C8) failed
MPIDI_CH3I_Progress(402).............:
MPID_nem_mpich2_blocking_recv(905)...:
MPID_nem_newtcp_module_poll(37)......:
MPID_nem_newtcp_module_connpoll(2656):
gen_read_fail_handler(1145)..........: read from socket failed - The specified network name is no longer available.

Our cluster has MPICH2 1.4.1p1 and Windows Server 2008 R2 installed on 22 slave nodes and 1 master node.

Thanks,
Feng

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpich.org/pipermail/discuss/attachments/20170306/cae17687/attachment.html>
-------------- next part --------------
_______________________________________________
discuss mailing list     discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss