Hello folks
I see on the LAM Subversion pages that the problem with dropped packets over
Myrinet (as discussed in February) has been fixed for release in 7.1. Because
I'm lazy, I downloaded the nightly snapshot (7.1a1r9601) and tried to compile
it. Alas, I get the message that 'error: GM temporarily disabled while we fix
ptmalloc'. Which revision in the tree has the GM packet dropping fixed and a
reasonably workable ptmalloc?
(In case anyone cares, I regularly get jobs outputing the send timed out error
and hanging. We think that it's because I'm accessing a heavily loaded NFS
server causing one or the other of my MPI processes to block and wait for the
IO to happen, which means that it doesn't participate in the message passing
like it should. Hence the timeout.)
Ciao
Terry
--
Dr Terry Frankcombe
LIC / Theoretical Chemistry
University of Leiden
Postbus 9502, 2300 RA Leiden, The Netherlands
Ph. +31 71 527 4533 Fax +31 71 527 4488
<T.Frankcombe_at_[hidden]>
|
