Brock Palen wrote:
Ok it looks like a bigger problem. The segfault is not related to
OMPI because when I go and rebuild 1.2 or another version we use with
IB all the time, it will now fail with a segfault when forcing IB.
The old libs of the same version still work. They of-course do not
ha
Ok it looks like a bigger problem. The segfault is not related to
OMPI because when I go and rebuild 1.2 or another version we use with
IB all the time, it will now fail with a segfault when forcing IB.
The old libs of the same version still work. They of-course do not
have the flag to t
On Jul 2, 2008, at 11:51 PM, Pavel Shamis (Pasha) wrote:
In trying to build 1.2.6 with the pgi compilers it makes an MPI
library that works with tcp, sm. But it segfaults on openib.
Both our intel compiler version and pgi version of 1.2.6 blow up
like this when we force IB. So this is a n
Check out this FAQ entry:
http://www.open-mpi.org/faq/?category=tcp#tcp-routability
We've long-since talked about adding an MCA param to tell Open MPI
"just assume all TCP addresses are reachable from each other" for
cases similar to yours, but it unfortunately hasn't happened yet. :-(
Hi,
To answer your question 172.x.y.z are not behind a NAT .
Moreover, I check the netstat command on the remote host and it seems like
the connection is ok
tcp0 0 10.160.x.x:39794172.x.y.z:50858
ESTABLISHED 20956/orted
unix 3 [ ] STREAM CONNECTED 763
In trying to build 1.2.6 with the pgi compilers it makes an MPI
library that works with tcp, sm. But it segfaults on openib.
Both our intel compiler version and pgi version of 1.2.6 blow up like
this when we force IB. So this is a new issue.
I have ompi 1.2.6 installed on my machines with I
