Isn't a similar patch required for the TCP BTL ?
Thanks,
george.
On Nov 30, 2007, at 4:59 PM, Jeff Squyres wrote:
Inspired by this thread:
http://www.open-mpi.org/community/lists/users/2007/11/4547.php
Brian kindly donated a patch to make Linux ECONNREFUSED behavior
better in the o
On Nov 30, 2007, at 6:51 PM, Karol Mroz wrote:
A couple other questions we had, and this references an email from a
while back, deals with SCTP BTL exclusivity. I will link the relevant
message below and any advice would be appreciated:
http://www.open-mpi.org/community/lists/devel/2007/11/2609.
On Nov 13, 2007, at 3:41 PM, Brad Penoff wrote:
A question I had was with respect to what to set for the default value
of btl_sctp_exclusivity... I had wanted the exclusivity to be
"slightly less than TCP" so it was available but not the default. In
the code I set btl_sctp_exclusivity to this:
Probably, but there's two main differences:
1) the TCP btl doesn't have the all-to-one startup issue that causes
the ECONNREFUSED when everyone goes back to the head node (doesn't
even do n-to-n, since it's lazy wireup)
2) the TCP btl doesn't squawk about connection retries nearly as often
