[Carpet] Problems with checkpoint recovery on AMD machine

Erik Schnetter schnetter at cct.lsu.edu
Thu Apr 26 07:23:42 CEST 2007


On Apr 23, 2007, at 13:50:43, Yosef Zlochower wrote:

> MPIRUN: 31 ranks have not yet exited 60 seconds after rank 2 (node
> n016.cluster) exited without reaching MPI_Finalize().

Yosef,

this seems to indicate that the problem appears with the 3rd  
horizon.  I think you showed output from the root processor, which is  
for the 1st horizon.  You need to use the option "-roe" to look at  
the output coming from the other processors, especially from rank 2.

-erik

-- 
Erik Schnetter <schnetter at cct.lsu.edu>

My email is as private as my paper mail.  I therefore support encrypting
and signing email messages.  Get my PGP key from www.keyserver.net.



-------------- next part --------------
A non-text attachment was scrubbed...
Name: PGP.sig
Type: application/pgp-signature
Size: 186 bytes
Desc: This is a digitally signed message part
Url : /archives/developers/attachments/20070426/c76484eb/attachment.pgp 


More information about the developers mailing list