[Pw_forum] Restarting PWSCF - usability issues

Paolo Giannozzi giannozz at nest.sns.it
Fri Mar 12 21:15:52 CET 2004


On Thursday 11 March 2004 20:23, Konstantin Kudin wrote:

> Also, if node A has the old *.wfc* files, and node B does not,
>  then the code hangs forever. I guess the nodes wait for B to 
> read in the *wfc* file, which never happens since that file
> does not exist.

I an not 100% sure, but I am quite confident that node B does 
the right thing, i.e. it stops and calls the error routine, which
aborts MPI among other things. In MPI refuses to die, as it
used to happen (and apparently still happens :-) on the SP3
in Princeton, there is little we can do. So i take exception to
your last statement:

> So this is another bug.

Paolo

-- 
Paolo Giannozzi             e-mail:  giannozz at nest.sns.it
Scuola Normale Superiore    Phone:   +39/050-509876, Fax:-563513 
Piazza dei Cavalieri 7      I-56126 Pisa, Italy




More information about the Pw_forum mailing list