Open MPI logo

Open MPI User's Mailing List Archives

  |   Home   |   Support   |   FAQ   |   all Open MPI User's mailing list

Subject: Re: [OMPI users] Checkpoint and restart
From: Josh Hursey (jjhursey_at_[hidden])
Date: 2008-07-22 07:27:41


On Jul 22, 2008, at 5:43 AM, Gabriele Fatigati wrote:

> Dear OpenMPI developers,
> i have some questions about application robustness. , I have read
> that in OpenMPI development trunk version will have implemented
> techniques of checkpoint and restart. But, i need to know ho this
> techniques works. Are they internal functions to insert in my code,
> external tool or other?

The checkpoint/restart technique is transparent so there are no
functions to insert into your code. The functionality is described in
the user document on the wiki:
   https://svn.open-mpi.org/trac/ompi/wiki/ProcessFT_CR

>
>
> And, when i restart my application, is it possible to modify the
> initial number of processors?

Not at this time. You must restart with the same number of processes
(-np) as you initially started with.

-- Josh

>
>
> --
> Gabriele Fatigati
>
> CINECA Systems & Tecnologies Department
>
> Supercomputing Group
>
> Via Magnanelli 6/3, Casalecchio di Reno (BO) Italy
>
> www.cineca.it Tel: +39 051 6171722
>
> g.fatigati_at_[hidden]
> _______________________________________________
> users mailing list
> users_at_[hidden]
> http://www.open-mpi.org/mailman/listinfo.cgi/users