[aspect-devel] Fwd: [cse.ucdavis.edu #13562] Fwd: Fwd: error when writing checkpoint files

Wolfgang Bangerth bangerth at colostate.edu
Fri Jul 6 20:23:36 PDT 2018


Magali & Bill,

> Is there a way to write checkpointing files without uses MPI -I/O?
> 
> Is the trickery involved in writing the checkpointing files such that I should 
> ask Bill (cc’d on this email) to enable MPI-IO?
> That is, even though Bill says is generally incompatible with the NFS file 
> system, should it work?

I don't know whether we really want to support systems that don't have MPI-IO. 
You're the first person to report a cluster where this doesn't work. I have no 
idea how MPI-IO is internally implemented (e.g., whether really every 
processor opens the same file at the same time, using file system support; or 
whether all MPI processes send their data to one process that then does the 
write), but the only way to achieve scalability is to use MPI-IO.

At any rate, it would require workarounds both in p4est and deal.II to avoid 
MPI-IO. p4est appears to already have that, but deal.II does not.

There is also the issue that I don't really know how we would determine 
whether MPI-IO is available. I can't see an automatic test working; it would 
have to be a switch one provides by hand.


So what I'm trying to say is that our preference would be for your clusters to 
learn how to use MPI-IO :-)

Best
  W.

-- 
------------------------------------------------------------------------
Wolfgang Bangerth          email:                 bangerth at colostate.edu
                            www: http://www.math.colostate.edu/~bangerth/



More information about the Aspect-devel mailing list