[mpich-discuss] bug in MPI_File_write_all?

[CANELA-XANDRI Oriol]

Ok, so it seems a problem with parallel access to this file system. Other network file systems like NFS, for instance, should not be a problem, right?

Do you know if there is some method just for checking that this kind of problems will not arise in a particular system (with an 'unknown' file system)?

Many thanks,

Oriol


-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.


-----Original Message-----
From: discuss-bounces at mpich.org [mailto:discuss-bounces at mpich.org] On Behalf Of Rob Latham
Sent: 20 May 2014 16:01
To: discuss at mpich.org
Subject: Re: [mpich-discuss] bug in MPI_File_write_all?



On 05/20/2014 09:37 AM, CANELA-XANDRI Oriol wrote:
> I am writing on a sshfs... Now, I tried on the 'local' disk (I am inside a virtual machine) and there seems that works ok. So, the problem is related with the sshfs?

sshfs and other fuse-based file systems have page-based accesses.  If two processes attempt to write different parts of the same page, it might not be clear who should win.

I don't know the exact details of the ssshfs/fusefs consistency semantics, but apparently they are not adequate for parallel access.

==rob

--
Rob Latham
Mathematics and Computer Science Division Argonne National Lab, IL USA _______________________________________________
discuss mailing list     discuss at mpich.org
To manage subscription options or unsubscribe:
https://lists.mpich.org/mailman/listinfo/discuss