is the code using shared file pointer operations (e.g.
There was a fix which removed a warning/error about not being to delete
the file when using shared file pointer around v.1.2.6 ( I don't
remember precisely when it hit the trunk), and I was wandering whether
that's the message that you see. The message was in reality dealing with
removing a 'hidden' file used for shared file pointer operations
Jeff Squyres wrote:
> After a little digging, I am able to run your code (it looks like it
> expects both an input file and an output file on the command line, or it
> segv's). But I don't get those errors, either with OMPI v1.2.8 or the
> upcoming v1.3 series; I ran with as many as 16 processes across 4 nodes.
> Can you narrow the problem down a bit more? You still didn't provide
> too many details about the problem. :-)
> On Oct 27, 2008, at 5:27 PM, Davi Vercillo C. Garcia (ãã´ã£) wrote:
>> On Mon, Oct 27, 2008 at 6:48 PM, Jeff Squyres <jsquyres_at_[hidden]> wrote:
>>> I can't seem to run your code, either. Can you provide a more precise
>>> description of what exactly is happening? It's quite possible /
>>> that Rob's old post is the answer, but I can't tell from your
>>> original post
>>> -- there just aren't enough details.
>> When I execute this code with more than once process (-n > 1), this
>> error message appear. My code is a distributed compressor, that the
>> compress task is distributed. A single process reads a block from a
>> file, compress it and writes a compressed block to a file.
>>> On Oct 27, 2008, at 3:26 AM, jody wrote:
>>>> Perhaps this post in the Open-MPI archives can help:
>> I already saw this post before, but this didn't help me. I'm not using
>> MPI_File_delete in my code.
>> Davi Vercillo Carneiro Garcia
>> Universidade Federal do Rio de Janeiro
>> Departamento de CiÃªncia da ComputaÃ§Ã£o
>> DCC-IM/UFRJ - http://www.dcc.ufrj.br
>> Grupo de UsuÃ¡rios GNU/Linux da UFRJ (GUL-UFRJ)
>> Linux User: #388711
>> "Theory is when you know something, but it doesn't work. Practice is
>> when something works, but you don't know why.
>> Programmers combine theory and practice: Nothing works and they don't
>> know why." - Anon
>> users mailing list