[mpi-21] Ballot 4 - MPI_File_set_info update or replacement

Thu Jan 31 11:29:41 CST 2008

The intent is that if the user calls MPI_File_set_info (or
MPI_File_set_view) twice, the 2nd call will only update (if possible) the
key-vals passed in the 2nd call; others are unmodified. If the 2nd call
passes MPI_INFO_NULL, nothing will change -- it won't nullify previously
passed hints.

Rajeev

  _____  

From: mpi-21-bounces_at_[hidden] [mailto:mpi-21-bounces_at_[hidden]] On
Behalf Of Richard Treumann
Sent: Thursday, January 31, 2008 9:23 AM
To: Mailing list for discussion of MPI 2.1
Subject: Re: [mpi-21] Ballot 4 - MPI_File_set_info update or replacement

I think we have an overall ambiguity about what the "current set of hints"
is. This ambiguity is evident in the question about what MPI_FILE_INFO_GET
returns and in this discussion too. If an implementation supports 5 file
hints then it must select a value for each of these hints an MPI_FILE_OPEN.
If there is an MPI_Info that stipulates 2 of the hints then how many hints
are in the "current set of hints"? 2 or 5? I would say there are 5 and I
think it makes sense for MPI_FILE_GET_INFO to return all 5 (key,value)
pairs.

Two more specific points -

1) I would expect that if at MPI_FILE_OPEN the implementation is given
non-default hints ("A","yes") and ("B","no") and then at MPI_FILE_INFO_SET
is given ("B","yes") the net effect is that hint "A" remains as set and hint
"B" is altered (if possible). If there is a hint "C" which has never been
mentioned it will have received a default value at MPI_FILE_OPEN and the
MPI_FILE_INFO_SET which does not mention "C" will leave that default
unchanged.

Is the "clarification" saying hint "A" must return to default when
MPI_FILE_INFO_SET fails to mention it? If that is the intent then I need to
be convinced. If we decide this is to be blessed then we probably need to
say that any use of MPI_FILE_SET_INFO must first call MPI_FILE_GET_INFO,
tweek the INFO it gets back from MPI_FILE_GET_INFO and pass that to
MPI_FILE_SET_INFO to avoid unexpected changes to the set of hints that is
"in effect".

2) Since a hint is a hint, not a command, it can be rejected. It is possible
that some hint can be honored at MPI_FILE_OPEN but once it has been honored,
cannot be altered at reasonable cost. 

For example, maybe somebody's MPI_FILE_OPEN could accept a hint
("buffer_size", "dynamic-64MB") meaning "start with a 64MB buffer but be
prepared to accept changes to buffer size". If the user has set hint
("buffer_size", "64MB") at FILE_OPEN, the implelentation would omit whatever
synchs are needed to preserve the ability to change on the fly. Passing
("buffer_size", "dynamic-16MB") to MPI_FILE_SET_INFO could be honored if the
user had chosen "dynamic" at FILE_OPEN but would need to be ignored if he
had not.

For most implementations, a hint like "buffer_size" could not be honored at
all after the first file read or write had been done.

Dick Treumann - MPI Team/TCEM 
IBM Systems & Technology Group
Dept 0lva / MS P963 -- 2455 South Road -- Poughkeepsie, NY 12601
Tele (845) 433-7846 Fax (845) 433-8363

mpi-21-bounces_at_[hidden] wrote on 01/31/2008 08:24:51 AM:

> This is a proposal for MPI 2.1, Ballot 4.
> 
> I'm asking especially the implementors to check, whether
> this interpretation is implemented in their MPI implementations,
> or does not contradict to the existing implementation.
> 
> This is a follow up to:
>   MPI_File_set_info
>   in http://www.cs.uiuc.edu/homes/wgropp/projects/parallel/MPI/mpi-
> errata/index.html
> with mail discussion not yet existing
> ___________________________________
> 
> Proposal:
> Add in MPI-2.0 Sect. 9.2.8, File Info, page 218, after line 18 the 
> following sentences:
> 
>   With MPI_FILE_SET_VIEW and MPI_FILE_SET_INFO the current setting
>   of all hints used by the system to this open file is updated by 
>   the (key,value) pairs in the info argument.
> ___________________________________
> Rationale for this clarification:
>   This text was missing. It was not clear, whether a info handles
>   in MPI_FILE_SET_VIEW and MPI_FILE_SET_INFO are updating or replacing
>   the current set of used hints. 
>   The developers from ROMIO decided to update the current set of used
hints.
>   Therefore, this behavior should be the expected behavior of a majority
>   of users.
> ___________________________________
> 
> Best regards
> Rolf
> 
> 
> 
> 
> Dr. Rolf Rabenseifner . . . . . . . . . .. email rabenseifner_at_[hidden]
> High Performance Computing Center (HLRS) . phone ++49(0)711/685-65530
> University of Stuttgart . . . . . . . . .. fax ++49(0)711 / 685-65832
> Head of Dpmt Parallel Computing . . . www.hlrs.de/people/rabenseifner
> Nobelstr. 19, D-70550 Stuttgart, Germany . (Office: Allmandring 30)
> _______________________________________________
> mpi-21 mailing list
> mpi-21_at_[hidden]
> http://lists.cs.uiuc.edu/mailman/listinfo/mpi-21

* 
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mpi-forum.org/pipermail/mpi-21/attachments/20080131/6d1d054b/attachment.html>