afternoon again, it might be friday until I can digg into that.
Was there any progress with this? Otherwise, what version of PVFS2 is
known to work with OMPI 1.6? Thanks.
Edgar, should I pick this up for MPICH, or was this fix specific to
OpenMPI ?
==rob
--
Rob Latham
Mathematics and Computer
that only matters
if ROMIO uses extended generalized requests. I trust ticket #1159 is
still accurate?
https://svn.open-mpi.org/trac/ompi/ticket/1159
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
off data sieving writes, which is what I would have first
guessed would trigger this lock message. So I guess you are hitting one
of the other cases.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
rg
http://www.open-mpi.org/mailman/listinfo.cgi/users
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
t;31 bit transfers"
fixes went into the MPICH-3.1 release. Slurping those changes, which
are individually small (using some _x versions of type-inquiry routines
here, some MPI_Count promotions there) but pervasive, might give OpenMPI
a bit of a headache.
==rob
Thanks,
Richard
On 7 May
On 05/07/2014 11:36 AM, Rob Latham wrote:
On 05/05/2014 09:20 PM, Richard Shaw wrote:
Hello,
I think I've come across a bug when using ROMIO to read in a 2D
distributed array. I've attached a test case to this email.
Thanks for the bug report and the test case.
I've o
just
get segfaults.
Thanks,
Richard
___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
On 05/07/2014 11:36 AM, Rob Latham wrote:
On 05/05/2014 09:20 PM, Richard Shaw wrote:
Hello,
I think I've come across a bug when using ROMIO to read in a 2D
distributed array. I've attached a test case to this email.
Thanks for the bug report and the test case.
I've o
ess rank 2 with PID 13969 on node oriol-VirtualBox
exited on signal 6 (Aborted).
--
___
users mailing list
us...@open-mpi.org
http://www.open-mpi.org/mailman/listinfo.cgi/users
i.org/mailman/listinfo.cgi/users
Link to this
post:http://www.open-mpi.org/community/lists/users/2014/07/24793.php
___
users mailing list
us...@open-mpi.org
Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users
Link to this post:
http:/
on Microsoft's intentions regarding MPI and
C99/C11 (just dreaming now).
hey, (almost all of) c99 support is in place in visual studio 2013
http://blogs.msdn.com/b/vcblog/archive/2013/07/19/c99-library-support-in-visual-studio-2013.aspx
==rob
On 2014-07-17 11:42 AM, Jed Brown wrote:
Rob Lath
c))
which (if I am reading fortran correctly) is a contiguous chunk of memory.
If instead you had a more elaborate data structure, like a mesh of some
kind, then passing an indexed type to the read call might make more sense.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
OpenMPI to pick up all
the bits...
As with Lustre, I don't have access to a PLFS system and would welcome
community contributions to integrate and test PLFS into ROMIO.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
mio resync. You are on your own with ompio!
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
mpich 3.1.2 , I don't see those issues.
Thanks,
Mohamad
___
users mailing list
us...@open-mpi.org
Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users
Link to this post:
http://www.open-mpi.org/community/lists/users/2014/08/24931.php
-
ity/lists/users/2014/08/24931.php
___
users mailing list
us...@open-mpi.org
Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users
Link to this post:
http://www.open-mpi.org/community/lists/users/2014/08/24963.php
--
Rob Latham
Mathematics and
orge.
On Mon, Aug 11, 2014 at 9:44 AM, Rob Latham mailto:r...@mcs.anl.gov>> wrote:
On 08/10/2014 07:32 PM, Mohamad Chaarawi wrote:
Update:
George suggested that I try with the 1.8.2 rc3 and that one
resolves the
hindexed_block segfault that I was seei
ink to this post:
http://www.open-mpi.org/community/lists/users/2014/08/25130.php
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
construct an HINDEXED type
(or with very new MPICH, HINDEXED_BLOCK) and send that instead of copying.
==rob
On Fri, Aug 22, 2014 at 3:38 PM, Rob Latham mailto:r...@mcs.anl.gov>> wrote:
On 08/22/2014 10:10 AM, Saliya Ekanayake wrote:
Hi,
I've a quick questi
PI?
Thx.John Cary
___
users mailing list
us...@open-mpi.org
Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users
Link to this post:
http://www.open-mpi.org/community/lists/users/2014/09/25311.php
--
Rob Latham
Mathematics and Computer Science Divisio
h this approach doesn't need RMA shared memory.
==rob
Thanks,
Beichuan
-Original Message-
From: users [mailto:users-boun...@open-mpi.org] On Behalf Of Rob Latham
Sent: Monday, April 14, 2014 14:24
To: Open MPI Users
Subject: Re: [OMPI users] File locking in ADIO, OpenMPI 1.6.4
t's the case. I'll dust off our old
RMA-based approach for shared file pointers. It's not perfect, but for
folks having difficulty with the file-backed shared file pointer
operations it might be useful.
==rob
Thanks,
Beichuan
-Original Message-----
From: users [mailto:users
scrutable -- and I like C-style 6 character variables a lot!
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
users mailing list
us...@open-mpi.org
Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users
Link to this post:
http://www.open-mpi.org/community/lists/users/2014/12/26006.php
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
//git.mpich.org/mpich.git/commit/a30a4721a2
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
193
==rob
Thanks for replays
Hanousek Vít
___
users mailing list
us...@open-mpi.org
Subscription: http://www.open-mpi.org/mailman/listinfo.cgi/users
Link to this post:
http://www.open-mpi.org/community/lists/users/2015/02/26382.php
--
Rob La
it, but nothing change (ROMIO works with special filename format,
OMPIO doesnt work)
Thanks for your help. If you point me to some usefull documentation, I will be
happy.
Hanousek Vít
-- Původní zpráva --
Od: Rob Latham
Komu: us...@open-mpi.org, vithanou...@seznam.cz
Datum: 24.
PI-IO
implementation, was this one:
r10377 | brbarret | 2007-07-02 21:53:06
so you're missing out on 8 years of I/O related bug fixes and optimizations.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
see Rob found a ROMIO commit in 2007.
since you asked:
r10400 | brbarret | 2008-06-08 23:18:04 -0500 (Sun, 08 Jun 2008) | 4 lines
- Fix issue with make -j and the dependency between libmpi.la
and liblamf77mpi.la. Thanks to Justin Bronder for bringing
this to our attention.
==rob
--
Rob Lat
On 06/02/2016 06:41 AM, Edgar Gabriel wrote:
Gilles,
I think the semantics of MPI_File_close does not necessarily mandate
that there has to be an MPI_Barrier based on that text snippet. However,
I think what the Barrier does in this scenario is 'hide' a consequence
of an implementation aspect.
On 06/22/2016 05:47 AM, Gilles Gouaillardet wrote:
Thanks for the info, I updated
https://github.com/open-mpi/ompi/issues/1809 accordingly.
fwiw, the bug occurs when addresses do not fit in 32 bits.
for some reasons, I always run into it on OSX but not on Linux, ubless I
use dmalloc.
I replace
you gave in the cb_config_list.
Try it and if it does/doesn't work, I'd like to hear.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
ted, is not going to perform very well, and
will likely, despite the library's best efforts, give you incorrect
results.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
that closing files comes a
little earlier in the shutdown process.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
ot free the subarray type)
- in writea you don't really need to seek and then write. You could
call MPI_FILE_WRITE_AT_ALL.
- You use collective I/O in writea (good for you!) but use independent
I/O in writeb. Especially for a 2d subarray, you'll likely see
better performance with MPI_FILE_WRITE_ALL.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
. MPI_SUCCESS) then
call MPI_ERROR_STRING(iret, string, outlen, ierr)
print *, string(1:outlen)
endif
end subroutine check_err
external32 is a good idea but nowadays portable files are better
served with something like HDF5, NetCDF-4 or Parallel-NetCDF, all of
which
ry inside OpenMPI-1.4.3 is pretty old. I
wonder if the locking we added over the years will help? Can you try
openmpi-1.5.3 and report what happens?
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
; in my program.
> It correctly worked on Open MPI on Linux.
> I would very much appreciate any information you could send me.
> I can't find it in Open MPI User's Mailing List Archives.
you probably need to configure OpenMPI so that ROMIO (the MPI-IO
library) is built with &
nsure that ROMIO's internal
structures get initialized exactly once, and the delete hooks help us
be good citizens and clean up on exit.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
nically non-decreasing order but
it can be jammed into memory any which way you want.
ROMIO should be better about reporting file views that violate this
part of the standard. We report it in a few places but clearly not
enough.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
where decomposing
the dataset over N processors will be more straightforward.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
s
> > report the correct filesize. Is this working as intended? Since
> > MPI_File_seek_shared is a collective, blocking function each process have
> > to synchronise at the return point of the function, but not when the
> > function is called. It seems that the use of MPI_File_seek_shared without
> > an MPI_Barrier call first is very dangerous, or am I missing something?
> >
> > ___
> > Care2 makes it easy for everyone to live a healthy, green lifestyle and
> > impact the causes you care about most. Over 12 Million members!
> > http://www.care2.com Feed a child by searching the web! Learn how
> > http://www.care2.com/toolbar___
> > users mailing list
> > us...@open-mpi.org
> > http://www.open-mpi.org/mailman/listinfo.cgi/users
> >
>
>
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
gt; report the correct filesize. Is this working as intended? Since
> > MPI_File_seek_shared is a collective, blocking function each process have
> > to synchronise at the return point of the function, but not when the
> > function is called. It seems that the use of MPI_File_seek_shared without
> > an MPI_Barrier call first is very dangerous, or am I missing something?
> >
> > ___
> > Care2 makes it easy for everyone to live a healthy, green lifestyle and
> > impact the causes you care about most. Over 12 Million members!
> > http://www.care2.com Feed a child by searching the web! Learn how
> > http://www.care2.com/toolbar___
> > users mailing list
> > us...@open-mpi.org
> > http://www.open-mpi.org/mailman/listinfo.cgi/users
> >
>
>
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
value of the shared
file pointer,
- Rank 0 did so before any other process read the value of the shared
file pointer (the green bar)
Anyway, this is all known behavior. collecting the traces seemed like
a fun way to spend the last hour on friday before the long (USA)
weekend :>
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
;Quincey Koziol from the HDF group is going to propose a follow on to this
> >>>ticket, specifically about the case you're referring to -- large counts
> >>>for file functions and datatype constructors. Quincey -- can you expand
> >>>on what you'll be proposing, perchance?
> >>Interesting, I think something along the lines of the note would be very
> >>useful and needed for large applications.
> >>
> >>Thanks a lot for the pointers and your suggestions,
> >>
> >>cheers,
> >>
> >>Troels
> >
>
> ___
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
s.
Do you use MPI datatypes to describe either a file view or the
application data? These noncontiguous in memory and/or noncontiguous
in file access patterns will also trigger fcntl lock calls. You can
use an MPI-IO hint to disable data sieving, at a potentially
disastrous performance cost.
==r
and friends are broken for
XFS or EXT3, those kinds of bugs get a lot of attention :>
At this point the usual course of action is "post a small reproducing
test case". Your first message said this was a big code, so perhaps
that will not be so easy...
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
v1.4.3)
> MCA routed: binomial (MCA v2.0, API v2.0, Component v1.4.3)
> MCA routed: direct (MCA v2.0, API v2.0, Component v1.4.3)
> MCA routed: linear (MCA v2.0, API v2.0, Component v1.4.3)
> MCA plm: rsh (MCA v2.0, API v2.0, Component v1.4.3)
> MCA plm: slurm (MCA v2.0, API v2.0, Component v1.4.3)
> MCA plm: tm (MCA v2.0, API v2.0, Component v1.4.3)
>MCA filem: rsh (MCA v2.0, API v2.0, Component v1.4.3)
> MCA errmgr: default (MCA v2.0, API v2.0, Component v1.4.3)
> MCA ess: env (MCA v2.0, API v2.0, Component v1.4.3)
> MCA ess: hnp (MCA v2.0, API v2.0, Component v1.4.3)
> MCA ess: singleton (MCA v2.0, API v2.0, Component v1.4.3)
> MCA ess: slurm (MCA v2.0, API v2.0, Component v1.4.3)
> MCA ess: tool (MCA v2.0, API v2.0, Component v1.4.3)
> MCA grpcomm: bad (MCA v2.0, API v2.0, Component v1.4.3)
> MCA grpcomm: basic (MCA v2.0, API v2.0, Component v1.4.3)
> ___
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
g a bit.
in general, if you plot "i/o performance vs blocksize", every file
system tops out around several tens of megabytes. So, we have given
the advice to just split up this nearly 2 gb request into several 1 gb
requests.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
here, or each processor will end up
writing the same data to the same location in the file. If you
duplicate the work identically to N processors then yeah, you will
take N times longer.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
some nice
ROMIO optimizations that will help you out with writes to GPFS if
you set the "striping_unit" hint to the GPFS block size.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
a long time, then switched to SVN in I think 2007?
I am way late to the git party, but git-svn is looking mighty
attractive as a first step towards transitioning to full git. One
more awful svn merge might be enough to push us over the edge.
==rob
--
Rob Latham
Mathematics and Computer Scienc
g but make the testing "surface area" a lot
larger. We are probably going to have a chance to improve things
greatly with some recently funded proposals.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
On Tue, Feb 21, 2012 at 05:30:20PM -0500, Rayson Ho wrote:
> On Tue, Feb 21, 2012 at 12:06 PM, Rob Latham wrote:
> > ROMIO's testing and performance regression framework is honestly a
> > shambles. Part of that is a challenge with the MPI-IO interface
> > itself. For
On Thu, Jul 12, 2012 at 10:53:52AM -0400, Jonathan Dursi wrote:
> Hi:
>
> One of our users is reporting trouble reading large files with
> MPI_File_read (or read_all). With a few different type sizes, to
> keep count lower than 2^31, the problem persists. A simple C
> program to test this is at
- Reuti
> >> ___
> >> users mailing list
> >> us...@open-mpi.org
> >> http://www.open-mpi.org/mailman/listinfo.cgi/users
> >>
> >
> > ___
> > users mailing list
> > us...@open-mpi.org
> > http://www.open-mpi.org/mailman/listinfo.cgi/users
>
>
> ___
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
intel --with-mpi=open_mpi
> >> --disable-aio>, data source: default value)
> >> Complete set of command line parameters passed to
> >> ROMIO's configure script
> >>
> >>Eric
> >>
> >>___
> >>users mailing list
> >>us...@open-mpi.org
> >>http://www.open-mpi.org/mailman/listinfo.cgi/users
> >
> >___
> >users mailing list
> >us...@open-mpi.org
> >http://www.open-mpi.org/mailman/listinfo.cgi/users
>
> ___
> users mailing list
> us...@open-mpi.org
> http://www.open-mpi.org/mailman/listinfo.cgi/users
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
RN, which is used for that purpose
in C.
It's important to note that MPI-IO routines *do* use ERROR_RETURN as
the error handler, so you will have to take the additional step of
setting that.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
be wrong.
> >
>
> I think but I am not sure that it is because the MPI I/O (ROMIO)
> code is the same for all distributions...
>
> It has been written by Rob Latham.
Hello! Rajeev wrote it when he was in grad school, then he passed the
torch to Rob Ross when he was a
On 02/11/2013 09:51 AM, Stefan Mauerberger wrote:
Hi Everyone!
Playing around with MPI_FILE_READ() puzzles me a little. To catch all
errors I set the error-handler - the one which is related to file I/O -
to MPI_ERRORS_ARE_FATAL.
However, when reading from a file which has not the necessary size
tually using parallel I/O the right way.
I think you're OK here. What are you seeing? Is this NFS?
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
;, ret);
> } else {
> MPI_File_close(&fh);
> }
> MPI_Finalize();
> return 0;
> }
The error code isn't very interesting, but if you can turn that error
code into a human readable string with the MPI_Error_string() routine,
then maybe you'll have a hint as to what is causing the problem.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
tions to the table and reduce your overall I/O costs,
perhaps even reducing them enough that you no longer miss true
asynchronous I/O ?
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
supports it). If you really need
to experiment with async I/O, I'd love to hear your experiences.
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
On Mon, Nov 23, 2009 at 01:32:24PM -0700, Barrett, Brian W wrote:
> On 11/23/09 8:42 AM, "Rob Latham" wrote:
>
> > Is it OK to mention MPICH2 on this list? I did prototype some MPI
> > extensions that allowed ROMIO to do true async I/O (at least as far
> >
h OpenMPI as well as an example program
> because this is the first time I've attempted this so I may well be
> doing something wrong.
It sounds like you're on the right track. I should update the PVFS
quickstart for the OpenMPI specifics. In addition to pvfs2-ping and
pvfs2-ls
though. Nothing
prevents rank 30 from hitting that loop before rank 2 does. To ensure
order, you could MPI_SEND a token around a ring of MPI processes.
Yuck.
One approach might be to use MPI_SCAN to collect offsets (the amount
of data each process will write) and then do an MPI_FILE_WRITE_AT_ALL
river and it's not on the list? First off, let me
know and I will probably want to visit your site and take a picture of
your system. Then, let me know how much longer you foresee using the
driver and we'll create a "deprecated" list for N more years.
Thanks
==rob
-
5/2016 12:31 PM, Rob Latham wrote:
I'm itching to discard some of the little-used file system drivers in
ROMIO, an MPI-IO implementation used by, well, everyone.
I've got more details in this ROMIO blog post:
http://press3.mcs.anl.gov/romio/2016/01/05/cleaning-out-old-romio-file-system-d
On 01/21/2016 05:59 AM, Dave Love wrote:
[Catching up...]
Rob Latham writes:
Do you use any of the other ROMIO file system drivers? If you don't
know if you do, or don't know what a ROMIO file system driver is, then
it's unlikely you are using one.
What if you use a driv
On 02/04/2016 11:35 AM, Dave Love wrote:
Jeff Hammond writes:
On Tuesday, February 2, 2016, Brice Goglin wrote:
I announced the end of the Open-MX maintenance to my users in December
because OMPI was dropping MX support. Nobody complained. So I don't plan
to bring back Open-MX to life nei
On 02/10/2016 12:07 PM, Edgar Gabriel wrote:
yes and no :-) That particular functions was fixed, but there are a few
other especially in the shardefp framework that would cause similar
problems if compiled without RTLD_GLOBAL.
But more importantly, I can confirm that ompio in the 1.8 and 1.10
On 01/21/2016 05:59 AM, Dave Love wrote:
:-), but what about plfs, which seems a notable omission? The patches
in the plfs distribution don't apply to recent adio, at least the
version in ompi 1.8 as far as I remember. I wonder if there's any
chance of fixing that and including it, assuming
On 01/26/2016 09:32 AM, Dave Love wrote:
Rob Latham writes:
We didn't need to deploy PLFS at Argonne: GPFS handled writing N-to-1
files just fine (once you line up the block sizes), so I'm beholden to
PLFS communities for ROMIO support.
I guess GPFS has improved in that res
On 03/13/2016 12:21 PM, George Bosilca wrote:
Eric,
A quick grep in Open MPI source indicates that the only 2 places where
MPI_ERR_UNSUPPORTED_DATAREP is issue are deep inside the imported ROMIO
code (3.14):
./ompi/mca/io/romio314/romio/adio/include/adioi_errmsg.h:70:MPI_ERR_UNSUPPORTED_DATAR
hat you've written. The MPI-IO library just
provides a wrapper around C system calls, so if you created this file
with fortran, you'll have to read it back with fortran.
Since you eventually want to do parallel I/O, I'd suggest creating the
file with MPI-IO (Even if it is MPI_FILE_WRITE from rank 0 or a
single process) as well as reading it back (perhaps with
MPI_FILE_READ_AT_ALL).
==rob
--
Rob Latham
Mathematics and Computer Science Division
Argonne National Lab, IL USA
76 matches
Mail list logo
