[Darshan-users] Darshan-users Digest, Vol 45, Issue 6

Phil Carns carns at mcs.anl.gov
Thu Jul 2 08:40:10 CDT 2015


Hi Adnan,

Python indeed might be a little trickier, but I think its possible.  
I'll see if I can find more information about this and report back.

I *think* that you need to actually do the reverse and disable the 
static instrumentation and use the dynamic LD_PRELOAD approach instead 
in this case.  I imagine that the Python MPI bindings are dynamically 
loading the MPI library at runtime even though the Python program itself 
doesn't show up as a dynamic executable.

The critical point in getting a Darshan log to be generated is that it 
must intercept MPI_Init() and MPI_Finalize().  If it can achieve that 
much then it should at least produce a log file.

Can you try that method again (disabling the static instrumentation and 
instead using LD_PRELOAD exclusively) and confirm the error?

thanks,
-Phil

On 06/29/2015 02:47 PM, Adnan Haider wrote:
> Hi Phil,
>
> Sorry for the late reply, we were focusing on some other aspects but 
> now we are back to using Darshan for analyzing our application. Our 
> executable is statically linked; the previous error was caused by 
> LD_PRELOAD being set in our environment. After resetting LD_PRELOAD 
> (so that we are not dynamically instrumenting), the application runs 
> and there are no symbol mapping errors. However after job completion, 
> no trace file appears in the log directory. We used environment 
> variables with the latest MPICH release in an attempt to statically 
> instrument our application. Compiling a simple mpi application with 
> the environment variables set does produce a Darshan trace file, but 
> our application does not. Also for our executable, using ldd <python 
> script> we get: "not a dynamic executable"
>
>
> Here is some more detail about our application and its dependencies. 
> Our application is written in python. The application uses mpi4py for 
> all MPI calls. Also we are reading and writing netcdf files but are 
> using PyNIO which breaks down python calls into standard netcdf I/O.  
> This site <http://www.alcf.anl.gov/user-guides/darshan> says that 
> dealing with languages other than c,c++,and Fortran could cause 
> issues. I was thinking the python code could be causing the issue. 
> Possibly, the PyNIO package on top of netcdf or mpi4py are not being 
> detected by Darshan. Or more likely, I am not correctly compiling the 
> correct software with the environment variables. The only software 
> that directly uses the mpi compiler is mpi4py, and I did recompile 
> this after setting the environment variables. I also recompiled PyNIO 
> and our application for good measure.
>
>
> Thanks, Adnan Haider
> B.S Candidate, Computer Science
> Illinois Institute of Technology
>
> On Fri, May 29, 2015 at 10:00 AM, 
> <darshan-users-request at lists.mcs.anl.gov 
> <mailto:darshan-users-request at lists.mcs.anl.gov>> wrote:
>
>     Send Darshan-users mailing list submissions to
>     darshan-users at lists.mcs.anl.gov
>     <mailto:darshan-users at lists.mcs.anl.gov>
>
>     To subscribe or unsubscribe via the World Wide Web, visit
>     https://lists.mcs.anl.gov/mailman/listinfo/darshan-users
>     <https://lists.mcs.anl.gov/mailman/listinfo/darshan-users>
>     or, via email, send a message with subject or body 'help' to
>     darshan-users-request at lists.mcs.anl.gov
>     <mailto:darshan-users-request at lists.mcs.anl.gov>
>
>     You can reach the person managing the list at
>     darshan-users-owner at lists.mcs.anl.gov
>     <mailto:darshan-users-owner at lists.mcs.anl.gov>
>
>     When replying, please edit your Subject line so it is more specific
>     than "Re: Contents of Darshan-users digest..."
>
>
>     Today's Topics:
>
>        1. Darshan error with HDF5 (Adnan Haider)
>        2. Re: Darshan error with HDF5 (Phil Carns)
>
>
>     ----------------------------------------------------------------------
>
>     Message: 1
>     Date: Thu, 28 May 2015 14:20:07 -0600
>     From: Adnan Haider <ahaider3 at hawk.iit.edu
>     <mailto:ahaider3 at hawk.iit.edu>>
>     To: darshan-users at lists.mcs.anl.gov
>     <mailto:darshan-users at lists.mcs.anl.gov>
>     Subject: [Darshan-users] Darshan error with HDF5
>     Message-ID:
>            
>     <CAM2fH+yEoqtPOnxVPvZNm853kCXEmhWQMrDpWWxZ8UEWC8jUcA at mail.gmail.com <mailto:CAM2fH%2ByEoqtPOnxVPvZNm853kCXEmhWQMrDpWWxZ8UEWC8jUcA at mail.gmail.com>>
>     Content-Type: text/plain; charset="utf-8"
>
>     Hi,
>     I am hoping to use Darshan for analyzing our application's
>     performance. We
>     are using HDF5 and netcdf 4. I installed Darshan version 2.3.1 and
>     mvapich2
>     for our mpi implementation. Darshan works fine for a standard mpi
>     pingpong
>     application. When we run our application, however, it gives the
>     following
>     error:
>     Darshan failed to map symbol: H5Fopen
>     Darshan failed to map symbol: H5Fopen
>     Darshan failed to map symbol: H5Fopen
>     Darshan failed to map symbol: H5Fopen
>
>     The four instances of the error probably have to do with the 4 mpi
>     ranks
>     specified at runtime. Nothing is written into the log directory.
>     This is
>     the only output, unless there is some error file I am not aware
>     of. I used
>     the static instrumentation approach for enabling Darshan. Thanks
>     for the
>     help!
>
>     Thanks, Adnan Haider
>     B.S Candidate, Computer Science
>     Illinois Institute of Technology
>     -------------- next part --------------
>     An HTML attachment was scrubbed...
>     URL:
>     <http://lists.mcs.anl.gov/pipermail/darshan-users/attachments/20150528/5ebdf005/attachment-0001.html>
>
>     ------------------------------
>
>     Message: 2
>     Date: Thu, 28 May 2015 16:32:04 -0400
>     From: Phil Carns <carns at mcs.anl.gov <mailto:carns at mcs.anl.gov>>
>     To: <darshan-users at lists.mcs.anl.gov
>     <mailto:darshan-users at lists.mcs.anl.gov>>
>     Subject: Re: [Darshan-users] Darshan error with HDF5
>     Message-ID: <55677B44.7060107 at mcs.anl.gov
>     <mailto:55677B44.7060107 at mcs.anl.gov>>
>     Content-Type: text/plain; charset="windows-1252"; Format="flowed"
>
>     Hi Adnan!
>
>     Is everything in the application statically linked (maybe check
>     with ldd
>     <executable>)?  That error message is supposed to only be generated by
>     the dynamic (ld-preloaded) darshan library, because it has to locate
>     underlying symbols at run time.  The symbol name mapping should be set
>     at link time for a static executable.
>
>     thanks,
>     -Phil
>
>     On 05/28/2015 04:20 PM, Adnan Haider wrote:
>     > Hi,
>     > I am hoping to use Darshan for analyzing our application's
>     > performance. We are using HDF5 and netcdf 4. I installed Darshan
>     > version 2.3.1 and mvapich2 for our mpi implementation. Darshan works
>     > fine for a standard mpi pingpong application. When we run our
>     > application, however, it gives the following error:
>     > Darshan failed to map symbol: H5Fopen
>     > Darshan failed to map symbol: H5Fopen
>     > Darshan failed to map symbol: H5Fopen
>     > Darshan failed to map symbol: H5Fopen
>     >
>     > The four instances of the error probably have to do with the 4 mpi
>     > ranks specified at runtime. Nothing is written into the log
>     directory.
>     > This is the only output, unless there is some error file I am not
>     > aware of. I used the static instrumentation approach for enabling
>     > Darshan. Thanks for the help!
>     >
>     > Thanks, Adnan Haider
>     > B.S Candidate, Computer Science
>     > Illinois Institute of Technology
>
>
>     -------------- next part --------------
>     An HTML attachment was scrubbed...
>     URL:
>     <http://lists.mcs.anl.gov/pipermail/darshan-users/attachments/20150528/bc72a5df/attachment-0001.html>
>
>     ------------------------------
>
>     _______________________________________________
>     Darshan-users mailing list
>     Darshan-users at lists.mcs.anl.gov
>     <mailto:Darshan-users at lists.mcs.anl.gov>
>     https://lists.mcs.anl.gov/mailman/listinfo/darshan-users
>
>
>     End of Darshan-users Digest, Vol 45, Issue 6
>     ********************************************
>
>

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/darshan-users/attachments/20150702/f7894a89/attachment.html>


More information about the Darshan-users mailing list