GitLab

The MPIC helper functions have been using MPI_Comm and MPI_Request
objects instead of their MPID_* counterparts. This leads to a bunch of
unnecessary conversions back and forth between the two types of objects
and makes the work incompatible with other parts of the codebase
(non-blocking collectives for instance).

This patch converts all of the MPIC_* functions to use MPID_Comm and
MPID_Request and changes all of the collective calls to use them now
too.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

The collective helper functions generally have an errflag that is used
when a failure is detected to allow the collective to continue while
also communicating that a failure occurred. That flag is now included
as a parameter for MPIC_Wait.

The rest of this commit is the refactoring necessary in the rest of the
helper functions to support the change.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

Signed-off-by: Charles J Archer <charles.j.archer@intel.com>

The tag for send was ignored and recvtag incorrectly used in its place.
Signed-off-by: Wesley Bland <wbland@anl.gov>

Rob Latham authored Jan 20, 2015 and Kenneth Raffenetti committed Jan 23, 2015

HDF5 folks reported a bug with ROMIO and one of their slightly-strange (but
100% legal) datatypes.  git-bisect points to the "promote size of length"
change.  Seems that MPICH does not like struct datatypes with zero-count
elements?  Further investigation requred.  This change (construct a simpler
datatype in more cases) is sufficient to help HDF5 move forward.

See #2221
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Rob Latham authored Jan 19, 2015 and Kenneth Raffenetti committed Jan 23, 2015

many many places where a 64 bit value is stored in a 32 bit value
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Rob Latham authored Jan 19, 2015 and Kenneth Raffenetti committed Jan 23, 2015

- bump up subtypes from 3 to 6. The limit is arbitrary.  I am trying to
  figure out a type with 4 sub-types.
- split up indexed/hindexed lists onto separate lines.  MPICH debug
  output format adds its own newlines, but we have to clean out MPICH's
  extra debug output anyway: joining a few lines isn't that much more
  work.
- output a name of the digraph that graphviz can actually parse.
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

When process fails, fault tolerance scheme takes a different path to
deal with MPI object reference counts than the existing one. Some
reference counts were not properly set in FT path so when configured
with --enable-g=all, some ft tests will show leaked context id, dirty
COMM, GROUP and REQUEST objects and so on when exit.

This patch fixes ft/shrink and ft/agree with "--enable-g=all". Stack
allocated objects of requests, communicators and groups will be freed by
FT.
Signed-off-by: Wesley Bland <wbland@anl.gov>

MPIX_Comm_agree should not return errors if the failed processes have
all been acknowledged. Previously, it was returning errors
unnecessarily, but this makes sure that the errcode is MPI_SUCCESS when
appropriate.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

 The segfault was caused by the library trying to free an already freed mpid_statp
 structure. The structure is freed right after the status information is printed.
 To fix the problem, the mpid_statp is set to NULL after the free is done.

 (ibm) D202018
Signed-off-by: Sameh Sharkawi <sssharka@us.ibm.com>

Wesley Bland authored Jan 15, 2015 and Kenneth Raffenetti committed Jan 15, 2015

For some reason, there was no MPIR_Testall_impl as there is with many of
the other MPI_* functions. This causes a linking problem when weak
symbols are disabled and another MPI function needs to call MPI_*.

This patch moves most of the MPI_Testall code into MPIR_Testall_impl and
has MPI_Waitall call that function instead of MPI_Testall.
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

User on OpenMPI list wanted to create a 259 character file.  shared file
pointer name construction used the magic '256' value to construct a full
path to the hidden shared file pointer file.  PATH_MAX already exists
for this purpose, so use it.

While there, found a few spots checking/setting PATH_MAX, so do that in
one place

Closes #2212
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Right now there's only one error condition: file name too long.  This
change checks return codes of ADIOI_Strncpy and informs caller.
Otherwise, really long names result in buffer overruns.

See #2212
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Compile time fix required for OFI threading model
No semantic changes
Signed-off-by: Yohann Burette <yohann.burette@intel.com>

There was an accidental ADI breakage earlier when MPI level codes would
query into the dev part of the MPID request object. This commit removes
that breakage by adding a new macro into the mpiimpl.h file to portably
check whether a request is anysource. For now, in pamid, this macro
always evaluates to 0. This can easily be fixed by overwriting it in the
pamid code, but since pamid doesn't support FT, it won't have any
functional change either.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

It was pointed out that by putting this in a macro and failing silently
when unimplemented, this make things challenging for derivatives which
will implement this function in the future. By moving this to an MPID
level function, it becomes more obvious that the function should be
implemented later.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

This macro was used inside CH3 to determine if the communicator could be
used for anysource communication. With the rewrite of the anysource
fault tolerance logic, it is now necessary to use it at the MPI level.
Because it is a macro and not a function, the macro is defined in
mpiimple.h as (1) and then overwritten in the ch3 device. Future devices
can also overwrite it if desired.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

If a blocking recv function (MPI_Recv and MPI_Sendrecv) includes an
MPI_ANY_SOURCE and there is a failure, handle it by cleaning up the
request and returning MPIX_ERR_PROC_FAILED.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

Test for the specific error code so it doesn't accidentally catch
MPI_ERR_OTHER.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

If the first argument is NULL, don't try to set it to MPI_REQUEST_NULL.
For blocking functions that want to complete the MPID_Request object,
this allows them to reuse the code.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

If a wait operation involves an anysource, we need to first check to
make sure that they haven't been disabled. If they have been, convert
the wait* function to a test* function to prevent deadlocking inside the
progress engine.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

If a failure is detected, even if no request is actually complete, the
completion counter will be incremented now as a way to give control back
to the MPI layer to let it decide whether or not to continue.

This gives the request completion functions a chance to see if they're
waiting on an MPI_ANY_SOURCE request and if so, to return an error
indicating that the completion function has a
MPIX_ERR_PROC_FAILED_PENDING failure that the user needs to acknowledge.

All of these functions should go into the progress engine at least once
as a way to ensure that even if they will be returning an error, they'll
at least give MPI a way to make progress and potentially still complete
the request objects even if the user never acknowledges the failure.

A follow on commit will add the functionality to keep the progress
engine from getting stuck if a failure is discovered before entering the
completion function.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

The existing way that we handle non-blocking requests involving wildcard
receive operations is incorrect. We're cancelling request operations and
trying to recreate them later. In the meantime, it's messing with
matching and makes it possible (likely?) that some messages that arrive
will never be matched. A new way of handling this is coming next.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

If we had a failure that caused a request to be pending, we were freeing
the request before calling the error handler. That caused segfaults. Now
we switch the ordering of the two to avoid that.

This also moves the assignment of the status_ptr to be a little earlier
to avoid another segfault.
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

CH3 ensures that self communication does not go through the netmod,
so there is no need for a process to pause/unpause itself.
Signed-off-by: Antonio J. Pena <apenya@mcs.anl.gov>

Signed-off-by: Sameh Sharkawi <sssharka@us.ibm.com>

Ralph Castain authored Jan 06, 2015 and Rob Latham committed Jan 08, 2015

OpenMPI uses 'make dist', but MPICH does not.  Some recently added
(internal) header files were not listed in ROMIO's noinst declaration

Note: RobL combined and edited these OpenMPI patches into this patch:
- e0927895db8d
- 84c41429e9ac
Signed-off-by: Rob Latham <robl@mcs.anl.gov>

Adding FCMODOUTFLAG directly to AM_FCFLAGS could cause conflicts with
certain libtool flags (-module) during linking. This change allows us
to set FCMODOUTFLAG during module creation, but not have it present
during linking. Refs #2024
Signed-off-by: Junchao Zhang <jczhang@mcs.anl.gov>

Recent versions of ifort on darwin will drop flags intended for the
linker unless they are prefixed with "-Wl,". Jeff Hammond checked with
the Intel compiler folks, and they confirmed that "-Wl," has been
supported since the initial ifort release on OSX (9.1).

Closes #2024
Signed-off-by: Junchao Zhang <jczhang@mcs.anl.gov>

Previous re-organization of the library symbols resulted in a
situation where Fortran programs could no longer be profiled using
tools written in C. Functions in libmpifort directly called the
PMPI_* versions in libmpi.

Now we always call the MPI_* versions from libmpifort. In the case
where we are building a separate profiling library, we use a new
preprocessor flag to ensure we call PMPI_* from inside libpmpi.

Additional bug fix:
  - always define mpi_conversion_fn_null_, there is no pmpi version

Fixes #2209
Signed-off-by: Junchao Zhang <jczhang@mcs.anl.gov>

Adds a way to pass a timelimit argument to the run command, as long
as the timelimit is in seconds.  This is enough for some of the MPICH
versions of mpiexec and for recent versions of the Cray aprun command.
Signed-off-by: Wesley Bland <wbland@anl.gov>

Signed-off-by: Wesley Bland <wbland@anl.gov>

Signed-off-by: Wesley Bland <wbland@anl.gov>

Signed-off-by: Wesley Bland <wbland@anl.gov>

Signed-off-by: Wesley Bland <wbland@anl.gov>

Wesley Bland authored Jan 05, 2015 and Kenneth Raffenetti committed Jan 05, 2015

Instead of using its own versioning system that wasn't getting updated
with any regularity, now the test suite will use the same versioning
scheme as mainline MPICH. This is consistent with other parts of MPICH
that get distributed separately (MPL, ROMIO, Hydra).
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Kenneth Raffenetti authored Dec 15, 2014 and Sangmin Seo committed Jan 04, 2015

Squashes a warning when using the embedded versions of OPA and MPL.
Signed-off-by: Sangmin Seo <sseo@anl.gov>

Kenneth Raffenetti authored Dec 04, 2014 and Sangmin Seo committed Jan 04, 2015

We were incorrectly adding the build directories for mpl and opa to
external_ldflags in Makefile.am, causing them to be listed in the
installed libmpi.la libtool file. If a linker does not handle this
potentially non-existant build directory gracefully, it could cause
an issue. Since the mpl and opa libraries are now embedded in libmpi
by default, we simply eliminate the flags unless we are using
pre-built, external libraries. Fixes #2208

Thanks to Markus Geimer for the bug report and suggested solution.
Signed-off-by: Sangmin Seo <sseo@anl.gov>

Paul Coffman authored Dec 12, 2014 and Rob Latham committed Dec 19, 2014

Currently in the MPI_File_close there is a barrier in place whenever the
ADIO_SHARED_FP feature is enabled AND the ADIO_UNLINK_AFTER_CLOSE
feature is disabled right before the code to close the shared file
pointer and potentially unlink the shared file itself.  PE testing on
GPFS revealed a situation using the non-collective
MPI_File_read_shared/MPI_File_write_shared
where based on this implementation all tasks needed to wait for all
other tasks to complete processing before unlinking the shared file
pointer or the open of the shared file pointer could fail.  This
situation is illustrated as follows with the simplest example of 2 tasks
that do this:
MPI_File_Open
MPI_File_set_view
MPI_File_Read_shared
MPI_File_close

So both tasks call MPI_File_Read_shared at the same time which first
does the ADIO_Get_shared_fp which does the file open with create mode on
the shared file pointer.   Only 1 task can actually create the file, so
there is a race to see who can get it done first.  If task 0 gets it
created then he is the winner and goes on to use it, read the file and
then MPI_File_close which then unlinks the shared file pointer first and
then closes the output file.  Meanwhile, task 1 lost the race to create
the file and is in error, the error handling in gpfs goes into effect
and task 1 now just tries to open the file that task 0 created.  The
problem is this error handling took longer that task 0 took to read and
close the output file, so at the time when task 0 does the close he is
the only process with a link since task 1 is still in the create file
error handlilng code so therefore gpfs goes ahead and deletes the shared
file pointer.  Then when the error handling code for task 1 does
complete and he tries to do the open, the file is no longer there, so
the open fails as does the subsequent read of the shared file pointer.
Currently GPFS has the ADIO_UNLINK_AFTER_CLOSE  feature enabled, so the
fix for this is to remove the additional condition of
ADIO_UNLINK_AFTER_CLOSE  being disabled for the barrier in the close to
be done.  Presumably this could be an issue for any parallel file system
so this change is being done in the common code.

See ticket #2214
Signed-off-by: Paul Coffman <pkcoff@us.ibm.com>
Signed-off-by: Rob Latham <robl@mcs.anl.gov>

Signed-off-by: Junchao Zhang <jczhang@mcs.anl.gov>