GitLab

We were using defines instead of enum to represent the same class of
flags.
Signed-off-by: Wesley Bland <wbland@anl.gov>

In nemesis we were managing a separate enum for the nemesis packet
handlers, which was somehow being force compared against the CH3
packet handler enums.  This is weird and a recipe for bugs.  This
patch unifies them into a single enum, but allowing the channel to
declare its own packet handlers into the structure.
Signed-off-by: Wesley Bland <wbland@anl.gov>

We were using an enum for packet types and used an int16_t for the
storage.  Instead we should directly use the enum as the storage.
Signed-off-by: Wesley Bland <wbland@anl.gov>

This is to help with debugging.  Zero is too common a value, and is
often set automatically by the system if not initialized.  Starting at
a different value helps us catch uninitialized cases more easily.

We pick "42" as our magic number as it is the answer to the ultimate
question of life, the Universe, and everything.
Signed-off-by: Wesley Bland <wbland@anl.gov>

Bad placement of commas was making indent very unhappy.
Signed-off-by: Wesley Bland <wbland@anl.gov>

No review

Junchao Zhang authored Jul 21, 2014 and Kenneth Raffenetti committed Jul 21, 2014

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

Junchao Zhang authored Jul 21, 2014 and Kenneth Raffenetti committed Jul 21, 2014

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

No reviewer.

Added the check on count and datatype on the following functions:

  - MPI_Iallreduce
  - MPI_Ialltoall
  - MPI_Ibcast
  - MPI_Igather
  - MPI_Ireduce
  - MPI_Iscan

(ibm) D198793

Fixes #2139
Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

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

Paul Coffman authored Jul 19, 2014 and Rob Latham committed Jul 19, 2014

Signed-off-by: Rob Latham <robl@mcs.anl.gov>

another round of strict warning cleanups before the release:  missing
prototypes and shadowed declarations

We often have a pretty good idea what hints are in use but it's not a
big deal to dump to stdout a list of the key-value pairs to confirm.
Signed-off-by: Paul Coffman <pkcoff@us.ibm.com>

clang finds a spot where we took the abs() of two unsigned numbers.
result can never be negative (could be surprisingly large).
Signed-off-by: Paul Coffman <pkcoff@us.ibm.com>

introduce the environment variable ROMIO_FSTYPE_FORCE which one can set
to forcibly override ROMIO's file system detection logic when the
"prepend a prefix" approach is infeasable.

there's no pre-defined MPI datatype for blksize_t, and we are still sort
of trying to avoid int64_t and related explicitly sized types for
maximum portability.  'long' should be big enough to hold a blocksize:
it's an int on many, a long int on some.

Closes #2123 (type mismatch in ad_opencoll.c)

ROMIO will pick some number of ranks P to be I/O aggregators, but had no
means to report that selection back to the user.  Now someone can query
this hint after opening a file to find out which ranks were selected.

Based on stat() or a user-provided prefix, the actual low-level file
system routines ROMIO uses might differ.  the info object provides a
simple portable way to report that back.

after re-engineering, ad_gpfs_open on some environments was missing a
header file for 'struct stat64'.  Found it was also bringing in header
files it did not need.
Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

even though they are the same value, clang noticed this structure
expected members from one kind of enum, but was initialized with a
different enum.
Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

This reverts commit 274a5a70.

See #2128
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

Fixes #2128
Signed-off-by: Huiwei Lu <huiweilu@mcs.anl.gov>

When the memory overhead for memory usage tracing is bigger than
the threshold value, a warning message is generated to indicate the
amount of the memory used in the tracing. Environment variables
to control the threshold value were added.

See #2068.
Signed-off-by: Pavan Balaji <balaji@anl.gov>

We were creating duplicating information in the operation structure
and in the packet structure when the message is actually issued.
Since most of the information is the same anyway, this patch just
embeds a packet structure into the operation structure.
Signed-off-by: Xin Zhao <xinzhao3@illinois.edu>

Paul Coffman authored Jul 15, 2014 and Rob Latham committed Jul 16, 2014

use ADIOI_Assert to guard againt infinite loop;  simpler easier-to-read
code for fd_size assignment
Signed-off-by: Rob Latham <robl@mcs.anl.gov>

Paul Coffman authored Jul 11, 2014 and Rob Latham committed Jul 16, 2014

P2PCONTIG memory leak fixes - MPI_Request cleanups via MPI_Wait for MPI_Isends
Signed-off-by: Rob Latham <robl@mcs.anl.gov>

Paul Coffman authored Jul 11, 2014 and Rob Latham committed Jul 16, 2014

The BGQPLATFORM bridgelist and bridgelistnum hints need to be freed in
ADIOI_Close because of the way the "create on one, reopen on all" logic
and the hint processing logic interact.
Signed-off-by: Rob Latham <robl@mcs.anl.gov>

Paul Coffman authored Jul 07, 2014 and Rob Latham committed Jul 16, 2014

After a call to ADIOI_P2PContig(Write/Read)Aggregation, code exits early
from ADIOI_GPFS_(Write/Read)StridedColl and was not freeing some data
structures
Signed-off-by: Rob Latham <robl@mcs.anl.gov>

(ibm) D197049
Signed-off-by: Michael Blocksome <blocksom@us.ibm.com>

This reverts commit 1c5c5945

.

Reopens #1788  (datatype performance tests failing)

but better to have poor performance than incorrect performance

Closes #2115 (RMA fails with derived type containing struct of struct)
Closes #2126 (Data Integrity issue in MPI_Gather ...)

Conflicts:
	src/mpid/common/datatype/dataloop/dataloop_optimize.c

but only because a subsequent commit removed bits of this optimization.
This commit fully removes this optimization, but we leave behind test
cases to help us make sure we get it right next time.  We also leave
behind some additional debugging support routines.
Signed-off-by: Junchao Zhang <jczhang@mcs.anl.gov>

Incorrect preprocessor directives caused when porting Python code to C.
Signed-off-by: Wesley Bland <wbland@anl.gov>

Test this case so we don't have another regression. Thanks for test case
contributed by Lisandro Dalcin (dalcinl@gmail.com).

See #2129
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Wesley Bland authored Jul 10, 2014 and Kenneth Raffenetti committed Jul 15, 2014

The refcounting for isends needs to be reset to 0 sometimes if an error occurs
before passing the request back to the user. This was mistakenly cleaned up in
[1e171ff6

] and now needs to be set back (along with a better comment
explaining the problem.

Thanks for the bug report to Lisandro Dalcin (dalcinl@gmail.com).

Fixes #2129
Signed-off-by: Ken Raffenetti <raffenet@mcs.anl.gov>

Pavan Balaji authored Jul 14, 2014 and Kenneth Raffenetti committed Jul 14, 2014

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