summaryrefslogtreecommitdiffstats
path: root/testpar/t_mpi.c
Commit message (Collapse)AuthorAgeFilesLines
* Fixes parallel issues from recent C99 changes (#809)Dana Robinson2021-06-301-2/+2
| | | | | | | * Fixes parallel issues from recent C99 changes * Adds MPE FUNC --> __func__ changes missed in earlier PRs * Even more missed FUNC --> __func__ macros
* Update license url part2 (#333)Larry Knox2021-02-171-1/+1
| | | | | | * Modify temporary rpath for testing in java example scripts. * Update URL in source file Copyright headers for web copy of COPYING file - files not in src or test.
* develop revert source to clang-format version 11 (#293)Allen Byrne2021-01-291-3/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * OESS-98 convert plugin option to FetchContent, add tests * Fixes for pkcfg files because of plugin option * OESS-98 fix tools test for plugins * Keep doxygen comments under 100 chars long - format hint * Whitespace * HDFFV-11144 - Reclassify CMake messages * HDFFV-11099/11100 added help text * Reworked switch statement to compare string instead * Fix typo * Update CDash mode * Correct name of threadsafe * Correct option name * Undo accidental commit * Note LLVM 10 to 11 format default changes * Update format plugin * Undo clang-format version 11 changes * One more correction
* Bring async branch to develop (#166)Quincey Koziol2020-12-141-3/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | * Add H5Fwait, H5Dwait, and other changes for async vol connector * Revert temporary testing changes * Add H5Fwait to header file * Add H5VLreset_lib_state() routine. * Correct VOL wrap context when retrieving library state for file open & create. * Manage the API context's VOL connector state as part of the library state. * Set the 'VOL connector property valid' flag when restoring the library state. * Don't push new API context on stack when retrieving "current" one. * Check for NULL VOL wrap context before decrementing refcount on it, when freeing the API context state. * Manage recount of underlying connector for VOL wrap context. * Add H5TSmutex_acquire() and H5TSmutex_release() routines to acquire and release the global lock on the HDF5 library. * Update library with new functions related to library global lock * Add asynchronous token API * Add new lightweight FUNC_ENTER / LEAVE macros for helping to structure the threadsafety (H5TS*) routines. * Sync w/develop * Initial event set code framework. * Elaborate on the H5ES routines, starting to add API routines. Update the "close ID" callbacks to allow asynchronous request tokens to be passed in from an asynchronous close API call. Refactor current asynchronous API routines (H5Fopen/H5Fclose and H5Dread/H5Dread) to use event sets instead of directly working with request tokens from the application. Clean up a few other minor warnings & code style issues. * Implement H5EScreate, H5ESget_count, and H5ESclose. It should be possible to write a simple application that creates an event set and uses it with H5Fopen_async, H5Dread_async, H5Dwrite_async, and H5Fclose_async, then calls H5ESclose (which waits for all async events to complete). * Add source file for event set test. * Refactor sync & async API routines to call common routine. Move dataset API read / write routines to src/H5D.c, along with all the other API routines. Progress on "fake" async VOL connector, for testing. * Modify async implementation to wrap async requests in a H5VL_object_t struct so the VOL layer can find the connector when accessing the request at a later point. * Free the requests is H5ESclose. Remove comments implying that request wait, notify, and cancel callbacks should free the request. * Fix bug in error handling in H5Fclose. * Fix bugs in async file routines. Rename H5VL_create_object_generic to H5VL_create_object. * Add explicit async version of H5Fcreate. * Add more _async routines * Correct typo for return value from H5Awrite changes * Add H5EStest and H5ESwait routines * Updated with API tracing info * Fix NULL pointer dereference in H5ES__wait * Add H5is_library_terminating() routine, so that VOL connectors can detect when the library is shutting down. * Fix typo * Remove event from event set's linked list * Move block of code so that vol_obj is valid * Avoid setting properties in the DXPL when reseting the library state (and in the test code). * Refactor argument tracing to implement new capability for tracing arguments of non-API routines, with the H5ARG_TRACE macro. This macro is updated automatically with the bin/trace script that runs as part of the autogen.sh process. Major changes were in src/H5trace.c and bin/trace, with the other changes being cleanups to the argument lists, to improve their presentation in the tracing output. Also - added the "managed string" routines, which can dynamically allocate strings, appending printf-formatted output to the string efficiently. * Release memory for managed strings * Fix printf() formats. * More printf() format fixes. * Add H5Eappend_stack routine and regression tests * Clean up a few missed merge conflicts and update the error stacks. * Remove unnecessary fork() operations and ten second sleep(). * Restore commented out attribute out, to better enable tracking down the previous failure * Allow multiple H5ARG_TRACE macros within a routine to be updated * Switch to using "new" H5ES_insert (which takes the arguments for the caller routine) for all event set operations. Renames H5ES_insert_new to H5ES_insert and removes the previous H5ES_insert. * Merge "managed" string routines into "ref-counted" strings, and refactor code to use them. * Add missing file. * Add caller's name and arguments to event, for error reporting * Refactor event set setup for "API common" internal routines * Checkin async API routines for H5A* and H5G* modules as listed in ID-283. Fix couple h5dump expected output files due to the changes. * Add some of the error query routines needed for event sets. * Refactor to make async setup / teardown and "common" routines cleaner * (1) Add async APIs to H5L, H5F, and H5D modules (2) Fix errors in previous checkins of async APIs in H5A and H5G modules (3) h5dump expected output changes * Enhance event info, for better error handling * Change name of temporary vol_obj variable, to help reduce coding errors * Fix oversight with vol_obj pointer * Minor code cleanup * Add missing \'valid\' flag for VOL wrapper context, when restoring the library\'s state * Run source formatter * Change H5TSmutex lock and release to include a lock count * Update error reporting ideas * Minor updates to improve sanity checking for retrieving / restoring library state * Updated with feedback from h5py team members * Refactor internal event set list and event handling, add implementation for H5ESget_err_info * Change the VOL request subclass callbacks that switch from using "H5ES_status_t" to "H5VL_request_status_t", and also add a H5VL_request_status_t* parameter to the 'cancel' callback in the request subclass. Also more code quality cleanups to add iterator callbacks to internal event set routines. * Update API tracing for new H5VL_request_status_t typedef * Finish converting internal event set operations to use list iterator callbacks, instead of directly accessing the list structure * Add H5VL_REQUEST_GET_ERR_STACK operation to request subclass, for retrieving a copy of the error stack for a failed asynchronous operation * Remove 'canceled' event status from Java constants * Be safer about releasing resources when inserting a newly opened/created object or file into an event set * Remove H5EStest, add H5ES_WAIT_NONE for 0 timeout, and revise parameters to H5ESwait, to make it more "aggregate". * Remove H5ES_STATUS_CANCELED from Java wrappers also * (a) Add async APIs for H5O module as listed in jira issue ID-283. (b) Remove verification of name parameter in async related routines for H55A and H5L modules because it is checked in H5VL_setup* routine. (c) Modify h5dump expected output due to the async changes. * Corrections based on PR feedback. * Further changes to make based on PR feedback. * Fix missed merge marker, and reformatted line * Clean up some warnings * Correct level of indirection * Relocate prototype (and doxygen info) for H5Aclose * Change non-static function declarations to be static * Ensure that H5TSpublic.h header gets installed (#129) * Add 'wrapper' versions of async calls, to allow language wrappers and layers on top of HDF5 to pass in their application information. * Switch H5Aexists\*_async and H5Lexists\*_async to use flag to return status, instead of return value. Make the corresponding changes through most of the v1 and v2 B-tree code. Clean up warnings in H5public.h and cmpd_dtransform.c. * Add H5Iregister_future routine and tests. * Correct return value for H5Lexists_async * Add H5_DLL macro to public H5ES API routines * Update supported -> flags parameter for introspect_query callback * Remove my email address. Update passthrough VOL connector ID. * Fix comment for post_open_api_common * Remove unused non-blocking VOL connector * Minor cleanup in async branch in preparation for merge to develop * Update CMake and the Autotools to use the new pass-through VOL ID * Fix for SWMR daily test failures (#160) The H5I_register_using_existing_id() call did not initialize the future ID callbacks, causing the library to segfault when it tried to resolve those function pointers. * Added selective async APIs (#150) * Added selective async APIs Description: Added the following APIs: H5Ropen_attr_async H5Ropen_object_async H5Ropen_region_async H5Mcreate_async H5Mopen_async H5Mput_async H5Mget_async H5Mclose_async H5Tcommit_async H5Topen_async H5Tcopy_async H5Tclose_async - Updated an expected output file to include a new internal function in the error stack for the failure case. * Updated async APIs per reviews, including removing async version of H5Tcopy. * Removed statements that were added by mistake in the previous commit. * Fix compile issues in H5M and warnings elsewhere * Reformat code * Brings VOL_LIST changes from develop. (#163) Co-authored-by: Houjun Tang <htang4@lbl.gov> Co-authored-by: Neil Fortner <nfortne2@hdfgroup.org> Co-authored-by: vchoi <vchoi@jelly.ad.hdfgroup.org> Co-authored-by: vchoi-hdfgroup <55293060+vchoi-hdfgroup@users.noreply.github.com> Co-authored-by: jhendersonHDF <jhenderson@hdfgroup.org> Co-authored-by: Dana Robinson <derobins@hdfgroup.org> Co-authored-by: Dana Robinson <43805+derobins@users.noreply.github.com> Co-authored-by: bmribler <39579120+bmribler@users.noreply.github.com>
* Clang-format of source filesAllen Byrne2020-09-301-313/+305
|
* Trim trailing whitespaceQuincey Koziol2020-04-201-1/+1
|
* revert type castkmu2020-02-281-2/+2
|
* Restore fix of test assert fail eror undone by later commit.Larry Knox2020-01-271-1/+1
|
* fix assert failkmu2020-01-241-1/+1
|
* squash cast warning fixkmu2020-01-231-5/+5
|
* fix test assert fail errorkmu2020-01-091-2/+2
|
* fix intel compile warningskmu2019-12-041-5/+5
|
* Revert "fix warnings from Intel compiler"kmu2019-11-261-5/+5
| | | | This reverts commit 8b9338ab57eec0cc8fa5a36c44d7b28e52e9a466.
* Revert "fix issues from previous PR comments"kmu2019-11-261-5/+5
| | | | This reverts commit d242a900f420b040e364f6c0976c01593e955db3.
* Revert "using a different MACRO"kmu2019-11-261-5/+5
| | | | This reverts commit fc61b7a9f3a38331809ebcb6247482943947cdb8.
* using a different MACROkmu2019-11-251-5/+5
|
* fix issues from previous PR commentskmu2019-11-251-5/+5
|
* fix warnings from Intel compilerkmu2019-11-071-5/+5
|
* OESS-29 Update HD prefix mostlyAllen Byrne2019-08-241-96/+96
|
* HDFFV-10845 C_FLAGS need set correctly for win32 vs mingwAllen Byrne2019-07-171-5/+5
|
* fix var nameAllen Byrne2019-07-091-1/+1
|
* Fix compile error with ifdef H5_HAVE_GETHOSTNAMEAllen Byrne2019-07-081-786/+757
|
* Merge pull request #426 in HDFFV/hdf5 from ~LRKNOX/hdf5_lrk:hdf5_1_10 to ↵Larry Knox2017-04-251-6/+4
| | | | | | | | | | hdf5_1_10 * commit '54957d37f5aa73912763dbb6e308555e863c43f4': Commit copyright header change for src/H5PLpkg.c which was added after running script to make changes. Add new files in release_docs to MANIFEST. Cimmit changes to Makefile.in(s) and H5PL.c that resulted from running autogen.sh. Merge pull request #407 in HDFFV/hdf5 from ~LRKNOX/hdf5_lrk:hdf5_1_10_1 to hdf5_1_10_1 Change copyright headers to replace url referring to file to be removed and replace it with new url for COPYING file.
* [svn-r28040] avoid use of MPI deprecated routines.Mohamad Chaarawi2015-10-121-9/+9
|
* [svn-r27768] Description:Quincey Koziol2015-09-141-1/+1
| | | | | | | | | | | | | | | | | | | | | | Complete revamp of package initialization/shutdown mechanism in the library. Each package now has a single init/term routine. This new way should avoid packages being re-initialized during library shutdown and is also be _much_ more proactive about giving feedback for resource leaks internal to the library. Introduces a new "module" header file for packages in the library (e.g src/H5Fmodule.h) which sets up some necessary package configuration macros for the FUNC_ENTER/LEAVE macros. (The VFL drivers have their own slightly modified version of this header, src/H5FDdrvr_module.h) Also cleaned up a bunch of resources leaks all across the library and tests, along with addressing many warnings, as I encountered them. Tested on: MacOSX/64 10.10.5 (amazon) w/serial & parallel Linux/64 3.10.x (kituo) w/serial & parallel Linux/64 2.6.x (ostrich) w/serial
* [svn-r27271] fix a few warnings in t_mpi.cMohamad Chaarawi2015-06-231-4/+3
|
* [svn-r25398] add a check to make sure MPI_File_get_size() returns correct ↵Mohamad Chaarawi2014-07-091-1/+2
| | | | value (HDFFV-8856).
* [svn-r25397] - remove configure checks for MPI_File_get_size and BigMohamad Chaarawi2014-07-071-19/+1
| | | | | MPI_File_set_size as they are supported by most MPI implementations. - fix bug in t_mpi.c (HDFFV-8856)
* [svn-r24380] The parallel test code now uses HDfree, HDmalloc, and HDcallocDana Robinson2013-10-311-1/+1
| | | | | | | | | | | exclusively. Part of the preparation for a fix for HDFFV-8551. Tested on: 32-bit LE linux (jam) w/ parallel and Fortran. There are no behavior changes, so testing was minimal.
* [svn-r22388] remove unbalanced bracketAllen Byrne2012-05-221-1/+1
|
* [svn-r22385] Skip tests using sparse file writes on Windows. JIRA issue ↵Allen Byrne2012-05-211-1/+5
| | | | (JIRA HDDFV-8064) created.
* [svn-r21334] HDFFV-7687: add HD macro prefrix to functions and use h5_stat_t ↵Allen Byrne2011-08-301-2/+2
| | | | | | where necessary reviewed
* [svn-r21101] HDFFV-7639Mike McGreevy2011-07-141-159/+102
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Purpose: Remove H5_MPI_SPECIAL_COLLECTIVE_IO_WORKS and H5_MPI_COMPLEX_DERIVED_DATATYPE_WORKS #defines from source. Description: Two advanced parallel functionalities, special collective IO and complex derived datatypes, are not supported by older implementations of mpi, and thus our code limits the use of these features with #ifdefs and has checks in configure to set them (or not). Unfortunately, configure can't actually run a parallel check to see if these features are working (nor not) so it resorts to looking in the config files where they are explicity enabled or disabled based on versions of mpi, sytems being built on, or for no documented reason at all (i.e. just set to on or off as some 'default'). Overriding these settings is easy if need be, provided it is known that it needs to be done to get improved performance, and oftentimes it is not. Most new MPI implementations successfully handle the functionality requested when these #defines are set, and many of the "turn these features off" cases in the config files are for old (> 5 years) versions of MPI and retired systems (such as NCSA's tungsten). Therefore, the decision has been made to remove the support for these old versions of MPI and systems that cannot handle these behaviors. The #ifdefs and supporting setup in the config/ files and configure script has been removed, and the code executed when these options were not set removed from the source. In passing, this commit also cleans up some whitespace issues in both t_mpi.c and H5Dmpio.c. Furthermore, in t_mpi.c, the special collective IO test was not getting regularly run due to it being written to work only with four processes (we regularly test with six, previously with three), and thus it failed when actually run due to an out of bounds data buffer assignment. It has been modified to run at any number of processes greater than four, and the memory problem has been fixed so the test passes. Tested: jam, h5committest, ember
* [svn-r19959] Bug: the VRFY macro, for some reason, called MPI_Finalize() ↵Albert Cheng2011-01-161-0/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | when it encountered error and wanted to exit the test program. This was not good since if only a subset of processes called MPI_Finalize(), the other processes will likely hang. That happened in AIX that it would waited till the alarm signal to kill the processes. Definitely a waste of time. Solution: Changed it to call MPI_Abort. That showed another problem. HDF5 has setup atexit post-process to try to close unclose objects, release resources, etc. But if the MPI processes have encountered an error and has been aborted, it is not likely any more MPI calls can function properly. E.g., it would attempt to free some communicators in the HDF5 MPIO file handle. It would again hang. Solution: need to call H5dont_atexit() to disable any atexit post-processing. This must be done early, like before calling H5open. This is added to each parallel test main program. testphdf5.h: Changed macros VRFY and MESG. Added comments too. testphdf5.c: t_mpi.c: t_cache.c: t_shapesame.c: Added H5dont_atexit. Tested: h5committest.
* [svn-r17654] Purpose:Mike McGreevy2009-10-151-4/+4
| | | | | | | | | | | | Configure cache-val cleanup Description: Corrected some misnamed cache values in configure / config files. Tested: h5committest
* [svn-r17318] Did some code cleanup.Albert Cheng2009-08-111-2/+4
| | | | | | | | | | t_file.c: replace the old variable, color, with a more meaningfule name of is_old. t_mpi.c: use the official mpi_file_delete, instead of remove, to delete a file in MPI environment. Tested: Only jam in parallel as changes are trivial.
* [svn-r16560] Description:Quincey Koziol2009-03-101-8/+6
| | | | | | | | | | Remove another call to H5E_clear_stack() from within the library. Clean up lots of compiler warnings. Tested on: Mac OS X/32 10.5.6 (amazon) (followup on other platforms forthcoming)
* [svn-r15628] Description:Quincey Koziol2008-09-161-4/+4
| | | | | | | | | | | | | Remove trailing whitespace from C/C++ source files, with the following script: foreach f (*.[ch] *.cpp) sed 's/[[:blank:]]*$//' $f > sed.out && mv sed.out $f end Tested on: Mac OS X/32 10.5.5 (amazon) No need for h5committest, just whitespace changes...
* [svn-r13829] Some systems (only SGI Altix ProPack 4 discovered so far) ↵Raymond Lu2007-06-021-0/+40
| | | | | | | | | | | | doesn't return correct file size from MPI_File_get_size. Bypass this problem by replacing it with stat. Add an option --disable-mpi-size in configure to indicate this function doesn't work properly. Add a test in testpar/t_mpi.c, too. If it returns wrong file size, print out a warning. Tested on kagiso (parallel) because already tested the same change to v1.6 on several platforms (kagiso, cobalt, copper, and sol).
* [svn-r13253] Updated all C and C++ style source code files with the THG ↵Albert Cheng2007-02-071-2/+3
| | | | | | | | | copyright notice. Tested platform: Kagiso only since it is only a comment block change. If it works in one machine, it should work in all, I hope. Still need to check the parallel build on copper.
* [svn-r12440] Purpose:Quincey Koziol2006-06-271-9/+9
| | | | | | | | | | | Code cleanup Description: Trim trailing whitespace in Makefile.am and C/C++ source files to make diffing changes easier. Platforms tested: None necessary, whitespace only change
* [svn-r12044] Purpose:MuQun Yang2006-03-091-25/+235
| | | | | | | | | | | | | | | Add new tests Description: Collective IO doesn't work for some platforms/mpio packages when more than one process has no contributions to IO. Solution: 1. Add a collective IO test to verify the correctness of the library when more than one process has no contributions to IO. 2. Add the similar MPI-IO test in t_mpi to help us maintain in more platforms. Platforms tested: heping, mir, copper Misc. update:
* [svn-r11483] Purpose:Leon Arber2005-09-291-7/+7
| | | | | | | | | | | | | | | | bug fix. Description: The complex derived datatype test assumed that the fill value would be 0. This is not the case on all systems. Solution: Modified the test to check against a known value in the outbuf array, instead of the fill value. Platforms tested: heping and MCR. Misc. update:
* [svn-r11481] Purpose:Leon Arber2005-09-291-1/+1
| | | | | | | | | | | | | | | bug fix. Description: Fixed typo in a comment. The word "file" was supposed to be "fill." The explanation of how the complex derived datatype test works is much clearer now. Solution: Platforms tested: minor change. Misc. update:
* [svn-r11459] Purpose:MuQun Yang2005-09-221-2/+3
| | | | | | | | | | | | | | | | | | A bug fix Description: MPI_Status_IGNORE is treated as a NULL pointer for mpich 1.2.4 or similar MPI packages. It caused segmentation fault for MPI derived datatype test. Solution: Define MPI_STATUS status, and pass &status into MPI_File_read and MPI_File_write. Platforms tested: too trivial to test. Misc. update:
* [svn-r11458] Purpose:Albert Cheng2005-09-221-13/+30
| | | | | | | | | | | | | | | | | | Improvement. Description: The test may hang if there are system failures that some processors are not working. Solution: Added the ALARM calls to limit all tests be done with the default alarm time. So, even if a process is hanging, the ALARM signal would terminate the process. Platforms tested: tg-login2 of NCSA. Misc. update:
* [svn-r11292] Purpose:Albert Cheng2005-08-231-3/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | "bug fix" Description: The test_mpio_derived_dtype() often hangs when fails. So it was not run by default to avoid hanging the daily tests or confusing users. But then new system or new codes in collective chunk fails while one can't tell for sure if it is because of the complicated derived type failures or something else. Solution: Changed the logic so it is skipped only if it is known that the complicated MPI derived type does not work. (This is indicated by macro H5_MPI_COMPLEX_DERIVED_DATATYPE_WORKS NOT defined. Platforms tested: heping pp (where it is tested by default). Modi4 pp (where it is SKIPPED by default.) I also forced modi4 to test it and modi4 said it actually is working and should change the setting of H5_MPI_COMPLEX_DERIVED_DATATYPE_WORKS to working?!! Misc. update:
* [svn-r11291] Purpose:Albert Cheng2005-08-231-33/+32
| | | | | | | | | | | | | | | | | | Code cleaning. Description: The block of code that is conditioned by the H5_MPI_COMPLEX_DERIVED_DATATYPE_WORKS and manipulates the return code of test_mpio_derived_dtype, does not really belong in main. If return code of test_mpio_derived_dtype needs to be adjusted, it should be done in test_mpio_derived_dtype. Solution: Moved that block of code test_mpio_derived_dtype. Platforms tested: heping PP. Misc. update:
* [svn-r11245] Purpose:Quincey Koziol2005-08-131-30/+30
| | | | | | | | | | | | | | | | | | | | Code cleanup Description: Trim trailing whitespace, which is making 'diff'ing the two branches difficult. Solution: Ran this script in each directory: foreach f (*.[ch] *.cpp) sed 's/[[:blank:]]*$//' $f > sed.out && mv sed.out $f end Platforms tested: FreeBSD 4.11 (sleipnir) Too minor to require h5committest
* [svn-r10510] Purpose:Albert Cheng2005-03-301-31/+39
| | | | | | | | | | | | | | Improvement. Description: The derived datatype test often hangs when it fails. This blocks daily test or automatic build. Run it only when hi verbose mode is used. Platforms tested: Tested in eirene pp. Misc. update:
generated by cgit v0.12 at 2024-07-05 07:41:14 (GMT)