Allow H5Pset_evict_on_close to be called regardless of whether a parallel build of HDF5 is being used
Fail during file opens if H5Pset_evict_on_close has been set to true on the given File Access Property List and the size of the MPI communicator being used is greater than 1
* Updated source file copyright headers to remove "Copyright by the Board of Trustees
of the University of Illinois", which is kept in the top-level COPYING file.
* H5Oflush causes H5Fclose to trigger an assertion failure in metadata cache for parallel. This commit makes sure H5Oflush fails for parallel until this problem is solved in the future.
* Committing clang-format changes
* Changed the use of H5F_get_driver_id to H5F_HAS_FEATURE.
Co-authored-by: songyulu <songyulu@jelly.ad.hdfgroup.org>
Co-authored-by: github-actions <41898282+github-actions[bot]@users.noreply.github.com>
* Committing clang-format changes
* Brings the native VFD H5Fdelete() implementation from Bitbucket
Only brings the 'del' callbacks, not the 'open/close' scheme.
* Formatter changes
* Committing clang-format changes
* Fixes direct VFD callback name
* Removes UNUSED macro from family API call
* Adds barrier and rank 0 check to MPI-I/O VFD delete
* Revert "Adds barrier and rank 0 check to MPI-I/O VFD delete"
This reverts commit 909765f759.
* Revert "Revert "Adds barrier and rank 0 check to MPI-I/O VFD delete""
This reverts commit 9b04bef115.
* Adds a second barrier after the delete in MPI-I/O VFD
* Only delete files in the core VFD when the backing store flag is set
* Fixes string issues in multi VFD
Also, h5test.c cleanup code now uses H5Fdelete().
* Formatted source
* Rework fapl checks for MPI-I/O VFD delete callback
Co-authored-by: github-actions <41898282+github-actions[bot]@users.noreply.github.com>
* 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.
* 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
* 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>
* 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.
with an alignment threshold set to be larger than the chunk size but smaller
than the size of the small data aggregator.
Tested: koala, ostrich (h5committest); jelly, ummon
Remove all traces of MPI-POSIX VFD and GPFS detection/code.
Remove remaining traces of stream VFD.
Remove testpar/t_posix_compliant test (it's not actually verifying anything).
Clean up H5D__mpio_opt_possible() further.
Moved environment variable that disables MPI collective operations into
MPI-IO VFD (instead of it being in src/H5S.c).
A few other small code cleanups.
Tested on:
Mac OSX/64 10.9.2 (amazon) w/parallel & serial
Check in Mohamad's changes to support collective I/O on point selections,
along with some other minor cleanups.
Tested on:
Mac OSX/64 10.9.2 (amazon) w/parallel & serial
(h5committest forthcoming)
Stop aliasing property to indicate internal collective metadata operations
with property to perform collective raw data operations from the application.
Tested on:
Mac OSX/64 10.8.3 (amazon) w/paralllel
HDFFV-8146 - Remove "multi-chunk IO without optimization" sub-feature from MPI I/O optimization for chunked dataset feature
Description:
The “multi-chunk IO without optimization” feature is removed and made the related xfer property (H5FD_MPIO_CHUNK_MULTI_IO) go directly to “multi-chunk-io” feature.
Also update/fix/cleanup testings (chunk collective IO and actual chunk opt mode) accordingly.
Tested:
jam (linux32-LE), koala (linux64-LE), ostrich (linuxppc64-BE), fred (mac64-LE), Windows (32-LE cmake), cmake (jam)
HDFFV-8143 Provide a routine(s) for telling the user why the library broke collective data access
Description:
Added H5Pget_mpio_no_collective_cause() function that retrive reasons why the collective I/O was broken during Read/Write IO access.
Reasons to break collective I/O:
- SET_INDEPENDENT
- DATATYPE_CONVERSION
- DATA_TRANSFORMS
- MPIPOSIX
- NOT_SIMPLE_OR_SCALAR_DATASPACES (NULL Space)
- POINT_SELECTIONS
- NOT_CONTIGUOUS_OR_CHUNKED_DATASET (Compact or External-Storage)
- FILTERS
Tested:
jam (linux32-LE), koala (linux64-LE), ostrich (linuxppc64-BE), tejeda (mac32-LE), linew (solaris-BE)
Check in "actual I/O mode" feature to trunk. Will merge back to 1.8 branch
after it bakes over the weekend.
Tested on:
FreeBSD/32 8.2 (loyalty) w/gcc4.6, w/C++ & FORTRAN, in debug mode
FreeBSD/64 8.2 (freedom) w/gcc4.6, w/C++ & FORTRAN, in debug mode
Linux/32 2.6 (jam) w/PGI compilers, w/default API=1.8.x,
w/C++ & FORTRAN, w/threadsafe, in debug mode
Linux/64-amd64 2.6 (koala) w/Intel compilers, w/default API=1.6.x,
w/C++ & FORTRAN, in production mode
Solaris/32 2.10 (linew) w/deprecated symbols disabled, w/C++ & FORTRAN,
w/szip filter, w/threadsafe, in production mode
Linux/PPC 2.6 (heiwa) w/C++ & FORTRAN, w/threadsafe, in debug mode
Linux/64-ia64 2.6 (ember) w/Intel compilers, w/C++ & FORTRAN,
in production mode
Linux/64-amd64 2.6 (abe) w/parallel, w/FORTRAN, in debug mode
Mac OS X/32 10.6.8 (amazon) in debug mode
Mac OS X/32 10.6.8 (amazon) w/C++ & FORTRAN, w/threadsafe,
in production mode
The shape same tests ran too long. Break them into smaller subtests
so that they can finish sub-test in a shorter time. Easier to tell
which one sub-test is taking too much time and/or errors occur in
one fo the sub-tests.
This one breaks the contig_hyperslab_dr_pio_test() into 4 smaller
sub-tests.
Tested: h5committest
John Mainzer fixed the bug and added a test which wrote file and flush a few
time; close the file then open it by serial and read simple structure. I
changed the test to two parallel running parts of ..._writer and ..._reader
and have the reader verify the file after every flush by the writer.
Tested: parallel in Jam and Amani.
of the H5Ocache.c code to update its image of the on disk representation
of the object header on a call to the clear callback.
This wasn't an issue as long as all flushes of the object header were
made from the same process, but if an object header is modified, and
then flushed on one process and cleared on the rest, the changes were
not be reflected in the images of the on disk representation on all
processes where the object header was cleared rather than flushed.
If one of these processes did the next flush, the changes were lost in
the on disk representation.
Fixed this by causing all dirty messages and to be written to the copy
of the on disk image maintained by the object header code on both flush
and clear.
Also added associated test code in t_mdset.c.
Also checking in some cache debug code developed while chasing this bug.
Commit tested and tested (parallel) on phoenix.
Bring "shape same" changes from LBL branch to trunk. These changes
allow shapes that are the same, but projected into dataspaces with different
ranks to be detected correctly, and also contains code to project a dataspace
into greater/lesser number of dimensions, so the I/O can proceed in a faster
way.
These changes also contain several bug fixes and _lots_ of code
cleanups to the MPI datatype creation code.
Many other misc. code cleanup are included as well...
Tested on:
FreeBSD/32 6.3 (duty) in debug mode
FreeBSD/64 6.3 (liberty) w/C++ & FORTRAN, in debug mode
Linux/32 2.6 (jam) w/PGI compilers, w/default API=1.8.x,
w/C++ & FORTRAN, w/threadsafe, in debug mode
Linux/64-amd64 2.6 (amani) w/Intel compilers, w/default API=1.6.x,
w/C++ & FORTRAN, in production mode
Solaris/32 2.10 (linew) w/deprecated symbols disabled, w/C++ & FORTRAN,
w/szip filter, in production mode
Linux/64-ia64 2.6 (cobalt) w/Intel compilers, w/C++ & FORTRAN,
in production mode
Linux/64-amd64 2.6 (abe) w/parallel, w/FORTRAN, in debug mode
Mac OS X/32 10.6.3 (amazon) in debug mode
Mac OS X/32 10.6.3 (amazon) w/C++ & FORTRAN, w/threadsafe,
in production mode
1. In H5Dwrite and H5Dread, let the data buffer point to a fake address if the application passes
in an empty buffer. This is mainly for MPIO programs that some processes may not have any
data to write or read but still participate the I/O. This solution solves some MPI's problem
like the ChaMPIon on tungsten which doesn't support empty buffer.
2. The ChaMPIon on tungsten doesn't support complex derived MPI data type correctly and collective
I/O when some processes don't have any data to write or read correctly. Detect the compiler
"cmpicc" in the system-specific config file and set the variables for these two cases to false.
The PHDF5 library already has set up a way to switch collective chunked I/O to independent
under these two cases.
3. A bug fix - During the work of the optimization for compound data I/O, the case for switching
collective chunked I/O to independent I/O was leftout. Fixed it by adding I/O caching to it in
H5D_multi_chunk_collective_io in H5Dmpio.c.
Tested on tungsten, cobalt, and kagiso for parallel; on linew and smirom for serial.
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.
