summaryrefslogtreecommitdiffstats
path: root/src/H5Cmpio.c
Commit message (Collapse)AuthorAgeFilesLines
* Fixed HDFFV-10404Binh-Minh Ribler2018-07-261-1/+1
| | | | | | | | | Description: Applied the typo fixes from user's report. The previous pull request couldn't be merged because it was too old, and it was too complicated for me to resolve conflicts. Platform tested: Linux/64 (jelly) - very minor
* Add API context interface and use it throughout the library.Quincey Koziol2018-03-151-92/+47
|
* 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.
* Checkin of fix for CGNS bugmainzer2017-04-061-23/+79
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | (https://jira.hdfgroup.org/browse/HDFFV-10055). Briefly, in H5C_collective_write() in H5Cmpio.c, the metadata cache attempts to perform a collective write of metadata cache entries. This worked fine as long as all processes had at least one entry to write. However, when the process has no entries, the function tries to participate in the collective write by calling MPI_File_set_view(), MPI_File_write_all() and then MPI_File_set_view() again, to match the calls in H5FD_mpio_write(). After pull request 183, the CGNS test benchmark_hdf5 started failing. On investigation, I determined that the failure occurred in the first call to MPI_File_set_view() in the "no data to write" path through H5C_collective_write(). Note that pull request 183 did not create the problem, it only exposed it. The bug can be observed after pull request 182 if one executes the CGNS progam src/ptests/benchmark_hdf5 with 90 processes. The problem appears to have been that the calls to MPI_File_set_view() in H5C_collective_write() and H5FD_mpio_write() were using different values for the info parameter. I patched the problem by adding a MPI specific VFD call allowing me to get the MPI_Info used in H5FD_mpio_write() for use in MPI_File_set_view() calls in H5C_collective_write(). Tested serial & parallel, debug & production on Jelly.
* Final merge of page buffering branch to developQuincey Koziol2017-03-141-3/+4
|
* Remove some usage of "prefetched_dirty" flag (which hasn't been merged from theQuincey Koziol2017-03-101-413/+577
| | | | | page_buffering branch yet. Also, bring over improvements to flush candidate entries for parallel code.
* Normalize against incoming page buffering changes.Quincey Koziol2017-03-011-7/+8
|
* Corrected version of 4b5e05c084f93c35dae946c2c9e814d565a613b0:Quincey Koziol2017-02-281-119/+73
| | | | | Fix some more signed -> unsigned value issues with cache data structures, also misc. style cleanups. All to align w/incoming page_buffering changes.
* Revert "Fix some more signed -> unsigned value issues with cache data ↵Quincey Koziol2017-02-281-26/+72
| | | | | | structures, also" This reverts commit 4b5e05c084f93c35dae946c2c9e814d565a613b0.
* Fix some more signed -> unsigned value issues with cache data structures, alsoQuincey Koziol2017-02-231-72/+26
| | | | misc. style cleanups. All to align w/incoming page_buffering changes.
* Misc. style cleanups from the page_buffering branch.Quincey Koziol2017-02-181-121/+77
|
* Remove "collective write list" parameter from H5C__flush_single_entry() as itQuincey Koziol2016-11-281-21/+32
| | | | | is only used in a couple of places. The collective write list has been moved to be internal to the cache data structure instead.
* Eliminate unnecessary data structure for parallel collective metadata cache I/OQuincey Koziol2016-11-281-45/+10
|
* Add a flag for H5C__flush_single_entry() to allow the parallel code to requestQuincey Koziol2016-11-251-10/+32
| | | | | that images for entries be generated, even when not writing the entry from an MPI rank.
* Clean up cache code to eliminate dead-ends and unify code.Quincey Koziol2016-11-101-8/+8
|
* [svn-r29077] Description:Quincey Koziol2016-02-101-88/+117
| | | | | | | | Normalize against the trunk, in preparation for final merge. Tested on: MacOSX/64 10.11.3 (amazon) w/serial & parallel (h5committest not required on this branch)
* [svn-r28959] merge from trunk.Mohamad Chaarawi2016-01-221-3/+2
|\ | | | | | | renaming metadata dxpl properties.
| * [svn-r28950] - remove META_FLUSH_COLLECTIVELY property for delayed sanity ↵Mohamad Chaarawi2016-01-211-3/+2
| | | | | | | | | | | | | | | | | | | | checks from metadata dxpls - remove H5AC_ind_dxpl_id and use only H5AC_dxpl_id everywhere instead. - remove flush_me_collectively flag from cache entries - add a collective sanity check (MPI_Barrier) for every HDF5 API routine that could possibly touch the file. This is trigerred when the environment variable H5_COLL_API_SANITY_CHECK is set to a non 0 digit. tested on BB-8 with serial and parallel.
* | [svn-r28649] - add new API to toggle collective metadata write.Mohamad Chaarawi2015-12-141-10/+16
| | | | | | | | | | - set default to FALSE - fix some bugs.
* | [svn-r27929] merge from trunk.Mohamad Chaarawi2015-10-011-2/+2
|\ \ | |/
| * [svn-r27768] Description:Quincey Koziol2015-09-141-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | 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-r27436] merge from trunk.Mohamad Chaarawi2015-07-271-9/+259
|/
* [svn-r27294] Description:Quincey Koziol2015-06-291-49/+9
| | | | | | | | | | Clean up parameters to H5C__flush_single_entry: accept cache entry instead of address, and make new flag for deleting entry from skiplist on destroy instead of a separate parameter to the routine. Tested on: MacOSX/64 10.10.3 (amazon) w/serial & parallel Linux/32 2.6.x (jam) w/serial & parallel
* [svn-r27293] Description:Quincey Koziol2015-06-271-0/+1260
Split parallel metadata cache code into separate source code modules. Tested on: MacOSX/64 10.10.3 (amazon) w/serial & parallel (too minor for h5committest)
generated by cgit v0.12 at 2024-11-09 16:28:36 (GMT)