| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
| |
and removed the redundant cleaning of Makefile.
Tested: jam parallel.
|
|
|
|
| |
Tested on jam and abe.
|
|
|
|
|
|
| |
Changed 'THG' to 'The HDF Group' in various HDF5 source files,
most of which are <subdirectory>/COPYING.
-- Closes Bugzilla entry 1403.
|
|
|
|
|
|
|
|
| |
HDF5 library. The Dependencies files are generated by
"make depend".
Tested:
h5committest, also serial in Kagiso is tested.
|
|
|
|
|
|
|
|
| |
Change the 'coord' parameter for H5Sselect_elements() from 'hsize_t **' to
'hsize_t *' in this branch also.
Tested on:
Mac OS X/32 10.5.1 (amazon)
|
|
|
|
| |
removing the stream-vfd.
|
|
|
|
|
|
|
| |
H5S_SEL_NONE case.
Added it in and added a test for one process not to participate writing or reading
data using H5Sselect_none (function none_selection_chunk in testpar/t_dset.c).
|
|
|
|
|
|
|
|
|
|
|
| |
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), cobalt, copper, and sol.
|
| |
|
| |
|
| |
|
|
|
|
| |
(combinations of) filters. Tested on kagiso and copper.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bug problem.
Description:
CHunk allocation actually does not always work in parallel. See Bug 281 and 636.
Case 2 test exposed the problem in an intermittent manner. Skip the test by
default but allow it to be tested IF verbose is set to at least low.
Platform tested:
Kagiso parallel since that is where it sometimes failed.
The problem did not show up in copper. The fix (skipping) is
straight forwarded. So, no other machine tested.
|
|
|
|
| |
Tested platform: Kagiso (serial, pp)
|
|
|
|
| |
Tested platform: Kagiso (serial, pp)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Description:
h5_get_file_size() was coded to return 0 if failed but
file size can be 0. Changed the failure return value to -1
which is allowed by the returned type of off_t which is a signed
type.
Also changed the checking code of the stat call to just == 0
since that is how it is defined.
Test:
Could test it in heping only. Both Sol and Copper failed to
compiled due to error in the Direct IO VFD code.
|
|
|
|
| |
h5_mpi_get_file_size() is no longer used. Removed the code.
|
|
|
|
|
|
|
|
| |
Description:
Add per-directory abbreviated copyright notices
(abbreviated COPYING files pointing to full notices).
Tested:
MANIFEST verified; not otherwise tested.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bug fix.
Description:
It failed when only 1 is used to test.
Solution:
Cleanup the code a little so that it works for any number
of processes to invoke it.
Platforms tested:
h5committested
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bug fix.
Description:
Sometimes the parallel prefix is given in the form of nfs:/mnt/pfs which
if given to a non-MPIO VFD like the default H5Fcreate, it would fail.
Called h5_rmprefix which would return the non-prefix component
part of the file name which would be okay for the default H5Fcreate and
such.
Platforms tested:
Tested in heping parallel.
|
|
|
|
|
|
|
|
|
|
|
| |
New feature
Description:
Added test to verify if the storage space allocation methods are compatible
between serial and parallel modes.
Platforms tested:
Tested on heping, copper in parallel mode.
|
|
|
|
| |
'hdf5_1_6'.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
bug fix 504
Description:
testpar/t_mpi would hang if $HDF5_NOCLEANUP is set. E.g.,
% env HDF5_NOCLEANUP=yes mpirun -np 3 ./t_mpi
This happened because the environment variables are not exported to all
mpi processes by the mpirun command. So, some attempted to do cleanup
while others don't and some hang waiting for others to act.
Solution:
Instead individual program checking getenv, they all just called h5_cleanup
no matter. h5_cleanup now uses getenv_all to check the $HDF5_NOCLEANUP if
it is in parallel mode.
Platforms tested:
h5committested, tested pp in heping too.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Appearance change.
Description:
depend1.in:
Change the style of the copyright generation commands to a simplier
style.
Dependencies:
Regenerated the Dependencies file.
Platforms tested:
Tested in heping in serial and parallel modes.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
To support collective IO for irregular selection in the upcoming 1.6.5 release
Description:
Make the collective IO tests the same as 1.7 branch.
The selections are complicated and big.
Solution:
Platforms tested:
AIX 5.1(32bit and 64bit)
Linux 2.4(heping)-mpich 1.2.6
Linux 2.4(NCSA teragrid) -mpich 1.2.5
Altrix(cobalt)
IRIX 6.5- c compiler version 7.4.3(NCAR SGI)
Linux 2.4(tune) - CMPI 2.1.0
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Code cleanup
Description:
Trim trailing whitespace, which is making 'diff'ing the two branches
difficult.
Solution:
Ran this script in each directory:
foreach f (*.[ch] *.cpp)
sed 's/[[:blank:]]*$//' $f > sed.out && mv sed.out $f
end
Platforms tested:
FreeBSD 4.11 (sleipnir)
Too minor to require h5committest
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
feature.
Description:
Added two new make check targets,
check-s: serial tests
check-p: parallel tests.
Check will run check-s and check-p, have the same effect as before.
Added $TEST_SCRIPTS_PARA for parallel test scripts.
Platforms tested:
h5committested".
Also, tested in heping (serial and pp) to verify with previous
test output for consistency.
Tested in modi4 for the special case of pmake (in progress.)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
typo fix and small improvement.
Description:
t_coll_chunk.c:
ccdataset_vrfy() was using a wrong routine name to identify itself.
testphdf5.c:
Add a definition of NFILENAME to be the common dimension size of
FILENAME[] and filenames[][] since they must have the same first
dimension size.
Platforms tested:
h5committested.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Remove feature
Description:
Retire threaded, balanced binary tree code from HDF5 use. Requiescat in
pace...
Also, regenerate dependencies files.
Platforms tested:
FreeBSD 4.10 (sleipnir) w/parallel
Too minor to require full h5committesting (the code is already
disconnected from everything except its tests)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bug Fix/Code Cleanup/Doc Cleanup/Optimization/Branch Sync :-)
Description:
Generally speaking, this is the "signed->unsigned" change to selections.
However, in the process of merging code back, things got stickier and stickier
until I ended up doing a big "sync the two branches up" operation. So... I
brought back all the "infrastructure" fixes from the development branch to the
release branch (which I think were actually making some improvement in
performance) as well as fixed several bugs which had been fixed in one branch,
but not the other.
I've also tagged the repository before making this checkin with the label
"before_signed_unsigned_changes".
Platforms tested:
FreeBSD 4.10 (sleipnir) w/parallel & fphdf5
FreeBSD 4.10 (sleipnir) w/threadsafe
FreeBSD 4.10 (sleipnir) w/backward compatibility
Solaris 2.7 (arabica) w/"purify options"
Solaris 2.8 (sol) w/FORTRAN & C++
AIX 5.x (copper) w/parallel & FORTRAN
IRIX64 6.5 (modi4) w/FORTRAN
Linux 2.4 (heping) w/FORTRAN & C++
Misc. update:
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Code cleanup & optimizations
Description:
Clean up some of the code in attributes to avoid allocating memory and
performing type conversions when the conversion is a noop.
Avoid memory allocations of attribute data structures by switching to use
library's free list memory allocator routines.
Avoid memory allocations of object header continuation data structures by
switching to use library's free list memory allocator routines.
Rearrange threaded, balanced binary tree macros slightly to avoid some
overhead.
Platforms tested:
FreeBSD 4.10 (sleipnir) w/parallel
Solaris 2.7 (arabica)
Too minor to require h5committest
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Improvement.
Description:
Made all processes print hostname() by default so that it is easier
to spot problems.
Platforms tested:
Tested in copper only. It is a trivial small change.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bug fix
Description:
Relax restrictions on parallel I/O to allow compressed, chunked datasets
to be read in parallel (collective access will be degraded to independent
access, but will retrieve the information still).
Platforms tested:
FreeBSD 4.10 (sleipnir) w/parallel
Solaris 2.7 (arabica)
IRIX64 6.5 (modi4)
h5committest
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Code clean up
Description:
The tests used to have their own test file names due to
the original program layout. Now that it is using the
common test interface, individual test can be invoked
at will (via -o). There is no need to have different
test filenames. Only requirement is that certain read
tests must follow immediately the corresponding write
test since they use the same file.
I have combined all test file names into just one common
file name. This reduces the printout of test file name,
very beneficial when the test is run by large number of processes.
It makes future code maintenance easier too.
Platforms tested:
Tested in Eirene(PP) only. No h5committest because this is
limited to the parallel tests and the changes are trivial.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Shrink HDF5 parallel test (folded what Kent has done in v1.7 to v1.6.)
Description:
Previously the collective chunk IO tests created and opened four HDF5 files;
it turned out that all collective chunk IO tests can use one file for testing.
Solution:
To use one file for all collective chunk IO tests with trunc option to be set in
H5Fcreate.
Platforms tested:
eirene (no need to use h5committest)
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Text display change
Description:
Changed the test names to much shorter strings for easier
use.
Platforms tested:
No h5committed test. Only test parallel in eirene.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
| |
Code cleanup.
Removed bunch of old options (r,w,v,i,b,e) that are no longer valid
or useful after adopting the general test interface. Moved the test
of sizeof MPI_Offset into the test routine itself.
Platforms tested:
Eirene and Sol using pp mode.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
feature
Description:
Another revamp of the test interface.
TestInit: is used to register Test Program name, test program specific
Usage and option parsing routines.
TestUsage: will invoke extra usage routine if provided.
TestParseCmdLine: will invoke extra option parsing routine if provided.
GetTestSummary() and GetTestCleanup() replaces the previous Summary and
CleanUp arguments of TestParseCmdLine.
test/testhdf5, test/ttsafe.c, testpar/t_mpi.c, testpar/testphdf5.c:
All have been updated to use the new Test Routines.
testpar/t_mpi.c:
Also a fix of a compiler optimization bug when pgcc in Linux is
used to compile it. Changed buf[] and expected to unsigned char
type to avoid a bug that failed to do sign-extension.
Platforms tested:
"h5committested"
Also tested thread-safe option in eirene.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Fix bug/feature which caused testphdf5 to fail when run with more than
32 processes.
Description:
32 process limit was a hard coded constant.
Solution:
Modified most of the routines in t_mdset.c to adapt dynamically to
the current number of processes. In passing, I also tidied up a
few memory leaks.
Platforms tested:
copper with a scattering of numbers of processes from 4 to 32, and all
numbers of processes from 32 to 64 inclusive.
h5committested
serial and parallel tests on Eirene
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Purpose:
Bug fix.
Description:
1. The IF-block of skipping collective chunk IO tests when the number of
processes is greater than some number essentially skipped all parallel tests.
2. John tested at copper with the number of processor = 64 and collective
chunk IO tests passed, so we increase the number of precessor =24 to 64 for
skipping the test.
Solution:
1. change the IF block flow so that it only skips collective chunk IO tests when
the number of process is greater than 64.
Platforms tested:
copper(only parallel test, no needs to test oh other platforms).
Misc. update:
|
|
|
|
|
|
|
|
|
|
| |
Feature
Description:
Updated to use the new syntax of TestParseCmdLine().
Platforms tested:
On eirene both serial and parallel.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
For collective chunk IO test, only let the main process(process 0) generate
the "skipped message".
Description:
Solution:
Platforms tested:
linux 2.4
Too trivial to use h5committest.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Parallel HDF5 Collective chunk IO testing message added
Description:
collective chunk IO tests have been verified with the number of process greater than 24 and
the test is very slow with big number of process.
That may cause confusions to users who run collective chunk IO tests.
Solution:
To avoid possible confusions, A if-block will be used to check whether the number of process
is greater than 24. If yes, the collective chunk tests will be skipped and a message will be printed out.
Platforms tested:
To trivial for h5committest,testing platform: eirene.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
To make collective chunk IO test more general
Description:
Previous collective chunk IO test only works with number of processor less than 4.
In case people would like to test with more processors, more general tests need to be used.
Solution:
The following changes have been made:
1. Change the way to use discontiguous hyperslab selection to work with larger number of processors,
2. Increase size of data array
Now, I can test with processor number = 12; however, the fourth test is very slow to the independent IO write and read.
Platforms tested:
eirene(only parallel test codes are modified, no need to test on other platforms).
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Cleanup and bug fix.
Description:
Bug fix:
the checking of dobig test was done in the wrong place
such that tests added after it would be run even for the -b option.
Moved the dobig test checking to AFTER all tests are added.
Cleanup:
Removed old code now that the new way is working fine.
Platforms tested:
Tested in Eirene parallel only.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Feature
Description:
Added a feature such that if the test name starts with '-', do not run it
by default.
Platforms tested:
Eirene both serial and parallel.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Backport feature
Description:
Backport Kent's collective chunk I/O work to date into the release branch.
Also, minor code cleanups, etc.
Platforms tested:
FreeBSD 4.10 (sleipnir) w/parallel
IRIX64 6.5 (modi4)
h5committested
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bug fixes & code cleanups
Description:
Backport MPI-I/O changes from the development branch to the release
branch in preparation for bringing Kent's collective chunk I/O changes back.
Removed last vestiges of FPHDF5 from this branch, as it was never working
here.
Various code cleanups & syncrontizations to better align with development
branch code and reduce diffs.
Regenerate dependencies.
Platforms tested:
FreeBSD 4.10 (sleipnir) w/parallel
IRIX64 6.5 (modi4)
h5committested
|
| |
|