Description: Removed PABLO from the source
Solution:
Platforms tested: arabica with 64-bit, copper with parallel,
heping with GNU C and C++ and PGI fortran (but
I disabled hl, there is some weird problem only
on heping: F9XMODFLAG is not
propagated to the Makefile files
Misc. update:
Code cleanup
Description:
Various minor tweaks to clean code up and bring it into closer
syncronization with the release branch.
Platforms tested:
FreeBSD 4.10 (sleipnir) w/parallel
h5committested
IRIX64 6.5 (modi4)
Code cleanup & minor optimization
Description:
Re-work the way interface initialization routines are specified in the
library to avoid the overhead of checking for them in routines where there is
no interface initialization routine. This cleans up warnings with gcc 3.4,
reduces the library binary size a bit (about 2-3%) and should speedup the
library's execution slightly.
Platforms tested:
FreeBSD 4.10 (sleipnir) w/gcc34
h5committest
Code cleanup
Description:
Clean up lots of warnings based on those reported from the SGI compilers
as well as gcc.
Platforms tested:
SGI O3900, IRIX64 6.5 (Cheryl's SGI machine)
FreeBSD 4.9 (sleipnir) w/ & w/o parallel
h5committest
bug fix.
Description:
H5FD_mpio_init was calling the public API version of H5Iget_type()
which would clear the error stack, thus cleared away error messages
prematurely.
Solution:
Changed it to call the private version of H5I_get_type() which
does not clear the error stack.
Platforms tested:
o2 (SGI) parallel.
Bug fix.
Description:
Revert the optimization to the MPI-I/O VFD from earlier this week that
eliminated calling MPI_File_set_size() when a file was truncated. This doesn't
work because of the way we track the 'eoa' (end of allocated space) in the
file: we just advance the eoa value when space is allocated in the file and we
don't zero out the space in the file. This causes a problem where we assume
that all "newly allocated" space in the file contains zero bytes, but if we
don't call MPI_File_set_size(), the file can contain the previous data (if the
file previously existed) and not zeros.
Unfortunately, because we allow independent raw data parallel I/O, there
is no way to address this issue. :-(
Solution:
Revert to previous method of retrieving the file's size, etc. from before
the optimization.
Platforms tested:
FreeBSD 4.9 (sleipnir) w/parallel
too minor to require h5committest.
Bug fix
Description:
Move assertion to allow closing non-HDF5 files with the MPI-I/O VFD to
work correctly again.
Platforms tested:
FreeBSD 4.9 (sleipnir)
h5committest
Code cleanup
Description:
Add destructor to match constructor fr VFLs when they are shut down by the
library.
Solution:
Added H5FD_*_term() routines to "undo" changes made in H5FD_*_init()
routines.
Platforms tested:
IBM p690 (copper)
too minor to require h5committest
Bug fix/optimization
Description:
Address slowdown in MPI-I/O file metadata operations that was introduced
mid-stream. We now _require_ a POSIX compliant parallel file system for the
MPI-I/O file driver (as well as for the MPI-POSIX file driver).
Also optimized file open operation when the file is being created by
reducing the number of collective & syncronizing calls.
Additionally, refactor the MPI routines into a common place, eliminating
duplicated code.
Platforms tested:
FreeBSD 4.9 (sleipnir) w/parallel
h5committest
Bug fix
Description:
When two property lists are compared, the H5Pequal routine was just
comparing the raw information for the property values. This causes problems
when the raw information contains pointers to other information.
Solution:
Allow a 'compare' callback to be registered for properties, so that a user
application get perform the comparison itself, allowing for "deep" compares of
the property value.
This was exported to the H5Pregister & H5Pinsert routines in the development
branch, but not the release branch.
Platforms tested:
FreeBSD 4.9 (sleipnir)
h5committest
Code cleanup, bug fixes
Description:
Wrap up rest of changes necessary for fixing the "short" MPI-I/O read
problem that Robb reported.
Platforms tested:
FreeBSD 4.9 (sleipnir)
too minor to require h5committest
Bug fix
Description:
MPIO driver did not detect partial read or write. It assumed if read
completed, all bytes requested are read. Therefore, if a dataset was
not completely written yet, the unread part will not be filled with
default fill value.
Solution:
Added the MPI_Get_elements call to find exactly how many bytes
are read (or written). For read case, if not enough is read,
the rest is padded with zeros. For write case, it is an error
if not able to write them all in first attempt. (It is not
always possible to repeat write for MPIO since file-view may
be changed, collective would hang, etc. So, we do just one attempt.)
Platforms tested:
eirene (pp). Should work for other platforms since these
have been tested in v1.6.
Misc. update:
Code cleanup
Description:
Clean up compiler warnings, especially the 'FUNC' variable not used which
comes out in production mode.
Solution:
Had to add a new FUNC_ENTER_NOAPI_NOINIT_NOFUNC macro for those non-API
functions which don't need the 'FUNC' variable defined. (This will be _so_
much easier when C99 is standard on all our supposed platforms, since it has a
__FUNC__ macro... )
Platforms tested:
FreeBSD 4.9 (sleipnir)
too minor for h5committest (although there were lots of files changed, the
change was minor in each one)
Bug fix
Description:
Our previous "optimization" of metadata writing which only wrote metadata
from one process was abusing MPI-I/O and after some consultation with Rob Ross
and Rajeev Thakur, Albert & I have come up with a solution...
Solution:
Instead of only writing from one process, issue a collective write
operation with all processes, for metadata writes.
Platforms tested:
FreeBSD 4.9 (sleipnir)
h5committest
Bug fix & code cleanups
Description:
Change our use of MPI derived datatypes to not create datatypes with
"0-sized" lengths, which causes the LANL Q machine to hang.
Also, get rid of "prefer MPI derived datatypes" environment variable since
it has no advantage.
Platforms tested:
FreeBSD 4.9 (sleipnir) w & w/o parallel
h5committest
Code cleanup
Description:
Untwist the last few sections of code before starting on fixing the
problems with reading off the end of the file in earnest.
Platforms tested:
FreeBSD 4.9 (sleipnir)
FreeBSD 4.9 (sleipnir) w/parallel
h5committest not necessary - parallel only changes
Code cleanup
Description:
Straighten out more goofiness in the MPI code dealing with collective I/O
transfers - mostly make certain that a view is set if-and-only-if collective
I/O is occurring on raw data (and vice versa for views and independent I/O)
Platforms tested:
FreeBSD 4.9 (sleipnir) w/parallel & FPHDF5
too minor to repquire h5committest
Bug fix
Description:
The MPI_File_set_size() routine on ASCI Red is not able to extend files
so that they are larger than 2GB.
Solution:
Add an extra macro which controls whether MPI_File_set_size() can handle
>2GB offsets or if our "older" way of reading a byte, then writing a byte at
the appropriate offset should be used.
Platforms tested:
FreeBSD 4.9 (sleipnir)
h5committest
Code cleanup/Feature removal
Description:
Remove "round robin" writing of metadata in MPI VFDs (and a couple of other
places). This never really worked the way I hoped it would and it causes
problems on certain machines.
Platforms tested:
FreeBSD 4.8 (sleipnir) w/parallel
Too small for triple check.
Code cleanup
Description:
Clean up warnings exposed by compiling on O2K. Also, revert some of Bill
and my changes to the H5S_mpi_opt_types_g, etc. and settle them back into their
original location.
Platforms tested:
h5committested.
Minor improvement
Description:
Moved the H5FD_mpio_Debug initialization to H5FD_mpio_init() so
that it is done only once instead of every file open.
Fixed blocked out patch that checks on INFO object so that
H5FD_mpio_Debug can be set via the INFO object.
(All these had been done to v1.4, now folded them int v1.5)
Platforms tested:
Did not h5committest since this is purely parallel code.
The changes were made in an isolated copy in Copper.
Tested in Copper parallel.
Misc. update:
Code cleanup
Description:
Replaced the comm/info freeing with H5FD_mpio_comm_info_free to make
it cleaner and consistent.
Replaced couple FUNC_LEAVE_NOAPI(SUCCEED) with FUNC_LEAVE_NOAPI(ret_value).
These were bugs since it was possible errors may occur at FUNC_ENTER...()
time and this hardcoding would not report those errors.
Documented some modification history.
Platforms tested:
Did not h5committested because these are all MPI code and well protected
by HAVE_PARALLEL.
Tested in eirene and modi4, both parallel mode.
Misc. update:
Silly bug fix.
Description:
Forgot to put the comm/info duplication code in.
Solution:
Put them back in.
Platforms tested:
Did not run h5committest since the changes are all in the MPIO driver code.
Tested on eirene and Modi4, both parallel modes.
Misc. update:
Bug fixes/API changes
Description:
Previously, the Communicator and Info object arguments supplied
to H5Pset_fapl_mpio() are stored in the property with its handle
values. This meant changes to the communicator or the Info object
after calling H5Pset_fapl_mpio would affect the how the property
list function. This was also the case when H5Fopen/create operated.
They just stored the handle value. This is not according to the
MPI-2 defined behavior of how Info objects should be handled. (MPI-2
defines Info objects must be parsed when called.)
The old design was trying to avoid numerous duplicates of the same
information (e.g., every property object holds one version, every
file opened holds another version, when all of them are referring to
the same original version.) Nevertheless it is safer to implement
it according to MPI-2 definition.
Futhermore, the library often needs to do message passing using the
supplied communicator. Using the same communicator as the application
version may result in some messages mix up.
Solution:
H5Pset_fapl_mpio now stores a duplicate of each of the communicator
and Info object.
H5Pget_fapl_mpio returns a duplicate of its stored communicator and
Info object. It is now the responsibility of the applications to free
those objects when done.
H5Fopen/create also stores a duplicate of the communicator and Info
object supplied by the File Access Property list.
H5Fclose frees those duplicates.
There are a few more internal VFL call back functions that they
follow this "make duplicates" requirement.
Platforms tested:
"h5committested".
What other platforms/configurations were tested?
Eirene (mpicc), sol(mpicc), copper(parallel)
Misc. update:
New Feature
Description:
Added support for the lock and unlock function calls for file
drivers. Only FPHDF5 uses this feature. All of these drivers don't
define lock or unlock methods.
Platforms tested:
Linux, Modi4, Sol
Misc. update:
Potential bug fix.
Description:
The code to rotate the metadata writing process may not be compiled
correctly in all cases.
Solution:
Change from using "++mpi_round" to "mpi_round+1"
Platforms tested:
Eyeballed...
Bug Fix
Description:
Metadata cache in parallel I/O can cause hangs in applications which
perform independent I/O on chunked datasets, because the metadata cache
can attempt to flush out dirty metadata from only a single process, instead
of collectively from all processes.
Solution:
Pass a dataset transfer property list down from every API function which
could possibly trigger metadata I/O.
Then, split the metadata cache into two sets of entries to allow dirty
metadata to be set aside when a hash table collision occurs during
independent I/O.
Platforms tested:
Tested h5committest {arabica (fortran), eirene (fortran, C++)
modi4 (parallel, fortran)}
FreeBSD 4.7 (sleipnir) serial & parallel
Misc. update:
Updated release_docs/RELEASE
Updated
Description:
Updated Copyright notice.
Replaced HGOTO_ERROR calls involving MPI calls with HMPI_GOTO_ERROR.
Platforms tested:
Tested h5committest {arabica (fortran), eirene (fortran, C++)
modi4 (parallel, fortran)}? Tested on Eirene (PP) only since
the code is in the MPIO module only.
Code cleanup/new feature.
Description:
Split FUNC_LEAVE into API and non-API specific versions. This allows a
solution to compiling this branch with C++, as well as reducing the size
of the binaries produced.
Platforms tested:
FreeBSD 4.7 (sleipnir) w/serial, parallel (including MPE) & thread-safe
Lots of performance improvements & a couple new internal API interfaces.
Description:
Performance Improvements:
- Cached file offset & length sizes in shared file struct, to avoid
constantly looking them up in the FCPL.
- Generic property improvements:
- Added "revision" number to generic property classes to speed
up comparisons.
- Changed method of storing properties from using a hash-table
to the TBBT routines in the library.
- Share the propery names between classes and the lists derived
from them.
- Removed redundant 'def_value' buffer from each property.
- Switching code to use a "copy on write" strategy for
properties in each list, where the properties in each list
are shared with the properties in the class, until a
property's value is changed in a list.
- Fixed error in layout code which was allocating too many buffers.
- Redefined public macros of the form (H5open()/H5check, <variable>)
internally to only be (<variable>), avoiding innumerable useless
calls to H5open() and H5check_version().
- Reuse already zeroed buffers in H5F_contig_fill instead of
constantly re-zeroing them.
- Don't write fill values if writing entire dataset.
- Use gettimeofday() system call instead of time() system when
checking the modification time of a dataset.
- Added reference counted string API and use it for tracking the
names of objects opening in a file (for the ID->name code).
- Removed redundant H5P_get() calls in B-tree routines.
- Redefine H5T datatype macros internally to the library, to avoid
calling H5check redundantly.
- Keep dataspace information for dataset locally instead of reading
from disk each time. Added new module to track open objects
in a file, to allow this (which will be useful eventually for
some FPH5 metadata caching issues).
- Remove H5AC_find macro which was inlining metadata cache lookups,
and call function instead.
- Remove redundant memset() calls from H5G_namei() routine.
- Remove redundant checking of object type when locating objects
in metadata cache and rely on the address only.
- Create default dataset object to use when default dataset creation
property list is used to create datasets, bypassing querying
for all the property list values.
- Use default I/O vector size when performing raw data with the
default dataset transfer property list, instead of querying for
I/O vector size.
- Remove H5P_DEFAULT internally to the library, replacing it with
more specific default property list based on the type of
property list needed.
- Remove redundant memset() calls in object header message (H5O*)
routines.
- Remove redunant memset() calls in data I/O routines.
- Split free-list allocation routines into malloc() and calloc()-
like routines, instead of one combined routine.
- Remove lots of indirection in H5O*() routines.
- Simplify metadata cache entry comparison routine (used when
flushing entire cache out).
- Only enable metadata cache statistics when H5AC_DEBUG is turned
on, instead of always tracking them.
- Simplify address comparison macro (H5F_addr_eq).
- Remove redundant metadata cache entry protections during dataset
creation by protecting the object header once and making all
the modifications necessary for the dataset creation before
unprotecting it.
- Reduce # of "number of element in extent" computations performed
by computing and storing the value during dataspace creation.
- Simplify checking for group location's file information, when file
has not been involving in file-mounting operations.
- Use binary encoding for modification time, instead of ASCII.
- Hoist H5HL_peek calls (to get information in a local heap)
out of loops in many group routine.
- Use static variable for iterators of selections, instead of
dynamically allocation them each time.
- Lookup & insert new entries in one step, avoiding traversing
group's B-tree twice.
- Fixed memory leak in H5Gget_objname_idx() routine (tangential to
performance improvements, but fixed along the way).
- Use free-list for reference counted strings.
- Don't bother copying object names into cached group entries,
since they are re-created when an object is opened.
The benchmark I used to measure these results created several thousand
small (2K) datasets in a file and wrote out the data for them. This is
Elena's "regular.c" benchmark.
These changes resulted in approximately ~4.3x speedup of the
development branch when compared to the previous code in the
development branch and ~1.4x speedup compared to the release
branch.
Additionally, these changes reduce the total memory used (code and
data) by the development branch by ~800KB, bringing the development
branch back into the same ballpark as the release branch.
I'll send out a more detailed description of the benchmark results
as a followup note.
New internal API routines:
Added "reference counted strings" API for tracking strings that get
used by multiple owners without duplicating the strings.
Added "ternary search tree" API for text->object mappings.
Platforms tested:
Tested h5committest {arabica (fortran), eirene (fortran, C++)
modi4 (parallel, fortran)}
Other platforms/configurations tested?
FreeBSD 4.7 (sleipnir) serial & parallel
Solaris 2.6 (baldric) serial
Purpose:
New API functions
Description:
Added API functions to return pointer to low-level file handle
(H5Fget_vfd_handle and H5FDget_vfd_handle) and related property list
setting functions(H5Pset_family_offset and H5Pset_multi_type).
Platforms tested:
Linux 2.2(eirene), Solaris 2.7(arabica), IRIX64 6.5(modi4)
Code cleanup
Description:
Combined H5P_isa_class and H5I_object functionality into a new internal
H5P API function: H5P_object_verify, which checks that a property list is
the appropriate class and then returns the property list object associated
with the property list ID.
This reduces the source code by about 200 LOC and trims the library binary
some more.
Platforms tested:
FreeBSD 4.6 (sleipnir)
Code cleanup
Description:
Changed the last HRETURN* statements in the FUNC_ENTER macros into HGOTO*
macros, which reduces the size of the library binary in certain
configurations by another 10%
Platforms tested:
FreeBSD 4.6 (sleipnir) serial & parallel, IRIX64 6.5 (modi4) serial &
parallel
Code cleanup
Description:
Change most (all?) HRETURN_ERROR macros to HGOTO_ERROR macros, along with
HRETURN macros to HGOTO_DONE macros. This unifies the error return path
from functions and reduces the size of the library by up to 10% on some
platforms.
Additionally, I improved a lot of the error cleanup code in many routines.
Platforms tested:
FreeBSD 4.6 (sleipnir) serial & parallel and IRIX64 6.5 (modi4) serial &
parallel.
Bug Fix
Description:
It was possible to create corrupted metadata information (either in memory
or in the file or both) with a parallel I/O program because of the way
metadata writes were being handled for writes out of the metadata cache.
Solution:
Added a dataset transfer property called "block before metadata write"
which is used by the MPI-I/O and MPI-posix drivers to sync up all the
processes before attempting a metadata write. This property is currently
only for metadata writes from the metadata cache.
Platforms tested:
IRIX64 6.5 (modi4) w/parallel
New feature.
Description:
Added MPI-posix VFL driver. This driver uses MPI to coordinate actions, but
performs I/O directly with posix sec(2) I/O functions. This driver should
_NOT_ be used if the file accessed is not on a parallel filesystem.
Platforms tested:
FreeBSD 4.6 (sleipnir) w/parallel & IRIX64 6.5 (modi4) w/parallel
Bug Fix
Description:
When parallel I/O is used, the MPI-I/O VFL driver uses a "lazy" model to
call MPI_File_set_view() in order to reduce the number of calls to this
function. However, this is unsafe, because if a collective I/O which uses
MPI derived types (and thus uses MPI_File_set_view()) is immediately
followed by an independent I/O, the code will attempt to call
MPI_File_set_view() in order to switch back to the default view of the
file. MPI_File_set_view() is a collective call however, and this causes
the application to hang.
Solution:
Removed "lazy" MPI_File_set_view() code, instead set the file view when it
is needed (with MPI derived types) and immediately set the file view back to
the default view before leaving the I/O routine.
Platforms tested:
IRIX64 6.5 (modi4) w/parallel. Also, tested with the latest development
and release code for the SAF library, which now works correctly with this
change. (Although the release branch of the SAF library seems to have a
bug, this 1.4.4 release candidate code gets as far as the version the SAF
library is released on top of (1.4.2-patch1, I believe)).
Code improvement
Description:
Some small code cleanups and took out the code the was turning off the
metadata cache for parallel I/O (!)
Platforms tested:
IRIX64 6.5 (modi4) w/parallel
Code optimization
Description:
Avoid creating MPI types (and thus requiring a MPI_File_set_view() call)
when contiguous selections are used for dataset I/O. This should be a
performance improvement for those sorts of selections.
Platforms tested:
Linux 2.2.x (eirene) w/parallel && IRIX64 6.5 (modi4) w/parallel & FORTRAN
Code cleanup
Description:
Use dataset transfer property list to hold information about the MPI types
for the current transfer, instead of setting pseudo-global variables in
the file's struct.
Platforms tested:
Linux 2.2.x (eirene) w/parallel & IRIX64 6.5 (modi4) w/parallel & FORTRAN
Code cleanup
Description:
Change MPI-I/O code to use the address of the dataset for the displacement,
instead of having a separate displacement value. Removed displacement
parameter from H5FD_mpio_setup parameters.
Platforms tested:
Linux 2.2.x (eirene) w/parallel & IRIX64 6.5 (modi4) w/parallel.
Code Improvement
Description:
Split the metadata accumulator code into two parts: one for allowing writes
of the accumulator buffer during reads (when the buffer is dirty and needs
to be flushed to disk in order to hold the new metadata being read in) and
another for only allowing writes of the buffer during writes.
This allows the MPI-I/O VFL driver to use the metadata accumulator (but
only during writes) and benefit from the reduced number of metadata I/O
operations that it brings.
Platforms tested:
IRIX64 6.5 (modi4) w/parallel
New feature.
Description:
Added a "small data" block allocation mechanism to the library, similar to
the mechanism used for allocating metadata currently.
See the RFC for more details:
http://hdf.ncsa.uiuc.edu/RFC/SmallData/SmallData.html
This reduces the number of I/O operations which hit the disk for my test
program from 19 to 15 (i.e. from 393 to 15, overall).
Platforms tested:
Solaris 2.7 (arabica) w/FORTRAN and FreeBSD 4.5 (sleipnir) w/C++
