| Commit message (Collapse) | Author | Age | Files | Lines |
|
|
|
|
|
|
|
| |
Description:
Looked for typos similar to user's report in HDFFV-10404.
Not all the same but many were found and fixed.
Platforms tested:
Linux/64 (jelly) - only typos
|
|
|
|
| |
removed and replace it with new url for COPYING file.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r25084, 25088, 25092, 25097 from trunk to 1.8 branch:
r25084:
Begin process of migrating from using property list IDs internally to the
library to using the internal generic property list data structure.
r25088:
Introduce "file I/O info" struct, to hold file & dxpl pointers, and start
propagating up through library.
r25092:
More migration to using H5F_io_info_t pointers and away from using
property list IDs internally. Also, clean up some compiler warnings in the
cache code.
r25097:
Make progress toward moving from DXPL IDs to property list structures
within the library. Also move the signature location code from the H5F
package to the H5FD package, where it's a better fit. Also, clean up some
more compiler warnings along the way.
Tested:
Mac OSX/64 10.9.2 (amazon) w/C++, FORTRAN & parallel
(h5committested on trunk)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
the failure
of the H5Ocache.c code to update its image of the on disk representation
of the object header on a call to 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.
|
|
|
|
|
|
|
|
|
| |
Rename H5AC_set() to H5AC_insert_entry()
Get rid of H5C_set_skip_flags() & related flags
Tested on:
Mac OS X/32 10.6.4 (amazon) w/debug
(too simple to require h5committest)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r19096 from trunk to 1.8 branch:
Bring "round robin" metadata write strategy code from 'round_robin'
branch to the trunk.
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r18837 from trunk to 1.8 branch:
Remove the size parameter from H5[A]C_unprotect() and the
H5[A]C__SIZE_CHANGED_FLAG, switching all clients & tests over to using
H5[A]C_resize_entry appropriately.
Tested on:
FreeBSD/32 6.3 (duty) in debug mode
FreeBSD/64 6.3 (liberty) w/C++ & 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
(h5committested on trunk)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r18740 from trunk to 1.8 branch:
Bring r18738 from metadata journaling 'merging' branch to trunk:
Switch H5AC_resize_pinned_entry() to work on protected entries as well,
and rename to H5AC_resize_entry()
Tested on:
FreeBSD/32 6.3 (duty) in debug mode
FreeBSD/64 6.3 (liberty) w/C++ & FORTRAN, in debug mode
(h5committested on trunk)
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r18725 from trunk to 1.8 branch:
Bring r18724 from metadata journaling 'merging' branch to trunk:
Rename H5[A]C_rename to H5[A]C_move_entry.
Tested on:
FreeBSD/32 6.3 (duty) w/debug
(h5committested on trunk)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r18721 from trunk to 1.8 branch:
Bring r18720 from metadata journaling merging branch to trunk:
Bring changes from metadata journaling branch to 'merging' branch:
Rename H5[A]C_mark_pinned_or_protected_entry_dirty() to
H5[A]C_mark_entry_dirty() and get rid of H5[A]C_mark_pinned_entry_dirty().
Tested on:
FreeBSD/32 6.3 (duty) in debug mode
(h5committested on trunk)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r18702 from trunk to 1.8 branch:
Bring r18672 from metadata journaling "merging" branch to trunk:
Mostly changes to move to only using one 'user data' parameter for
calls to H5AC_protect(), along with some minor reformatting code cleanups.
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 production 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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r18460 from trunk to 1.8 branch:
Fold metadata journaling changes into the trunk: mostly tweaky
small stuff, also removed the H5F_t* field from the H5G_entry_t struct.
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-ia64 2.4 (tg-login3) w/parallel, w/FORTRAN, in debug mode
Linux/64-amd64 2.6 (abe) w/parallel, w/FORTRAN, in production mode
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r18171 from trunk to 1.8 branch (with appropriate tweaks):
Bring r18169 from 'merge_metadata_journaling' branch back to trunk:
Converge changes on metadata_journaling branch and trunk:
- Remove H5F_t* parameter from H5HL_unprotect()
- Remove H5F_t* parameter from H5HL_dirty()
- Remove H5F_t* parameter from H5O_unprotect()
- Bring changes to metadata caching routines back:
- H5AC_pin_protected_entry()
- H5AC_resize_pinned_entry()
- H5AC_unpin_entry()
- H5AC_mark_pinned_entry_dirty()
- H5AC_mark_pinned_or_protected_entry_dirty()
- Revise internal H5C routines to drop H5F_t* and/or H5C_t* as
parameter where possible
- Revise tests to follow internal routine changes
Also, other minor changes to speedup the 'cache' test.
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-ia64 2.4 (tg-login3) w/parallel, w/FORTRAN, in debug mode
Linux/64-amd64 2.6 (abe) w/parallel, w/FORTRAN, in production mode
Mac OS X/32 10.6.2 (amazon) in debug mode
Mac OS X/32 10.6.2 (amazon) w/C++ & FORTRAN, w/threadsafe,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r17408, 17411, 17412, 17413 & 17414 from trunk back to 1.8 branch:
r17408:
Move flush operation on mounted file hierarchy into H5Fmount module.
r17411:
Make H5AC_flush just flush the cache and make H5AC_dest perform the
proper parallel synchronization before destroying the cache. Also, further
discriminate between 'closing' and 'non-closing' actions in H5F_flush.
r17412:
Seperate 'flush' functionality from 'destroy' functionality at the
H5F level also.
r17413:
Remove vestigial intermediate routine for flushing file and move it
into API routine. Also, remove private, unused (now) 'H5F_FLUSH_DOWN' symbol
from public header file.
r17414:
Flush the core VFD's buffer before closing the file, also flush the
metadata accumulator before reseting it. Write the driver info message out
in the superblock flush routine more directly, instead of using wrapper
routine, since the wrapper routine won't work when the superblock is being
shutdown.
Tested on:
FreeBSD/32 6.3 (duty) in debug mode
(h5committest performed on trunk)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Modifying default cache configuration, and adding an #ifdef to allow for a
separate default configuration when parallel is enabled. This is being
modified in order to address an observed performance problem with the
current default configuration.
Description of Changes:
- increasing maximum cache size from 16MB to 32MB
- increasing maximum entry size from 10MB to 32MB
- decreasing min_clean_fraction from 0.3 to 0.01 in serial case
- increasing flash_multiple from 1.0 to 1.4 in serial case
Tested:
jam
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Merge these trunk revisions which occurred during the 1.8.3 release code
freeze back to the 1.8 branch:
From Quincey: 16845 16847 16849 16851 16858 16869 16897
From Ray: 16859 16880
From Allen: 16863
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/C++ & FORTRAN, w/threadsafe,
in debug mode
Linux/64-amd64 2.6 (smirom) 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-ia64 2.4 (tg-login3) w/parallel, w/FORTRAN, in debug mode
Linux/64-amd64 2.6 (abe) w/parallel, w/FORTRAN, in production mode
Mac OS X/32 10.5.6 (amazon) in debug mode
Mac OS X/32 10.5.6 (amazon) w/C++ & FORTRAN, w/threadsafe,
in production mode
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Bring r15800 back from trunk:
- File free space branch changes through r15794
Tested on:
Mac OS X/32 10.5.5 (amazon) in debug mode
Mac OS X/32 10.5.5 (amazon) w/C++ & FORTRAN, w/threadsafe,
in production mode
FreeBSD/32 6.3 (duty) in debug mode
FreeBSD/64 6.3 (liberty) w/C++ & FORTRAN, in debug mode
Linux/32 2.6 (kagiso) w/PGI compilers, w/C++ & FORTRAN, w/threadsafe,
in debug mode
Linux/64-amd64 2.6 (smirom) 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-ia64 2.4 (tg-login3) w/parallel, w/FORTRAN, in production mode
Linux/64-amd64 2.6 (abe) w/parallel, w/FORTRAN, in production mode
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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...
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
entry flush
callback functions modifies the skip list or LRU out from under a partial
or complete flush of the cache. This is a test for a situation that
should not occur, but we test anyway.
Also added code to skip longer tests in cache_api in express tests.
Tested serial and parallel on phoenix (debian --x86-32), and commit test.
Elena commit tested as well, and ran a manual test under MacOS X.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
large entry, or to a large increases in the size of an existing entry.
This required some additions to the cache configuration structure, and
thus will require changes in the metadata cache documentation.
The basic idea is to monitor the size of entries as they are loaded,
inserted, or increased in size. If the size of the entry (or increase)
exceeds some user selected fraction of the size of the cache, increase
the size of the cache.
Note that this fix was designed quickly -- while it deals with the
use case that exposed the problem, we may have to revisit the issue
later.
Tested serial and parallel on Phoenix, and h5committest.
|
|
|
|
|
|
|
|
| |
First attempt contained slightly dated versions of the files
listed below.
Must also note that the mods were tested with h5committest,
and two other linux builds.
|
|
|
|
| |
Also implemented associated test code.
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Fully enable readers/writer locking in metadata cache and correct errors
in cache clients which were modifying a cache entry while only holding a
read lock on it.
Tested on:
Mac OS X/32 10.4.9 (amazon)
Linux/32 2.6 (chicago)
Linux/64 2.6 (chicago2)
FreeBSD/32 6.2 (duty)
FreeBSD/64 6.2 (liberty)
|
|
|
|
|
|
|
|
|
|
| |
cache entries. Added test code to test the new feature. Also some
minor cleanum
h5committested -- passed on copper and sol. Failed on osage with
a configuration error that appears unrelated to my changes. Serial
test (debug mode) passes on Phoenix (Linux x86 2.6 kernel), so I
went ahead with the checkin.
|
|
|
|
|
|
|
|
|
| |
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.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
handle flush callbacks which can dirty other entries, and
resize and/or rename the target entry.
This feature is needed by the fractal heap code.
Also added associated test code.
H5Commit tested. Test failed on heping, but the
error appears to be a syntax error in an un-related
file.
Tests on copper & sol passed, along with tests on
phoenix.
|
|
|
|
|
|
|
|
|
|
|
| |
flag, and pin an entry as it is inserted.
The objective is to avoid some function call overhead in fheap.
Also added matching test code in test/cache.c & test/cache_common.c
(also testpar/t_cache.c checked in separately by accident)
h5commit tested
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
1) Added trace file support to the metadata cache. This allows capture
of all metadata cache calls in trace files for purposes of optimization
and debuging.
2) Added an expunge entry function. This allows an entry to be deleteded
from the cache without writing it to disk even if it is dirty.
3) Added a function call to resize pinned entries.
4) Added code to deal with entries that are dirty on load. This is
needed in support of a bug fix which can alter object headers on
load to repair files.
5) Added progress reporting code to the "MDC API smoke check" test in
cache_api.c. To enable the progress reporting, set report_progress
to TRUE in mdc_api_call_smoke_check().
Tested with h5committest, and a parallel test on phoenix (dual athelon
linux box).
|
|
|
|
|
|
|
|
|
|
|
| |
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
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
1) Check in potential fix to unreproduceable bug in t_cache observed on
Cobalt
2) Check in code supporting added pinned entry features in the metadata
cache.
Description:
1) Elena encountered a bug in t_cache when running on Cobalt. On
investigation I found a potential race condition in t_cache that
could explain her observation.
2) Quincey requested additions to the metadata cache allowing renaming
of pinned entryies, and marking of pinned or protected entries as
dirty.
Solution:
1) Modified t_cache.c to prevent the potential race condition. Elena
was unable to reproduce the bug on Cobalt, so we don't know if my
fix actually addressed the problem.
2) Added code supporting the requested functions. The changes were
relatively trivial, but required substantial new test code.
Platforms tested:
h5committest, serial test on heping, parallel test on phoenix.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add pinned entry capability to cache.
Description:
For frequently accessed cache entries, the protect/unprotect overhead
is sometimes a bottleneck.
Solution:
Allow entries to be pinned in the cache. Pinned entries can't be
evicted, but can be flushed or modified.
Platforms tested:
h5committested -- minus one small typo in test/cache.c whose fix was
tested on copper and heping only.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
1) Add parallel test for metadata cache
2) Split serial test for metadata cache into two parts
3) Fix bug in which cache was flushed needlessly when the
cache wasn't full.
4) Performance improvements
5) Update API for parallel cache coherency bug fix.
Description:
See above.
Solution:
See above.
Platforms tested:
h5committest
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Repair synchronization bug in the metadata cache in PHDF5
Also repair numerous other bugs that surfaced in testing the
bug fix.
Description:
While operations modifying metadata must be collective, we allow
independant reads. This allows metadata caches on different processes
to adjust to different sizes, and to place the entries on their dirty
lists in different orders. Since only process 0 actually writes
metadata to disk (all other processes thought they did, but the writes
were discarded on the theory that they had to be collective), this made
it possible for another process to modify metadata, flush it, and then
read it back in in its original form (pre-modification) form. The
possibilities for file corruption should be obvious.
Solution:
Make the policy that only process 0 can write to file explicit, and
visible to the metadata caches. Thus only process 0 may flush dirty
entries -- all other caches must retain dirty entries until they are
informed by process 0 that the entries are clean.
Synchronization is handled by counting the bytes of dirty cache entries
created, and then synching up between the caches whenever the sum
exceeds an (eventually user specified) limit. Dirty metadata creation
is consistent across all processes because all operations modifying
metadata must be collective.
This change uncovered may bugs which are repaired in this checkin.
It also required modification of H5HL and H5O to allocate file space
on insertion rather than on flush from cache.
Platforms tested:
H5committest, heping(parallel & serial)
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
|
|
|
|
|
|
|
|
|
|
|
|
| |
Code cleanup
Description:
Refactor metadata cache to merge "dirtied" flag in with other flags for
H5AC_unprotect and H5C_unprotect.
Platforms tested:
FreeBSD 4.11 (sleipnir)
h5committest
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Interim checkin of code changes moving management of the is_dirty flag
into the cache code.
Description:
Prior to this checkin, management of the is_dirty flag was handled
above the level of the metadata cache. This can no longer be allowed,
as it introduces a race condition in the proposed fix for a cache
coherency bug in PHDF5.
Solution:
Move management fo the is_dirty flag to the cache code proper.
Entries are now marked as dirty via a flag on the unprotect call.
Platforms tested:
h5committested
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Add API calls allowing user control of the metadata cache.
Description:
Prior to this update, the metadata cache was not configurable
from outside the library.
Solution:
Add API calls allowing the user to configure the metadata cache
either at file open time, or for any open file. Also added calls
permitting the user to monitor cache size and hit rate. These
latter facilities are needed for "manual" cache size control
Platforms tested:
h5committested
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
1) Provide facilities in cache to allow us to avoid a potential cache
consistency bug in the parallel case.
2) Clean up a off by one sanity checking bug.
3) Turn off execution of long running tests in debug mode.
Description:
1) In the parallel case, all writes to metadata must be collective,
but reads may not be. In pricipal, this allows us to different
contents in different caches. This isn't a problem as long as the
correct data is always on disk, but unless we can force certain
writes immediately, that need not be the case.
2) & 3) should need no further explanation.
Solution:
1) Add code allowing us to mark cache entries, and then force
these entries to be flushed at a later time.
Note that to actually avoid the bug, we will have to modify
existing code to use these new features.
2) & 3) should need no further explanation.
Platforms tested:
heping (serial debug and production)
committest (copper, sol, and heping). test failed on heping in the
c++ portion of the build, but at Quincey's siggestion, I am proceeding
with the checkin.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
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:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Modify the cache code (H5C) to support automatic cache resizing to
adapt to the work load at run time.
Description:
Different applications require different sized caches to maintain
an acceptable hit rate. This set of changes attempts to provide the
ability to adjust to circumstances automatically.
Solution:
Added highly configurable code to allow the user to either set a
fixed cache size, or allow the cache to grow and shrink according to
conditions.
If enabled, cache size increases are triggered when the hit rate
drops below a user specified threshold in a user specified interval.
Cache size reductions (if enabled) are triggered when either the
hit rate exceeds some user specified threshold over a user specified
interval, when the cache contains "enough" entries that haven't been
accessed for a user specified interval, or some mix of the above.
See the header comments on the H5C_auto_size_ctl_t structure in
H5Cprivate.h for further details.
At present, the cache resize configuration options are not
accessible via the user API. Must add this.
Platforms tested:
h5committested, heping (serial), and copper (parallel)
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Code optimization
Description:
Retarget metadata cache code from using TBBT routines to using new skiplist
routines, for a reasonable speedup (when dealing with dirty metadata)
Platforms tested:
FreeBSD 4.10 (sleipnir) w/parallel
Solaris 2.7 (arabica)
Too minor to require h5committest
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Description: Cache was running too slowly.
Solution: Added a hash table for indexing. Retained the tree, but
only for dirty entries. As we need to flush dirty entries
in increasing address order, this is sufficient.
Updated statistics collection code for the above.
Converted a number of local functions into macros to avoid
the function call overhead.
Added code to disable the clean and dirty LRU lists in serial
mode.
Updated test code to account for the above changes.
Platforms tested: h5committested + serial, parallel, and fp on Eirene.
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
bug fix for windows testing
Description:
A function called H5C_stats_reset doesn't have H5_DLL in front of it,
it cause windows DLL test failed.
Solution:
Add H5_DLL in front of it.
Platforms tested:
windows xp, sol 2.7, linux 2.4, aix 5.1
Misc. update:
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Code cleanup
Description:
Fix problems when compiling with C++ compiler.
Also clean up some warnings with gcc 3.4.x
Platforms tested:
FreeBSD 4.10 (sleipnir)
Too minor to require h5committest
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
performance.
Description:
Replaced the old metadata cache with a cache with a modified LRU
replacement policy. This should improve the hit rate.
Solution:
Since we want to flush cache entries in increasing address order, I
used the threaded binary B-tree code to store the cache entries.
There is a fair bit of overhead here, so we may want to consider
other options.
While the code is designed to allow the support of other replacement
algorithms, at present, only a modified version of LRU is supported.
The modified LRU algorithm requires that a user selectable portion
of the cache entries be clean. The clean entries are evicted first
when writes are not permitted. If the pool of clean entries is used
up, the cache grows beyond its user specified maximum size. The
cache can also exceed its maximum size if the combined size of the
protected (or locked) entries exceeds the maximum size of the cache.
Platforms tested:
eirene (serial, parallel, fp), h5committested
Misc. update:
|
|
|
|
| |
from H5C to H5P
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
----------------------
./configure.in
./src/H5Fprivate.h
./src/H5Fsec2.c
We now detect and use lseek64() on systems that have it (e.g.,
Irix64) and are able to generate >2GB files on Irix XFS file
systems (and anything else that supports large files). This
change also removed some warning messages from the Irix `-64'
compiler.
> $ ls -l istore.h5
> -rw-r--r-- 1 matzke meshtv 8605436856 Feb 17 14:03 istore.h5
./configure.in
./src/H5Fprivate.h
./src/H5Fstdio.h
We now detect and use fseek64() on systems that have it (e.g.,
Irix64) and are able to generate >2GB files on Irix XFS file
systems (and anything else that supports large files). This
change also removed some warning messages from the Iris `-64'
compiler.
./src/H5E.c
./src/H5Epublic.h
Added the H5E_OVERFLOW error to signal file address overflow.
./src/H5Fpublic.h
./examples/h5_chunk_read.c
./examples/h5_compound.c
./examples/h5_extend_write.c
./examples/h5_group.c
./examples/h5_read.c
./examples/h5_write.c
./html/Datasets.html
./html/Files.html
./html/H5.api.html
./html/H5.intro.html
./html/H5.sample_code.html
./html/ph5example.c
./html/review1.html
./test/cmpd_dset.c
./test/dsets.c
./test/extend.c
./test/tfile.c
./test/th5p.c
./test/theap.c
./test/tohdr.c
./test/tstab.c
./testpar/phdf5.c
Renamed file access constants to follow the naming scheme.
Also changed the base names a little to be more accurate as to
what they do. The old names H5ACC_WRITE and H5ACC_OVERWRITE
will temporarily work.
H5ACC_DEFAULT --> H5F_ACC_RDONLY for H5Fopen()
H5ACC_DEFAULT --> H5F_ACC_EXCL for H5Fcreate()
H5ACC_WRITE --> H5F_ACC_RDWR
H5ACC_OVERWRITE --> H5F_ACC_TRUNC
Albert or Kim: The H5ACC_INDEPENDENT and H5ACC_COLLECTIVE
macros in H5Fpublic.h should be an enum typedef and have names
more like H5F_MPIO_INDEPENDENT and H5F_MPIO_COLLECTIVE. Also
change the access_mode argument of H5Cset_mpio().
H5Fcreate() and H5Fopen() are more strict now about which
flags are acceptable for the operation.
./src/H5Fprivate.h
./src/H5F.c
./src/H5C.c
Changed the file access template to make it more general. A
union contains a struct for each type of low-level driver and
the default template is initialized at run-time.
./src/H5Fpublic.h
./src/H5F.c
Added H5Fget_access_template() and cleaned up
H5Fget_create_template().
./src/H5C.c
The H5Cset_mpi() no longer trashes the file access template
when an error is detected. We check for errors and *then*
update the file access template.
Added H5C_close() so Albert and Kim have a place to release
the MPI communicator and info from the file access property
list.
Kim or Albert: I notice in H5Cset_mpi() you copy the MPI
communicator. Do you need to do something similar in
H5C_copy()?
./src/H5F.c
Added more error checking for the file creation and access
property lists because it used to be possible to make the
library dump core by swapping the creation and access property
list ID numbers of H5Fcreate().
./test/istore.c
./test/tfile.c
./test/th5p.c
./test/theap.c
./test/tohdr.c
./test/tstab.c
./testpar/testphdf5.c
One must pass H5C_DEFAULT as the file creation or access
property list in order to get the default property list. It
is no longer possible to pass zero or any other arbitrary bad
object ID.
./src/H5Fcore.c
./src/H5Ffamly.c
./src/H5Flow.c
./src/H5Fmpio.c
./src/H5Fsec2.c
./src/H5Fsplit.c
./src/H5Fstdio.c
./src/H5MF.c
The file access property list is passed to all H5F_low_...()
functions and to the drivers.
./src/H5Fcore.c
The block size can be set at run time on a per-file basis
instead of at compile time across all files. The "5000 items in
a group test" now takes 1.6 seconds.
./src/H5private.h
Removed inclusion of mpi.h and mpio.h since they're included
from H5public.h.
./src/H5Cpublic.h
./src/H5C.c
Added H5Cset_stdio(), H5Cset_sec2(), H5Cset_core(),
H5Cset_split(), and H5Cset_family() in addition to the
H5Cset_mpio() that Kim and Albert already wrote. We still
need the H5Cget_driver() and an H5Cget...() counterpart for
each of those functions. The split and family drivers still
need a little work but I'm checking this in anyway.
|
|
|
|
|
|
|
|
|
|
|
| |
----------------------
./src/H5C.c
./src/H5Cprivate.h
./src/H5D.c
./src/H5Dpublic.h
Added H5Dget_create_parms(), trying to stay one step ahead of
Elena ;-)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
----------------------
./src/*.h
Fixed indentation where indent(1) screwed up. This isn't by
any means the final say, but it's better than it was.
./src/H5A.c
./src/H5Aprivate.h
./src/H5Apublic.h
./src/H5C.c
./src/H5D.c
./src/H5E.c
./src/H5F.c
./src/H5G.c
./src/H5M.c
./src/H5P.c
./src/H5T.c
./src/H5Tconv.c
./src/debug.c
./test/dtypes.c
./test/istore.c
./test/theap.c
./test/tohdr.c
./test/tstab.c
Removed some atom functions from the API and made them
library-scope. Also changed some names by removing the
redundant `atom' from the name and by adding a `_' after the
`H5A'.
|
| |
|