diff options
| author | Quincey Koziol <koziol@hdfgroup.org> | 2002-05-17 12:56:40 (GMT) |
|---|---|---|
| committer | Quincey Koziol <koziol@hdfgroup.org> | 2002-05-17 12:56:40 (GMT) |
| commit | c1531ed7e76ef2d71dbf50e1fb35d5ae2c4f1be5 (patch) | |
| tree | 8eeecadd52cf26a3e0460acb3686e0831a178f8e /release_docs | |
| parent | bca854d17a36e160569a0aa2c2ff95508bbb8420 (diff) | |
| download | hdf5-c1531ed7e76ef2d71dbf50e1fb35d5ae2c4f1be5.zip hdf5-c1531ed7e76ef2d71dbf50e1fb35d5ae2c4f1be5.tar.gz hdf5-c1531ed7e76ef2d71dbf50e1fb35d5ae2c4f1be5.tar.bz2 | |
[svn-r5432] Purpose:
Document Bug fix/Code improvement below:
Description:
Currently, the chunk data allocation routine invoked to allocate space for
the entire dataset is inefficient. It writes out each chunk in the dataset,
whether it is already allocated or not. Additionally, this happens not
only when it is created, but also anytime it is opened for writing, or the
dataset is extended. Worse, there's too much parallel I/O syncronization,
which slows things down even more.
Solution:
Only attempt to write out chunks that don't already exist. Additionally,
share the I/O writing between all the nodes, instead of writing everything
with process 0. Then, only block with MPI_Barrier if chunks were actually
created.
Diffstat (limited to 'release_docs')
| -rw-r--r-- | release_docs/RELEASE.txt | 8 |
1 files changed, 6 insertions, 2 deletions
diff --git a/release_docs/RELEASE.txt b/release_docs/RELEASE.txt index 79da74d..f42702d 100644 --- a/release_docs/RELEASE.txt +++ b/release_docs/RELEASE.txt @@ -44,11 +44,11 @@ New Features --------- * Fill-value's forward-compatibility with 1.5 was added. SLU - 2002/04/11 - * Added serial multi-gigabyte file size test. "test/big -h" shows - the help page. AKC - 2002/03/29 * A new query function H5Tget_member_index has been added for compound and enumeration data types, to retrieve member's index by name. SLU - 2002/04/05 + * Added serial multi-gigabyte file size test. "test/big -h" shows + the help page. AKC - 2002/03/29 o APIs ------ @@ -63,6 +63,10 @@ New Features o Parallel Library ================== + * Changed method for allocating chunked dataset blocks to only allocate + blocks that don't already exist, instead of attempting to create all the + blocks all the time. This improves performance for chunked + datasets. QAK - 2002/05/17 * Allowed the call to MPI_File_sync to be avoided when the file is going to immediately be closed, improving performance. QAK - 2002/05/13 * Allow the metadata writes to be shared among all processes, easing the |