summaryrefslogtreecommitdiffstats
path: root/src/H5Cprivate.h
diff options
context:
space:
mode:
authormainzer <mainzer#hdfgroup.org>2017-04-06 23:11:21 (GMT)
committermainzer <mainzer#hdfgroup.org>2017-04-06 23:11:21 (GMT)
commit94c34773ceae5b30c4afb227d0385ebf4ab6ce28 (patch)
tree562c854493b7f45343ad61009cc4be31495398d8 /src/H5Cprivate.h
parent60167ae8753e48eb00be0dc015d3a476b8e02662 (diff)
downloadhdf5-94c34773ceae5b30c4afb227d0385ebf4ab6ce28.zip
hdf5-94c34773ceae5b30c4afb227d0385ebf4ab6ce28.tar.gz
hdf5-94c34773ceae5b30c4afb227d0385ebf4ab6ce28.tar.bz2
Checkin of fix for CGNS bug
(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.
Diffstat (limited to 'src/H5Cprivate.h')
-rw-r--r--src/H5Cprivate.h5
1 files changed, 4 insertions, 1 deletions
diff --git a/src/H5Cprivate.h b/src/H5Cprivate.h
index bdfb23e..5c5a666 100644
--- a/src/H5Cprivate.h
+++ b/src/H5Cprivate.h
@@ -2340,9 +2340,12 @@ H5_DLL herr_t H5C_dump_cache_LRU(H5C_t *cache_ptr, const char *cache_name);
H5_DLL hbool_t H5C_get_serialization_in_progress(const H5C_t *cache_ptr);
H5_DLL hbool_t H5C_cache_is_clean(const H5C_t *cache_ptr, H5C_ring_t inner_ring);
H5_DLL herr_t H5C_dump_cache_skip_list(H5C_t *cache_ptr, char *calling_fcn);
+#ifdef H5_HAVE_PARALLEL
+H5_DLL herr_t H5C_dump_coll_write_list(H5C_t * cache_ptr, char * calling_fcn);
+#endif /* H5_HAVE_PARALLEL */
H5_DLL herr_t H5C_get_entry_ptr_from_addr(H5C_t *cache_ptr, haddr_t addr,
void **entry_ptr_ptr);
-H5_DLL herr_t H5C_flush_dependency_exists(H5C_t *cache_ptr, haddr_t parent_addr,
+H5_DLL herr_t H5C_flush_dependency_exists(H5C_t *cache_ptr, haddr_t parent_addr,
haddr_t child_addr, hbool_t *fd_exists_ptr);
H5_DLL herr_t H5C_verify_entry_type(H5C_t *cache_ptr, haddr_t addr,
const H5C_class_t *expected_type, hbool_t *in_cache_ptr,