[svn-r6252] Purpose:

    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

1 files changed, 24 insertions, 17 deletions

diff --git a/src/H5FDfamily.c b/src/H5FDfamily.c
index 00a98db..f6ad440 100644
--- a/src/H5FDfamily.c
+++ b/src/H5FDfamily.c
@@ -194,8 +194,11 @@ H5Pset_fapl_family(hid_t fapl_id, hsize_t memb_size, hid_t memb_fapl_id)
     /* Check arguments */
     if(TRUE != H5P_isa_class(fapl_id, H5P_FILE_ACCESS))
         HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, FAIL, "not a file access property list");
-    if(memb_fapl_id!=H5P_DEFAULT && TRUE != H5P_isa_class(memb_fapl_id, H5P_FILE_ACCESS))
-        HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, FAIL, "not a file access list");
+    if(H5P_DEFAULT == memb_fapl_id)
+        memb_fapl_id = H5P_FILE_ACCESS_DEFAULT;
+    else
+        if(TRUE != H5P_isa_class(memb_fapl_id, H5P_FILE_ACCESS))
+            HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, FAIL, "not a file access list");
 
     /*
      * Initialize driver specific information. No need to copy it into the FA
@@ -345,8 +348,8 @@ H5FD_family_fapl_copy(const void *_old_fa)
     memcpy(new_fa, old_fa, sizeof(H5FD_family_fapl_t));
 
     /* Deep copy the property list objects in the structure */
-    if(old_fa->memb_fapl_id==H5P_DEFAULT)
-        new_fa->memb_fapl_id = H5P_DEFAULT;
+    if(old_fa->memb_fapl_id==H5P_FILE_ACCESS_DEFAULT)
+        H5I_inc_ref(new_fa->memb_fapl_id);
     else {
         if(NULL == (plist = H5I_object(old_fa->memb_fapl_id)))
             HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, NULL, "not a file access property list");
@@ -427,9 +430,14 @@ H5FD_family_dxpl_copy(const void *_old_dx)
         HGOTO_ERROR(H5E_RESOURCE, H5E_NOSPACE, NULL, "memory allocation failed");
 
     memcpy(new_dx, old_dx, sizeof(H5FD_family_dxpl_t));
-    if(NULL == (plist = H5I_object(old_dx->memb_dxpl_id)))
-        HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, NULL, "not a file access property list");
-    new_dx->memb_dxpl_id = H5P_copy_plist(plist);
+
+    if(old_dx->memb_dxpl_id==H5P_DATASET_XFER_DEFAULT)
+        H5I_inc_ref(new_dx->memb_dxpl_id);
+    else {
+        if(NULL == (plist = H5I_object(old_dx->memb_dxpl_id)))
+            HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, NULL, "not a file access property list");
+        new_dx->memb_dxpl_id = H5P_copy_plist(plist);
+    } /* end else */
 
     /* Set return value */
     ret_value=new_dx;
@@ -515,8 +523,9 @@ H5FD_family_open(const char *name, unsigned flags, hid_t fapl_id,
     /* Initialize file from file access properties */
     if (NULL==(file=H5MM_calloc(sizeof(H5FD_family_t))))
         HGOTO_ERROR(H5E_RESOURCE, H5E_NOSPACE, NULL, "unable to allocate file struct");
-    if (H5P_DEFAULT==fapl_id) {
-        file->memb_fapl_id = H5P_DEFAULT;
+    if (H5P_FILE_ACCESS_DEFAULT==fapl_id) {
+        file->memb_fapl_id = H5P_FILE_ACCESS_DEFAULT;
+        H5I_inc_ref(file->memb_fapl_id);
         file->memb_size = 1024*1024*1024; /*1GB*/
     } else {
         H5FD_family_fapl_t *fa;
@@ -524,8 +533,8 @@ H5FD_family_open(const char *name, unsigned flags, hid_t fapl_id,
         if(NULL == (plist = H5I_object(fapl_id)))
             HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, NULL, "not a file access property list");
         fa = H5P_get_driver_info(plist);
-        if(fa->memb_fapl_id==H5P_DEFAULT)
-            file->memb_fapl_id = H5P_DEFAULT;
+        if(fa->memb_fapl_id==H5P_FILE_ACCESS_DEFAULT)
+            H5I_inc_ref(file->memb_fapl_id);
         else {
             if(NULL == (plist = H5I_object(fa->memb_fapl_id)))
                 HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, NULL, "not a file access property list");
@@ -920,8 +929,6 @@ H5FD_family_get_handle(H5FD_t *_file, hid_t fapl, void** file_handle)
     FUNC_ENTER_NOAPI(H5FD_family_get_handle, FAIL);
 
     /* Get the plist structure and family offset */
-    if(H5P_DEFAULT == fapl)
-        fapl = H5Pcreate(H5P_FILE_ACCESS);
     if(NULL == (plist = H5P_object_verify(fapl, H5P_FILE_ACCESS)))
         HGOTO_ERROR(H5E_ATOM, H5E_BADATOM, FAIL, "can't find object for ID");
     if(H5P_get(plist, H5F_ACS_FAMILY_OFFSET_NAME, &offset) < 0)
@@ -963,7 +970,7 @@ H5FD_family_read(H5FD_t *_file, H5FD_mem_t type, hid_t dxpl_id, haddr_t addr, si
 {
     H5FD_family_t	*file = (H5FD_family_t*)_file;
     unsigned char	*buf = (unsigned char*)_buf;
-    hid_t		memb_dxpl_id = H5P_DEFAULT;
+    hid_t		memb_dxpl_id = H5P_DATASET_XFER_DEFAULT;
     int			i;
     haddr_t		sub;
     size_t		req;
@@ -979,7 +986,7 @@ H5FD_family_read(H5FD_t *_file, H5FD_mem_t type, hid_t dxpl_id, haddr_t addr, si
      */
     if(NULL == (plist = H5I_object(dxpl_id)))
         HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, FAIL, "not a file access property list");
-    if (H5P_DEFAULT!=dxpl_id && H5FD_FAMILY==H5P_get_driver(plist)) {
+    if (H5P_DATASET_XFER_DEFAULT!=dxpl_id && H5FD_FAMILY==H5P_get_driver(plist)) {
         H5FD_family_dxpl_t *dx = H5P_get_driver_info(plist);
 
         assert(TRUE==H5P_isa_class(dxpl_id, H5P_DATASET_XFER));
@@ -1040,7 +1047,7 @@ H5FD_family_write(H5FD_t *_file, H5FD_mem_t type, hid_t dxpl_id, haddr_t addr, s
 {
     H5FD_family_t	*file = (H5FD_family_t*)_file;
     const unsigned char	*buf = (const unsigned char*)_buf;
-    hid_t		memb_dxpl_id = H5P_DEFAULT;
+    hid_t		memb_dxpl_id = H5P_DATASET_XFER_DEFAULT;
     int			i;
     haddr_t		sub;
     size_t		req;
@@ -1056,7 +1063,7 @@ H5FD_family_write(H5FD_t *_file, H5FD_mem_t type, hid_t dxpl_id, haddr_t addr, s
      */
     if(NULL == (plist = H5I_object(dxpl_id)))
         HGOTO_ERROR(H5E_ARGS, H5E_BADTYPE, FAIL, "not a file access property list");
-    if (H5P_DEFAULT!=dxpl_id && H5FD_FAMILY==H5P_get_driver(plist)) {
+    if (H5P_DATASET_XFER_DEFAULT!=dxpl_id && H5FD_FAMILY==H5P_get_driver(plist)) {
         H5FD_family_dxpl_t *dx = H5P_get_driver_info(plist);
 
         assert(TRUE==H5P_isa_class(dxpl_id, H5P_DATASET_XFER));