[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, 29 insertions, 9 deletions

diff --git a/src/H5FLprivate.h b/src/H5FLprivate.h
index 35b3555..72e28d8 100644
--- a/src/H5FLprivate.h
+++ b/src/H5FLprivate.h
@@ -66,7 +66,10 @@ typedef struct H5FL_reg_head_t {
 #define H5FL_DEFINE_STATIC(t)  static H5FL_DEFINE(t)
 
 /* Allocate an object of type 't' */
-#define H5FL_ALLOC(t,clr) H5FL_reg_alloc(&(t##_free_list),clr)
+#define H5FL_MALLOC(t) H5FL_reg_malloc(&(t##_free_list))
+
+/* Allocate an object of type 't' and clear it to all zeros */
+#define H5FL_CALLOC(t) H5FL_reg_calloc(&(t##_free_list))
 
 /* Free an object of type 't' */
 #define H5FL_FREE(t,obj) H5FL_reg_free(&(t##_free_list),obj)
@@ -80,7 +83,8 @@ typedef struct H5FL_reg_head_t {
 #define H5FL_DEFINE(t)  int t##_reg_free_list_placeholder
 #define H5FL_EXTERN(t)  extern int t##_reg_free_list_placeholder
 #define H5FL_DEFINE_STATIC(t)  static H5FL_DEFINE(t)
-#define H5FL_ALLOC(t,clr) (clr ? H5MM_calloc(sizeof(t)) : H5MM_malloc(sizeof(t)))
+#define H5FL_MALLOC(t) H5MM_malloc(sizeof(t))
+#define H5FL_CALLOC(t) H5MM_calloc(sizeof(t))
 #define H5FL_FREE(t,obj) H5MM_xfree(obj)
 #endif /* H5_NO_REG_FREE_LISTS */
 
@@ -124,7 +128,10 @@ typedef struct H5FL_blk_head_t {
 #define H5FL_BLK_DEFINE_STATIC(t)  static H5FL_BLK_DEFINE(t)
 
 /* Allocate an block of type 't' */
-#define H5FL_BLK_ALLOC(t,size,clr) H5FL_blk_alloc(&(t##_pq),size,clr)
+#define H5FL_BLK_MALLOC(t,size) H5FL_blk_malloc(&(t##_pq),size)
+
+/* Allocate an block of type 't' and clear it to zeros */
+#define H5FL_BLK_CALLOC(t,size) H5FL_blk_calloc(&(t##_pq),size)
 
 /* Free a block of type 't' */
 #define H5FL_BLK_FREE(t,blk) H5FL_blk_free(&(t##_pq),blk)
@@ -132,13 +139,18 @@ typedef struct H5FL_blk_head_t {
 /* Re-allocate a block of type 't' */
 #define H5FL_BLK_REALLOC(t,blk,new_size) H5FL_blk_realloc(&(t##_pq),blk,new_size)
 
+/* Check if there is a free block available to re-use */
+#define H5FL_BLK_AVAIL(t,size)  H5FL_blk_free_block_avail(&(t##_pq),size)
+
 #else /* H5_NO_BLK_FREE_LISTS */
 #define H5FL_BLK_DEFINE(t)      int t##_blk_free_list_placeholder
 #define H5FL_BLK_EXTERN(t)      extern int t##_blk_free_list_placeholder
 #define H5FL_BLK_DEFINE_STATIC(t)  static H5FL_BLK_DEFINE(t)
-#define H5FL_BLK_ALLOC(t,size,clr) (clr ? H5MM_calloc(size) : H5MM_malloc(size))
+#define H5FL_BLK_MALLOC(t,size) H5MM_malloc(size)
+#define H5FL_BLK_CALLOC(t,size) H5MM_calloc(size)
 #define H5FL_BLK_FREE(t,blk) H5MM_xfree(blk)
 #define H5FL_BLK_REALLOC(t,blk,new_size) H5MM_realloc(blk,new_size)
+#define H5FL_BLK_AVAIL(t,size)  (FALSE)
 #endif /* H5_NO_BLK_FREE_LISTS */
 
 /* Data structure to store each array in free list */
@@ -178,7 +190,10 @@ typedef struct H5FL_arr_head_t {
 #define H5FL_ARR_DEFINE_STATIC(t,m)  static H5FL_ARR_DEFINE(t,m)
 
 /* Allocate an array of type 't' */
-#define H5FL_ARR_ALLOC(t,elem,clr) H5FL_arr_alloc(&(t##_arr_free_list),elem,clr)
+#define H5FL_ARR_MALLOC(t,elem) H5FL_arr_malloc(&(t##_arr_free_list),elem)
+
+/* Allocate an array of type 't' and clear it to all zeros */
+#define H5FL_ARR_CALLOC(t,elem) H5FL_arr_calloc(&(t##_arr_free_list),elem)
 
 /* Free an array of type 't' */
 #define H5FL_ARR_FREE(t,obj) H5FL_arr_free(&(t##_arr_free_list),obj)
@@ -190,7 +205,8 @@ typedef struct H5FL_arr_head_t {
 #define H5FL_ARR_DEFINE(t,m)    int t##_arr_free_list_placeholder
 #define H5FL_ARR_EXTERN(t)      extern int t##_arr_free_list_placeholder
 #define H5FL_ARR_DEFINE_STATIC(t,m)  static H5FL_ARR_DEFINE(t,m)
-#define H5FL_ARR_ALLOC(t,elem,clr) (clr ? H5MM_calloc(elem*sizeof(t)) : H5MM_malloc(elem*sizeof(t)))
+#define H5FL_ARR_MALLOC(t,elem) H5MM_malloc(elem*sizeof(t))
+#define H5FL_ARR_CALLOC(t,elem) H5MM_calloc(elem*sizeof(t))
 #define H5FL_ARR_FREE(t,obj) H5MM_xfree(obj)
 #define H5FL_ARR_REALLOC(t,obj,new_elem) H5MM_realloc(obj,new_elem*sizeof(t))
 #endif /* H5_NO_ARR_FREE_LISTS */
@@ -198,12 +214,16 @@ typedef struct H5FL_arr_head_t {
 /*
  * Library prototypes.
  */
-H5_DLL void * H5FL_blk_alloc(H5FL_blk_head_t *head, size_t size, unsigned clear);
+H5_DLL void * H5FL_blk_malloc(H5FL_blk_head_t *head, size_t size);
+H5_DLL void * H5FL_blk_calloc(H5FL_blk_head_t *head, size_t size);
 H5_DLL void * H5FL_blk_free(H5FL_blk_head_t *head, void *block);
 H5_DLL void * H5FL_blk_realloc(H5FL_blk_head_t *head, void *block, size_t new_size);
-H5_DLL void * H5FL_reg_alloc(H5FL_reg_head_t *head, unsigned clear);
+H5_DLL htri_t H5FL_blk_free_block_avail(H5FL_blk_head_t *head, size_t size);
+H5_DLL void * H5FL_reg_malloc(H5FL_reg_head_t *head);
+H5_DLL void * H5FL_reg_calloc(H5FL_reg_head_t *head);
 H5_DLL void * H5FL_reg_free(H5FL_reg_head_t *head, void *obj);
-H5_DLL void * H5FL_arr_alloc(H5FL_arr_head_t *head, size_t elem, unsigned clear);
+H5_DLL void * H5FL_arr_malloc(H5FL_arr_head_t *head, size_t elem);
+H5_DLL void * H5FL_arr_calloc(H5FL_arr_head_t *head, size_t elem);
 H5_DLL void * H5FL_arr_free(H5FL_arr_head_t *head, void *obj);
 H5_DLL void * H5FL_arr_realloc(H5FL_arr_head_t *head, void *obj, size_t new_elem);
 H5_DLL herr_t H5FL_garbage_coll(void);