[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, 16 insertions, 11 deletions

diff --git a/src/H5Ppkg.h b/src/H5Ppkg.h
index b600769..65b76a0 100644
--- a/src/H5Ppkg.h
+++ b/src/H5Ppkg.h
@@ -24,6 +24,14 @@
 #endif
 
 #include "H5Pprivate.h"
+#include "H5TBprivate.h"	/* TBBTs	  		        */
+
+/* Define enum for type of object that property is within */
+typedef enum {
+    H5P_PROP_WITHIN_UNKNOWN=0,  /* Property container is unknown */
+    H5P_PROP_WITHIN_LIST,       /* Property is within a list */
+    H5P_PROP_WITHIN_CLASS       /* Property is within a class */
+} H5P_prop_within_t;
 
 /* Define enum for modifications to class */
 typedef enum {
@@ -40,21 +48,19 @@ typedef enum {
 /* Define structure to hold property information */
 typedef struct H5P_genprop_t {
     /* Values for this property */
-    unsigned xor_val;      /* XOR'ed version of the name, for faster comparisons */
     char *name;         /* Name of property */
     size_t size;        /* Size of property value */
     void *value;        /* Pointer to property value */
+    H5P_prop_within_t type;     /* Type of object the property is within */
+    unsigned shared_name;       /* Boolean: whether the name is shared or not */
 
     /* Callback function pointers & info */
     H5P_prp_create_func_t create;   /* Function to call when a property is created */
-    void *def_value;      /* Pointer to default value to pass along to create callback */
     H5P_prp_set_func_t set; /* Function to call when a property value is set */
     H5P_prp_get_func_t get; /* Function to call when a property value is retrieved */
     H5P_prp_delete_func_t del; /* Function to call when a property is deleted */
     H5P_prp_copy_func_t copy;  /* Function to call when a property is copied */
     H5P_prp_close_func_t close; /* Function to call when a property is closed */
-
-    struct H5P_genprop_t *next;  /* Pointer to the next property in this list */
 } H5P_genprop_t;
 
 /* Define structure to hold class information */
@@ -62,12 +68,13 @@ struct H5P_genclass_t {
     struct H5P_genclass_t *parent;     /* Pointer to parent class */
     char *name;         /* Name of property list class */
     size_t  nprops;     /* Number of properties in class */
-    unsigned   hashsize;   /* Hash table size */
     unsigned   plists;     /* Number of property lists that have been created since the last modification to the class */
     unsigned   classes;    /* Number of classes that have been derived since the last modification to the class */
     unsigned   ref_count;  /* Number of oustanding ID's open on this class object */
     unsigned   internal;   /* Whether this class is internal to the library or not */
     unsigned   deleted;    /* Whether this class has been deleted and is waiting for dependent classes & proplists to close */
+    unsigned   revision;   /* Revision number of a particular class (global) */
+    H5TB_TREE *props;   /* TBBT containing properties */
 
     /* Callback function pointers & info */
     H5P_cls_create_func_t create_func;  /* Function to call when a property list is created */
@@ -76,8 +83,6 @@ struct H5P_genclass_t {
     void *copy_data;    /* Pointer to user data to pass along to copy callback */
     H5P_cls_close_func_t close_func;   /* Function to call when a property list is closed */
     void *close_data;   /* Pointer to user data to pass along to close callback */
-
-    H5P_genprop_t *props[1];  /* Hash table of pointers to properties in the class */
 };
 
 /* Define structure to hold property list information */
@@ -86,14 +91,14 @@ struct H5P_genplist_t {
     hid_t   plist_id;       /* Copy of the property list ID (for use in close callback) */
     size_t  nprops;         /* Number of properties in class */
     unsigned   class_init:1;   /* Whether the class initialization callback finished successfully */
-
-    /* Hash size for a property list is same as class */
-    H5P_genprop_t *props[1];  /* Hash table of pointers to properties in the list */
+    H5TB_TREE *del;     /* TBBT containing names of deleted properties */
+    H5TB_TREE *props;   /* TBBT containing properties */
 };
 
 /* Private functions, not part of the publicly documented API */
-H5_DLL herr_t H5P_add_prop(H5P_genprop_t *hash[], unsigned hashsize, H5P_genprop_t *prop);
+H5_DLL herr_t H5P_add_prop(H5TB_TREE *props, H5P_genprop_t *prop);
 H5_DLL herr_t H5P_access_class(H5P_genclass_t *pclass, H5P_class_mod_t mod);
+H5_DLL int H5P_tbbt_strcmp(const void *k1, const void *k2, int UNUSED cmparg);
 
 #endif /* _H5Ppkg_H */