* Resolves: bug #735464 Fix the loop limit used to initialize the table directory, was based on count, now limited to segment_count.

* Do not pre-allocate all buckets based on requested table size. This
  defeats the point of a dynamic hash table which adjusts it's memory
  usage depending upon the number of items it holds. Pre-allocation
  also runs afoul of the table contraction logic, if the table is
  pre-allocated to a large size it will subsequently try to compact it
  negating the pre-allocation. Now the initial allocation is
  restricted to one directory segment (i.e. table->segment_count == 1)

* If the caller did not specify the directory_bits and segment_bits
  then compute them from the requested table size. The directory_size
  and segment_size must be powers of 2 to accmodate fast
  arithmetic. An optimal maximum number of buckets would be equal to
  the anticipated table size. If there were no collisions that would
  mean each item would be located in it's own bucket whose chain
  length is 1, the item would be immediatly found upon indexing into
  the bucket table.

* There is a requirment there be at least one directory
  segment, however contract_table() failed to enforce this
  requirement. Add a check to enforce the requirement.

* If hash_create() or hash_create_ex() failed it left the tbl
  parameter uninitialized but returned an error code. Now upon failure
  tbl is initialized to NULL as well as returning an error code.

* Clean up how the directory and segment sizes were computed. It had
  been using a loop and shifting 1 bit at a time, now it shifts all
  the bits in one operation and assures at least one directory and
  segment are allocated.

* In the event of an early exit from hash_create_ex() due to an error
  make sure all previously allocated resources are cleaned up by
  calling hash_destroy(). There was only one place this was
  missing. hash_destroy() blindly assumed the table had a directory,
  normally it would unless hash_destroy was called due to an early
  exit in hash_create_ex(). Modify hash_destroy() to check for the
  existence of the directory before cleaning up the directory
  contents.

* Update the function documentation in dhash.h to explain each
  parameter of hash_create() and hash_create_ex().

* Enhance dhash_test.c
  - To output the random seed used to intialize the random number
    generator and add command line option to set the random seed. This
    permits recreating a failed test run.
  - Add command line parameter to set the initial table size.
  - Use proper string to long conversion routines when reading command
    line parameters (e.g. strtoul() instead of atoi())
  - Add logic to make sure each test value is unique.

* Add additional information to the debug output to show the computed
  directory_bits, segment_bits, sizes, etc.

* Adjust the debug_level conditionals to be less verbose.

1 files changed, 37 insertions, 10 deletions

diff --git a/dhash/examples/dhash_test.c b/dhash/examples/dhash_test.c
index 6c02de1..8c11227 100644
--- a/dhash/examples/dhash_test.c
+++ b/dhash/examples/dhash_test.c
@@ -132,7 +132,9 @@ typedef struct test_val_t {
 int main(int argc, char **argv)
 {
     test_val_t *test = NULL;
-    long i, k;
+    long i, j, k;
+    bool duplicate;
+    long val;
     int status;
     hash_value_t value;
     hash_value_t old_value;
@@ -141,8 +143,10 @@ int main(int argc, char **argv)
     char buf[1024];
     hash_table_t *table = NULL;
     unsigned long callback_count = 0;
-    unsigned int directory_bits = HASH_DEFAULT_DIRECTORY_BITS;
-    unsigned int segment_bits = HASH_DEFAULT_SEGMENT_BITS;
+    unsigned long table_size = 0;
+    unsigned int seed = time(0);
+    unsigned int directory_bits = 0;
+    unsigned int segment_bits = 0;
     unsigned long min_load_factor = HASH_DEFAULT_MIN_LOAD_FACTOR;
     unsigned long max_load_factor = HASH_DEFAULT_MAX_LOAD_FACTOR;
 
@@ -153,20 +157,22 @@ int main(int argc, char **argv)
             {"count", 1, 0, 'c'},
             {"verbose", 1, 0, 'v'},
             {"quiet", 1, 0, 'q'},
+            {"table-size", 1, 0, 't'},
             {"directory-bits", 1, 0, 'd'},
             {"segment-bits", 1, 0, 's'},
             {"min-load-factor", 1, 0, 'l'},
             {"max-load-factor", 1, 0, 'h'},
+            {"seed", 1, 0, 'r'},
             {0, 0, 0, 0}
         };
 
-        arg = getopt_long(argc, argv, "c:vqd:s:l:h:",
+        arg = getopt_long(argc, argv, "c:vqt:d:s:l:h:r:",
                           long_options, &option_index);
         if (arg == -1) break;
 
         switch (arg) {
         case 'c':
-            max_test = atol(optarg);
+            max_test = strtoul(optarg, NULL, 0);
             break;
         case 'v':
             verbose = 1;
@@ -174,6 +180,9 @@ int main(int argc, char **argv)
         case 'q':
             verbose = 0;
             break;
+        case 't':
+            table_size = strtoul(optarg, NULL, 0);
+            break;
         case 'd':
             directory_bits = atoi(optarg);
             break;
@@ -181,10 +190,13 @@ int main(int argc, char **argv)
             segment_bits = atoi(optarg);
             break;
         case 'l':
-            min_load_factor = atol(optarg);
+            min_load_factor = strtoul(optarg, NULL, 0);
             break;
         case 'h':
-            max_load_factor = atol(optarg);
+            max_load_factor = strtoul(optarg, NULL, 0);
+            break;
+        case 'r':
+            seed = strtoul(optarg, NULL, 0);
             break;
         }
     }
@@ -204,10 +216,11 @@ int main(int argc, char **argv)
 
 
     /* Initialize the random number generator */
-    srandom(time(0));
+    srandom(seed);
+    printf("random seed: %#x\n", seed);
 
     /* Create the hash table as small as possible to exercise growth */
-    if ((status = hash_create_ex(1, &table,
+    if ((status = hash_create_ex(table_size, &table,
                                  directory_bits, segment_bits,
                                  min_load_factor, max_load_factor,
                                  NULL, NULL, NULL,
@@ -218,7 +231,19 @@ int main(int argc, char **argv)
 
     /* Initialize the array of test values */
     for (i = 0; i < max_test; i++) {
-        test[i].val = random();
+        /* Get random value, make sure it's unique */
+        duplicate = true;
+        while (duplicate) {
+            duplicate = false;
+            val = random();
+            for (j = 0; j < i; j++) {
+                if (test[j].val == val) {
+                    duplicate = true;
+                    break;
+                }
+            }
+        }
+        test[i].val = val;
         /* If the value is odd we'll use a string as the key,
          * otherwise we'll use an unsigned long as the key */
         if (test[i].val & 1) {
@@ -228,6 +253,8 @@ int main(int argc, char **argv)
         }
     }
 
+    printf("Completed building test values, beginning test ...\n");
+
     /* Enter all the test values into the hash table */
     for (i = 0; i < max_test; i++) {
         if (test[i].val & 1) {