X-Git-Url: https://git.saurik.com/redis.git/blobdiff_plain/aaada3f962a9f87fb239e55e3d26c1e794d411d5..52c863ddac711b08390216c5360bf703ecf29dc7:/src/dict.c

diff --git a/src/dict.c b/src/dict.c
index 2d1e752b..24001fdd 100644
--- a/src/dict.c
+++ b/src/dict.c
@@ -42,6 +42,7 @@
 #include <assert.h>
 #include <limits.h>
 #include <sys/time.h>
+#include <ctype.h>
 
 #include "dict.h"
 #include "zmalloc.h"
@@ -49,8 +50,13 @@
 /* Using dictEnableResize() / dictDisableResize() we make possible to
  * enable/disable resizing of the hash table as needed. This is very important
  * for Redis, as we use copy-on-write and don't want to move too much memory
- * around when there is a child performing saving operations. */
+ * around when there is a child performing saving operations.
+ *
+ * Note that even when dict_can_resize is set to 0, not all resizes are
+ * prevented: an hash table is still allowed to grow if the ratio between
+ * the number of elements and the buckets > dict_force_resize_ratio. */
 static int dict_can_resize = 1;
+static unsigned int dict_force_resize_ratio = 5;
 
 /* -------------------------- private prototypes ---------------------------- */
 
@@ -89,6 +95,15 @@ unsigned int dictGenHashFunction(const unsigned char *buf, int len) {
     return hash;
 }
 
+/* And a case insensitive version */
+unsigned int dictGenCaseHashFunction(const unsigned char *buf, int len) {
+    unsigned int hash = 5381;
+
+    while (len--)
+        hash = ((hash << 5) + hash) + (tolower(*buf++)); /* hash * 33 + c */
+    return hash;
+}
+
 /* ----------------------------- API implementation ------------------------- */
 
 /* Reset an hashtable already initialized with ht_init().
@@ -125,7 +140,7 @@ int _dictInit(dict *d, dictType *type,
 }
 
 /* Resize the table to the minimal size that contains all the elements,
- * but with the invariant of a USER/BUCKETS ration near to <= 1 */
+ * but with the invariant of a USER/BUCKETS ratio near to <= 1 */
 int dictResize(dict *d)
 {
     int minimal;
@@ -188,6 +203,7 @@ int dictRehash(dict *d, int n) {
 
         /* Note that rehashidx can't overflow as we are sure there are more
          * elements because ht[0].used != 0 */
+        assert(d->ht[0].size > (unsigned)d->rehashidx);
         while(d->ht[0].table[d->rehashidx] == NULL) d->rehashidx++;
         de = d->ht[0].table[d->rehashidx];
         /* Move all the keys in this bucket from the old to the new hash HT */
@@ -229,9 +245,9 @@ int dictRehashMilliseconds(dict *d, int ms) {
 }
 
 /* This function performs just a step of rehashing, and only if there are
- * not iterators bound to our hash table. When we have iterators in the middle
- * of a rehashing we can't mess with the two hash tables otherwise some element
- * can be missed or duplicated.
+ * no safe iterators bound to our hash table. When we have iterators in the
+ * middle of a rehashing we can't mess with the two hash tables otherwise
+ * some element can be missed or duplicated.
  *
  * This function is called by common lookup or update operations in the
  * dictionary so that the hash table automatically migrates from H1 to H2
@@ -408,17 +424,26 @@ dictIterator *dictGetIterator(dict *d)
     iter->d = d;
     iter->table = 0;
     iter->index = -1;
+    iter->safe = 0;
     iter->entry = NULL;
     iter->nextEntry = NULL;
     return iter;
 }
 
+dictIterator *dictGetSafeIterator(dict *d) {
+    dictIterator *i = dictGetIterator(d);
+
+    i->safe = 1;
+    return i;
+}
+
 dictEntry *dictNext(dictIterator *iter)
 {
     while (1) {
         if (iter->entry == NULL) {
             dictht *ht = &iter->d->ht[iter->table];
-            if (iter->index == -1 && iter->table == 0) iter->d->iterators++;
+            if (iter->safe && iter->index == -1 && iter->table == 0)
+                iter->d->iterators++;
             iter->index++;
             if (iter->index >= (signed) ht->size) {
                 if (dictIsRehashing(iter->d) && iter->table == 0) {
@@ -445,7 +470,8 @@ dictEntry *dictNext(dictIterator *iter)
 
 void dictReleaseIterator(dictIterator *iter)
 {
-    if (!(iter->index == -1 && iter->table == 0)) iter->d->iterators--;
+    if (iter->safe && !(iter->index == -1 && iter->table == 0))
+        iter->d->iterators--;
     zfree(iter);
 }
 
@@ -493,14 +519,23 @@ dictEntry *dictGetRandomKey(dict *d)
 /* Expand the hash table if needed */
 static int _dictExpandIfNeeded(dict *d)
 {
-    /* If the hash table is empty expand it to the intial size,
-     * if the table is "full" dobule its size. */
+    /* Incremental rehashing already in progress. Return. */
     if (dictIsRehashing(d)) return DICT_OK;
-    if (d->ht[0].size == 0)
-        return dictExpand(d, DICT_HT_INITIAL_SIZE);
-    if (d->ht[0].used >= d->ht[0].size && dict_can_resize)
+
+    /* If the hash table is empty expand it to the intial size. */
+    if (d->ht[0].size == 0) return dictExpand(d, DICT_HT_INITIAL_SIZE);
+
+    /* If we reached the 1:1 ratio, and we are allowed to resize the hash
+     * table (global setting) or we should avoid it but the ratio between
+     * elements/buckets is over the "safe" threshold, we resize doubling
+     * the number of buckets. */
+    if (d->ht[0].used >= d->ht[0].size &&
+        (dict_can_resize ||
+         d->ht[0].used/d->ht[0].size > dict_force_resize_ratio))
+    {
         return dictExpand(d, ((d->ht[0].size > d->ht[0].used) ?
                                     d->ht[0].size : d->ht[0].used)*2);
+    }
     return DICT_OK;
 }