Add ziplist test for deleting next to last entries

[redis.git] / src / dict.c

diff --git a/src/dict.c b/src/dict.c
index 77ce90cb0c0eaadc68a8180b8f744b660ef13514..69656734c6085a9e28b51eb75df218e3dd71da7a 100644 (file)
--- a/src/dict.c
+++ b/src/dict.c
@@ -42,6 +42,7 @@
 #include <assert.h>
 #include <limits.h>
 #include <sys/time.h>
 #include <assert.h>
 #include <limits.h>
 #include <sys/time.h>

+#include <ctype.h>

 
 #include "dict.h"
 #include "zmalloc.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
 /* 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 int dict_can_resize = 1;

+static unsigned int dict_force_resize_ratio = 5;

 
 /* -------------------------- private prototypes ---------------------------- */
 
 
 /* -------------------------- private prototypes ---------------------------- */
 


@@ -79,16 +85,35 @@ unsigned int dictIdentityHashFunction(unsigned int key)
     return key;
 }
 
     return key;
 }
 

+static int dict_hash_function_seed = 5381;
+
+void dictSetHashFunctionSeed(unsigned int seed) {
+    dict_hash_function_seed = seed;
+}
+
+unsigned int dictGetHashFunctionSeed(void) {
+    return dict_hash_function_seed;
+}
+

 /* Generic hash function (a popular one from Bernstein).
  * I tested a few and this was the best. */
 unsigned int dictGenHashFunction(const unsigned char *buf, int len) {
 /* Generic hash function (a popular one from Bernstein).
  * I tested a few and this was the best. */
 unsigned int dictGenHashFunction(const unsigned char *buf, int len) {

-    unsigned int hash = 5381;
+    unsigned int hash = dict_hash_function_seed;

 
     while (len--)
         hash = ((hash << 5) + hash) + (*buf++); /* hash * 33 + c */
     return hash;
 }
 
 
     while (len--)
         hash = ((hash << 5) + hash) + (*buf++); /* hash * 33 + c */
     return hash;
 }
 

+/* And a case insensitive version */
+unsigned int dictGenCaseHashFunction(const unsigned char *buf, int len) {
+    unsigned int hash = dict_hash_function_seed;
+
+    while (len--)
+        hash = ((hash << 5) + hash) + (tolower(*buf++)); /* hash * 33 + c */
+    return hash;
+}
+

 /* ----------------------------- API implementation ------------------------- */
 
 /* Reset an hashtable already initialized with ht_init().
 /* ----------------------------- API implementation ------------------------- */
 
 /* Reset an hashtable already initialized with ht_init().


@@ -125,7 +150,7 @@ int _dictInit(dict *d, dictType *type,
 }
 
 /* Resize the table to the minimal size that contains all the elements,
 }
 
 /* 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 USED/BUCKETS ratio near to <= 1 */

 int dictResize(dict *d)
 {
     int minimal;
 int dictResize(dict *d)
 {
     int minimal;


@@ -188,6 +213,7 @@ 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 */
 
         /* 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 */
         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 +255,9 @@ int dictRehashMilliseconds(dict *d, int ms) {
 }
 
 /* This function performs just a step of rehashing, and only if there are
 }
 
 /* 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
  *
  * This function is called by common lookup or update operations in the
  * dictionary so that the hash table automatically migrates from H1 to H2


@@ -242,6 +268,30 @@ static void _dictRehashStep(dict *d) {
 
 /* Add an element to the target hash table */
 int dictAdd(dict *d, void *key, void *val)
 
 /* Add an element to the target hash table */
 int dictAdd(dict *d, void *key, void *val)

+{
+    dictEntry *entry = dictAddRaw(d,key);
+
+    if (!entry) return DICT_ERR;
+    dictSetVal(d, entry, val);
+    return DICT_OK;
+}
+
+/* Low level add. This function adds the entry but instead of setting
+ * a value returns the dictEntry structure to the user, that will make
+ * sure to fill the value field as he wishes.
+ *
+ * This function is also directly expoed to user API to be called
+ * mainly in order to store non-pointers inside the hash value, example:
+ *
+ * entry = dictAddRaw(dict,mykey);
+ * if (entry != NULL) dictSetSignedIntegerVal(entry,1000);
+ *
+ * Return values:
+ *
+ * If key already exists NULL is returned.
+ * If key was added, the hash entry is returned to be manipulated by the caller.
+ */
+dictEntry *dictAddRaw(dict *d, void *key)

 {
     int index;
     dictEntry *entry;
 {
     int index;
     dictEntry *entry;


@@ -252,9 +302,9 @@ int dictAdd(dict *d, void *key, void *val)
     /* Get the index of the new element, or -1 if
      * the element already exists. */
     if ((index = _dictKeyIndex(d, key)) == -1)
     /* Get the index of the new element, or -1 if
      * the element already exists. */
     if ((index = _dictKeyIndex(d, key)) == -1)

-        return DICT_ERR;
+        return NULL;

 
 

-    /* Allocates the memory and stores key */
+    /* Allocate the memory and store the new entry */

     ht = dictIsRehashing(d) ? &d->ht[1] : &d->ht[0];
     entry = zmalloc(sizeof(*entry));
     entry->next = ht->table[index];
     ht = dictIsRehashing(d) ? &d->ht[1] : &d->ht[0];
     entry = zmalloc(sizeof(*entry));
     entry->next = ht->table[index];


@@ -262,9 +312,8 @@ int dictAdd(dict *d, void *key, void *val)
     ht->used++;
 
     /* Set the hash entry fields. */
     ht->used++;
 
     /* Set the hash entry fields. */

-    dictSetHashKey(d, entry, key);
-    dictSetHashVal(d, entry, val);
-    return DICT_OK;
+    dictSetKey(d, entry, key);
+    return entry;

 }
 
 /* Add an element, discarding the old if the key already exists.
 }
 
 /* Add an element, discarding the old if the key already exists.


@@ -281,18 +330,29 @@ int dictReplace(dict *d, void *key, void *val)
         return 1;
     /* It already exists, get the entry */
     entry = dictFind(d, key);
         return 1;
     /* It already exists, get the entry */
     entry = dictFind(d, key);

-    /* Free the old value and set the new one */

     /* Set the new value and free the old one. Note that it is important
      * to do that in this order, as the value may just be exactly the same
      * as the previous one. In this context, think to reference counting,
      * you want to increment (set), and then decrement (free), and not the
      * reverse. */
     auxentry = *entry;
     /* Set the new value and free the old one. Note that it is important
      * to do that in this order, as the value may just be exactly the same
      * as the previous one. In this context, think to reference counting,
      * you want to increment (set), and then decrement (free), and not the
      * reverse. */
     auxentry = *entry;

-    dictSetHashVal(d, entry, val);
-    dictFreeEntryVal(d, &auxentry);
+    dictSetVal(d, entry, val);
+    dictFreeVal(d, &auxentry);

     return 0;
 }
 
     return 0;
 }
 

+/* dictReplaceRaw() is simply a version of dictAddRaw() that always
+ * returns the hash entry of the specified key, even if the key already
+ * exists and can't be added (in that case the entry of the already
+ * existing key is returned.)
+ *
+ * See dictAddRaw() for more information. */
+dictEntry *dictReplaceRaw(dict *d, void *key) {
+    dictEntry *entry = dictFind(d,key);
+
+    return entry ? entry : dictAddRaw(d,key);
+}
+

 /* Search and remove an element */
 static int dictGenericDelete(dict *d, const void *key, int nofree)
 {
 /* Search and remove an element */
 static int dictGenericDelete(dict *d, const void *key, int nofree)
 {


@@ -309,15 +369,15 @@ static int dictGenericDelete(dict *d, const void *key, int nofree)
         he = d->ht[table].table[idx];
         prevHe = NULL;
         while(he) {
         he = d->ht[table].table[idx];
         prevHe = NULL;
         while(he) {

-            if (dictCompareHashKeys(d, key, he->key)) {
+            if (dictCompareKeys(d, key, he->key)) {

                 /* Unlink the element from the list */
                 if (prevHe)
                     prevHe->next = he->next;
                 else
                     d->ht[table].table[idx] = he->next;
                 if (!nofree) {
                 /* Unlink the element from the list */
                 if (prevHe)
                     prevHe->next = he->next;
                 else
                     d->ht[table].table[idx] = he->next;
                 if (!nofree) {

-                    dictFreeEntryKey(d, he);
-                    dictFreeEntryVal(d, he);
+                    dictFreeKey(d, he);
+                    dictFreeVal(d, he);

                 }
                 zfree(he);
                 d->ht[table].used--;
                 }
                 zfree(he);
                 d->ht[table].used--;


@@ -351,8 +411,8 @@ int _dictClear(dict *d, dictht *ht)
         if ((he = ht->table[i]) == NULL) continue;
         while(he) {
             nextHe = he->next;
         if ((he = ht->table[i]) == NULL) continue;
         while(he) {
             nextHe = he->next;

-            dictFreeEntryKey(d, he);
-            dictFreeEntryVal(d, he);
+            dictFreeKey(d, he);
+            dictFreeVal(d, he);

             zfree(he);
             ht->used--;
             he = nextHe;
             zfree(he);
             ht->used--;
             he = nextHe;


@@ -385,7 +445,7 @@ dictEntry *dictFind(dict *d, const void *key)
         idx = h & d->ht[table].sizemask;
         he = d->ht[table].table[idx];
         while(he) {
         idx = h & d->ht[table].sizemask;
         he = d->ht[table].table[idx];
         while(he) {

-            if (dictCompareHashKeys(d, key, he->key))
+            if (dictCompareKeys(d, key, he->key))

                 return he;
             he = he->next;
         }
                 return he;
             he = he->next;
         }


@@ -398,7 +458,7 @@ void *dictFetchValue(dict *d, const void *key) {
     dictEntry *he;
 
     he = dictFind(d,key);
     dictEntry *he;
 
     he = dictFind(d,key);

-    return he ? dictGetEntryVal(he) : NULL;
+    return he ? dictGetVal(he) : NULL;

 }
 
 dictIterator *dictGetIterator(dict *d)
 }
 
 dictIterator *dictGetIterator(dict *d)


@@ -408,17 +468,26 @@ dictIterator *dictGetIterator(dict *d)
     iter->d = d;
     iter->table = 0;
     iter->index = -1;
     iter->d = d;
     iter->table = 0;
     iter->index = -1;

+    iter->safe = 0;

     iter->entry = NULL;
     iter->nextEntry = NULL;
     return iter;
 }
 
     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];
 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) {
             iter->index++;
             if (iter->index >= (signed) ht->size) {
                 if (dictIsRehashing(iter->d) && iter->table == 0) {


@@ -445,7 +514,8 @@ dictEntry *dictNext(dictIterator *iter)
 
 void dictReleaseIterator(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);
 }
 
     zfree(iter);
 }
 


@@ -493,14 +563,23 @@ dictEntry *dictGetRandomKey(dict *d)
 /* Expand the hash table if needed */
 static int _dictExpandIfNeeded(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 (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 dictExpand(d, ((d->ht[0].size > d->ht[0].used) ?
                                     d->ht[0].size : d->ht[0].used)*2);

+    }

     return DICT_OK;
 }
 
     return DICT_OK;
 }
 


@@ -538,7 +617,7 @@ static int _dictKeyIndex(dict *d, const void *key)
         /* Search if this slot does not already contain the given key */
         he = d->ht[table].table[idx];
         while(he) {
         /* Search if this slot does not already contain the given key */
         he = d->ht[table].table[idx];
         while(he) {

-            if (dictCompareHashKeys(d, key, he->key))
+            if (dictCompareKeys(d, key, he->key))

                 return -1;
             he = he->next;
         }
                 return -1;
             he = he->next;
         }


@@ -554,6 +633,21 @@ void dictEmpty(dict *d) {
     d->iterators = 0;
 }
 
     d->iterators = 0;
 }
 

+void dictEnableResize(void) {
+    dict_can_resize = 1;
+}
+
+void dictDisableResize(void) {
+    dict_can_resize = 0;
+}
+
+#if 0
+
+/* The following is code that we don't use for Redis currently, but that is part
+of the library. */
+
+/* ----------------------- Debugging ------------------------*/
+

 #define DICT_STATS_VECTLEN 50
 static void _dictPrintStatsHt(dictht *ht) {
     unsigned long i, slots = 0, chainlen, maxchainlen = 0;
 #define DICT_STATS_VECTLEN 50
 static void _dictPrintStatsHt(dictht *ht) {
     unsigned long i, slots = 0, chainlen, maxchainlen = 0;


@@ -607,14 +701,6 @@ void dictPrintStats(dict *d) {
     }
 }
 
     }
 }
 

-void dictEnableResize(void) {
-    dict_can_resize = 1;
-}
-
-void dictDisableResize(void) {
-    dict_can_resize = 0;
-}
-

 /* ----------------------- StringCopy Hash Table Type ------------------------*/
 
 static unsigned int _dictStringCopyHTHashFunction(const void *key)
 /* ----------------------- StringCopy Hash Table Type ------------------------*/
 
 static unsigned int _dictStringCopyHTHashFunction(const void *key)


@@ -678,3 +764,4 @@ dictType dictTypeHeapStringCopyKeyValue = {
     _dictStringDestructor,         /* key destructor */
     _dictStringDestructor,         /* val destructor */
 };
     _dictStringDestructor,         /* key destructor */
     _dictStringDestructor,         /* val destructor */
 };

+#endif