Merge remote-tracking branch 'origin/2.6' into 2.6

src/ae.c

@@ -37,6 +37,7 @@
 #include <stdlib.h>
 #include <poll.h>
 #include <string.h>
+#include <time.h>
 
 #include "ae.h"
 #include "zmalloc.h"
@@ -67,6 +68,7 @@ aeEventLoop *aeCreateEventLoop(int setsize) {
     eventLoop->fired = zmalloc(sizeof(aeFiredEvent)*setsize);
     if (eventLoop->events == NULL || eventLoop->fired == NULL) goto err;
     eventLoop->setsize = setsize;
+    eventLoop->lastTime = time(NULL);
     eventLoop->timeEventHead = NULL;
     eventLoop->timeEventNextId = 0;
     eventLoop->stop = 0;
@@ -236,6 +238,24 @@ static int processTimeEvents(aeEventLoop *eventLoop) {
     int processed = 0;
     aeTimeEvent *te;
     long long maxId;
+    time_t now = time(NULL);
+
+    /* If the system clock is moved to the future, and then set back to the
+     * right value, time events may be delayed in a random way. Often this
+     * means that scheduled operations will not be performed soon enough.
+     *
+     * Here we try to detect system clock skews, and force all the time
+     * events to be processed ASAP when this happens: the idea is that
+     * processing events earlier is less dangerous than delaying them
+     * indefinitely, and practice suggests it is. */
+    if (now < eventLoop->lastTime) {
+        te = eventLoop->timeEventHead;
+        while(te) {
+            te->when_sec = 0;
+            te = te->next;
+        }
+    }
+    eventLoop->lastTime = now;
 
     te = eventLoop->timeEventHead;
     maxId = eventLoop->timeEventNextId-1;

src/ae.h

@@ -88,6 +88,7 @@ typedef struct aeEventLoop {
     int maxfd;   /* highest file descriptor currently registered */
     int setsize; /* max number of file descriptors tracked */
     long long timeEventNextId;
+    time_t lastTime;     /* Used to detect system clock skew */
     aeFileEvent *events; /* Registered events */
     aeFiredEvent *fired; /* Fired events */
     aeTimeEvent *timeEventHead;

src/config.c

@@ -438,7 +438,12 @@ void configSetCommand(redisClient *c) {
         if (getLongLongFromObject(o,&ll) == REDIS_ERR ||
             ll < 0) goto badfmt;
         server.maxmemory = ll;
-        if (server.maxmemory) freeMemoryIfNeeded();
+        if (server.maxmemory) {
+            if (server.maxmemory < zmalloc_used_memory()) {
+                redisLog(REDIS_WARNING,"WARNING: the new maxmemory value set via CONFIG SET is smaller than the current memory usage. This will result in keys eviction and/or inability to accept new write commands depending on the maxmemory-policy.");
+            }
+            freeMemoryIfNeeded();
+        }
     } else if (!strcasecmp(c->argv[2]->ptr,"maxmemory-policy")) {
         if (!strcasecmp(o->ptr,"volatile-lru")) {
             server.maxmemory_policy = REDIS_MAXMEMORY_VOLATILE_LRU;

src/dict.c

@@ -85,29 +85,73 @@ unsigned int dictIdentityHashFunction(unsigned int key)
     return key;
 }
 
-static int dict_hash_function_seed = 5381;
+static uint32_t dict_hash_function_seed = 5381;
 
-void dictSetHashFunctionSeed(unsigned int seed) {
+void dictSetHashFunctionSeed(uint32_t seed) {
     dict_hash_function_seed = seed;
 }
 
-unsigned int dictGetHashFunctionSeed(void) {
+uint32_t 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) {
-    unsigned int hash = dict_hash_function_seed;
+/* MurmurHash2, by Austin Appleby
+ * Note - This code makes a few assumptions about how your machine behaves -
+ * 1. We can read a 4-byte value from any address without crashing
+ * 2. sizeof(int) == 4
+ *
+ * And it has a few limitations -
+ *
+ * 1. It will not work incrementally.
+ * 2. It will not produce the same results on little-endian and big-endian
+ *    machines.
+ */
+unsigned int dictGenHashFunction(const void *key, int len) {
+    /* 'm' and 'r' are mixing constants generated offline.
+     They're not really 'magic', they just happen to work well.  */
+    uint32_t seed = dict_hash_function_seed;
+    const uint32_t m = 0x5bd1e995;
+    const int r = 24;
 
-    while (len--)
-        hash = ((hash << 5) + hash) + (*buf++); /* hash * 33 + c */
-    return hash;
+    /* Initialize the hash to a 'random' value */
+    uint32_t h = seed ^ len;
+
+    /* Mix 4 bytes at a time into the hash */
+    const unsigned char *data = (const unsigned char *)key;
+
+    while(len >= 4) {
+        uint32_t k = *(uint32_t*)data;
+
+        k *= m;
+        k ^= k >> r;
+        k *= m;
+
+        h *= m;
+        h ^= k;
+
+        data += 4;
+        len -= 4;
+    }
+
+    /* Handle the last few bytes of the input array  */
+    switch(len) {
+    case 3: h ^= data[2] << 16;
+    case 2: h ^= data[1] << 8;
+    case 1: h ^= data[0]; h *= m;
+    };
+
+    /* Do a few final mixes of the hash to ensure the last few
+     * bytes are well-incorporated. */
+    h ^= h >> 13;
+    h *= m;
+    h ^= h >> 15;
+
+    return (unsigned int)h;
 }
 
-/* And a case insensitive version */
+/* And a case insensitive hash function (based on djb hash) */
 unsigned int dictGenCaseHashFunction(const unsigned char *buf, int len) {
-    unsigned int hash = dict_hash_function_seed;
+    unsigned int hash = (unsigned int)dict_hash_function_seed;
 
     while (len--)
         hash = ((hash << 5) + hash) + (tolower(*buf++)); /* hash * 33 + c */

src/dict.h

@@ -155,7 +155,7 @@ dictEntry *dictNext(dictIterator *iter);
 void dictReleaseIterator(dictIterator *iter);
 dictEntry *dictGetRandomKey(dict *d);
 void dictPrintStats(dict *d);
-unsigned int dictGenHashFunction(const unsigned char *buf, int len);
+unsigned int dictGenHashFunction(const void *key, int len);
 unsigned int dictGenCaseHashFunction(const unsigned char *buf, int len);
 void dictEmpty(dict *d);
 void dictEnableResize(void);

src/redis.c

@@ -2579,6 +2579,11 @@ int main(int argc, char **argv) {
             redisLog(REDIS_NOTICE,"The server is now ready to accept connections at %s", server.unixsocket);
     }
 
+    /* Warning the user about suspicious maxmemory setting. */
+    if (server.maxmemory > 0 && server.maxmemory < 1024*1024) {
+        redisLog(REDIS_WARNING,"WARNING: You specified a maxmemory value that is less than 1MB (current value is %llu bytes). Are you sure this is what you really want?", server.maxmemory);
+    }
+
     aeSetBeforeSleepProc(server.el,beforeSleep);
     aeMain(server.el);
     aeDeleteEventLoop(server.el);

src/replication.c

@@ -721,7 +721,7 @@ void replicationCron(void) {
     if (server.masterhost && server.repl_state == REDIS_REPL_TRANSFER &&
         (time(NULL)-server.repl_transfer_lastio) > server.repl_timeout)
     {
-        redisLog(REDIS_WARNING,"Timeout receiving bulk data from MASTER...");
+        redisLog(REDIS_WARNING,"Timeout receiving bulk data from MASTER... If the problem persists try to set the 'repl-timeout' parameter in redis.conf to a larger value.");
         replicationAbortSyncTransfer();
     }
 

src/sort.c

@@ -2,6 +2,8 @@
 #include "pqsort.h" /* Partial qsort for SORT+LIMIT */
 #include <math.h> /* isnan() */
 
+zskiplistNode* zslGetElementByRank(zskiplist *zsl, unsigned long rank);
+
 redisSortOperation *createSortOperation(int type, robj *pattern) {
     redisSortOperation *so = zmalloc(sizeof(*so));
     so->type = type;
@@ -156,8 +158,9 @@ void sortCommand(redisClient *c) {
 
     /* Lookup the key to sort. It must be of the right types */
     sortval = lookupKeyRead(c->db,c->argv[1]);
-    if (sortval && sortval->type != REDIS_SET && sortval->type != REDIS_LIST &&
-        sortval->type != REDIS_ZSET)
+    if (sortval && sortval->type != REDIS_SET &&
+                   sortval->type != REDIS_LIST &&
+                   sortval->type != REDIS_ZSET)
     {
         addReply(c,shared.wrongtypeerr);
         return;
@@ -167,7 +170,7 @@ void sortCommand(redisClient *c) {
      * Operations can be GET/DEL/INCR/DECR */
     operations = listCreate();
     listSetFreeMethod(operations,zfree);
-    j = 2;
+    j = 2; /* options start at argv[2] */
 
     /* Now we need to protect sortval incrementing its count, in the future
      * SORT may have options able to overwrite/delete keys during the sorting
@@ -213,13 +216,18 @@ void sortCommand(redisClient *c) {
         j++;
     }
 
-    /* If we have STORE we need to force sorting for deterministic output
-     * and replication. We use alpha sorting since this is guaranteed to
-     * work with any input.
+    /* For the STORE option, or when SORT is called from a Lua script,
+     * we want to force a specific ordering even when no explicit ordering
+     * was asked (SORT BY nosort). This guarantees that replication / AOF
+     * is deterministic.
      *
-     * We also want determinism when SORT is called from Lua scripts, so
-     * in this case we also force alpha sorting. */
-    if ((storekey || c->flags & REDIS_LUA_CLIENT) && dontsort) {
+     * However in the case 'dontsort' is true, but the type to sort is a
+     * sorted set, we don't need to do anything as ordering is guaranteed
+     * in this special case. */
+    if ((storekey || c->flags & REDIS_LUA_CLIENT) &&
+        (dontsort && sortval->type != REDIS_ZSET))
+    {
+        /* Force ALPHA sorting */
         dontsort = 0;
         alpha = 1;
         sortby = NULL;
@@ -229,13 +237,41 @@ void sortCommand(redisClient *c) {
     if (sortval->type == REDIS_ZSET)
         zsetConvert(sortval, REDIS_ENCODING_SKIPLIST);
 
-    /* Load the sorting vector with all the objects to sort */
+    /* Objtain the length of the object to sort. */
     switch(sortval->type) {
     case REDIS_LIST: vectorlen = listTypeLength(sortval); break;
     case REDIS_SET: vectorlen =  setTypeSize(sortval); break;
     case REDIS_ZSET: vectorlen = dictSize(((zset*)sortval->ptr)->dict); break;
     default: vectorlen = 0; redisPanic("Bad SORT type"); /* Avoid GCC warning */
     }
+
+    /* Perform LIMIT start,count sanity checking. */
+    start = (limit_start < 0) ? 0 : limit_start;
+    end = (limit_count < 0) ? vectorlen-1 : start+limit_count-1;
+    if (start >= vectorlen) {
+        start = vectorlen-1;
+        end = vectorlen-2;
+    }
+    if (end >= vectorlen) end = vectorlen-1;
+
+    /* Optimization:
+     *
+     * 1) if the object to sort is a sorted set.
+     * 2) There is nothing to sort as dontsort is true (BY <constant string>).
+     * 3) We have a LIMIT option that actually reduces the number of elements
+     *    to fetch.
+     *
+     * In this case to load all the objects in the vector is a huge waste of
+     * resources. We just allocate a vector that is big enough for the selected
+     * range length, and make sure to load just this part in the vector. */
+    if (sortval->type == REDIS_ZSET &&
+        dontsort &&
+        (start != 0 || end != vectorlen-1))
+    {
+        vectorlen = end-start+1;
+    }
+
+    /* Load the sorting vector with all the objects to sort */
     vector = zmalloc(sizeof(redisSortObject)*vectorlen);
     j = 0;
 
@@ -259,6 +295,48 @@ void sortCommand(redisClient *c) {
             j++;
         }
         setTypeReleaseIterator(si);
+    } else if (sortval->type == REDIS_ZSET && dontsort) {
+        /* Special handling for a sorted set, if 'dontsort' is true.
+         * This makes sure we return elements in the sorted set original
+         * ordering, accordingly to DESC / ASC options.
+         *
+         * Note that in this case we also handle LIMIT here in a direct
+         * way, just getting the required range, as an optimization. */
+
+        zset *zs = sortval->ptr;
+        zskiplist *zsl = zs->zsl;
+        zskiplistNode *ln;
+        robj *ele;
+        int rangelen = vectorlen;
+
+        /* Check if starting point is trivial, before doing log(N) lookup. */
+        if (desc) {
+            long zsetlen = dictSize(((zset*)sortval->ptr)->dict);
+
+            ln = zsl->tail;
+            if (start > 0)
+                ln = zslGetElementByRank(zsl,zsetlen-start);
+        } else {
+            ln = zsl->header->level[0].forward;
+            if (start > 0)
+                ln = zslGetElementByRank(zsl,start+1);
+        }
+
+        while(rangelen--) {
+            redisAssertWithInfo(c,sortval,ln != NULL);
+            ele = ln->obj;
+            vector[j].obj = ele;
+            vector[j].u.score = 0;
+            vector[j].u.cmpobj = NULL;
+            j++;
+            ln = desc ? ln->backward : ln->level[0].forward;
+        }
+        /* The code producing the output does not know that in the case of
+         * sorted set, 'dontsort', and LIMIT, we are able to get just the
+         * range, already sorted, so we need to adjust "start" and "end"
+         * to make sure start is set to 0. */
+        end -= start;
+        start = 0;
     } else if (sortval->type == REDIS_ZSET) {
         dict *set = ((zset*)sortval->ptr)->dict;
         dictIterator *di;
@@ -319,16 +397,6 @@ void sortCommand(redisClient *c) {
         }
     }
 
-    /* We are ready to sort the vector... perform a bit of sanity check
-     * on the LIMIT option too. We'll use a partial version of quicksort. */
-    start = (limit_start < 0) ? 0 : limit_start;
-    end = (limit_count < 0) ? vectorlen-1 : start+limit_count-1;
-    if (start >= vectorlen) {
-        start = vectorlen-1;
-        end = vectorlen-2;
-    }
-    if (end >= vectorlen) end = vectorlen-1;
-
     if (dontsort == 0) {
         server.sort_desc = desc;
         server.sort_alpha = alpha;

src/version.h

@@ -1 +1 @@
-#define REDIS_VERSION "2.5.13"
+#define REDIS_VERSION "2.5.14"