Redis 源码解析：深入了解 Redis 的渐进式 rehash 算法

/* Performs N steps of incremental rehashing. Returns 1 if there are still
 * keys to move from the old to the new hash table, otherwise 0 is returned.
 *
 * Note that a rehashing step consists in moving a bucket (that may have more
 * than one key as we use chaining) from the old to the new hash table, however
 * since part of the hash table may be composed of empty spaces, it is not
 * guaranteed that this function will rehash even a single bucket, since it
 * will visit at max N*10 empty buckets in total, otherwise the amount of
 * work it does would be unbound and the function may block for a long time. */

int dictRehash(dict *d, int n) {
    int empty_visits = n*10; /* Max number of empty buckets to visit. */
    if (!dictIsRehashing(d)) return 0;
    printf("dictRehash step=%d\n", n);
    while(n-- && d->ht[0].used != 0) {
        dictEntry *de, *nextde;

        /* 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 long)d->rehashidx);
        while(d->ht[0].table[d->rehashidx] == NULL) {
            d->rehashidx++;
            if (--empty_visits == 0) return 1;
        }
        de = d->ht[0].table[d->rehashidx];
        /* Move all the keys in this bucket from the old to the new hash HT */
        while(de) {
            uint64_t h;

            nextde = de->next;
            /* Get the index in the new hash table */
            h = dictHashKey(d, de->key) & d->ht[1].sizemask;
            de->next = d->ht[1].table[h];
            d->ht[1].table[h] = de;
            d->ht[0].used--;
            d->ht[1].used++;
            de = nextde;
        }
        d->ht[0].table[d->rehashidx] = NULL;
        d->rehashidx++;
    }

    /* Check if we already rehashed the whole table... */
    if (d->ht[0].used == 0) {
        zfree(d->ht[0].table);
        d->ht[0] = d->ht[1];
        _dictReset(&d->ht[1]);
        d->rehashidx = -1;
        return 0;
    }

    /* More to rehash... */
    return 1;
}

#define dictIsRehashing(d) ((d)->rehashidx != -1)

/* This function performs just a step of rehashing, and only if there are
 * 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
 * while it is actively used. */
static void _dictRehashStep(dict *d) {
    if (d->iterators == 0) dictRehash(d,1);
}

/* Low level add or find:
 * 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 exposed to the user API to be called
 * mainly in order to store non-pointers inside the hash value, example:
 *
 * entry = dictAddRaw(dict,mykey,NULL);
 * if (entry != NULL) dictSetSignedIntegerVal(entry,1000);
 *
 * Return values:
 *
 * If key already exists NULL is returned, and "*existing" is populated
 * with the existing entry if existing is not NULL.
 *
 * If key was added, the hash entry is returned to be manipulated by the caller.
 */
dictEntry *dictAddRaw(dict *d, void *key, dictEntry **existing)
{
    long index;
    dictEntry *entry;
    dictht *ht;

    if (dictIsRehashing(d)) _dictRehashStep(d);

    /* Get the index of the new element, or -1 if
     * the element already exists. */
    if ((index = _dictKeyIndex(d, key, dictHashKey(d,key), existing)) == -1)
        return NULL;

    /* Allocate the memory and store the new entry.
     * Insert the element in top, with the assumption that in a database
     * system it is more likely that recently added entries are accessed
     * more frequently. */
    ht = dictIsRehashing(d) ? &d->ht[1] : &d->ht[0];
    entry = zmalloc(sizeof(*entry));
    entry->next = ht->table[index];
    ht->table[index] = entry;
    ht->used++;

    /* Set the hash entry fields. */
    dictSetKey(d, entry, key);
    return entry;
}

/* Search and remove an element. This is an helper function for
 * dictDelete() and dictUnlink(), please check the top comment
 * of those functions. */
static dictEntry *dictGenericDelete(dict *d, const void *key, int nofree) {
    uint64_t h, idx;
    dictEntry *he, *prevHe;
    int table;

    if (d->ht[0].used == 0 && d->ht[1].used == 0) return NULL;

    if (dictIsRehashing(d)) _dictRehashStep(d);
    h = dictHashKey(d, key);

    for (table = 0; table <= 1; table++) {
        idx = h & d->ht[table].sizemask;
        he = d->ht[table].table[idx];
        prevHe = NULL;
        while(he) {
            if (key==he->key || 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) {
                    dictFreeKey(d, he);
                    dictFreeVal(d, he);
                    zfree(he);
                }
                d->ht[table].used--;
                return he;
            }
            prevHe = he;
            he = he->next;
        }
        if (!dictIsRehashing(d)) break;
    }
    return NULL; /* not found */
}

dictEntry *dictFind(dict *d, const void *key)
{
    dictEntry *he;
    uint64_t h, idx, table;

    if (dictSize(d) == 0) return NULL; /* dict is empty */
    if (dictIsRehashing(d)) _dictRehashStep(d);
    h = dictHashKey(d, key);
    for (table = 0; table <= 1; table++) {
        idx = h & d->ht[table].sizemask;
        he = d->ht[table].table[idx];
        while(he) {
            if (key==he->key || dictCompareKeys(d, key, he->key))
                return he;
            he = he->next;
        }
        if (!dictIsRehashing(d)) return NULL;
    }
    return NULL;
}

/* Return a random entry from the hash table. Useful to
 * implement randomized algorithms */
dictEntry *dictGetRandomKey(dict *d)
{
    dictEntry *he, *orighe;
    unsigned long h;
    int listlen, listele;

    if (dictSize(d) == 0) return NULL;
    if (dictIsRehashing(d)) _dictRehashStep(d);
    if (dictIsRehashing(d)) {
        do {
            /* We are sure there are no elements in indexes from 0
             * to rehashidx-1 */
            h = d->rehashidx + (randomULong() % (dictSlots(d) - d->rehashidx));
            he = (h >= d->ht[0].size) ? d->ht[1].table[h - d->ht[0].size] :
                                      d->ht[0].table[h];
        } while(he == NULL);
    } else {
        do {
            h = randomULong() & d->ht[0].sizemask;
            he = d->ht[0].table[h];
        } while(he == NULL);
    }

    /* Now we found a non empty bucket, but it is a linked
     * list and we need to get a random element from the list.
     * The only sane way to do so is counting the elements and
     * select a random index. */
    listlen = 0;
    orighe = he;
    while(he) {
        he = he->next;
        listlen++;
    }
    listele = random() % listlen;
    he = orighe;
    while(listele--) he = he->next;
    return he;
}

/* This function samples the dictionary to return a few keys from random
 * locations.
 *
 * It does not guarantee to return all the keys specified in 'count', nor
 * it does guarantee to return non-duplicated elements, however it will make
 * some effort to do both things.
 *
 * Returned pointers to hash table entries are stored into 'des' that
 * points to an array of dictEntry pointers. The array must have room for
 * at least 'count' elements, that is the argument we pass to the function
 * to tell how many random elements we need.
 *
 * The function returns the number of items stored into 'des', that may
 * be less than 'count' if the hash table has less than 'count' elements
 * inside, or if not enough elements were found in a reasonable amount of
 * steps.
 *
 * Note that this function is not suitable when you need a good distribution
 * of the returned items, but only when you need to "sample" a given number
 * of continuous elements to run some kind of algorithm or to produce
 * statistics. However the function is much faster than dictGetRandomKey()
 * at producing N elements. */
unsigned int dictGetSomeKeys(dict *d, dictEntry **des, unsigned int count) {
    unsigned long j; /* internal hash table id, 0 or 1. */
    unsigned long tables; /* 1 or 2 tables? */
    unsigned long stored = 0, maxsizemask;
    unsigned long maxsteps;

    if (dictSize(d) < count) count = dictSize(d);
    maxsteps = count*10;

    /* Try to do a rehashing work proportional to 'count'. */
    for (j = 0; j < count; j++) {
        if (dictIsRehashing(d))
            _dictRehashStep(d);
        else
            break;
    }

    tables = dictIsRehashing(d) ? 2 : 1;
    maxsizemask = d->ht[0].sizemask;
    if (tables > 1 && maxsizemask < d->ht[1].sizemask)
        maxsizemask = d->ht[1].sizemask;

    /* Pick a random point inside the larger table. */
    unsigned long i = randomULong() & maxsizemask;
    unsigned long emptylen = 0; /* Continuous empty entries so far. */
    while(stored < count && maxsteps--) {
        for (j = 0; j < tables; j++) {
            /* Invariant of the dict.c rehashing: up to the indexes already
             * visited in ht[0] during the rehashing, there are no populated
             * buckets, so we can skip ht[0] for indexes between 0 and idx-1. */
            if (tables == 2 && j == 0 && i < (unsigned long) d->rehashidx) {
                /* Moreover, if we are currently out of range in the second
                 * table, there will be no elements in both tables up to
                 * the current rehashing index, so we jump if possible.
                 * (this happens when going from big to small table). */
                if (i >= d->ht[1].size)
                    i = d->rehashidx;
                else
                    continue;
            }
            if (i >= d->ht[j].size) continue; /* Out of range for this table. */
            dictEntry *he = d->ht[j].table[i];

            /* Count contiguous empty buckets, and jump to other
             * locations if they reach 'count' (with a minimum of 5). */
            if (he == NULL) {
                emptylen++;
                if (emptylen >= 5 && emptylen > count) {
                    i = randomULong() & maxsizemask;
                    emptylen = 0;
                }
            } else {
                emptylen = 0;
                while (he) {
                    /* Collect all the elements of the buckets found non
                     * empty while iterating. */
                    *des = he;
                    des++;
                    he = he->next;
                    stored++;
                    if (stored == count) return stored;
                }
            }
        }
        i = (i+1) & maxsizemask;
    }
    return stored;
}

/* Rehash in ms+"delta" milliseconds. The value of "delta" is larger 
 * than 0, and is smaller than 1 in most cases. The exact upper bound 
 * depends on the running time of dictRehash(d,100).*/
int dictRehashMilliseconds(dict *d, int ms) {
    long long start = timeInMilliseconds();
    int rehashes = 0;

    while(dictRehash(d,100)) {
        rehashes += 100;
        if (timeInMilliseconds()-start > ms) break;
    }
    return rehashes;
}

/* Our hash table implementation performs rehashing incrementally while
 * we write/read from the hash table. Still if the server is idle, the hash
 * table will use two tables for a long time. So we try to use 1 millisecond
 * of CPU time at every call of this function to perform some rehashing.
 *
 * The function returns 1 if some rehashing was performed, otherwise 0
 * is returned. */
int incrementallyRehash(int dbid) {
    /* Keys dictionary */
    if (dictIsRehashing(server.db[dbid].dict)) {
        dictRehashMilliseconds(server.db[dbid].dict,1);
        return 1; /* already used our millisecond for this loop... */
    }
    /* Expires */
    if (dictIsRehashing(server.db[dbid].expires)) {
        dictRehashMilliseconds(server.db[dbid].expires,1);
        return 1; /* already used our millisecond for this loop... */
    }
    return 0;
}

/* Resize the table to the minimal size that contains all the elements,
 * but with the invariant of a USED/BUCKETS ratio near to <= 1 */
int dictResize(dict *d)
{
    unsigned long minimal;

    if (!dict_can_resize || dictIsRehashing(d)) return DICT_ERR;
    minimal = d->ht[0].used;
    if (minimal < DICT_HT_INITIAL_SIZE)
        minimal = DICT_HT_INITIAL_SIZE;
    return dictExpand(d, minimal);
}

/* Expand or create the hash table */
int dictExpand(dict *d, unsigned long size)
{
    /* the size is invalid if it is smaller than the number of
     * elements already inside the hash table */
    if (dictIsRehashing(d) || d->ht[0].used > size)
        return DICT_ERR;

    dictht n; /* the new hash table */
    unsigned long realsize = _dictNextPower(size);

    /* Rehashing to the same table size is not useful. */
    if (realsize == d->ht[0].size) return DICT_ERR;

    /* Allocate the new hash table and initialize all pointers to NULL */
    n.size = realsize;
    n.sizemask = realsize-1;
    n.table = zcalloc(realsize*sizeof(dictEntry*));
    n.used = 0;

    /* Is this the first initialization? If so it's not really a rehashing
     * we just set the first hash table so that it can accept keys. */
    if (d->ht[0].table == NULL) {
        d->ht[0] = n;
        return DICT_OK;
    }

    /* Prepare a second hash table for incremental rehashing */
    d->ht[1] = n;
    d->rehashidx = 0;
    return DICT_OK;
}

/* Resize the table to the minimal size that contains all the elements,
 * but with the invariant of a USED/BUCKETS ratio near to <= 1 */
int htNeedsResize(dict *dict) {
    long long size, used;

    size = dictSlots(dict);
    used = dictSize(dict);
    return (size > DICT_HT_INITIAL_SIZE &&
            (used*100/size < HASHTABLE_MIN_FILL));
}

/* If the percentage of used slots in the HT reaches HASHTABLE_MIN_FILL
 * we resize the hash table to save memory */
void tryResizeHashTables(int dbid) {
    if (htNeedsResize(server.db[dbid].dict))
        dictResize(server.db[dbid].dict);
    if (htNeedsResize(server.db[dbid].expires))
        dictResize(server.db[dbid].expires);
}

/* This function handles 'background' operations we are required to do
 * incrementally in Redis databases, such as active key expiring, resizing,
 * rehashing. */
void databasesCron(void) {
    /* Expire keys by random sampling. Not required for slaves
     * as master will synthesize DELs for us. */
    if (server.active_expire_enabled) {
        if (iAmMaster()) {
            activeExpireCycle(ACTIVE_EXPIRE_CYCLE_SLOW);
        } else {
            expireSlaveKeys();
        }
    }

    /* Defrag keys gradually. */
    activeDefragCycle();

    /* Perform hash tables rehashing if needed, but only if there are no
     * other processes saving the DB on disk. Otherwise rehashing is bad
     * as will cause a lot of copy-on-write of memory pages. */
    if (!hasActiveChildProcess()) {
        /* We use global counters so if we stop the computation at a given
         * DB we'll be able to start from the successive in the next
         * cron loop iteration. */
        static unsigned int resize_db = 0;
        static unsigned int rehash_db = 0;
        int dbs_per_call = CRON_DBS_PER_CALL;
        int j;

        /* Don't test more DBs than we have. */
        if (dbs_per_call > server.dbnum) dbs_per_call = server.dbnum;

        /* Resize */
        for (j = 0; j < dbs_per_call; j++) {
            tryResizeHashTables(resize_db % server.dbnum);
            resize_db++;
        }

        /* Rehash */
        if (server.activerehashing) {
            for (j = 0; j < dbs_per_call; j++) {
                int work_done = incrementallyRehash(rehash_db);
                if (work_done) {
                    /* If the function did some work, stop here, we'll do
                     * more at the next cron loop. */
                    break;
                } else {
                    /* If this db didn't need rehash, we'll try the next one. */
                    rehash_db++;
                    rehash_db %= server.dbnum;
                }
            }
        }
    }
}

/* Expand the hash table if needed */
static int _dictExpandIfNeeded(dict *d)
{
    /* Incremental rehashing already in progress. Return. */
    if (dictIsRehashing(d)) return DICT_OK;

    /* If the hash table is empty expand it to the initial 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].used*2);
    }
    return DICT_OK;
}

/* Low level add or find:
 * 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 exposed to the user API to be called
 * mainly in order to store non-pointers inside the hash value, example:
 *
 * entry = dictAddRaw(dict,mykey,NULL);
 * if (entry != NULL) dictSetSignedIntegerVal(entry,1000);
 *
 * Return values:
 *
 * If key already exists NULL is returned, and "*existing" is populated
 * with the existing entry if existing is not NULL.
 *
 * If key was added, the hash entry is returned to be manipulated by the caller.
 */
dictEntry *dictAddRaw(dict *d, void *key, dictEntry **existing)
{
    long index;
    dictEntry *entry;
    dictht *ht;

    if (dictIsRehashing(d)) _dictRehashStep(d);

    /* Get the index of the new element, or -1 if
     * the element already exists. */
    if ((index = _dictKeyIndex(d, key, dictHashKey(d,key), existing)) == -1)
        return NULL;

    /* Allocate the memory and store the new entry.
     * Insert the element in top, with the assumption that in a database
     * system it is more likely that recently added entries are accessed
     * more frequently. */
    ht = dictIsRehashing(d) ? &d->ht[1] : &d->ht[0];
    entry = zmalloc(sizeof(*entry));
    entry->next = ht->table[index];
    ht->table[index] = entry;
    ht->used++;

    /* Set the hash entry fields. */
    dictSetKey(d, entry, key);
    return entry;
}

/* Returns the index of a free slot that can be populated with
 * a hash entry for the given 'key'.
 * If the key already exists, -1 is returned
 * and the optional output parameter may be filled.
 *
 * Note that if we are in the process of rehashing the hash table, the
 * index is always returned in the context of the second (new) hash table. */
static long _dictKeyIndex(dict *d, const void *key, uint64_t hash, dictEntry **existing)
{
    unsigned long idx, table;
    dictEntry *he;
    if (existing) *existing = NULL;

    /* Expand the hash table if needed */
    if (_dictExpandIfNeeded(d) == DICT_ERR)
        return -1;
    for (table = 0; table <= 1; table++) {
        idx = hash & d->ht[table].sizemask;
        /* Search if this slot does not already contain the given key */
        he = d->ht[table].table[idx];
        while(he) {
            if (key==he->key || dictCompareKeys(d, key, he->key)) {
                if (existing) *existing = he;
                return -1;
            }
            he = he->next;
        }
        if (!dictIsRehashing(d)) break;
    }
    return idx;
}