【Redis核心原理专题】（1）「技术提升系列」分析探究如何实现LFU的热点key发现机制以及内部的Scan扫描技术的原理

typedef struct redisObject {
    unsigned type:4;
    unsigned encoding:4;
    unsigned lru:LRU_BITS; /* LRU time (relative to global lru_clock) or
                            * LFU data (least significant 8 bits frequency
                            * and most significant 16 bits access time). */
    int refcount;
    void *ptr;
} robj;
复制代码

uint8_t LFULogIncr(uint8_t counter) {
      if (counter == 255) return 255;
      double r = (double)rand()/RAND_MAX;
      double baseval = counter - LFU_INIT_VAL;
      if (baseval < 0) baseval = 0;
      double p = 1.0/(baseval*server.lfu_log_factor+1);
      if (r < p) counter++;
      return counter;
  }
复制代码

1/((counter-LFU_INIT_VAL)*server.lfu_log_factor+1)
复制代码

unsigned long LFUDecrAndReturn(robj *o) {
    unsigned long ldt = o->lru >> 8;
    unsigned long counter = o->lru & 255;
    unsigned long num_periods = server.lfu_decay_time ? LFUTimeElapsed(ldt) / server.lfu_decay_time : 0;
    if (num_periods)
        counter = (num_periods > counter) ? 0 : counter - num_periods;
    return counter;
}
复制代码

lfu-log-factor 10
lfu-decay-time 1
复制代码

void updateLFU(robj *val) {
    unsigned long counter = LFUDecrAndReturn(val);
    counter = LFULogIncr(counter);
    val->lru = (LFUGetTimeInMinutes()<<8) | counter;
}
复制代码

127.0.0.1:6379> config get maxmemory-policy
1) "maxmemory-policy"
2) "noeviction"
127.0.0.1:6379> object freq counter:000000006889
(error) ERR An LFU maxmemory policy is not selected, access frequency not tracked. Please note that when switching between policies at runtime LRU and LFU data will take some time to adjust.
127.0.0.1:6379> config set maxmemory-policy allkeys-lfu
OK
127.0.0.1:6379> object freq counter:000000006889
(integer) 3
复制代码

$./redis-cli --hotkeys
# Scanning the entire keyspace to find hot keys as well as
# average sizes per key type.  You can use -i 0.1 to sleep 0.1 sec
# per 100 SCAN commands (not usually needed).
[00.00%] Hot key 'counter:000000000002' found so far with counter 87
[00.00%] Hot key 'key:000000000001' found so far with counter 254
[00.00%] Hot key 'mylist' found so far with counter 107
[00.00%] Hot key 'key:000000000000' found so far with counter 254
[45.45%] Hot key 'counter:000000000001' found so far with counter 87
[45.45%] Hot key 'key:000000000002' found so far with counter 254
[45.45%] Hot key 'myset' found so far with counter 64
[45.45%] Hot key 'counter:000000000000' found so far with counter 93
-------- summary -------
Sampled 22 keys in the keyspace!
hot key found with counter: 254    keyname: key:000000000001
hot key found with counter: 254    keyname: key:000000000000
hot key found with counter: 254    keyname: key:000000000002
hot key found with counter: 107    keyname: mylist
hot key found with counter: 93    keyname: counter:000000000000
hot key found with counter: 87    keyname: counter:000000000002
hot key found with counter: 87    keyname: counter:000000000001
hot key found with counter: 64    keyname: myset
复制代码

127.0.0.1:6379> scan 0 match key99* count 1000
1) "13976"
2)  1) "key9911"
    2) "key9974"
    3) "key9994"
    4) "key9910"
    5) "key9907"
    6) "key9989"
    7) "key9971"
    8) "key99"
    9) "key9966"
   10) "key992"
   11) "key9903"
   12) "key9905"
127.0.0.1:6379> scan 13976 match key99* count 1000
1) "1996"
2)  1) "key9982"
    2) "key9997"
    3) "key9963"
    4) "key996"
    5) "key9912"
    6) "key9999"
    7) "key9921"
    8) "key994"
    9) "key9956"
   10) "key9919"
127.0.0.1:6379> scan 1996 match key99* count 1000
1) "12594"
2) 1) "key9939"
   2) "key9941"
   3) "key9967"
   4) "key9938"
   5) "key9906"
   6) "key999"
   7) "key9909"
   8) "key9933"
   9) "key9992"
......
127.0.0.1:6379> scan 11687 match key99* count 1000
1) "0"
2)  1) "key9969"
    2) "key998"
    3) "key9986"
    4) "key9968"
    5) "key9965"
    6) "key9990"
    7) "key9915"
    8) "key9928"
    9) "key9908"
   10) "key9929"
   11) "key9944"...
复制代码

127.0.0.1:6379> keys *
1) "db_number"
2) "key1"
3) "myKey"
127.0.0.1:6379> scan 0 MATCH * COUNT 1
1) "2"
2) 1) "db_number"
127.0.0.1:6379> scan 2 MATCH * COUNT 1
1) "1"
2) 1) "myKey"
127.0.0.1:6379> scan 1 MATCH * COUNT 1
1) "3"
2) 1) "key1"
127.0.0.1:6379> scan 3 MATCH * COUNT 1
1) "0"
2) (empty list or set)
复制代码

0->2->1->3
复制代码

v = rev(v);
v++;
v = rev(v);
复制代码

/* 字典 */
typedef struct dict {
    // 类型特定函数
    dictType *type;
    // 私有数据
    void *privdata;
    // 哈希表
    dictht ht[2];
    // rehash 索引
    // 当 rehash 不在进行时，值为 -1
    int rehashidx; /* rehashing not in progress if rehashidx == -1 */
    // 目前正在运行的安全迭代器的数量
    int iterators; /* number of iterators currently running */
} dict;
复制代码

/* 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;
    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;
}
复制代码