Redis源码剖析之内存淘汰策略(Evict)

typedef struct redisObject {
    unsigned type:4;  
    unsigned encoding:4;
    unsigned lru:LRU_BITS; 
    int refcount;      
    void *ptr;            
} robj;

robj *lookupKey(redisDb *db, robj *key, int flags) {
    dictEntry *de = dictFind(db->dict,key->ptr);
    if (de) {
        robj *val = dictGetVal(de);
        if (!hasActiveChildProcess() && !(flags & LOOKUP_NOTOUCH)){
            if (server.maxmemory_policy & MAXMEMORY_FLAG_LFU) {
                updateLFU(val);
            } else {
                val->lru = LRU_CLOCK();  // 这里更新LRU时间戳  
            }
        }
        return val;
    } else {
        return NULL;
    }
}

/* 更新lfu的counter，counter并不是一个准确的数值，而是概率增长，counter的数值越大其增长速度越慢
 * 只能反映出某个时间窗口的热度，无法反映出具体访问次数 */
uint8_t LFULogIncr(uint8_t counter) {
    if (counter == 255) return 255;
    double r = (double)rand()/RAND_MAX;
    double baseval = counter - LFU_INIT_VAL; // LFU_INIT_VAL为5
    if (baseval < 0) baseval = 0;
    double p = 1.0/(baseval*server.lfu_log_factor+1);  // server.lfu_log_factor可配置，默认是10 
    if (r < p) counter++;
    return counter;
}

/* lfu counter衰减逻辑, lfu_decay_time是指多久counter衰减1，比如lfu_decay_time == 10
 * 表示每10分钟counter衰减一，但lfu_decay_time为0时counter不衰减 */
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;
}

static int isSafeToPerformEvictions(void) {
    /* 没有lua脚本执行超时，也没有在做数据超时 */
    if (server.lua_timedout || server.loading) return 0;
    /* 只有master才需要做evict */
    if (server.masterhost && server.repl_slave_ignore_maxmemory) return 0;
    /* 当客户端暂停时，不需要evict，因为数据是不会变化的 */
    if (checkClientPauseTimeoutAndReturnIfPaused()) return 0;
    return 1;
}

int performEvictions(void) {
    if (!isSafeToPerformEvictions()) return EVICT_OK;
    int keys_freed = 0;
    size_t mem_reported, mem_tofree;
    long long mem_freed; /* May be negative */
    mstime_t latency, eviction_latency;
    long long delta;
    int slaves = listLength(server.slaves);
    int result = EVICT_FAIL;
    if (getMaxmemoryState(&mem_reported,NULL,&mem_tofree,NULL) == C_OK)
        return EVICT_OK;
    if (server.maxmemory_policy == MAXMEMORY_NO_EVICTION)
        return EVICT_FAIL;  /* We need to free memory, but policy forbids. */
    unsigned long eviction_time_limit_us = evictionTimeLimitUs();
    mem_freed = 0;
    latencyStartMonitor(latency);
    monotime evictionTimer;
    elapsedStart(&evictionTimer);
    while (mem_freed < (long long)mem_tofree) {
        int j, k, i;
        static unsigned int next_db = 0;
        sds bestkey = NULL;
        int bestdbid;
        redisDb *db;
        dict *dict;
        dictEntry *de;
        if (server.maxmemory_policy & (MAXMEMORY_FLAG_LRU|MAXMEMORY_FLAG_LFU) ||
            server.maxmemory_policy == MAXMEMORY_VOLATILE_TTL)
        {
            struct evictionPoolEntry *pool = EvictionPoolLRU;
            while(bestkey == NULL) {
                unsigned long total_keys = 0, keys;
                /* We don't want to make local-db choices when expiring keys,
                 * so to start populate the eviction pool sampling keys from
                 * every DB. 
                 * 先从dict中采样key并放到pool中 */
                for (i = 0; i < server.dbnum; i++) {
                    db = server.db+i;
                    dict = (server.maxmemory_policy & MAXMEMORY_FLAG_ALLKEYS) ?
                            db->dict : db->expires;
                    if ((keys = dictSize(dict)) != 0) {
                        evictionPoolPopulate(i, dict, db->dict, pool);
                        total_keys += keys;
                    }
                }
                if (!total_keys) break; /* No keys to evict. */
                /* 从pool中选择最适合淘汰的key. */
                for (k = EVPOOL_SIZE-1; k >= 0; k--) {
                    if (pool[k].key == NULL) continue;
                    bestdbid = pool[k].dbid;
                    if (server.maxmemory_policy & MAXMEMORY_FLAG_ALLKEYS) {
                        de = dictFind(server.db[pool[k].dbid].dict,
                            pool[k].key);
                    } else {
                        de = dictFind(server.db[pool[k].dbid].expires,
                            pool[k].key);
                    }
                    /* 从淘汰池中移除. */
                    if (pool[k].key != pool[k].cached)
                        sdsfree(pool[k].key);
                    pool[k].key = NULL;
                    pool[k].idle = 0;
                    /* If the key exists, is our pick. Otherwise it is
                     * a ghost and we need to try the next element. */
                    if (de) {
                        bestkey = dictGetKey(de);
                        break;
                    } else {
                        /* Ghost... Iterate again. */
                    }
                }
            }
        }
        /* volatile-random and allkeys-random 策略 */
        else if (server.maxmemory_policy == MAXMEMORY_ALLKEYS_RANDOM ||
                 server.maxmemory_policy == MAXMEMORY_VOLATILE_RANDOM)
        {
            /* 当随机淘汰时，我们用静态变量next_db来存储当前执行到哪个db了*/
            for (i = 0; i < server.dbnum; i++) {
                j = (++next_db) % server.dbnum;
                db = server.db+j;
                dict = (server.maxmemory_policy == MAXMEMORY_ALLKEYS_RANDOM) ?
                        db->dict : db->expires;
                if (dictSize(dict) != 0) {
                    de = dictGetRandomKey(dict);
                    bestkey = dictGetKey(de);
                    bestdbid = j;
                    break;
                }
            }
        }
        /* 从dict中移除被选中的key. */
        if (bestkey) {
            db = server.db+bestdbid;
            robj *keyobj = createStringObject(bestkey,sdslen(bestkey));
            propagateExpire(db,keyobj,server.lazyfree_lazy_eviction);
            /*我们单独计算db*Delete()释放的内存量。实际上，在AOF和副本传播所需的内存可能大于我们正在释放的内存（删除key）
            ，如果我们考虑这点的话会很绕。由signalModifiedKey生成的CSC失效消息也是这样。
            因为AOF和输出缓冲区内存最终会被释放，所以我们只需要关心key空间使用的内存即可。*/
            delta = (long long) zmalloc_used_memory();
            latencyStartMonitor(eviction_latency);
            if (server.lazyfree_lazy_eviction)
                dbAsyncDelete(db,keyobj);
            else
                dbSyncDelete(db,keyobj);
            latencyEndMonitor(eviction_latency);
            latencyAddSampleIfNeeded("eviction-del",eviction_latency);
            delta -= (long long) zmalloc_used_memory();
            mem_freed += delta;
            server.stat_evictedkeys++;
            signalModifiedKey(NULL,db,keyobj);
            notifyKeyspaceEvent(NOTIFY_EVICTED, "evicted",
                keyobj, db->id);
            decrRefCount(keyobj);
            keys_freed++;
            if (keys_freed % 16 == 0) {
                /*当要释放的内存开始足够大时，我们可能会在这里花费太多时间，不可能足够快地将数据传送到副本，因此我们会在循环中强制传输。*/
                if (slaves) flushSlavesOutputBuffers();
                /*通常我们的停止条件是释放一个固定的，预先计算的内存量。但是，当我们*在另一个线程中删除对象时，
                最好不时*检查是否已经达到目标*内存，因为“mem\u freed”量只在dbAsyncDelete（）调用中*计算，
                而线程可以*一直释放内存。*/
                if (server.lazyfree_lazy_eviction) {
                    if (getMaxmemoryState(NULL,NULL,NULL,NULL) == C_OK) {
                        break;
                    }
                }
                /*一段时间后，尽早退出循环-即使尚未达到内存限制*。如果我们突然需要释放大量的内存，不要在这里花太多时间。*/
                if (elapsedUs(evictionTimer) > eviction_time_limit_us) {
                    // We still need to free memory - start eviction timer proc
                    if (!isEvictionProcRunning) {
                        isEvictionProcRunning = 1;
                        aeCreateTimeEvent(server.el, 0,
                                evictionTimeProc, NULL, NULL);
                    }
                    break;
                }
            }
        } else {
            goto cant_free; /* nothing to free... */
        }
    }
    /* at this point, the memory is OK, or we have reached the time limit */
    result = (isEvictionProcRunning) ? EVICT_RUNNING : EVICT_OK;
cant_free:
    if (result == EVICT_FAIL) {
        /* At this point, we have run out of evictable items.  It's possible
         * that some items are being freed in the lazyfree thread.  Perform a
         * short wait here if such jobs exist, but don't wait long.  */
        if (bioPendingJobsOfType(BIO_LAZY_FREE)) {
            usleep(eviction_time_limit_us);
            if (getMaxmemoryState(NULL,NULL,NULL,NULL) == C_OK) {
                result = EVICT_OK;
            }
        }
    }
    latencyEndMonitor(latency);
    latencyAddSampleIfNeeded("eviction-cycle",latency);
    return result;
}