Redis源码剖析之数据过期(expire)

int expireIfNeeded(redisDb *db, robj *key) {
    if (!keyIsExpired(db,key)) return 0;

    /* 如果是在slave上下文中运行，直接返回1，因为slave的key过期是由master控制的，
     * master会给slave发送数据删除命令。 
     * 
     * 如果返回0表示数据不需要清理，返回1表示数据这次标记为过期 */
    if (server.masterhost != NULL) return 1;
    if (checkClientPauseTimeoutAndReturnIfPaused()) return 1;

    /* 删除key */
    server.stat_expiredkeys++;
    propagateExpire(db,key,server.lazyfree_lazy_expire);
    notifyKeyspaceEvent(NOTIFY_EXPIRED,
        "expired",key,db->id);
    int retval = server.lazyfree_lazy_expire ? dbAsyncDelete(db,key) :
                                               dbSyncDelete(db,key);
    if (retval) signalModifiedKey(NULL,db,key);
    return retval;
}

int retval = server.lazyfree_lazy_expire ? dbAsyncDelete(db,key) :
                                               dbSyncDelete(db,key);

#define LAZYFREE_THRESHOLD 64
int dbAsyncDelete(redisDb *db, robj *key) {
    /* 从db->expires中删除key，只是删除其指针而已，并没有删除实际值 */
    if (dictSize(db->expires) > 0) dictDelete(db->expires,key->ptr);

    /* If the value is composed of a few allocations, to free in a lazy way
     * is actually just slower... So under a certain limit we just free
     * the object synchronously. */
    /*
    * 在字典中摘除这个key(没有真正删除，只是查不到而已)，如果被摘除的dictEntry不为
    * 空就去执行下面的释放逻辑 
    */
    dictEntry *de = dictUnlink(db->dict,key->ptr);
    if (de) {
        robj *val = dictGetVal(de);
        /* Tells the module that the key has been unlinked from the database. */
        moduleNotifyKeyUnlink(key,val);

        /* lazy_free并不是完全异步的，而是先评估释放操作所需工作量，如果影响较小就直接在主线程中删除了 */
        size_t free_effort = lazyfreeGetFreeEffort(key,val);

        /* 如果释放这个对象需要做大量的工作，就把他放到异步线程里做
         * 但如果这个对象是共享对象(refcount > 1)就不能直接释放了，当然这很少发送，但有可能redis
         * 核心会调用incrRefCount来保护对象，然后调用dbDelete。这我只需要直接调用dictFreeUnlinkedEntry，
         * 等价于调用decrRefCount */
        if (free_effort > LAZYFREE_THRESHOLD && val->refcount == 1) {
            atomicIncr(lazyfree_objects,1);
            bioCreateLazyFreeJob(lazyfreeFreeObject,1, val);
            dictSetVal(db->dict,de,NULL);
        }
    }

    /* 释放键值对所占用的内存，如果是lazyFree，val已经是null了，只需要释放key的内存即可 */
    if (de) {
        dictFreeUnlinkedEntry(db->dict,de);
        if (server.cluster_enabled) slotToKeyDel(key->ptr);
        return 1;
    } else {
        return 0;
    }
}

void bioCreateLazyFreeJob(lazy_free_fn free_fn, int arg_count, ...) {
    va_list valist;
    /* Allocate memory for the job structure and all required
     * arguments */
    struct bio_job *job = zmalloc(sizeof(*job) + sizeof(void *) * (arg_count));
    job->free_fn = free_fn;

    va_start(valist, arg_count);
    for (int i = 0; i < arg_count; i++) {
        job->free_args[i] = va_arg(valist, void *);
    }
    va_end(valist);
    bioSubmitJob(BIO_LAZY_FREE, job);
} 

void bioSubmitJob(int type, struct bio_job *job) {
    job->time = time(NULL);
    // 多线程需要加锁，把待处理的job添加到队列末尾
    pthread_mutex_lock(&bio_mutex[type]);
    listAddNodeTail(bio_jobs[type],job);
    bio_pending[type]++;
    pthread_cond_signal(&bio_newjob_cond[type]);
    pthread_mutex_unlock(&bio_mutex[type]);
}

/* 有两种清理模式，快速清理和慢速清理 */
void activeExpireCycle(int type) {
    /* Adjust the running parameters according to the configured expire
     * effort. The default effort is 1, and the maximum configurable effort
     * is 10. */
    unsigned long
    effort = server.active_expire_effort-1, /* Rescale from 0 to 9. */
    config_keys_per_loop = ACTIVE_EXPIRE_CYCLE_KEYS_PER_LOOP +
                           ACTIVE_EXPIRE_CYCLE_KEYS_PER_LOOP/4*effort,  // 每次抽样的数据量大小 
    config_cycle_fast_duration = ACTIVE_EXPIRE_CYCLE_FAST_DURATION +
                                 ACTIVE_EXPIRE_CYCLE_FAST_DURATION/4*effort, // 每次清理的持续时间
    config_cycle_slow_time_perc = ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC +
                                  2*effort,  // 最大CPU周期使用率 
    config_cycle_acceptable_stale = ACTIVE_EXPIRE_CYCLE_ACCEPTABLE_STALE-
                                    effort; // 可接受的过期数据占比 

    /* This function has some global state in order to continue the work
     * incrementally across calls. */
    static unsigned int current_db = 0; /* Last DB tested. */
    static int timelimit_exit = 0;      /* Time limit hit in previous call? */
    static long long last_fast_cycle = 0; /* When last fast cycle ran. */

    int j, iteration = 0;
    int dbs_per_call = CRON_DBS_PER_CALL;
    long long start = ustime(), timelimit, elapsed;

    /* When clients are paused the dataset should be static not just from the
     * POV of clients not being able to write, but also from the POV of
     * expires and evictions of keys not being performed. */
    if (checkClientPauseTimeoutAndReturnIfPaused()) return;
    // 快速清理 
    if (type == ACTIVE_EXPIRE_CYCLE_FAST) {
        /* Don't start a fast cycle if the previous cycle did not exit
         * for time limit, unless the percentage of estimated stale keys is
         * too high. Also never repeat a fast cycle for the same period
         * as the fast cycle total duration itself. */
        // 如果上次执行没有触发timelimit_exit, 跳过执行
        if (!timelimit_exit &&
            server.stat_expired_stale_perc < config_cycle_acceptable_stale)
            return;
        // 两个快速清理周期内不执行快速清理
        if (start < last_fast_cycle + (long long)config_cycle_fast_duration*2)
            return;

        last_fast_cycle = start;
    }

    /* We usually should test CRON_DBS_PER_CALL per iteration, with
     * two exceptions:
     *
     * 1) Don't test more DBs than we have.
     * 2) If last time we hit the time limit, we want to scan all DBs
     * in this iteration, as there is work to do in some DB and we don't want
     * expired keys to use memory for too much time. */
    if (dbs_per_call > server.dbnum || timelimit_exit)
        dbs_per_call = server.dbnum;

    /* We can use at max 'config_cycle_slow_time_perc' percentage of CPU
     * time per iteration. Since this function gets called with a frequency of
     * server.hz times per second, the following is the max amount of
     * microseconds we can spend in this function. 
     * config_cycle_slow_time_perc是清理所能占用的CPU周期数配置，这里将周期数转化为具体的时间 */
    timelimit = config_cycle_slow_time_perc*1000000/server.hz/100;
    timelimit_exit = 0;
    if (timelimit <= 0) timelimit = 1;

    if (type == ACTIVE_EXPIRE_CYCLE_FAST)
        timelimit = config_cycle_fast_duration; /* in microseconds. */

    /* Accumulate some global stats as we expire keys, to have some idea
     * about the number of keys that are already logically expired, but still
     * existing inside the database. */
    long total_sampled = 0;
    long total_expired = 0;
    
    for (j = 0; j < dbs_per_call && timelimit_exit == 0; j++) {
        /* Expired and checked in a single loop. */
        unsigned long expired, sampled;
        
        redisDb *db = server.db+(current_db % server.dbnum);

        /* Increment the DB now so we are sure if we run out of time
         * in the current DB we'll restart from the next. This allows to
         * distribute the time evenly across DBs. */
        current_db++;

        /* Continue to expire if at the end of the cycle there are still
         * a big percentage of keys to expire, compared to the number of keys
         * we scanned. The percentage, stored in config_cycle_acceptable_stale
         * is not fixed, but depends on the Redis configured "expire effort". */
        do {
            unsigned long num, slots;
            long long now, ttl_sum;
            int ttl_samples;
            iteration++;

            /* 如果没有可清理的，直接结束 */
            if ((num = dictSize(db->expires)) == 0) {
                db->avg_ttl = 0;
                break;
            }
            slots = dictSlots(db->expires);
            now = mstime();

            /* 如果slot的填充率小于1%，采样的成本太高，跳过执行，等待下次合适的机会。*/
            if (num && slots > DICT_HT_INITIAL_SIZE &&
                (num*100/slots < 1)) break;

            /* 记录本次采样的数据和其中过期的数量 */
            expired = 0;
            sampled = 0;
            ttl_sum = 0;
            ttl_samples = 0;
            // 每次最多抽样num个 
            if (num > config_keys_per_loop)
                num = config_keys_per_loop;

            /* 这里因为性能考量，我们访问了hashcode的的底层实现，代码和dict.c有些类型，
             * 但十几年内很难改变。 
             * 
             * 注意：hashtable很多特定的地方是空的，所以我们的终止条件需要考虑到已扫描的bucket
             * 数量。 但实际上扫描空bucket是很快的，因为都是在cpu 缓存行里线性扫描，所以可以多
             * 扫一些bucket */
            long max_buckets = num*20;
            long checked_buckets = 0;
            // 这里有采样数据和bucket数量的限制。 
            while (sampled < num && checked_buckets < max_buckets) {
                for (int table = 0; table < 2; table++) {
                    if (table == 1 && !dictIsRehashing(db->expires)) break;

                    unsigned long idx = db->expires_cursor;
                    idx &= db->expires->ht[table].sizemask;
                    dictEntry *de = db->expires->ht[table].table[idx];
                    long long ttl;

                    /* 遍历当前bucket中的所有entry*/
                    checked_buckets++;
                    while(de) {
                        /* Get the next entry now since this entry may get
                         * deleted. */
                        dictEntry *e = de;
                        de = de->next;

                        ttl = dictGetSignedIntegerVal(e)-now;
                        if (activeExpireCycleTryExpire(db,e,now)) expired++;
                        if (ttl > 0) {
                            /* We want the average TTL of keys yet
                             * not expired. */
                            ttl_sum += ttl;
                            ttl_samples++;
                        }
                        sampled++;
                    }
                }
                db->expires_cursor++;
            }
            total_expired += expired;
            total_sampled += sampled;

            /* 更新ttl统计信息 */
            if (ttl_samples) {
                long long avg_ttl = ttl_sum/ttl_samples;

                /* Do a simple running average with a few samples.
                 * We just use the current estimate with a weight of 2%
                 * and the previous estimate with a weight of 98%. */
                if (db->avg_ttl == 0) db->avg_ttl = avg_ttl;
                db->avg_ttl = (db->avg_ttl/50)*49 + (avg_ttl/50);
            }

            /* We can't block forever here even if there are many keys to
             * expire. So after a given amount of milliseconds return to the
             * caller waiting for the other active expire cycle. 
             * 不能一直阻塞在这里做清理工作，如果超时了要结束清理循环*/
            if ((iteration & 0xf) == 0) { /* check once every 16 iterations. */
                elapsed = ustime()-start;
                if (elapsed > timelimit) {
                    timelimit_exit = 1;
                    server.stat_expired_time_cap_reached_count++;
                    break;
                }
            }
            /*
             * 如果过期key数量超过采样数的10%+effort，说明过期测数量较多，要多清理下，所以
             * 继续循环做一次采样清理。     
             */
        } while (sampled == 0 ||
                 (expired*100/sampled) > config_cycle_acceptable_stale);
    }

    elapsed = ustime()-start;
    server.stat_expire_cycle_time_used += elapsed;
    latencyAddSampleIfNeeded("expire-cycle",elapsed/1000);

    /* Update our estimate of keys existing but yet to be expired.
     * Running average with this sample accounting for 5%. */
    double current_perc;
    if (total_sampled) {
        current_perc = (double)total_expired/total_sampled;
    } else
        current_perc = 0;
    server.stat_expired_stale_perc = (current_perc*0.05)+
                                     (server.stat_expired_stale_perc*0.95);
}