Redis中key过期策略的实现

maxmomory <bytes>  # redis占用的最大内存

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

    /* If we are running in the context of a slave, instead of
     * evicting the expired key from the database, we return ASAP:
     * the slave key expiration is controlled by the master that will
     * send us synthesized DEL operations for expired keys.
     *
     * Still we try to return the right information to the caller,
     * that is, 0 if we think the key should be still valid, 1 if
     * we think the key is expired at this time. */
    // 如果有配置masterhost，说明是从节点，那么不执行key删除操作
    if (server.masterhost != NULL) return 1;

    /* Delete the key */
    server.stat_expiredkeys++;
    propagateExpire(db,key,server.lazyfree_lazy_expire);
    notifyKeyspaceEvent(NOTIFY_EXPIRED,
        "expired",key,db->id);
    // 判断lazyfree_lazy_expire是否开启，开启执行异步删除，不开启执行同步删除，4.0之后新增的功能，默认是关闭
    int retval = server.lazyfree_lazy_expire ? dbAsyncDelete(db,key) :
                                               dbSyncDelete(db,key);
    if (retval) signalModifiedKey(NULL,db,key);
    return retval;
}

/* Handle background operations on Redis databases. */
databasesCron();

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()) { // 是否主服务器
            activeExpireCycle(ACTIVE_EXPIRE_CYCLE_SLOW);
        } else { // 从服务器
            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;
                }
            }
        }
    }
}

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,
    config_cycle_fast_duration = ACTIVE_EXPIRE_CYCLE_FAST_DURATION +
                                 ACTIVE_EXPIRE_CYCLE_FAST_DURATION/4*effort,
    config_cycle_slow_time_perc = ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC +
                                  2*effort,
    config_cycle_acceptable_stale = ACTIVE_EXPIRE_CYCLE_ACCEPTABLE_STALE-
                                    effort;

    /* 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 (clientsArePaused()) return;

    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. */
        if (!timelimit_exit &&
            server.stat_expired_stale_perc < config_cycle_acceptable_stale)
            return;

        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. */
    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++;

            /* If there is nothing to expire try next DB ASAP. */
            if ((num = dictSize(db->expires)) == 0) {
                db->avg_ttl = 0;
                break;
            }
            slots = dictSlots(db->expires);
            now = mstime();

            /* When there are less than 1% filled slots, sampling the key
             * space is expensive, so stop here waiting for better times...
             * The dictionary will be resized asap. */
            if (num && slots > DICT_HT_INITIAL_SIZE &&
                (num*100/slots < 1)) break;

            /* The main collection cycle. Sample random keys among keys
             * with an expire set, checking for expired ones. */
            expired = 0;
            sampled = 0;
            ttl_sum = 0;
            ttl_samples = 0;
			// 最多那20个
            if (num > config_keys_per_loop)
                num = config_keys_per_loop;

            /* Here we access the low level representation of the hash table
             * for speed concerns: this makes this code coupled with dict.c,
             * but it hardly changed in ten years.
             *
             * Note that certain places of the hash table may be empty,
             * so we want also a stop condition about the number of
             * buckets that we scanned. However scanning for free buckets
             * is very fast: we are in the cache line scanning a sequential
             * array of NULL pointers, so we can scan a lot more buckets
             * than keys in the same time. */
            long max_buckets = num*20;
            long checked_buckets = 0;
			// 如果拿到的key数量大于20 或者 checked_buckets大于400，跳出循环
            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;
                    // 根据index拿到hash桶
                    dictEntry *de = db->expires->ht[table].table[idx];
                    long long ttl;

                    /* Scan the current bucket of the current table. */
                    checked_buckets++;
                    // 循环hash桶里的key
                    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;

            /* Update the average TTL stats for this database. */
            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. */
            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;
                }
            }
            /* We don't repeat the cycle for the current database if there are
             * an acceptable amount of stale keys (logically expired but yet
             * not reclaimed). */
             // 比例超过10%，expired过期的key数量，sampled总的扫描数量
        } 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);
}