Redis中的数据过期策略详解

127.0.0.1:6379> setex s 20 1
OK
127.0.0.1:6379> ttl s
(integer) 17
127.0.0.1:6379> setex s 200 1
OK
127.0.0.1:6379> ttl s
(integer) 195
127.0.0.1:6379> setrange s 3 100
(integer) 6
127.0.0.1:6379> ttl s
(integer) 152
127.0.0.1:6379> get s
"1\x00\x00100"
127.0.0.1:6379> ttl s
(integer) 108
127.0.0.1:6379> getset s 200
"1\x00\x00100"
127.0.0.1:6379> get s
"200"
127.0.0.1:6379> ttl s
(integer) -1

127.0.0.1:6379> setex s 100 test
OK
127.0.0.1:6379> get s
"test"
127.0.0.1:6379> ttl s
(integer) 94
127.0.0.1:6379> type s
string
127.0.0.1:6379> strlen s
(integer) 4
127.0.0.1:6379> persist s
(integer) 1
127.0.0.1:6379> ttl s
(integer) -1
127.0.0.1:6379> get s
"test"

127.0.0.1:6379> expire s 200
(integer) 1
127.0.0.1:6379> ttl s
(integer) 198
127.0.0.1:6379> rename s ss
OK
127.0.0.1:6379> ttl ss
(integer) 187
127.0.0.1:6379> type ss
string
127.0.0.1:6379> get ss
"test"

/*-----------------------------------------------------------------------------
 * Expires API
 *----------------------------------------------------------------------------*/
 
int removeExpire(redisDb *db, robj *key) {
 /* An expire may only be removed if there is a corresponding entry in the
 * main dict. Otherwise, the key will never be freed. */
 redisAssertWithInfo(NULL,key,dictFind(db->dict,key->ptr) != NULL);
 return dictDelete(db->expires,key->ptr) == DICT_OK;
}
 
void setExpire(redisDb *db, robj *key, long long when) {
 dictEntry *kde, *de;
 
 /* Reuse the sds from the main dict in the expire dict */
 kde = dictFind(db->dict,key->ptr);
 redisAssertWithInfo(NULL,key,kde != NULL);
 de = dictReplaceRaw(db->expires,dictGetKey(kde));
 dictSetSignedIntegerVal(de,when);
}
 
/* Return the expire time of the specified key, or -1 if no expire
 * is associated with this key (i.e. the key is non volatile) */
long long getExpire(redisDb *db, robj *key) {
 dictEntry *de;
 
 /* No expire"expired",key,db->id);
 return dbDelete(db,key);
}
 
/*-----------------------------------------------------------------------------
 * Expires Commands
 *----------------------------------------------------------------------------*/
 
/* This is the generic command implementation for EXPIRE, PEXPIRE, EXPIREAT
 * and PEXPIREAT. Because the commad second argument may be relative or absolute
 * the "basetime" argument is used to signal what the base time is (either 0
 * for *AT variants of the command, or the current time for relative expires).
 *
 * unit is either UNIT_SECONDS or UNIT_MILLISECONDS, and is only used for
 * the argv[2] parameter. The basetime is always specified in milliseconds. */
void expireGenericCommand(redisClient *c, long long basetime, int unit) {
 robj *key = c->argv[1], *param = c->argv[2];
 long long when; /* unix time in milliseconds when the key will expire. */
 
 if (getLongLongFromObjectOrReply(c, param, &when, NULL) != REDIS_OK)
 return;
 
 if (unit == UNIT_SECONDS) when *= 1000;
 when += basetime;
 
 /* No key, return zero. */
 if (lookupKeyRead(c->db,key) == NULL) {
 addReply(c,shared.czero);
 return;
 }
 
 /* EXPIRE with negative TTL, or EXPIREAT with a timestamp into the past
 * should never be executed as a DEL when load the AOF or in the context
 * of a slave instance.
 *
 * Instead we take the other branch of the IF statement setting an expire
 * (possibly in the past) and wait for an explicit DEL from the master. */
 if (when <= mstime() && !server.loading && !server.masterhost) { robj *aux; redisAssertWithInfo(c,key,dbDelete(c->db,key));
 server.dirty++;
 
 /* Replicate/AOF this as an explicit DEL. */
 aux = createStringObject("DEL",3);
 rewriteClientCommandVector(c,2,aux,key);
 decrRefCount(aux);
 signalModifiedKey(c->db,key);
 notifyKeyspaceEvent(REDIS_NOTIFY_GENERIC,"del",key,c->db->id);
 addReply(c, shared.cone);
 return;
 } else {
 setExpire(c->db,key,when);
 addReply(c,shared.cone);
 signalModifiedKey(c->db,key);
 notifyKeyspaceEvent(REDIS_NOTIFY_GENERIC,"expire",key,c->db->id);
 server.dirty++;
 return;
 }
}
 
void expireCommand(redisClient *c) {
 expireGenericCommand(c,mstime(),UNIT_SECONDS);
}
 
void expireatCommand(redisClient *c) {
 expireGenericCommand(c,0,UNIT_SECONDS);
}
 
void pexpireCommand(redisClient *c) {
 expireGenericCommand(c,mstime(),UNIT_MILLISECONDS);
}
 
void pexpireatCommand(redisClient *c) {
 expireGenericCommand(c,0,UNIT_MILLISECONDS);
}
 
void ttlGenericCommand(redisClient *c, int output_ms) {
 long long expire, ttl = -1;
 
 /* If the key does not exist at all, return -2 */
 if (lookupKeyRead(c->db,c->argv[1]) == NULL) {
 addReplyLongLong(c,-2);
 return;
 }
 /* The key exists. Return -1 if it has no expire, or the actual
 * TTL value otherwise. */
 expire = getExpire(c->db,c->argv[1]);
 if (expire != -1) {
 ttl = expire-mstime();
 if (ttl < 0) ttl = 0; } if (ttl == -1) { addReplyLongLong(c,-1); } else { addReplyLongLong(c,output_ms "htmlcode">

#define ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC 25 /* CPU max % for keys collection */ 
... 
timelimit = 1000000*ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC/server.hz/100;


hz调大将会提高Redis主动淘汰的频率，如果你的Redis存储中包含很多冷数据占用内存过大的话，可以考虑将这个值调大，但Redis作者建议这个值不要超过100。我们实际线上将这个值调大到100，观察到CPU会增加2%左右，但对冷数据的内存释放速度确实有明显的提高（通过观察keyspace个数和used_memory大小）。
可以看出timelimit和server.hz是一个倒数的关系，也就是说hz配置越大，timelimit就越小。换句话说是每秒钟期望的主动淘汰频率越高，则每次淘汰最长占用时间就越短。这里每秒钟的最长淘汰占用时间是固定的250ms（1000000*ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC/100），而淘汰频率和每次淘汰的最长时间是通过hz参数控制的。
从以上的分析看，当redis中的过期key比率没有超过25%之前，提高hz可以明显提高扫描key的最小个数。假设hz为10，则一秒内最少扫描200个key（一秒调用10次*每次最少随机取出20个key），如果hz改为100，则一秒内最少扫描2000个key；另一方面，如果过期key比率超过25%，则扫描key的个数无上限，但是cpu时间每秒钟最多占用250ms。
当REDIS运行在主从模式时，只有主结点才会执行上述这两种过期删除策略，然后把删除操作”del key”同步到从结点。
maxmemory
当前已用内存超过maxmemory限定时，触发主动清理策略

  
volatile-lru：只对设置了过期时间的key进行LRU（默认值）
  
allkeys-lru ： 删除lru算法的key
  
volatile-random：随机删除即将过期key
  
allkeys-random：随机删除
  
volatile-ttl ： 删除即将过期的
  
noeviction ： 永不过期，返回错误当mem_used内存已经超过maxmemory的设定，对于所有的读写请求，都会触发redis.c/freeMemoryIfNeeded(void)函数以清理超出的内存。注意这个清理过程是阻塞的，直到清理出足够的内存空间。所以如果在达到maxmemory并且调用方还在不断写入的情况下，可能会反复触发主动清理策略，导致请求会有一定的延迟。

当mem_used内存已经超过maxmemory的设定，对于所有的读写请求，都会触发redis.c/freeMemoryIfNeeded(void)函数以清理超出的内存。注意这个清理过程是阻塞的，直到清理出足够的内存空间。所以如果在达到maxmemory并且调用方还在不断写入的情况下，可能会反复触发主动清理策略，导致请求会有一定的延迟。
清理时会根据用户配置的maxmemory-policy来做适当的清理（一般是LRU或TTL），这里的LRU或TTL策略并不是针对redis的所有key，而是以配置文件中的maxmemory-samples个key作为样本池进行抽样清理。
maxmemory-samples在redis-3.0.0中的默认配置为5，如果增加，会提高LRU或TTL的精准度，redis作者测试的结果是当这个配置为10时已经非常接近全量LRU的精准度了，并且增加maxmemory-samples会导致在主动清理时消耗更多的CPU时间，建议：

  
尽量不要触发maxmemory，最好在mem_used内存占用达到maxmemory的一定比例后，需要考虑调大hz以加快淘汰，或者进行集群扩容。
  
如果能够控制住内存，则可以不用修改maxmemory-samples配置；如果Redis本身就作为LRU cache服务（这种服务一般长时间处于maxmemory状态，由Redis自动做LRU淘汰），可以适当调大maxmemory-samples。

  

以下是上文中提到的配置参数的说明


# Redis calls an internal function to perform many background tasks, like 
# closing connections of clients in timeout, purging expired keys that are 
# never requested, and so forth. 
# 
# Not all tasks are performed with the same frequency, but Redis checks for 
# tasks to perform according to the specified "hz" value. 
# 
# By default "hz" is set to 10. Raising the value will use more CPU when 
# Redis is idle, but at the same time will make Redis more responsive when 
# there are many keys expiring at the same time, and timeouts may be 
# handled with more precision. 
# 
# The range is between 1 and 500, however a value over 100 is usually not 
# a good idea. Most users should use the default of 10 and raise this up to 
# 100 only in environments where very low latency is required. 
hz 10 
 
# MAXMEMORY POLICY: how Redis will select what to remove when maxmemory 
# is reached. You can select among five behaviors: 
# 
# volatile-lru -> remove the key with an expire set using an LRU algorithm 
# allkeys-lru -> remove any key according to the LRU algorithm 
# volatile-random -> remove a random key with an expire set 
# allkeys-random -> remove a random key, any key 
# volatile-ttl -> remove the key with the nearest expire time (minor TTL) 
# noeviction -> don't expire at all, just return an error on write operations 
# 
# Note: with any of the above policies, Redis will return an error on write 
# operations, when there are no suitable keys for eviction. 
# 
# At the date of writing these commands are: set setnx setex append 
# incr decr rpush lpush rpushx lpushx linsert lset rpoplpush sadd 
# sinter sinterstore sunion sunionstore sdiff sdiffstore zadd zincrby 
# zunionstore zinterstore hset hsetnx hmset hincrby incrby decrby 
# getset mset msetnx exec sort 
# 
# The default is: 
# 
maxmemory-policy noeviction 
 
# LRU and minimal TTL algorithms are not precise algorithms but approximated 
# algorithms (in order to save memory), so you can tune it for speed or 
# accuracy. For default Redis will check five keys and pick the one that was 
# used less recently, you can change the sample size using the following 
# configuration directive. 
# 
# The default of 5 produces good enough results. 10 Approximates very closely 
# true LRU but costs a bit more CPU. 3 is very fast but not very accurate. 
# 
maxmemory-samples 5


Replication link和AOF文件中的过期处理
为了获得正确的行为而不至于导致一致性问题，当一个key过期时DEL操作将被记录在AOF文件并传递到所有相关的slave。也即过期删除操作统一在master实例中进行并向下传递，而不是各salve各自掌控。这样一来便不会出现数据不一致的情形。当slave连接到master后并不能立即清理已过期的key（需要等待由master传递过来的DEL操作），slave仍需对数据集中的过期状态进行管理维护以便于在slave被提升为master会能像master一样独立的进行过期处理。
总结
以上就是这篇文章的全部内容了，希望本文的内容对大家的学习或者工作能带来一定的帮助，如果有疑问大家可以留言交流。