Redis5.0源码阅读-数据库实现
涉及源代码文件
server.hserver.cdb.cexpire.cnotify.c
疑问点
- 过期的机制是怎么实现，如何保证精确呢
- 其实不必精确，只需要在涉及到键的操作时，检验一下是否过期了就可以了
数据库结构
文件：server.h第942行
源码：定义了redisServer 的数据结构，redisServer有很多的字段，
struct redisServer {
redisDb *db; 定义了数据库的数据库数组对象
int dbnum; 定义了配置的数据库的总数量
list *clients; /* List of active clients */
client *current_client; /* Current client executing the command. */
......
......
};
文件: server.h 第725行
源码：定义了单独一个client数据结构
typedef struct client {
redisDb *db; 定义了当前的指向的db
......
......
} client
切换数据库的时候 指针指向就变换到相应的数据库
文件：server.h, 第646行起
源码：定义了单个redisDb的数据结构
/* Redis database representation. There are multiple databases identified
* by integers from 0 (the default database) up to the max configured
* database. The database number is the 'id' field in the structure. */
typedef struct redisDb {
dict *dict; /* The keyspace for this DB */
dict *expires; /* Timeout of keys with a timeout set */
dict *blocking_keys; /* Keys with clients waiting for data (BLPOP)*/
dict *ready_keys; /* Blocked keys that received a PUSH */
dict *watched_keys; /* WATCHED keys for MULTI/EXEC CAS */
int id; /* Database ID */
long long avg_ttl; /* Average TTL, just for stats */
list *defrag_later; /* List of key names to attempt to defrag one by one, gradually. */
} redisDb;
其中expries 就存储了在该数据库中被设置了过期时间的键
Redis过期键删除策略
redis 使用以下两种策略 删除过期键
定期删除
服务器每隔一段时间执行删除过期键的逻辑
文件：expire.c, 第75行起
源码(复制过来的，还带有英文注释)：
/* Try to expire a few timed out keys. The algorithm used is adaptive and
* will use few CPU cycles if there are few expiring keys, otherwise
* it will get more aggressive to avoid that too much memory is used by
* keys that can be removed from the keyspace.
*
* No more than CRON_DBS_PER_CALL databases are tested at every
* iteration.
*
* This kind of call is used when Redis detects that timelimit_exit is
* true, so there is more work to do, and we do it more incrementally from
* the beforeSleep() function of the event loop.
*
* Expire cycle type:
*
* If type is ACTIVE_EXPIRE_CYCLE_FAST the function will try to run a
* "fast" expire cycle that takes no longer than EXPIRE_FAST_CYCLE_DURATION
* microseconds, and is not repeated again before the same amount of time.
*
* If type is ACTIVE_EXPIRE_CYCLE_SLOW, that normal expire cycle is
* executed, where the time limit is a percentage of the REDIS_HZ period
* as specified by the ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC define. */
void activeExpireCycle(int type) {
/* This function has some global state in order to continue the work
* incrementally across calls. */
// 标记了当前的检查进度，注意这里是static变量
static unsigned int current_db = 0; /* Last DB tested. */
// 标记了上次的检查是否正常结束
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;
// 检验此次循环的模式，从函数注释可以看出有Fast，slow 两种模式。redis 不允许在前一个fast模式运行未退出的状态下，再次运行一个fast模式的循环
if (type == ACTIVE_EXPIRE_CYCLE_FAST) {
/* Don't start a fast cycle if the previous cycle did not exit
* for time limit. Also don't repeat a fast cycle for the same period
* as the fast cycle total duration itself. */
if (!timelimit_exit) return;
if (start < last_fast_cycle + ACTIVE_EXPIRE_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)
// 以redis 实际数据库数量为准
dbs_per_call = server.dbnum;
/* We can use at max ACTIVE_EXPIRE_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 = 1000000*ACTIVE_EXPIRE_CYCLE_SLOW_TIME_PERC/server.hz/100;
timelimit_exit = 0;
if (timelimit <= 0) timelimit = 1;
if (type == ACTIVE_EXPIRE_CYCLE_FAST)
timelimit = ACTIVE_EXPIRE_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++) {
int expired;
// 获取需要检验的数据库
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. */
// 进度增加
current_db++;
/* Continue to expire if at the end of the cycle more than 25%
* of the keys were expired. */
do {
unsigned long num, slots;
long long now, ttl_sum;
int ttl_samples;
iteration++;
/* If there is nothing to expire try next DB ASAP. */
// 判断过期表是否为空，计算了表内已使用的数量
if ((num = dictSize(db->expires)) == 0) {
db->avg_ttl = 0;
break;
}
//计算了过期表的总容量，包括ht[0],ht[1]
slots = dictSlots(db->expires);
now = mstime();
/* When there are less than 1% filled slots getting random
* keys 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;
ttl_sum = 0;
ttl_samples = 0;
if (num > ACTIVE_EXPIRE_CYCLE_LOOKUPS_PER_LOOP)
num = ACTIVE_EXPIRE_CYCLE_LOOKUPS_PER_LOOP;
while (num--) {
dictEntry *de;
long long ttl;
if ((de = dictGetRandomKey(db->expires)) == NULL) break;
ttl = dictGetSignedIntegerVal(de)-now;
// 在此函数中，做了删除过期键的操作，并做删除之后的后续操作，如通知等
if (activeExpireCycleTryExpire(db,de,now)) expired++;
if (ttl > 0) {
/* We want the average TTL of keys yet not expired. */
ttl_sum += ttl;
ttl_samples++;
}
total_sampled++;
}
total_expired += expired;
/* 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 if there are less than 25% of keys
* found expired in the current DB. */
} while (expired > ACTIVE_EXPIRE_CYCLE_LOOKUPS_PER_LOOP/4);
}
elapsed = ustime()-start;
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);
}
惰性删除
惰性删除存在于用户对redis进行命令操作时，每次用户使用命令操作时，redis都会检查该key是否过期，
文件: db.c 第79行开始
/* Lookup a key for read operations, or return NULL if the key is not found
* in the specified DB.
*
* As a side effect of calling this function:
* 1. A key gets expired if it reached it's TTL.
* 2. The key last access time is updated.
* 3. The global keys hits/misses stats are updated (reported in INFO).
*
* This API should not be used when we write to the key after obtaining
* the object linked to the key, but only for read only operations.
*
* Flags change the behavior of this command:
*
* LOOKUP_NONE (or zero): no special flags are passed.
* LOOKUP_NOTOUCH: don't alter the last access time of the key.
*
* Note: this function also returns NULL if the key is logically expired
* but still existing, in case this is a slave, since this API is called only
* for read operations. Even if the key expiry is master-driven, we can
* correctly report a key is expired on slaves even if the master is lagging
* expiring our key via DELs in the replication link. */
robj *lookupKeyReadWithFlags(redisDb *db, robj *key, int flags) {
robj *val;
if (expireIfNeeded(db,key) == 1) {
/* Key expired. If we are in the context of a master, expireIfNeeded()
* returns 0 only when the key does not exist at all, so it's safe
* to return NULL ASAP. */
if (server.masterhost == NULL) {
server.stat_keyspace_misses++;
return NULL;
}
/* However if we are in the context of a slave, expireIfNeeded() will
* not really try to expire the key, it only returns information
* about the "logical" status of the key: key expiring is up to the
* master in order to have a consistent view of master's data set.
*
* However, if the command caller is not the master, and as additional
* safety measure, the command invoked is a read-only command, we can
* safely return NULL here, and provide a more consistent behavior
* to clients accessign expired values in a read-only fashion, that
* will say the key as non existing.
*
* Notably this covers GETs when slaves are used to scale reads. */
if (server.current_client &&
server.current_client != server.master &&
server.current_client->cmd &&
server.current_client->cmd->flags & CMD_READONLY)
{
server.stat_keyspace_misses++;
return NULL;
}
}
val = lookupKey(db,key,flags);
if (val == NULL)
server.stat_keyspace_misses++;
else
server.stat_keyspace_hits++;
return val;
}
如这个函数，在查找key时，会判断该key是否是过期的。
这里面也有一个需要注意的点，如果当前这个主机不是master，那么这个过期操作，不会删除任何过期的key， 只会返回这个key逻辑上是否被删除的结果，真正被删除是主从同步的时候删除的
文件: db.c 第1186行
/* This function is called when we are going to perform some operation
* in a given key, but such key may be already logically expired even if
* it still exists in the database. The main way this function is called
* is via lookupKey*() family of functions.
*
* The behavior of the function depends on the replication role of the
* instance, because slave instances do not expire keys, they wait
* for DELs from the master for consistency matters. However even
* slaves will try to have a coherent return value for the function,
* so that read commands executed in the slave side will be able to
* behave like if the key is expired even if still present (because the
* master has yet to propagate the DEL).
*
* In masters as a side effect of finding a key which is expired, such
* key will be evicted from the database. Also this may trigger the
* propagation of a DEL/UNLINK command in AOF / replication stream.
*
* The return value of the function is 0 if the key is still valid,
* otherwise the function returns 1 if the key is expired. */
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. */
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);
return server.lazyfree_lazy_expire ? dbAsyncDelete(db,key) :
dbSyncDelete(db,key);
}
这个函数中判断了 该主机是否为master，当不为master时，只返回了是否过期的结果，并没有真正做删除过期键的操作
数据通知
- 键空间通知：关注”某个键执行了什么命令“
- 键事件通知：关注“某个命令被什么键执行了”
文件：notify.c 第90行
/* The API provided to the rest of the Redis core is a simple function:
*
* notifyKeyspaceEvent(char *event, robj *key, int dbid);
*
* 'event' is a C string representing the event name.
* 'key' is a Redis object representing the key name.
* 'dbid' is the database ID where the key lives. */
void notifyKeyspaceEvent(int type, char *event, robj *key, int dbid) {
sds chan;
robj *chanobj, *eventobj;
int len = -1;
char buf[24];
/* If any modules are interested in events, notify the module system now.
* This bypasses the notifications configuration, but the module engine
* will only call event subscribers if the event type matches the types
* they are interested in. */
// 用户通知Module RedisModule是redis4.0的新特性
moduleNotifyKeyspaceEvent(type, event, key, dbid);
/* If notifications for this class of events are off, return ASAP. */
// 判断server 的配置中 是否有和这个一样的type，如果有就处理
if (!(server.notify_keyspace_events & type)) return;
eventobj = createStringObject(event,strlen(event));
/* __keyspace@<db>__:<key> <event> notifications. */
// 判断是否为键空间通知
if (server.notify_keyspace_events & NOTIFY_KEYSPACE) {
// 拼接channel信息
chan = sdsnewlen("__keyspace@",11);
len = ll2string(buf,sizeof(buf),dbid);
chan = sdscatlen(chan, buf, len);
chan = sdscatlen(chan, "__:", 3);
chan = sdscatsds(chan, key->ptr);
chanobj = createObject(OBJ_STRING, chan);
//向channel 发送 事件信息
pubsubPublishMessage(chanobj, eventobj);
//释放空间
decrRefCount(chanobj);
}
/* __keyevent@<db>__:<event> <key> notifications. */
// 判断是否为键事件通知
if (server.notify_keyspace_events & NOTIFY_KEYEVENT) {
//拼接channel信息
chan = sdsnewlen("__keyevent@",11);
if (len == -1) len = ll2string(buf,sizeof(buf),dbid);
chan = sdscatlen(chan, buf, len);
chan = sdscatlen(chan, "__:", 3);
chan = sdscatsds(chan, eventobj->ptr);
chanobj = createObject(OBJ_STRING, chan);
//向channel 发送 事件信息
pubsubPublishMessage(chanobj, key);
decrRefCount(chanobj);
}
decrRefCount(eventobj);
}
参考
《redis设计与实现》
