目录
volatile-lru and allkeys-lru 策略
Redis占用的内存会被限定在一个固定大小。在32bit系统中,redis占用的memory不超过32GB。因此需要内存管理,将长时间未用的键值对删除(即volatile-lru and allkeys-lru策略(近似lru));将临近过期的键值对删除(即volatile-ttl策略)。
下面以内存管理函数freeMemoryIfNeeded(void)为例进行学习。在学习该函数中,将碰到的问题记录如下:
redis对象类型
【Redis实现中用到一个基础数据结构:robj。那到底什么是robj呢?它有什么用呢?
从Redis的使用者的角度来看,一个Redis节点包含多个database(非cluster模式下默认是16个,cluster模式下只能是1个),而一个database维护了从key space到object space的映射关系。这个映射关系的key是string类型,而value可以是多种数据类型,比如:string, list, hash等。我们可以看到,key的类型固定是string,而value可能的类型是多个。】【引自http://zhangtielei.com/posts/blog-redis-robj.html 该文章对robj结构介绍的非常清楚 。】
robj结构如下:
typedef struct redisObject {
unsigned type:4;
unsigned encoding:4;
unsigned lru:LRU_BITS; /* lru time (relative to server.lruclock) */
int refcount;
void *ptr;
} robj;
键的类型只有string类型,下面就是将一个string类型的thiskey创建为一个keyobj对象。
typedef char *sds;
sds thiskey;
robj *keyobj = createStringObject(bestkey,sdslen(bestkey));
robj *createStringObject(char *ptr, size_t len) {
return createObject(REDIS_STRING,sdsnewlen(ptr,len));
}
robj *createObject(int type, void *ptr) {
robj *o = zmalloc(sizeof(*o));
o->type = type;
o->encoding = REDIS_ENCODING_RAW;
o->ptr = ptr;
o->refcount = 1;
/* Set the LRU to the current lruclock (minutes resolution). */
o->lru = server.lruclock;
return o;
空转时间计算
关于robj结构中lru属性,以及server.lruclock。
lru属性计录了robj最后一次被命令访问的时间。robj被访问时,会进行赋值o.lru = server.lruclock。
lruclock属性保存了服务器的lru时钟,每10秒计算一次。REDIS_LRU_CLOCK_RESOLUTION =10,server.unixtime/REDIS_LRU_CLOCK_RESOLUTION。
estimateObjectIdleTime(robj *o)函数计算robj *o的空转时间,空转时间就是server.lruclock - o.lru,在之后计算空转时间时,还需 * REDIS_LRU_CLOCK_RESOLUTION,即 return (server.lruclock - o->lru) * REDIS_LRU_CLOCK_RESOLUTION;
#define REDIS_LRU_CLOCK_RESOLUTION 10 /* LRU clock resolution in seconds */
void updateLRUClock(void) { 更新服务器LRU时间
server.lruclock = (server.unixtime/REDIS_LRU_CLOCK_RESOLUTION) &
REDIS_LRU_CLOCK_MAX;
}
server.unixtime = time(NULL);
// time_t time(time_t *timer) timer=NULL时,得到机器日历时间, =时间数值时 用于设置日历时间;
unsigned long estimateObjectIdleTime(robj *o) {
if (server.lruclock >= o->lru) {
return (server.lruclock - o->lru) * REDIS_LRU_CLOCK_RESOLUTION;
} else {
return ((REDIS_LRU_CLOCK_MAX - o->lru) + server.lruclock) *
REDIS_LRU_CLOCK_RESOLUTION;
}
}
volatile-ttl策略
redisDb结构的expire字典数据库中所有建的过期时间。
expire的键是一个指针,指向键空间中某个键对象。
expire的值是一个long long整数,保存了键所指向的数据库键的过期时间,是一个毫秒精度的UNIX时间戳。(因此在涉及的计算中,可能会*1000,或者除1000);expire数据库的值越小,意味着expire的键越临近过期。
volatile-ttl策略下,即server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_TTL时,用的就是通过expire的值大小,来计算是否过期删除。
server.maxmemory_samples是一个整数,可以是3或者5等。server.maxmemory_samples代表了一次取多少个样本来进行判断。
if (bestkey == NULL || thisval < bestval) {
//thisval就是expire数据库的值,值最小的就是最临近过期。
bestkey = thiskey;
bestval = thisval;
/* volatile-ttl */
else if (server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_TTL) {
for (k = 0; k < server.maxmemory_samples; k++) {
sds thiskey;
long thisval;
de = dictGetRandomKey(dict);//随机化返回一个entry
thiskey = dictGetKey(de);
thisval = (long) dictGetVal(de);
/* Expire sooner (minor expire unix timestamp) is better
* candidate for deletion */
if (bestkey == NULL || thisval < bestval) {
bestkey = thiskey;
bestval = thisval;
}
}
}
volatile-lru and allkeys-lru 策略
else if (server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_LRU ||
server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_LRU)
与上面不同的是,选出的对象需计算空转时间,thisval = estimateObjectIdleTime(o); thisval越大,说明这个对象越久没有被访问到,越应该被删除,保存为bestval,同时记录bestkey,方便之后查找键。(这里涉及到redis数据库的设计,值和键都是以对象的形式实现。o = dictGetVal(de);取值是一个对象类型。而expire比较特殊,取值是long型 thisval = (long) dictGetVal(de); 值和键实现的数据库比较灵活,贯穿于redis的实现中)。
else if (server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_LRU ||
server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_LRU)
{
for (k = 0; k < server.maxmemory_samples; k++) {
sds thiskey;
long thisval;
robj *o;
de = dictGetRandomKey(dict);
thiskey = dictGetKey(de);
/* When policy is volatile-lru we need an additional lookup
* to locate the real key, as dict is set to db->expires. */
if (server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_LRU)
de = dictFind(db->dict, thiskey);
o = dictGetVal(de);
thisval = estimateObjectIdleTime(o);
/* Higher idle time is better candidate for deletion */
if (bestkey == NULL || thisval > bestval) {
bestkey = thiskey;
bestval = thisval;
}
}
}
int freeMemoryIfNeeded(void) {
size_t mem_used, mem_tofree, mem_freed;
int slaves = listLength(server.slaves);
/* Remove the size of slaves output buffers and AOF buffer from the
* count of used memory. */
mem_used = zmalloc_used_memory();
if (slaves) {
listIter li;
listNode *ln;
listRewind(server.slaves,&li);
while((ln = listNext(&li))) {
redisClient *slave = listNodeValue(ln);
unsigned long obuf_bytes = getClientOutputBufferMemoryUsage(slave);
if (obuf_bytes > mem_used)
mem_used = 0;
else
mem_used -= obuf_bytes;
}
}
if (server.aof_state != REDIS_AOF_OFF) {
mem_used -= sdslen(server.aof_buf);
mem_used -= aofRewriteBufferSize();
}
/* Check if we are over the memory limit. */
if (mem_used <= server.maxmemory) return REDIS_OK;
if (server.maxmemory_policy == REDIS_MAXMEMORY_NO_EVICTION)
return REDIS_ERR; /* We need to free memory, but policy forbids. */
/* Compute how much memory we need to free. */
mem_tofree = mem_used - server.maxmemory;
mem_freed = 0;
while (mem_freed < mem_tofree) {
int j, k, keys_freed = 0;
for (j = 0; j < server.dbnum; j++) {
long bestval = 0; /* just to prevent warning */
sds bestkey = NULL;
struct dictEntry *de;
redisDb *db = server.db+j;
dict *dict;
if (server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_LRU ||
server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_RANDOM)
{
dict = server.db[j].dict;
} else {
dict = server.db[j].expires;
}
if (dictSize(dict) == 0) continue;
/* volatile-random and allkeys-random policy */
if (server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_RANDOM ||
server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_RANDOM)
{
de = dictGetRandomKey(dict);
bestkey = dictGetKey(de);
}
/* volatile-lru and allkeys-lru policy */
else if (server.maxmemory_policy == REDIS_MAXMEMORY_ALLKEYS_LRU ||
server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_LRU)
{
for (k = 0; k < server.maxmemory_samples; k++) {
sds thiskey;
long thisval;
robj *o;
de = dictGetRandomKey(dict);
thiskey = dictGetKey(de);
/* When policy is volatile-lru we need an additional lookup
* to locate the real key, as dict is set to db->expires. */
if (server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_LRU)
de = dictFind(db->dict, thiskey);
o = dictGetVal(de);
thisval = estimateObjectIdleTime(o);
/* Higher idle time is better candidate for deletion */
if (bestkey == NULL || thisval > bestval) {
bestkey = thiskey;
bestval = thisval;
}
}
}
/* volatile-ttl */
else if (server.maxmemory_policy == REDIS_MAXMEMORY_VOLATILE_TTL) {
for (k = 0; k < server.maxmemory_samples; k++) {
sds thiskey;
long thisval;
de = dictGetRandomKey(dict);
thiskey = dictGetKey(de);
thisval = (long) dictGetVal(de);
/* Expire sooner (minor expire unix timestamp) is better
* candidate for deletion */
if (bestkey == NULL || thisval < bestval) {
bestkey = thiskey;
bestval = thisval;
}
}
}
/* Finally remove the selected key. */
if (bestkey) {
long long delta;
robj *keyobj = createStringObject(bestkey,sdslen(bestkey));
propagateExpire(db,keyobj);
/* We compute the amount of memory freed by dbDelete() alone.
* It is possible that actually the memory needed to propagate
* the DEL in AOF and replication link is greater than the one
* we are freeing removing the key, but we can't account for
* that otherwise we would never exit the loop.
*
* AOF and Output buffer memory will be freed eventually so
* we only care about memory used by the key space. */
delta = (long long) zmalloc_used_memory();
dbDelete(db,keyobj);
delta -= (long long) zmalloc_used_memory();
mem_freed += delta;
server.stat_evictedkeys++;
notifyKeyspaceEvent(REDIS_NOTIFY_EVICTED, "evicted",
keyobj, db->id);
decrRefCount(keyobj);
keys_freed++;
/* When the memory to free starts to be big enough, we may
* start spending so much time here that is impossible to
* deliver data to the slaves fast enough, so we force the
* transmission here inside the loop. */
if (slaves) flushSlavesOutputBuffers();
}
}
if (!keys_freed) return REDIS_ERR; /* nothing to free... */
}
return REDIS_OK;
}
本文代码均来自redis2.8.2。