Redis底层数据结构详解

/* 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;                 /* 存储数据库所有的key-value */
    dict *expires;              /* 存储key的过期时间 */
    dict *blocking_keys;        /* blpop 存储阻塞key和客户端对象*/
    dict *ready_keys;           /* 阻塞后push 响应阻塞客户端 存储阻塞后push的key和客户端对象 */
    dict *watched_keys;         /* 存储watch监控的的key和客户端对象 */
    int id;                     /* Database ID */
    long long avg_ttl;          /* 存储的数据库对象的平均ttl（time to live），用于统计 */
    unsigned long expires_cursor; /* 循环过期检查的光标. */
    list *defrag_later;         /* 需要尝试去清理磁盘碎片的链表，会慢慢的清理 */
} redisDb;

typedef struct redisObject {
    unsigned type:4; //类型 对象类型
    unsigned encoding:4;//编码
	// LRU_BITS为24bit 记录最后一次被命令程序访问的时间
    unsigned lru:LRU_BITS; /* LRU time (relative to global lru_clock) or
                            * LFU data (least significant 8 bits frequency
                            * and most significant 16 bits access time). */
    int refcount; //引用计数
    void *ptr;//指向底层实现数据结构的指针
} robj;

127.0.0.1:6379> set a1 111
OK
127.0.0.1:6379> type a1
string

127.0.0.1:6379> OBJECT encoding a1
"int"

/* Note: sdshdr5 is never used, we just access the flags byte directly.
 * However is here to document the layout of type 5 SDS strings. */
struct __attribute__ ((__packed__)) sdshdr5 {
    unsigned char flags; /* 3 lsb of type, and 5 msb of string length */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr8 {
    uint8_t len; /* used */
    uint8_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr16 {
    uint16_t len; /* used */
    uint16_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr32 {
    uint32_t len; /* used */
    uint32_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};
struct __attribute__ ((__packed__)) sdshdr64 {
    uint64_t len; /* used */
    uint64_t alloc; /* excluding the header and null terminator */
    unsigned char flags; /* 3 lsb of type, 5 unused bits */
    char buf[];
};

/* ZSETs use a specialized version of Skiplists */
typedef struct zskiplistNode {
    /* 存储字符串类型数据 redis3.0版本中使用robj类型表示，但是在redis4.0.1中直接使用sds类型表示 */
    sds ele;
    /*存储排序的分值*/
    double score;
    /*后退指针，指向当前节点最底层的前一个节点*/
    struct zskiplistNode *backward;
    /*层，柔性数组，随机生成1-64的值*/
    struct zskidictEntryplistLevel {
        struct zskiplistNode *forward; //指向本层下一个节点
        unsigned long span; //本层下个节点到本节点的元素个数
    } level[];
} zskiplistNode;

typedef struct zskiplist {
    //表头节点和表尾节点
    struct zskiplistNode *header, *tail;
    //表中节点的数量
    unsigned long length;
    //表中层数最大的节点的层数
    int level;
} zskiplist;

typedef struct dictht {
    dictEntry **table; // 哈希表数组
    unsigned long size; // 哈希表数组的大小
    unsigned long sizemask; // 用于映射位置的掩码，值永远等于(size-1)
    unsigned long used; // 哈希表已有节点的数量,包含next单链表数据
} dictht;

typedef struct dictEntry {
    void *key; // 键
    union { // 值v的类型可以是以下4种类型
        void *val;
        uint64_t u64;
        int64_t s64;
        double d;
    } v;
    struct dictEntry *next; // 指向下一个哈希表节点，形成单向链表 解决hash冲突, 单链表中会存储key和value
} dictEntry;

typedef struct dict {
    dictType *type; //该字典对应的特定操作函数
    void *privdata; //上述类型函数对应的可选参数
    dictht ht[2];/* 两张哈希表，存储键值对数据，ht[0]为原生哈希表，ht[1]为 rehash 哈希表 */
    long rehashidx; /* rehash标识 当等于-1时表示没有在rehash，否则表示正在进行rehash操作，
    				存储的值表示hash表 ht[0]的rehash进行到哪个索引值(数组下标)*/
    unsigned long iterators; /* 当前运行的迭代器数量 */
} dict;

typedef struct dictType {
    // 计算哈希值的函数
    uint64_t (*hashFunction)(const void *key);

    // 复制键的函数
    void *(*keyDup)(void *privdata, const void *key);

    // 比较键的函数
    void *(*valDup)(void *privdata, const void *obj);

    // 比较键的函数
    int (*keyCompare)(void *privdata, const void *key1, const void *key2);

    // 销毁键的函数
    void (*keyDestructor)(void *privdata, void *key);

    // 销毁值的函数
    void (*valDestructor)(void *privdata, void *obj);
} dictType;

struct ziplist<T>{
    unsigned int zlbytes; // ziplist的长度字节数，包含头部、所有entry和zipend。
    unsigned int zloffset; // 从ziplist的头指针到指向最后一个entry的偏移量，用于快速反向查询
    unsigned short int zllength; // entry元素个数T[] entry; // 元素值
    unsigned char zlend; // ziplist结束符，值固定为0xFF
}
typedef struct zlentry {
    unsigned int prevrawlensize; //previous_entry_length字段的长度
    unsigned int prevrawlen; //previous_entry_length字段存储的内容
    unsigned int lensize; //encoding字段的长度
    unsigned int len; //数据内容长度
    unsigned int headersize; //当前元素的首部长度，即previous_entry_length字段长度与 encoding字段长度之和。
    unsigned char encoding; //数据类型
    unsigned char *p; //当前元素首地址
} zlentry;

127.0.0.1:6379> SADD set:1 12  6  8
(integer) 3
127.0.0.1:6379> OBJECT encoding set:1
"intset"
127.0.0.1:6379> SADD set:2 1 1000000000000000000000000000000000000000000000000000000 99999999999999999999999999999
(integer) 3
127.0.0.1:6379> OBJECT encoding set:2
"hashtable"

typedef struct intset{
    //编码方式
    uint32_t encoding;
    //集合包含的元素数量
    uint32_t length;
    //保存元素的数组
    int8_t contents[];
}intset;

127.0.0.1:6379> LPUSH list:001  2 3 5 6 7
(integer) 5
127.0.0.1:6379> OBJECT encoding list:001
"quicklist"

#if UINTPTR_MAX == 0xffffffff
/* 32-bit */
#   define QL_FILL_BITS 14
#   define QL_COMP_BITS 14
#   define QL_BM_BITS 4
#elif UINTPTR_MAX == 0xffffffffffffffff
/* 64-bit */
#   define QL_FILL_BITS 16
#   define QL_COMP_BITS 16
#   define QL_BM_BITS 4 /* we can encode more, but we rather limit the user
                           since they cause performance degradation. */
#else
#   error unknown arch bits count
#endif

/* quicklist is a 40 byte struct (on 64-bit systems) describing a quicklist.
 * 'count' is the number of total entries.
 * 'len' is the number of quicklist nodes.
 * 'compress' is: 0 if compression disabled, otherwise it's the number
 *                of quicklistNodes to leave uncompressed at ends of quicklist.
 * 'fill' is the user-requested (or default) fill factor.
 * 'bookmakrs are an optional feature that is used by realloc this struct,
 *      so that they don't consume memory when not used. */
typedef struct quicklist {
    quicklistNode *head; // 指向quicklist的头部
    quicklistNode *tail; // 指向quicklist的尾部
    unsigned long count;        /* 列表中所有数据项的个数总和 */
    unsigned long len;          /* quicklist节点的个数，即ziplist的个数 */
    int fill : QL_FILL_BITS;              /* ziplist大小限定，由list-max-ziplist-size给定  (Redis设定)*/
    unsigned int compress : QL_COMP_BITS; /* depth of end nodes not to compress;0=off */
    unsigned int bookmark_count: QL_BM_BITS; /*节点压缩深度设置，由list-compress-depth给定*/
    quicklistBookmark bookmarks[]; /*可选新特性 使用realloc重新分配空间的时候会用到*/
} quicklist;

/* quicklistNode is a 32 byte struct describing a ziplist for a quicklist.
 * We use bit fields keep the quicklistNode at 32 bytes.
 * count: 16 bits, max 65536 (max zl bytes is 65k, so max count actually < 32k).
 * encoding: 2 bits, RAW=1, LZF=2.
 * container: 2 bits, NONE=1, ZIPLIST=2.
 * recompress: 1 bit, bool, true if node is temporary decompressed for usage.
 * attempted_compress: 1 bit, boolean, used for verifying during testing.
 * extra: 10 bits, free for future use; pads out the remainder of 32 bits */
typedef struct quicklistNode {
    struct quicklistNode *prev; // 指向上一个ziplist节点
    struct quicklistNode *next; // 指向下一个ziplist节点
    unsigned char *zl; // 数据指针，如果没有被压缩，就指向ziplist结构，反之指向 quicklistLZF结构
    unsigned int sz; // 表示指向ziplist结构的总长度(内存占用长度)
    unsigned int count : 16; // 表示ziplist中的数据项个数
    unsigned int encoding : 2; // 编码方式，1--ziplist，2--quicklistLZF
    unsigned int container : 2; // 预留字段，存放数据的方式，1--NONE，2--ziplist
    unsigned int recompress : 1; // 解压标记，当查看一个被压缩的数据时，需要暂时解压，标记此参数为 1，之后再重新进行压缩
    unsigned int attempted_compress : 1; // 测试相关
    unsigned int extra : 10; // 扩展字段，暂时没用
} quicklistNode;

/* quicklistLZF is a 4+N byte struct holding 'sz' followed by 'compressed'.
 * 'sz' is byte length of 'compressed' field.
 * 'compressed' is LZF data with total (compressed) length 'sz'
 * NOTE: uncompressed length is stored in quicklistNode->sz.
 * When quicklistNode->zl is compressed, node->zl points to a quicklistLZF */
typedef struct quicklistLZF {
    unsigned int sz; /* LZF压缩后占用的字节数*/
    char compressed[]; //柔性数组，指向数据部分
} quicklistLZF;

/* Objects encoding. Some kind of objects like Strings and Hashes can be
 * internally represented in multiple ways. The 'encoding' field of the object
 * is set to one of this fields for this object. */
#define OBJ_ENCODING_RAW 0     /* Raw representation */
#define OBJ_ENCODING_INT 1     /* Encoded as integer */
#define OBJ_ENCODING_HT 2      /* Encoded as hash table */
#define OBJ_ENCODING_ZIPMAP 3  /* Encoded as zipmap */
#define OBJ_ENCODING_LINKEDLIST 4 /* No longer used: old list encoding. */
#define OBJ_ENCODING_ZIPLIST 5 /* Encoded as ziplist */
#define OBJ_ENCODING_INTSET 6  /* Encoded as intset */
#define OBJ_ENCODING_SKIPLIST 7  /* Encoded as skiplist */
#define OBJ_ENCODING_EMBSTR 8  /* Embedded sds string encoding */
#define OBJ_ENCODING_QUICKLIST 9 /* Encoded as linked list of ziplists */
#define OBJ_ENCODING_STREAM 10 /* Encoded as a radix tree of listpacks */

127.0.0.1:6379> sadd set:001 1 3 5 6 2
(integer) 5
127.0.0.1:6379> object encoding set:001
"intset"
127.0.0.1:6379> sadd set:004 1 100000000000000000000000000 9999999999
(integer) 3
127.0.0.1:6379> object encoding set:004
"hashtable"

127.0.0.1:6379> set n1 123
OK
127.0.0.1:6379> object encoding n1
"int"

127.0.0.1:6379> set name:001 zhangfei
OK
127.0.0.1:6379> object encoding name:001
"embstr"

127.0.0.1:6379> set address:001 asdasdasdasdasdasdsadasdasdasdasdasdasdasdasdasdasdasdasdasdasdasdasdasdasdasdasdasdasdas
OK
127.0.0.1:6379> object encoding address:001
"raw"

127.0.0.1:6379> lpush list:001 1 2 5 4 3
(integer) 5
127.0.0.1:6379> object encoding list:001
"quicklist"

127.0.0.1:6379> hmset user:003 username111111111111111111111111111111111111111111111111111111111111111111111111 11111111111111111111111111111111 zhangfei password 111 num 2300000000000000000000000000000000000000000000000000
OK
127.0.0.1:6379> object encoding user:003
"hashtable"

127.0.0.1:6379> HSET user:001 username zhanyun password 123456
(integer) 2
127.0.0.1:6379> OBJECT encoding user:001
"ziplist"

127.0.0.1:6379> sadd set:001 1 3 5 6 2
(integer) 5
127.0.0.1:6379> object encoding set:001
"intset"

127.0.0.1:6379> sadd set:004 1 100000000000000000000000000 9999999999
(integer) 3
127.0.0.1:6379> object encoding set:004
"hashtable"

127.0.0.1:6379> zadd hit:1 100 item1 20 item2 45 item3
(integer) 3
127.0.0.1:6379> object encoding hit:1
"ziplist"

127.0.0.1:6379> zadd hit:2 100 item1111111111111111111111111111111111111111111111111111111111111111111111111111 1111111111111111111111111111111111 20 item2 45 item3
(integer) 3
127.0.0.1:6379> object encoding hit:2
"skiplist"