Redis底層數據結構詳解

/* 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;                 /* 存儲數據庫所有的key-value */
    dict *expires;              /* 存儲key的過期時間 */
    dict *blocking_keys;        /* blpop 存儲阻塞key和客戶端對象*/
    dict *ready_keys;           /* 阻塞後push 響應阻塞客戶端 存儲阻塞後push的key和客戶端對象 */
    dict *watched_keys;         /* 存儲watch監控的的key和客戶端對象 */
    int id;                     /* Database ID */
    long long avg_ttl;          /* 存儲的數據庫對象的平均ttl（time to live），用於統計 */
    unsigned long expires_cursor; /* 循環過期檢查的光標. */
    list *defrag_later;         /* 需要嘗試去清理磁盤碎片的鏈表，會慢慢的清理 */
} redisDb;

typedef struct redisObject {
    unsigned type:4; //類型 對象類型
    unsigned encoding:4;//編碼
	// LRU_BITS為24bit 記錄最後一次被命令程序訪問的時間
    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; //引用計數
    void *ptr;//指向底層實現數據結構的指針
} 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 {
    /* 存儲字符串類型數據 redis3.0版本中使用robj類型表示，但是在redis4.0.1中直接使用sds類型表示 */
    sds ele;
    /*存儲排序的分值*/
    double score;
    /*後退指針，指向當前節點最底層的前一個節點*/
    struct zskiplistNode *backward;
    /*層，柔性數組，隨機生成1-64的值*/
    struct zskidictEntryplistLevel {
        struct zskiplistNode *forward; //指向本層下一個節點
        unsigned long span; //本層下個節點到本節點的元素個數
    } level[];
} zskiplistNode;

typedef struct zskiplist {
    //表頭節點和表尾節點
    struct zskiplistNode *header, *tail;
    //表中節點的數量
    unsigned long length;
    //表中層數最大的節點的層數
    int level;
} zskiplist;

typedef struct dictht {
    dictEntry **table; // 哈希表數組
    unsigned long size; // 哈希表數組的大小
    unsigned long sizemask; // 用於映射位置的掩碼，值永遠等於(size-1)
    unsigned long used; // 哈希表已有節點的數量,包含next單鏈表數據
} dictht;

typedef struct dictEntry {
    void *key; // 鍵
    union { // 值v的類型可以是以下4種類型
        void *val;
        uint64_t u64;
        int64_t s64;
        double d;
    } v;
    struct dictEntry *next; // 指向下一個哈希表節點，形成單向鏈表 解決hash沖突, 單鏈表中會存儲key和value
} dictEntry;

typedef struct dict {
    dictType *type; //該字典對應的特定操作函數
    void *privdata; //上述類型函數對應的可選參數
    dictht ht[2];/* 兩張哈希表，存儲鍵值對數據，ht[0]為原生哈希表，ht[1]為 rehash 哈希表 */
    long rehashidx; /* rehash標識 當等於-1時表示沒有在rehash，否則表示正在進行rehash操作，
    				存儲的值表示hash表 ht[0]的rehash進行到哪個索引值(數組下標)*/
    unsigned long iterators; /* 當前運行的迭代器數量 */
} dict;

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

    // 復制鍵的函數
    void *(*keyDup)(void *privdata, const void *key);

    // 比較鍵的函數
    void *(*valDup)(void *privdata, const void *obj);

    // 比較鍵的函數
    int (*keyCompare)(void *privdata, const void *key1, const void *key2);

    // 銷毀鍵的函數
    void (*keyDestructor)(void *privdata, void *key);

    // 銷毀值的函數
    void (*valDestructor)(void *privdata, void *obj);
} dictType;

struct ziplist<T>{
    unsigned int zlbytes; // ziplist的長度字節數，包含頭部、所有entry和zipend。
    unsigned int zloffset; // 從ziplist的頭指針到指向最後一個entry的偏移量，用於快速反向查詢
    unsigned short int zllength; // entry元素個數T[] entry; // 元素值
    unsigned char zlend; // ziplist結束符，值固定為0xFF
}
typedef struct zlentry {
    unsigned int prevrawlensize; //previous_entry_length字段的長度
    unsigned int prevrawlen; //previous_entry_length字段存儲的內容
    unsigned int lensize; //encoding字段的長度
    unsigned int len; //數據內容長度
    unsigned int headersize; //當前元素的首部長度，即previous_entry_length字段長度與 encoding字段長度之和。
    unsigned char encoding; //數據類型
    unsigned char *p; //當前元素首地址
} 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{
    //編碼方式
    uint32_t encoding;
    //集合包含的元素數量
    uint32_t length;
    //保存元素的數組
    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的頭部
    quicklistNode *tail; // 指向quicklist的尾部
    unsigned long count;        /* 列表中所有數據項的個數總和 */
    unsigned long len;          /* quicklist節點的個數，即ziplist的個數 */
    int fill : QL_FILL_BITS;              /* ziplist大小限定，由list-max-ziplist-size給定  (Redis設定)*/
    unsigned int compress : QL_COMP_BITS; /* depth of end nodes not to compress;0=off */
    unsigned int bookmark_count: QL_BM_BITS; /*節點壓縮深度設置，由list-compress-depth給定*/
    quicklistBookmark bookmarks[]; /*可選新特性 使用realloc重新分配空間的時候會用到*/
} 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; // 指向上一個ziplist節點
    struct quicklistNode *next; // 指向下一個ziplist節點
    unsigned char *zl; // 數據指針，如果沒有被壓縮，就指向ziplist結構，反之指向 quicklistLZF結構
    unsigned int sz; // 表示指向ziplist結構的總長度(內存占用長度)
    unsigned int count : 16; // 表示ziplist中的數據項個數
    unsigned int encoding : 2; // 編碼方式，1--ziplist，2--quicklistLZF
    unsigned int container : 2; // 預留字段，存放數據的方式，1--NONE，2--ziplist
    unsigned int recompress : 1; // 解壓標記，當查看一個被壓縮的數據時，需要暫時解壓，標記此參數為 1，之後再重新進行壓縮
    unsigned int attempted_compress : 1; // 測試相關
    unsigned int extra : 10; // 擴展字段，暫時沒用
} 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壓縮後占用的字節數*/
    char compressed[]; //柔性數組，指向數據部分
} 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"