第一部分：数据结构与对象

1
2
3
4
5
6

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[];
};

1

sds _sdsnewlen(const void *init, size_t initlen, int trymalloc)

1
2
3

    s = (char*)sh+hdrlen;
    fp = ((unsigned char*)s)-1;
    usable = usable-hdrlen-1;

1
2
3
4
5

typedef struct listNode {
    struct listNode *prev;
    struct listNode *next;
    void *value;
} listNode;

1
2
3
4
5
6
7
8

typedef struct list {
    listNode *head;
    listNode *tail;
    void *(*dup)(void *ptr);
    void (*free)(void *ptr);
    int (*match)(void *ptr, void *key);
    unsigned long len;
} list;

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18

/* 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;
    quicklistNode *tail;
    unsigned long count;        /* total count of all entries in all ziplists */
    unsigned long len;          /* number of quicklistNodes */
    int fill : QL_FILL_BITS;              /* fill factor for individual nodes */
    unsigned int compress : QL_COMP_BITS; /* depth of end nodes not to compress;0=off */
    unsigned int bookmark_count: QL_BM_BITS;
    quicklistBookmark bookmarks[];
} quicklist;

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12

/* Bookmarks are padded with realloc at the end of of the quicklist struct.
 * They should only be used for very big lists if thousands of nodes were the
 * excess memory usage is negligible, and there's a real need to iterate on them
 * in portions.
 * When not used, they don't add any memory overhead, but when used and then
 * deleted, some overhead remains (to avoid resonance).
 * The number of bookmarks used should be kept to minimum since it also adds
 * overhead on node deletion (searching for a bookmark to update). */
typedef struct quicklistBookmark {
    quicklistNode *node;
    char *name;
} quicklistBookmark;

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16
17
18
19
20

/* 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;
    struct quicklistNode *next;
    unsigned char *zl;
    unsigned int sz;             /* ziplist size in bytes */
    unsigned int count : 16;     /* count of items in ziplist */
    unsigned int encoding : 2;   /* RAW==1 or LZF==2 */
    unsigned int container : 2;  /* NONE==1 or ZIPLIST==2 */
    unsigned int recompress : 1; /* was this node previous compressed? */
    unsigned int attempted_compress : 1; /* node can't compress; too small */
    unsigned int extra : 10; /* more bits to steal for future usage */
} quicklistNode;

1
2
3
4
5
6
7

typedef struct dict {
    dictType *type;
    void *privdata;
    dictht ht[2];
    long rehashidx; /* rehashing not in progress if rehashidx == -1 */
    int16_t pauserehash; /* If >0 rehashing is paused (<0 indicates coding error) */
} dict;

1
2
3
4
5
6

typedef struct dictht {
    dictEntry **table;
    unsigned long size;
    unsigned long sizemask;
    unsigned long used;
} dictht;

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

typedef struct dictEntry {
    void *key;
    union {
        void *val;
        uint64_t u64;
        int64_t s64;
        double d;
    } v;
    struct dictEntry *next;
} dictEntry;

1

int _dictExpand(dict *d, unsigned long size, int* malloc_failed)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

static unsigned long _dictNextPower(unsigned long size)
{
    unsigned long i = DICT_HT_INITIAL_SIZE;	// 4
    if (size >= LONG_MAX) return LONG_MAX + 1LU;
    while(1) {
        if (i >= size)
            return i;
        i *= 2;
    }
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14
15
16

/* Expand the hash table if needed */
static int _dictExpandIfNeeded(dict *d) {
  	/// ...
		/* If we reached the 1:1 ratio, and we are allowed to resize the hash
     * table (global setting) or we should avoid it but the ratio between
     * elements/buckets is over the "safe" threshold, we resize doubling
     * the number of buckets. */
    if (d->ht[0].used >= d->ht[0].size &&
        (dict_can_resize ||
         d->ht[0].used/d->ht[0].size > dict_force_resize_ratio) &&
        dictTypeExpandAllowed(d))
    {
        return dictExpand(d, d->ht[0].used + 1);
    }
  	/// ...
}

 1
 2
 3
 4
 5
 6
 7
 8
 9
10

/* Performs N steps of incremental rehashing. Returns 1 if there are still
 * keys to move from the old to the new hash table, otherwise 0 is returned.
 *
 * Note that a rehashing step consists in moving a bucket (that may have more
 * than one key as we use chaining) from the old to the new hash table, however
 * since part of the hash table may be composed of empty spaces, it is not
 * guaranteed that this function will rehash even a single bucket, since it
 * will visit at max N*10 empty buckets in total, otherwise the amount of
 * work it does would be unbound and the function may block for a long time. */
int dictRehash(dict *d, int n)

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13

/* Rehash in ms+"delta" milliseconds. The value of "delta" is larger 
 * than 0, and is smaller than 1 in most cases. The exact upper bound 
 * depends on the running time of dictRehash(d,100).*/
int dictRehashMilliseconds(dict *d, int ms) {
    if (d->pauserehash > 0) return 0;
    long long start = timeInMilliseconds();
    int rehashes = 0;
    while(dictRehash(d,100)) {
        rehashes += 100;
        if (timeInMilliseconds()-start > ms) break;
    }
    return rehashes;
}

1
2
3
4
5
6
7

unsigned char *zipmapNew(void) {
    unsigned char *zm = zmalloc(2);

    zm[0] = 0; /* Length */
    zm[1] = ZIPMAP_END;
    return zm;
}

1
2
3
4
5

typedef struct zskiplist {
    struct zskiplistNode *header, *tail;
    unsigned long length;
    int level;
} zskiplist;

1
2
3
4
5
6
7
8
9

typedef struct zskiplistNode {
    sds ele;
    double score;
    struct zskiplistNode *backward;
    struct zskiplistLevel {
        struct zskiplistNode *forward;
        unsigned long span;
    } level[];
} zskiplistNode;

1

#define ZSKIPLIST_P 0.25      /* Skiplist P = 1/4 */

1
2
3
4
5

typedef struct intset {
    uint32_t encoding;
    uint32_t length;
    int8_t contents[];
} intset;

1
2
3

#define INTSET_ENC_INT16 (sizeof(int16_t))
#define INTSET_ENC_INT32 (sizeof(int32_t))
#define INTSET_ENC_INT64 (sizeof(int64_t))

1
2

/* Upgrades the intset to a larger encoding and inserts the given integer. */
static intset *intsetUpgradeAndAdd(intset *is, int64_t value)

1

<zlbytes> <zltail> <zllen> <entry> <entry> ... <entry> <zlend>

1

<prevlen> <encoding> <entry-data>

1

<prevlen> <encoding>

1

0xFE <4 bytes unsigned little endian prevlen> <encoding> <entry>

1
2
3
4
5
6
7
8
9

typedef struct redisObject {
    unsigned type:4;
    unsigned encoding:4;
    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;
    void *ptr;
} robj;

1
2
3
4
5
6

/* The actual Redis Object */
#define OBJ_STRING 0    /* String object. */
#define OBJ_LIST 1      /* List object. */
#define OBJ_SET 2       /* Set object. */
#define OBJ_ZSET 3      /* Sorted set object. */
#define OBJ_HASH 4      /* Hash object. */

 1
 2
 3
 4
 5
 6
 7
 8
 9
10
11
12
13
14

/* 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 */