本節簡單介紹了PostgreSQL中的資料結構HTAB.

### 一、資料結構
```
/*
 * Top control structure for a hashtable --- in a shared table, each backend
 * has its own copy (OK since no fields change at runtime)
 * 雜湊表的頂層控制結構.
 * 在這個共享雜湊表中,每一個後臺程式都有自己的複製
 * (之所以沒有問題是因為fork出來後,在執行期沒有欄位會變化)
 */
struct HTAB
{
    //指向共享的控制資訊
    HASHHDR    *hctl;           /* => shared control information */
    //段目錄
    HASHSEGMENT *dir;           /* directory of segment starts */
    //雜湊函式
    HashValueFunc hash;         /* hash function */
    //雜湊鍵比較函式
    HashCompareFunc match;      /* key comparison function */
    //雜湊鍵複製函式
    HashCopyFunc keycopy;       /* key copying function */
    //記憶體分配器
    HashAllocFunc alloc;        /* memory allocator */
    //記憶體上下文
    MemoryContext hcxt;         /* memory context if default allocator used */
    //表名(用於錯誤資訊)
    char       *tabname;        /* table name (for error messages) */
    //如在共享記憶體中,則為T
    bool        isshared;       /* true if table is in shared memory */
    //如為T,則固定大小不能擴充套件
    bool        isfixed;        /* if true, don't enlarge */

/* freezing a shared table isn't allowed, so we can keep state here */
    //不允許凍結共享表,因此這裡會儲存相關狀態
    bool        frozen;         /* true = no more inserts allowed */

/* We keep local copies of these fixed values to reduce contention */
    //儲存這些固定值的本地複製,以減少衝突
    //雜湊鍵長度(以位元組為單位)
    Size        keysize;        /* hash key length in bytes */
    //段大小,必須為2的冪
    long        ssize;          /* segment size --- must be power of 2 */
    //段偏移,ssize的對數
    int         sshift;         /* segment shift = log2(ssize) */
};

/*
 * Header structure for a hash table --- contains all changeable info
 * 雜湊表的頭部結構 -- 儲存所有可變資訊
 *
 * In a shared-memory hash table, the HASHHDR is in shared memory, while
 * each backend has a local HTAB struct.  For a non-shared table, there isn't
 * any functional difference between HASHHDR and HTAB, but we separate them
 * anyway to share code between shared and non-shared tables.
 * 在共享記憶體雜湊表中,HASHHDR位於共享記憶體中,每一個後臺程式都有一個本地HTAB結構.
 * 對於非共享雜湊表,HASHHDR和HTAB沒有任何功能性的不同,
 * 但無論如何,我們還是把它們區分為共享和非共享表.
 */
struct HASHHDR
{
    /*
     * The freelist can become a point of contention in high-concurrency hash
     * tables, so we use an array of freelists, each with its own mutex and
     * nentries count, instead of just a single one.  Although the freelists
     * normally operate independently, we will scavenge entries from freelists
     * other than a hashcode's default freelist when necessary.
     * 在高併發的雜湊表中,空閒連結串列會成為競爭熱點,因此我們使用空閒連結串列陣列,
     *   陣列中的每一個元素都有自己的mutex和條目統計,而不是使用一個.
     *
     * If the hash table is not partitioned, only freeList[0] is used and its
     * spinlock is not used at all; callers' locking is assumed sufficient.
     * 如果雜湊表沒有分割槽,那麼只有freelist[0]元素是有用的,自旋鎖沒有任何用處;
     * 呼叫者鎖定被認為已足夠OK.
     */
    /* Number of freelists to be used for a partitioned hash table. */
    //#define NUM_FREELISTS           32
    FreeListData freeList[NUM_FREELISTS];

/* These fields can change, but not in a partitioned table */
    //這些域欄位可以改變,但不適用於分割槽表
    /* Also, dsize can't change in a shared table, even if unpartitioned */
    //同時,就算是非分割槽表,共享表的dsize也不能改變
    //目錄大小
    long        dsize;          /* directory size */
    //已分配的段大小(<= dsize)
    long        nsegs;          /* number of allocated segments (<= dsize) */
    //正在使用的最大桶ID
    uint32      max_bucket;     /* ID of maximum bucket in use */
    //進入整個雜湊表的模掩碼
    uint32      high_mask;      /* mask to modulo into entire table */
    //進入低位雜湊表的模掩碼
    uint32      low_mask;       /* mask to modulo into lower half of table */

/* These fields are fixed at hashtable creation */
    //下面這些欄位在雜湊表建立時已固定
    //雜湊鍵大小(以位元組為單位)
    Size        keysize;        /* hash key length in bytes */
    //所有使用者元素大小(以位元組為單位)
    Size        entrysize;      /* total user element size in bytes */
    //分割槽個數(2的冪),或者為0
    long        num_partitions; /* # partitions (must be power of 2), or 0 */
    //目標的填充因子
    long        ffactor;        /* target fill factor */
    //如目錄是固定大小,則該值為dsize的上限值
    long        max_dsize;      /* 'dsize' limit if directory is fixed size */
    //段大小,必須是2的冪
    long        ssize;          /* segment size --- must be power of 2 */
    //段偏移,ssize的對數
    int         sshift;         /* segment shift = log2(ssize) */
    //一次性分配的條目個數
    int         nelem_alloc;    /* number of entries to allocate at once */

#ifdef HASH_STATISTICS

/*
     * Count statistics here.  NB: stats code doesn't bother with mutex, so
     * counts could be corrupted a bit in a partitioned table.
     * 統計資訊.
     * 注意:統計相關的程式碼不會影響mutex,因此對於分割槽表,統計可能有一點點問題
     */
    long        accesses;
    long        collisions;
#endif
};

/*
 * Per-freelist data.
 * 空閒連結串列資料.
 *
 * In a partitioned hash table, each freelist is associated with a specific
 * set of hashcodes, as determined by the FREELIST_IDX() macro below.
 * nentries tracks the number of live hashtable entries having those hashcodes
 * (NOT the number of entries in the freelist, as you might expect).
 * 在一個分割槽雜湊表中,每一個空閒連結串列與特定的hashcodes集合相關,透過下面的FREELIST_IDX()宏進行定義.
 * nentries跟蹤有這些hashcodes的仍存活的hashtable條目個數.
 * (注意不要搞錯,不是空閒的條目個數)
 *
 * The coverage of a freelist might be more or less than one partition, so it
 * needs its own lock rather than relying on caller locking.  Relying on that
 * wouldn't work even if the coverage was the same, because of the occasional
 * need to "borrow" entries from another freelist; see get_hash_entry().
 * 空閒連結串列的覆蓋範圍可能比一個分割槽多或少,因此需要自己的鎖而不能僅僅依賴呼叫者的鎖.
 * 依賴呼叫者鎖在覆蓋面一樣的情況下也不會起效,因為偶爾需要從另一個自由列表“借用”條目,詳細參見get_hash_entry()
 *
 * Using an array of FreeListData instead of separate arrays of mutexes,
 * nentries and freeLists helps to reduce sharing of cache lines between
 * different mutexes.
 * 使用FreeListData陣列而不是一個獨立的mutexes,nentries和freelists陣列有助於減少不同mutexes之間的快取線共享.
 */
typedef struct
{
    //該空閒連結串列的自旋鎖
    slock_t     mutex;          /* spinlock for this freelist */
    //相關桶中的條目個數
    long        nentries;       /* number of entries in associated buckets */
    //空閒元素鏈
    HASHELEMENT *freeList;      /* chain of free elements */
} FreeListData;

/*
 * HASHELEMENT is the private part of a hashtable entry.  The caller's data
 * follows the HASHELEMENT structure (on a MAXALIGN'd boundary).  The hash key
 * is expected to be at the start of the caller's hash entry data structure.
 * HASHELEMENT是雜湊表條目的私有部分.
 * 呼叫者的資料按照HASHELEMENT結構組織(位於MAXALIGN的邊界).
 * 雜湊鍵應位於呼叫者hash條目資料結構的開始位置.
 */
typedef struct HASHELEMENT
{
    //連結到相同桶中的下一個條目
    struct HASHELEMENT *link;   /* link to next entry in same bucket */
    //該條目的雜湊函式結果
    uint32      hashvalue;      /* hash function result for this entry */
} HASHELEMENT;

/* Hash table header struct is an opaque type known only within dynahash.c */
//雜湊表頭部結構,非透明型別,用於dynahash.c
typedef struct HASHHDR HASHHDR;

/* Hash table control struct is an opaque type known only within dynahash.c */
//雜湊表控制結構,非透明型別,用於dynahash.c
typedef struct HTAB HTAB;

/* Parameter data structure for hash_create */
//hash_create使用的引數資料結構
/* Only those fields indicated by hash_flags need be set */
//根據hash_flags標記設定相應的欄位
typedef struct HASHCTL
{
    //分割槽個數(必須是2的冪)
    long        num_partitions; /* # partitions (must be power of 2) */
    //段大小
    long        ssize;          /* segment size */
    //初始化目錄大小
    long        dsize;          /* (initial) directory size */
    //dsize上限
    long        max_dsize;      /* limit to dsize if dir size is limited */
    //填充因子
    long        ffactor;        /* fill factor */
    //雜湊鍵大小(位元組為單位)
    Size        keysize;        /* hash key length in bytes */
    //參見上述資料結構註釋
    Size        entrysize;      /* total user element size in bytes */
    //
    HashValueFunc hash;         /* hash function */
    HashCompareFunc match;      /* key comparison function */
    HashCopyFunc keycopy;       /* key copying function */
    HashAllocFunc alloc;        /* memory allocator */
    MemoryContext hcxt;         /* memory context to use for allocations */
    //共享記憶體中的雜湊頭部結構地址
    HASHHDR    *hctl;           /* location of header in shared mem */
} HASHCTL;

/* A hash bucket is a linked list of HASHELEMENTs */
//雜湊桶是HASHELEMENTs連結串列
typedef HASHELEMENT *HASHBUCKET;

/* A hash segment is an array of bucket headers */
//hash segment是桶陣列
typedef HASHBUCKET *HASHSEGMENT;

/*
 * Hash functions must have this signature.
 * Hash函式必須有它自己的標識
 */
typedef uint32 (*HashValueFunc) (const void *key, Size keysize);

/*
 * Key comparison functions must have this signature.  Comparison functions
 * return zero for match, nonzero for no match.  (The comparison function
 * definition is designed to allow memcmp() and strncmp() to be used directly
 * as key comparison functions.)
 * 雜湊鍵對比函式必須有自己的標識.
 * 如匹配則對比函式返回0,不匹配返回非0.
 * (對比函式定義被設計為允許在對比鍵值時可直接使用memcmp()和strncmp())
 */
typedef int (*HashCompareFunc) (const void *key1, const void *key2,
 Size keysize);

/*
 * Key copying functions must have this signature.  The return value is not
 * used.  (The definition is set up to allow memcpy() and strlcpy() to be
 * used directly.)
 * 鍵複製函式必須有自己的標識.
 * 返回值無用.
 */
typedef void *(*HashCopyFunc) (void *dest, const void *src, Size keysize);

/*
 * Space allocation function for a hashtable --- designed to match malloc().
 * Note: there is no free function API; can't destroy a hashtable unless you
 * use the default allocator.
 * 雜湊表的恐懼分配函式 -- 被設計為與malloc()函式匹配.
 * 注意:這裡沒有釋放函式API;不能銷燬雜湊表,除非使用預設的分配器.
 */
typedef void *(*HashAllocFunc) (Size request);

```

其結構如下圖所示：
![](http://img.blog.itpub.net/blog/2020/01/16/47399be06e997336.png?x-oss-process=style/bb)

### 二、跟蹤分析
測試指令碼
```
\pset footer off
\pset tuples_only on
\o /tmp/drop.sql
SELECT 'drop table if exists tbl' || id || ' ;' as "--"
       FROM generate_series(1, 20000) AS id;
\i /tmp/drop.sql

\pset footer off
\pset tuples_only on
\o /tmp/create.sql
SELECT 'CREATE TABLE tbl' || id || ' (id int);' as "--"
       FROM generate_series(1, 10000) AS id;

begin;
\o /tmp/ret.txt
\i /tmp/create.sql

```
跟蹤分析
```
...
HASHSEGMENT *dir --> HASHELEMENT ***dir;
dir --> HASHELEMENT ***

(gdb) p *hctl
$1 = {freeList = {{mutex = 0 '\000', nentries = 312, freeList = 0x7fd906ab84c0}, {mutex = 0 '\000', 
      nentries = 298, freeList = 0x7fd907097c40}, {mutex = 0 '\000', nentries = 292, 
      freeList = 0x7fd906ac2520}, {mutex = 0 '\000', nentries = 321, freeList = 0x7fd906ac8120}, {
      mutex = 0 '\000', nentries = 341, freeList = 0x7fd907229980}, {mutex = 0 '\000', nentries = 334, 
      freeList = 0x7fd906ad3f08}, {mutex = 0 '\000', nentries = 316, freeList = 0x7fd906ad6fb8}, {
      mutex = 0 '\000', nentries = 299, freeList = 0x7fd906ade550}, {mutex = 0 '\000', nentries = 328, 
      freeList = 0x7fd906ae1600}, {mutex = 0 '\000', nentries = 328, freeList = 0x7fd906ae62e8}, {
      mutex = 0 '\000', nentries = 308, freeList = 0x7fd906aeb660}, {mutex = 0 '\000', nentries = 327, 
      freeList = 0x7fd90706f338}, {mutex = 0 '\000', nentries = 346, freeList = 0x7fd906af6bc0}, {
      mutex = 0 '\000', nentries = 323, freeList = 0x7fd907237bc0}, {mutex = 0 '\000', nentries = 304, 
      freeList = 0x7fd9071ddb40}, {mutex = 0 '\000', nentries = 311, freeList = 0x7fd906b06238}, {
      mutex = 0 '\000', nentries = 292, freeList = 0x7fd90707b620}, {mutex = 0 '\000', nentries = 303, 
      freeList = 0x7fd90723dd20}, {mutex = 0 '\000', nentries = 302, freeList = 0x7fd906b137e0}, {
      mutex = 0 '\000', nentries = 307, freeList = 0x7fd9070873c8}, {mutex = 0 '\000', nentries = 314, 
      freeList = 0x7fd90723bb68}, {mutex = 0 '\000', nentries = 279, freeList = 0x7fd906b22678}, {
      mutex = 0 '\000', nentries = 297, freeList = 0x7fd907073e08}, {mutex = 0 '\000', nentries = 309, 
      freeList = 0x7fd90721f888}, {mutex = 0 '\000', nentries = 317, freeList = 0x7fd906b33880}, {
      mutex = 0 '\000', nentries = 283, freeList = 0x7fd907086168}, {mutex = 0 '\000', nentries = 331, 
      freeList = 0x7fd906b3d838}, {mutex = 0 '\000', nentries = 330, freeList = 0x7fd906b41f38}, {
      mutex = 0 '\000', nentries = 313, freeList = 0x7fd906b46440}, {mutex = 0 '\000', nentries = 304, 
      freeList = 0x7fd906b4b5c0}, {mutex = 0 '\000', nentries = 310, freeList = 0x7fd90720ed80}, {
      mutex = 0 '\000', nentries = 323, freeList = 0x7fd906b575a0}}, dsize = 256, nsegs = 16, 
  max_bucket = 4095, high_mask = 8191, low_mask = 4095, keysize = 16, entrysize = 152, num_partitions = 16, 
  ffactor = 1, max_dsize = 256, ssize = 256, sshift = 8, nelem_alloc = 48}
(gdb) p *hashp
$2 = {hctl = 0x7fd906aae980, dir = 0x7fd906aaecd8, hash = 0xa79ac6 <tag_hash>, match = 0x47cb70 <memcmp>, 
  keycopy = 0x47d0a0 <memcpy>, alloc = 0x8c3419 <shmemallocnoerror>, hcxt = 0x0, 
  tabname = 0x160f1d0 "LOCK hash", isshared = true, isfixed = false, frozen = false, keysize = 16, 
  ssize = 256, sshift = 8}
(gdb) p *hashp->dir
$3 = (HASHSEGMENT) 0x7fd906aaf500
(gdb) p hashp->dir
$4 = (HASHSEGMENT *) 0x7fd906aaecd8
(gdb) p **hashp->dir
$5 = (HASHBUCKET) 0x7fd907212dd0
(gdb) p ***hashp->dir
$6 = {link = 0x7fd9071a7b90, hashvalue = 1748602880}
(gdb) n
949     if (action == HASH_ENTER || action == HASH_ENTER_NULL)
(gdb) 
956         if (!IS_PARTITIONED(hctl) && !hashp->frozen &&
(gdb) 
965     bucket = calc_bucket(hctl, hashvalue); --> hash桶
(gdb) 
967     segment_num = bucket >> hashp->sshift; --> 桶號右移8位得到段號
(gdb) 
968     segment_ndx = MOD(bucket, hashp->ssize); --> 桶號取模得到段內偏移
(gdb) 
970     segp = hashp->dir[segment_num]; --> 獲取段（HASHELEMENT **）
(gdb) 
972     if (segp == NULL)
(gdb) p bucket
$7 = 2072
(gdb) p segment_num
$8 = 8
(gdb) p segment_ndx
$9 = 24
(gdb) p segp --> 
$10 = (HASHSEGMENT) 0x7fd906ab3500
(gdb) 
(gdb) n
975     prevBucketPtr = &segp[segment_ndx]; --> HASHELEMENT **
(gdb) 
976     currBucket = *prevBucketPtr; --> HASHELEMENT *
(gdb) 
981     match = hashp->match;       /* save one fetch in inner loop */
(gdb) p prevBucketPtr
$12 = (HASHBUCKET *) 0x7fd906ab35c0
(gdb) p currBucket
$13 = (HASHBUCKET) 0x7fd90714da68
(gdb)

```

DONE!

### 三、參考資料
N/A</shmemallocnoerror></memcpy></memcmp></tag_hash>

PostgreSQL 原始碼解讀（240）- HTAB簡介

相關文章