本節簡單介紹了PostgreSQL手工執行vacuum的主處理流程,主要分析了ExecVacuum函式的實現邏輯。

### 一、資料結構
**宏定義**
Vacuum和Analyze命令選項
```
/* ----------------------
 *      Vacuum and Analyze Statements
 *      Vacuum和Analyze命令選項
 * 
 * Even though these are nominally two statements, it's convenient to use
 * just one node type for both.  Note that at least one of VACOPT_VACUUM
 * and VACOPT_ANALYZE must be set in options.
 * 雖然在這裡有兩種不同的語句,但只需要使用統一的Node型別即可.
 * 注意至少VACOPT_VACUUM/VACOPT_ANALYZE在選項中設定.
 * ----------------------
 */
typedef enum VacuumOption
{
    VACOPT_VACUUM = 1 << 0,     /* do VACUUM */
    VACOPT_ANALYZE = 1 << 1,    /* do ANALYZE */
    VACOPT_VERBOSE = 1 << 2,    /* print progress info */
    VACOPT_FREEZE = 1 << 3,     /* FREEZE option */
    VACOPT_FULL = 1 << 4,       /* FULL (non-concurrent) vacuum */
    VACOPT_SKIP_LOCKED = 1 << 5,    /* skip if cannot get lock */
    VACOPT_SKIPTOAST = 1 << 6,  /* don't process the TOAST table, if any */
    VACOPT_DISABLE_PAGE_SKIPPING = 1 << 7   /* don't skip any pages */
} VacuumOption;

```

**VacuumStmt**
儲存vacuum命令的option&Relation連結串列
```
typedef struct VacuumStmt
{
    NodeTag     type;//Tag
    //VacuumOption位標記
    int         options;        /* OR of VacuumOption flags */
    //VacuumRelation連結串列,如為NIL-->所有Relation.
    List       *rels;           /* list of VacuumRelation, or NIL for all */
} VacuumStmt;
 
 
```

**VacuumParams**
vacuum命令引數
```
/*
 * Parameters customizing behavior of VACUUM and ANALYZE.
 * 客戶端呼叫VACUUM/ANALYZE時的定製化引數
 */
typedef struct VacuumParams
{
    //最小freeze age,-1表示使用預設
    int         freeze_min_age; /* min freeze age, -1 to use default */
    //掃描整個table的freeze age
    int         freeze_table_age;   /* age at which to scan whole table */
    //最小的multixact freeze age,-1表示預設
    int         multixact_freeze_min_age;   /* min multixact freeze age, -1 to
                                             * use default */
    //掃描全表的freeze age,-1表示預設
    int         multixact_freeze_table_age; /* multixact age at which to scan
                                             * whole table */
    //是否強制wraparound?
    bool        is_wraparound;  /* force a for-wraparound vacuum */
    //以毫秒為單位的最小執行閾值
    int         log_min_duration;   /* minimum execution threshold in ms at
                                     * which  verbose logs are activated, -1
                                     * to use default */
} VacuumParams;

```

**VacuumRelation**
VACUUM/ANALYZE命令的目標表資訊
```
/*
 * Info about a single target table of VACUUM/ANALYZE.
 * VACUUM/ANALYZE命令的目標表資訊.
 *  
 * If the OID field is set, it always identifies the table to process.
 * Then the relation field can be NULL; if it isn't, it's used only to report
 * failure to open/lock the relation.
 * 如設定了OID欄位,該值通常是將要處理的資料表.
 * 那麼關係欄位可以為空;如果不是，則僅用於報告未能開啟/鎖定關係。
 */
typedef struct VacuumRelation
{
    NodeTag     type;
    RangeVar   *relation;       /* table name to process, or NULL */
    Oid         oid;            /* table's OID; InvalidOid if not looked up */
    List       *va_cols;        /* list of column names, or NIL for all */
} VacuumRelation;
 
```

### 二、原始碼解讀
ExecVacuum函式,手工執行VACUUM/ANALYZE命令時的主入口,vacuum()函式的包裝器(wrapper).
```
/*
 * Primary entry point for manual VACUUM and ANALYZE commands
 * 手工執行VACUUM/ANALYZE命令時的主入口
 *
 * This is mainly a preparation wrapper for the real operations that will
 * happen in vacuum().
 * 這是vacuum()函式的包裝器(wrapper)
 */
void
ExecVacuum(VacuumStmt *vacstmt, bool isTopLevel)
{
    VacuumParams params;

/* sanity checks on options */
    //驗證&檢查
    Assert(vacstmt->options & (VACOPT_VACUUM | VACOPT_ANALYZE));
    Assert((vacstmt->options & VACOPT_VACUUM) ||
           !(vacstmt->options & (VACOPT_FULL | VACOPT_FREEZE)));
    Assert(!(vacstmt->options & VACOPT_SKIPTOAST));

/*
     * Make sure VACOPT_ANALYZE is specified if any column lists are present.
     * 如出現欄位列表,則確保指定了VACOPT_ANALYZE選項
     */
    if (!(vacstmt->options & VACOPT_ANALYZE))
    {
        ListCell   *lc;

foreach(lc, vacstmt->rels)
        {
            VacuumRelation *vrel = lfirst_node(VacuumRelation, lc);

if (vrel->va_cols != NIL)
                ereport(ERROR,
                        (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                         errmsg("ANALYZE option must be specified when a column list is provided")));
        }
    }

/*
     * All freeze ages are zero if the FREEZE option is given; otherwise pass
     * them as -1 which means to use the default values.
     * 如指定了FREEZE選項則設定所有freeze ages為0.
     * 否則的話,傳遞-1(即使用預設值).
     */
    if (vacstmt->options & VACOPT_FREEZE)
    {
        //指定VACOPT_FREEZE
        params.freeze_min_age = 0;
        params.freeze_table_age = 0;
        params.multixact_freeze_min_age = 0;
        params.multixact_freeze_table_age = 0;
    }
    else
    {
        params.freeze_min_age = -1;
        params.freeze_table_age = -1;
        params.multixact_freeze_min_age = -1;
        params.multixact_freeze_table_age = -1;
    }

/* user-invoked vacuum is never "for wraparound" */
    //使用者呼叫的vacuum永遠不會是wraparound
    params.is_wraparound = false;

/* user-invoked vacuum never uses this parameter */
    //使用者呼叫vacuum永遠不會使用該引數
    params.log_min_duration = -1;

/* Now go through the common routine */
    //呼叫vacuum
    vacuum(vacstmt->options, vacstmt->rels, &params, NULL, isTopLevel);
}

```

### 三、跟蹤分析
測試指令碼
```
17:19:28 (xdb@[local]:5432)testdb=# vacuum t1;

```

啟動gdb,設定斷點
```
(gdb) b ExecVacuum
Breakpoint 1 at 0x6b99a1: file vacuum.c, line 92.
(gdb) c
Continuing.

Breakpoint 1, ExecVacuum (vacstmt=0x210e9c0, isTopLevel=true) at vacuum.c:92
92      Assert(vacstmt->options & (VACOPT_VACUUM | VACOPT_ANALYZE));
(gdb) 
```
輸入引數
options = 1 --> VACOPT_VACUUM
```
(gdb) p *vacstmt
$1 = {type = T_VacuumStmt, options = 1, rels = 0x210e988}
(gdb) 
```
獲取Relation相關資訊
```
gdb) n
93      Assert((vacstmt->options & VACOPT_VACUUM) ||
(gdb) 
95      Assert(!(vacstmt->options & VACOPT_SKIPTOAST));
(gdb) 
100     if (!(vacstmt->options & VACOPT_ANALYZE))
(gdb) 
104         foreach(lc, vacstmt->rels)
(gdb) 
106             VacuumRelation *vrel = lfirst_node(VacuumRelation, lc);
(gdb) 
108             if (vrel->va_cols != NIL)
(gdb) p *vrel
$3 = {type = T_VacuumRelation, relation = 0x210e8d0, oid = 0, va_cols = 0x0}
(gdb) p *vrel->relation
$4 = {type = T_RangeVar, catalogname = 0x0, schemaname = 0x0, relname = 0x210e8b0 "t1", inh = true, 
  relpersistence = 112 'p', alias = 0x0, location = 7}
(gdb) 
```
設定vacuum引數
```
(gdb) n
104         foreach(lc, vacstmt->rels)
(gdb) 
119     if (vacstmt->options & VACOPT_FREEZE)
(gdb) 
128         params.freeze_min_age = -1;
(gdb) 
129         params.freeze_table_age = -1;
(gdb) 
130         params.multixact_freeze_min_age = -1;
(gdb) 
131         params.multixact_freeze_table_age = -1;
(gdb) 
135     params.is_wraparound = false;
(gdb) 
(gdb) n
138     params.log_min_duration = -1;
(gdb) 
```
呼叫vacuum
```
141     vacuum(vacstmt->options, vacstmt->rels, &params, NULL, isTopLevel);
(gdb) 
142 }
(gdb) 
standard_ProcessUtility (pstmt=0x210ea80, queryString=0x210dec8 "vacuum t1;", context=PROCESS_UTILITY_TOPLEVEL, params=0x0, 
    queryEnv=0x0, dest=0x210ed70, completionTag=0x7fff1d69dea0 "") at utility.c:672
672             break;
```
DONE!

### 四、參考資料
[PG Source Code](https://doxygen.postgresql.org)

PostgreSQL 原始碼解讀（125）- MVCC#9（vacuum-主流程）

相關文章