openGauss数据库源码解析系列文章——AI技术（三）：智能索引推荐

SuggestedIndex *suggest_index(const char *query_string, _out_ int *len)
{
    ……
    // 对查询语句进行词法和语法解析，获得解析树
List *parse_tree_list = raw_parser(query_string);
…
    // 递归地搜索解析树中的SelectStmt结构
    Node *parsetree = (Node *)lfirst(list_head(parse_tree_list));
    find_select_stmt(parsetree);
   …
 
    // 依次解析和处理SelectStmt结构中的各个子句部分
    ListCell *item = NULL;
 
    foreach (item, g_stmt_list) {
        SelectStmt *stmt = (SelectStmt *)lfirst(item);
        /* 处理SelectStmt 结构体中涉及的FROM子句，提取涉及的表，解析和保存这些表中的join关系 */
        parse_from_clause(stmt->fromClause);
        …
        if (g_table_list) {
            // 处理WHERE子句，提取条件表达式中的谓词并添加候选索引，解析和保存其中的join关系
            parse_where_clause(stmt->whereClause);
            // 根据保存的join关系确定驱动表
            determine_driver_table();
            // 处理GROUP子句，如果满足条件，则将其中的谓词添加为候选索引
            if (parse_group_clause(stmt->groupClause, stmt->targetList)) {
                add_index_from_group_order(g_driver_table, stmt->groupClause, stmt->targetList, true);
            /* 处理ORDER子句，如果满足条件，则将其中的谓词添加为候选索引 */
            } else if (parse_order_clause(stmt->sortClause, stmt->targetList)) {
                add_index_from_group_order(g_driver_table, stmt->sortClause, stmt->targetList, false);
            }
            // 如果是多表查询，则根据保存的join关系为被驱动表添加候选索引
            if (g_table_list->length > 1 && g_driver_table) {
                add_index_for_drived_tables();
            }
            /* 对全局变量中的每个table依次进行处理，函数generate_final_index将前述过程生成的候选索引进行字符串拼接，并检查和已存在的索引是否重复 */
            ListCell *table_item = NULL;
 
            foreach (table_item, g_table_list) {
                TableCell *table = (TableCell *)lfirst(table_item);
                if (table->index != NIL) {
                    Oid table_oid = find_table_oid(query_tree->rtable, table->table_name);
                    if (table_oid == 0) {
                        continue;
                    }
                    generate_final_index(table, table_oid);
                }
            }
            g_driver_table = NULL;
        }
    }
……
    return array;
}
复制

typedef struct hypoIndex {
    Oid oid;           /* 虚拟索引的oid，该oid是唯一的 */
    Oid relid;         /* 涉及的表的oid */
    …
    char *indexname;   /* 虚拟索引名 */
 
    BlockNumber pages; /* 预估索引使用的磁盘页数 */
    double tuples;     /* 预估索引所涉及的元组数目 */
 
    /* 索引描述信息 */
    int ncolumns;         /* 涉及的总列数 */
    int nkeycolumns;      /* 涉及的关键列数 */
    …
    Oid relam;            /* 记录索引操作回调函数的元组的oid, 从pg_am系统表中获取的 */
    …
} hypoIndex;
复制

hypoIndex *hypo_index_store_parsetree(IndexStmt *node, const char *queryString)
{
……
// 获得创建索引的表的oid
    relid = RangeVarGetRelid(node->relation, AccessShareLock, false);
    ……
    // 对该创建索引的语句进行语法解析
    node = transformIndexStmt(relid, node, queryString);
    ……
    // 新建虚拟索引，该虚拟索引的结构体类型hypoIndex定于位于文件openGauss-server/src/include/dbmind/hypopg_index.h，与索引结构体IndexOptInfo类似
    entry = hypo_newIndex(relid, node->accessMethod, nkeycolumns, ninccolumns, node->options);
    // 根据语法树的解析结果为虚拟索引entry内的各个成员赋值
    PG_TRY();
{
   ……
        entry->unique = node->unique;
        entry->ncolumns = nkeycolumns + ninccolumns;
        entry->nkeycolumns = nkeycolumns;
        ……
    }
    PG_CATCH();
    {        
        hypo_index_pfree(entry);
        PG_RE_THROW();
    }
    PG_END_TRY();
    // 设置虚拟索引的名字
    hypo_set_indexname(entry, indexRelationName.data);
    // 将新建的虚拟索引entry添加到虚拟索引的全局链表hypoIndexes上，该全局变量为节点类型为hypoIndex*的List链表，记录了全部创建过的虚拟索引
    hypo_addIndex(entry);
 
    return entry;
}
// 该函数被赋值给全局的函数指针get_relation_info_hook，当数据库执行EXPLAIN时，会通过该函数指针跳转到本函数
void hypo_get_relation_info_hook(PlannerInfo *root, Oid relationObjectId, bool inhparent, RelOptInfo *rel)
{
    /* 判断是否开启GUC参数enable_hypo_index，当SQL语句是EXPLAIN命令时，变量isExplain的值为真 */
    if (u_sess->attr.attr_sql.enable_hypo_index && isExplain) {
        Relation relation;
 
        relation = heap_open(relationObjectId, AccessShareLock);
 
        if (relation->rd_rel->relkind == RELKIND_RELATION) {
            ListCell *lc;
            /* 遍历全局变量链表hypoIndexes中的每个创建过的虚拟索引 */
            foreach (lc, hypoIndexes) {
                hypoIndex *entry = (hypoIndex *)lfirst(lc);
                // 判断该虚拟索引和该表是否匹配
                if (hypo_index_match_table(entry, RelationGetRelid(relation))) {
                    // 如果匹配，则将该索引加入该表的indexlist中，indexlist是节点类型为IndexOptInfo的链表，是结构体类型RelOptInfo的成员，记录了表的所有的索引
                    hypo_injectHypotheticalIndex(root, relationObjectId, inhparent, rel, relation, entry);
                }
            }
        }
        heap_close(relation, AccessShareLock);
}
……
}
复制

opengauss=> select * from gs_index_advise('SELECT c_discount from bmsql_customer where c_w_id = 10');
     table      |  column  
----------------+----------
 bmsql_customer | (c_w_id)
(1 row)
复制

CREATE INDEX idx on bmsql_customer(c_w_id);
复制

opengauss=# select * from gs_index_advise('select name, age, sex from t1 where age >= 18 and age < 35 and sex = ''f'';');
 table | column
-------+------------
 t1    | (age, sex)
(1 row)
复制

CREATE INDEX idx1 on t1(age, sex);
复制

opengauss=> select * from hypopg_create_index('create index on bmsql_customer(c_w_id)');
 indexrelid |              indexname              
------------+-------------------------------------
     329726 | <329726>btree_bmsql_customer_c_w_id
(1 row)
复制

opengauss=> set enable_hypo_index = on;
SET
复制

opengauss=> explain SELECT c_discount from bmsql_customer where c_w_id = 10;
                              QUERY PLAN                              
--------------------------------------------------------------------
 Seq Scan on bmsql_customer  (cost=0.00..52963.06 rows=31224 width=4)
   Filter: (c_w_id = 10)
(2 rows)
复制

opengauss=> explain SELECT c_discount from bmsql_customer where c_w_id = 10;
                              QUERY PLAN                          
--------------------------------------------------------------------
 [Bypass]
 Index Scan using <329726>btree_bmsql_customer_c_w_id on bmsql_customer  (cost=0.00..39678.69 rows=31224 width=4)
   Index Cond: (c_w_id = 10)
(3 rows)
复制

opengauss=> select * from hypopg_display_index();
                 indexname                  | indexrelid |     table      |      column      
--------------------------------------------+------------+----------------+------------------
 <329726>btree_bmsql_customer_c_w_id        |     329726 | bmsql_customer | (c_w_id)
 <329729>btree_bmsql_customer_c_d_id_c_w_id |     329729 | bmsql_customer | (c_d_id, c_w_id)
(2 rows)
复制

opengauss=> select * from hypopg_estimate_size(329730);
 hypopg_estimate_size
----------------------
             15687680
(1 row)
复制

opengauss=> select * from hypopg_drop_index(329726);
 hypopg_drop_index
-------------------
 t
(1 row)
复制

opengauss=> select * from hypopg_reset_index();
 hypopg_reset_index
--------------------
    
(1 row)
复制

python index_advisor_workload.py [p PORT] [d DATABASE] [f FILE] [--h HOST] [-U USERNAME] [-W PASSWORD]
[--max_index_num MAX_INDEX_NUM] [--multi_iter_mode]
复制

python index_advisor_workload.py 6001 opengauss tpcc_log.txt --max_index_num 10 --multi_iter_mode
复制

create index ind0 on bmsql_stock(s_i_id,s_w_id);
create index ind1 on bmsql_customer(c_w_id,c_id,c_d_id);
create index ind2 on bmsql_order_line(ol_w_id,ol_o_id,ol_d_id);
create index ind3 on bmsql_item(i_id);
create index ind4 on bmsql_oorder(o_w_id,o_id,o_d_id);
create index ind5 on bmsql_new_order(no_w_id,no_d_id,no_o_id);
create index ind6 on bmsql_customer(c_w_id,c_d_id,c_last,c_first);
create index ind7 on bmsql_new_order(no_w_id);
create index ind8 on bmsql_oorder(o_w_id,o_c_id,o_d_id);
create index ind9 on bmsql_district(d_w_id);
复制