MySQL全文索引源码剖析之Insert语句执行过程

mysql> CREATE TABLE opening_lines (
           id INT UNSIGNED AUTO_INCREMENT NOT NULL PRIMARY KEY,
           opening_line TEXT(500),
           author VARCHAR(200),
           title VARCHAR(200),
           FULLTEXT idx (opening_line)
           ) ENGINE=InnoDB;    
mysql> INSERT INTO opening_lines(opening_line,author,title) VALUES
           ('Call me Ishmael.','Herman Melville','Moby-Dick'),
           ('A screaming comes across the sky.','Thomas Pynchon','Gravity\'s Rainbow'), 
           ('I am an invisible man.','Ralph Ellison','Invisible Man'),
           ('Where now? Who now? When now?','Samuel Beckett','The Unnamable');      
mysql> SET GLOBAL innodb_ft_aux_table='test/opening_lines';
mysql> select * from information_schema.INNODB_FT_INDEX_TABLE; 
 +-----------+--------------+-------------+-----------+--------+----------+  
| WORD      | FIRST_DOC_ID | LAST_DOC_ID | DOC_COUNT | DOC_ID | POSITION |  
+-----------+--------------+-------------+-----------+--------+----------+  
| across    |            4 |           4 |         1 |      4 |       18 |  
| call      |            3 |           3 |         1 |      3 |        0 |  
| comes     |            4 |           4 |         1 |      4 |       12 |  
| invisible |            5 |           5 |         1 |      5 |        8 |  
| ishmael   |            3 |           3 |         1 |      3 |        8 |  
| man       |            5 |           5 |         1 |      5 |       18 |  
| now       |            6 |           6 |         1 |      6 |        6 |  
| now       |            6 |           6 |         1 |      6 |        9 |  
| now       |            6 |           6 |         1 |      6 |       10 |  
| screaming |            4 |           4 |         1 |      4 |        2 |  
| sky       |            4 |           4 |         1 |      4 |       29 |  
+-----------+--------------+-------------+-----------+--------+----------+

  ha_innobase::write_row
        ->row_insert_for_mysql
            ->row_insert_for_mysql_using_ins_graph
                ->row_mysql_convert_row_to_innobase
                    ->fts_create_doc_id
                        ->fts_get_next_doc_id
                ->fts_trx_add_op
                    ->fts_trx_table_add_op

fts_commit_table
      ->fts_add
          ->fts_add_doc_by_id
              ->fts_cache_add_doc
                    // 根据doc_id获取文档，对文档分词
                  ->fts_fetch_doc_from_rec
                    // 将分词结果添加到cache中
                  ->fts_cache_add_doc
              ->fts_optimize_request_sync_table
                    // 创建FTS_MSG_SYNC_TABLE消息，通知刷脏线程刷脏
                  ->fts_optimize_create_msg(FTS_MSG_SYNC_TABLE)

   static ulint fts_add_doc_by_id(fts_trx_table_t *ftt, doc_id_t doc_id)
    {
            /* 1. 根据docid在fts_doc_id_index索引中的查找记录 */
          /* btr_pcur_open_with_no_init函数中会调用btr_cur_search_to_nth_level，btr_cur_search_to_nth_level
            会执行b+树搜索记录的过程，先从根节点找到docid记录所在的叶子节点，再通过二分查找找到docid记录。*/
        btr_pcur_open_with_no_init(fts_id_index, tuple, PAGE_CUR_LE,
                                    BTR_SEARCH_LEAF, &pcur, 0, &mtr);
        if (btr_pcur_get_low_match(&pcur) == 1) { /* 如果找到了docid记录 */
            if (is_id_cluster) {
                 /** 1.1 如果fts_doc_id_index是聚集索引，则意味着已经找到行记录数据, 直接保存行记录 **/
                doc_pcur = &pcur;
              } else {
                /** 1.2 如果fts_doc_id_index是辅助索引，则需要根据1.1找到的主键id在聚集索引上进一步搜 索行记录，找到后保存行记录**/                btr_pcur_open_with_no_init(clust_index, clust_ref, PAGE_CUR_LE,
                                           BTR_SEARCH_LEAF, &clust_pcur, 0, &mtr); 
               doc_pcur = &clust_pcur;
             }        // 遍历cache->get_docs
            for (ulint i = 0; i < num_idx; ++i) {
                /***** 2. 对文档执行分词，获取{单词,(单词所在的文档，单词在文档中的偏移)}关联对，并添加到cache中 *****/
                fts_doc_t doc;
                fts_doc_init(&doc);
        /** 2.1 根据doc_id获取行记录中该全文索引对应列的内容文档，解析文档，主要是为了构建               fts_doc_t结构体的tokens，tokens为一个红黑树结构，每个元素是一个               {单词，[该单词在文档中出现的位置]}的结构，解析结果存于doc中 **/
                fts_fetch_doc_from_rec(ftt->fts_trx->trx, get_doc, clust_index,doc_pcur, offsets, &doc);
                /** 2.2 将2.1步骤获得的{单词，[该单词在文档中出现的位置]}添加到index_cache中 **/
                fts_cache_add_doc(table->fts->cache, get_doc->index_cache, doc_id, doc.tokens);
               /***** 3. 判断cache->total_size是否达到阈值时。  若达到阈值，则往刷脏线程的消息队列添加一个FTS_MSG_SYNC_TABLE消息, 通知该线程刷脏 *****/
                bool need_sync = false;
                if ((cache->total_size - cache->total_size_before_sync >
                     fts_max_cache_size / 10 || fts_need_sync) &&!cache->sync->in_progress) {
                  /** 3.1 判断是达到阈值 **/
                  need_sync = true;
                  cache->total_size_before_sync = cache->total_size;
                }
                    if (need_sync) {
                    /** 3.2 打包FTS_MSG_SYNC_TABLE消息挂载至fts_optimize_wq队列，                   通知fts_optimize_thread线程刷脏，消息的内容为table id **/                  fts_optimize_request_sync_table(table);
                }
            }
        }
    }  

  fts_optimize_thread
        ->ib_wqueue_timedwait
            ->fts_optimize_sync_table
                ->fts_sync_table
                    ->fts_sync
                        ->fts_sync_commit
                            ->fts_cache_clear