Oracle索引质量介绍和分析脚本分享

--获取指定schema或表上的索引质量信息报告
gx_adm@CABO3> @idx_quality
Enter value for input_owner: GX_ADM
Enter value for input_tbname: CLIENT_TRADE_TBL -->如果我们省略具体的表名则会输出整个schema的索引质量报告

                 Table   Table               Index Data Blks Leaf Blks    Clust Index
Table               Rows   Blocks Index           Size MB  per Key  per Key    Factor Quality
------------------------- ------------ ---------- ------------------------- ------- --------- --------- ------------ -------------
CLIENT_TRADE_TBL       6,318,035   278488 I_TDCL_ARC_STL_DATE_STOCK   62    312    13   171,017 5-Excellent
                         I_TDCL_ARC_STL_DATE_CASH    62    318    13   174,599 5-Excellent
                         I_TDCL_ARC_CANCEL_DATE     83    238     8   288,678 5-Excellent
                         I_TDCL_ARC_INPUT_DATE     144    249    13   310,974 5-Excellent
                         I_TDCL_ARC_TRADE_DATE     144    269    14   337,097 5-Excellent
                         PK_CLIENT_TRADE_TBL      200     1     1   798,216 2-Good
                         I_TDCL_ARC_GRP_REF_ID     144     1     1   811,468 2-Good
                         UNI_TDCL_ARC_REF_ID      136     1     1   765,603 2-Good
                         I_TDCL_ARC_CONTRACT_NUM    72     1     1   834,491 2-Good
                         I_TDCL_ARC_SETTLED_DATE    61    299     5   380,699 1-Poor
                         I_TDCL_ARC_ACC_NUM      184    624     3  3,899,446 1-Poor
                         I_TDCL_ARC_PL_STK       176    218     1  4,348,804 1-Poor
                         I_TDCL_ARC_INSTRU_ID     120   2,667     8  4,273,038 1-Poor

--从上面的单表输出的索引质量可知，出现了4个处于Poor级别的索引，也就是说这些个索引具有较大的聚簇因子，几乎接近于表上的行了
--对于这几个索引的质量还应结合该索引的使用频率来考量该索引存在的必要性
--对于聚簇因子，只能通过重新组织表上的数据来，以及调整相应索引列的顺序得以改善
       
--查询单表上索引列的相关信息       
gx_adm@CABO3> @idx_info
Enter value for owner: GX_ADM
Enter value for table_name: CLIENT_TRADE_TBL

TABLE_NAME        INDEX_NAME           CL_NAM        CL_POS STATUS  IDX_TYP     DSCD
------------------------- ------------------------------ -------------------- ------ -------- --------------- ----
CLIENT_TRADE_TBL     I_TDCL_ARC_ACC_NUM      ACC_NUM          1 VALID  NORMAL     ASC
             I_TDCL_ARC_CANCEL_DATE    CANCEL_DATE        1 VALID  NORMAL     ASC
             I_TDCL_ARC_CONTRACT_NUM   CONTRACT_NUM       1 VALID  NORMAL     ASC
             I_TDCL_ARC_GRP_REF_ID    GRP_REF_ID        1 VALID  NORMAL     ASC
             I_TDCL_ARC_INPUT_DATE    INPUT_DATE        1 VALID  NORMAL     ASC
             I_TDCL_ARC_INSTRU_ID     INSTRU_ID         1 VALID  NORMAL     ASC
             I_TDCL_ARC_PL_STK      STOCK_CD         1 VALID  NORMAL     ASC
             I_TDCL_ARC_PL_STK      PL_CD           2 VALID  NORMAL     ASC
             I_TDCL_ARC_SETTLED_DATE   SETTLED_DATE       1 VALID  NORMAL     ASC
             I_TDCL_ARC_STL_DATE_CASH   STL_DATE_CASH       1 VALID  NORMAL     ASC
             I_TDCL_ARC_STL_DATE_STOCK  STL_DATE_STOCK      1 VALID  NORMAL     ASC
             I_TDCL_ARC_TRADE_DATE    TRADE_DATE        1 VALID  NORMAL     ASC
             PK_CLIENT_TRADE_TBL     BUSINESS_DATE       1 VALID  NORMAL     ASC
             PK_CLIENT_TRADE_TBL     REF_ID          2 VALID  NORMAL     ASC
             UNI_TDCL_ARC_REF_ID     REF_ID          1 VALID  NORMAL     ASC
            
--从上面的查询结果可知，当前表TRADE_CLIENT_TBL上含有13个索引，应该来说该表索引存在一定冗余。
--大多数情况下，单表上6-7个索引是比较理想的。过多的索引导致过大的资源开销，以及降低DML性能。

--script name: idx_quality.sql   --Author : Leshami --Blog: http://blog.csdn./leshami 
--index quality retrieval
SET LINESIZE 145
SET PAGESIZE 1000
SET VERIFY OFF

CLEAR COMPUTES
CLEAR BREAKS

BREAK ON table_name ON num_rows ON blocks

COLUMN owner FORMAT a14 HEADING 'Index owner'
COLUMN table_name FORMAT a25 HEADING 'Table'
COLUMN index_name FORMAT a25 HEADING 'Index'
COLUMN num_rows FORMAT 999G999G990 HEADING 'Table|Rows'
COLUMN MB FORMAT 9G990 HEADING 'Index|Size MB'
COLUMN blocks HEADING 'Table|Blocks'
COLUMN num_blocks FORMAT 9G990 HEADING 'Data|Blocks'
COLUMN avg_data_blocks_per_key FORMAT 999G990 HEADING 'Data Blks|per Key'
COLUMN avg_leaf_blocks_per_key FORMAT 999G990 HEADING 'Leaf Blks|per Key'
COLUMN clustering_factor FORMAT 999G999G990 HEADING 'Clust|Factor'
COLUMN Index_Quality FORMAT A13 HEADING 'Index|Quality'

--SPOOL index_quality

 SELECT i.table_name,
     t.num_rows,
     t.blocks,
     i.index_name,
     o.bytes / 1048576 mb,
     i.avg_data_blocks_per_key,
     i.avg_leaf_blocks_per_key,
     i.clustering_factor,
     CASE
      WHEN NVL (i.clustering_factor, 0) = 0 THEN '0-No Stats'
      WHEN NVL (t.num_rows, 0) = 0 THEN '0-No Stats'
      WHEN (ROUND (i.clustering_factor / t.num_rows  100)) < 6 THEN '5-Excellent'
      WHEN (ROUND (i.clustering_factor / t.num_rows  100)) BETWEEN 7 AND 11 THEN '4-Very Good'
      WHEN (ROUND (i.clustering_factor / t.num_rows  100)) BETWEEN 12 AND 15 THEN '2-Good'
      WHEN (ROUND (i.clustering_factor / t.num_rows  100)) BETWEEN 16 AND 25 THEN '2-Fair'
      ELSE '1-Poor'
     END
      index_quality
  FROM dba_indexes i, dba_segments o, dba_tables t
  WHERE 
   --  i.index_name LIKE UPPER ('%&&1%') AND
     i.owner = t.owner
     AND i.table_name = t.table_name
     AND i.owner = o.owner
     AND i.index_name = o.segment_name
     AND t.owner = UPPER('&input_owner')
     AND t.table_name LIKE UPPER('%&input_tbname%')
ORDER BY table_name,
     num_rows,
     blocks,
     index_quality DESC;

--SPOOL OFF;

===========================================================================================
--script name: idx_info.sql 
--get the index column information by specified table
set linesize 180
col cl_nam format a20
col table_name format a25
col cl_pos format 9
col idx_typ format a15
SELECT b.table_name,
      a.index_name,
      a.column_name   cl_nam,
      a.column_position cl_pos,
      b.status,
      b.index_type   idx_typ,
      a.descend     dscd
FROM  dba_ind_columns a, dba_indexes b
WHERE a.index_name = b.index_name
      AND owner = upper('&owner')
      AND a.table_name LIKE upper('%&table_name%')
ORDER BY 2, 4;