Oracle聚簇因子

1、聚簇因子(clustering_factor)：是使用B樹索引進行區間掃描的成本很重要因素，反映資料在表中分布的隨機程度

2、聚簇因子的計算方法：
①掃描索引
②比較某行的ROWID和前一行的ROWID，如果這兩個ROWID不屬於同一個資料區塊，那麼聚簇因子增加1

 --對選擇最優查詢路徑影響最大的只有列的選擇率和聚簇因子

3、實驗測試

create table t1 as
select trunc((rownum-1)/100) id,
rpad(rownum,100) t_pad
from dba_source
where rownum <= 10000;
create index t1_idx1 on t1(id);
exec dbms_stats.gather_table_stats(user,'t1',method_opt=>'FOR ALL COLUMNS SIZE 1',cascade=>TRUE);

create table t2 as
select mod(rownum,100) id,
rpad(rownum,100) t_pad
from dba_source
where rownum <= 10000;
create index t2_idx1 on t2(id);
exec dbms_stats.gather_table_stats(user,'t2',method_opt=>'FOR ALL COLUMNS SIZE 1',cascade=>TRUE);
select count(*) ct from t1 where id = 1 ;
select count(*) ct from t2 where id = 1 ;

--索引的聚簇因子
select t.table_name||'.'||i.index_name idx_name,
i.clustering_factor, t.blocks, t.num_rows
from user_indexes i, user_tables t
where i.table_name = t.table_name
and t.table_name in ('T1','T2')
order by t.table_name, i.index_name;

--計算索引的聚簇因子
select t.table_name||'.'||i.index_name idx_name,
i.clustering_factor, t.blocks, t.num_rows
from all_indexes i, all_tables t
where i.table_name = t.table_name
and t.table_name = 'EMPLOYEES'
and t.owner = 'HR'
and i.index_name = 'EMP_DEPARTMENT_IX'
order by t.table_name, i.index_name;

select department_id, last_name, blk_no,
lag (blk_no,1,blk_no) over (order by department_id) prev_blk_no,
case when blk_no != lag (blk_no,1,blk_no) over (order by department_id)
or rownum = 1
then '*** +1'
else null
end cluf_ct
from (
select department_id, last_name,
dbms_rowid.rowid_block_number(rowid) blk_no
from hr.employees
where department_id is not null
order by department_id
);

查看本欄目更多精彩內容：http://www.bianceng.cnhttp://www.bianceng.cn/database/Oracle/