[jira] [Resolved] (DRILL-7122) TPCDS queries 29 25 17 are slower when Statistics is disabled.

["Gautam Parai (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/DRILL-7122?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Gautam Parai resolved DRILL-7122.
---------------------------------
    Resolution: Fixed

> TPCDS queries 29 25 17 are slower when Statistics is disabled.
> --------------------------------------------------------------
>
>                 Key: DRILL-7122
>                 URL: https://issues.apache.org/jira/browse/DRILL-7122
>             Project: Apache Drill
>          Issue Type: Bug
>          Components: Query Planning & Optimization
>    Affects Versions: 1.16.0
>            Reporter: Robert Hou
>            Assignee: Gautam Parai
>            Priority: Blocker
>             Fix For: 1.16.0
>
>
> Here is query 29 with sf 100:
> {noformat}
> SELECT i_item_id, 
>                i_item_desc, 
>                s_store_id, 
>                s_store_name, 
>                Avg(ss_quantity)        AS store_sales_quantity, 
>                Avg(sr_return_quantity) AS store_returns_quantity, 
>                Avg(cs_quantity)        AS catalog_sales_quantity 
> FROM   store_sales, 
>        store_returns, 
>        catalog_sales, 
>        date_dim d1, 
>        date_dim d2, 
>        date_dim d3, 
>        store, 
>        item 
> WHERE  d1.d_moy = 4 
>        AND d1.d_year = 1998 
>        AND d1.d_date_sk = ss_sold_date_sk 
>        AND i_item_sk = ss_item_sk 
>        AND s_store_sk = ss_store_sk 
>        AND ss_customer_sk = sr_customer_sk 
>        AND ss_item_sk = sr_item_sk 
>        AND ss_ticket_number = sr_ticket_number 
>        AND sr_returned_date_sk = d2.d_date_sk 
>        AND d2.d_moy BETWEEN 4 AND 4 + 3 
>        AND d2.d_year = 1998 
>        AND sr_customer_sk = cs_bill_customer_sk 
>        AND sr_item_sk = cs_item_sk 
>        AND cs_sold_date_sk = d3.d_date_sk 
>        AND d3.d_year IN ( 1998, 1998 + 1, 1998 + 2 ) 
> GROUP  BY i_item_id, 
>           i_item_desc, 
>           s_store_id, 
>           s_store_name 
> ORDER  BY i_item_id, 
>           i_item_desc, 
>           s_store_id, 
>           s_store_name
> LIMIT 100; 
> {noformat}
> The hash join order has changed.  As a result, one of the hash joins does not seem to reduce the number of rows significantly.



--
This message was sent by Atlassian JIRA
(v7.6.3#76005)