[IMPALA-3635] Order group by clause based on cardinality and cost

• Type: Improvement
• Status: Resolved
• Priority: Major
• Resolution: Won't Fix
• Affects Version/s: Impala 2.2
• Component/s: Frontend
• Labels: performance planner ramp-up
• Assignee: Thomas Tauber-Marshall
• Reporter: Mostafa Mokhtar
• Created: 27/May/16 17:57
• Updated: 28/Jul/16 22:48
• Resolved: 28/Jul/16 22:48

Description

Similar to IMPALA-2805 Group by clause should be ordered by cardinality and cost.

From TPC-DS Q78

Bad current order

group by d_year, ws_item_sk, ws_bill_customer_sk

Ideal current order

group by ws_bill_customer_sk, ws_item_sk, d_year

Subset of TPC-DS Q78

select d_year AS ws_sold_year, ws_item_sk,
    ws_bill_customer_sk ws_customer_sk,
    sum(ws_quantity) ws_qty,
    sum(ws_wholesale_cost) ws_wc,
    sum(ws_sales_price) ws_sp
   from web_sales
   left join web_returns on wr_order_number=ws_order_number and ws_item_sk=wr_item_sk
   join date_dim on ws_sold_date_sk = d_date_sk
   where wr_order_number is null
   group by d_year, ws_item_sk, ws_bill_customer_sk

Issue Links

• relates to: IMPALA-2805 Order filters based on selectivity and cost