[IMPALA-3089] Handle between predicate in disjunctions during static partition pruning in the FE

• Type: Bug
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Affects Version/s: Impala 2.3.4
• Fix Version/s: Impala 2.5.0
• Component/s: Frontend
• Labels: performance planner
• Target Version: Impala 2.5.0
• Assignee: Dimitris Tsirogiannis
• Reporter: Dimitris Tsirogiannis
• Created: 26/Feb/16 00:33
• Updated: 26/Feb/16 17:18
• Resolved: 26/Feb/16 17:18

Description

TPC-DS Q3 has regressed in 2.5 compared to 2.3 due to query planning taking 6s compared to 1.3s for 2.3. Most of this time is spent in evaluating the partition pruning exprs in the BE. The FE can handle the expr on ss_sold_date_sk partition column and avoid the calls to the BE.

Query

select
  dt.d_year,
  item.i_brand_id brand_id,
  item.i_brand brand,
  sum(ss_ext_sales_price) sum_agg
from
  date_dim dt,
  store_sales,
  item
where
  dt.d_date_sk = store_sales.ss_sold_date_sk
  and store_sales.ss_item_sk = item.i_item_sk
  and item.i_manufact_id = 436
  and dt.d_moy = 12
  -- partition key filters
  and (ss_sold_date_sk between 2451149 and 2451179
    or ss_sold_date_sk between 2451514 and 2451544
    or ss_sold_date_sk between 2451880 and 2451910
    or ss_sold_date_sk between 2452245 and 2452275
    or ss_sold_date_sk between 2452610 and 2452640)
group by
  dt.d_year,
  item.i_brand,
  item.i_brand_id
order by
  dt.d_year,
  sum_agg desc,
  brand_id
limit 100