github/spark-sql-perf
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fixes for Q34 and Q73 to return results deterministically.

Browse Source 
Author: Nong Li <nong@databricks.com>

Closes #38 from nongli/tpcds.
This commit is contained in:
Nong Li 2015-11-25 15:03:33 -08:00
parent 70e0dbe656
commit 43c2f23bb9
2 changed files with 13 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
src/main/scala/com/databricks/spark/sql/perf/tpcds/ImpalaKitQueries.scala
View File

@ -181,7 +181,9 @@ trait ImpalaKitQueries extends Benchmark {
| c_last_name,
| c_first_name,
| c_salutation,
| c_preferred_cust_flag desc
| c_preferred_cust_flag desc,
| ss_ticket_number,
| cnt
|limit 1000
|-- end query 1 in stream 0 using template query34.tpl
""".stripMargin),
@ -744,7 +746,7 @@ trait ImpalaKitQueries extends Benchmark {
| join store on (store_sales.ss_store_sk = store.s_store_sk)
| -- join date_dim on (store_sales.ss_sold_date_sk = date_dim.d_date_sk)
| where
| store.s_county in ('Saginaw County', 'Sumner County', 'Appanoose County', 'Daviess County')
| store.s_county in ('Williamson County','Franklin Parish','Bronx County','Orange County')
| -- and date_dim.d_dom between 1 and 2
| -- and date_dim.d_year in(1998, 1998 + 1, 1998 + 2)
| -- and ss_date between '1999-01-01' and '2001-12-02'
@ -1150,7 +1152,13 @@ trait ImpalaKitQueries extends Benchmark {
JOIN customer ON dn.ss_customer_sk = customer.c_customer_sk
WHERE
cnt between 15 and 20
order by c_last_name,c_first_name,c_salutation,c_preferred_cust_flag desc"""),
order by
c_last_name,
c_first_name,
c_salutation,
c_preferred_cust_flag desc,
ss_ticket_number,
cnt"""),
("q42", """
select d_year
@ -1418,7 +1426,7 @@ trait ImpalaKitQueries extends Benchmark {
and case when household_demographics.hd_vehicle_count > 0 then
household_demographics.hd_dep_count/ household_demographics.hd_vehicle_count else null end > 1
and date_dim.d_year in (1998,1998+1,1998+2)
and store.s_county in ('Williamson County','Williamson County','Williamson County','Williamson County')
and store.s_county in ('Williamson County','Franklin Parish','Bronx County','Orange County')
group by ss_ticket_number,ss_customer_sk) dj
JOIN customer ON dj.ss_customer_sk = customer.c_customer_sk
where

1
src/main/scala/com/databricks/spark/sql/perf/tpcds/SimpleQueries.scala
View File

@ -33,6 +33,7 @@ trait SimpleQueries extends Benchmark {
| select count(*) from store_sales
| join store_returns
| on store_sales.ss_item_sk = store_returns.sr_item_sk
| and store_sales.ss_ticket_number = store_returns.sr_ticket_number
""".stripMargin)
).map { case (name, sqlText) =>
Query(name = name, sqlText = sqlText, description = "", executionMode = ForeachResults)