http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query49.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query49.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query49.q.out new file mode 100644 index 0000000..9c31d61 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query49.q.out @@ -0,0 +1,330 @@ +PREHOOK: query: explain cbo +select + 'web' as channel + ,web.item + ,web.return_ratio + ,web.return_rank + ,web.currency_rank + from ( + select + item + ,return_ratio + ,currency_ratio + ,rank() over (order by return_ratio) as return_rank + ,rank() over (order by currency_ratio) as currency_rank + from + ( select ws.ws_item_sk as item + ,(cast(sum(coalesce(wr.wr_return_quantity,0)) as dec(15,4))/ + cast(sum(coalesce(ws.ws_quantity,0)) as dec(15,4) )) as return_ratio + ,(cast(sum(coalesce(wr.wr_return_amt,0)) as dec(15,4))/ + cast(sum(coalesce(ws.ws_net_paid,0)) as dec(15,4) )) as currency_ratio + from + web_sales ws left outer join web_returns wr + on (ws.ws_order_number = wr.wr_order_number and + ws.ws_item_sk = wr.wr_item_sk) + ,date_dim + where + wr.wr_return_amt > 10000 + and ws.ws_net_profit > 1 + and ws.ws_net_paid > 0 + and ws.ws_quantity > 0 + and ws_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 12 + group by ws.ws_item_sk + ) in_web + ) web + where + ( + web.return_rank <= 10 + or + web.currency_rank <= 10 + ) + union + select + 'catalog' as channel + ,catalog.item + ,catalog.return_ratio + ,catalog.return_rank + ,catalog.currency_rank + from ( + select + item + ,return_ratio + ,currency_ratio + ,rank() over (order by return_ratio) as return_rank + ,rank() over (order by currency_ratio) as currency_rank + from + ( select + cs.cs_item_sk as item + ,(cast(sum(coalesce(cr.cr_return_quantity,0)) as dec(15,4))/ + cast(sum(coalesce(cs.cs_quantity,0)) as dec(15,4) )) as return_ratio + ,(cast(sum(coalesce(cr.cr_return_amount,0)) as dec(15,4))/ + cast(sum(coalesce(cs.cs_net_paid,0)) as dec(15,4) )) as currency_ratio + from + catalog_sales cs left outer join catalog_returns cr + on (cs.cs_order_number = cr.cr_order_number and + cs.cs_item_sk = cr.cr_item_sk) + ,date_dim + where + cr.cr_return_amount > 10000 + and cs.cs_net_profit > 1 + and cs.cs_net_paid > 0 + and cs.cs_quantity > 0 + and cs_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 12 + group by cs.cs_item_sk + ) in_cat + ) catalog + where + ( + catalog.return_rank <= 10 + or + catalog.currency_rank <=10 + ) + union + select + 'store' as channel + ,store.item + ,store.return_ratio + ,store.return_rank + ,store.currency_rank + from ( + select + item + ,return_ratio + ,currency_ratio + ,rank() over (order by return_ratio) as return_rank + ,rank() over (order by currency_ratio) as currency_rank + from + ( select sts.ss_item_sk as item + ,(cast(sum(coalesce(sr.sr_return_quantity,0)) as dec(15,4))/cast(sum(coalesce(sts.ss_quantity,0)) as dec(15,4) )) as return_ratio + ,(cast(sum(coalesce(sr.sr_return_amt,0)) as dec(15,4))/cast(sum(coalesce(sts.ss_net_paid,0)) as dec(15,4) )) as currency_ratio + from + store_sales sts left outer join store_returns sr + on (sts.ss_ticket_number = sr.sr_ticket_number and sts.ss_item_sk = sr.sr_item_sk) + ,date_dim + where + sr.sr_return_amt > 10000 + and sts.ss_net_profit > 1 + and sts.ss_net_paid > 0 + and sts.ss_quantity > 0 + and ss_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 12 + group by sts.ss_item_sk + ) in_store + ) store + where ( + store.return_rank <= 10 + or + store.currency_rank <= 10 + ) + order by 1,4,5 + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@catalog_returns +PREHOOK: Input: default@catalog_sales +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@store_returns +PREHOOK: Input: default@store_sales +PREHOOK: Input: default@web_returns +PREHOOK: Input: default@web_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select + 'web' as channel + ,web.item + ,web.return_ratio + ,web.return_rank + ,web.currency_rank + from ( + select + item + ,return_ratio + ,currency_ratio + ,rank() over (order by return_ratio) as return_rank + ,rank() over (order by currency_ratio) as currency_rank + from + ( select ws.ws_item_sk as item + ,(cast(sum(coalesce(wr.wr_return_quantity,0)) as dec(15,4))/ + cast(sum(coalesce(ws.ws_quantity,0)) as dec(15,4) )) as return_ratio + ,(cast(sum(coalesce(wr.wr_return_amt,0)) as dec(15,4))/ + cast(sum(coalesce(ws.ws_net_paid,0)) as dec(15,4) )) as currency_ratio + from + web_sales ws left outer join web_returns wr + on (ws.ws_order_number = wr.wr_order_number and + ws.ws_item_sk = wr.wr_item_sk) + ,date_dim + where + wr.wr_return_amt > 10000 + and ws.ws_net_profit > 1 + and ws.ws_net_paid > 0 + and ws.ws_quantity > 0 + and ws_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 12 + group by ws.ws_item_sk + ) in_web + ) web + where + ( + web.return_rank <= 10 + or + web.currency_rank <= 10 + ) + union + select + 'catalog' as channel + ,catalog.item + ,catalog.return_ratio + ,catalog.return_rank + ,catalog.currency_rank + from ( + select + item + ,return_ratio + ,currency_ratio + ,rank() over (order by return_ratio) as return_rank + ,rank() over (order by currency_ratio) as currency_rank + from + ( select + cs.cs_item_sk as item + ,(cast(sum(coalesce(cr.cr_return_quantity,0)) as dec(15,4))/ + cast(sum(coalesce(cs.cs_quantity,0)) as dec(15,4) )) as return_ratio + ,(cast(sum(coalesce(cr.cr_return_amount,0)) as dec(15,4))/ + cast(sum(coalesce(cs.cs_net_paid,0)) as dec(15,4) )) as currency_ratio + from + catalog_sales cs left outer join catalog_returns cr + on (cs.cs_order_number = cr.cr_order_number and + cs.cs_item_sk = cr.cr_item_sk) + ,date_dim + where + cr.cr_return_amount > 10000 + and cs.cs_net_profit > 1 + and cs.cs_net_paid > 0 + and cs.cs_quantity > 0 + and cs_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 12 + group by cs.cs_item_sk + ) in_cat + ) catalog + where + ( + catalog.return_rank <= 10 + or + catalog.currency_rank <=10 + ) + union + select + 'store' as channel + ,store.item + ,store.return_ratio + ,store.return_rank + ,store.currency_rank + from ( + select + item + ,return_ratio + ,currency_ratio + ,rank() over (order by return_ratio) as return_rank + ,rank() over (order by currency_ratio) as currency_rank + from + ( select sts.ss_item_sk as item + ,(cast(sum(coalesce(sr.sr_return_quantity,0)) as dec(15,4))/cast(sum(coalesce(sts.ss_quantity,0)) as dec(15,4) )) as return_ratio + ,(cast(sum(coalesce(sr.sr_return_amt,0)) as dec(15,4))/cast(sum(coalesce(sts.ss_net_paid,0)) as dec(15,4) )) as currency_ratio + from + store_sales sts left outer join store_returns sr + on (sts.ss_ticket_number = sr.sr_ticket_number and sts.ss_item_sk = sr.sr_item_sk) + ,date_dim + where + sr.sr_return_amt > 10000 + and sts.ss_net_profit > 1 + and sts.ss_net_paid > 0 + and sts.ss_quantity > 0 + and ss_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 12 + group by sts.ss_item_sk + ) in_store + ) store + where ( + store.return_rank <= 10 + or + store.currency_rank <= 10 + ) + order by 1,4,5 + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@catalog_returns +POSTHOOK: Input: default@catalog_sales +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@store_returns +POSTHOOK: Input: default@store_sales +POSTHOOK: Input: default@web_returns +POSTHOOK: Input: default@web_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$0], sort1=[$3], sort2=[$4], dir0=[ASC], dir1=[ASC], dir2=[ASC], fetch=[100]) + HiveProject(channel=[$0], item=[$1], return_ratio=[$2], return_rank=[$3], currency_rank=[$4]) + HiveAggregate(group=[{0, 1, 2, 3, 4}]) + HiveProject(channel=[$0], item=[$1], return_ratio=[$2], return_rank=[$3], currency_rank=[$4]) + HiveUnion(all=[true]) + HiveProject(channel=[$0], item=[$1], return_ratio=[$2], return_rank=[$3], currency_rank=[$4]) + HiveAggregate(group=[{0, 1, 2, 3, 4}]) + HiveProject(channel=[$0], item=[$1], return_ratio=[$2], return_rank=[$3], currency_rank=[$4]) + HiveUnion(all=[true]) + HiveProject(channel=[_UTF-16LE'web'], item=[$0], return_ratio=[$1], return_rank=[$2], currency_rank=[$3]) + HiveFilter(condition=[OR(<=($2, 10), <=($3, 10))]) + HiveProject(item=[$0], return_ratio=[/(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4))], rank_window_0=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)], rank_window_1=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($3):DECIMAL(15, 4), CAST($4):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)], agg#3=[sum($4)]) + HiveProject($f0=[$5], $f1=[CASE(IS NOT NULL($2), $2, 0)], $f2=[CASE(IS NOT NULL($7), $7, 0)], $f3=[CASE(IS NOT NULL($3), $3, 0)], $f4=[CASE(IS NOT NULL($8), $8, 0)]) + HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(wr_item_sk=[$2], wr_order_number=[$13], wr_return_quantity=[$14], wr_return_amt=[$15]) + HiveFilter(condition=[AND(>($15, 10000), IS NOT NULL($13), IS NOT NULL($2))]) + HiveTableScan(table=[[default, web_returns]], table:alias=[wr]) + HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_order_number=[$17], ws_quantity=[$18], ws_net_paid=[$29], ws_net_profit=[$33]) + HiveFilter(condition=[AND(>($33, 1), >($29, 0), >($18, 0), IS NOT NULL($17), IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[ws]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 12), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(channel=[_UTF-16LE'catalog'], item=[$0], return_ratio=[$1], return_rank=[$2], currency_rank=[$3]) + HiveFilter(condition=[OR(<=($2, 10), <=($3, 10))]) + HiveProject(item=[$0], return_ratio=[/(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4))], rank_window_0=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)], rank_window_1=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($3):DECIMAL(15, 4), CAST($4):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)], agg#3=[sum($4)]) + HiveProject($f0=[$5], $f1=[CASE(IS NOT NULL($2), $2, 0)], $f2=[CASE(IS NOT NULL($7), $7, 0)], $f3=[CASE(IS NOT NULL($3), $3, 0)], $f4=[CASE(IS NOT NULL($8), $8, 0)]) + HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cr_item_sk=[$2], cr_order_number=[$16], cr_return_quantity=[$17], cr_return_amount=[$18]) + HiveFilter(condition=[AND(>($18, 10000), IS NOT NULL($16), IS NOT NULL($2))]) + HiveTableScan(table=[[default, catalog_returns]], table:alias=[cr]) + HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_order_number=[$17], cs_quantity=[$18], cs_net_paid=[$29], cs_net_profit=[$33]) + HiveFilter(condition=[AND(>($33, 1), >($29, 0), >($18, 0), IS NOT NULL($17), IS NOT NULL($15), IS NOT NULL($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[cs]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 12), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(channel=[_UTF-16LE'store'], item=[$0], return_ratio=[$1], return_rank=[$2], currency_rank=[$3]) + HiveFilter(condition=[OR(<=($2, 10), <=($3, 10))]) + HiveProject(item=[$0], return_ratio=[/(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4))], rank_window_0=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($1):DECIMAL(15, 4), CAST($2):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)], rank_window_1=[rank() OVER (PARTITION BY 0 ORDER BY /(CAST($3):DECIMAL(15, 4), CAST($4):DECIMAL(15, 4)) NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[sum($2)], agg#2=[sum($3)], agg#3=[sum($4)]) + HiveProject($f0=[$5], $f1=[CASE(IS NOT NULL($2), $2, 0)], $f2=[CASE(IS NOT NULL($7), $7, 0)], $f3=[CASE(IS NOT NULL($3), $3, 0)], $f4=[CASE(IS NOT NULL($8), $8, 0)]) + HiveJoin(condition=[AND(=($6, $1), =($5, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(sr_item_sk=[$2], sr_ticket_number=[$9], sr_return_quantity=[$10], sr_return_amt=[$11]) + HiveFilter(condition=[AND(>($11, 10000), IS NOT NULL($9), IS NOT NULL($2))]) + HiveTableScan(table=[[default, store_returns]], table:alias=[sr]) + HiveJoin(condition=[=($0, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ticket_number=[$9], ss_quantity=[$10], ss_net_paid=[$20], ss_net_profit=[$22]) + HiveFilter(condition=[AND(>($22, 1), >($20, 0), >($10, 0), IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[sts]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 12), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) +
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query5.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query5.q.out new file mode 100644 index 0000000..a82f011 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query5.q.out @@ -0,0 +1,342 @@ +PREHOOK: query: explain cbo +with ssr as + (select s_store_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select ss_store_sk as store_sk, + ss_sold_date_sk as date_sk, + ss_ext_sales_price as sales_price, + ss_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from store_sales + union all + select sr_store_sk as store_sk, + sr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + sr_return_amt as return_amt, + sr_net_loss as net_loss + from store_returns + ) salesreturns, + date_dim, + store + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and store_sk = s_store_sk + group by s_store_id) + , + csr as + (select cp_catalog_page_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select cs_catalog_page_sk as page_sk, + cs_sold_date_sk as date_sk, + cs_ext_sales_price as sales_price, + cs_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from catalog_sales + union all + select cr_catalog_page_sk as page_sk, + cr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + cr_return_amount as return_amt, + cr_net_loss as net_loss + from catalog_returns + ) salesreturns, + date_dim, + catalog_page + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and page_sk = cp_catalog_page_sk + group by cp_catalog_page_id) + , + wsr as + (select web_site_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select ws_web_site_sk as wsr_web_site_sk, + ws_sold_date_sk as date_sk, + ws_ext_sales_price as sales_price, + ws_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from web_sales + union all + select ws_web_site_sk as wsr_web_site_sk, + wr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + wr_return_amt as return_amt, + wr_net_loss as net_loss + from web_returns left outer join web_sales on + ( wr_item_sk = ws_item_sk + and wr_order_number = ws_order_number) + ) salesreturns, + date_dim, + web_site + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and wsr_web_site_sk = web_site_sk + group by web_site_id) + select channel + , id + , sum(sales) as sales + , sum(returns) as returns + , sum(profit) as profit + from + (select 'store channel' as channel + , 'store' || s_store_id as id + , sales + , returns + , (profit - profit_loss) as profit + from ssr + union all + select 'catalog channel' as channel + , 'catalog_page' || cp_catalog_page_id as id + , sales + , returns + , (profit - profit_loss) as profit + from csr + union all + select 'web channel' as channel + , 'web_site' || web_site_id as id + , sales + , returns + , (profit - profit_loss) as profit + from wsr + ) x + group by rollup (channel, id) + order by channel + ,id + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@catalog_page +PREHOOK: Input: default@catalog_returns +PREHOOK: Input: default@catalog_sales +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@store +PREHOOK: Input: default@store_returns +PREHOOK: Input: default@store_sales +PREHOOK: Input: default@web_returns +PREHOOK: Input: default@web_sales +PREHOOK: Input: default@web_site +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +with ssr as + (select s_store_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select ss_store_sk as store_sk, + ss_sold_date_sk as date_sk, + ss_ext_sales_price as sales_price, + ss_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from store_sales + union all + select sr_store_sk as store_sk, + sr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + sr_return_amt as return_amt, + sr_net_loss as net_loss + from store_returns + ) salesreturns, + date_dim, + store + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and store_sk = s_store_sk + group by s_store_id) + , + csr as + (select cp_catalog_page_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select cs_catalog_page_sk as page_sk, + cs_sold_date_sk as date_sk, + cs_ext_sales_price as sales_price, + cs_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from catalog_sales + union all + select cr_catalog_page_sk as page_sk, + cr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + cr_return_amount as return_amt, + cr_net_loss as net_loss + from catalog_returns + ) salesreturns, + date_dim, + catalog_page + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and page_sk = cp_catalog_page_sk + group by cp_catalog_page_id) + , + wsr as + (select web_site_id, + sum(sales_price) as sales, + sum(profit) as profit, + sum(return_amt) as returns, + sum(net_loss) as profit_loss + from + ( select ws_web_site_sk as wsr_web_site_sk, + ws_sold_date_sk as date_sk, + ws_ext_sales_price as sales_price, + ws_net_profit as profit, + cast(0 as decimal(7,2)) as return_amt, + cast(0 as decimal(7,2)) as net_loss + from web_sales + union all + select ws_web_site_sk as wsr_web_site_sk, + wr_returned_date_sk as date_sk, + cast(0 as decimal(7,2)) as sales_price, + cast(0 as decimal(7,2)) as profit, + wr_return_amt as return_amt, + wr_net_loss as net_loss + from web_returns left outer join web_sales on + ( wr_item_sk = ws_item_sk + and wr_order_number = ws_order_number) + ) salesreturns, + date_dim, + web_site + where date_sk = d_date_sk + and d_date between cast('1998-08-04' as date) + and (cast('1998-08-04' as date) + 14 days) + and wsr_web_site_sk = web_site_sk + group by web_site_id) + select channel + , id + , sum(sales) as sales + , sum(returns) as returns + , sum(profit) as profit + from + (select 'store channel' as channel + , 'store' || s_store_id as id + , sales + , returns + , (profit - profit_loss) as profit + from ssr + union all + select 'catalog channel' as channel + , 'catalog_page' || cp_catalog_page_id as id + , sales + , returns + , (profit - profit_loss) as profit + from csr + union all + select 'web channel' as channel + , 'web_site' || web_site_id as id + , sales + , returns + , (profit - profit_loss) as profit + from wsr + ) x + group by rollup (channel, id) + order by channel + ,id + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@catalog_page +POSTHOOK: Input: default@catalog_returns +POSTHOOK: Input: default@catalog_sales +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_returns +POSTHOOK: Input: default@store_sales +POSTHOOK: Input: default@web_returns +POSTHOOK: Input: default@web_sales +POSTHOOK: Input: default@web_site +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) + HiveProject(channel=[$0], id=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{0, 1}], groups=[[{0, 1}, {0}, {}]], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)]) + HiveProject(channel=[$0], id=[$1], sales=[$2], returns=[$3], profit=[$4]) + HiveUnion(all=[true]) + HiveProject(channel=[_UTF-16LE'store channel'], id=[||(_UTF-16LE'store', $0)], sales=[$1], returns=[$3], profit=[-($2, $4)]) + HiveAggregate(group=[{9}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)]) + HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(store_sk=[$0], date_sk=[$1], sales_price=[$2], profit=[$3], return_amt=[$4], net_loss=[$5]) + HiveUnion(all=[true]) + HiveProject(store_sk=[$7], date_sk=[$0], sales_price=[$15], profit=[$22], return_amt=[CAST(0):DECIMAL(7, 2)], net_loss=[CAST(0):DECIMAL(7, 2)]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(store_sk=[$7], date_sk=[$0], sales_price=[CAST(0):DECIMAL(7, 2)], profit=[CAST(0):DECIMAL(7, 2)], return_amt=[$11], net_loss=[$19]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) + HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-08-18 00:00:00), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(s_store_sk=[$0], s_store_id=[$1]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(channel=[_UTF-16LE'catalog channel'], id=[||(_UTF-16LE'catalog_page', $0)], sales=[$1], returns=[$3], profit=[-($2, $4)]) + HiveAggregate(group=[{1}], agg#0=[sum($4)], agg#1=[sum($5)], agg#2=[sum($6)], agg#3=[sum($7)]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cp_catalog_page_sk=[$0], cp_catalog_page_id=[$1]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_page]], table:alias=[catalog_page]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(page_sk=[$0], date_sk=[$1], sales_price=[$2], profit=[$3], return_amt=[$4], net_loss=[$5]) + HiveUnion(all=[true]) + HiveProject(page_sk=[$12], date_sk=[$0], sales_price=[$23], profit=[$33], return_amt=[CAST(0):DECIMAL(7, 2)], net_loss=[CAST(0):DECIMAL(7, 2)]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($12))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(page_sk=[$12], date_sk=[$0], sales_price=[CAST(0):DECIMAL(7, 2)], profit=[CAST(0):DECIMAL(7, 2)], return_amt=[$18], net_loss=[$26]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($12))]) + HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns]) + HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-08-18 00:00:00), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(channel=[_UTF-16LE'web channel'], id=[||(_UTF-16LE'web_site', $0)], sales=[$1], returns=[$3], profit=[-($2, $4)]) + HiveAggregate(group=[{9}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)]) + HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(wsr_web_site_sk=[$0], date_sk=[$1], sales_price=[$2], profit=[$3], return_amt=[$4], net_loss=[$5]) + HiveUnion(all=[true]) + HiveProject(wsr_web_site_sk=[$13], date_sk=[$0], sales_price=[$23], profit=[$33], return_amt=[CAST(0):DECIMAL(7, 2)], net_loss=[CAST(0):DECIMAL(7, 2)]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($13))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(wsr_web_site_sk=[$1], date_sk=[$3], sales_price=[CAST(0):DECIMAL(7, 2)], profit=[CAST(0):DECIMAL(7, 2)], return_amt=[$6], net_loss=[$7]) + HiveJoin(condition=[AND(=($4, $0), =($5, $2))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_item_sk=[$3], ws_web_site_sk=[$13], ws_order_number=[$17]) + HiveFilter(condition=[AND(IS NOT NULL($13), IS NOT NULL($3), IS NOT NULL($17))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(wr_returned_date_sk=[$0], wr_item_sk=[$2], wr_order_number=[$13], wr_return_amt=[$15], wr_net_loss=[$23]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2), IS NOT NULL($13))]) + HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) + HiveProject(d_date_sk=[$0], d_date=[$2]) + HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-08-18 00:00:00), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(web_site_sk=[$0], web_site_id=[$1]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_site]], table:alias=[web_site]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query50.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query50.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query50.q.out new file mode 100644 index 0000000..2be59c1 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query50.q.out @@ -0,0 +1,151 @@ +PREHOOK: query: explain cbo +select + s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk <= 30 ) then 1 else 0 end) as `30 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 30) and + (sr_returned_date_sk - ss_sold_date_sk <= 60) then 1 else 0 end ) as `31-60 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 60) and + (sr_returned_date_sk - ss_sold_date_sk <= 90) then 1 else 0 end) as `61-90 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 90) and + (sr_returned_date_sk - ss_sold_date_sk <= 120) then 1 else 0 end) as `91-120 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 120) then 1 else 0 end) as `>120 days` +from + store_sales + ,store_returns + ,store + ,date_dim d1 + ,date_dim d2 +where + d2.d_year = 2000 +and d2.d_moy = 9 +and ss_ticket_number = sr_ticket_number +and ss_item_sk = sr_item_sk +and ss_sold_date_sk = d1.d_date_sk +and sr_returned_date_sk = d2.d_date_sk +and ss_customer_sk = sr_customer_sk +and ss_store_sk = s_store_sk +group by + s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip +order by s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@store +PREHOOK: Input: default@store_returns +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select + s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk <= 30 ) then 1 else 0 end) as `30 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 30) and + (sr_returned_date_sk - ss_sold_date_sk <= 60) then 1 else 0 end ) as `31-60 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 60) and + (sr_returned_date_sk - ss_sold_date_sk <= 90) then 1 else 0 end) as `61-90 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 90) and + (sr_returned_date_sk - ss_sold_date_sk <= 120) then 1 else 0 end) as `91-120 days` + ,sum(case when (sr_returned_date_sk - ss_sold_date_sk > 120) then 1 else 0 end) as `>120 days` +from + store_sales + ,store_returns + ,store + ,date_dim d1 + ,date_dim d2 +where + d2.d_year = 2000 +and d2.d_moy = 9 +and ss_ticket_number = sr_ticket_number +and ss_item_sk = sr_item_sk +and ss_sold_date_sk = d1.d_date_sk +and sr_returned_date_sk = d2.d_date_sk +and ss_customer_sk = sr_customer_sk +and ss_store_sk = s_store_sk +group by + s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip +order by s_store_name + ,s_company_id + ,s_street_number + ,s_street_name + ,s_street_type + ,s_suite_number + ,s_city + ,s_county + ,s_state + ,s_zip +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_returns +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], sort5=[$5], sort6=[$6], sort7=[$7], sort8=[$8], sort9=[$9], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC], dir6=[ASC], dir7=[ASC], dir8=[ASC], dir9=[ASC], fetch=[100]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f8=[$8], $f9=[$9], $f10=[$10], $f11=[$11], $f12=[$12], $f13=[$13], $f14=[$14]) + HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6, 7, 8, 9}], agg#0=[sum($10)], agg#1=[sum($11)], agg#2=[sum($12)], agg#3=[sum($13)], agg#4=[sum($14)]) + HiveProject($f0=[$14], $f1=[$15], $f2=[$16], $f3=[$17], $f4=[$18], $f5=[$19], $f6=[$20], $f7=[$21], $f8=[$22], $f9=[$23], $f10=[CASE(<=(-($5, $0), 30), 1, 0)], $f11=[CASE(AND(>(-($5, $0), 30), <=(-($5, $0), 60)), 1, 0)], $f12=[CASE(AND(>(-($5, $0), 60), <=(-($5, $0), 90)), 1, 0)], $f13=[CASE(AND(>(-($5, $0), 90), <=(-($5, $0), 120)), 1, 0)], $f14=[CASE(>(-($5, $0), 120), 1, 0)]) + HiveJoin(condition=[=($3, $13)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $12)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(AND(=($4, $8), =($1, $6)), =($2, $7))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_customer_sk=[$3], ss_store_sk=[$7], ss_ticket_number=[$9]) + HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($3), IS NOT NULL($7), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(sr_returned_date_sk=[$0], sr_item_sk=[$2], sr_customer_sk=[$3], sr_ticket_number=[$9]) + HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($2), IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(9):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 9), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_company_id=[$16], s_street_number=[$18], s_street_name=[$19], s_street_type=[$20], s_suite_number=[$21], s_city=[$22], s_county=[$23], s_state=[$24], s_zip=[$25]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query51.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query51.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query51.q.out new file mode 100644 index 0000000..fed8677 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query51.q.out @@ -0,0 +1,125 @@ +PREHOOK: query: explain cbo +WITH web_v1 as ( +select + ws_item_sk item_sk, d_date, + sum(sum(ws_sales_price)) + over (partition by ws_item_sk order by d_date rows between unbounded preceding and current row) cume_sales +from web_sales + ,date_dim +where ws_sold_date_sk=d_date_sk + and d_month_seq between 1212 and 1212+11 + and ws_item_sk is not NULL +group by ws_item_sk, d_date), +store_v1 as ( +select + ss_item_sk item_sk, d_date, + sum(sum(ss_sales_price)) + over (partition by ss_item_sk order by d_date rows between unbounded preceding and current row) cume_sales +from store_sales + ,date_dim +where ss_sold_date_sk=d_date_sk + and d_month_seq between 1212 and 1212+11 + and ss_item_sk is not NULL +group by ss_item_sk, d_date) + select * +from (select item_sk + ,d_date + ,web_sales + ,store_sales + ,max(web_sales) + over (partition by item_sk order by d_date rows between unbounded preceding and current row) web_cumulative + ,max(store_sales) + over (partition by item_sk order by d_date rows between unbounded preceding and current row) store_cumulative + from (select case when web.item_sk is not null then web.item_sk else store.item_sk end item_sk + ,case when web.d_date is not null then web.d_date else store.d_date end d_date + ,web.cume_sales web_sales + ,store.cume_sales store_sales + from web_v1 web full outer join store_v1 store on (web.item_sk = store.item_sk + and web.d_date = store.d_date) + )x )y +where web_cumulative > store_cumulative +order by item_sk + ,d_date +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@store_sales +PREHOOK: Input: default@web_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +WITH web_v1 as ( +select + ws_item_sk item_sk, d_date, + sum(sum(ws_sales_price)) + over (partition by ws_item_sk order by d_date rows between unbounded preceding and current row) cume_sales +from web_sales + ,date_dim +where ws_sold_date_sk=d_date_sk + and d_month_seq between 1212 and 1212+11 + and ws_item_sk is not NULL +group by ws_item_sk, d_date), +store_v1 as ( +select + ss_item_sk item_sk, d_date, + sum(sum(ss_sales_price)) + over (partition by ss_item_sk order by d_date rows between unbounded preceding and current row) cume_sales +from store_sales + ,date_dim +where ss_sold_date_sk=d_date_sk + and d_month_seq between 1212 and 1212+11 + and ss_item_sk is not NULL +group by ss_item_sk, d_date) + select * +from (select item_sk + ,d_date + ,web_sales + ,store_sales + ,max(web_sales) + over (partition by item_sk order by d_date rows between unbounded preceding and current row) web_cumulative + ,max(store_sales) + over (partition by item_sk order by d_date rows between unbounded preceding and current row) store_cumulative + from (select case when web.item_sk is not null then web.item_sk else store.item_sk end item_sk + ,case when web.d_date is not null then web.d_date else store.d_date end d_date + ,web.cume_sales web_sales + ,store.cume_sales store_sales + from web_v1 web full outer join store_v1 store on (web.item_sk = store.item_sk + and web.d_date = store.d_date) + )x )y +where web_cumulative > store_cumulative +order by item_sk + ,d_date +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@store_sales +POSTHOOK: Input: default@web_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) + HiveProject(item_sk=[$0], d_date=[$1], web_sales=[$2], store_sales=[$3], max_window_0=[$4], max_window_1=[$5]) + HiveFilter(condition=[>($4, $5)]) + HiveProject(item_sk=[CASE(IS NOT NULL($3), $3, $0)], d_date=[CASE(IS NOT NULL($4), $4, $1)], web_sales=[$5], store_sales=[$2], max_window_0=[max($5) OVER (PARTITION BY CASE(IS NOT NULL($3), $3, $0) ORDER BY CASE(IS NOT NULL($4), $4, $1) NULLS LAST ROWS BETWEEN CURRENT ROW AND 2147483647 PRECEDING)], max_window_1=[max($2) OVER (PARTITION BY CASE(IS NOT NULL($3), $3, $0) ORDER BY CASE(IS NOT NULL($4), $4, $1) NULLS LAST ROWS BETWEEN CURRENT ROW AND 2147483647 PRECEDING)]) + HiveJoin(condition=[AND(=($3, $0), =($4, $1))], joinType=[full], algorithm=[none], cost=[not available]) + HiveProject((tok_table_or_col ss_item_sk)=[$0], (tok_table_or_col d_date)=[$1], sum_window_0=[$2]) + HiveProject((tok_table_or_col ss_item_sk)=[$0], (tok_table_or_col d_date)=[$1], sum_window_0=[sum($2) OVER (PARTITION BY $0 ORDER BY $1 NULLS LAST ROWS BETWEEN CURRENT ROW AND 2147483647 PRECEDING)], window_col_0=[$2]) + HiveProject(ss_item_sk=[$0], d_date=[$1], $f2=[$2]) + HiveAggregate(group=[{1, 4}], agg#0=[sum($2)]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_sales_price=[$13]) + HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject((tok_table_or_col ws_item_sk)=[$0], (tok_table_or_col d_date)=[$1], sum_window_0=[$2]) + HiveProject((tok_table_or_col ws_item_sk)=[$0], (tok_table_or_col d_date)=[$1], sum_window_0=[sum($2) OVER (PARTITION BY $0 ORDER BY $1 NULLS LAST ROWS BETWEEN CURRENT ROW AND 2147483647 PRECEDING)], window_col_0=[$2]) + HiveProject(ws_item_sk=[$0], d_date=[$1], $f2=[$2]) + HiveAggregate(group=[{1, 4}], agg#0=[sum($2)]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_sales_price=[$21]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3]) + HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query52.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query52.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query52.q.out new file mode 100644 index 0000000..627b8b0 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query52.q.out @@ -0,0 +1,67 @@ +PREHOOK: query: explain cbo +select dt.d_year + ,item.i_brand_id brand_id + ,item.i_brand brand + ,sum(ss_ext_sales_price) ext_price + 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_manager_id = 1 + and dt.d_moy=12 + and dt.d_year=1998 + group by dt.d_year + ,item.i_brand + ,item.i_brand_id + order by dt.d_year + ,ext_price desc + ,brand_id +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@item +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select dt.d_year + ,item.i_brand_id brand_id + ,item.i_brand brand + ,sum(ss_ext_sales_price) ext_price + 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_manager_id = 1 + and dt.d_moy=12 + and dt.d_year=1998 + group by dt.d_year + ,item.i_brand + ,item.i_brand_id + order by dt.d_year + ,ext_price desc + ,brand_id +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@item +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveProject(d_year=[CAST(1998):INTEGER], brand_id=[$0], brand=[$1], ext_price=[$2]) + HiveSortLimit(sort0=[$2], sort1=[$0], dir0=[DESC-nulls-last], dir1=[ASC], fetch=[100]) + HiveProject(i_brand_id=[$0], i_brand=[$1], $f2=[$2]) + HiveAggregate(group=[{7, 8}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveFilter(condition=[AND(=($8, 12), =($6, 1998), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[dt]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8], i_manager_id=[CAST(1):INTEGER]) + HiveFilter(condition=[AND(=($20, 1), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query53.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query53.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query53.q.out new file mode 100644 index 0000000..56b1ba2 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query53.q.out @@ -0,0 +1,87 @@ +PREHOOK: query: explain cbo +select * from +(select i_manufact_id, +sum(ss_sales_price) sum_sales, +avg(sum(ss_sales_price)) over (partition by i_manufact_id) avg_quarterly_sales +from item, store_sales, date_dim, store +where ss_item_sk = i_item_sk and +ss_sold_date_sk = d_date_sk and +ss_store_sk = s_store_sk and +d_month_seq in (1212,1212+1,1212+2,1212+3,1212+4,1212+5,1212+6,1212+7,1212+8,1212+9,1212+10,1212+11) and +((i_category in ('Books','Children','Electronics') and +i_class in ('personal','portable','reference','self-help') and +i_brand in ('scholaramalgamalg #14','scholaramalgamalg #7', + 'exportiunivamalg #9','scholaramalgamalg #9')) +or(i_category in ('Women','Music','Men') and +i_class in ('accessories','classical','fragrances','pants') and +i_brand in ('amalgimporto #1','edu packscholar #1','exportiimporto #1', + 'importoamalg #1'))) +group by i_manufact_id, d_qoy ) tmp1 +where case when avg_quarterly_sales > 0 + then abs (sum_sales - avg_quarterly_sales)/ avg_quarterly_sales + else null end > 0.1 +order by avg_quarterly_sales, + sum_sales, + i_manufact_id +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@item +PREHOOK: Input: default@store +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select * from +(select i_manufact_id, +sum(ss_sales_price) sum_sales, +avg(sum(ss_sales_price)) over (partition by i_manufact_id) avg_quarterly_sales +from item, store_sales, date_dim, store +where ss_item_sk = i_item_sk and +ss_sold_date_sk = d_date_sk and +ss_store_sk = s_store_sk and +d_month_seq in (1212,1212+1,1212+2,1212+3,1212+4,1212+5,1212+6,1212+7,1212+8,1212+9,1212+10,1212+11) and +((i_category in ('Books','Children','Electronics') and +i_class in ('personal','portable','reference','self-help') and +i_brand in ('scholaramalgamalg #14','scholaramalgamalg #7', + 'exportiunivamalg #9','scholaramalgamalg #9')) +or(i_category in ('Women','Music','Men') and +i_class in ('accessories','classical','fragrances','pants') and +i_brand in ('amalgimporto #1','edu packscholar #1','exportiimporto #1', + 'importoamalg #1'))) +group by i_manufact_id, d_qoy ) tmp1 +where case when avg_quarterly_sales > 0 + then abs (sum_sales - avg_quarterly_sales)/ avg_quarterly_sales + else null end > 0.1 +order by avg_quarterly_sales, + sum_sales, + i_manufact_id +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@item +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$2], sort1=[$1], sort2=[$0], dir0=[ASC], dir1=[ASC], dir2=[ASC], fetch=[100]) + HiveProject((tok_table_or_col i_manufact_id)=[$0], (tok_function sum (tok_table_or_col ss_sales_price))=[$1], avg_window_0=[$2]) + HiveFilter(condition=[CASE(>($2, 0), >(/(ABS(-($1, $2)), $2), 0.1), null)]) + HiveProject((tok_table_or_col i_manufact_id)=[$0], (tok_function sum (tok_table_or_col ss_sales_price))=[$2], avg_window_0=[avg($2) OVER (PARTITION BY $0 ORDER BY $0 NULLS FIRST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) + HiveProject(i_manufact_id=[$0], d_qoy=[$1], $f2=[$2]) + HiveAggregate(group=[{9, 12}], agg#0=[sum($4)]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(s_store_sk=[$0]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_store_sk=[$7], ss_sales_price=[$13]) + HiveFilter(condition=[AND(IS NOT NULL($2), IS NOT NULL($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(i_item_sk=[$0], i_brand=[$8], i_class=[$10], i_category=[$12], i_manufact_id=[$13]) + HiveFilter(condition=[AND(IN($10, _UTF-16LE'personal', _UTF-16LE'portable', _UTF-16LE'reference', _UTF-16LE'self-help', _UTF-16LE'accessories', _UTF-16LE'classical', _UTF-16LE'fragrances', _UTF-16LE'pants'), IN($8, _UTF-16LE'scholaramalgamalg #14', _UTF-16LE'scholaramalgamalg #7', _UTF-16LE'exportiunivamalg #9', _UTF-16LE'scholaramalgamalg #9', _UTF-16LE'amalgimporto #1', _UTF-16LE'edu packscholar #1', _UTF-16LE'exportiimporto #1', _UTF-16LE'importoamalg #1'), IN($12, _UTF-16LE'Books', _UTF-16LE'Children', _UTF-16LE'Electronics', _UTF-16LE'Women', _UTF-16LE'Music', _UTF-16LE'Men'), OR(AND(IN($12, _UTF-16LE'Books', _UTF-16LE'Children', _UTF-16LE'Electronics'), IN($10, _UTF-16LE'personal', _UTF-16LE'portable', _UTF-16LE'reference', _UTF-16LE'self-help'), IN($8, _UTF-16LE'scholaramalgamalg #14', _UTF-16LE'scholaramalgamalg #7', _UTF-16LE'exportiunivamalg #9', _UTF-16LE'scholaramalgamalg #9')), AND(IN($12, _UTF-16LE'Women', _UTF-16LE'Music', _UTF-16LE'Men'), IN($10, _UTF-16LE'accessories', _UTF-16LE'classical', _UTF-16LE'fragrances', _UTF-16LE'pants'), IN($8, _UTF-16LE'amalgimporto #1', _UTF-16LE'edu packscholar #1', _UTF-16LE'exportiimporto #1', _UTF-16LE'importoamalg #1'))), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(d_date_sk=[$0], d_month_seq=[$3], d_qoy=[$10]) + HiveFilter(condition=[AND(IN($3, 1212, 1213, 1214, 1215, 1216, 1217, 1218, 1219, 1220, 1221, 1222, 1223), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query54.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query54.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query54.q.out new file mode 100644 index 0000000..eaf2536 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query54.q.out @@ -0,0 +1,213 @@ +Warning: Shuffle Join MERGEJOIN[271][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product +Warning: Shuffle Join MERGEJOIN[272][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3, $hdt$_4]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[270][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 32' is a cross product +Warning: Shuffle Join MERGEJOIN[273][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product +PREHOOK: query: explain cbo +with my_customers as ( + select distinct c_customer_sk + , c_current_addr_sk + from + ( select cs_sold_date_sk sold_date_sk, + cs_bill_customer_sk customer_sk, + cs_item_sk item_sk + from catalog_sales + union all + select ws_sold_date_sk sold_date_sk, + ws_bill_customer_sk customer_sk, + ws_item_sk item_sk + from web_sales + ) cs_or_ws_sales, + item, + date_dim, + customer + where sold_date_sk = d_date_sk + and item_sk = i_item_sk + and i_category = 'Jewelry' + and i_class = 'consignment' + and c_customer_sk = cs_or_ws_sales.customer_sk + and d_moy = 3 + and d_year = 1999 + ) + , my_revenue as ( + select c_customer_sk, + sum(ss_ext_sales_price) as revenue + from my_customers, + store_sales, + customer_address, + store, + date_dim + where c_current_addr_sk = ca_address_sk + and ca_county = s_county + and ca_state = s_state + and ss_sold_date_sk = d_date_sk + and c_customer_sk = ss_customer_sk + and d_month_seq between (select distinct d_month_seq+1 + from date_dim where d_year = 1999 and d_moy = 3) + and (select distinct d_month_seq+3 + from date_dim where d_year = 1999 and d_moy = 3) + group by c_customer_sk + ) + , segments as + (select cast((revenue/50) as int) as segment + from my_revenue + ) + select segment, count(*) as num_customers, segment*50 as segment_base + from segments + group by segment + order by segment, num_customers + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@catalog_sales +PREHOOK: Input: default@customer +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@item +PREHOOK: Input: default@store +PREHOOK: Input: default@store_sales +PREHOOK: Input: default@web_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +with my_customers as ( + select distinct c_customer_sk + , c_current_addr_sk + from + ( select cs_sold_date_sk sold_date_sk, + cs_bill_customer_sk customer_sk, + cs_item_sk item_sk + from catalog_sales + union all + select ws_sold_date_sk sold_date_sk, + ws_bill_customer_sk customer_sk, + ws_item_sk item_sk + from web_sales + ) cs_or_ws_sales, + item, + date_dim, + customer + where sold_date_sk = d_date_sk + and item_sk = i_item_sk + and i_category = 'Jewelry' + and i_class = 'consignment' + and c_customer_sk = cs_or_ws_sales.customer_sk + and d_moy = 3 + and d_year = 1999 + ) + , my_revenue as ( + select c_customer_sk, + sum(ss_ext_sales_price) as revenue + from my_customers, + store_sales, + customer_address, + store, + date_dim + where c_current_addr_sk = ca_address_sk + and ca_county = s_county + and ca_state = s_state + and ss_sold_date_sk = d_date_sk + and c_customer_sk = ss_customer_sk + and d_month_seq between (select distinct d_month_seq+1 + from date_dim where d_year = 1999 and d_moy = 3) + and (select distinct d_month_seq+3 + from date_dim where d_year = 1999 and d_moy = 3) + group by c_customer_sk + ) + , segments as + (select cast((revenue/50) as int) as segment + from my_revenue + ) + select segment, count(*) as num_customers, segment*50 as segment_base + from segments + group by segment + order by segment, num_customers + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@catalog_sales +POSTHOOK: Input: default@customer +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@item +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_sales +POSTHOOK: Input: default@web_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) + HiveProject(segment=[$0], num_customers=[$1], segment_base=[*($0, 50)]) + HiveAggregate(group=[{0}], agg#0=[count()]) + HiveProject(segment=[CAST(/($1, CAST(50):DECIMAL(10, 0))):INTEGER]) + HiveAggregate(group=[{0}], agg#0=[sum($1)]) + HiveFilter(condition=[BETWEEN(false, $2, $3, $4)]) + HiveProject(c_customer_sk=[$0], ss_ext_sales_price=[$4], d_month_seq=[$11], _o__c0=[$13], $f0=[$14]) + HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$10], $f1=[$11], ss_sold_date_sk=[$0], ss_customer_sk=[$1], ss_ext_sales_price=[$2], ca_address_sk=[$5], ca_county=[$6], ca_state=[$7], s_county=[$8], s_state=[$9], d_date_sk=[$3], d_month_seq=[$4], cnt=[$12], $f00=[$13]) + HiveJoin(condition=[true], joinType=[left], algorithm=[none], cost=[not available]) + HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($10, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_sales_price=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_month_seq=[$3]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(ca_address_sk=[$0], ca_county=[$1], ca_state=[$2], s_county=[$3], s_state=[$4], c_customer_sk=[$5], c_current_addr_sk=[$6]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[AND(=($1, $3), =($2, $4))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_county=[$7], ca_state=[$8]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($8))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(s_county=[$23], s_state=[$24]) + HiveFilter(condition=[AND(IS NOT NULL($23), IS NOT NULL($24))]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$1]) + HiveAggregate(group=[{0, 1}]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($4))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($2, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_item_sk=[$2]) + HiveUnion(all=[true]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_item_sk=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0), IS NOT NULL($3))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(sold_date_sk=[$0], customer_sk=[$4], item_sk=[$3]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0), IS NOT NULL($4))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(3):INTEGER]) + HiveFilter(condition=[AND(=($8, 3), =($6, 1999), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(i_item_sk=[$0], i_class=[CAST(_UTF-16LE'consignment'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], i_category=[CAST(_UTF-16LE'Jewelry'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + HiveFilter(condition=[AND(=($12, _UTF-16LE'Jewelry'), =($10, _UTF-16LE'consignment'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(cnt=[$0]) + HiveFilter(condition=[<=(sq_count_check($0), 1)]) + HiveProject(cnt=[$0]) + HiveAggregate(group=[{}], cnt=[COUNT()]) + HiveProject($f0=[$0]) + HiveAggregate(group=[{0}]) + HiveProject($f0=[+($3, 1)]) + HiveFilter(condition=[AND(=($6, 1999), =($8, 3))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject($f0=[$0]) + HiveAggregate(group=[{0}]) + HiveProject($f0=[+($3, 1)]) + HiveFilter(condition=[AND(=($6, 1999), =($8, 3))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[true], joinType=[right], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0]) + HiveAggregate(group=[{0}]) + HiveProject($f0=[+($3, 3)]) + HiveFilter(condition=[AND(=($6, 1999), =($8, 3))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(cnt=[$0]) + HiveFilter(condition=[<=(sq_count_check($0), 1)]) + HiveProject(cnt=[$0]) + HiveAggregate(group=[{}], cnt=[COUNT()]) + HiveProject($f0=[$0]) + HiveAggregate(group=[{0}]) + HiveProject($f0=[+($3, 3)]) + HiveFilter(condition=[AND(=($6, 1999), =($8, 3))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query55.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query55.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query55.q.out new file mode 100644 index 0000000..4182de0 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query55.q.out @@ -0,0 +1,51 @@ +PREHOOK: query: explain cbo +select i_brand_id brand_id, i_brand brand, + sum(ss_ext_sales_price) ext_price + from date_dim, store_sales, item + where d_date_sk = ss_sold_date_sk + and ss_item_sk = i_item_sk + and i_manager_id=36 + and d_moy=12 + and d_year=2001 + group by i_brand, i_brand_id + order by ext_price desc, i_brand_id +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@item +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select i_brand_id brand_id, i_brand brand, + sum(ss_ext_sales_price) ext_price + from date_dim, store_sales, item + where d_date_sk = ss_sold_date_sk + and ss_item_sk = i_item_sk + and i_manager_id=36 + and d_moy=12 + and d_year=2001 + group by i_brand, i_brand_id + order by ext_price desc, i_brand_id +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@item +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveProject(brand_id=[$0], brand=[$1], ext_price=[$2]) + HiveSortLimit(sort0=[$2], sort1=[$3], dir0=[DESC-nulls-last], dir1=[ASC], fetch=[100]) + HiveProject(brand_id=[$0], brand=[$1], ext_price=[$2], (tok_table_or_col i_brand_id)=[$0]) + HiveAggregate(group=[{7, 8}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER], d_moy=[CAST(12):INTEGER]) + HiveFilter(condition=[AND(=($8, 12), =($6, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_brand=[$8], i_manager_id=[CAST(36):INTEGER]) + HiveFilter(condition=[AND(=($20, 36), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query56.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query56.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query56.q.out new file mode 100644 index 0000000..579d06a --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query56.q.out @@ -0,0 +1,224 @@ +PREHOOK: query: explain cbo +with ss as ( + select i_item_id,sum(ss_ext_sales_price) total_sales + from + store_sales, + date_dim, + customer_address, + item + where i_item_id in (select + i_item_id +from item +where i_color in ('orchid','chiffon','lace')) + and ss_item_sk = i_item_sk + and ss_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 1 + and ss_addr_sk = ca_address_sk + and ca_gmt_offset = -8 + group by i_item_id), + cs as ( + select i_item_id,sum(cs_ext_sales_price) total_sales + from + catalog_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from item +where i_color in ('orchid','chiffon','lace')) + and cs_item_sk = i_item_sk + and cs_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 1 + and cs_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -8 + group by i_item_id), + ws as ( + select i_item_id,sum(ws_ext_sales_price) total_sales + from + web_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from item +where i_color in ('orchid','chiffon','lace')) + and ws_item_sk = i_item_sk + and ws_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 1 + and ws_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -8 + group by i_item_id) + select i_item_id ,sum(total_sales) total_sales + from (select * from ss + union all + select * from cs + union all + select * from ws) tmp1 + group by i_item_id + order by total_sales + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@catalog_sales +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@item +PREHOOK: Input: default@store_sales +PREHOOK: Input: default@web_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +with ss as ( + select i_item_id,sum(ss_ext_sales_price) total_sales + from + store_sales, + date_dim, + customer_address, + item + where i_item_id in (select + i_item_id +from item +where i_color in ('orchid','chiffon','lace')) + and ss_item_sk = i_item_sk + and ss_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 1 + and ss_addr_sk = ca_address_sk + and ca_gmt_offset = -8 + group by i_item_id), + cs as ( + select i_item_id,sum(cs_ext_sales_price) total_sales + from + catalog_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from item +where i_color in ('orchid','chiffon','lace')) + and cs_item_sk = i_item_sk + and cs_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 1 + and cs_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -8 + group by i_item_id), + ws as ( + select i_item_id,sum(ws_ext_sales_price) total_sales + from + web_sales, + date_dim, + customer_address, + item + where + i_item_id in (select + i_item_id +from item +where i_color in ('orchid','chiffon','lace')) + and ws_item_sk = i_item_sk + and ws_sold_date_sk = d_date_sk + and d_year = 2000 + and d_moy = 1 + and ws_bill_addr_sk = ca_address_sk + and ca_gmt_offset = -8 + group by i_item_id) + select i_item_id ,sum(total_sales) total_sales + from (select * from ss + union all + select * from cs + union all + select * from ws) tmp1 + group by i_item_id + order by total_sales + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@catalog_sales +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@item +POSTHOOK: Input: default@store_sales +POSTHOOK: Input: default@web_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$1], dir0=[ASC], fetch=[100]) + HiveProject(i_item_id=[$0], $f1=[$1]) + HiveAggregate(group=[{0}], agg#0=[sum($1)]) + HiveProject(i_item_id=[$0], $f1=[$1]) + HiveUnion(all=[true]) + HiveProject(i_item_id=[$0], $f1=[$1]) + HiveAggregate(group=[{1}], agg#0=[sum($8)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_item_id=[$1]) + HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(i_item_id=[$0]) + HiveAggregate(group=[{1}]) + HiveFilter(condition=[AND(IN($17, _UTF-16LE'orchid', _UTF-16LE'chiffon', _UTF-16LE'lace'), IS NOT NULL($1))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], ss_sold_date_sk=[$2], ss_item_sk=[$3], ss_addr_sk=[$4], ss_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) + HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-8):DECIMAL(5, 2)]) + HiveFilter(condition=[AND(=($11, -8), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_addr_sk=[$6], ss_ext_sales_price=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6), IS NOT NULL($2))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(1):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 1), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(i_item_id=[$0], $f1=[$1]) + HiveAggregate(group=[{1}], agg#0=[sum($8)]) + HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_item_id=[$1]) + HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(i_item_id=[$0]) + HiveAggregate(group=[{1}]) + HiveFilter(condition=[AND(IN($17, _UTF-16LE'orchid', _UTF-16LE'chiffon', _UTF-16LE'lace'), IS NOT NULL($1))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], cs_sold_date_sk=[$2], cs_bill_addr_sk=[$3], cs_item_sk=[$4], cs_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-8):DECIMAL(5, 2)]) + HiveFilter(condition=[AND(=($11, -8), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_addr_sk=[$6], cs_item_sk=[$15], cs_ext_sales_price=[$23]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($6), IS NOT NULL($15))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(1):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 1), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(i_item_id=[$0], $f1=[$1]) + HiveAggregate(group=[{1}], agg#0=[sum($8)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_item_id=[$1]) + HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(i_item_id=[$0]) + HiveAggregate(group=[{1}]) + HiveFilter(condition=[AND(IN($17, _UTF-16LE'orchid', _UTF-16LE'chiffon', _UTF-16LE'lace'), IS NOT NULL($1))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(ca_address_sk=[$0], ca_gmt_offset=[$1], ws_sold_date_sk=[$2], ws_item_sk=[$3], ws_bill_addr_sk=[$4], ws_ext_sales_price=[$5], d_date_sk=[$6], d_year=[$7], d_moy=[$8]) + HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_gmt_offset=[CAST(-8):DECIMAL(5, 2)]) + HiveFilter(condition=[AND(=($11, -8), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_bill_addr_sk=[$7], ws_ext_sales_price=[$23]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($3))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(1):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 1), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) +
