http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query42.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query42.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query42.q.out new file mode 100644 index 0000000..8f2f79f --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query42.q.out @@ -0,0 +1,68 @@ +PREHOOK: query: explain cbo +select dt.d_year + ,item.i_category_id + ,item.i_category + ,sum(ss_ext_sales_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_category_id + ,item.i_category + order by sum(ss_ext_sales_price) desc,dt.d_year + ,item.i_category_id + ,item.i_category +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_category_id + ,item.i_category + ,sum(ss_ext_sales_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_category_id + ,item.i_category + order by sum(ss_ext_sales_price) desc,dt.d_year + ,item.i_category_id + ,item.i_category +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: +HiveSortLimit(fetch=[100]) + HiveProject(d_year=[CAST(1998):INTEGER], i_category_id=[$0], i_category=[$1], _o__c3=[$2]) + HiveSortLimit(sort0=[$3], sort1=[$0], sort2=[$1], dir0=[DESC-nulls-last], dir1=[ASC], dir2=[ASC]) + HiveProject(i_category_id=[$0], i_category=[$1], _o__c3=[$2], (tok_function sum (tok_table_or_col ss_ext_sales_price))=[$2]) + HiveAggregate(group=[{5, 6}], agg#0=[sum($2)]) + HiveJoin(condition=[=($1, $4)], 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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($8, 12), =($6, 1998))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[dt]) + HiveProject(i_item_sk=[$0], i_category_id=[$11], i_category=[$12]) + HiveFilter(condition=[=($20, 1)]) + 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/constraints/cbo_query43.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query43.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query43.q.out new file mode 100644 index 0000000..6b21ee4 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query43.q.out @@ -0,0 +1,61 @@ +PREHOOK: query: explain cbo +select s_store_name, s_store_id, + sum(case when (d_day_name='Sunday') then ss_sales_price else null end) sun_sales, + sum(case when (d_day_name='Monday') then ss_sales_price else null end) mon_sales, + sum(case when (d_day_name='Tuesday') then ss_sales_price else null end) tue_sales, + sum(case when (d_day_name='Wednesday') then ss_sales_price else null end) wed_sales, + sum(case when (d_day_name='Thursday') then ss_sales_price else null end) thu_sales, + sum(case when (d_day_name='Friday') then ss_sales_price else null end) fri_sales, + sum(case when (d_day_name='Saturday') then ss_sales_price else null end) sat_sales + from date_dim, store_sales, store + where d_date_sk = ss_sold_date_sk and + s_store_sk = ss_store_sk and + s_gmt_offset = -6 and + d_year = 1998 + group by s_store_name, s_store_id + order by s_store_name, s_store_id,sun_sales,mon_sales,tue_sales,wed_sales,thu_sales,fri_sales,sat_sales + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@store +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select s_store_name, s_store_id, + sum(case when (d_day_name='Sunday') then ss_sales_price else null end) sun_sales, + sum(case when (d_day_name='Monday') then ss_sales_price else null end) mon_sales, + sum(case when (d_day_name='Tuesday') then ss_sales_price else null end) tue_sales, + sum(case when (d_day_name='Wednesday') then ss_sales_price else null end) wed_sales, + sum(case when (d_day_name='Thursday') then ss_sales_price else null end) thu_sales, + sum(case when (d_day_name='Friday') then ss_sales_price else null end) fri_sales, + sum(case when (d_day_name='Saturday') then ss_sales_price else null end) sat_sales + from date_dim, store_sales, store + where d_date_sk = ss_sold_date_sk and + s_store_sk = ss_store_sk and + s_gmt_offset = -6 and + d_year = 1998 + group by s_store_name, s_store_id + order by s_store_name, s_store_id,sun_sales,mon_sales,tue_sales,wed_sales,thu_sales,fri_sales,sat_sales + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@store +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=[$8], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC], dir6=[ASC], dir7=[ASC], dir8=[ASC], fetch=[100]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f8=[$8]) + HiveAggregate(group=[{0, 1}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)], agg#4=[sum($6)], agg#5=[sum($7)], agg#6=[sum($8)]) + HiveProject($f0=[$13], $f1=[$12], $f2=[CASE($4, $2, null)], $f3=[CASE($5, $2, null)], $f4=[CASE($6, $2, null)], $f5=[CASE($7, $2, null)], $f6=[CASE($8, $2, null)], $f7=[CASE($9, $2, null)], $f8=[CASE($10, $2, null)]) + HiveJoin(condition=[=($11, $1)], 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_store_sk=[$7], ss_sales_price=[$13]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], ==[=($14, _UTF-16LE'Sunday')], =2=[=($14, _UTF-16LE'Monday')], =3=[=($14, _UTF-16LE'Tuesday')], =4=[=($14, _UTF-16LE'Wednesday')], =5=[=($14, _UTF-16LE'Thursday')], =6=[=($14, _UTF-16LE'Friday')], =7=[=($14, _UTF-16LE'Saturday')]) + HiveFilter(condition=[=($6, 1998)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5]) + HiveFilter(condition=[=($27, -6)]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query44.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query44.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query44.q.out new file mode 100644 index 0000000..8cc89f6 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query44.q.out @@ -0,0 +1,113 @@ +Warning: Shuffle Join MERGEJOIN[101][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 8' is a cross product +PREHOOK: query: explain cbo +select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing +from(select * + from (select item_sk,rank() over (order by rank_col asc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V1)V11 + where rnk < 11) asceding, + (select * + from (select item_sk,rank() over (order by rank_col desc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V2)V21 + where rnk < 11) descending, +item i1, +item i2 +where asceding.rnk = descending.rnk + and i1.i_item_sk=asceding.item_sk + and i2.i_item_sk=descending.item_sk +order by asceding.rnk +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@item +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select asceding.rnk, i1.i_product_name best_performing, i2.i_product_name worst_performing +from(select * + from (select item_sk,rank() over (order by rank_col asc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V1)V11 + where rnk < 11) asceding, + (select * + from (select item_sk,rank() over (order by rank_col desc) rnk + from (select ss_item_sk item_sk,avg(ss_net_profit) rank_col + from store_sales ss1 + where ss_store_sk = 410 + group by ss_item_sk + having avg(ss_net_profit) > 0.9*(select avg(ss_net_profit) rank_col + from store_sales + where ss_store_sk = 410 + and ss_hdemo_sk is null + group by ss_store_sk))V2)V21 + where rnk < 11) descending, +item i1, +item i2 +where asceding.rnk = descending.rnk + and i1.i_item_sk=asceding.item_sk + and i2.i_item_sk=descending.item_sk +order by asceding.rnk +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@item +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) + HiveProject(rnk=[$3], best_performing=[$1], worst_performing=[$5]) + HiveJoin(condition=[=($3, $7)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_product_name=[$21]) + HiveTableScan(table=[[default, item]], table:alias=[i1]) + HiveProject(item_sk=[$0], rank_window_0=[$1]) + HiveFilter(condition=[<($1, 11)]) + HiveProject(item_sk=[$0], rank_window_0=[rank() OVER (PARTITION BY 0 ORDER BY $1 NULLS FIRST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) + HiveJoin(condition=[>($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f1=[/($1, $2)]) + HiveAggregate(group=[{2}], agg#0=[sum($22)], agg#1=[count($22)]) + HiveFilter(condition=[=($7, 410)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[ss1]) + HiveProject(*=[*(0.9, /($1, $2))]) + HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[count($1)]) + HiveProject($f0=[true], $f1=[$22]) + HiveFilter(condition=[AND(=($7, 410), IS NULL($5))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(i_item_sk=[$0], i_product_name=[$1], item_sk=[$2], rank_window_0=[$3]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_product_name=[$21]) + HiveTableScan(table=[[default, item]], table:alias=[i2]) + HiveProject(item_sk=[$0], rank_window_0=[$1]) + HiveFilter(condition=[<($1, 11)]) + HiveProject(item_sk=[$0], rank_window_0=[rank() OVER (PARTITION BY 0 ORDER BY $1 DESC NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) + HiveJoin(condition=[>($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f1=[/($1, $2)]) + HiveAggregate(group=[{2}], agg#0=[sum($22)], agg#1=[count($22)]) + HiveFilter(condition=[=($7, 410)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[ss1]) + HiveProject(*=[*(0.9, /($1, $2))]) + HiveAggregate(group=[{0}], agg#0=[sum($1)], agg#1=[count($1)]) + HiveProject($f0=[true], $f1=[$22]) + HiveFilter(condition=[AND(=($7, 410), IS NULL($5))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query45.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query45.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query45.q.out new file mode 100644 index 0000000..85f8116 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query45.q.out @@ -0,0 +1,81 @@ +PREHOOK: query: explain cbo +select ca_zip, ca_county, sum(ws_sales_price) + from web_sales, customer, customer_address, date_dim, item + where ws_bill_customer_sk = c_customer_sk + and c_current_addr_sk = ca_address_sk + and ws_item_sk = i_item_sk + and ( substr(ca_zip,1,5) in ('85669', '86197','88274','83405','86475', '85392', '85460', '80348', '81792') + or + i_item_id in (select i_item_id + from item + where i_item_sk in (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) + ) + ) + and ws_sold_date_sk = d_date_sk + and d_qoy = 2 and d_year = 2000 + group by ca_zip, ca_county + order by ca_zip, ca_county + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@customer +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@item +PREHOOK: Input: default@web_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select ca_zip, ca_county, sum(ws_sales_price) + from web_sales, customer, customer_address, date_dim, item + where ws_bill_customer_sk = c_customer_sk + and c_current_addr_sk = ca_address_sk + and ws_item_sk = i_item_sk + and ( substr(ca_zip,1,5) in ('85669', '86197','88274','83405','86475', '85392', '85460', '80348', '81792') + or + i_item_id in (select i_item_id + from item + where i_item_sk in (2, 3, 5, 7, 11, 13, 17, 19, 23, 29) + ) + ) + and ws_sold_date_sk = d_date_sk + and d_qoy = 2 and d_year = 2000 + group by ca_zip, ca_county + order by ca_zip, ca_county + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@item +POSTHOOK: Input: default@web_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100]) + HiveProject(ca_zip=[$1], ca_county=[$0], $f2=[$2]) + HiveAggregate(group=[{7, 8}], agg#0=[sum($3)]) + HiveFilter(condition=[OR(IN(substr($8, 1, 5), _UTF-16LE'85669', _UTF-16LE'86197', _UTF-16LE'88274', _UTF-16LE'83405', _UTF-16LE'86475', _UTF-16LE'85392', _UTF-16LE'85460', _UTF-16LE'80348', _UTF-16LE'81792'), IS NOT NULL($15))]) + HiveProject(ws_sold_date_sk=[$9], ws_item_sk=[$10], ws_bill_customer_sk=[$11], ws_sales_price=[$12], c_customer_sk=[$0], c_current_addr_sk=[$1], ca_address_sk=[$2], ca_county=[$3], ca_zip=[$4], d_date_sk=[$13], d_year=[$14], d_qoy=[$15], i_item_sk=[$5], i_item_id=[$6], i_item_id0=[$7], i1160=[$8]) + HiveJoin(condition=[=($11, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4]) + HiveFilter(condition=[IS NOT NULL($4)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveProject(ca_address_sk=[$0], ca_county=[$7], ca_zip=[$9]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_id0=[$2], i1160=[$3], ws_sold_date_sk=[$4], ws_item_sk=[$5], ws_bill_customer_sk=[$6], ws_sales_price=[$7], d_date_sk=[$8], d_year=[$9], d_qoy=[$10]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $2)], joinType=[left], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_item_id=[$1]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(i_item_id=[$0], i1160=[true]) + HiveAggregate(group=[{1}]) + HiveFilter(condition=[IN($0, 2, 3, 5, 7, 11, 13, 17, 19, 23, 29)]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$1], ws_bill_customer_sk=[$2], ws_sales_price=[$3], d_date_sk=[$4], d_year=[$5], d_qoy=[$6]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_bill_customer_sk=[$4], ws_sales_price=[$21]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_qoy=[CAST(2):INTEGER]) + HiveFilter(condition=[AND(=($10, 2), =($6, 2000))]) + 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/constraints/cbo_query46.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query46.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query46.q.out new file mode 100644 index 0000000..df36f9b --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query46.q.out @@ -0,0 +1,113 @@ +PREHOOK: query: explain cbo +select c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + ,amt,profit + from + (select ss_ticket_number + ,ss_customer_sk + ,ca_city bought_city + ,sum(ss_coupon_amt) amt + ,sum(ss_net_profit) profit + from store_sales,date_dim,store,household_demographics,customer_address + where store_sales.ss_sold_date_sk = date_dim.d_date_sk + and store_sales.ss_store_sk = store.s_store_sk + and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk + and store_sales.ss_addr_sk = customer_address.ca_address_sk + and (household_demographics.hd_dep_count = 2 or + household_demographics.hd_vehicle_count= 1) + and date_dim.d_dow in (6,0) + and date_dim.d_year in (1998,1998+1,1998+2) + and store.s_city in ('Cedar Grove','Wildwood','Union','Salem','Highland Park') + group by ss_ticket_number,ss_customer_sk,ss_addr_sk,ca_city) dn,customer,customer_address current_addr + where ss_customer_sk = c_customer_sk + and customer.c_current_addr_sk = current_addr.ca_address_sk + and current_addr.ca_city <> bought_city + order by c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@customer +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@household_demographics +PREHOOK: Input: default@store +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + ,amt,profit + from + (select ss_ticket_number + ,ss_customer_sk + ,ca_city bought_city + ,sum(ss_coupon_amt) amt + ,sum(ss_net_profit) profit + from store_sales,date_dim,store,household_demographics,customer_address + where store_sales.ss_sold_date_sk = date_dim.d_date_sk + and store_sales.ss_store_sk = store.s_store_sk + and store_sales.ss_hdemo_sk = household_demographics.hd_demo_sk + and store_sales.ss_addr_sk = customer_address.ca_address_sk + and (household_demographics.hd_dep_count = 2 or + household_demographics.hd_vehicle_count= 1) + and date_dim.d_dow in (6,0) + and date_dim.d_year in (1998,1998+1,1998+2) + and store.s_city in ('Cedar Grove','Wildwood','Union','Salem','Highland Park') + group by ss_ticket_number,ss_customer_sk,ss_addr_sk,ca_city) dn,customer,customer_address current_addr + where ss_customer_sk = c_customer_sk + and customer.c_current_addr_sk = current_addr.ca_address_sk + and current_addr.ca_city <> bought_city + order by c_last_name + ,c_first_name + ,ca_city + ,bought_city + ,ss_ticket_number + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@household_demographics +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], fetch=[100]) + HiveProject(c_last_name=[$3], c_first_name=[$2], ca_city=[$5], bought_city=[$8], ss_ticket_number=[$6], amt=[$9], profit=[$10]) + HiveJoin(condition=[AND(<>($5, $8), =($7, $0))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_addr_sk=[$4], c_first_name=[$8], c_last_name=[$9]) + HiveFilter(condition=[IS NOT NULL($4)]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveProject(ca_address_sk=[$0], ca_city=[$6]) + HiveTableScan(table=[[default, customer_address]], table:alias=[current_addr]) + HiveProject(ss_ticket_number=[$3], ss_customer_sk=[$1], bought_city=[$0], amt=[$4], profit=[$5]) + HiveAggregate(group=[{1, 3, 5, 7}], agg#0=[sum($8)], agg#1=[sum($9)]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_city=[$6]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($2, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($4, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_ticket_number=[$9], ss_coupon_amt=[$19], ss_net_profit=[$22]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($5), IS NOT NULL($6), IS NOT NULL($3))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(IN($7, 6, 0), IN($6, 1998, 1999, 2000))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(s_store_sk=[$0]) + HiveFilter(condition=[IN($22, _UTF-16LE'Cedar Grove', _UTF-16LE'Wildwood', _UTF-16LE'Union', _UTF-16LE'Salem', _UTF-16LE'Highland Park')]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject(hd_demo_sk=[$0]) + HiveFilter(condition=[OR(=($3, 2), =($4, 1))]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query47.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query47.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query47.q.out new file mode 100644 index 0000000..3c90232 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query47.q.out @@ -0,0 +1,177 @@ +PREHOOK: query: explain cbo +with v1 as( + select i_category, i_brand, + s_store_name, s_company_name, + d_year, d_moy, + sum(ss_sales_price) sum_sales, + avg(sum(ss_sales_price)) over + (partition by i_category, i_brand, + s_store_name, s_company_name, d_year) + avg_monthly_sales, + rank() over + (partition by i_category, i_brand, + s_store_name, s_company_name + order by d_year, d_moy) rn + 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_year = 2000 or + ( d_year = 2000-1 and d_moy =12) or + ( d_year = 2000+1 and d_moy =1) + ) + group by i_category, i_brand, + s_store_name, s_company_name, + d_year, d_moy), + v2 as( + select v1.i_category + ,v1.d_year, v1.d_moy + ,v1.avg_monthly_sales + ,v1.sum_sales, v1_lag.sum_sales psum, v1_lead.sum_sales nsum + from v1, v1 v1_lag, v1 v1_lead + where v1.i_category = v1_lag.i_category and + v1.i_category = v1_lead.i_category and + v1.i_brand = v1_lag.i_brand and + v1.i_brand = v1_lead.i_brand and + v1.s_store_name = v1_lag.s_store_name and + v1.s_store_name = v1_lead.s_store_name and + v1.s_company_name = v1_lag.s_company_name and + v1.s_company_name = v1_lead.s_company_name and + v1.rn = v1_lag.rn + 1 and + v1.rn = v1_lead.rn - 1) + select * + from v2 + where d_year = 2000 and + avg_monthly_sales > 0 and + case when avg_monthly_sales > 0 then abs(sum_sales - avg_monthly_sales) / avg_monthly_sales else null end > 0.1 + order by sum_sales - avg_monthly_sales, 3 + 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 +with v1 as( + select i_category, i_brand, + s_store_name, s_company_name, + d_year, d_moy, + sum(ss_sales_price) sum_sales, + avg(sum(ss_sales_price)) over + (partition by i_category, i_brand, + s_store_name, s_company_name, d_year) + avg_monthly_sales, + rank() over + (partition by i_category, i_brand, + s_store_name, s_company_name + order by d_year, d_moy) rn + 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_year = 2000 or + ( d_year = 2000-1 and d_moy =12) or + ( d_year = 2000+1 and d_moy =1) + ) + group by i_category, i_brand, + s_store_name, s_company_name, + d_year, d_moy), + v2 as( + select v1.i_category + ,v1.d_year, v1.d_moy + ,v1.avg_monthly_sales + ,v1.sum_sales, v1_lag.sum_sales psum, v1_lead.sum_sales nsum + from v1, v1 v1_lag, v1 v1_lead + where v1.i_category = v1_lag.i_category and + v1.i_category = v1_lead.i_category and + v1.i_brand = v1_lag.i_brand and + v1.i_brand = v1_lead.i_brand and + v1.s_store_name = v1_lag.s_store_name and + v1.s_store_name = v1_lead.s_store_name and + v1.s_company_name = v1_lag.s_company_name and + v1.s_company_name = v1_lead.s_company_name and + v1.rn = v1_lag.rn + 1 and + v1.rn = v1_lead.rn - 1) + select * + from v2 + where d_year = 2000 and + avg_monthly_sales > 0 and + case when avg_monthly_sales > 0 then abs(sum_sales - avg_monthly_sales) / avg_monthly_sales else null end > 0.1 + order by sum_sales - avg_monthly_sales, 3 + 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: +HiveProject(i_category=[$0], d_year=[$1], d_moy=[$2], avg_monthly_sales=[$3], sum_sales=[$4], psum=[$5], nsum=[$6]) + HiveSortLimit(sort0=[$7], sort1=[$2], dir0=[ASC], dir1=[ASC], fetch=[100]) + HiveProject(i_category=[$12], d_year=[$16], d_moy=[$17], avg_monthly_sales=[$19], sum_sales=[$18], psum=[$10], nsum=[$4], (- (tok_table_or_col sum_sales) (tok_table_or_col avg_monthly_sales))=[-($18, $19)]) + HiveJoin(condition=[AND(AND(AND(AND(=($12, $0), =($13, $1)), =($14, $2)), =($15, $3)), =($20, $5))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col s_store_name)=[$2], (tok_table_or_col s_company_name)=[$3], (tok_function sum (tok_table_or_col ss_sales_price))=[$4], -=[-($5, 1)]) + HiveFilter(condition=[IS NOT NULL($5)]) + HiveProject((tok_table_or_col i_category)=[$1], (tok_table_or_col i_brand)=[$0], (tok_table_or_col s_store_name)=[$4], (tok_table_or_col s_company_name)=[$5], (tok_function sum (tok_table_or_col ss_sales_price))=[$6], rank_window_1=[rank() OVER (PARTITION BY $1, $0, $4, $5 ORDER BY $2 NULLS LAST, $3 NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) + HiveProject(i_brand=[$0], i_category=[$1], d_year=[$2], d_moy=[$3], s_store_name=[$4], s_company_name=[$5], $f6=[$6]) + HiveAggregate(group=[{1, 2, 8, 9, 11, 12}], agg#0=[sum($6)]) + HiveJoin(condition=[=($5, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand=[$8], i_category=[$12]) + HiveFilter(condition=[AND(IS NOT NULL($12), IS NOT NULL($8))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($0, $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($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6], d_moy=[$8]) + HiveFilter(condition=[AND(IN($6, 2000, 1999, 2001), OR(=($6, 2000), IN(ROW($6, $8), ROW(1999, 12), ROW(2001, 1))))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_company_name=[$17]) + HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($17))]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveJoin(condition=[AND(AND(AND(AND(=($6, $0), =($7, $1)), =($8, $2)), =($9, $3)), =($14, $5))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col s_store_name)=[$2], (tok_table_or_col s_company_name)=[$3], (tok_function sum (tok_table_or_col ss_sales_price))=[$4], +=[+($5, 1)]) + HiveFilter(condition=[IS NOT NULL($5)]) + HiveProject((tok_table_or_col i_category)=[$1], (tok_table_or_col i_brand)=[$0], (tok_table_or_col s_store_name)=[$4], (tok_table_or_col s_company_name)=[$5], (tok_function sum (tok_table_or_col ss_sales_price))=[$6], rank_window_1=[rank() OVER (PARTITION BY $1, $0, $4, $5 ORDER BY $2 NULLS LAST, $3 NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) + HiveProject(i_brand=[$0], i_category=[$1], d_year=[$2], d_moy=[$3], s_store_name=[$4], s_company_name=[$5], $f6=[$6]) + HiveAggregate(group=[{1, 2, 8, 9, 11, 12}], agg#0=[sum($6)]) + HiveJoin(condition=[=($5, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand=[$8], i_category=[$12]) + HiveFilter(condition=[AND(IS NOT NULL($12), IS NOT NULL($8))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($0, $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($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6], d_moy=[$8]) + HiveFilter(condition=[AND(IN($6, 2000, 1999, 2001), OR(=($6, 2000), IN(ROW($6, $8), ROW(1999, 12), ROW(2001, 1))))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_company_name=[$17]) + HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($17))]) + HiveTableScan(table=[[default, store]], table:alias=[store]) + HiveProject((tok_table_or_col i_category)=[$0], (tok_table_or_col i_brand)=[$1], (tok_table_or_col s_store_name)=[$2], (tok_table_or_col s_company_name)=[$3], (tok_table_or_col d_year)=[$4], (tok_table_or_col d_moy)=[$5], (tok_function sum (tok_table_or_col ss_sales_price))=[$6], avg_window_0=[$7], rank_window_1=[$8]) + HiveFilter(condition=[AND(=($4, 2000), >($7, 0), CASE(>($7, 0), >(/(ABS(-($6, $7)), $7), 0.1), null), IS NOT NULL($8))]) + HiveProject((tok_table_or_col i_category)=[$1], (tok_table_or_col i_brand)=[$0], (tok_table_or_col s_store_name)=[$4], (tok_table_or_col s_company_name)=[$5], (tok_table_or_col d_year)=[$2], (tok_table_or_col d_moy)=[$3], (tok_function sum (tok_table_or_col ss_sales_price))=[$6], avg_window_0=[avg($6) OVER (PARTITION BY $1, $0, $4, $5, $2 ORDER BY $1 NULLS FIRST, $0 NULLS FIRST, $4 NULLS FIRST, $5 NULLS FIRST, $2 NULLS FIRST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)], rank_window_1=[rank() OVER (PARTITION BY $1, $0, $4, $5 ORDER BY $2 NULLS LAST, $3 NULLS LAST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING)]) + HiveProject(i_brand=[$0], i_category=[$1], d_year=[$2], d_moy=[$3], s_store_name=[$4], s_company_name=[$5], $f6=[$6]) + HiveAggregate(group=[{1, 2, 8, 9, 11, 12}], agg#0=[sum($6)]) + HiveJoin(condition=[=($5, $10)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand=[$8], i_category=[$12]) + HiveFilter(condition=[AND(IS NOT NULL($12), IS NOT NULL($8))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($0, $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($0), IS NOT NULL($7))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6], d_moy=[$8]) + HiveFilter(condition=[AND(IN($6, 2000, 1999, 2001), OR(=($6, 2000), IN(ROW($6, $8), ROW(1999, 12), ROW(2001, 1))))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(s_store_sk=[$0], s_store_name=[$5], s_company_name=[$17]) + HiveFilter(condition=[AND(IS NOT NULL($5), IS NOT NULL($17))]) + 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/constraints/cbo_query48.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query48.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query48.q.out new file mode 100644 index 0000000..12d5934 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query48.q.out @@ -0,0 +1,160 @@ +PREHOOK: query: explain cbo +select sum (ss_quantity) + from store_sales, store, customer_demographics, customer_address, date_dim + where s_store_sk = ss_store_sk + and ss_sold_date_sk = d_date_sk and d_year = 1998 + and + ( + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 100.00 and 150.00 + ) + or + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 50.00 and 100.00 + ) + or + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 150.00 and 200.00 + ) + ) + and + ( + ( + ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('KY', 'GA', 'NM') + and ss_net_profit between 0 and 2000 + ) + or + (ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('MT', 'OR', 'IN') + and ss_net_profit between 150 and 3000 + ) + or + (ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('WI', 'MO', 'WV') + and ss_net_profit between 50 and 25000 + ) + ) +PREHOOK: type: QUERY +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@customer_demographics +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@store +PREHOOK: Input: default@store_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select sum (ss_quantity) + from store_sales, store, customer_demographics, customer_address, date_dim + where s_store_sk = ss_store_sk + and ss_sold_date_sk = d_date_sk and d_year = 1998 + and + ( + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 100.00 and 150.00 + ) + or + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 50.00 and 100.00 + ) + or + ( + cd_demo_sk = ss_cdemo_sk + and + cd_marital_status = 'M' + and + cd_education_status = '4 yr Degree' + and + ss_sales_price between 150.00 and 200.00 + ) + ) + and + ( + ( + ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('KY', 'GA', 'NM') + and ss_net_profit between 0 and 2000 + ) + or + (ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('MT', 'OR', 'IN') + and ss_net_profit between 150 and 3000 + ) + or + (ss_addr_sk = ca_address_sk + and + ca_country = 'United States' + and + ca_state in ('WI', 'MO', 'WV') + and ss_net_profit between 50 and 25000 + ) + ) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@customer_demographics +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@store +POSTHOOK: Input: default@store_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveAggregate(group=[{}], agg#0=[sum($9)]) + HiveJoin(condition=[AND(=($8, $0), OR(AND($1, $10), AND($2, $11), AND($3, $12)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], IN=[IN($8, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM')], IN2=[IN($8, _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN')], IN3=[IN($8, _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV')]) + HiveFilter(condition=[AND(IN($8, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM', _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN', _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), =($10, _UTF-16LE'United States'))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[=($6, 1998)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cd_demo_sk=[$0]) + HiveFilter(condition=[AND(=($2, _UTF-16LE'M'), =($3, _UTF-16LE'4 yr Degree'))]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) + HiveProject(ss_sold_date_sk=[$0], ss_cdemo_sk=[$4], ss_addr_sk=[$6], ss_quantity=[$10], BETWEEN=[BETWEEN(false, $22, 0, 2000)], BETWEEN6=[BETWEEN(false, $22, 150, 3000)], BETWEEN7=[BETWEEN(false, $22, 50, 25000)]) + HiveFilter(condition=[AND(OR(BETWEEN(false, $13, 100, 150), BETWEEN(false, $13, 50, 100), BETWEEN(false, $13, 150, 200)), OR(BETWEEN(false, $22, 0, 2000), BETWEEN(false, $22, 150, 3000), BETWEEN(false, $22, 50, 25000)), IS NOT NULL($7), IS NOT NULL($4), IS NOT NULL($6), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query49.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query49.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query49.q.out new file mode 100644 index 0000000..bc108db --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/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=[>($15, 10000)]) + 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($0))]) + HiveTableScan(table=[[default, web_sales]], table:alias=[ws]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 12))]) + 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=[>($18, 10000)]) + 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($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[cs]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 12))]) + 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=[>($11, 10000)]) + 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($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[sts]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 12))]) + 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/constraints/cbo_query5.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query5.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query5.q.out new file mode 100644 index 0000000..54f3dd6 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query5.q.out @@ -0,0 +1,339 @@ +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=[{8}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)]) + HiveJoin(condition=[=($0, $7)], 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]) + HiveFilter(condition=[BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-08-18 00:00:00)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(s_store_sk=[$0], s_store_id=[$1]) + 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]) + 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]) + HiveFilter(condition=[BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-08-18 00:00:00)]) + 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=[{8}], agg#0=[sum($2)], agg#1=[sum($3)], agg#2=[sum($4)], agg#3=[sum($5)]) + HiveJoin(condition=[=($0, $7)], 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(ws_web_site_sk=[$1], wr_returned_date_sk=[$3], $f2=[CAST(0):DECIMAL(7, 2)], $f3=[CAST(0):DECIMAL(7, 2)], wr_return_amt=[$6], wr_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=[IS NOT NULL($13)]) + 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=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-08-04 00:00:00, 1998-08-18 00:00:00)]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(web_site_sk=[$0], web_site_id=[$1]) + 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/constraints/cbo_query50.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query50.q.out b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query50.q.out new file mode 100644 index 0000000..49c87ee --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/constraints/cbo_query50.q.out @@ -0,0 +1,146 @@ +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=[$11], $f1=[$12], $f2=[$13], $f3=[$14], $f4=[$15], $f5=[$16], $f6=[$17], $f7=[$18], $f8=[$19], $f9=[$20], $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, $10)], 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($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($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_returns]], table:alias=[store_returns]) + HiveProject(d_date_sk=[$0]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 9))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) + 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]) + HiveTableScan(table=[[default, store]], table:alias=[store]) +
