http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out new file mode 100644 index 0000000..b226905 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query10.q.out @@ -0,0 +1,178 @@ +PREHOOK: query: explain cbo +select + cd_gender, + cd_marital_status, + cd_education_status, + count(*) cnt1, + cd_purchase_estimate, + count(*) cnt2, + cd_credit_rating, + count(*) cnt3, + cd_dep_count, + count(*) cnt4, + cd_dep_employed_count, + count(*) cnt5, + cd_dep_college_count, + count(*) cnt6 + from + customer c,customer_address ca,customer_demographics + where + c.c_current_addr_sk = ca.ca_address_sk and + ca_county in ('Walker County','Richland County','Gaines County','Douglas County','Dona Ana County') and + cd_demo_sk = c.c_current_cdemo_sk and + exists (select * + from store_sales,date_dim + where c.c_customer_sk = ss_customer_sk and + ss_sold_date_sk = d_date_sk and + d_year = 2002 and + d_moy between 4 and 4+3) and + (exists (select * + from web_sales,date_dim + where c.c_customer_sk = ws_bill_customer_sk and + ws_sold_date_sk = d_date_sk and + d_year = 2002 and + d_moy between 4 ANd 4+3) or + exists (select * + from catalog_sales,date_dim + where c.c_customer_sk = cs_ship_customer_sk and + cs_sold_date_sk = d_date_sk and + d_year = 2002 and + d_moy between 4 and 4+3)) + group by cd_gender, + cd_marital_status, + cd_education_status, + cd_purchase_estimate, + cd_credit_rating, + cd_dep_count, + cd_dep_employed_count, + cd_dep_college_count + order by cd_gender, + cd_marital_status, + cd_education_status, + cd_purchase_estimate, + cd_credit_rating, + cd_dep_count, + cd_dep_employed_count, + cd_dep_college_count +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@catalog_sales +PREHOOK: Input: default@customer +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@customer_demographics +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@store_sales +PREHOOK: Input: default@web_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select + cd_gender, + cd_marital_status, + cd_education_status, + count(*) cnt1, + cd_purchase_estimate, + count(*) cnt2, + cd_credit_rating, + count(*) cnt3, + cd_dep_count, + count(*) cnt4, + cd_dep_employed_count, + count(*) cnt5, + cd_dep_college_count, + count(*) cnt6 + from + customer c,customer_address ca,customer_demographics + where + c.c_current_addr_sk = ca.ca_address_sk and + ca_county in ('Walker County','Richland County','Gaines County','Douglas County','Dona Ana County') and + cd_demo_sk = c.c_current_cdemo_sk and + exists (select * + from store_sales,date_dim + where c.c_customer_sk = ss_customer_sk and + ss_sold_date_sk = d_date_sk and + d_year = 2002 and + d_moy between 4 and 4+3) and + (exists (select * + from web_sales,date_dim + where c.c_customer_sk = ws_bill_customer_sk and + ws_sold_date_sk = d_date_sk and + d_year = 2002 and + d_moy between 4 ANd 4+3) or + exists (select * + from catalog_sales,date_dim + where c.c_customer_sk = cs_ship_customer_sk and + cs_sold_date_sk = d_date_sk and + d_year = 2002 and + d_moy between 4 and 4+3)) + group by cd_gender, + cd_marital_status, + cd_education_status, + cd_purchase_estimate, + cd_credit_rating, + cd_dep_count, + cd_dep_employed_count, + cd_dep_college_count + order by cd_gender, + cd_marital_status, + cd_education_status, + cd_purchase_estimate, + cd_credit_rating, + cd_dep_count, + cd_dep_employed_count, + cd_dep_college_count +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@catalog_sales +POSTHOOK: Input: default@customer +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@customer_demographics +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], sort2=[$2], sort3=[$4], sort4=[$6], sort5=[$8], sort6=[$10], sort7=[$12], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC], dir6=[ASC], dir7=[ASC], fetch=[100]) + HiveProject(cd_gender=[$0], cd_marital_status=[$1], cd_education_status=[$2], cnt1=[$8], cd_purchase_estimate=[$3], cnt2=[$8], cd_credit_rating=[$4], cnt3=[$8], cd_dep_count=[$5], cnt4=[$8], cd_dep_employed_count=[$6], cnt5=[$8], cd_dep_college_count=[$7], cnt6=[$8]) + HiveAggregate(group=[{6, 7, 8, 9, 10, 11, 12, 13}], agg#0=[count()]) + HiveFilter(condition=[OR(IS NOT NULL($15), IS NOT NULL($17))]) + HiveJoin(condition=[=($0, $16)], joinType=[left], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $14)], joinType=[left], algorithm=[none], cost=[not available]) + HiveSemiJoin(condition=[=($0, $14)], joinType=[inner]) + HiveJoin(condition=[=($5, $1)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_current_cdemo_sk=[$2], c_current_addr_sk=[$4]) + HiveFilter(condition=[AND(IS NOT NULL($4), IS NOT NULL($2), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer]], table:alias=[c]) + HiveProject(ca_address_sk=[$0], ca_county=[$7]) + HiveFilter(condition=[AND(IN($7, _UTF-16LE'Walker County', _UTF-16LE'Richland County', _UTF-16LE'Gaines County', _UTF-16LE'Douglas County', _UTF-16LE'Dona Ana County'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[ca]) + HiveProject(cd_demo_sk=[$0], cd_gender=[$1], cd_marital_status=[$2], cd_education_status=[$3], cd_purchase_estimate=[$4], cd_credit_rating=[$5], cd_dep_count=[$6], cd_dep_employed_count=[$7], cd_dep_college_count=[$8]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) + HiveProject(ss_customer_sk0=[$1]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3]) + 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_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveFilter(condition=[AND(=($6, 2002), BETWEEN(false, $8, 4, 7), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(ws_bill_customer_sk0=[$0], $f1=[true]) + HiveAggregate(group=[{1}]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4]) + 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(2002):INTEGER], d_moy=[$8]) + HiveFilter(condition=[AND(=($6, 2002), BETWEEN(false, $8, 4, 7), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(cs_ship_customer_sk0=[$0], $f1=[true]) + HiveAggregate(group=[{1}]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_ship_customer_sk=[$7]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2002):INTEGER], d_moy=[$8]) + HiveFilter(condition=[AND(=($6, 2002), BETWEEN(false, $8, 4, 7), 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_query11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out new file mode 100644 index 0000000..e09f7ec --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query11.q.out @@ -0,0 +1,223 @@ +PREHOOK: query: explain cbo +with year_total as ( + select c_customer_id customer_id + ,c_first_name customer_first_name + ,c_last_name customer_last_name + ,c_preferred_cust_flag + ,c_birth_country customer_birth_country + ,c_login customer_login + ,c_email_address customer_email_address + ,d_year dyear + ,sum(ss_ext_list_price-ss_ext_discount_amt) year_total + ,'s' sale_type + from customer + ,store_sales + ,date_dim + where c_customer_sk = ss_customer_sk + and ss_sold_date_sk = d_date_sk + group by c_customer_id + ,c_first_name + ,c_last_name + ,d_year + ,c_preferred_cust_flag + ,c_birth_country + ,c_login + ,c_email_address + ,d_year + union all + select c_customer_id customer_id + ,c_first_name customer_first_name + ,c_last_name customer_last_name + ,c_preferred_cust_flag + ,c_birth_country customer_birth_country + ,c_login customer_login + ,c_email_address customer_email_address + ,d_year dyear + ,sum(ws_ext_list_price-ws_ext_discount_amt) year_total + ,'w' sale_type + from customer + ,web_sales + ,date_dim + where c_customer_sk = ws_bill_customer_sk + and ws_sold_date_sk = d_date_sk + group by c_customer_id + ,c_first_name + ,c_last_name + ,c_preferred_cust_flag + ,c_birth_country + ,c_login + ,c_email_address + ,d_year + ) + select t_s_secyear.c_preferred_cust_flag + from year_total t_s_firstyear + ,year_total t_s_secyear + ,year_total t_w_firstyear + ,year_total t_w_secyear + where t_s_secyear.customer_id = t_s_firstyear.customer_id + and t_s_firstyear.customer_id = t_w_secyear.customer_id + and t_s_firstyear.customer_id = t_w_firstyear.customer_id + and t_s_firstyear.sale_type = 's' + and t_w_firstyear.sale_type = 'w' + and t_s_secyear.sale_type = 's' + and t_w_secyear.sale_type = 'w' + and t_s_firstyear.dyear = 2001 + and t_s_secyear.dyear = 2001+1 + and t_w_firstyear.dyear = 2001 + and t_w_secyear.dyear = 2001+1 + and t_s_firstyear.year_total > 0 + and t_w_firstyear.year_total > 0 + and case when t_w_firstyear.year_total > 0 then t_w_secyear.year_total / t_w_firstyear.year_total else null end + > case when t_s_firstyear.year_total > 0 then t_s_secyear.year_total / t_s_firstyear.year_total else null end + order by t_s_secyear.c_preferred_cust_flag +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@customer +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 year_total as ( + select c_customer_id customer_id + ,c_first_name customer_first_name + ,c_last_name customer_last_name + ,c_preferred_cust_flag + ,c_birth_country customer_birth_country + ,c_login customer_login + ,c_email_address customer_email_address + ,d_year dyear + ,sum(ss_ext_list_price-ss_ext_discount_amt) year_total + ,'s' sale_type + from customer + ,store_sales + ,date_dim + where c_customer_sk = ss_customer_sk + and ss_sold_date_sk = d_date_sk + group by c_customer_id + ,c_first_name + ,c_last_name + ,d_year + ,c_preferred_cust_flag + ,c_birth_country + ,c_login + ,c_email_address + ,d_year + union all + select c_customer_id customer_id + ,c_first_name customer_first_name + ,c_last_name customer_last_name + ,c_preferred_cust_flag + ,c_birth_country customer_birth_country + ,c_login customer_login + ,c_email_address customer_email_address + ,d_year dyear + ,sum(ws_ext_list_price-ws_ext_discount_amt) year_total + ,'w' sale_type + from customer + ,web_sales + ,date_dim + where c_customer_sk = ws_bill_customer_sk + and ws_sold_date_sk = d_date_sk + group by c_customer_id + ,c_first_name + ,c_last_name + ,c_preferred_cust_flag + ,c_birth_country + ,c_login + ,c_email_address + ,d_year + ) + select t_s_secyear.c_preferred_cust_flag + from year_total t_s_firstyear + ,year_total t_s_secyear + ,year_total t_w_firstyear + ,year_total t_w_secyear + where t_s_secyear.customer_id = t_s_firstyear.customer_id + and t_s_firstyear.customer_id = t_w_secyear.customer_id + and t_s_firstyear.customer_id = t_w_firstyear.customer_id + and t_s_firstyear.sale_type = 's' + and t_w_firstyear.sale_type = 'w' + and t_s_secyear.sale_type = 's' + and t_w_secyear.sale_type = 'w' + and t_s_firstyear.dyear = 2001 + and t_s_secyear.dyear = 2001+1 + and t_w_firstyear.dyear = 2001 + and t_w_secyear.dyear = 2001+1 + and t_s_firstyear.year_total > 0 + and t_w_firstyear.year_total > 0 + and case when t_w_firstyear.year_total > 0 then t_w_secyear.year_total / t_w_firstyear.year_total else null end + > case when t_s_firstyear.year_total > 0 then t_s_secyear.year_total / t_s_firstyear.year_total else null end + order by t_s_secyear.c_preferred_cust_flag +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer +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], dir0=[ASC], fetch=[100]) + HiveProject(c_preferred_cust_flag=[$1]) + HiveJoin(condition=[AND(=($0, $5), CASE(CAST(IS NOT NULL($6)):BOOLEAN, CASE(CAST(IS NOT NULL($8)):BOOLEAN, >(/($4, $8), /($2, $6)), >(null, /($2, $6))), CASE(CAST(IS NOT NULL($8)):BOOLEAN, >(/($4, $8), null), null)))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f4=[$3], $f9=[$7]) + HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) + HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f9=[-($11, $10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_list_price=[$17]) + 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_year=[CAST(2002):INTEGER]) + HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($2, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f8=[$7]) + HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) + HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[-($11, $10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_ext_discount_amt=[$22], ws_ext_list_price=[$25]) + 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(2002):INTEGER]) + HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject($f0=[$0], $f9=[$7]) + HiveFilter(condition=[>($7, 0)]) + HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) + HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f4=[$4], $f5=[$5], $f6=[$6], $f7=[$7], $f9=[-($11, $10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_list_price=[$17]) + 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_year=[CAST(2001):INTEGER]) + HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject($f0=[$0], $f8=[$7]) + HiveFilter(condition=[>($7, 0)]) + HiveAggregate(group=[{0, 1, 2, 3, 4, 5, 6}], agg#0=[sum($7)]) + HiveProject($f0=[$1], $f1=[$2], $f2=[$3], $f3=[$4], $f4=[$5], $f5=[$6], $f6=[$7], $f8=[-($11, $10)]) + HiveJoin(condition=[=($0, $9)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_country=[$14], c_login=[$15], c_email_address=[$16]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($1))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_bill_customer_sk=[$4], ws_ext_discount_amt=[$22], ws_ext_list_price=[$25]) + 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(2001):INTEGER]) + HiveFilter(condition=[AND(=($6, 2001), 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_query12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out new file mode 100644 index 0000000..dbfe6e7 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query12.q.out @@ -0,0 +1,89 @@ +PREHOOK: query: explain cbo +select i_item_desc + ,i_category + ,i_class + ,i_current_price + ,sum(ws_ext_sales_price) as itemrevenue + ,sum(ws_ext_sales_price)*100/sum(sum(ws_ext_sales_price)) over + (partition by i_class) as revenueratio +from + web_sales + ,item + ,date_dim +where + ws_item_sk = i_item_sk + and i_category in ('Jewelry', 'Sports', 'Books') + and ws_sold_date_sk = d_date_sk + and d_date between cast('2001-01-12' as date) + and (cast('2001-01-12' as date) + 30 days) +group by + i_item_id + ,i_item_desc + ,i_category + ,i_class + ,i_current_price +order by + i_category + ,i_class + ,i_item_id + ,i_item_desc + ,revenueratio +limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@date_dim +PREHOOK: Input: default@item +PREHOOK: Input: default@web_sales +PREHOOK: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select i_item_desc + ,i_category + ,i_class + ,i_current_price + ,sum(ws_ext_sales_price) as itemrevenue + ,sum(ws_ext_sales_price)*100/sum(sum(ws_ext_sales_price)) over + (partition by i_class) as revenueratio +from + web_sales + ,item + ,date_dim +where + ws_item_sk = i_item_sk + and i_category in ('Jewelry', 'Sports', 'Books') + and ws_sold_date_sk = d_date_sk + and d_date between cast('2001-01-12' as date) + and (cast('2001-01-12' as date) + 30 days) +group by + i_item_id + ,i_item_desc + ,i_category + ,i_class + ,i_current_price +order by + i_category + ,i_class + ,i_item_id + ,i_item_desc + ,revenueratio +limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@date_dim +POSTHOOK: Input: default@item +POSTHOOK: Input: default@web_sales +POSTHOOK: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveProject(i_item_desc=[$0], i_category=[$1], i_class=[$2], i_current_price=[$3], itemrevenue=[$4], revenueratio=[$5]) + HiveSortLimit(sort0=[$1], sort1=[$2], sort2=[$6], sort3=[$0], sort4=[$5], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], fetch=[100]) + HiveProject(i_item_desc=[$1], i_category=[$4], i_class=[$3], i_current_price=[$2], itemrevenue=[$5], revenueratio=[/(*($5, CAST(100):DECIMAL(10, 0)), sum($5) OVER (PARTITION BY $3 ORDER BY $3 NULLS FIRST ROWS BETWEEN 2147483647 FOLLOWING AND 2147483647 PRECEDING))], (tok_table_or_col i_item_id)=[$0]) + HiveAggregate(group=[{1, 2, 3, 4, 5}], agg#0=[sum($8)]) + HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_desc=[$4], i_current_price=[$5], i_class=[$10], i_category=[$12]) + HiveFilter(condition=[AND(IN($12, _UTF-16LE'Jewelry', _UTF-16LE'Sports', _UTF-16LE'Books'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_ext_sales_price=[$23]) + 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]) + HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 2001-01-12 00:00:00, 2001-02-11 00:00:00), 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_query13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query13.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query13.q.out new file mode 100644 index 0000000..ccad088 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query13.q.out @@ -0,0 +1,141 @@ +PREHOOK: query: explain cbo +select avg(ss_quantity) + ,avg(ss_ext_sales_price) + ,avg(ss_ext_wholesale_cost) + ,sum(ss_ext_wholesale_cost) + from store_sales + ,store + ,customer_demographics + ,household_demographics + ,customer_address + ,date_dim + where s_store_sk = ss_store_sk + and ss_sold_date_sk = d_date_sk and d_year = 2001 + and((ss_hdemo_sk=hd_demo_sk + 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 + and hd_dep_count = 3 + )or + (ss_hdemo_sk=hd_demo_sk + and cd_demo_sk = ss_cdemo_sk + and cd_marital_status = 'D' + and cd_education_status = 'Primary' + and ss_sales_price between 50.00 and 100.00 + and hd_dep_count = 1 + ) or + (ss_hdemo_sk=hd_demo_sk + and cd_demo_sk = ss_cdemo_sk + and cd_marital_status = 'U' + and cd_education_status = 'Advanced Degree' + and ss_sales_price between 150.00 and 200.00 + and hd_dep_count = 1 + )) + and((ss_addr_sk = ca_address_sk + and ca_country = 'United States' + and ca_state in ('KY', 'GA', 'NM') + and ss_net_profit between 100 and 200 + ) 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 300 + ) 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 250 + )) +PREHOOK: type: QUERY +PREHOOK: Input: default@customer_address +PREHOOK: Input: default@customer_demographics +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 avg(ss_quantity) + ,avg(ss_ext_sales_price) + ,avg(ss_ext_wholesale_cost) + ,sum(ss_ext_wholesale_cost) + from store_sales + ,store + ,customer_demographics + ,household_demographics + ,customer_address + ,date_dim + where s_store_sk = ss_store_sk + and ss_sold_date_sk = d_date_sk and d_year = 2001 + and((ss_hdemo_sk=hd_demo_sk + 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 + and hd_dep_count = 3 + )or + (ss_hdemo_sk=hd_demo_sk + and cd_demo_sk = ss_cdemo_sk + and cd_marital_status = 'D' + and cd_education_status = 'Primary' + and ss_sales_price between 50.00 and 100.00 + and hd_dep_count = 1 + ) or + (ss_hdemo_sk=hd_demo_sk + and cd_demo_sk = ss_cdemo_sk + and cd_marital_status = 'U' + and cd_education_status = 'Advanced Degree' + and ss_sales_price between 150.00 and 200.00 + and hd_dep_count = 1 + )) + and((ss_addr_sk = ca_address_sk + and ca_country = 'United States' + and ca_state in ('KY', 'GA', 'NM') + and ss_net_profit between 100 and 200 + ) 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 300 + ) 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 250 + )) +POSTHOOK: type: QUERY +POSTHOOK: Input: default@customer_address +POSTHOOK: Input: default@customer_demographics +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: +HiveProject($f0=[/(CAST($0):DOUBLE, $1)], $f1=[/($2, $3)], $f2=[/($4, $5)], $f3=[CAST($4):DECIMAL(17, 2)]) + HiveAggregate(group=[{}], agg#0=[sum($16)], agg#1=[count($16)], agg#2=[sum($18)], agg#3=[count($18)], agg#4=[sum($19)], agg#5=[count($19)]) + HiveJoin(condition=[AND(=($0, $12), OR(AND(=($1, _UTF-16LE'M'), =($2, _UTF-16LE'4 yr Degree'), BETWEEN(false, $17, 100, 150), =($7, 3)), AND(=($1, _UTF-16LE'D'), =($2, _UTF-16LE'Primary'), BETWEEN(false, $17, 50, 100), =($7, 1)), AND(=($1, _UTF-16LE'U'), =($2, _UTF-16LE'Advanced Degree'), BETWEEN(false, $17, 150, 200), =($7, 1))))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cd_demo_sk=[$0], cd_marital_status=[$2], cd_education_status=[$3]) + HiveFilter(condition=[AND(IN($2, _UTF-16LE'M', _UTF-16LE'D', _UTF-16LE'U'), IN($3, _UTF-16LE'4 yr Degree', _UTF-16LE'Primary', _UTF-16LE'Advanced Degree'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics]) + HiveJoin(condition=[AND(=($11, $0), OR(AND(IN($1, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM'), BETWEEN(false, $17, 100, 200)), AND(IN($1, _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN'), BETWEEN(false, $17, 150, 300)), AND(IN($1, _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), BETWEEN(false, $17, 50, 250))))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_country=[CAST(_UTF-16LE'United States'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"]) + 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'), IS NOT NULL($0))]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveJoin(condition=[=($7, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3]) + HiveFilter(condition=[AND(IN($3, 3, 1), IS NOT NULL($0))]) + HiveTableScan(table=[[default, household_demographics]], table:alias=[household_demographics]) + HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2001):INTEGER]) + HiveFilter(condition=[AND(=($6, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[=($0, $5)], 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]) + HiveProject(ss_sold_date_sk=[$0], ss_cdemo_sk=[$4], ss_hdemo_sk=[$5], ss_addr_sk=[$6], ss_store_sk=[$7], ss_quantity=[$10], ss_sales_price=[$13], ss_ext_sales_price=[$15], ss_ext_wholesale_cost=[$16], ss_net_profit=[$22]) + HiveFilter(condition=[AND(OR(BETWEEN(false, $13, 100, 150), BETWEEN(false, $13, 50, 100), BETWEEN(false, $13, 150, 200)), OR(BETWEEN(false, $22, 100, 200), BETWEEN(false, $22, 150, 300), BETWEEN(false, $22, 50, 250)), IS NOT NULL($7), IS NOT NULL($4), IS NOT NULL($5), IS NOT NULL($6), IS NOT NULL($0))]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query14.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query14.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query14.q.out new file mode 100644 index 0000000..9bb4f2e --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query14.q.out @@ -0,0 +1,618 @@ +Warning: Shuffle Join MERGEJOIN[1446][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 5' is a cross product +Warning: Shuffle Join MERGEJOIN[1458][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 6' is a cross product +Warning: Shuffle Join MERGEJOIN[1448][tables = [$hdt$_1, $hdt$_2]] in Stage 'Reducer 13' is a cross product +Warning: Shuffle Join MERGEJOIN[1471][tables = [$hdt$_1, $hdt$_2, $hdt$_0]] in Stage 'Reducer 14' is a cross product +Warning: Shuffle Join MERGEJOIN[1450][tables = [$hdt$_2, $hdt$_3]] in Stage 'Reducer 18' is a cross product +Warning: Shuffle Join MERGEJOIN[1484][tables = [$hdt$_2, $hdt$_3, $hdt$_1]] in Stage 'Reducer 19' is a cross product +PREHOOK: query: explain cbo +with cross_items as + (select i_item_sk ss_item_sk + from item, + (select iss.i_brand_id brand_id + ,iss.i_class_id class_id + ,iss.i_category_id category_id + from store_sales + ,item iss + ,date_dim d1 + where ss_item_sk = iss.i_item_sk + and ss_sold_date_sk = d1.d_date_sk + and d1.d_year between 1999 AND 1999 + 2 + intersect + select ics.i_brand_id + ,ics.i_class_id + ,ics.i_category_id + from catalog_sales + ,item ics + ,date_dim d2 + where cs_item_sk = ics.i_item_sk + and cs_sold_date_sk = d2.d_date_sk + and d2.d_year between 1999 AND 1999 + 2 + intersect + select iws.i_brand_id + ,iws.i_class_id + ,iws.i_category_id + from web_sales + ,item iws + ,date_dim d3 + where ws_item_sk = iws.i_item_sk + and ws_sold_date_sk = d3.d_date_sk + and d3.d_year between 1999 AND 1999 + 2) x + where i_brand_id = brand_id + and i_class_id = class_id + and i_category_id = category_id +), + avg_sales as + (select avg(quantity*list_price) average_sales + from (select ss_quantity quantity + ,ss_list_price list_price + from store_sales + ,date_dim + where ss_sold_date_sk = d_date_sk + and d_year between 1999 and 2001 + union all + select cs_quantity quantity + ,cs_list_price list_price + from catalog_sales + ,date_dim + where cs_sold_date_sk = d_date_sk + and d_year between 1998 and 1998 + 2 + union all + select ws_quantity quantity + ,ws_list_price list_price + from web_sales + ,date_dim + where ws_sold_date_sk = d_date_sk + and d_year between 1998 and 1998 + 2) x) + select channel, i_brand_id,i_class_id,i_category_id,sum(sales), sum(number_sales) + from( + select 'store' channel, i_brand_id,i_class_id + ,i_category_id,sum(ss_quantity*ss_list_price) sales + , count(*) number_sales + from store_sales + ,item + ,date_dim + where ss_item_sk in (select ss_item_sk from cross_items) + and ss_item_sk = i_item_sk + and ss_sold_date_sk = d_date_sk + and d_year = 1998+2 + and d_moy = 11 + group by i_brand_id,i_class_id,i_category_id + having sum(ss_quantity*ss_list_price) > (select average_sales from avg_sales) + union all + select 'catalog' channel, i_brand_id,i_class_id,i_category_id, sum(cs_quantity*cs_list_price) sales, count(*) number_sales + from catalog_sales + ,item + ,date_dim + where cs_item_sk in (select ss_item_sk from cross_items) + and cs_item_sk = i_item_sk + and cs_sold_date_sk = d_date_sk + and d_year = 1998+2 + and d_moy = 11 + group by i_brand_id,i_class_id,i_category_id + having sum(cs_quantity*cs_list_price) > (select average_sales from avg_sales) + union all + select 'web' channel, i_brand_id,i_class_id,i_category_id, sum(ws_quantity*ws_list_price) sales , count(*) number_sales + from web_sales + ,item + ,date_dim + where ws_item_sk in (select ss_item_sk from cross_items) + and ws_item_sk = i_item_sk + and ws_sold_date_sk = d_date_sk + and d_year = 1998+2 + and d_moy = 11 + group by i_brand_id,i_class_id,i_category_id + having sum(ws_quantity*ws_list_price) > (select average_sales from avg_sales) + ) y + group by rollup (channel, i_brand_id,i_class_id,i_category_id) + order by channel,i_brand_id,i_class_id,i_category_id + limit 100 +PREHOOK: type: QUERY +PREHOOK: Input: default@catalog_sales +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 cross_items as + (select i_item_sk ss_item_sk + from item, + (select iss.i_brand_id brand_id + ,iss.i_class_id class_id + ,iss.i_category_id category_id + from store_sales + ,item iss + ,date_dim d1 + where ss_item_sk = iss.i_item_sk + and ss_sold_date_sk = d1.d_date_sk + and d1.d_year between 1999 AND 1999 + 2 + intersect + select ics.i_brand_id + ,ics.i_class_id + ,ics.i_category_id + from catalog_sales + ,item ics + ,date_dim d2 + where cs_item_sk = ics.i_item_sk + and cs_sold_date_sk = d2.d_date_sk + and d2.d_year between 1999 AND 1999 + 2 + intersect + select iws.i_brand_id + ,iws.i_class_id + ,iws.i_category_id + from web_sales + ,item iws + ,date_dim d3 + where ws_item_sk = iws.i_item_sk + and ws_sold_date_sk = d3.d_date_sk + and d3.d_year between 1999 AND 1999 + 2) x + where i_brand_id = brand_id + and i_class_id = class_id + and i_category_id = category_id +), + avg_sales as + (select avg(quantity*list_price) average_sales + from (select ss_quantity quantity + ,ss_list_price list_price + from store_sales + ,date_dim + where ss_sold_date_sk = d_date_sk + and d_year between 1999 and 2001 + union all + select cs_quantity quantity + ,cs_list_price list_price + from catalog_sales + ,date_dim + where cs_sold_date_sk = d_date_sk + and d_year between 1998 and 1998 + 2 + union all + select ws_quantity quantity + ,ws_list_price list_price + from web_sales + ,date_dim + where ws_sold_date_sk = d_date_sk + and d_year between 1998 and 1998 + 2) x) + select channel, i_brand_id,i_class_id,i_category_id,sum(sales), sum(number_sales) + from( + select 'store' channel, i_brand_id,i_class_id + ,i_category_id,sum(ss_quantity*ss_list_price) sales + , count(*) number_sales + from store_sales + ,item + ,date_dim + where ss_item_sk in (select ss_item_sk from cross_items) + and ss_item_sk = i_item_sk + and ss_sold_date_sk = d_date_sk + and d_year = 1998+2 + and d_moy = 11 + group by i_brand_id,i_class_id,i_category_id + having sum(ss_quantity*ss_list_price) > (select average_sales from avg_sales) + union all + select 'catalog' channel, i_brand_id,i_class_id,i_category_id, sum(cs_quantity*cs_list_price) sales, count(*) number_sales + from catalog_sales + ,item + ,date_dim + where cs_item_sk in (select ss_item_sk from cross_items) + and cs_item_sk = i_item_sk + and cs_sold_date_sk = d_date_sk + and d_year = 1998+2 + and d_moy = 11 + group by i_brand_id,i_class_id,i_category_id + having sum(cs_quantity*cs_list_price) > (select average_sales from avg_sales) + union all + select 'web' channel, i_brand_id,i_class_id,i_category_id, sum(ws_quantity*ws_list_price) sales , count(*) number_sales + from web_sales + ,item + ,date_dim + where ws_item_sk in (select ss_item_sk from cross_items) + and ws_item_sk = i_item_sk + and ws_sold_date_sk = d_date_sk + and d_year = 1998+2 + and d_moy = 11 + group by i_brand_id,i_class_id,i_category_id + having sum(ws_quantity*ws_list_price) > (select average_sales from avg_sales) + ) y + group by rollup (channel, i_brand_id,i_class_id,i_category_id) + order by channel,i_brand_id,i_class_id,i_category_id + limit 100 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@catalog_sales +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=[$0], sort1=[$1], sort2=[$2], sort3=[$3], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], fetch=[100]) + HiveProject(channel=[$0], i_brand_id=[$1], i_class_id=[$2], i_category_id=[$3], $f4=[$4], $f5=[$5]) + HiveAggregate(group=[{0, 1, 2, 3}], groups=[[{0, 1, 2, 3}, {0, 1, 2}, {0, 1}, {0}, {}]], agg#0=[sum($4)], agg#1=[sum($5)]) + HiveProject(channel=[$0], i_brand_id=[$1], i_class_id=[$2], i_category_id=[$3], sales=[$4], number_sales=[$5]) + HiveUnion(all=[true]) + HiveProject(channel=[_UTF-16LE'store'], i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], sales=[$3], number_sales=[$4]) + HiveJoin(condition=[>($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($3)], agg#1=[count()]) + HiveProject($f0=[$2], $f1=[$3], $f2=[$4], $f3=[*(CAST($7):DECIMAL(10, 0), $8)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0]) + HiveAggregate(group=[{0}]) + HiveJoin(condition=[AND(AND(=($1, $4), =($2, $5)), =($3, $6))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) + HiveFilter(condition=[=($3, 3)]) + HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveUnion(all=[true]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) + 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_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[iss]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[ics]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3]) + 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_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[iws]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[IS NOT NULL($0)]) + 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_quantity=[$10], ss_list_price=[$12]) + 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_year=[CAST(2000):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 11), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cnt=[$0]) + HiveFilter(condition=[<=(sq_count_check($0), 1)]) + HiveProject(cnt=[$0]) + HiveAggregate(group=[{}], cnt=[COUNT()]) + HiveProject + HiveProject($f0=[$0]) + HiveAggregate(group=[{}], agg#0=[count($0)]) + HiveProject(quantity=[$0], list_price=[$1]) + HiveUnion(all=[true]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject($f0=[/($0, $1)]) + HiveAggregate(group=[{}], agg#0=[sum($0)], agg#1=[count($0)]) + HiveProject($f0=[*(CAST($0):DECIMAL(10, 0), $1)]) + HiveUnion(all=[true]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(channel=[_UTF-16LE'catalog'], i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], sales=[$3], number_sales=[$4]) + HiveJoin(condition=[>($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($3)], agg#1=[count()]) + HiveProject($f0=[$2], $f1=[$3], $f2=[$4], $f3=[*(CAST($7):DECIMAL(10, 0), $8)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0]) + HiveAggregate(group=[{0}]) + HiveJoin(condition=[AND(AND(=($1, $4), =($2, $5)), =($3, $6))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) + HiveFilter(condition=[=($3, 3)]) + HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveUnion(all=[true]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) + 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_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[iss]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[ics]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3]) + 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_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[iws]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15], cs_quantity=[$18], cs_list_price=[$20]) + HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 11), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cnt=[$0]) + HiveFilter(condition=[<=(sq_count_check($0), 1)]) + HiveProject(cnt=[$0]) + HiveAggregate(group=[{}], cnt=[COUNT()]) + HiveProject + HiveProject($f0=[$0]) + HiveAggregate(group=[{}], agg#0=[count($0)]) + HiveProject(quantity=[$0], list_price=[$1]) + HiveUnion(all=[true]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject($f0=[/($0, $1)]) + HiveAggregate(group=[{}], agg#0=[sum($0)], agg#1=[count($0)]) + HiveProject($f0=[*(CAST($0):DECIMAL(10, 0), $1)]) + HiveUnion(all=[true]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(channel=[_UTF-16LE'web'], i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], sales=[$3], number_sales=[$4]) + HiveJoin(condition=[>($3, $6)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3], $f4=[$4]) + HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($3)], agg#1=[count()]) + HiveProject($f0=[$2], $f1=[$3], $f2=[$4], $f3=[*(CAST($7):DECIMAL(10, 0), $8)]) + HiveJoin(condition=[=($6, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0]) + HiveAggregate(group=[{0}]) + HiveJoin(condition=[AND(AND(=($1, $4), =($2, $5)), =($3, $6))], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11), IS NOT NULL($0))]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveProject($f0=[$0], $f1=[$1], $f2=[$2]) + HiveFilter(condition=[=($3, 3)]) + HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveUnion(all=[true]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2]) + 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_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d1]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[iss]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_item_sk=[$15]) + HiveFilter(condition=[AND(IS NOT NULL($15), IS NOT NULL($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d2]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[ics]) + HiveProject(i_brand_id=[$0], i_class_id=[$1], i_category_id=[$2], $f3=[$3]) + HiveAggregate(group=[{5, 6, 7}], agg#0=[count()]) + HiveJoin(condition=[=($1, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3]) + 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_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[d3]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($7), IS NOT NULL($9), IS NOT NULL($11))]) + HiveTableScan(table=[[default, item]], table:alias=[iws]) + HiveJoin(condition=[=($5, $0)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(i_item_sk=[$0], i_brand_id=[$7], i_class_id=[$9], i_category_id=[$11]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, item]], table:alias=[item]) + HiveJoin(condition=[=($0, $4)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_item_sk=[$3], ws_quantity=[$18], ws_list_price=[$20]) + 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_year=[CAST(2000):INTEGER], d_moy=[CAST(11):INTEGER]) + HiveFilter(condition=[AND(=($6, 2000), =($8, 11), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cnt=[$0]) + HiveFilter(condition=[<=(sq_count_check($0), 1)]) + HiveProject(cnt=[$0]) + HiveAggregate(group=[{}], cnt=[COUNT()]) + HiveProject + HiveProject($f0=[$0]) + HiveAggregate(group=[{}], agg#0=[count($0)]) + HiveProject(quantity=[$0], list_price=[$1]) + HiveUnion(all=[true]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject($f0=[/($0, $1)]) + HiveAggregate(group=[{}], agg#0=[sum($0)], agg#1=[count($0)]) + HiveProject($f0=[*(CAST($0):DECIMAL(10, 0), $1)]) + HiveUnion(all=[true]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ss_sold_date_sk=[$0], ss_quantity=[$10], ss_list_price=[$12]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1999, 2001), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_quantity=[$18], cs_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) + HiveProject(quantity=[$1], list_price=[$2]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(ws_sold_date_sk=[$0], ws_quantity=[$18], ws_list_price=[$20]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales]) + HiveProject(d_date_sk=[$0], d_year=[$6]) + HiveFilter(condition=[AND(BETWEEN(false, $6, 1998, 2000), 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_query15.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query15.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query15.q.out new file mode 100644 index 0000000..02ad7c2 --- /dev/null +++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query15.q.out @@ -0,0 +1,69 @@ +PREHOOK: query: explain cbo +select ca_zip + ,sum(cs_sales_price) + from catalog_sales + ,customer + ,customer_address + ,date_dim + where cs_bill_customer_sk = c_customer_sk + and c_current_addr_sk = ca_address_sk + and ( substr(ca_zip,1,5) in ('85669', '86197','88274','83405','86475', + '85392', '85460', '80348', '81792') + or ca_state in ('CA','WA','GA') + or cs_sales_price > 500) + and cs_sold_date_sk = d_date_sk + and d_qoy = 2 and d_year = 2000 + group by ca_zip + order by ca_zip + 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: Output: hdfs://### HDFS PATH ### +POSTHOOK: query: explain cbo +select ca_zip + ,sum(cs_sales_price) + from catalog_sales + ,customer + ,customer_address + ,date_dim + where cs_bill_customer_sk = c_customer_sk + and c_current_addr_sk = ca_address_sk + and ( substr(ca_zip,1,5) in ('85669', '86197','88274','83405','86475', + '85392', '85460', '80348', '81792') + or ca_state in ('CA','WA','GA') + or cs_sales_price > 500) + and cs_sold_date_sk = d_date_sk + and d_qoy = 2 and d_year = 2000 + group by ca_zip + order by ca_zip + 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: Output: hdfs://### HDFS PATH ### +CBO PLAN: +HiveSortLimit(sort0=[$0], dir0=[ASC], fetch=[100]) + HiveProject(ca_zip=[$0], $f1=[$1]) + HiveAggregate(group=[{4}], agg#0=[sum($7)]) + HiveJoin(condition=[AND(=($6, $0), OR(IN(substr($4, 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'), >($7, 500), IN($3, _UTF-16LE'CA', _UTF-16LE'WA', _UTF-16LE'GA')))], 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=[AND(IS NOT NULL($0), IS NOT NULL($4))]) + HiveTableScan(table=[[default, customer]], table:alias=[customer]) + HiveProject(ca_address_sk=[$0], ca_state=[$8], ca_zip=[$9]) + HiveFilter(condition=[IS NOT NULL($0)]) + HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$1], cs_sales_price=[$2], d_date_sk=[$3], d_year=[$4], d_qoy=[$5]) + HiveJoin(condition=[=($0, $3)], joinType=[inner], algorithm=[none], cost=[not available]) + HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_sales_price=[$21]) + HiveFilter(condition=[AND(IS NOT NULL($3), IS NOT NULL($0))]) + HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales]) + HiveProject(d_date_sk=[$0], d_year=[CAST(2000):INTEGER], d_qoy=[CAST(2):INTEGER]) + HiveFilter(condition=[AND(=($10, 2), =($6, 2000), IS NOT NULL($0))]) + HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim]) +
