You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by jc...@apache.org on 2018/10/22 02:10:49 UTC
[44/51] [partial] hive git commit: HIVE-20718: Add perf cli driver
with constraints (Jesus Camacho Rodriguez, reviewed by Ashutosh Chauhan)
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query38.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query38.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query38.q.out
new file mode 100644
index 0000000..9633df1
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query38.q.out
@@ -0,0 +1,111 @@
+PREHOOK: query: explain cbo
+select count(*) from (
+ select distinct c_last_name, c_first_name, d_date
+ from store_sales, date_dim, customer
+ where store_sales.ss_sold_date_sk = date_dim.d_date_sk
+ and store_sales.ss_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212 + 11
+ intersect
+ select distinct c_last_name, c_first_name, d_date
+ from catalog_sales, date_dim, customer
+ where catalog_sales.cs_sold_date_sk = date_dim.d_date_sk
+ and catalog_sales.cs_bill_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212 + 11
+ intersect
+ select distinct c_last_name, c_first_name, d_date
+ from web_sales, date_dim, customer
+ where web_sales.ws_sold_date_sk = date_dim.d_date_sk
+ and web_sales.ws_bill_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212 + 11
+) hot_cust
+limit 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@catalog_sales
+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
+select count(*) from (
+ select distinct c_last_name, c_first_name, d_date
+ from store_sales, date_dim, customer
+ where store_sales.ss_sold_date_sk = date_dim.d_date_sk
+ and store_sales.ss_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212 + 11
+ intersect
+ select distinct c_last_name, c_first_name, d_date
+ from catalog_sales, date_dim, customer
+ where catalog_sales.cs_sold_date_sk = date_dim.d_date_sk
+ and catalog_sales.cs_bill_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212 + 11
+ intersect
+ select distinct c_last_name, c_first_name, d_date
+ from web_sales, date_dim, customer
+ where web_sales.ws_sold_date_sk = date_dim.d_date_sk
+ and web_sales.ws_bill_customer_sk = customer.c_customer_sk
+ and d_month_seq between 1212 and 1212 + 11
+) hot_cust
+limit 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@catalog_sales
+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(fetch=[100])
+ HiveProject($f0=[$0])
+ HiveAggregate(group=[{}], agg#0=[count()])
+ HiveProject(c_last_name=[$0], c_first_name=[$1], d_date=[$2], $f3=[$3])
+ HiveFilter(condition=[=($3, 3)])
+ HiveAggregate(group=[{0, 1, 2}], agg#0=[count($3)])
+ HiveProject(c_last_name=[$0], c_first_name=[$1], d_date=[$2], $f3=[$3])
+ HiveUnion(all=[true])
+ HiveProject(c_last_name=[$1], c_first_name=[$0], d_date=[$2], $f3=[$3])
+ HiveAggregate(group=[{0, 1, 2}], agg#0=[count()])
+ HiveProject(c_first_name=[$0], c_last_name=[$1], d_date=[$2])
+ HiveAggregate(group=[{1, 2, 6}])
+ HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(c_customer_sk=[$0], c_first_name=[$8], c_last_name=[$9])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, customer]], table:alias=[customer])
+ 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($0), IS NOT NULL($3))])
+ HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales])
+ HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3])
+ HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveProject(c_last_name=[$1], c_first_name=[$0], d_date=[$2], $f3=[$3])
+ HiveAggregate(group=[{0, 1, 2}], agg#0=[count()])
+ HiveProject(c_first_name=[$0], c_last_name=[$1], d_date=[$2])
+ HiveAggregate(group=[{1, 2, 6}])
+ HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(c_customer_sk=[$0], c_first_name=[$8], c_last_name=[$9])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, customer]], table:alias=[customer])
+ HiveJoin(condition=[=($0, $2)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3])
+ HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($3))])
+ HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales])
+ HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3])
+ HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveProject(c_last_name=[$1], c_first_name=[$0], d_date=[$2], $f3=[$3])
+ HiveAggregate(group=[{0, 1, 2}], agg#0=[count()])
+ HiveProject(c_first_name=[$0], c_last_name=[$1], d_date=[$2])
+ HiveAggregate(group=[{1, 2, 6}])
+ HiveJoin(condition=[=($4, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(c_customer_sk=[$0], c_first_name=[$8], c_last_name=[$9])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, customer]], table:alias=[customer])
+ 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($0), IS NOT NULL($4))])
+ HiveTableScan(table=[[default, web_sales]], table:alias=[web_sales])
+ HiveProject(d_date_sk=[$0], d_date=[$2], d_month_seq=[$3])
+ HiveFilter(condition=[AND(BETWEEN(false, $3, 1212, 1223), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query39.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query39.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query39.q.out
new file mode 100644
index 0000000..fd3038e
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query39.q.out
@@ -0,0 +1,168 @@
+PREHOOK: query: explain cbo
+with inv as
+(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
+ ,stdev,mean, case mean when 0 then null else stdev/mean end cov
+ from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
+ ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean
+ from inventory
+ ,item
+ ,warehouse
+ ,date_dim
+ where inv_item_sk = i_item_sk
+ and inv_warehouse_sk = w_warehouse_sk
+ and inv_date_sk = d_date_sk
+ and d_year =1999
+ group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo
+ where case mean when 0 then 0 else stdev/mean end > 1)
+select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov
+ ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov
+from inv inv1,inv inv2
+where inv1.i_item_sk = inv2.i_item_sk
+ and inv1.w_warehouse_sk = inv2.w_warehouse_sk
+ and inv1.d_moy=4
+ and inv2.d_moy=4+1
+order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov
+ ,inv2.d_moy,inv2.mean, inv2.cov
+PREHOOK: type: QUERY
+PREHOOK: Input: default@date_dim
+PREHOOK: Input: default@inventory
+PREHOOK: Input: default@item
+PREHOOK: Input: default@warehouse
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: explain cbo
+with inv as
+(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
+ ,stdev,mean, case mean when 0 then null else stdev/mean end cov
+ from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
+ ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean
+ from inventory
+ ,item
+ ,warehouse
+ ,date_dim
+ where inv_item_sk = i_item_sk
+ and inv_warehouse_sk = w_warehouse_sk
+ and inv_date_sk = d_date_sk
+ and d_year =1999
+ group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo
+ where case mean when 0 then 0 else stdev/mean end > 1)
+select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov
+ ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov
+from inv inv1,inv inv2
+where inv1.i_item_sk = inv2.i_item_sk
+ and inv1.w_warehouse_sk = inv2.w_warehouse_sk
+ and inv1.d_moy=4
+ and inv2.d_moy=4+1
+order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov
+ ,inv2.d_moy,inv2.mean, inv2.cov
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@date_dim
+POSTHOOK: Input: default@inventory
+POSTHOOK: Input: default@item
+POSTHOOK: Input: default@warehouse
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+CBO PLAN:
+HiveProject(w_warehouse_sk=[$0], i_item_sk=[$1], d_moy=[CAST(4):INTEGER], mean=[$2], cov=[$3], w_warehouse_sk1=[$4], i_item_sk1=[$5], d_moy1=[CAST(5):INTEGER], mean1=[$6], cov1=[$7])
+ HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$6], sort5=[$7], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC])
+ HiveProject(w_warehouse_sk=[$0], i_item_sk=[$1], mean=[$2], cov=[$3], w_warehouse_sk0=[$4], i_item_sk0=[$5], mean0=[$6], cov0=[$7])
+ HiveJoin(condition=[AND(=($1, $5), =($0, $4))], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(w_warehouse_sk=[$1], i_item_sk=[$2], mean=[/(CAST($6):DOUBLE, $5)], cov=[CASE(=(/(CAST($6):DOUBLE, $5), 0), null, /(POWER(/(-($3, /(*($4, $4), $5)), CASE(=($5, 1), null, -($5, 1))), 0.5), /(CAST($6):DOUBLE, $5)))])
+ HiveFilter(condition=[CASE(=(/(CAST($6):DOUBLE, $5), 0), false, >(/(POWER(/(-($3, /(*($4, $4), $5)), CASE(=($5, 1), null, -($5, 1))), 0.5), /(CAST($6):DOUBLE, $5)), 1))])
+ HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($5)], agg#1=[sum($4)], agg#2=[count($3)], agg#3=[sum($3)])
+ HiveProject($f0=[$9], $f1=[$8], $f2=[$0], $f4=[$4], $f40=[CAST($4):DOUBLE], $f6=[*(CAST($4):DOUBLE, CAST($4):DOUBLE)])
+ HiveJoin(condition=[=($3, $8)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(i_item_sk=[$0])
+ 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(inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3])
+ HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($2), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, inventory]], table:alias=[inventory])
+ HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(4):INTEGER])
+ HiveFilter(condition=[AND(=($6, 1999), =($8, 4), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse])
+ HiveProject(w_warehouse_sk=[$1], i_item_sk=[$2], mean=[/(CAST($6):DOUBLE, $5)], cov=[CASE(=(/(CAST($6):DOUBLE, $5), 0), null, /(POWER(/(-($3, /(*($4, $4), $5)), CASE(=($5, 1), null, -($5, 1))), 0.5), /(CAST($6):DOUBLE, $5)))])
+ HiveFilter(condition=[CASE(=(/(CAST($6):DOUBLE, $5), 0), false, >(/(POWER(/(-($3, /(*($4, $4), $5)), CASE(=($5, 1), null, -($5, 1))), 0.5), /(CAST($6):DOUBLE, $5)), 1))])
+ HiveAggregate(group=[{0, 1, 2}], agg#0=[sum($5)], agg#1=[sum($4)], agg#2=[count($3)], agg#3=[sum($3)])
+ HiveProject($f0=[$9], $f1=[$8], $f2=[$0], $f4=[$4], $f40=[CAST($4):DOUBLE], $f6=[*(CAST($4):DOUBLE, CAST($4):DOUBLE)])
+ HiveJoin(condition=[=($3, $8)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveJoin(condition=[=($2, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(i_item_sk=[$0])
+ 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(inv_date_sk=[$0], inv_item_sk=[$1], inv_warehouse_sk=[$2], inv_quantity_on_hand=[$3])
+ HiveFilter(condition=[AND(IS NOT NULL($1), IS NOT NULL($2), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, inventory]], table:alias=[inventory])
+ HiveProject(d_date_sk=[$0], d_year=[CAST(1999):INTEGER], d_moy=[CAST(5):INTEGER])
+ HiveFilter(condition=[AND(=($6, 1999), =($8, 5), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveProject(w_warehouse_sk=[$0], w_warehouse_name=[$2])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse])
+
+PREHOOK: query: with inv as
+(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
+ ,stdev,mean, case mean when 0 then null else stdev/mean end cov
+ from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
+ ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean
+ from inventory
+ ,item
+ ,warehouse
+ ,date_dim
+ where inv_item_sk = i_item_sk
+ and inv_warehouse_sk = w_warehouse_sk
+ and inv_date_sk = d_date_sk
+ and d_year =1999
+ group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo
+ where case mean when 0 then 0 else stdev/mean end > 1)
+select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov
+ ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov
+from inv inv1,inv inv2
+where inv1.i_item_sk = inv2.i_item_sk
+ and inv1.w_warehouse_sk = inv2.w_warehouse_sk
+ and inv1.d_moy=4
+ and inv2.d_moy=4+1
+ and inv1.cov > 1.5
+order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov
+ ,inv2.d_moy,inv2.mean, inv2.cov
+PREHOOK: type: QUERY
+PREHOOK: Input: default@date_dim
+PREHOOK: Input: default@inventory
+PREHOOK: Input: default@item
+PREHOOK: Input: default@warehouse
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: with inv as
+(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
+ ,stdev,mean, case mean when 0 then null else stdev/mean end cov
+ from(select w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy
+ ,stddev_samp(inv_quantity_on_hand) stdev,avg(inv_quantity_on_hand) mean
+ from inventory
+ ,item
+ ,warehouse
+ ,date_dim
+ where inv_item_sk = i_item_sk
+ and inv_warehouse_sk = w_warehouse_sk
+ and inv_date_sk = d_date_sk
+ and d_year =1999
+ group by w_warehouse_name,w_warehouse_sk,i_item_sk,d_moy) foo
+ where case mean when 0 then 0 else stdev/mean end > 1)
+select inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean, inv1.cov
+ ,inv2.w_warehouse_sk,inv2.i_item_sk,inv2.d_moy,inv2.mean, inv2.cov
+from inv inv1,inv inv2
+where inv1.i_item_sk = inv2.i_item_sk
+ and inv1.w_warehouse_sk = inv2.w_warehouse_sk
+ and inv1.d_moy=4
+ and inv2.d_moy=4+1
+ and inv1.cov > 1.5
+order by inv1.w_warehouse_sk,inv1.i_item_sk,inv1.d_moy,inv1.mean,inv1.cov
+ ,inv2.d_moy,inv2.mean, inv2.cov
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@date_dim
+POSTHOOK: Input: default@inventory
+POSTHOOK: Input: default@item
+POSTHOOK: Input: default@warehouse
+POSTHOOK: Output: hdfs://### HDFS PATH ###
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query4.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query4.q.out
new file mode 100644
index 0000000..d796f86
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query4.q.out
@@ -0,0 +1,324 @@
+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 customer_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_wholesale_cost-ss_ext_discount_amt)+ss_ext_sales_price)/2) 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
+ ,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 customer_preferred_cust_flag
+ ,c_birth_country customer_birth_country
+ ,c_login customer_login
+ ,c_email_address customer_email_address
+ ,d_year dyear
+ ,sum((((cs_ext_list_price-cs_ext_wholesale_cost-cs_ext_discount_amt)+cs_ext_sales_price)/2) ) year_total
+ ,'c' sale_type
+ from customer
+ ,catalog_sales
+ ,date_dim
+ where c_customer_sk = cs_bill_customer_sk
+ and cs_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
+union all
+ select c_customer_id customer_id
+ ,c_first_name customer_first_name
+ ,c_last_name customer_last_name
+ ,c_preferred_cust_flag customer_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_wholesale_cost-ws_ext_discount_amt)+ws_ext_sales_price)/2) ) 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.customer_preferred_cust_flag
+ from year_total t_s_firstyear
+ ,year_total t_s_secyear
+ ,year_total t_c_firstyear
+ ,year_total t_c_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_c_secyear.customer_id
+ and t_s_firstyear.customer_id = t_c_firstyear.customer_id
+ and t_s_firstyear.customer_id = t_w_firstyear.customer_id
+ and t_s_firstyear.customer_id = t_w_secyear.customer_id
+ and t_s_firstyear.sale_type = 's'
+ and t_c_firstyear.sale_type = 'c'
+ and t_w_firstyear.sale_type = 'w'
+ and t_s_secyear.sale_type = 's'
+ and t_c_secyear.sale_type = 'c'
+ and t_w_secyear.sale_type = 'w'
+ and t_s_firstyear.dyear = 2001
+ and t_s_secyear.dyear = 2001+1
+ and t_c_firstyear.dyear = 2001
+ and t_c_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_c_firstyear.year_total > 0
+ and t_w_firstyear.year_total > 0
+ and case when t_c_firstyear.year_total > 0 then t_c_secyear.year_total / t_c_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
+ and case when t_c_firstyear.year_total > 0 then t_c_secyear.year_total / t_c_firstyear.year_total else null end
+ > case when t_w_firstyear.year_total > 0 then t_w_secyear.year_total / t_w_firstyear.year_total else null end
+ order by t_s_secyear.customer_preferred_cust_flag
+limit 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@catalog_sales
+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 customer_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_wholesale_cost-ss_ext_discount_amt)+ss_ext_sales_price)/2) 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
+ ,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 customer_preferred_cust_flag
+ ,c_birth_country customer_birth_country
+ ,c_login customer_login
+ ,c_email_address customer_email_address
+ ,d_year dyear
+ ,sum((((cs_ext_list_price-cs_ext_wholesale_cost-cs_ext_discount_amt)+cs_ext_sales_price)/2) ) year_total
+ ,'c' sale_type
+ from customer
+ ,catalog_sales
+ ,date_dim
+ where c_customer_sk = cs_bill_customer_sk
+ and cs_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
+union all
+ select c_customer_id customer_id
+ ,c_first_name customer_first_name
+ ,c_last_name customer_last_name
+ ,c_preferred_cust_flag customer_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_wholesale_cost-ws_ext_discount_amt)+ws_ext_sales_price)/2) ) 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.customer_preferred_cust_flag
+ from year_total t_s_firstyear
+ ,year_total t_s_secyear
+ ,year_total t_c_firstyear
+ ,year_total t_c_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_c_secyear.customer_id
+ and t_s_firstyear.customer_id = t_c_firstyear.customer_id
+ and t_s_firstyear.customer_id = t_w_firstyear.customer_id
+ and t_s_firstyear.customer_id = t_w_secyear.customer_id
+ and t_s_firstyear.sale_type = 's'
+ and t_c_firstyear.sale_type = 'c'
+ and t_w_firstyear.sale_type = 'w'
+ and t_s_secyear.sale_type = 's'
+ and t_c_secyear.sale_type = 'c'
+ and t_w_secyear.sale_type = 'w'
+ and t_s_firstyear.dyear = 2001
+ and t_s_secyear.dyear = 2001+1
+ and t_c_firstyear.dyear = 2001
+ and t_c_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_c_firstyear.year_total > 0
+ and t_w_firstyear.year_total > 0
+ and case when t_c_firstyear.year_total > 0 then t_c_secyear.year_total / t_c_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
+ and case when t_c_firstyear.year_total > 0 then t_c_secyear.year_total / t_c_firstyear.year_total else null end
+ > case when t_w_firstyear.year_total > 0 then t_w_secyear.year_total / t_w_firstyear.year_total else null end
+ order by t_s_secyear.customer_preferred_cust_flag
+limit 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@catalog_sales
+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(customer_preferred_cust_flag=[$1])
+ HiveJoin(condition=[AND(=($0, $7), CASE(CAST(IS NOT NULL($8)):BOOLEAN, CASE(CAST(IS NOT NULL($10)):BOOLEAN, >(/($4, $10), /($2, $8)), >(null, /($2, $8))), CASE(CAST(IS NOT NULL($10)):BOOLEAN, >(/($4, $10), null), null)))], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject($f0=[$0], $f3=[$3], $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=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))])
+ 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, $6)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_sales_price=[$15], ss_ext_wholesale_cost=[$16], 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=[AND(=($4, $0), CASE(CAST(IS NOT NULL($9)):BOOLEAN, CASE(CAST(IS NOT NULL($7)):BOOLEAN, >(/($1, $7), /($3, $9)), >(null, /($3, $9))), CASE(CAST(IS NOT NULL($7)):BOOLEAN, >(/($1, $7), null), null)))], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject($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=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))])
+ 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, $6)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_ext_discount_amt=[$22], cs_ext_sales_price=[$23], cs_ext_wholesale_cost=[$24], cs_ext_list_price=[$25])
+ 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(2002):INTEGER])
+ HiveFilter(condition=[AND(=($6, 2002), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveJoin(condition=[=($2, $6)], joinType=[inner], algorithm=[none], cost=[not available])
+ 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=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))])
+ 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, $6)], 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_sales_price=[$23], ws_ext_wholesale_cost=[$24], 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], $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=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))])
+ 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, $6)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(ss_sold_date_sk=[$0], ss_customer_sk=[$3], ss_ext_discount_amt=[$14], ss_ext_sales_price=[$15], ss_ext_wholesale_cost=[$16], 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=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))])
+ 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, $6)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(cs_sold_date_sk=[$0], cs_bill_customer_sk=[$3], cs_ext_discount_amt=[$22], cs_ext_sales_price=[$23], cs_ext_wholesale_cost=[$24], cs_ext_list_price=[$25])
+ 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(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=[/(+(-(-($13, $12), $10), $11), CAST(2):DECIMAL(10, 0))])
+ 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, $6)], 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_sales_price=[$23], ws_ext_wholesale_cost=[$24], 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_query40.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query40.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query40.q.out
new file mode 100644
index 0000000..7d8fc9b
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query40.q.out
@@ -0,0 +1,91 @@
+PREHOOK: query: explain cbo
+select
+ w_state
+ ,i_item_id
+ ,sum(case when (cast(d_date as date) < cast ('1998-04-08' as date))
+ then cs_sales_price - coalesce(cr_refunded_cash,0) else 0 end) as sales_before
+ ,sum(case when (cast(d_date as date) >= cast ('1998-04-08' as date))
+ then cs_sales_price - coalesce(cr_refunded_cash,0) else 0 end) as sales_after
+ from
+ catalog_sales left outer join catalog_returns on
+ (cs_order_number = cr_order_number
+ and cs_item_sk = cr_item_sk)
+ ,warehouse
+ ,item
+ ,date_dim
+ where
+ i_current_price between 0.99 and 1.49
+ and i_item_sk = cs_item_sk
+ and cs_warehouse_sk = w_warehouse_sk
+ and cs_sold_date_sk = d_date_sk
+ and d_date between (cast ('1998-04-08' as date) - 30 days)
+ and (cast ('1998-04-08' as date) + 30 days)
+ group by
+ w_state,i_item_id
+ order by w_state,i_item_id
+limit 100
+PREHOOK: type: QUERY
+PREHOOK: Input: default@catalog_returns
+PREHOOK: Input: default@catalog_sales
+PREHOOK: Input: default@date_dim
+PREHOOK: Input: default@item
+PREHOOK: Input: default@warehouse
+PREHOOK: Output: hdfs://### HDFS PATH ###
+POSTHOOK: query: explain cbo
+select
+ w_state
+ ,i_item_id
+ ,sum(case when (cast(d_date as date) < cast ('1998-04-08' as date))
+ then cs_sales_price - coalesce(cr_refunded_cash,0) else 0 end) as sales_before
+ ,sum(case when (cast(d_date as date) >= cast ('1998-04-08' as date))
+ then cs_sales_price - coalesce(cr_refunded_cash,0) else 0 end) as sales_after
+ from
+ catalog_sales left outer join catalog_returns on
+ (cs_order_number = cr_order_number
+ and cs_item_sk = cr_item_sk)
+ ,warehouse
+ ,item
+ ,date_dim
+ where
+ i_current_price between 0.99 and 1.49
+ and i_item_sk = cs_item_sk
+ and cs_warehouse_sk = w_warehouse_sk
+ and cs_sold_date_sk = d_date_sk
+ and d_date between (cast ('1998-04-08' as date) - 30 days)
+ and (cast ('1998-04-08' as date) + 30 days)
+ group by
+ w_state,i_item_id
+ order by w_state,i_item_id
+limit 100
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@catalog_returns
+POSTHOOK: Input: default@catalog_sales
+POSTHOOK: Input: default@date_dim
+POSTHOOK: Input: default@item
+POSTHOOK: Input: default@warehouse
+POSTHOOK: Output: hdfs://### HDFS PATH ###
+CBO PLAN:
+HiveSortLimit(sort0=[$0], sort1=[$1], dir0=[ASC], dir1=[ASC], fetch=[100])
+ HiveProject($f0=[$0], $f1=[$1], $f2=[$2], $f3=[$3])
+ HiveAggregate(group=[{0, 1}], agg#0=[sum($2)], agg#1=[sum($3)])
+ HiveProject($f0=[$1], $f1=[$13], $f2=[CASE(<(CAST($11):DATE, 1998-04-08), -($6, CASE(IS NOT NULL($9), $9, 0)), 0)], $f3=[CASE(>=(CAST($11):DATE, 1998-04-08), -($6, CASE(IS NOT NULL($9), $9, 0)), 0)])
+ HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(w_warehouse_sk=[$0], w_state=[$10])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, warehouse]], table:alias=[warehouse])
+ HiveJoin(condition=[=($10, $2)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveJoin(condition=[=($0, $8)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveJoin(condition=[AND(=($3, $6), =($2, $5))], joinType=[left], algorithm=[none], cost=[not available])
+ HiveProject(cs_sold_date_sk=[$0], cs_warehouse_sk=[$14], cs_item_sk=[$15], cs_order_number=[$17], cs_sales_price=[$21])
+ HiveFilter(condition=[AND(IS NOT NULL($14), IS NOT NULL($15), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, catalog_sales]], table:alias=[catalog_sales])
+ HiveProject(cr_item_sk=[$2], cr_order_number=[$16], cr_refunded_cash=[$23])
+ HiveFilter(condition=[IS NOT NULL($2)])
+ HiveTableScan(table=[[default, catalog_returns]], table:alias=[catalog_returns])
+ HiveProject(d_date_sk=[$0], d_date=[$2])
+ HiveFilter(condition=[AND(BETWEEN(false, CAST($2):TIMESTAMP(9), 1998-03-09 00:00:00, 1998-05-08 00:00:00), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveProject(i_item_sk=[$0], i_item_id=[$1], i_current_price=[$5])
+ HiveFilter(condition=[AND(BETWEEN(false, $5, 0.99, 1.49), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, item]], table:alias=[item])
+
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query42.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query42.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query42.q.out
new file mode 100644
index 0000000..ddb3223
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/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=[{7, 8}], agg#0=[sum($2)])
+ HiveJoin(condition=[=($1, $6)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(ss_sold_date_sk=[$0], ss_item_sk=[$2], ss_ext_sales_price=[$15])
+ HiveFilter(condition=[AND(IS NOT NULL($0), IS NOT NULL($2))])
+ HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales])
+ HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER], d_moy=[CAST(12):INTEGER])
+ HiveFilter(condition=[AND(=($8, 12), =($6, 1998), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[dt])
+ HiveProject(i_item_sk=[$0], i_category_id=[$11], i_category=[$12], i_manager_id=[CAST(1):INTEGER])
+ HiveFilter(condition=[AND(=($20, 1), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, item]], table:alias=[item])
+
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query43.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query43.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query43.q.out
new file mode 100644
index 0000000..f6eeae3
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/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=[$8], $f1=[$7], $f2=[CASE(=($5, _UTF-16LE'Sunday'), $2, null)], $f3=[CASE(=($5, _UTF-16LE'Monday'), $2, null)], $f4=[CASE(=($5, _UTF-16LE'Tuesday'), $2, null)], $f5=[CASE(=($5, _UTF-16LE'Wednesday'), $2, null)], $f6=[CASE(=($5, _UTF-16LE'Thursday'), $2, null)], $f7=[CASE(=($5, _UTF-16LE'Friday'), $2, null)], $f8=[CASE(=($5, _UTF-16LE'Saturday'), $2, null)])
+ HiveJoin(condition=[=($6, $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], d_year=[CAST(1998):INTEGER], d_day_name=[$14])
+ HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveProject(s_store_sk=[$0], s_store_id=[$1], s_store_name=[$5], s_gmt_offset=[CAST(-6):DECIMAL(5, 2)])
+ HiveFilter(condition=[AND(=($27, -6), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, store]], table:alias=[store])
+
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query44.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query44.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query44.q.out
new file mode 100644
index 0000000..73d4213
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query44.q.out
@@ -0,0 +1,115 @@
+Warning: Shuffle Join MERGEJOIN[103][tables = [$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])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, item]], table:alias=[i1])
+ HiveProject(item_sk=[$0], rank_window_0=[$1])
+ HiveFilter(condition=[AND(<($1, 11), IS NOT NULL($0))])
+ 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, *(0.9, $2))], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject($f0=[$0], $f1=[/($1, $2)])
+ HiveAggregate(group=[{2}], agg#0=[sum($22)], agg#1=[count($22)])
+ HiveFilter(condition=[=($7, 410)])
+ HiveTableScan(table=[[default, store_sales]], table:alias=[ss1])
+ HiveProject($f1=[/($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])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, item]], table:alias=[i2])
+ HiveProject(item_sk=[$0], rank_window_0=[$1])
+ HiveFilter(condition=[AND(<($1, 11), IS NOT NULL($0))])
+ 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, *(0.9, $2))], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject($f0=[$0], $f1=[/($1, $2)])
+ HiveAggregate(group=[{2}], agg#0=[sum($22)], agg#1=[count($22)])
+ HiveFilter(condition=[=($7, 410)])
+ HiveTableScan(table=[[default, store_sales]], table:alias=[ss1])
+ HiveProject($f1=[/($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($5))])
+ HiveTableScan(table=[[default, store_sales]], table:alias=[store_sales])
+
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query45.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query45.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query45.q.out
new file mode 100644
index 0000000..986dae9
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query45.q.out
@@ -0,0 +1,89 @@
+Warning: Shuffle Join MERGEJOIN[133][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Reducer 4' is a cross product
+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'), CASE(=($14, 0), false, IS NOT NULL($17), true, IS NULL($13), null, <($15, $14), null, false))])
+ 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], c=[$16], ck=[$17], i_item_id0=[$7], i1142=[$8])
+ HiveJoin(condition=[true], joinType=[inner], algorithm=[none], cost=[not available])
+ 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=[AND(IS NOT NULL($0), IS NOT NULL($4))])
+ HiveTableScan(table=[[default, customer]], table:alias=[customer])
+ HiveProject(ca_address_sk=[$0], ca_county=[$7], ca_zip=[$9])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address])
+ HiveProject(i_item_sk=[$0], i_item_id=[$1], i_item_id0=[$2], i1142=[$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])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, item]], table:alias=[item])
+ HiveProject(i_item_id=[$0], i1142=[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), IS NOT NULL($3))])
+ 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), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveProject(c=[$0], ck=[$1])
+ HiveAggregate(group=[{}], c=[COUNT()], ck=[COUNT($1)])
+ HiveFilter(condition=[IN($0, 2, 3, 5, 7, 11, 13, 17, 19, 23, 29)])
+ HiveTableScan(table=[[default, item]], table:alias=[item])
+
http://git-wip-us.apache.org/repos/asf/hive/blob/b8299551/ql/src/test/results/clientpositive/perf/tez/cbo_query46.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query46.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query46.q.out
new file mode 100644
index 0000000..0728056
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query46.q.out
@@ -0,0 +1,115 @@
+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=[AND(IS NOT NULL($0), IS NOT NULL($4))])
+ HiveTableScan(table=[[default, customer]], table:alias=[customer])
+ HiveProject(ca_address_sk=[$0], ca_city=[$6])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ 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])
+ HiveFilter(condition=[IS NOT NULL($0)])
+ HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address])
+ HiveJoin(condition=[=($2, $13)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveJoin(condition=[=($4, $11)], 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], d_year=[$6], d_dow=[$7])
+ HiveFilter(condition=[AND(IN($7, 6, 0), IN($6, 1998, 1999, 2000), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveProject(s_store_sk=[$0], s_city=[$22])
+ HiveFilter(condition=[AND(IN($22, _UTF-16LE'Cedar Grove', _UTF-16LE'Wildwood', _UTF-16LE'Union', _UTF-16LE'Salem', _UTF-16LE'Highland Park'), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, store]], table:alias=[store])
+ HiveProject(hd_demo_sk=[$0], hd_dep_count=[$3], hd_vehicle_count=[$4])
+ HiveFilter(condition=[AND(OR(=($3, 2), =($4, 1)), IS NOT NULL($0))])
+ 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/cbo_query47.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query47.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query47.q.out
new file mode 100644
index 0000000..11fd577
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/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, 1)))], 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], rank_window_1=[$5])
+ 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($0), 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($2), 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))), IS NOT NULL($0))])
+ 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($0), 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, 1)))], 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], rank_window_1=[$5])
+ 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($0), 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($2), 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))), IS NOT NULL($0))])
+ 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($0), 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($0), 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($2), 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))), IS NOT NULL($0))])
+ 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($0), 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/cbo_query48.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/perf/tez/cbo_query48.q.out b/ql/src/test/results/clientpositive/perf/tez/cbo_query48.q.out
new file mode 100644
index 0000000..feb4012
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tez/cbo_query48.q.out
@@ -0,0 +1,164 @@
+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($13)])
+ HiveJoin(condition=[AND(=($11, $0), OR(AND(IN($1, _UTF-16LE'KY', _UTF-16LE'GA', _UTF-16LE'NM'), BETWEEN(false, $15, 0, 2000)), AND(IN($1, _UTF-16LE'MT', _UTF-16LE'OR', _UTF-16LE'IN'), BETWEEN(false, $15, 150, 3000)), AND(IN($1, _UTF-16LE'WI', _UTF-16LE'MO', _UTF-16LE'WV'), BETWEEN(false, $15, 50, 25000))))], 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=[=($0, $7)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(cd_demo_sk=[$0], cd_marital_status=[CAST(_UTF-16LE'M'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"], cd_education_status=[CAST(_UTF-16LE'4 yr Degree'):VARCHAR(2147483647) CHARACTER SET "UTF-16LE" COLLATE "ISO-8859-1$en_US$primary"])
+ HiveFilter(condition=[AND(=($2, _UTF-16LE'M'), =($3, _UTF-16LE'4 yr Degree'), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, customer_demographics]], table:alias=[customer_demographics])
+ HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(d_date_sk=[$0], d_year=[CAST(1998):INTEGER])
+ HiveFilter(condition=[AND(=($6, 1998), IS NOT NULL($0))])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveJoin(condition=[=($0, $4)], 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_addr_sk=[$6], ss_store_sk=[$7], ss_quantity=[$10], ss_sales_price=[$13], 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, 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])
+