You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by kr...@apache.org on 2024/07/30 04:36:11 UTC
(hive) branch master updated: HIVE-23964: SemanticException in query 30 while generating logical plan (Krisztian Kasa, reviewed by Stamatis Zampetakis)
This is an automated email from the ASF dual-hosted git repository.
krisztiankasa pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/hive.git
The following commit(s) were added to refs/heads/master by this push:
new 929305f077f HIVE-23964: SemanticException in query 30 while generating logical plan (Krisztian Kasa, reviewed by Stamatis Zampetakis)
929305f077f is described below
commit 929305f077f5e40311939ce7256adb3b35d985b0
Author: Krisztian Kasa <kk...@cloudera.com>
AuthorDate: Tue Jul 30 06:36:04 2024 +0200
HIVE-23964: SemanticException in query 30 while generating logical plan (Krisztian Kasa, reviewed by Stamatis Zampetakis)
---
.../test/queries/clientpositive/perf/cbo_query30.q | 5 +-
ql/src/test/queries/clientpositive/perf/query30.q | 5 +-
.../perf/tpcds30tb/tez/cbo_query30.q.out | 44 +++
.../perf/tpcds30tb/tez/query30.q.out | 421 +++++++++++++++++++++
4 files changed, 469 insertions(+), 6 deletions(-)
diff --git a/ql/src/test/queries/clientpositive/perf/cbo_query30.q b/ql/src/test/queries/clientpositive/perf/cbo_query30.q
index dbcae2dbd52..bfb56294eb0 100644
--- a/ql/src/test/queries/clientpositive/perf/cbo_query30.q
+++ b/ql/src/test/queries/clientpositive/perf/cbo_query30.q
@@ -1,4 +1,3 @@
---! qt:disabled:HIVE-23964
set hive.mapred.mode=nonstrict;
-- start query 1 in stream 0 using template query30.tpl and seed 1819994127
explain cbo
@@ -16,7 +15,7 @@ with customer_total_return as
,ca_state)
select c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
- ,c_last_review_date,ctr_total_return
+ ,c_last_review_date_sk,ctr_total_return
from customer_total_return ctr1
,customer_address
,customer
@@ -28,7 +27,7 @@ with customer_total_return as
and ctr1.ctr_customer_sk = c_customer_sk
order by c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
- ,c_last_review_date,ctr_total_return
+ ,c_last_review_date_sk,ctr_total_return
limit 100;
-- end query 1 in stream 0 using template query30.tpl
diff --git a/ql/src/test/queries/clientpositive/perf/query30.q b/ql/src/test/queries/clientpositive/perf/query30.q
index b3073d26cb6..0ee1fe9823a 100644
--- a/ql/src/test/queries/clientpositive/perf/query30.q
+++ b/ql/src/test/queries/clientpositive/perf/query30.q
@@ -1,4 +1,3 @@
---! qt:disabled:HIVE-23964
set hive.mapred.mode=nonstrict;
-- start query 1 in stream 0 using template query30.tpl and seed 1819994127
explain
@@ -16,7 +15,7 @@ with customer_total_return as
,ca_state)
select c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
- ,c_last_review_date,ctr_total_return
+ ,c_last_review_date_sk,ctr_total_return
from customer_total_return ctr1
,customer_address
,customer
@@ -28,7 +27,7 @@ with customer_total_return as
and ctr1.ctr_customer_sk = c_customer_sk
order by c_customer_id,c_salutation,c_first_name,c_last_name,c_preferred_cust_flag
,c_birth_day,c_birth_month,c_birth_year,c_birth_country,c_login,c_email_address
- ,c_last_review_date,ctr_total_return
+ ,c_last_review_date_sk,ctr_total_return
limit 100;
-- end query 1 in stream 0 using template query30.tpl
diff --git a/ql/src/test/results/clientpositive/perf/tpcds30tb/tez/cbo_query30.q.out b/ql/src/test/results/clientpositive/perf/tpcds30tb/tez/cbo_query30.q.out
new file mode 100644
index 00000000000..5e5de8b19ec
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tpcds30tb/tez/cbo_query30.q.out
@@ -0,0 +1,44 @@
+CBO PLAN:
+HiveSortLimit(sort0=[$0], sort1=[$1], sort2=[$2], sort3=[$3], sort4=[$4], sort5=[$5], sort6=[$6], sort7=[$7], sort8=[$8], sort9=[$9], sort10=[$10], sort11=[$11], sort12=[$12], dir0=[ASC], dir1=[ASC], dir2=[ASC], dir3=[ASC], dir4=[ASC], dir5=[ASC], dir6=[ASC], dir7=[ASC], dir8=[ASC], dir9=[ASC], dir10=[ASC], dir11=[ASC], dir12=[ASC], fetch=[100])
+ HiveProject(c_customer_id=[$1], c_salutation=[$3], c_first_name=[$4], c_last_name=[$5], c_preferred_cust_flag=[$6], c_birth_day=[$7], c_birth_month=[$8], c_birth_year=[$9], c_birth_country=[$10], c_login=[$11], c_email_address=[$12], c_last_review_date_sk=[$13], ctr_total_return=[$17])
+ HiveJoin(condition=[AND(=($16, $19), >($17, $18))], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveJoin(condition=[=($15, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveJoin(condition=[=($14, $2)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(c_customer_sk=[$0], c_customer_id=[$1], c_current_addr_sk=[$4], c_salutation=[$7], c_first_name=[$8], c_last_name=[$9], c_preferred_cust_flag=[$10], c_birth_day=[$11], c_birth_month=[$12], c_birth_year=[$13], c_birth_country=[$14], c_login=[$15], c_email_address=[$16], c_last_review_date_sk=[$17])
+ HiveFilter(condition=[IS NOT NULL($4)])
+ HiveTableScan(table=[[default, customer]], table:alias=[customer])
+ HiveProject(ca_address_sk=[$0])
+ HiveFilter(condition=[=($8, _UTF-16LE'IL')])
+ HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address])
+ HiveProject(wr_returning_customer_sk=[$0], ca_state=[$1], $f2=[$2])
+ HiveFilter(condition=[IS NOT NULL($2)])
+ HiveProject(wr_returning_customer_sk=[$1], ca_state=[$0], $f2=[$2])
+ HiveAggregate(group=[{1, 2}], agg#0=[sum($4)])
+ HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(ca_address_sk=[$0], ca_state=[$8])
+ HiveFilter(condition=[IS NOT NULL($8)])
+ HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address])
+ HiveJoin(condition=[=($3, $4)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(wr_returning_customer_sk=[$6], wr_returning_addr_sk=[$9], wr_return_amt=[$14], wr_returned_date_sk=[$23])
+ HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($6), IS NOT NULL($23))])
+ HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns])
+ HiveProject(d_date_sk=[$0])
+ HiveFilter(condition=[=($6, 2002)])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+ HiveProject(_o__c0=[*(CAST(/($1, $2)):DECIMAL(21, 6), 1.2:DECIMAL(2, 1))], ctr_state=[$0])
+ HiveFilter(condition=[IS NOT NULL(CAST(/($1, $2)):DECIMAL(21, 6))])
+ HiveAggregate(group=[{0}], agg#0=[sum($2)], agg#1=[count($2)])
+ HiveProject(ca_state=[$0], wr_returning_customer_sk=[$1], $f2=[$2])
+ HiveAggregate(group=[{1, 2}], agg#0=[sum($4)])
+ HiveJoin(condition=[=($3, $0)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(ca_address_sk=[$0], ca_state=[$8])
+ HiveFilter(condition=[IS NOT NULL($8)])
+ HiveTableScan(table=[[default, customer_address]], table:alias=[customer_address])
+ HiveJoin(condition=[=($3, $4)], joinType=[inner], algorithm=[none], cost=[not available])
+ HiveProject(wr_returning_customer_sk=[$6], wr_returning_addr_sk=[$9], wr_return_amt=[$14], wr_returned_date_sk=[$23])
+ HiveFilter(condition=[AND(IS NOT NULL($9), IS NOT NULL($23))])
+ HiveTableScan(table=[[default, web_returns]], table:alias=[web_returns])
+ HiveProject(d_date_sk=[$0])
+ HiveFilter(condition=[=($6, 2002)])
+ HiveTableScan(table=[[default, date_dim]], table:alias=[date_dim])
+
diff --git a/ql/src/test/results/clientpositive/perf/tpcds30tb/tez/query30.q.out b/ql/src/test/results/clientpositive/perf/tpcds30tb/tez/query30.q.out
new file mode 100644
index 00000000000..39636685cd6
--- /dev/null
+++ b/ql/src/test/results/clientpositive/perf/tpcds30tb/tez/query30.q.out
@@ -0,0 +1,421 @@
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+ Stage: Stage-1
+ Tez
+#### A masked pattern was here ####
+ Edges:
+ Map 1 <- Map 3 (BROADCAST_EDGE)
+ Map 5 <- Map 10 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Reducer 11 (BROADCAST_EDGE), Reducer 2 (BROADCAST_EDGE), Reducer 4 (BROADCAST_EDGE)
+ Reducer 11 <- Map 10 (SIMPLE_EDGE)
+ Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
+ Reducer 4 <- Map 3 (SIMPLE_EDGE)
+ Reducer 6 <- Map 5 (SIMPLE_EDGE)
+ Reducer 7 <- Reducer 6 (SIMPLE_EDGE)
+ Reducer 8 <- Map 1 (BROADCAST_EDGE), Map 5 (SIMPLE_EDGE), Reducer 7 (BROADCAST_EDGE)
+ Reducer 9 <- Reducer 8 (SIMPLE_EDGE)
+#### A masked pattern was here ####
+ Vertices:
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: customer
+ filterExpr: c_current_addr_sk is not null (type: boolean)
+ probeDecodeDetails: cacheKey:HASH_MAP_MAPJOIN_159_container, bigKeyColName:c_current_addr_sk, smallTablePos:1, keyRatio:0.0185202875
+ Statistics: Num rows: 80000000 Data size: 61944003308 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: c_current_addr_sk is not null (type: boolean)
+ Statistics: Num rows: 80000000 Data size: 61944003308 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: c_customer_sk (type: bigint), c_customer_id (type: char(16)), c_current_addr_sk (type: bigint), c_salutation (type: char(10)), c_first_name (type: char(20)), c_last_name (type: char(30)), c_preferred_cust_flag (type: char(1)), c_birth_day (type: int), c_birth_month (type: int), c_birth_year (type: int), c_birth_country (type: varchar(20)), c_login (type: char(13)), c_email_address (type: char(50)), c_last_review_date_sk (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
+ Statistics: Num rows: 80000000 Data size: 61944003308 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col2 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 1509434 Data size: 1127547218 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 1509434 Data size: 1127547218 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: char(16)), _col3 (type: char(10)), _col4 (type: char(20)), _col5 (type: char(30)), _col6 (type: char(1)), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col10 (type: varchar(20)), _col11 (type: char(13)), _col12 (type: char(50)), _col13 (type: bigint)
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 1509434 Data size: 12075472 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=1481623)
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: binary)
+ Execution mode: vectorized, llap
+ LLAP IO: may be used (ACID table)
+ Map 10
+ Map Operator Tree:
+ TableScan
+ alias: date_dim
+ filterExpr: (d_year = 2002) (type: boolean)
+ Statistics: Num rows: 73049 Data size: 876588 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (d_year = 2002) (type: boolean)
+ Statistics: Num rows: 367 Data size: 4404 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: d_date_sk (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: bigint)
+ minReductionHashAggr: 0.4
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Dynamic Partitioning Event Operator
+ Target column: wr_returned_date_sk (bigint)
+ Target Input: web_returns
+ Partition key expr: wr_returned_date_sk
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Target Vertex: Map 5
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ keys: _col0 (type: bigint)
+ minReductionHashAggr: 0.4
+ mode: hash
+ outputColumnNames: _col0
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Dynamic Partitioning Event Operator
+ Target column: wr_returned_date_sk (bigint)
+ Target Input: web_returns
+ Partition key expr: wr_returned_date_sk
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Target Vertex: Map 5
+ Execution mode: vectorized, llap
+ LLAP IO: may be used (ACID table)
+ Map 3
+ Map Operator Tree:
+ TableScan
+ alias: customer_address
+ filterExpr: (ca_state is not null or (ca_state = 'IL')) (type: boolean)
+ Statistics: Num rows: 40000000 Data size: 3760000000 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: ca_state is not null (type: boolean)
+ Statistics: Num rows: 40000000 Data size: 3760000000 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: ca_address_sk (type: bigint), ca_state (type: char(2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 40000000 Data size: 3760000000 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 40000000 Data size: 3760000000 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: char(2))
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 40000000 Data size: 3760000000 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: char(2))
+ Filter Operator
+ predicate: (ca_state = 'IL') (type: boolean)
+ Statistics: Num rows: 754717 Data size: 70943398 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: ca_address_sk (type: bigint)
+ outputColumnNames: _col0
+ Statistics: Num rows: 754717 Data size: 6037736 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 754717 Data size: 6037736 Basic stats: COMPLETE Column stats: COMPLETE
+ Execution mode: vectorized, llap
+ LLAP IO: may be used (ACID table)
+ Map 5
+ Map Operator Tree:
+ TableScan
+ alias: web_returns
+ filterExpr: ((wr_returning_addr_sk is not null or (wr_returning_addr_sk is not null and wr_returning_customer_sk is not null)) and wr_returning_customer_sk BETWEEN DynamicValue(RS_57_customer_c_customer_sk_min) AND DynamicValue(RS_57_customer_c_customer_sk_max) and in_bloom_filter(wr_returning_customer_sk, DynamicValue(RS_57_customer_c_customer_sk_bloom_filter))) (type: boolean)
+ Statistics: Num rows: 2062802370 Data size: 274320709664 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: wr_returning_addr_sk is not null (type: boolean)
+ Statistics: Num rows: 2014201109 Data size: 267857496080 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: wr_returning_customer_sk (type: bigint), wr_returning_addr_sk (type: bigint), wr_return_amt (type: decimal(7,2)), wr_returned_date_sk (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 2014201109 Data size: 267857496080 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ input vertices:
+ 1 Map 10
+ Statistics: Num rows: 338617340 Data size: 37269164776 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col2, _col6
+ input vertices:
+ 1 Map 3
+ Statistics: Num rows: 338617340 Data size: 64060966704 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2)
+ keys: _col6 (type: char(2)), _col0 (type: bigint)
+ minReductionHashAggr: 0.71617645
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 338617340 Data size: 69375636960 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: char(2)), _col1 (type: bigint)
+ null sort order: zz
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: char(2)), _col1 (type: bigint)
+ Statistics: Num rows: 338617340 Data size: 69375636960 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: decimal(17,2))
+ Filter Operator
+ predicate: (wr_returning_addr_sk is not null and wr_returning_customer_sk is not null and wr_returning_customer_sk BETWEEN DynamicValue(RS_57_customer_c_customer_sk_min) AND DynamicValue(RS_57_customer_c_customer_sk_max) and in_bloom_filter(wr_returning_customer_sk, DynamicValue(RS_57_customer_c_customer_sk_bloom_filter))) (type: boolean)
+ Statistics: Num rows: 1966759223 Data size: 261548461240 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: wr_returning_customer_sk (type: bigint), wr_returning_addr_sk (type: bigint), wr_return_amt (type: decimal(7,2)), wr_returned_date_sk (type: bigint)
+ outputColumnNames: _col0, _col1, _col2, _col3
+ Statistics: Num rows: 1966759223 Data size: 261548461240 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col3 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col1, _col2
+ input vertices:
+ 1 Reducer 11
+ Statistics: Num rows: 330641649 Data size: 36391337984 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col0, _col2, _col6
+ input vertices:
+ 1 Reducer 4
+ Statistics: Num rows: 330641649 Data size: 62552093862 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2)
+ keys: _col0 (type: bigint), _col6 (type: char(2))
+ minReductionHashAggr: 0.7093301
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 330641649 Data size: 67741584070 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint), _col1 (type: char(2))
+ null sort order: zz
+ sort order: ++
+ Map-reduce partition columns: _col0 (type: bigint), _col1 (type: char(2))
+ Statistics: Num rows: 330641649 Data size: 67741584070 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col2 (type: decimal(17,2))
+ Execution mode: vectorized, llap
+ LLAP IO: may be used (ACID table)
+ Reducer 11
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: bigint)
+ outputColumnNames: _col0
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 367 Data size: 2936 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 2
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, 1, expectedEntries=1481623)
+ mode: final
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ null sort order:
+ sort order:
+ Statistics: Num rows: 1 Data size: 160 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: binary)
+ Reducer 4
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: bigint), VALUE._col0 (type: char(2))
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions: _col0 (type: bigint)
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: bigint)
+ Statistics: Num rows: 40000000 Data size: 3760000000 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: char(2))
+ Reducer 6
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: char(2)), KEY._col1 (type: bigint)
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 338617340 Data size: 69375636960 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: _col0 (type: char(2)), _col2 (type: decimal(17,2))
+ outputColumnNames: _col0, _col2
+ Statistics: Num rows: 338617340 Data size: 69375636960 Basic stats: COMPLETE Column stats: COMPLETE
+ Group By Operator
+ aggregations: sum(_col2), count(_col2)
+ keys: _col0 (type: char(2))
+ minReductionHashAggr: 0.99
+ mode: hash
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 14363 Data size: 2958778 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: char(2))
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col0 (type: char(2))
+ Statistics: Num rows: 14363 Data size: 2958778 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col1 (type: decimal(27,2)), _col2 (type: bigint)
+ Reducer 7
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0), count(VALUE._col1)
+ keys: KEY._col0 (type: char(2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 53 Data size: 10918 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: CAST( (_col1 / _col2) AS decimal(21,6)) is not null (type: boolean)
+ Statistics: Num rows: 53 Data size: 10918 Basic stats: COMPLETE Column stats: COMPLETE
+ Select Operator
+ expressions: (CAST( (_col1 / _col2) AS decimal(21,6)) * 1.2) (type: decimal(24,7)), _col0 (type: char(2))
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 53 Data size: 10494 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col1 (type: char(2))
+ null sort order: z
+ sort order: +
+ Map-reduce partition columns: _col1 (type: char(2))
+ Statistics: Num rows: 53 Data size: 10494 Basic stats: COMPLETE Column stats: COMPLETE
+ value expressions: _col0 (type: decimal(24,7))
+ Reducer 8
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations: sum(VALUE._col0)
+ keys: KEY._col0 (type: bigint), KEY._col1 (type: char(2))
+ mode: mergepartial
+ outputColumnNames: _col0, _col1, _col2
+ Statistics: Num rows: 330641649 Data size: 67741584070 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: _col2 is not null (type: boolean)
+ Statistics: Num rows: 330641649 Data size: 67741584070 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: bigint)
+ 1 _col0 (type: bigint)
+ outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col16, _col17
+ input vertices:
+ 0 Map 1
+ Statistics: Num rows: 330641649 Data size: 316393869433 Basic stats: COMPLETE Column stats: COMPLETE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col16 (type: char(2))
+ 1 _col1 (type: char(2))
+ outputColumnNames: _col1, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col17, _col18
+ input vertices:
+ 1 Reducer 7
+ Statistics: Num rows: 330641649 Data size: 324990552307 Basic stats: COMPLETE Column stats: COMPLETE
+ Filter Operator
+ predicate: (_col17 > _col18) (type: boolean)
+ Statistics: Num rows: 110213883 Data size: 108330184109 Basic stats: COMPLETE Column stats: COMPLETE
+ Top N Key Operator
+ sort order: +++++++++++++
+ keys: _col1 (type: char(16)), _col3 (type: char(10)), _col4 (type: char(20)), _col5 (type: char(30)), _col6 (type: char(1)), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col10 (type: varchar(20)), _col11 (type: char(13)), _col12 (type: char(50)), _col13 (type: bigint), _col17 (type: decimal(17,2))
+ null sort order: zzzzzzzzzzzzz
+ Statistics: Num rows: 110213883 Data size: 108330184109 Basic stats: COMPLETE Column stats: COMPLETE
+ top n: 100
+ Select Operator
+ expressions: _col1 (type: char(16)), _col3 (type: char(10)), _col4 (type: char(20)), _col5 (type: char(30)), _col6 (type: char(1)), _col7 (type: int), _col8 (type: int), _col9 (type: int), _col10 (type: varchar(20)), _col11 (type: char(13)), _col12 (type: char(50)), _col13 (type: bigint), _col17 (type: decimal(17,2))
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
+ Statistics: Num rows: 110213883 Data size: 95976166313 Basic stats: COMPLETE Column stats: COMPLETE
+ Reduce Output Operator
+ key expressions: _col0 (type: char(16)), _col1 (type: char(10)), _col2 (type: char(20)), _col3 (type: char(30)), _col4 (type: char(1)), _col5 (type: int), _col6 (type: int), _col7 (type: int), _col8 (type: varchar(20)), _col9 (type: char(13)), _col10 (type: char(50)), _col11 (type: bigint), _col12 (type: decimal(17,2))
+ null sort order: zzzzzzzzzzzzz
+ sort order: +++++++++++++
+ Statistics: Num rows: 110213883 Data size: 95976166313 Basic stats: COMPLETE Column stats: COMPLETE
+ Reducer 9
+ Execution mode: vectorized, llap
+ Reduce Operator Tree:
+ Select Operator
+ expressions: KEY.reducesinkkey0 (type: char(16)), KEY.reducesinkkey1 (type: char(10)), KEY.reducesinkkey2 (type: char(20)), KEY.reducesinkkey3 (type: char(30)), KEY.reducesinkkey4 (type: char(1)), KEY.reducesinkkey5 (type: int), KEY.reducesinkkey6 (type: int), KEY.reducesinkkey7 (type: int), KEY.reducesinkkey8 (type: varchar(20)), KEY.reducesinkkey9 (type: char(13)), KEY.reducesinkkey10 (type: char(50)), KEY.reducesinkkey11 (type: bigint), KEY.reducesinkkey12 (type: decim [...]
+ outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12
+ Statistics: Num rows: 110213883 Data size: 95976166313 Basic stats: COMPLETE Column stats: COMPLETE
+ Limit
+ Number of rows: 100
+ Statistics: Num rows: 100 Data size: 87100 Basic stats: COMPLETE Column stats: COMPLETE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 100 Data size: 87100 Basic stats: COMPLETE Column stats: COMPLETE
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: 100
+ Processor Tree:
+ ListSink
+